ABSTRACT
Aim: The purpose of this chapter is to educate clinicians and healthcare professionals on the value of healthcare analytics. This chapter demonstrates how the analysis of health data, such as blood cholesterol, blood pressure, smoking, and obesity, can identify high-risk heart attack patients, and how the proactive changes in these high-risk patient lifestyles and use of medication can prevent a heart attack from taking place.
Methods: The logistic regression model was used to build a coronary heart disease (CHD) risk factor model. The dataset had 4,240 patients, and four types of risk factors were investigated (demographic, behavior, medical history, and risk factors from first examination).
Results: The accuracy of the coronary heart disease risk model was determined using a confusion matrix. Seven hundred sixty-three patients out of 1,097 patients were classified correctly as not having a risk of CHD or having a risk of CHD. Five out of 15 risk factors were identified as CHD indicators. Age was the most important risk factor, followed by male patients, blood pressure, blood glucose, and cigarettes per day.
Conclusion: Data analytical techniques, particularly machine learning techniques and logistic regression model, are valuable for clinicians, as these techniques can accurately identify which patients are high-risk CHD patients, allowing clinicians to provide earlier patient diagnosis and treatment, thereby reducing patient risk of CHD or preventing them from getting a heart attack.
