LIGHTS: The Northern Lighthouse Predicting and Preventing Cardiometabolic Diseases

Cardiometabolic diseases, including type 2 diabetes and its associated complications, remain among the leading causes of morbidity, mortality, and healthcare costs globally. Despite advances in diagnostics and therapeutics, clinical decision-making often follows a “one-size-fits-all” model. To transform this paradigm, we propose a concerted initiative to leverage artificial intelligence (AI) and multimodal data integration to predict, prevent, and personalize care for cardiometabolic disease.

Our aim
A key strength of our approach lies in the opportunity to develop, test, and validate models using existing cohorts, such as the DD2 cohort: a nationwide, longitudinal resource with deep phenotyping, lifestyle information, medication history, and long-term outcomes. Rather than generating new data, our focus is on combining complementary expertise across clinical, technical, and analytical domains to unlock the full potential of already available, high-quality data sources. Building on this foundation, we aim to drive progress in the following areas:

Predictive modeling of long-term complications
Patient stratification for personalized care planning
Decision support tools for clinicians and patients
Multimodal data integration across clinical and molecular domains
Health economic value through targeted prevention
Real-world implementation with transparency and fairness

Our Vision 

We envision establishing a Danish flagship initiative in AI-driven cardiometabolic research — combining cutting-edge analytics with national-scale data and a focus on real-world impact. What sets our approach apart is not the generation of new data, but our ability to unlock untapped value in existing, richly phenotyped cohorts through interdisciplinary collaboration across clinical, technical, and analytical domains. This integration enables a new level of insight, where disease trajectories and treatment outcomes can be predicted, personalized, and supported in practice.