Kane, Garvan

Abstract Echocardiography is the most widely used cardiac imaging modality, yet artificial intelligence-enabled interpretation remains limited by the inability of existing models to integrate visual assessment, quantitative measurement, and clinical reasoning within a unified framework. Here we present EchoAtlas, the first autoregressive vision-language model developed for echocardiographic interpretation. Trained on over 12.9 million question-answer pairs derived from approximately 2 million echocardiogram videos, EchoAtlas achieves 0.966 accuracy on multiple-choice questions in our internal test set and establishes a new state-of-the-art on the public MIMIC-EchoQA benchmark (0.699 vs. 0.508 previously). EchoAtlas also provides accurate quantitative measurements, segment-level regional wall motion assessment, longitudinal comparison, and diagnostic reasoning across diverse question formats — capabilities not previously demonstrated in this domain. These results highlight the potential of autoregressive vision-language models as a foundation for interactive echocardiographic interpretation, representing an early step toward scalable, auditable artificial intelligence systems in cardiology practice.

Calf muscle pump (CMP) promotes venous return from the lower extremity and contributes to preload and cardiac output. Impaired CMP function may reflect a measure of frailty or cumulative disease burden or may impede cardiac function. The study objective was to test the hypothesis that impaired CMP negatively impacts survival. Consecutive adult patients who underwent venous strain gauge plethysmography at the Mayo Clinic Gonda Vascular Laboratory (January 1, 1998 – December 31, 2011) were assessed for overall survival. Patients with venous incompetence, venous obstruction or unilateral calf pump dysfunction were excluded. Risk of mortality was assessed with Cox proportional hazard ratios and after adjusting for Charlson Comorbidity Index variables. Over the study period, 2728 patients were included in the analysis. Compared to patients with normal CMP, those with impaired CMP were older ( p < 0.001), predominantly female ( p = 0.01) and had higher mean Charlson scores ( p < 0.001). Patients with impaired CMP had a higher mortality rate at 5 (8.9% vs 2.4%), 10 (17.5% vs 5.9%), and 15 years (22.8% vs 8.3%) compared to those with normal CMP ( p < 0.001 for each comparison). Of patients with heart failure, those with impaired CMP had worse survival at each 5-year increment compared to those with normal CMP ( p < 0.05 at each increment). In conclusion, impaired CMP appears to be an independent predictor of poor outcomes after adjusting for variables within the Charlson Comorbidity Index. The association between impaired CMP, heart failure, and mortality may represent a negative impact on circulatory function or a surrogate measure of frailty.