Circadian rhythms, governed by core clock genes (e.g., CLOCK-BMAL1) and synchronized by light-dark cycles, regulate systemic physiology, including metabolism, immune response, and cellular repair. Disruptions in these 24-hour cycles are implicated in diverse diseases-including diabetes, cancer, neurodegenerative disorders, and cardiovascular events-with time-dependent “chronorisk windows” driving adverse outcomes. This study aims to systematically investigate population-level variations in circadian rhythms and their associations with diverse disease risks and health outcomes. Leveraging an interdisciplinary approach, we will develop deep learning frameworks to integrate multimodal data sources-including electronic health records (EHRs), environmental exposures, wearable device metrics, and medical imaging-to precisely characterize individual circadian patterns and predict associated health risks.
This research holds transformative implications for understanding circadian mechanisms and their clinical applications. Through multimodal data integration, healthcare providers and individuals may achieve early detection of circadian disruption patterns, enabling precision health strategies that could substantially reduce disease incidence and mortality through timely interventions. By advancing our understanding of the mechanistic links between circadian rhythms and diverse pathologies, this work aims to: (1) elucidate fundamental circadian regulatory principles governing systemic physiology; (2) establish validated circadian biomarkers for disease susceptibility across populations; and (3) inform next-generation predictive models and chronotherapeutic protocols. These insights will catalyze the development of AI-driven tools for personalized circadian monitoring and evidence-based guidelines for optimizing lifestyle/therapeutic timing, ultimately bridging circadian biology to actionable preventive medicine.
