Review reveals clinical benefits and implementation hurdles of artificial intelligence in cardiometabolic care, highlighting the need for real-world validation and explainable models.
Optimising cardiometabolic health is a global priority given the high morbidity and mortality rates of cardiometabolic conditions. The rapid digitalisation of healthcare has catalysed the integration of artificial intelligence (AI) and digital health innovations into cardiometabolic care. While these innovations demonstrate strong clinical potential, they have yet to fully transcend traditional intervention paradigms. Synthesising evidence from recent systematic reviews, meta-analyses, randomised clinical trials, and observational studies, this comprehensive review evaluates the current landscape of digital health in cardiometabolic care. We highlight the evolving capabilities of AI in outperforming traditional risk models, extracting high-dimensional patterns from multimodal data, and powering clinical decision support systems through electronic medical records integration. Although these technologies successfully promote patient engagement, improve clinical outcomes, and enhance healthcare access, sustained implementation faces significant challenges. Inequality in digital health access, data privacy, algorithmic bias, and generalisability across diverse demographics need to be addressed. Taken together, to realise the transformative potential of these tools in prevention and treatment, future investments must prioritise (1) rigorous, real-world validation, (2) the adoption of Explainable AI (XAI), and (3) robust regulatory frameworks to optimise their clinical and population health impact.
No takes yet. Share an insight, caveat, or question.
Tiong et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: