AI-Driven Analysis of Lifestyle Patterns for Early Detection of Metabolic Disorders
Keywords:
Convergence, Medical Electronics, Consumer Electronics, Data Analysis, Artificial Intelligence, Early Detection, Disease Prevention, Diabetes, Wearable Electronics, Heart Rate Monitoring, SpO2, Location Tracking, Skin Impedance, Lifestyle Patterns, Pre-Diabetic State, Fasting Glycemia, AI-Driven Analysis, Statistical Analysis, Urban Mobility, Behavior Quantification.Abstract
Convergence of medical and consumer electronics, as well as data analysis techniques such as artificial intelligence, allows early detection and prevention of diseases such as diabetes. Using custom-designed wearable electronics to monitor heart rate, SpO2, location, and skin impedance continuously over more than a year allows the detection of changes in lifestyle patterns coinciding with serious modifications in physiology related to the pre-diabetic state several months before fasting glycemia exceeds the 125 mg/dL diagnostic threshold. The recorded data reveal differences in lifestyle patterns between individuals who exhibited major versus small normal-to-pre-diabetic transitions, allowing a preliminary AI-driven statistical analysis of pre-diabetic indicators. Additionally, urban mobility, the intake of both food and drink, and sleep efficiency were identified and quantified as the most indicative types of behavior in this context.
