This prospective cohort study aims to develop and validate a personalized disease risk prediction model for adults by integrating multiple sources of health data. The study will recruit community-dwelling adults aged 18 years and older in Taiwan. After providing informed consent, participants will complete a structured questionnaire, undergo pure tone hearing testing, and wear a smartwatch for 2 weeks to collect continuous physiological data, including heart rate and physical activity. With participant authorization, the study will also collect data from personal health records and national health insurance databases to allow longer-term follow-up of health outcomes. The main goals of the study are to examine the relationships among hearing, lifestyle factors, and wearable device data; to identify combinations of risk factors associated with progression from health to subclinical or chronic disease states; and to develop analytical methods for integrating heterogeneous health data from questionnaires, physiological monitoring, hearing tests, and medical databases. Machine learning methods will be used to identify important predictors and build risk prediction models. The study hypothesis is that combining hearing measures, lifestyle information, wearable physiological data, and longitudinal medical record data will improve the ability to identify individuals at higher risk of future disease compared with using a single source of information alone. The long-term objective is to support early risk identification, personalized health management, and prevention strategies in community adults.
See this in plain English?
AI-rewrites the medical criteria so a patient or caregiver can understand them. Always confirm with the trial site.
Performance of Personalized Disease Risk Prediction Models
Timeframe: At the completion of data collection and model validation, including baseline assessment and 2-week wearable monitoring