Supervised Learning for Early Detection of Chronic Diseases
Using Wearable and Other Health Data in NHANES
Impact StatementLeveraging supervised machine learning models to analyze wearable and medical data for early detection of pre-diabetes.
AbstractWith the rise of fitness trackers, identifying meaningful patterns is crucial for detecting early indicators of chronic diseases such as pre-diabetes mellitus. This approach leverages wearable and other health data from the National Health and Nutrition Examination Survey (NHANES) to develop a Supervised Learning (SL) framework that detects pre-diabetes mellitus symptoms using hypertension, sleep and physical activity measurements from wearables. Exploratory analysis is conducted for data preprocessing and visualization, and several benchmark SL methods are explored. This study provides a data-driven approach for early detection of chronic diseases, leading to effective behavioral changes, improved patient outcomes and a healthier society.