Abstract
AIMS: Biological age is increasingly recognized as a superior predictor of morbidity, mortality, compared with chronological age. Artificial intelligence (AI)-driven ageing clocks enable rapid, non-invasive assessment. Cardiovascular (CV) ageing is of particular relevance given its central role in systemic metabolic health. This study evaluated the clinical utility of an ultrasound (US)-based CV biological age clock derived from handheld point-of-care ultrasound (POCUS), in comparison with haematological and electrocardiographic (ECG)-based clocks. METHODS AND RESULTS: We analysed 243 adults (median age 62 years; 54% women) from the Sheba Healthspan Research Population (SHARP) study. Ultrasound-based CV age was estimated using focused cardiac POCUS with AI software. Blood age was calculated using the SenoClock platform from 45 routine biomarkers, and ECG age was derived using a convolutional neural network trained on >770 000 tracings. Correlations with chronological age and inter-clock agreement were examined. Participants were stratified into quintiles of US delta (US-chronological age). All three clocks correlated with chronological age (blood: r = 0.89, US: r = 0.74, ECG: r = 0.61; all P < 0.001). US-accelerated agers (top quintile) displayed a more adverse cardiometabolic profile, including higher diastolic blood pressure, body mass index, waist circumference, triglycerides, alongside lower HDL cholesterol, and more than double the prevalence of metabolic syndrome. Those with US age ≥2 years above chronological age had significantly higher odds of metabolic syndrome (odds ratio = 2.34, 95% confidence interval: 1.07-5.17, P = 0.034). CONCLUSION: AI-derived ultrasound-based cardiovascular biological age from handheld POCUS is associated with prevalent metabolic syndrome in this cross-sectional cohort, even when routine focused POCUS shows no abnormalities warranting referral.