Machine Learning and Bioinformatics for Diagnosis Analysis of Obesity Spectrum Disorders

Globally, the number of obese patients has doubled due to sedentary\nlifestyles and improper dieting. The tremendous increase altered human\ngenetics, and health. According to the world health organization, Life\nexpectancy dropped from 80 to 75 years, as obese people struggle with different\nchronic diseases. This report will address the problems of obesity in children\nand adults using ML datasets to feature, predict, and analyze the causes of\nobesity. By engaging neural ML networks, we will explore neural control using\ndiffusion tensor imaging to consider body fats, BMI, waist \\& hip ratio\ncircumference of obese patients. To predict the present and future causes of\nobesity with ML, we will discuss ML techniques like decision trees, SVM, RF,\nGBM, LASSO, BN, and ANN and use datasets implement the stated algorithms.\nDifferent theoretical literature from experts ML \\& Bioinformatics experiments\nwill be outlined in this report while making recommendations on how to advance\nML for predicting obesity and other chronic diseases.\n