Medical Artificial Intelligence Observation

NB: We do not resell your papers. Upon ordering, we do an original paper exclusively for you.

NB: All your data is kept safe from the public.

Abstract

Medical Artificial Intelligence (MAI) regularly uses computer techniques for clinical diagnosis and treatment recommendations. AI has the ability to detecting meaningful relationships in a dataset and has been widely used to diagnose, cure, and predict responses in many clinical situations. In our paper focus on discussing the rule-based system in disease diagnosis as an expert system that is an application of MAI. Where AI methodologies have demonstrated great abilities and capabilities in recognizing meaningful data patterns and thus have been commonly experimented as tools for medical studies, in specific to help decision-making about diagnoses and subsequent treatments for every step, as well as prognoses and predictions.

System, Disease Diagnosis

I. Introduction

We can clearly see the great development that occurred in the industry and the tremendous rise in population growth rates, which was directly reflected in the environment, where we note that the rates of environmental pollution have increased recently, and therefore the spread of diseases and epidemics increased, which made it difficult for doctors to diagnose and treat. As a result of the increasing number of patients, it is difficult for doctors to work accurately and quickly on diagnosis and treatment, especially in severe cases and epidemics. This is due to several reasons, the most important of which are fatigue, lack of experience, or seizures, towards dangerous cases. Hence the need for artificial intelligence in the medical field.

Artificial Intelligence (AI) means to make computer perform some tasks by adding humans’ intelligent simulations in their system to be capable to do some humans work. It is defined by Kok et al. (2002) as systems that think like humans, systems that act like humans, systems that think rationally, and systems that act rationally. AI in the medical field used to analyzes complex medical data, when it coded correctly it can be used in virtually every medical field due to his ability to make meaningful relationships within a dataset, better handling of huge information, low error rate as relative to humans and unbelievable accuracy and speed which can be used in many medical fields like drug development, disease diagnosis, health monitoring, digital consultation, managing medical date, analysis of health plans, personalized treatment, surgical treatment and medical treatment (Naveen et al, 2019 & Amisha et al, 2019). And in this paper we will focus on using AI in disease diagnosis.

There are several applications for medical artificial intelligence such as expert systems, machine learning, data mining, and image processing. Medical artificial intelligence reveals the great potential and expectations of applying AI techniques to realistic clinical practices and empirical medical informatics, in particular, the following areas:

AI Techniques in Medicine
Medical Expert Systems
Data Mining in Medicine
Machine Learning-Based Medical Systems

This paper summarizes some applications of Medical Expert Systems with a special emphasis on the rule-based expert system within the last several years. Expert Systems (ESs) is an intelligent computer program using knowledge and inference to solve a problem that is complex enough to require considerable human expertise to solve it. ESs consists of three main components: the knowledge base, Inference engine, and User interface which has the ability to mimic, judge, and justify on the basis of some rules given to it (Durkin, 1994; Gath & Kulkarni, 2012). In this paper, we will focus on the rule-based expert system as a type of expert system in the medical field.

The rule-based system defined as a way of encoding a human expert’s knowledge in a fairly narrow area into an automated system by Gath & Kulkarni (2012). As the following in the paper, we will discuss in part II the issue of this paper, in part III the literature review about medical expert systems, in part IV the methodology of the rule-based system, in part V the result of using the rule-based system in disease diagnosis and finally part VI including the conclusion.

II. Issue

The insufficient medical professional in most developing countries has raised the mortality rate of patients suffering from various diseases. TheMlack of medical specialists may never be overcome in a short span of time. Furthermore, higher education institutions should take urgent steps to produce doctors to be able to able to deal with the increasing numbers of patients as a lot of them already died while waiting for students to become doctors and doctors to become specialists. Current high-risk diseases required patients to seek consultation for diagnosis and treatment from a specialist such as the Covid-19 virus. Sometimes medical doctors may not have sufficient expertise to deal with complex or new diseases so we need to use computer technology which can help to reduce the number of errors in disease diagnosis so we can reduce the number of deaths. Computer programs or software developed by emulating human intelligence could be used to help the doctors make decisions without straightforwardly consulting the experts. This software was not designed to replace the experts or doctors, yet it was designed to assist general physicians and experts in the diagnosis and prediction of patient conditions from certain rules or experiences. In this paper, we will suggest using the rule-based export system as an application of artificial intelligence in human diseases diagnosis.

III. Literature Review

Expert systems are widely used in almost all fields of human expertise that will help users to make decisions where human expatriation and multifaceted decision-making are required, like medical diagnosis, monitoring, financial decision-making, planning and policy-making, strategic assessment, analysis (Gath & Kulkarni, 2012).

Medical artificial intelligence is concerned with developing AI programs that perform diagnosis and offering recommendations for treatment. Medical Expert Systems (MESs) are used mainly in clinical laboratories and educational environments, for clinical observation, or in data-rich areas such as intensive care. What is now being realized is that intelligent programs that offer significant benefits if they fill up with the appropriate rules (Shortliffe, 1993). Medical export systems have been used in full swing since the early 1970s when MYCIN was developed to diagnose bacteria that caused serious infections Stanford University was founded to assist physicians in the diagnosis and treatment of patients with infectious blood diseases caused by bacteremia (bacteria in the blood) and meningitis (a bacterial disease- causing inflammation of the brain and spinal cord underlying membranes).

These illnesses can be lethal if they are not quickly diagnosed and treated. The system was developed in the mid-1970s, and it took about 20 years to be completed. MYCIN is a Rule-Based Expert system (RBES) that uses backward chaining and comprises around 500 rules. The system was written using Interlisp which is an environment built to support programming language Lisp (liebowitz, 1997). There is a lot of medical expert systems such as PUFF (RBES) the system started to work since1979 it uses the existence and extent of pulmonary diagnosis for diagnosis and provides reports for the patient’s records it doesn’t involves direct contact with a physician. ANGY (RBESs) for Automated Coronary Vessel Segmentation from Remote Subtracted Angiograms helps physicians diagnose coronary vessel narrowing by recognizing and isolating coronary vessels in angiograms (Giarratano et al., 2005).

A collection of rules can be used to capture the domain knowledge of a human expert, which used to replicate the problem solving of the expert in that domain . RBES contain both artificial intelligence (AI) techniques such as knowledge-based systems (KBSs) and traditional techniques, such as database management systems (DBMSs) (Russell & Norvig, 2002). DBMSs are used in used in medical expert systems to store, retrieve, and generally manipulate patient data, while ESs are mainly used to conduct patient data-based diagnoses because they can naturally reflect the way experts think and provide the solution to the problem at hand (Mahesh, 2009). RBES is used to diagnosis the following diseases such as malaria, typhoid fever, cholera, breast cancer, tuberculosis, and other diseases (Adewole et al., 2015).

IV. Methodology

The rule-based expert system is an expert system that contains a set of knowledge that is generally represented as a set of rules and facts that are used to explain specific patterns in which data are collected and evaluated using those rules. If the rules are logically satisfied, the pattern is identified, and a problem associated with that pattern is suggested after the deduction process and each particular problem might require specific treatment.

The rule-based approach uses IF-THEN type rules: if it is living then it is mortal. A typical rule-based system includes four basic components (Adewole et al., 2015; Grosan & Abraham 2011);

1. A list of rules base, which is a specific type of knowledge base which contains the rules necessary for the completion of its task.

2. An inference engine matches rules to data to derive its conclusions in which infers information or takes action based on the interaction of input and the rule base. The interpreter executes a production system program by using the following recognize-act cycle consist of four stages;

Match the condition patterns in the rules against the elements in the working memory to identify the set of satisfied rules.
If there is more than one rule that can be executed, then use a Conflict Resolution strategy to choose which one to apply. If no rules are applicable, then stop or terminate.
Apply the chosen rule, which may result in modifying the working memory by adding new items, or in deleting old ones.
Check if the terminating condition is fired. If it is, then stop. Otherwise, return to the beginning. The termination condition can either be defined by a goal state, or by some kind of time limitation (as an example: a maximum number of cycles).

3. A user interface enables the user to query the system input information and receive the advice.

4. Database Consists of predicate calculus facts in the knowledge base which fit the IF sections of the rules.

5. Explanation subsystem Analyzes and describes the system’s logical process to the user, which gives the user the ability to ask about the structures about how a decision was drawn, or the evidence used.

6. Knowledge engineer it’s normally an AI-trained computer scientist who works with an application expert to portray the expert’s applicable information in a way that can be incorporated into the knowledge base.

7. Knowledge acquisition subsystem the thorough knowledge base checks and updates for potential contradictions and missing details.

We can replace the manual method of diagnosing the diseases with an expert system which is able to correct all the limitations related to the manual method (Djam et al., 2011).

V. Result

The rule-based expert system as an application of artificial intelligence allows organizations to safe the informations that help the employees to arrive to the best accuracy of diagnosis disease. It minimize errors because massive, repetitive or vital tasks are automated. It reduce the time needed to check the system and analyze the data and reduce costs by accelerating up the detection of faults, it also help in eliminate the work that people shouldn’t west time on it (such as tasks that are complex, time-consuming, or prone to error, jobs where training needs are high or expensive). It facilitate the decision making process and it provide knowledge collection, method analysis, data analysis, and system, verification. It improved visibility of managed system status .

So instead of manual methods that lead to inaccuracy in diagnosing the disease caused by the physicians exhaustion or from a panic attack in serous situations and from new physicians who do not have enough experience, also in times of epidemic manual method may lead to increase the spread of the disease among the medical staff and by the increasing numbers of affected patients the pressure increase so we can use the rule- based expert system to help in the process of diagnosis disease with accurate way and save imported information to help physicians at any time.

VI. Conclusion

It is obvious that the rule-based expert system as an application of artificial intelligence is an adequate methodology for all medical dominions and tasks for the following reasons cognitive adequacy, clear experience, and subjective knowledge automatic acquisition of subjective knowledge and system integration. The rule-based expert system provides an important technology for the creation of an insightful diagnostic decision support system that can greatly help improve physician decision-making and is developed and tested to overcome the various challenges of the conventional disease diagnostic process.

References

Adewole, K. S., Hambali M. A., and Jimoh M. K. (2015), “RULE-BASED EXPERT SYSTEM FOR DISEASE DIAGNOSIS”, Proceedings of the International Conference on Science, Technology, Education, Arts, Management and Social Sciences, Ilorin.
Amisha, Malik, P., Pathania, M. and Rathaur, V. K. (2019), “Overview of artificial intelligence in medicine”, Journal of Family Medicine and Primary Care, Wolters Kluwer ‑ Medknow.
Djam, X. Y., Wajiga, G. M., Kimbi, Y. H., and Blamah, N. V. (2011), “A Fuzzy Expert System for the Management of Malaria”, International Journal of Pure Apply Science Technology, 5(2), 84-108.
Durkin, J. (1994), “Expert System: Design and Development”, Macmillan Publishing Company Inc, New York.
Gath, S. J. and Kulkarni, R. V. (2012), “A Review: Expert System for Diagnosis of Myocardial Infarction”, International Journal of Computer Science and Information Technologies (IJCSIT), 3 (6).
Giarratano, J. and Riley, G. (2005), “Expert Systems: Principles and Programming, Fouth Edition”, Canada.
Grosan, C. and Abraham, A. (2011) “Intelligent Systems a Modern Approach”, Springer Intelligent Systems Reference Library , Vol 17, 154-176.
Kok, J. N., Boers, E. J. W., Kosters, W. A., Putten, P. V. D. and Poel, M. (2002), “ARTIFICIAL INTELLIGENCE: DEFINITION, TRENDS,TECHNIQUES, AND CASES”, Knowledge for sustainable development: an insight into the Encyclopedia of life support Encyclopedia of Life Support Systems, UNESCO publishing.
Liebowitz, J. (1997), “The Handbook of APPLIED EXPERT SYSTEMS”, CRC Press, 66-67.
Mahesh, V., Kandaswamy, A., and Venkatesa, R. (2009), “Telecardiology for Rural Health Care”, International Journal of Recent Trends in Engineering, 2(3).
Naveen, G., Naidu, M. A., Rao, B. T. and Radha, k. (2019), “A Comparative Study on Artificial Intelligence and Expert Systems”, International Research Journal of Engineering and Technology, Vol 6.
Russell, S. and Norvig, P. (2002), “Artificial Intelligence: A Modern Approach, Second Edition”, Prentice Hall.
Shortliffe, E.H. (1993), “The adolescence of AI in medicine: will the field come of age in the ’90s?” Artif Intell Med, 5(2), 93-106.
Tomar, P. P. S., Singh, R., and Saxena, P. K. (2012), “MULTIMEDIA BASED DECISION SUPPORT SYSTEM FOR MEDICAL DIAGNOSIS OF OCCUPATIONAL CHRONIC LUNG DISEASES”, Narosa Publishing House, India.

Click Here To Order Now!