The Breaking Of Bones And Dreams In The Book Of Mice And Men

The deep green pigment in the Salinas Valley River stained the future of Lennie Small and the image of the events that happened there left memories of the colorful scenery in black and white. The breaking of Curley’s bones prompted Lennie’s dreams to reside among the river. Of Mice and Men is a novel by John Steinbeck encompassing the characters Lennie and Curley. Steinbeck was a Nobel Prize winning American writer. He is known for his realistic and elaborate writing style. Growing up in Salinas California with a family farm still standing, Steinbeck took aspects of his early life and it was portrayed as a setting for his novel in 1937. The storyline seems to have an underlying message that is hardly noticed without evaluation. The conflict in the novel begins with George Milton, Lennie’s traveling partner, helping Lennie get work on a ranch. His previously reckless behavior was being contained until Curley, the boss’s son, felt threatened by Lennie and defensively pushed him around. Feeling intimidated, Lennie acted irrationally and broke Curley’s hand. With Lennie’s clear urge for the American dream, he acknowledged his actions. Although, his boundary between right and wrong was once again blurred from that point forward. George then took matters into his own hands. He used euthanasia to conclude Lennie’s frequent and worsening mistakes. Due to this, readers can observe that the breaking of Curley’s hand essentially led to the breaking of Lennie’s dreams.

Curley aspired to be a figure of authority at the ranch. He used violence as a defense mechanism to combat his insecurities. In “Insecure Men May Be More Prone to Violence”, it shows that men who are more consumed by feeling masculine tend to be more violent. It seemed like Curley did not feel like he met the requirements that he saw other men on the ranch embody. In Candy’s words, “He’s alla time picking scraps with big guys. Kind of like he’s mad at ‘em because he ain’t a big guy” (Steinbeck 26). This shows that Curley has a history of this behavior. He tends to pick fights with people bigger than him. This gave George an uneasy feeling that a problem may come of it. Slim later explains “Looks to me like ever’ bone in his han’ is bust” (Steinbeck 64). This quote is referring to the fight between Curley and Lennie. Candy had made a disgusted remark about Curley’s glove full of vaseline and Curley mistakenly thought Lennie had laughed at it. This threw Curley into a fit of rage. Lennie ended up breaking Curley’s hand. Lennie felt remorse in saying that he did not mean to hurt him. This all alludes to the fact that Curley encouraged Lennie’s bad behavior while picking a fight with him.

Consequently, these factors contributed to Lennie’s altered behavior. This behavior was displayed in many situations. For example, “I was jus’ playin with him . . . . an’ he made like he’s gonna bite me . . . . an’ I made like I was gonna smack him . . . . an’. . . . an’ I done it” (Steinbeck 87). This shows the next chronological mistake that occured. Lennie had accidentally killed his puppy by hitting it. Lennie had not meant any harm to the puppy, but he had developed the tendency to unintentionally kill the animals that were in his care. His tendencies only worsened in sequence. To further validate this, Lennie remarks “I don’t want to hurt you, but George’ll be mad if you yell” (Steinbeck 91). This is a quote from Lennie right after he had broken Curley’s wife’s neck, which led to her death. Lennie wanted to keep his job of tending the rabbits in the future, so he clearly did not intend to do something that could possibly threaten his dream. This pattern supports the idea that Lennie was not in complete control of his actions which resulted in an undesirable series of events.

Subsequently, George recognized this pattern. He had taken inspiration from Candy’s comment “Ain’t nothing left for him. Can’t eat, can’t see, can’t even walk without hurtin’” (Steinbeck 47). This citation is found within the discussion of euthanasia. Candy’s dog was old and had been suffering for a long time. The men at the ranch agreed that euthanasia was just. George used this to justify the repetition of this strategy. In “Human and Animal Euthanasia: Dare to Compare?” the article explains the difference between human and animal euthanasia. It expresses the ethical compassion used for animals and essentially suggests that people should have the same compassion for loved ones. George later stated “Ever’body gonna be nice to you. Ain’t gonna be no more trouble” (Steinbeck 106). This occurred before one single bullet euthanized Lennie. George previously asked Lennie to look at the Salinas Valley River and picture their dream coming true. George was standing behind him, Carlson’s luger in his shaky hand. He wanted to give Lennie a good memory as his last, which is why he disclosed where Lennie had been hiding. This, in turn, was the breaking of Lennie’s dreams by euthanasia.

To conclude, Curley’s incentive to trigger Lennie’s bad behavior influenced said behavior to prevail. This, overall, was the reason why Lennie’s innocent mistakes became increasingly more severe. When the severity became too dangerous, George explored the idea of euthanizing Lennie. Having seen it done, he decided that much like Candy’s suffering dog, he would put Lennie out of his misery. Societally, this situation can be represented by dreams of an unattainable life standard. After planning to live the American dream with George by his side, Lennie’s dreams became unfulfilled whispers that lay near the edge of the unfathomable green pool. Collectively, it is shown that the breaking of Curley’s hand essentially led to the breaking of Lennie’s dreams.

Works Cited

  1. Goldbaum, Elizabeth. “Insecure Men May Be More Prone to Violence.” LiveScience, Purch, 26 Aug. 2015, www.livescience.com/51979-masculinity-gender-norms-violence.html.
  2. Steinbeck, John. Of Mice and Men. Penguin, 1986.
  3. Pierce, Jessica. “Human and Animal Euthanasia: Dare to Compare?” Psychology Today, Sussex Publishers, 29 Nov. 2011, www.psychologytoday.com/us/blog/all-dogs-go-heaven/201111/human-and-animal-euthanasia-dare-compare.

Human Bone Cell Types

As we know that the human skeleton is mainly composed of bone tissues which provides support for the body, and gives protection to the vital organs such as those in the cranial and thoracic cavities, and encloses medullary cavity containing bone marrow ,as well as bone tissues, also serve as reservoir of phosphate, calcium, and other ions. Bone tissues also provide mechanical and metabolic function to skeleton. Bone is a specialized connective tissue which comprises bone matrix, calcified extracellular material, and three major cell types (osteocytes, osteoblasts and osteoclasts). All bones on their external and internal surface are lined by the layer of connective tissues, (internal surface is surrounded by the endosteum and external surface is surrounded by the periosteum). Now I will write about the types of bone cell.

Osteoblast

It is a types of bone cell which helps to secrete the substance of bone like bone matrix, including type 1 collagen fibers, proteoglycans, and matricellular glycoproteins. Active osteoblast is located entirely at the surface of bone matrix, and wrapped by integrins by forming a single layer of cuboidal cells which is joined by the adherent and gap junction. After the completion of their synthetic activity some osteoblasts differentiate as osteocytes and captured in matrix-bound lacunae while some flatten and cover the matrix surface as bone lining cells. Osteoblast are large cell which is responsible for the synthesis and mineralization of bone during the initial bone formation and later bone remodelling, it also forms a closely packed sheet on the surface of the bone, from which cellular processes expand through the developing bone.

Osteocytes

As I have mentioned that some osteoblasts differentiate into osteocytes and enclosed in the lacunae. During the change from osteoblast to osteocytes, the cell continues many long dendritic processes which is surrounded by calcifying matrix, and come to occupy the many canaliculi. The almond shaped osteocytes are most abundant cells in bone exhibit crucially less Rough endoplasmic reticulum, smaller Golgi complexes, and more condensed nuclear chromatin than osteoblasts. Diffusion of metabolites between osteocytes and blood vessels which takes place through the small amount of interstitial fluid in the canaliculi. The communication of osteocytes takes place via osteoblast and bone lining. Osteocyte maintain the calcified matrix and their death is followed by matrix reabsorption. Osteocyte express many proteins with paracrine and endocrine effect in order to regulate bone remodeling.

Osteoclast

hey are very large, motile cells with multiple nuclei, and they are responsible for matrix reabsorption during bone growth and remodeling. The development of osteoclast requires two polypeptide which is produced by osteoblast: macrophage-colony–stimulating factor (M-CSF), and the receptor activator of nuclear factor-κB ligand (RANKL). In the active osteoclast the membrane domain contacts the bone to forms a circular sealing zone in order to binds the cell tightly to the bone matrix and surrounds an area with many surface projections, called the ruffled border at this process a specialized microenvironment is created between osteoclast and matrix where bone reabsorption takes place. Osteoclast pumps protons to acidify and promote dissolution of the adjoining hydroxyapatite, and releases matrix metalloproteinases and other hydrolytic enzymes from lysosome-associated secretory vesicles for the localized digestion of matrix proteins.

Critical Review of Bone Age Assessment Methods

Globally, age has become the benchmark for many social events such as alcohol consumption, marriage and employment. And with it, entails legal responsibilities and ramifications. With the rise in illegal immigrants from war-torn and impoverished nations into developing countries, an individual’s age becomes one of the most important factors in determining their subsequent treatment. An illegal immigrant coming into the country is without birth records, as a result of poorly maintained birth records or undocumented births from their country of origin (Mohammed, et al., 2015). As such, skeletal age is used instead to determine the chronological age, more specifically the biological maturity, of the individual.

The assessment of skeletal age is generally achieved by assessing the radiographs of hands and wrists because they contain many bones – 8 carpals, 5 metacarpals and 14 phalanges. It is the individual growth and degree of maturation of ossification centres in each bone, appearing at particular ages, that serves as the basis for skeletal age (De Sanctis, et al., 2014). Due to the dominance of right-handed individuals, the risk of injury to the right hand and wrist are increased. Therefore, the left hand and wrist are typically radiographed and assessed (Satoh, 2015). The Greulich-Pyle and Tanner-Whitehouse methods are commonly utilised for skeletal age assessment, internationally. However, these methods are not without their respective shortcomings. Hence, the development of other methods such as ultrasonography, MRI and automated computerised assessments, in recent years (Satoh, 2015).

This literature review will be evaluating each method.

Greulich-Pyle Method

Greulich-Pyle (GP) method is considered to be the standard when it comes to the estimation of age in modern children and adolescents around the world, due to its simpleness. Radiographs of the left hand and wrist are taken and compared to standardised radiographs within the GP atlas, to estimate an individual’s chronological age. The atlas is a chronological compilation of anthropometric data and radiographs of 1000 healthy Ohio children progressing through childhood. The longitudinal study collected data at intervals of 3 to 12 months, between 1931 and 1942. However, it was the 1959 edition that was separated into two series: one following female development and the other following male development (Tsehay, Afework, & Mesifin, 2017).

In spite of the commonality of utilising GP assessments, there has been a lot of controversy over the accuracy and reliability of its predictions due to methodology, mainly because it compares radiographs of other ethnic population samples to the reference population. In one study for medicolegal purposes, the chronological age of 4.5 to 9.4-year-old Pakistani children was found to be significantly underestimated, with the average difference between the skeletal and chronological ages for males and females being 15.78 and 6.65 months, respectively. The study contained 139 males and 81 females from Pakistan, all of which had their skeletal ages calculated according to the GP atlas and compared to their respective chronological ages (Mughal, Hassan, & Ahmed, 2014). Compared to the former study, the GP method also accurately predicted the chronological age of 535 children from an Italian sample population of another study, in particular, those aged between 7 to 9 and 10.4 to 11.5 years (Santoro, et al., 2012). For the latter study, this means that despite ethnic differences between the reference and contemporary populations, the analysis could be considered to be reliable. But this prediction could be explained by both populations being of Caucasian descent.

There are also many other issues that the GP method overlooks, such as factors that can influence the development of bone in the contemporary sample population, which are not reflected in the reference population. Factors such as the variation in bone development between subsequent generations due to differences in socioeconomic status (Hsieh, Liu, Tiu, Chen, & Jong, 2011) and whether individuals are in possession of endocrine diseases (Xing, Cheng, Wergedal, & Mohan, 2014).

Tanner-Whitehouse Method

Unlike the Greulich-Pyle method, there are two assessment systems in the Tanner-Whitehouse (TW) method: “RUS” (radio, ulna and selected metacarpals and phalanges) and ‘Carpal’, which evaluates all carpal bones except pisiform. The Tanner-Whitehouse 2 (TW2) method is an earlier version of the TW method which analysed the level of maturity of up to 20 regions of interest in specific bones. Radiographs of the contemporary population are taken, and a numerical score is assigned to particular stages of development for each bone. The sum of all scores produces a total maturity score that correlates to a skeletal age – separate for males and females. The reference population of the TW2 method were UK children possessing average socioeconomic status (Satoh, 2015).

In 2001, publication of the Tanner-Whitehouse 3 (TW3) method was introduced. While the new methodology maintained the two systems of assessment as in TW2, the reference population and radiographs for the systems was changed to those belonging to children from North America. Thereby, improving on the accuracy and reproducibility of the original TW and TW2 method (Ortega, et al., 2006). There are also reports of standardised TW methods, where longitudinal studies for different regions and populations are conducted and utilised as the new reference population, in place of the original TW reference population. And by doing so, most of the issues that the GP method overlooks is addressed, as the relationship between the total maturity score and the bone age is changed to become more suitable for that particular group. However, while this makes it more favourable for accuracy compared to the GP method, the TW does require more time to process and reproduce the complex data into a chronological age estimate (Zhang, et al., 2013). According to a 1994 study, the average time to perform a GP assessment was approximately six times quicker than a TW2 assessment (King, et al., 1994).

Ultrasonography

One the of major disadvantages present in both GP and TW methods is that individuals are exposed to ionising radiation for radiographs. Ultrasonography or ultrasound (US) is a less harmful alternative in its initial stages of clinical application. A 2009 study assessed the accuracy of skeletal age predications from the wrists of 100 children via US, and it was found that the linear correlation between the predictions by GP, TW and US methods varied greatly. The strongest correlation between the three methods was found in the ‘normal’ bone age group (80.0% to 86.1%). However, the US method overestimated delayed bone ages and underestimated advanced bone ages. Thereby, producing weaker correlations of 77.1% to 86.9% in ‘delayed’ bone age group and 62.2% to 81.1% in ‘advanced’ bone age group (Khan, Miller, Hoggard, Somani, & Sarafoglou, 2009). Therefore, despite sufficiently providing an assessment for skeletal age estimation, the correlations between the US and GP and TW methods are not accurate or valid enough to become a reliable alternative.

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is another method that does not require exposure to ionising radiation. A 2014 preliminary study found that a strong linear correlation existed between MRI predications and the chronological ages of 179 individuals. The methodology of the study consisted of T1-weighted MRI scans of the hand and wrist being collected and evaluated by two blinded radiologist. Depending on various factors such as cartilage appearance and vacuolisation, provisional calcification, progression of and completion of ossification, a correlating skeletal age prediction would be produced (Tomei, et al., 2014). The only problem with MRI assessments, despite strong correlational results, would be that MRI equipment are not readily accessible and is relative more expensive than radiographic methods.

Automated Computerised Assessments

Automated skeletal age assessments by a software called BoneXpert is recently being adopted by many hospitals. One of the major problems that automated assessments are able to solve is the variability in manual skeletal age predictions, as it highly dependent on the individual performing the rating. However, for this method, the radiographs of abnormal bone morphologies are rejected. The BoneXpert method first reconstructs the borders of 15 bones from radiographs of the patient’s hand, of which 13 bones are automatically assigned with intrinsic bones ages. The intrinsic bone ages are not only dependent on various scores derived from preliminary analysis, but also the consensus bone age concept that defines the best bone age estimation for each bone. This is possible due to the software being capable of containing a large database of hand radiographs from children of varying ages. Thereby producing for a common skeletal age model – separate for males and females. The intrinsic bones ages are then converted into GP and TW bone ages (Thodberg, Kreiborg, Juul, & Pedersen, 2009).

As the BoneXpert method is dependent on its database, it is also possible to eliminate the issues with ethnic differences, which are present in the GP method. In a 2010 study, a large database of 1380 hand radiographs of children with varying ethnic backgrounds were analysed using BoneXpert. It was found that the root-mean-square (RMS) deviation between two manually-rated bone ages were approximately 7.5 months, and the RMS deviation between the automated bone age and the average of the manually-rated bone ages was 7.3 months (Thodberg & Sävendahl, Validation and reference values of automated bone age determination for four ethnicities., 2010). These results suggest that utilisation of BoneXpert is a valid and reliable alternative.

Structure and Basic Functions of the Human Skeleton

The human skeleton is the internal framework of the human body. The skeleton main function is to support and give the human body shape. The major bones of the skeleton are:

  1. The skull- It is made up of the cranium, mandible, and maxilla;
  2. The shoulder girdle- It consist of the clavicle and scapula;
  3. The arm- It consist of the humerus, radius, ulna;
  4. The hand- it is made up of carpals, metacarpals, and phalanges;
  5. The chest- It is made up of the Sternum, and ribs;
  6. The spine- It consist of the Cervical area (top7 vertebrae), Thoracic (next 12), Lumbar (bottom 5 vertebrae), Sacrum (5fused together bones) and the Coccyx (the tiny bit at the bottom of the spine);
  7. The pelvic girdle- It consist of the Ilium, Pubis and Ischium;
  8. The leg- It consist of the Femur, Tibia and Fibula;
  9. The ankle- It consist of the Talus and calcaneus;
  10. The foot- It consist of the Tarsals, Metatarsals and Phalanges.

It is the internal structure that supports the human body with the help of the muscular system allows movement, it also helps to protect the vital organs found inside it from being damaged.

The human skeleton is made up of 275 different bones and as the body matures some of these bones start to fuse together leaving only 206 bones in an adult body.

The function of the human skeleton includes: 1) blood production; 2) movement; 3) shape; 4) protection.

The two major systems of bones in the human body are axial and appendicular skeleton. Axial skeleton is mainly for protection. It forms the main axis/core of a human skeletal system. Cranium protects the brain. Made up of hard sheets of bones with fixed joints. Sort of a ball shape at the back. It is comprised of eight cranial and fourteen facial bones. The cranial bones make up the protective frame of bone around the brain. The facial bones make up the shape of a human face. Thorax protects the heart and lungs, and it also helps in shape of the body. The vertebrae of a human spine are held together firmly by strong ligaments that allow little movement between your adjacent vertebrae but allow a reasonable degree of flexibility along the spine. Its main function is to protect the spinal cord and it also helps in supporting the ribcage by maintaining the balance between it and the abdominal cavity.

Appendicular skeleton also help sometimes in protection. It allows easy body movement and protects the organs of digestion, excretion, and reproduction. The appendicular skeleton is the part of the skeleton that includes the pectoral girdle, the upper limbs, the pelvic girdle, and the lower limbs. The appendicular skeleton and the axial skeleton together make up the complete skeleton.

FEA on Assembled Fractured Human Femur Bone with and without Hydroxyapatite: Analytical Essay

Abstract

Femur, also called thighbone or hind leg in human body supports the maximum weight of the body under loading conditions. In this present work, the fractured femur bone is reconstructed using DICOM files obtained from Computed Tomography scan images using software’s 3D slicer and blender. In accordance with the crack, prosthetic plate was modeled in Unigraphics NX 11.0 version. The plate is then assembled with the fractured femur bone using Assembly module of the Unigraphics NX 11.0 version. Then Static structure Finite element Analysis was performed on the Assembly for different prosthetic plate materials like SS316L, Alumina, Nylon, Titanium, PMMA and PEEK with and without Hydroxyapatite(HA) coating on the prosthetic plate . It was proved in this work that best results are obtained with HA-coated prosthetic plate material that means the bone healing will be much faster when prosthetic plated are coated with Hydroxyapatite.

Keywords: Femur bone, DICOM files, Prosthetic plate, hydroxyapatite (HA), FEA

1. Introduction

By measurement, femur bone is longest bone in human body and supports the weight of body and allows motion to the leg. Fractures in femur bone are caused due to large force, impact loads, accidents, falls from high altitudes, and disease in the bone. Femur fractures that are simple, short cracks in the bone usually do not require surgery, but sever impact fracture, partial fracture, completely displaced fracture need to treat the bone using prosthetic implants. Fracture management products include a wide variety of devices including wires, pins, screws, plates, spinal fixation devices, and artificial ligaments. The types of prosthetic plates from early stages to the present day of implantation surgeries are Compression plate (CP), Dynamic compression plate (DCP), Limited- contact dynamic compression plate (LC-DCP), Point contact fixator (PC-Fix), Less invasive stabilization system (LISS), Locking compression plate (LCP), Precontoured LCP.

1.1 Materials available for prosthetic plates manufacturing

Biomaterial is defined as “A nondrug substance suitable for inclusion in systems which augment or replace the function of bodily tissues or organs. There are different biomaterials that are used to make these prosthetic plates like metals, polymers, composites, and ceramics. Mostly Stainless steel is used in orthopedic implants for temporary fixation plates because of its widely availability and cost-effectiveness. These plates are removed after the healing process is completed. Titanium is also used as a prosthetic implant which is stronger and lighter in weight compared to stainless steel. Polymers are also used in the form of implants and medical devices to replace and restore the function of damaged parts. Examples of polymers and composites are Polymethyl-methacrylate (PMMA), Polylactic acid (PLA), Polyglycolic acid (PGA). Alumina and hydroxylapatite (HA) come under the category of bioceramics. But this materials cannot be used directly as implants due to its low mechanical strength and low fracture toughness. But these materials can be used in the form of coatings and in mixed ratios with other biomaterials.

To develop the 3D models of bones CT or MRI data is collected. CT or MRI data is saved in the form of DICOM files and is used in CAD software to develop the models.

1.2 Reconstruction of bone using 3D Slicer

The collected DICOM files with slice thickness of 0.6mm were imported into this software. By enabling the volume rendering feature we can observe the visualization of the files on the slicer window in 4 views i.e., axial view, three dimension view, sagittal view, and coronal view as shown in fig2.1.A preset selection of CT bones was selected and it can be observed that in the three-dimensional view, only bones were visualized removing all the other unwanted material which is shown in fig 2.2

Fig 2.1 3D slicer window showing 4 views

Fig 2.2. Preset selection

After this, cropping was done by using the crop volume module. Here the cropping was done to get the right femur bone of the image. The cropped new volume is shown in figure 2.3.

Fig 2.3. Cropped volume

From the obtained CAD model it was observed that the model is with a lot of obstructions, irregularities, and discontinuous as it is already gone for a prosthesis with implantations. So to obtain the best model without any errors, paint effect was used in editor module. After using the paint effects the best 3D cad model of right femur is as shown in figure 2.4. This obtained model was saved in STL file format as to import the model into blender. The obtained model was with some errors and the surface achieved was rough. To remove this, software called Blender was used.

Fig 2.4 Showing 3D CAD model of the right femur after using paint effect

2.2 Finishing the femur model using Blender

The obtained model from 3D slicer was imported into Blender to remove the discontinuous shapes and errors and to obtain a good surface finish which is shown in figure 2.5 from the selection mode, the continuous and inverted links were selected by vertex selection and the inverted links were deleted to obtain an error-free femur bone without any obstructions which are shown in figure 2.6 (a) & (b).

Fig 2.5 Blender window with imported STL file of the right femur bone

Fig 2.6 Showing (a) inverted links (b) obtained model without errors

(c) Final 3D CAD model of right femur with the good surface finish

After applying the smoothening option from object modifiers, the final 3D CAD model of the femur with the good surface finish is shown in figure 2.6(c).

2.3 Initiation of fracture on the femur bone

Partial fracture was initiated for further study on the analysis of fractured femur bone. The fracture was generated in NX by removing the part material from the shaft of the femur bone as shown in figure 2.7

3. Fractured femur bone analysis

The fractured femur bone was inserted into the static structural module and the material properties of the femur bone were assigned from references [2] and[18].

3.1 Meshing

The meshing of the fractured femur bone was done with Element type triangular and element size of 5mm

Fig 2.7Fracture on femur shaft

3.2 Boundary conditions

The lower part of the femur bone was fixed and two forces on the upper part of the femur were assigned.

Force 1: 750N, 150, 0 and Force 2: -150N, -50N, 0

Force 1 is the total body weight of the person which is acting downwards when the person is standing and force 2 is the reaction force which acting in the opposite direction as shown in fig 3.1

Fig 3.1Boundary conditions

3.3 Results of fractured bone analysis

Static structural analysis is carried out and it was noted that the maximum stresses are acting on the shaft at the initiation of fracture for the boundary conditions that are considered and the total deformation was seen maximum on head of the femur bone. The results are as shown below figure 3.2

Fig 3.2 Fractured bone (a) Maximum principal stress (b) Equivalent stress (c) Total deformation

4. Assembly for fractured bone and prosthetic plate

In this work, prosthetic plate of LCP type is modeled and assembly is done as shown in figure 4.1

Fig 4.1 Assembly of the femur and prosthetic plate

5. Assembly analysis

Edge size meshing was generated at the crack by using same mesh sizing as of fractured bone and the boundary conditions are kept same as of fractured bone. Analysis of the assembly was carried out by changing the material properties of prosthetic plates, from references [2], [17], [19], and [20]. The results of stresses and deformation of prosthetic plate materials SS316L, alumina, titanium, PEEK are as shown in fig 5.1 to 5.4.

5.1 Analysis results of fractured bone with SS316L prosthetic plate

Fig 5.1 Maximum principal stress, Equivalent stress, Total deformation of fractured bone with SS316L plate

5.2 Analysis results of fractured bone with Alumina prosthetic plate

Fig 5.2Maximum principal stress, Equivalent stress, Total deformation of fractured bone with Alumina plate

5.3 Analysis of results of fractured bone with Titanium prosthetic plate

Fig 5.3Maximum principal stress, Equivalent stress, Total deformation of fractured bone with Titanium plate

5.4 Analysis results of fractured bone with PEEK prosthetic plate

Maximum principal stress, Equivalent stress, Total deformation of fractured bone with PEEK plate

The results of stresses and deformation of prosthetic plate materials with HA-coated on SS316L, alumina, titanium, PEEK are as shown in fig 5.5 to 5.8.

5.5 Analysis results of fractured bone with HA-coated SS316L

Maximum principal stress, Equivalent stress, Total deformation of fractured bone with HA-coated SS316L plate

5.6 Analysis of results of fractured bone with HA-coated Titanium

Maximum principal stress, Equivalent stress, Total deformation of fractured bone with HA-coated Titanium plate

5.7 Analysis results of fractured bone with HA-coated Alumina

Maximum principal stress, Equivalent stress, Total deformation of fractured bone with HA-coated Alumina plate

5.8 Analysis results of fractured bone with HA-coated PEEK

Maximum principal stress, Equivalent stress, Total deformation of fractured bone with HA coated PEEK plate

6. Results and Discussions

It was observed that for HA coated Prosthetic plates stresses are been increased and deformations are reduced. The maximum stresses were acting on the plate which means that the bone was not taking the load. The decrease in the deformations means that the load-bearing capacity was increased by the plates which are affixed to the bone. The obtained maximum stresses and deformations are tabulated as shown in table 6.1 and 6.2

Table 6.1 Equivalent stress, Maximum principle stress, and total deformation of fractured bone with Prosthetic plates of different materials

  • Equivalent Stress
  • (Pa) Max principle stress
  • (Pa) Total deformation
  • (m)
  1. SS316L 1.1985e8 6.7819e7 0.0017282
  2. Alumina 1.322e8 09.5249e7 0.0017076
  3. Titanium 2.436e8 2.3294e8 0.0016636
  4. PEEK 6.9348e7 5.0685e7 0.001858

Table 6.2 Equivalent stress, Maximum principle stress and total deformation of fractured bone with HA coated Prosthetic plates of different materials

  • HA Coated plates Equivalent stress
  • (Pa) Max principle stress
  • (Pa) Total deformation
  • (m)
  1. SS316L 6.0371e8 4.9614e8 0.0015459
  2. Alumina 6.5522e8 5.364e8 0.0013172
  3. Titanium 1.7232e8 1.1508e9 0.00094946
  4. PEEK 1.908e8 1.8263e8 0.0015637

7. Conclusions and future scope

7.1 Conclusions:

  • Construction of femur bone was successfully done using 3D Slicer and Blender software’s from DICOM files or CT scan data
  • Analysis was carried out with different prosthetic plate materials without HA coating to the assembled fracture femur bone.
  • Same procedure was carried out with 0.3mm hydroxyapatite (HA) coated on different base prosthetic plate material.
  • From the results it was concluded that for HA coated plates the stresses were increased and were acting on the plate, taking the maximum load.
  • It was concluded that deformations were decreased and so that the healing can be obtained with less time duration.

7.2 Future scope

Fibers and other composite materials can be used as prosthetic plates in future which should be tested clinically.

References

  1. Sandeep Kumar Parashar, Jai Kumar Sharma, A Review on Application of finite element modelling in bone biomechanics. Perspectives in Science (2016)8,696-698.
  2. Ajay Dhanopia, Prof. (Dr.) Manish Bhargava, Finite Element Analysis of Human fractured femur bone implantations with PMMA Thermoplastic Prosthetic Plate. Procedia Engineering 173(2017)1658-1665.
  3. W. K. Chiu, W. H. Ong, M. Russ, M. Fitzgerald, Simulated vibrational analysis of internally fixated femur to monitor healing at various fracture angles. Procedia engineering 188 (2017)408-414.
  4. Ashwani Kumar, Himanshu jaiswal, Tarun Garg, Pravin P Patil, Free Vibration Modes Analysis of Femur Bone Fracture Using varying Boundary Conditions Based on FEA. Procedia materials science 6(2014)1593-1599.
  5. P.S.R. Senthil Maharaj, R. Maheswaran, A. Vasanthanathan, Numerical Analysis of Fractured Bone with Prosthetic Bone Plates. Procedia engineering 64 (2013) 1242-1251.
  6. Saeid Samiezadeh, Pouria Tavakkoli Avval, Zouheir Fawaz, Habiba Bougherara, Biomechanical assessment of composite versus metallic intramedullary nailing system in femoral shaft fractures: A finite element study. Clinical Biomechanics 29 (2014) 803-810.
  7. Ehsan Basafa, Rober S.Armiger, Michaes D. Kutzer, Stephen M. Belkoff, Simon C. Mears, Mehran Armand. Patient-specific finite element modeling for femoral bone augmentation. Medical engineering and Physics 35 (2013) 860-865.
  8. M Vijay kumar reddy, BKC Ganesh, KCK Bharathi, P ChittiBabu, Use of finite element analysis to predict type of bone fractures and fracture risks in femur due to Osteoporosis. J Osteopor Phys Act 2016, 4:3.
  9. N.D. Deokar, Dr. A.G. Thakur, Design Development and Analysis of Femur Bone by using Rapid Prototyping. IJEDR 2016 ISSN: 2321-9939.
  10. Baradeswaran. A, Joshua Selvakumar. L and Padma Priya. R. Reconstruction of images into 3D models using CAD techniques, European journal of applied engineering and scientific research, 2104, 3(1): 1-8.
  11. George Z. Cheng, Raul San Jose Estepar, Erik Folch, Jorge Onieva, Sidhu Gangadharan and Adnan Majid. Three dimensional printing and 3D slicer-powerful tools in understanding and treating structure lung diseases, CHEST, 2016, 149(5): 1136-1142.
  12. Emmanuel Rios Velazquez, Chintan Parmar, Mohammed Jermoumi, Raymond H. Mak, Angela van Baardwijk, Fiona M. Fennessy, John H. Lewis, Dirk De Ruysscher, Ron Kikinis, Philippe Lambin & Hugo J. W. L. Aerts. Volumetric CT-based segmentation of NSCLC using 3D-Slicer, Scientific Reports | 3:3529 |DOI:10.1038/srep035.
  13. Cornel IGNA and Larsia SCHUSZLER. Current concepts of internal plate fixations on fractures. Bulletin UASVM, veterinary medicine 67 (2)/2010. ISSN1843-5270.
  14. Javad Malekani, Beat Schmutz, Yuantong GU, Michael Schuetz, Prasad Yarlagadda. Orthopaedic bone plates: Evolution in structure; Implementation technique and biomaterials. GSTF. International journal of engineering Technology. Vol.1 2012.
  15. Seemab Mehmood, Umar Ansari, Murtaza Najabat Ali, Nosheen Fatima Rana. Internal fixation: An evolutionary appraisal of methods used for long bone fractures. International Journal of Biomedical and Advance Research. ISSN: 2229-3809.
  16. Soumya Nag and Rajarshi Banerjee. Fundamentals of Medical Implant Materials. ASM Handbook, Volume 23, Materials for Medical Devices (2012).
  17. M. Navarro, A. Mirchiardi, O. Castano and J. A. Planell. Biomaterial in orthopaedics. J.R. Soc. Interface (2008) 5, 1137-1158.
  18. Tony M. Keaveny, Elise F. Morgan, Oscar C. Yeh. Bone mechanics. The McGraw-Hill Companies (2004).
  19. Ryan K. Roeder Ph.D. and Timothy L. Conrad B.S.Bioactive Polyaryletherketone Composites.PEEK Biomaterials Handbook. DOI: 10.1016/B978-1-4377-4463-7.10011-9 (2012).
  20. S. M. Kurtz and J. N. Devine. PEEK Biomaterials in Trauma, Orthopedic, and Spinal Implants. Biomaterials. 2007 November; 28(32): 4845–4869.
  21. M.J. Long and H.J. Rack, Titanium Alloys in Total Joint Replacement—A Materials Science Perspective, Biomaterials, Vol 19, 1998, p 1621–1639
  22. V.C. Mow and L.J. Soslowsky, Friction, Lubrication, and Wear of Dithridial Joints, Basic Orthopedic Biomechanics, Raven Press Ltd., New York, 1991, p 245–292
  23. D. Dowson, Chap. 29, Bio-Tribology of Natural and Replacement Synovial Joints, Biomechanics of Diarthrodial Joints, Vol II, V.C. Mow, A. Ratcliffe, and S.L.-Y. Woo, Ed., 1992, p 305–345
  24. E.W. Lowman, Osteoarthiritis, J. Am. Med. Acad., Vol 157, 1955, p 487
  25. B.D. Ratner, A.S. Hoffman, F.J. Schoen, and J.E. Lemons, Biomaterials Science: An Introduction to Materials in Medicine, 2nd ed., Elsevier Academic Press, San Diego, CA, 2004
  26. F. H. Martini, “Fundamentals of Anatomy and Physiology”, 6th Ed., Prentice Hall, New Jersey, USA, 182-207 (2004).
  27. R. B. Martin, “Bone as a Ceramic Composite Material”, Mater. Sci. For., 293, 5-16 (1999).
  28. E. N. Maribe, “Human Anatomy and Physiology”, 6th Ed., Benjamin/Cummings Publishing Company Inc., California, USA, 175-201 (2004).

Bone Disease Prediction: Analytical Essay

1. Introduction

1.1 Applications

Data Mining is implementing in wide variety of areas. There are many commercial data mining systems available in the world today. It is used in Loan payment prediction and customer credit policy analysis as far as financial data analysis is considered. In retail industry analysis of effectiveness of sales, campaigns is done with data mining. It plays an important role in providing the visualization tools in telecommunication data analysis. Biological data mining is a very important part of Bioinformatics. [10] In Biological data analysis, discovery of structural patterns and analysis of genetic networks and protein pathways is done with the help of data mining. It also contributes in intrusion detections. [10]

1.4 Research motivation and problem statement

1.4.1 Research motivation

Bone diseases like trauma, inflammation, arthritis, osteoporosis, bone tumor, etc are nowadays very common in people. Not only these diseases but also the bone fractures are very much common in the people nowadays. Hence we came up with the system which considers and analyses the previously-stored symptoms of the bone disease patients and predicts the status of the new patient which determines the complexity, and type of the bone disease the patient is involved. As a result of our system, unnecessary tests on bones can be avoided.

1.5 Research objectives and contributionS

1.5.1 Primary objectives

Bone is one of the important components of a human body. It is the one which supports and protects various organs. And it also provides a structure for the body. Being so important to our body it may also get affected by various diseases or infections. So our primary objective is to identify those diseases or infections of humans at the initial state itself which will avoid the unnecessary tests on bones.

1.5.2 Main contributions

We in our project are considering the symptoms, signs, age found to be affected, and gender found to be affected, of the previously affected patients and when a new patient comes with the similar symptom or sign we consider the previously stored and analyzed data and predict whether the patient is affected by the similar disease or not. As a result of this, the person may avoid some of the unnecessary tests.

1.6 Organization of the report

The report is well organized. It is divided into totally 9 chapters. The first chapter is the introduction which includes background, brief history of technology, applications, research motivation and problem statement, research objectives, contributions, organization of the report, and summary. The next chapter is Literature Survey, the other chapter is System Requirements Specifications, the other chapters are Design, Implementation, Testcases, Results, Conclusion, and References.

2. Literature survey

2.1 Introduction

The research works have been found related to “Bone Disease Prediction Using Data Mining Techniques”. The dataset, the algorithms, the methodology used by the authors, and the observed results along with the future work is carried out in finding out efficient models of medical diagnosis for various bone diseases.

Bone diseases are mainly of the following types:

Bone disease is any of the diseases or injuries that affect human bones. In, Osteoporosis is a condition that weakens bones, making them fragile and more likely to break. More than 300,000 people receive hospital treatment for fragility fractures every year as a result of osteoporosis.

2.2 Related work

Here is a brief discussion about the work related to Bone Disease Prediction that has been already carried out in past few years.

  1. 1. Prediction of fracture risk in postmenopausal white women with peripheral bone densitometry: Evidence from the national osteoporosis risk assessment.

Low Bone Mineral Density (BMD) is a risk factor for fracture and is considered as the important predictor of future fractures. The authors studied the relationship between Bone Mineral Density measurements at peripheral sites and subsequent fracture risk at the hip, wrist/forearm, spine, and rib in 149524 postmenopausal white women, without a prior diagnosis of osteoporosis. At enrollment, each participant completed a risk assessment questionnaire and had BMD testing at the heel, forearm, or finger. Main outcomes were new fractures of the hip, wrist/forearm, spine, or rib within the first 12 months after testing. The test is considered as the T-scores which is the measure of Bone Mineral Density for the prediction. The authors examined BMD measurement, Questionnaires, and Data analysis for the prediction purpose. The authors inspected the performance of the algorithms through evaluation criteria such as sensitivity and specificity

  1. 2. Biochemical Markers of Bone Metabolism and Prediction of Fracture in Elderly Women.

The authors studied that different markers of bone turnover predict the fracture in 1040 elderly women. The various markers considered were Serum bone-specific alkaline phosphatase and four different forms of serum osteocalcin (S-OC), and others as markers of bone resorption. They considered Sampling procedures, Bone markers formation, Bone markers resorption, Bone markers urine osteocalcin, and other measurements for the prediction.

  1. 3. Fracture prediction from bone mineral density in Japanese men and women

The paper mainly focuses on low bone mineral density which is the important predictors of future fractures. The authors considered the association of Bone Mineral Density(BMD) with the risk of fracture of the spine or hip among a cohort of 2356 men and women aged 47–95 years, who were followed up by biennial health examinations. Follow-up averaged 4 years after baseline measurements of BMD that were taken with the use of Dual-energy X-ray Absorptiometry(DXA). Vertebral fracture was assessed using semiquantitative methods, and the diagnosis of hip fracture was based on medical records. Poisson and Cox regression analysis were the models used.

  1. 4. Prediction and Informative Risk Factor Selection for Bone Disease.

The authors trained an independent model based on a specific group of patients. They examined Comprehensive Disease Memory (CDM) which captures the characteristics for all patients to predict the disease. Bone disease memory (BDM) memorizes the characteristics of those considered individuals who suffer from bone diseases. Similarly, the Non-Disease Memory (NDM) memorizes attributes for non-diseased individuals. They have used Shallow Restricted Boltzmann Machine and 2-Layer Deep Belief Network for the prediction purpose.

  1. 5. Predict and prevent bone disease using data mining techniques.

This work applied many models to predict and prevent various bone diseases. In the respective research, the author has used oomph model as the opening to the proposed method, then single-layer and multi-layer learning approaches are introduced to construct the different disease memories. Finally, they have proposed their model that are focusing on the prediction and educational Risk Factor selection for bone diseases. The author analyzes the performance of the algorithms through evaluation criteria such as sensitivity to skewed class, sensitivity to noisy data, and parameter selection.

2.3 Study of tools/technology

We consider Python interpreter for implementation purposes and Jupyter notebook web application for the better visualization of data and to check the accurate algorithm among Logistic Regression (LR), Linear Discriminant Analysis (LDA), K-Nearest Neighbor (KNN), Decision Tree (DT), Naïve Bayes (NB), Support Vector Machine (SVM) which we have used.

Jupyter Notebook: The Jupyter Notebook is an open-source web application that can be used to create and share documents that contain live code, equations, visualizations, and text.

Summary

3. System requirements specifications

3.1 General Description

3.1.1 Product Perspective

The system predicts the type of bone diseases which are generally occurring in the human body by analyzing the dataset which can be divided into training and test set, based on the different number of features and by using more accurate algorithm. The prediction system predicts the two types of bone diseases such as Traumatic bone disease and Degenerative bone disease.

3.2 System Requirements

3.2.1 Hardware Requirements

  1. Processor: 2.10 GHz Dual Core (Faster is better)
  2. RAM:- 4 GB (2018 At least 8 GB)
  3. System type: 64-bit Operating System

3.2.2 Software Requirements

  1. 1. Anaconda-Jupyter

The Jupyter Notebook is an open-source web application which can be used to create and share the documents that contain live code, equations, visualizations, and text.

Fig 3.2.2.1. Jupyter web application

  1. 2. Python 3.6.4 Idle

Fig 3.2.2.2. Python 3.6.4 Idle

3.2.2.1 Functional Requirments & Non-functional Requirements

  • EfficiencyThe system determines the efficiencies of the algorithms. The Accuracy of the considered algorithms will be determined among which the system selects the most accurate algorithm for prediction of bone diseases.
  • Graph: The algorithm’s accuracy are represented in bar graph for better visualization.

3.2.2.2 User Requirements

The different modules are explained below:

  • The Real-time Dataset consists of age, region affected, symptoms, signs, and functional disabilities of all the patients. LR model analyzes this stored data and predicts the type of bone disease that a new patient is incurred.
  • The System determines the accuracy of all the considered algorithms in which the LR algorithm is selected for further process.
  • LR model analyzes the stored data and predicts the type of bone disease that a new patient is incurred.

3.3 Summary

In this section, we have discussed and organized the functional requirements for the prediction system. And also the System requirement for the prediction system which includes hardware and software requirements are specified in this section. These are the requirements that should be fulfilled to successfully complete this project.

4. Design

4.1 Architectural design

Fig 4.1: Architectural Design

The above diagram Fig.4.1 demonstrates the architectural design for carrying out the prediction. The dataset (i.e Bone disease dataset) is fed to the ‘Training phase’ where six algorithms, kNN, Support Machine Vector, Decision Trees, Linear Discriminant, Logistic Regression, and Naïve Bayes are applied on the dataset to compare their efficiency. In the ‘Testing phase,’ the most efficient algorithm is selected among all of the six algorithms, then it is used to predict the type of bone disease when new data is fed for prediction.

4.2 Dataflow Diagram

Fig 4.2: Dataflow Diagram

The above diagram Fig.4.2. demonstrates the flow design for carrying out the prediction. Flow diagram is basically used to demonstrate how the data flows in the proposed system. The dataset is separated into the Training set and the Test set. The Training set is the set of data which is used to train a model. In training the model, specific features are picked out from the training set. Test data is the set of data on which the model is applied to predict the output. In the figure above, training set undergoes pre-processing to understand and select the special features and after pre-processing, the pre-processed data is fed to several algorithms, among which the most efficient is selected for the prediction. Test data is fed to the selected model to obtain the predicted output.

4.3 Class hierarchy Diagram

Fig 4.3: Class Hierarchy Diagram

The above diagram Fig.4.3. demonstrates the Class design for carrying out the prediction. Class diagram basically consists of all the classes defined in the project with its attributes and functions. In our project, there are four classes: main, get_data, predict_disease, and get_data1. get_data is the class which retrieves the data from the database. Predict_disease class is where prediction of bone disease is carried out.

4.4 Usecase Diagram

Fig 4.4: Usecase Diagram

The above diagram Fig.4.4. demonstrates the use case design for carrying out the prediction. Usecase diagram is basically about how the user interacts with the system and the database. Here, the dataset is collected from several patients and these datasets are stored in the database. The database feeds these datasets to several algorithms. The predicted results are stored in the Excel sheet and the results can be viewed by the patient.

4.5 Sequence Diagram

Fig 4.5: Sequence Diagram

The above diagram Fig.4.5. demonstrates the Sequence design for carrying out the prediction. The sequence diagram basically is used to demonstrate the sequence in which the whole process of disease prediction takes place. Here, data is collected from the patient and then stored in the database. After which the dataset stored in the database is fed to the algorithms and compared based on efficiency. The algorithm having best efficiency is then used to predict the result once the new data is fed to the selected algorithm. The predicted result and the dataset is stored in the database.

4.6 Activity diagram

Fig 4.6: Activity diagram

The above diagram Fig.4.6. demonstrates the activity design for carrying out the prediction. The dataset is fed to six considered algorithms(kNN, SVM, LR, LD, DT & NB) and the best algorithm among all six is selected based on their efficiency. New data is fed as input to the selected algorithm and the result is obtained.

5. Implementation

Dataset

The Dataset is collected from Sun Orthopedic Hospital, Mathikere. It has 47 rows, 29 attributes, and 2 classes.

Names do not contribute for the purpose of bone disease prediction. So this attribute is not used in our models. The dataset description is given in Table 5.1.1.

  • Attribute
  • Value
  • Description
  • Name
  • String
  1. Name of the patient
  • Age
  • Integer
  1. Age of the patient entered in years
  • Gender
  • Boolean
  1. Yes, if Male. No, if Female.
  • Body
  • Boolean
  1. The region affected due to bone disease is body. (0=No; 1=Yes)
  • Knee
  • Boolean
  1. The region affected due to bone disease is knee. (0=No; 1=Yes)
  • Ankle
  • Boolean
  1. The region affected due to bone disease is ankle. (0=No; 1=Yes)
  • Foot
  • Boolean
  1. The region affected due to bone disease is foot. (0=No; 1=Yes)
  • Lumbous Hip
  • Boolean
  1. The region affected due to bone disease is lumbous hip. (0=No; 1=Yes)
  • Shoulder
  • Boolean
  1. The region affected due to bone disease is shoulder. (0=No; 1=Yes)
  • Wrist
  • Boolean
  1. The region affected due to bone disease is wrist. (0=No; 1=Yes)
  • Thumb
  • Boolean
  1. The region affected due to bone disease is thumb. (0=No; 1=Yes)
  • Shoulder Joint
  • Boolean
  1. The region affected due to bone disease is shoulder joint. (0=No; 1=Yes)
  • Hand
  • Boolean
  1. The region affected due to bone disease is hand. (0=No; 1=Yes)
  • Leg
  • Boolean
  1. The region affected due to bone disease is leg. (0=No; 1=Yes)
  • Rib
  • Boolean
  1. The region affected due to bone disease is rib. (0=No; 1=Yes)
  • Multiple Joint
  • Boolean
  1. The region affected due to bone disease is multiple joint. (0=No; 1=Yes)
  • Lower Back
  • Boolean
  1. The region affected due to bone disease is lower back. (0=No; 1=Yes)
  • Thigh
  • Boolean
  1. The region affected due to bone disease is thigh. (0=No; 1=Yes)
  • Around Neck
  • Boolean
  1. The region affected due to bone disease is around neck. (0=No; 1=Yes)
  • Spine
  • Boolean
  1. The region affected due to bone disease is spine. (0=No; 1=Yes)
  • Hip
  • Boolean
  1. The region affected due to bone disease is hip. (0=No; 1=Yes)
  • Elbow
  • Boolean
  1. The region affected due to bone disease is elbow. (0=No; 1=Yes)
  • Knee Joint
  • Boolean
  1. The region affected due to bone disease is knee joint. (0=No; 1=Yes)
  • Pain
  • Boolean
  1. The symptom that indicates the bone disease is pain in affected region. (0=No; 1=Yes)
  • Difficulty in Movement
  • Boolean
  1. The symptom that indicates the bone disease is difficulty in movement. (0=No; 1=Yes)
  • Buckling
  • Boolean
  1. The symptom that indicates the bone disease is buckling. (0=No; 1=Yes)
  • Weakness in Muscle
  • Boolean
  1. The symptom that indicates the bone disease is weakness in muscle. (0=No; 1=Yes)
  • Swelling
  • Boolean
  1. The sign that indicates the bone disease is swelling. (0=No; 1=Yes)
  • Redness
  • Boolean
  1. The sign that indicates the bone disease is redness. (0=No; 1=Yes)
  • Itching
  • Boolean
  1. The sign that indicates the bone disease is itching. (0=No; 1=Yes)
  • Ankle Deformity
  • Boolean
  1. The sign that indicates the bone disease is ankle deformality. (0=No; 1=Yes)
  • Feverish due to Pain
  • Boolean
  1. The sign that indicates the bone disease is fever due to pain. (0=No; 1=Yes)
  • Pain in Ribs
  • Boolean
  1. The sign that indicates the bone disease is pain in ribs. (0=No; 1=Yes)
  • Tenderness
  • Boolean
  1. The sign that indicates the bone disease is tenderness. (0=No; 1=Yes)
  • Sweating
  • Boolean
  1. The sign that indicates the bone disease is sweating. (0=No; 1=Yes)
  • Vomiting Sensation
  • Boolean
  1. The sign that indicates the bone disease is vomiting sensation. (0=No; 1=Yes)
  • Latchment
  • Boolean
  1. The sign that indicates the bone disease is latchment. (0=No; 1=Yes)
  • Minimal Pain
  • Boolean
  1. The sign that indicates the bone disease is minimal pain in affected region. (0=No; 1=Yes)
  • Diabetic Control
  • Boolean
  1. The sign that indicates the bone disease is diabetic control. (0=No; 1=Yes)
  • Bending
  • Boolean
  1. The sign that indicates the bone disease is bending. (0=No; 1=Yes)
  • Water Content in Joint
  • Boolean
  1. The sign that indicates the bone disease is water content in joint. (0=No; 1=Yes)
  • No Signs
  • Boolean
  1. The patient has no signs that indicate bone disease. (0=No;1=Yes)
  • Pain
  • Boolean
  1. The physical incapacity to do chores due to bone disease is pain in affected region. (0=No; 1=Yes)
  • Bone Dislocation
  • Boolean
  1. The physical incapacity to do chores due to bone disease is bone dislocation. (0=No; 1=Yes)
  • Difficulty in Doing Daily Activities
  • Boolean
  1. The functional disability due to bone disease is difficulty in doing daily activities. (0=No; 1=Yes)
  • Difficulty in Movement
  • Boolean
  1. The functional disability due to bone disease is difficulty in movement. (0=No; 1=Yes)
  • Class
  • Integer
  1. Indicates the type of bone disease.(1=Traumatic bone disease; 2=Degenerative bone disease)

Table 5.1.1. Dataset Description

5.1 Methodology

5.1.1. Algorithms

The algorithms which are used for the prediction of bone diseases are Decision Trees (DT), Logistic Regression (LR), Support Vector Machine (SVM), and K-Nearest Neighbor (K-NN). The description of these algorithms is given in the following section.

  1. 1. Logistic Regression (LR):

Logistic regression is a classification and predictive algorithm. LR is used to describe data and to explain the relationship between one dependent binary variable. There are one or more independent variables that determine an outcome. The binary logistic model is used to estimate the probability of a binary response based on one or more predictors. It is used to predict a binary outcome such as, “0” or “1” which may represent “Yes” or “No”, “True” or “false” in a given set of an independent variables.[9]

Logistic Regression Equation is shown in Equation (1) and its respective Sigmoid curve is shown in Fig. 4.2. (1)

  • where S(x) represents Sigmoid function,
  • x represents a real number.

Fig. 5.1.1.1. Logistic Regression Sigmoid Curve

  1. 2. Linear discriminant Analysis (LDA):

LDA is most commonly used as dimensionality reduction technique in the pre-processing step for the pattern-classification and the machine learning applications. The goal is to project a dataset onto a lower-dimensional space with good class separability in order to avoid overfitting and also to reduce the computational costs.

  1. 3. K-Nearest Neighbor (KNN):

The KNN algorithm is a non-parametric method used for classification and regression. The input consists of the k closest training examples in the feature space. The output depends on whether k-NN is used for classification or regression.[7] The K nearest neighbors are measured by a distance function, distance function considered is Euclidean distance.

  1. 4. Decision Trees (DT):

The decision Trees algorithm can be used for solving regression and classification problems. Decision Tree creates the Training model which will be used to predict the class or value of target variables by learning decision rules inferred from the training data.

  1. 5. Naïve Bayes (NB):

The Naive Bayes algorithm is a technique based on Bayes Theorem which is used for classification with an assumption of independence between class predictors. The Naive Bayes classification algorithm assumes that the presence of an exact feature in a class is dissimilar to the presence of any other features. The Naive Bayes algorithm model is easy to implement and useful for large datasets.

Bayes theorem describes the way of calculating posterior probability P(Cx|X) from P(C), P(X), and P(X|Cx) shown in equation (3.1).

  1. 6. Support Vector Machine (SVM):

Support Vector Machine is used for classification and regression analysis.

5.2 Description of process

The implementation can be broadly divided into 6 parts:

  • 1. Dataset: The realtime dataset is collected and split into Test and Training datasets.
  • 2. Efficiency: Summarize the efficiencies of all algorithms.
  • 3. Select: Choose the accurate algorithm that is LR.
  • 4. Logistic Regression (LR): LR predicts bone disease.
  • 5. Response: Generate a response from a set of data instances.
  • 6. Main: It reads the Training Dataset and analyzes it, to predict the newly entered data. It stores the newly entered data in Excel.
  1. Dataset: The real-time dataset is collected and split into Test and Training datasets. The data is in CSV format. We can open the file by using the open function and read the data lines using the reader function in the CSV module. The data is splitted into a training dataset that LR can use to make predictions and the test dataset used to evaluate the accuracy of the model. A ratio of 70/30 for the train/test is a standard ratio used. We define a function called read_csv to load the dataset, with the provided filename and splits it randomly into training and test datasets by using the provided split ratio.
  2. Efficiency: It Summarizes the efficiencies of the algorithms. We have considered a few algorithms like LR, LDA, KNN, DT, NB, and SVM. The Accuracy of the considered algorithms will be determined among which the system selects the most accurate algorithm for prediction of bone diseases. The algorithm’s accuracy are represented in bar graph for better visualization.
  3. Select: Choose the accurate algorithm. By computation of all algorithms, the accuracy of each one is known. From this observation, LR came out to be the more accurate algorithm. Hence, LR is selected as the predicting model as it is more accurate compared to others.
  4. Logistic Regression (LR): LR predicts bone diseases. It uses Euclidean distance measure. LR is used to explain data and to brief the relationship between one dependent binary variable. There are one or more independent variables that determine an outcome. The binary logistic model is used to determine the probability of a binary response based on one or more predictors. It is used to predict a binary outcome such as, “0” or “1” which may represent “Yes” or “No”, “True” or “false” in a given set of independent variables.
  5. Response: The LR Model compares the stored dataset and the newly entered data, based on which the model predicts the type of bone disease that is either Traumatic bone disease or Degenerative bone disease.
  6. Main: It reads the Training Dataset and analyzes it, to predict the newly entered data. It stores the newly entered data in Excel. The dataset is split in the ratio of 70/30, where 70 is Training dataset and 30 is Test dataset. The LR model which is having more accuracy is used to compare the stored dataset with newly entered data. As a result, the type of bone disease that is either Traumatic or Degenerative bone disease is predicted.

6. Testcases

  1. Name of the Bone Disease
  2. Case
  3. Condition
  4. Status
  5. Traumatic

1

  1. Disease Predicted
  2. Display and data entry to the Excel sheet
  3. Degenerative

2

  1. Disease Predicted
  2. Display and data entry to the Excel sheet
  3. Dataset(Age)

1

  1. Age55 years
  2. Degenerative

Table 6.1. Testcases

7. Results

  1. Algorithm
  2. Accuracy
  3. Error rate
  • NB
  1. 0.51
  2. 0.48
  • DT
  1. 0.68
  2. 0.32
  • LR
  1. 0.74
  2. 0.25
  • LDA
  1. 0.46
  2. 0.53
  • SVM
  1. 0.65
  2. 0.34
  • KNN
  1. 0.72
  2. 0.27

Table.7.1. Accuracy and Error rate of Algorithms

The above table specifies the accuracy and error rate of the algorithms. The system checks for the accuracy of the algorithms. As a result, it stores the algorithm which is more accurate and having least error rate compared to others for the further prediction of newly entered Bone Disease data. In our case, LR algorithm is chosen as it having more accuracy and least error rate than others.

Fig.7.2. Comparative performance analysis of models

The above figure shows the comparative performance analysis of models. Accuracy and error rate are considered as the legends of the graph.

Fig.7.1. The Accuracy of all Algorithms

Fig.7.2. The Splitting of Training and Test Data

Fig.7.3. A Simple Login Application

Fig 7.4. Incomplete login

Fig.7.5. Enter Username and Password to login

Fig.7.6. Invalid Username and Password

Fig.7.7. Data entering interface

Fig.7.8. New Patient (Test Data) entry

Fig.7.9. Traumatic Bone Disease

Fig.7.10. New Patient (Test Data) entry

Fig.7.11. Degenerative Bone Disease

Fig.7.12. Description of Bone Disease

8. Conclusions

In this project we consider greater number of features and efficient algorithms to predict bone diseases more accurately. The system evaluates various data mining techniques such as Support Vector Machine, Logistic Regression, Decision Trees, and K-Nearest Neighbor. Through our evaluation, we found that Logistic Regression algorithm gives better accuracy than other data mining algorithms. Hence Logistic Regression algorithm is used for predicting the bone diseases. With the training dataset, we develop a model that predicts the type of bone diseases. The developed Logistic Regression model performs classification and prediction of the test dataset based on the training dataset. The prediction of bone diseases considered in our work are Degenerative and Traumatic diseases.

9. References

  1. Paul D. Miller M.D., “Prediction of Fracture Risk in Postmenopausal White Women With Peripheral Bone Densitometry: Evidence From the National Osteoporosis Risk Assessment†,” Journal of Bone and Mineral Research., published.
  2. Paul Gerdhem, “Biochemical Markers of Bone Metabolism and Prediction of Fracture in Elderly Women†,” Journal of Bone and Mineral Research., published.
  3. Saeko Fujiwara, “Fracture Prediction From Bone Mineral Density in Japanese Men and Women†,” Journal of Bone and Mineral Research., published.
  4. Hui Li, Xiaoyi Li, Murali Ramanathan, and Aidong Zhang, “Prediction and Informative Risk Factor Selection for Bone Disease”, IEEE, DOI 10.1109/TCBB.2014.2330579, 2013.
  5. M Saranya and Dr. K Sarojini, “An Improved and Optimal Prediction of Bone Disease Based on Risk Factors”, IJCSIT, ISSN: 0975-9646, Volume 7(2), 2016.
  6. A Keerthana and Mrs. P Renukadevi, “Predict and Prevent the Bone Disease using Data Mining Techniques”, IJETCSE, ISSN: 0976-1353, Volume 21, Issue 4, APRIL 2016.
  7. Belur V. Dasarathy, ed. (1991). Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques. ISBN 978-0-8186-8930-7.
  8. Data Flair, “SVM – Support Vector Machine Tutorial for Beginners”, Data Flair team, November192018,[Online]. Available: https://data-flair.training/blogs/svm-support-vectormachine-tutorial/ [Accessed: April 14,2019].
  9. JasonBrownlee,MachineLearningMastery,“LogisticRegressionTutorialForMachine Learning”, April 4 2016, [Online].Available:https://machinelearningmastery.com/logisticregression-tutorial-for-machine-learning/[Accessed: April 14,2019].
  10. [Online].Available:https://www.tutorialspoint.com/data_mining/dm_applications_trends.htm.
  11. Accuracy NB DT LR LDA SVM KNN 0.51555599999999957 0.6800000000000006 0.74666699999999997 0.466667 0.65777800000000175 0.72444399999999998 Error rate NB DT LR LDA SVM KNN 0.48444400000000032 0.32000000000000056 0.25333300000000003 0.5333329999999985 0.3422220000000003 0.27555600000000002 2018-19

Effects of Bone Deformities on Muscle Moment Arms: Analytical Essay

1.1 Abstract

In this paper, we try to answer the question which is “How Bone Deformation Effect on Muscle Moment Arm” and showing how that is affect in the motion of human body. By knowing the reasons of these deformations in bones we have an ability to simulate that in the “Solid Work” program. The next step “Effect Bone Deformation on Muscle Moment Arm” is a topic that needs more time and as possible an accurate work to get well results. Here we list some subtopics that could be the next step in this topic:

Make the 3D model of bone that used in the study to be more accurate and with more details, to get more accurate results.

How can this topic have an effect in children growth and its result at the adulthood and motion of human body?

As we know the reasons that cause this defamation, we may know how to treat this issue with high percent of success of treatment.

Study more about the deformation by analyses different bones and joints in the human body.

1.2 Introduction

In our daily life, we do various activities walking, washing, using phone and many more. These movements which are done in a few seconds. But it is a very complex movement in the scientific aspect. These activities are done by cooperating relation between muscles and bones, disturbance of this relation may affect our normal life. That relation can be found in any part of a human body which results in angular motion, rectilinear movement and curve motion. A unique part of human body is having a muscle moment arm, this is usually found in lateral parts that have the major role of our movement activates that make these parts important. Although muscle moment arm is important, the movement is not done without a cooprationing relation with bone. In summary, to have a good movement we consider the state of bone and muscle to be at normal state.

1.3 Objects

In this paper we will talk about some aspects of “Effects of Bone Deformities on Muscle Moment Arms”, and it: Muscle Bone Relation – Muscle Moment Arm – Bone Deformation.

1.4 Previous Investigation

  • “The preceding evidence suggests muscle loads the skeleton to induce bone adaptation. However, there is also evidence that muscle can also be protective of bone loading” [2].
  • “The goal of this paper is to present a rigorous, clear and unambiguous definition of muscle moment-arm” [1].
  • the goal of this paper is describing and understanding the bone characteristics, types of fractures, bone diseases and their treatment [3].

2. Muscle Bone Relation

“Muscle and bone are inextricably linked genetically, molecularly, and mechanically, the intertwining of the connections at the different organizational levels (subcellular, cellular, and sup acellular) makes it difficult to tease out the relative contributions of each connection” [2]

3. Muscle Moment Arm

3.1 Definition of Muscle Moment Arm

At the beginning let’s define the Muscle Moment Arm, what is it?

“In Newton’s second law, the link between the force generated by a muscle and the motion of the system is the muscle moment-arm” [1]. The equation that used to calculate muscle moment arm is:

  • F: Applied Force unit in Newton (N). d= Moment Arm (Lever Arm) which is the perpendicular distance from the force’s line of application the axis of rotation, and its unit is unit of length (m, cm, mm…). T: Moment (Torque) is the mathematical product of applied force and moment arm its unit is (N.m, N.cm, …). For a specific muscle, the moment on each body are computed by isolating each body and considering the forces applied by the muscle on the body, keeping in mind that forces are transmitted through the joints. The total moment is then defined as the sum of the moment created by each force at one of the joints associated with the body. [1]

3.2 Classes of Moment Arms

  • First-Class Lever: The axis of rotation is between applied force and resistive force.
  • Second-Class Lever: The resistive force is between the axis of rotation and applied force.
  • Third-Class Lever: The applied force is between the axis of rotation and resistive force. These classes are shown in figure (1).

Figure (1)

this picture explains a different classis of moment arm.

These classes of moment arm are introducing us to the term Mechanical Advantage. Mechanical advantage (M.A) is describe how relative efficient of the class lever and it is calculated by this equation: Mm / MR. Mm: Moment arm of the muscle force. MR: Moment arm of the resistance force. When 1 > M.A it is a disadvantage mechanical system, 1 < M.A it is an advantage mechanical system.

4. Bone Tissue Structure and Its Physical Characteristics

Bones have two types of tissues (compact) and (spongy) they may also be called either cortical or trabecular, these two types of bones are categorizing that way because of their porosity level [3].

  • location:
  1. 1- cortical: in diaphysis of long bones [3]

Characteristics: 1-cortical: high density and low porosity level between 5% – 10%, it forms the external shield of trabecular bone, consist of 80% of bone mass [3]

  1. 2- spongy bone: low density, very high porosity level (50% – 90%), its 1000 micro-meter and 0.2 micro-meter thick[3].It has no definite structure like cortical, trabeculae do not blood vessel in the central canal, it is task with absorption and transfer energy from joints, it is a total of 20% of bone mass because of its structure that has a larger surface than compact [3].The polymer and minerals are the reason for bone characteristics [3]. Location: at the epiphysis of long bone and in the vertebral bodies and flat bones [3]. Compact bone: the basic of it is osteon, osteon layers are concentric or the thickness of lamella between (3 micro-meter to 7 micro-meter) [3]. Osteocyte is a network that are connected to each other through cytoplasmic extension that occupy tiny canals (canaliculi) that’s used for communication on areas of deformation and are found in ellipsoid lacunae that are found between lamella [3]. Lamellae consist of type 1 collagen and minerals that been deposited in collagen fibres, the fibres have individual lamellae with an orientation and are in parallel position [3].

4.1 Bone tissue characteristics

  1. 1- self-regeneration: (after being injured it heal all tissue in the organism) and adapt to it so that next time it well has a better resistance to mechanical load, we cannot treat it as rigid material but dynamic, that’s why it changes structure constantly [3]. A fully-grown bone (mature) has a certain range of deformation which it remains elastic after a force application [3].

Resistant: compressive > shear

Bone Trauma-Clinical Association

Bone healing is a difficulty process, a lot of factors involved to heal the bone function, different factors determine the healing process ( the mechanics of the organism and Biological factors) . [3]

4.2 Fractures and Their Categorisation

A normal and healthy bone (the cause of fracture): a strong force. A diseased causes change in shape (the cause of fracture): a strong and weak force.

Directed force: a fracture occurs at the spot of force application.

Indirect force: the bone breaks in the weakest spot (lowest resistance) due to a shift [3]. Wolff’s law: shape, and size of bones is determined by direction and magnitude of the acting force.

4.3 Osteoporotic Fractures of the Femur

These types of fractures are the most common in elderly people. The average age of injured people is 75 years [3]. In younger patients, they result from high-energy injuries. 70% of these fractures occur in women. Factors, affecting this ration, are larger tendency to osteoporosis and longer life expectancy than in men. However, it is implied that the main cause for injuries is muscular weakness, paresis, instability due neurological diseases and osteoporosis is only a factor contributing to the injury [3]. At times the bone breaks due to severe osteoporosis when taking an awkward step and the fall results in a fracture. Due to osteoporotic changes in the bone tissue, comminuted fractures often occur [3].

4.4 Bone Tissue Characteristics

Healing bone can be by considering the bone as dynamic tissue because the bone tissue has a special advantage which is the regeneration of the bone structure. that will give us an ability to use Wolf’s law [3]. Mature bone has a range of deformation, but that deformation makes bone still elastic even after applying a force. Bone behaviour is different with different types of loads, bone has the least resistance for shear load and more in compression [3]. The solidity of an individual bone depends on its shape, density, place of force application and speed of force [3]. If a force is applied for a short period of time, the bone will respond to it by increasing its solidity. The final goal of this adjustment is that the bone becomes more resistant to tension and as a result, will be able to absorb more energy before it will give in [3]. Therefore, fractures become comminuted after a sudden increase in force because the force will accumulate within the bone before the bone will give in, besides the bones’ ability to self-regenerate, the bone may also give in, and fractures may result if the material wears out and the frequency of the load exceeds the time frame necessary for bone regeneration and its adjustment to forces, as human body has a variety geometric shapes of bone, have a different solidity in each bone, solidity has some factors that affect the bone solidity like place of force application and speed of force, the relation between bone solidity and force speed, when applying force in short period of time, the bone’s solidity will increase as a result of that [3]. If a force is applied for a short period of time, the bone will respond to it by increasing its solidity [3].

5. Current study

Methodology:

Use Solid Work 2012 to simulate the effect of bone deformation on muscle moment arm.

We download a 3D model of left human femoral bone from Solid Work website figure (2).

Figure (2)

3D model of femur bone

Costume material has been made to satisfy bone mechanical properties, which is provided by Eng. Mohammad Alwahiby.

Apply bending flexion on the object, figure (3).with variation of the angles of deformations as shown in the table below, table(1)

Figure (3)

Bone after apply bending flexion.

In this experiment, we neglect the total body weight, by considering our mechanical system is the femur bone, for resistance force it is considered as the foot and leg weights, as shown in figure of free body diagram.

the foot and leg weight are provided from the references book of 228 and we also neglect femur weight

As an assumption and approximation, we take the value of muscle force is 37N then we measure the moment arm at every change, figure (4).

Figure (4)

Use measure tool to for measure moment arm

we calculate the torque as: 431.458 mm x 37 N = 15963.95 N.mm

Then we calculate the force required at every change in the muscle moment arm due to deformation of the bone. The Psoas major muscle acts as the muscle moment arm in the femur. Force = torque/ Muscle moment arm

  • ∑▒〖M=(Fm×Mm)-(FR×MR)=0〗

Degree of flexion Resistance Moment Arm (mm) Resistance Force (N) Muscle moment arm (mm) Muscle force

(N)

  1. 0 431.458 37 98.287 162.42
  2. 2 431.027 37 98.287 162.25
  3. 4 430.615 37 98.287 162.1
  4. 6 429.968 37 98.287 161.86

Table (1)

5.2 Conclusion

The motion in human body has a several factors that affect their motion, in this paper, we had study about the bone deformation and how it is affect the main factor in every motion is the muscle moment arm. We did a simple and approximation experiment of these two factors in solid work and we found that

We found in the experiment that the muscle force decreases as the resistance moment arm decreases, in other words, the force needed to lift the femoral bone decreases as the angle of curvature increases in the femoral bone.

References

  1. David, I. & Christoph, E. Alain, F. & Alexandre, T. & Philippe, M. (2013). Muscle moment-arms: a key element in muscle-force estimation. Computer Methods in Biomechanics and Biomedical Engineering. 18, 506-513. DOI: https://doi.org/10.1080/10255842.2013.818666
  2. Avin, K.G., Bloomfield, S.A., Gross, T.S. et al. Curr Osteoporos Rep (2015) 13: 1. D.O.E: 4/4/2019. Retrived from: https://link.springer.com/article/10.1007/s11914-014-0244-x
  3. Velnar, T., Bunc, G. and Gradisnik, L. (2015) Fractures and Biomechanical Characteristics of the Bone. Surgical Science, 6, 255-263. http://dx.doi.org/10.4236/ss.2015.66039

Bone Disease Prediction Using Data Mining Techniques: Analytical Essay

Abstract

Data mining is a practice that is performed on large databases for extracting hidden patterns by using combinational approach from statistical analysis, machine learning, and database technology. Further, the medical data mining is an extremely essential research field due to its importance in the development of various applications in flourishing healthcare domain. Diseases and injuries of bones are the major causes of abnormalities of the human skeletal system. The identification of the possibility of bone disease in a person is complicated task for medical practitioners because it requires years of experience and intense medical tests to be conducted. In this work, four data mining classification algorithms namely Decision Trees, Support Machine Vector, Logistic Regression, and K-Nearest Neighbor are used to develop a prediction system in order to analyze and predict the possible type of bone diseases. The main objective of this significant research work is to identify the best algorithm suitable for providing maximum efficiency. Thus, prevention of permanent damage at an earlier stage is possible. The experimental setup has been made for the evaluation of the performance of algorithms with the help of the wealth of health records shared by the patients suffering from various bone diseases. It is found that Logistic Regression algorithm performs the best with 80% precision when compared to other algorithms for bone disease prediction.

Keywords— Algorithm, Bone disease, Data mining, Dataset, Logistic Regression.

I. Introduction

Bone Diseases occur due to abnormalities of one or more factors like the metabolic disorder, genetic disorder, hormonal imbalance, loss of bone mineral density, an endocrine disorder, and nutrition deficiencies. These factors present to the development of bone disease either in the early or later stages of one’s life rely on gender, age, medical condition, family history, and lifestyle.

Various kinds of disorders are:

  • Osteoporosis
  • Paget’s Disease
  • Osteitis fibrosa
  • Rickets
  • Renal Osteodystrophy
  • Osteogenesis imperfecta

Data mining techniques has been utilized in healthcare domain. Medicinal data mining can utilize the uncovered patterns present in huge medical data which otherwise is left undiscovered. Data mining techniques which are useful to medical data consist of association rule mining for finding frequent patterns, prediction, classification, and clustering. Data mining techniques are very useful in predicting bone diseases, heart diseases, breast cancer, lung cancer, diabetes, etc.

II. Bone disease

Bone is the base of our Skeletal System. Bone disease is any of the diseases or injuries that affect human bones. Diseases and injuries of bones are major causes of abnormalities of the human skeletal system.

The types of bone diseases are shown in Table 1

  • Type of Bone Disease
  • Examples
  • Traumatic
  • Fracture or any bone injury
  • Inflammatory
  • Septic and Rheumatoid Arthritis, Synovitis
  • Infective
  • Trauma, Polio
  • Degenerative
  • Degenerative Arthritis
  • Hormonal/Metabolic
  • Rickets or Osteomalacia
  • Bone Tumor
  • Osteochondromas, Chondrosarcoma
  • Congenital
  • Osteogenesis imperfecta, Clubfoot

Table 1: Types of Bone Diseases

This research focuses on predicting two common types of bone diseases:

  • a) Degenerative bone disease
  • b) Traumatic bone disease
  1. a) Degenerative bone disease: It is a condition in which the protective cartilage that cushions the top of bones degenerates or wears down with age. Degenerative bone disease is shown in Fig.1.

Fig.1: Degenerative bone disease

  1. b) Traumatic bone disease: It is a condition in which the bone is damaged due to some trauma or accident. Traumatic bone disease is shown in Fig. 2.

Fig. 2: Traumatic bone disease

III. Literature survey

A very few works have been found related to “Bone Disease Prediction Using Data Mining Techniques”. The dataset, the algorithms, the methodology used by the authors, and the observed results along with the future work is carried out in finding out efficient models of medical diagnosis for various bone diseases.

According to A. Keerthana[3] there are many models to predict and prevent various bone diseases. In the respective research, the author has used oomph models as the openings to the proposed method, then single-layer and multi-layer learning approaches are introduced to construct different disease memories. They have proposed their model focusing on the prediction and educational Risk Factor selection for bone diseases. The author analyzes the performance of the algorithms through evaluation criteria such as sensitivity to skewed class, sensitivity to noisy data, and parameter selection.

Saeko Fujiwara[4], mainly focuses on low bone mineral density, which is the important predictor of future fractures. The authors examined the association of Bone Mineral Density (BMD) with the risk of fracture of the spine or hip among a cohort of 2356 men and women aged 47–95 years, Follow-up averaged 4 years after baseline measurements of BMD that were taken with the use of Dual-energy X-ray Absorptiometry (DXA). The vertebral fracture was assessed using semi-quantitative methods, and the diagnosis of hip fracture was based on medical records. Poisson and Cox regression analysis were the models used.

Paul D. Miller M.D.[5], considers Low Bone Mineral Density (BMD) as a risk factor for fracture. The author studied the relationship between Bone Mineral Density measurements at peripheral sites and subsequent fracture risk at the hip, wrist/forearm, spine, and rib in 149524 postmenopausal women. The test considered T-scores that are the measure of Bone Mineral Density for the prediction. The authors considered BMD measurement, Questionnaires, and Data analysis for the prediction purpose. The authors analyzed the performance of the algorithms through evaluation criteria such as sensitivity and specificity Paul Gerdhem[6], the author studied that different markers of bone turnover predict the fracture in 1040 elderly women. The different markers considered were Serum bone-specific alkaline phosphatase and four different forms of serum osteocalcin (S-OC), and others as markers of bone resorption. They considered Sampling procedures, Bone markers formation, Bone markers resorption, Bone markers urine osteocalcin, and other measurements for the prediction.

Hui Li[7], the author trained an independent model based on a specific group of patients. They considered Comprehensive Disease Memory (CDM), which captures the characteristics for all patients to predict the disease. Bone disease memory (BDM) memorizes the characteristics of those individuals who suffer from bone diseases. Similarly, the Non-Disease Memory (NDM) memorizes attributes for non-diseased individuals. They have used Shallow Restricted Boltzmann Machine and 2-Layer Deep Belief Network for the prediction purpose of M Saranya[8], the author considers that risk factor analysis is the process of finding bone diseases in various stages. The author, in the proposed methodology, analyzed the risk factors in 2 levels. In first level, disease prediction is done with relevancies present in different risk factors and the next level is Deep Belief Network (DBN) Algorithm is applied on 2 specific forecast tasks, they are osteoporosis and bone loss rate.

IV. Dataset

The Dataset is collected from Sun Orthopedic Hospital, Mathikere. It has 29 rows and 2 classes. The dataset description is given in Table 2.

  • Attribute
  • Value
  • Description
  • Name
  • String
  1. Name of the patient
  • Age
  • Integer
  1. Age of patient entered in years
  • Gender
  • Boolean
  1. Yes, if Male. No, if Female.
  • Body
  • Boolean
  1. The region affected due to bone disease is body. (0=No; 1=Yes)
  • Thigh and Knee
  • Boolean
  1. The region affected due to bone disease is thigh & knee. (0=No; 1=Yes)
  • Ankle and Foot
  • Boolean
  1. The region affected due to bone disease is ankle & foot. (0=No; 1=Yes)
  • Lumbous Hip and Hip
  • Boolean
  1. The region affected due to bone disease is lumbous hip & hip. (0=No; 1=Yes)
  • Shoulder and Shoulder Joint
  • Boolean
  1. The region affected due to bone disease is shoulder & shoulder joint. (0=No; 1=Yes)
  • Wrist and Thumb
  • Boolean
  1. The region affected due to bone disease is wrist & thumb. (0=No; 1=Yes)
  • Hand
  • Boolean
  1. The region affected due to bone disease is hand. (0=No; 1=Yes)
  • Leg
  • Boolean
  1. The region affected due to bone disease is leg. (0=No; 1=Yes)
  • Multiple Joint
  • Boolean
  1. The region affected due to bone disease is multiple joint. (0=No; 1=Yes)
  • Lower Back
  1. Boolean
  2. The region affected due to bone disease is lower back. (0=No; 1=Yes)
  • Around Neck
  • Boolean
  1. The region affected due to bone disease is around neck. (0=No; 1=Yes)
  • Spine
  • Boolean
  1. The region affected due to bone disease is spine. (0=No; 1=Yes)
  • Elbow
  • Boolean
  1. The region affected due to bone disease is elbow. (0=No; 1=Yes)
  • Pain
  • Boolean
  1. The symptom that indicates the bone disease is pain in affected region. (0=No; 1=Yes)
  • Buckling
  • Boolean
  1. The symptom that indicates the bone disease is buckling. (0=No; 1=Yes)
  • Weakness in Muscle
  • Boolean
  1. The symptom that indicates the bone disease is weakness in muscle. (0=No; 1=Yes)
  • Swelling
  • Boolean
  1. The sign that indicates the bone disease is swelling. (0=No; 1=Yes)
  • Redness and Sweating
  • Boolean
  1. The sign that indicates the bone disease is redness & Sweating. (0=No; 1=Yes)
  • Itching
  • Boolean
  1. The sign that indicates the bone disease is itching. (0=No; 1=Yes)
  • Ankle Deformality
  • Boolean
  1. The sign that indicates the bone disease is ankle deformality. (0=No; 1=Yes)
  • Feverish due to Pain
  • Boolean
  1. The sign that indicates the bone disease is fever due to pain. (0=No; 1=Yes)
  • Tenderness
  • Boolean
  1. The sign that indicates the bone disease is tenderness. (0=No; 1=Yes)
  • Water Content in Joint
  • Boolean
  1. The sign that indicates the bone disease is water content in joint. (0=No; 1=Yes)
  • Bone Dislocation
  • Boolean
  1. The physical incapacity to do chores due to bone disease is bone dislocation. (0=No; 1=Yes)
  • Difficulty in Doing Daily Activities
  • Boolean
  1. The functional disability due to bone disease is difficulty in doing daily activities. (0=No; 1=Yes)
  • Difficulty in Movement
  • Boolean
  1. The functional disability due to bone disease is difficulty in movement. (0=No; 1=Yes)
  • Class
  • Integer
  1. Indicates the type of bone disease.(1=Traumatic bone disease; 2=Degenerative bone disease)

Table 2: Bone disease dataset

Since the attribute “Name” does not contribute for the purpose of prediction, we have not used it for prediction.

V. Methodology

The algorithms which are used for the prediction of bone diseases are Decision Trees(DT), Logistic Regression(LR), Support Vector Machine(SVM), and K-Nearest Neighbor(KNN). The description of these algorithms is given in the following section.

  1. 1. Decision Trees (DT):

The decision Trees algorithm can be used for solving regression and classification problems. Decision Tree creates a training model which will be used to predict class or value of target variables by learning decision rules inferred from the training data.

  1. Step 1. Place the best attribute of the dataset at the root of the tree.
  2. Step 2. Split the training set into subsets. Subsets should be made in such a way that each subset contains data with the same value for an attribute.
  3. Step 3. Repeat step 1 and step 2 on each subset until you find leaf nodes in all the branches of the tree.

Fig. 3: Pseudocode of Decision Tree

  1. 2. Logistic Regression (LR):

Logistic regression is a classification and predictive algorithm. LR is used to outline data and to describe the connection between one dependent binary variable. There are one or more independent variables that govern the result. The binary logistic model is used to determine the probability of a binary response based on one or more predictors. It is used to predict a binary outcome such as, “0” or “1” which may represent “Yes” or “No”, “True” or “false” in a given set of independent variables.[11]

Logistic Regression Equation is shown in Equation (1) and its respective Sigmoid curve is shown in Fig. 4.(1)

  • where S(x) represents Sigmoid function,
  • x represents real number.

Fig. 4: Logistic Regression Sigmoid Curve

The basic equation for the generalized linear model is shown in Equation (2):

  • g(E(y)) = α + βx1 + γx2 (2)

In the equation,

  • g(): link function
  • E(y): the expected value of the target variable
  • α, β, and γ: merits which are to be predicted
  1. 3. Support Vector Machine (SVM):

Support Vector Machine is utilized for classification and regression analysis. In SVM algorithm, it will design each data item set as a point in n-dimensional space. In this space, n is used for number of features in training dataset and with the value of each feature being the value of a specific coordinate. Then, we achieve classification by finding and constructing the hyper-plane on dataset that divides the dataset into two classes.[10]

  1. candidates = { closest pair from opposite classes }

while there are violating points do

Find a violator

  • candidateSV = candidateSV S violator
  • if any αp < 0 due to addition of c to S then
  • candidateSV = candidateSV/ p
  • repeat till all such points are pruned
  • end if
  • end while

Fig. 5: Pseudocode of Support Vector Machine

  1. 4. K-Nearest Neighbor (KNN):

The KNN algorithm is a non-parametric method utilized for classification and regression. The input contains the k closest training instances in the feature space. The output depends on whether k-NN is used for classification or regression.[9] K nearest neighbors are measured by a distance function, distance function considered is Euclidean distance.

Input: Let K be the number of nearest neighbors and D be the set of training examples.

  1. for each test example, z=(x’,y’) do
  • compute d(x’,x), the distance between z and every example, (x, y) ∈ D
  • select Dz in D, the set of k closest training examples to z.
  1. y’=argmax Σ (xi,yi) ∈ Dz I(v=yi)
  • end for

Fig. 6: Pseudocode of KNN

VI. Results

The results of applying the Decision Trees (DT), Logistic Regression(LR), Support Vector Machine(SVM) and K-Nearest Neighbor(KNN) algorithms is shown in the Table 3.

  • Model
  • Accuracy
  • Error rate
  1. DT
  • 0.68
  • 0.32
  1. LR
  • 0.74
  • 0.25
  1. SVM
  • 0.65
  • 0.34
  1. KNN
  • 0.72
  • 0.27

Table 3: Results

The graph in Fig. 7 shows the comparative performance of the models. The logistic regression (LR) model gives better accuracy than other models.

Fig. 7: Comparative Performance Analysis of models

VII. Conclusion

The health care industry is facing challenges now, and recent development in advanced technologies has broad opportunities for confronting such challenges. In this research, we consider greater number of features of the real-time data and efficient algorithm to predict bone diseases more accurately. The prediction of bone diseases considered in our work is Degenerative and Traumatic bone diseases. The system evaluates various data mining techniques such as Support Vector Machine, Logistic Regression, Decision Trees, and K-Nearest Neighbor. Through our evaluation, we found that accuracy of Logistic Regression algorithm is highest among all the other algorithms. Hence, Logistic Regression algorithm is used for predicting the bone diseases. With the training dataset, we develop a model that predicts the type of bone disease. The developed Logistic Regression model performs classification and prediction of the test dataset based on the training dataset. The experimental result of this work proves that the proposed methodology provides performance improvement than the existing methodologies in terms of more accuracy.

IV. Acknowledgement

We express our sincere gratitude to Sun Orthopedic Hospital and their team for sharing their pearls of wisdom with us during the course of this research.

IX. References

  1. Orthopedic Center of Southern Illinois, Accessed: April 15th, 2019, Available: https://orthocenter-si.com/sites/all/files/images/Knee-arthritis-can-cause-pain-inside-knee.jpg
  2. Christian Nordqvist, December 14th, 2017, Medical News Today, Accessed: April 15th, 2019, Available: https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTSUTzf5fVbRdbiAYbhIvi9Qe5FKVaflCAJgwpFqEKnnDK1OtQY
  3. Paul D. Miller M.D., “Prediction of Fracture Risk in Postmenopausal White Women With Peripheral Bone Densitometry: Evidence From the National Osteoporosis Risk Assessment†,” Journal of Bone and Mineral Research., published.
  4. Paul Gerdhem, “Biochemical Markers of Bone Metabolism and Prediction of Fracture in Elderly Women†,” Journal of Bone and Mineral Research., published.
  5. Saeko Fujiwara, “Fracture Prediction From Bone Mineral Density in Japanese Men and Women†,” Journal of Bone and Mineral Research., published.
  6. Hui Li, Xiaoyi Li, Murali Ramanathan, and Aidong Zhang, “Prediction and Informative Risk Factor Selection for Bone Disease”, IEEE, DOI 10.1109/TCBB.2014.2330579, 2013.
  7. M Saranya and Dr. K Sarojini, “An Improved and Optimal Prediction of Bone Disease Based on Risk Factors”, IJCSIT, ISSN: 0975-9646, Volume 7(2), 2016.
  8. A Keerthana and Mrs. P Renukadevi, “Predict and Prevent the Bone Disease using Data Mining Techniques”, IJETCSE, ISSN: 0976-1353, Volume 21, Issue 4, APRIL 2016.
  9. Belur V. Dasarathy, ed. (1991). Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques. ISBN 978-0-8186-8930-7.
  10. Data Flair, “SVM – Support Vector Machine Tutorial for Beginners”, Data Flair team, November 19, 2018, [Online]. Available: https://data-flair.training/blogs/svm-support-vector-machine-tutorial/ [Accessed: April 14, 2019].
  11. Jason Brownlee, Machine Learning Mastery, “Logistic Regression Tutorial For Machine Learning”, April 4, 2016, [Online]. Available:https://machinelearningmastery.com/logistic-regression-tutorial-for-machine-learning/ [Accessed: April 14, 2019].

Essay on Bone Cancer

Cancer involves the uncontrolled division of the body’s cells, which cancer can cause in any tissue of the body, and each type of cancer has its own unusual characteristics. Cancer begins when a cell breaks free from conventional restrictions on cell division and begins to require motivation to proliferate. “All the cells conveyed by division of this to start with, genetic cell and its descendant in addition appear uncivilized proliferation” (Cho, Y. J., Cho, Y. M., Kim, S. H., Shin, K. H., Jung, S. T., & Kim, H. S. (2019). Bone cancer may well be an outstandingly unprecedented be that as it may powerful shape of cancer that in or around the bones, cancer makes over time interior body. A tumor, or mass of cells, molded of these odd cells may remain interior the tissue in which it begun (a condition called in situ cancer), or it may start to assault adjoining tissues (a condition called invasive cancer). Fundamental bone tumor may be a tumor that appears up inside the bone tissue itself and is liberal or unsafe (bone cancer). Kind (noncancerous) tumors are more common than bone cancers. When cancer happens in bone, the cancer happens in bone (like fundamental bone cancer), or it happens in other parts and after that exchanges to bone (metastasis or assistant metastasis to cancer). An invasive tumor is said to be perilous, and cells shed into the blood or lymph from a hurtful tumor are likely to set up unused tumors metastases all through the body. Tumors debilitate a person’s life when their improvement disrupts the tissues and organs required for survival.

Clarification on Bone Cancer

Bone cancer can happen in each human bone, but it as a run the show happens inside the long bones of the upper members and lower members of individuals. A couple of sorts of bone malignancies are known, some impact the children, others basically impact developed-ups (Mayo Clinic, 2015, page 1). There are five differing sorts of bone cancer that can impact individuals from ages 10-60 a long time antiquated. Bone cancer can happen in any bone inside the body from the legs to the head. The signs of bone cancer are not always obvious. For the most part, the main symptom is suffering. Osteosarcoma, also known as osteogenic sarcoma, occurs in people between the ages of 10 and 30. It is the first common sort of bone cancer and routinely starts in bone cells inside the arms, legs or pelvis. Ewing’s tumor, as well known as Ewing’s sarcoma, is the third most common shape of basic bone cancer routinely starts inside the bones, but it may as well outline in other tissues and muscles. T Ewing’s tumors happen most frequently in children and youths and is once in a whereas seen in developed-ups over the age of 30. Fibrosarcoma and undermining fibrous histiocytoma routinely makes inside the sensitive tissue around the bones, such as tendons, ligaments, fat or muscle. These sorts of bone cancer besides tend to happen in more prepared developed-ups. Chondrosarcoma is another sort of bone cancer. It more regularly than not makes inside the cartilage of the pelvis, upper parcel of legs and arms, and the bear. Chondrosarcoma impacts individuals from ages 50-60 a long time antiquated. Ewing’s sarcoma may be a bone cancer that’s known to start in adolescent nerve tissue inside the bone marrow. It attacks the pelvis, femur, and tibia It tends to be a direct-creating tumor with a moo risk of spreading to evacuated locales, but it may return at the primary area in case not removed completely in the midst of surgery. Chordoma may as well unavoidably spread to the lungs, liver or lymph nodes.

Signs and Diagnosis of Bone Cancer

Signs of bone cancer can join torment, swelling and delicacy close the impacted locale, debilitated bones driving to break, shortcoming, unintended weight hardship (Mayo Clinic 2018). A physical exam which incorporates point by point evaluation of family history is the essential step in p the diagnosis of bone cancer. The taking after step is to accumulate blood and urine test to choose the levels of two enzymes called alkaline phosphatase and dehydrogenase. These enzymes in tremendous entireties are a sign of bone cancer. Finally, imaging tests such as X-Bar, bone scan, CT and MRI are performed. The preeminent conclusive test in diagnosing bone cancer may be a bone biopsy in which tissue from the tumor is taken outline a extend interior the bone and analyzed underneath an amplifying instrument.

Treatment Options for Bone Cancer

Cancer treatment options can consolidate surgery, chemotherapy, radiation therapy, cryosurgery, and targeted therapy. Surgery is the ordinary treatment for bone cancer. The pro evacuates the total tumor. Chemotherapy livelihoods solid antagonistic to-cancer drugs, as a run the show passed on through a vein intravenously, to kill cancer cells. Radiation therapy is regularly utilized a few times as of late an operation since it can draw back the tumor and make it less requesting to empty. This, in turn, can offer help diminish the likelihood that evacuation will be crucial. t is used after surgery to kill any remaining cancer cells. Clinical trials are in addition a magnificent way cancer understanding get cutting edge medications or up and coming treatments, such as immunotherapy and vaccines, that target certain sorts of cancers without any charge to the calm. Cancer treatments are especially expensive and these clinical trials bear individuals with obliged assets a chance to urge cutting edge medications, and treatment from world prominence masters like the NIH, Mayo Clinic and Cancer Centers of America.

Conclusion

In conclusion, cancer reasonable does not affect peace, but it affects your family, work colleagues or anyone you interact with. It really can be an overwhelming, life-changing attraction. The key to your survival is to stay positive, taking one day at a time, keeping God first, with your family and friends, keeping them together with your treatment and the therapeutic results of your treatment. Finding a bunch of specialists or craftsmen that you simply can accept and consider the choices made for you should be your claims advocate to become a vigorous participant in your treatment options and care plans. It works. I experienced it, starting with my mother’s hands.