Obesity and Coronary Heart Disease

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.

Table of Contents

Introduction
Exposure Variable and Disease
Relative Risk
Confounding Variables
High Cholesterol
Possible Sources of Bias
Conclusion
References

Introduction

The study about obesity, cholesterol, and coronary heart disease (CHD) explores several factors and looks at the relationship between them to find connections between the conditions. It has exposure variables and confounding variables that affect the authors’ conclusions. Moreover, it may have potential sources of bias that the researchers have to address to avoid making false assumptions and presenting unsupported or skewed results.

Exposure Variable and Disease

In the case of the chosen hypothetical study, the exposure variable is obesity. An exposure variable is a type of variable that can affect the study outcome. As the researchers measure the correlation between a person having obesity and being diagnosed with coronary heart disease (CHD), the influence of obesity on CHD is the exposure variable. For example, Lassale et al. (2018) and Riaz et al. (2018) conducted similar investigations exploring the relationship between obesity and CHD. In this study, the disease under investigation is CHD, as this is the outcome that the researchers predict may or may not happen due to the influence of other factors.

Relative Risk

The relative risk of an event occurring refers to the probability that one outcome happens compared to the likelihood of another outcome happening. As shown in Table 1, the researchers have collected data about the rate of obesity and CHD in the chosen group. To calculate relative risk, one may use this data and perform the following steps:

Divide the number of events occurring in people with the exposure variable by the sum of all people with the exposure variable in the selected population;
Divide the number of events occurring without the exposure variable by the sum of all people without the exposure variable in the selected population;
Divide the first number by the second one.

Table 1. Data Collected During the Study

	CHD	No CHD
Obese	79	745
Not Obese	286	8290

Applying the described formula, one can get the following calculation: relative risk = (79 / (79 + 745)) / (286 / (286 + 8290)). The result, shortened to two decimal places, is 2.87. The probability of the event occurring is much higher than one, meaning a significant difference in the chances of the event happening for the two selected groups (Tenny & Hoffman, 2022). This number implies that the relative risk of people with obesity being diagnosed with CHD is almost three times higher than those without obesity. For example, if one looks at the rate of CHD diagnosis in the separate groups, people with obesity obtained with diagnosis in almost 10% of all cases. At the same time, the CHD rate among individuals without obesity is about 3.3%. Thus, one can see the difference in the percentages and the connected relative risk findings.

Confounding Variables

Confounding variables describe various events and characteristics that may influence the study results. For example, they may skew the findings, showing unfair or untrue numbers (Tyagi, 2021). While many confounding variables may exist for the selected study, the difference in group sizes is the most apparent. There are 824 people with obesity in the study, while the researchers were able to find 8574 individuals without obesity. Therefore, the second group is larger than the first one by about ten times. Having such different population sizes may change the outcomes of the study as people with obesity are much less represented, demonstrating less variety and increasing the risk of misrepresenting the entire population segment. It is possible that including more people with obesity in the sample could change the relative risk and lead to different conclusions.

Another possible confounding variable is the individual aspects of the sample. For example, the participants’ age, gender, occupation, and other characteristics are not defined or discussed. In particular, people’s age may play a significant role in their well-being, as comorbidities and health problems are more prevalent among older adults than younger people (Oneglia et al., 2020). Moreover, relating to heart conditions, cardiovascular diseases disproportionately affect older adults, which should be considered when discussing research conclusions. At the same time, gender may also play a vital role in one’s heart health (Oneglia et al., 2020). This and other variables must be acknowledged to make the study’s findings more reliable.

High Cholesterol

The information about cholesterol in the study can be considered a confounding variable because it shows the uneven presence of comorbidities in the two sample segments. Among people with obesity, 106 people have high cholesterol, which constitutes almost 13% of the segment: ((55 + 51) / (55 + 51 + 24 + 694) * 100= 12.86. At the same time, much less than 1% of all people not classified as obese have high cholesterol: ((5 + 5) / (5 + 5 + 281 + 8285) * 100 = 0.12. Therefore, the rate of high cholesterol is overrepresented in one sample and underrepresented in another. For high cholesterol not to be a confounding variable, it should be equally distributed among the groups to ensure that it does not affect the results in a meaningful way.

The discrepancy between the two sample groups may affect the results, as the connection between obesity and CHD becomes confounded with the link between CHD and cholesterol levels. According to the calculations, people with high cholesterol are much more likely to be diagnosed with CHD. When using the connection between high cholesterol and the diagnosis of CHD, the relative risk is 15.74: (60 / (60 + 56)) / (305 / (305 + 8979)). Therefore, one cannot state that the selection of the sample does not skew the study’s findings, as the relative risk is much higher than that linked to obesity.

Possible Sources of Bias

The study’s design increases the risk of two potential bias types – selection bias and confirmation bias. First, as shown above, the sample groups of people diagnosed and not diagnosed with obesity are not equal, which affects the results and can lead to conclusions that would not be confirmed if the sample sizes were equal (Smith, 2020). Such a difference in results constitutes selection bias – a problem where researchers consciously or accidentally form sample groups that underrepresent or overrepresent certain characteristics that impact the final outcome. Similarly, the use of cholesterol level measurements can further contribute to the effect of selection bias, as there are more people with obesity and high cholesterol among participants.

Second, the risk of confirmation bias may exist in the study. It is necessary to see the hypotheses made by researchers and their conclusions to establish whether this type of bias is present. Nevertheless, one may assume that the choice of samples and their differing numbers demonstrate that the authors did not approach the selection process with the required vigor. The limited information about conclusions, however, makes it challenging to confirm the presence of this bias in the study.

Conclusion

The study findings under investigation analyze the connection between obesity and coronary heart disease (CHD). The research shows a relative risk of 2.87 for people with obesity to be diagnosed with CHD. However, the authors underrepresent the sample of people with diabetes in relation to individuals without diabetes. Moreover, they do not account for several confounding variables that may affect the interpretation of the findings. The researchers’ focus on cholesterol also reveals a potential point of selection bias.

References

Lassale, C., Tzoulaki, I., Moons, K. G., Sweeting, M., Boer, J., Johnson, L., Huerta, J. M., Agnoli, C., Freisling, H., Weiderpass, E., Wennberg, P., van der A., D. L., Arriola, L., Benetou, V., Boeing, H., Bonnet, F., Colorado-Yohar, S. M., Engström, G., Eriksen, A. K., … Butterworth, A. S. (2018). Separate and combined associations of obesity and metabolic health with coronary heart disease: A pan-European case-cohort analysis. European Heart Journal, 39(5), 397-406.

Oneglia, A., Nelson, M. D., & Merz, C. (2020). Sex differences in cardiovascular aging and heart failure. Current Heart Failure Reports, 17(6), 409-423.

Riaz, H., Khan, M. S., Siddiqi, T. J., Usman, M. S., Shah, N., Goyal, A., Khan., S., Mookadam, F., Krasuski, R., & Ahmed, H. (2018). Association between obesity and cardiovascular outcomes: A systematic review and meta-analysis of Mendelian randomization studies. JAMA Network Open, 1(7), e183788.

Smith, L. H. (2020). Selection mechanisms and their consequences: Understanding and addressing selection bias. Current Epidemiology Reports, 7(4), 179-189.

Tenny, S., & Hoffman, M. R. (2022). Relative risk. National Library of Medicine. Web.

Tyagi, N. (2021). What are confounding variables? Effects and controlling. Analytic Steps. Web.

Click Here To Order Now!