Applying Multiple Regression Analyses to Compare the Regression Predicted and Originally Calculated CVD/Stroke Risk Probabilities Using Medical Condition and Lifestyle Detail Scores as Inputs over a 10-year Period for a type 2 Diabetes Patient Based on GH-Method: Math-Physical Medicine (No. 546)

Abstract

In the author’s previous medical research reports, he mainly applied physics theories, engineering models, mathematical equations, computer big data analytics and artificial intelligence (AI) techniques, as well as some statistical approaches to explore and interpret various biophysical phenomena. However, the majority of medical research papers he has read thus far are primarily based on statistics. As a result, in this article, he selects some basic statistical tools, such as correlation, variance, p-values, and multiple regression analyses, to study the predicted CVD/Stroke risk probability as the output (dependent variable) by using his medical condition and lifestyle detail scores as inputs (independent variables). Since 1/1/2012, the author has been collecting various data related to his health (~3 million data) which includes 4 categories of medical conditions, obesity, diabetes, hypertension, and hyperlipidemia (m1 through m4), along with 6 categories of lifestyle details, including exercise, water intake, sleep, stress, food, and daily life routines (m6 through m10). However, due to the limitation of his learned knowledge in earlier years, the data from 2012-2013 is incomplete; therefore, the scores in this study for the initial period of 2012-2013 are his best-guessed data based on an incomplete dataset. Previously, he has researched and published a few articles regarding the risks of having CVD/Stroke based on his metabolism index (MI). In this paper, he will compare his previously calculated CVD risks based on the MI method versus the newly calculated CVD risks based on multiple regression analysis methods. In this study, he will not repeat the detailed introduction of the regression analysis in the Method section because it is available in many statistics textbook. It should be noted that in regression analysis, the correlation coefficient R should be > 0.5 or 50% to indicate a strong inter-connectivity and the p-value should be <0.05 to be considered as statistically significant.