CardioCLIP: sequential multimodal prediction of echocardiographic abnormalities and natriuretic peptide elevation from electrocardiogram and chest radiographs.
AI can predict heart function changes flexibly from multiple tests in any order, matching how doctors actually practice medicine.
Diagnostic reasoning in clinical practice is inherently sequential and multimodal, with physicians integrating heterogeneous examinations under constraints such as missing data and variable test order. CardioCLIP demonstrated the feasibility of order-flexible sequential multimodal prediction.
What the study was
- Study design
- Diagnostic or model validation study
- Population
- The model was trained on 9458 patients from a single tertiary centre and evaluated for B-type natriuretic peptide (BNP), left ventricular ejection fraction (LVEF), and E / e '.
- Sample size
- 9458
- Category
- Diagnostics
- Maturity
- Validated
- Journal
- Eur Heart J Digit Health
Why it surfaced
Diagnostic or model validation study with a PubMed abstract reviewed; the 7/10 score reflects conservative novelty, relevance, design-quality, and population/unmet-need assessment.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.