Published Paper Details:

- A worldwide increase in lifestyle-related diseases (such as diabetes, cardiovascular disease, hypertension and obesity) is associated with unhealthy lifestyles (e.g., sedentary behavior, poor dietary habits and increased stress levels). Early identification of these types of diseases can improve the outcomes of treatment and reduce long-term healthcare costs. Traditional diagnosis approaches use clinical testing as the primary means of identifying these diseases and generally, identify them after they have advanced or reached a More severe state based on symptoms. This research proposes an artificial intelligence (AI) and machine learning (ML) framework to assess and predict disease using lifestyle data. The application provides assessments of various parameters of an individual's lifestyle (such as physical activity, sleep, eating habits, stress levels and substance use) and finds patterns among those parameters that increase an individual's risk of developing a certain disease. Using predictive algorithms such as logistic regression, decision trees and random forest, predictive models are developed to classify individuals into categories. This approach is to create a preventative healthcare approach by delivering interventions before symptoms reach a severe state. Experimental results show that these predictive models using lifestyle data can generate highly accurate and reliable results, which makes them suitable for use in health care facilities or through wearable technologies .