Key result
Cardioverse-BAV AI platform on cardiac CT detected Type 0-BAV with 99.2% accuracy and 94.6% recall in external validation, outperforming TTE recall of 13.5%.
Why the study?
The study aimed to develop an AI platform for population-wide Type 0-bicuspid aortic valve screening using ECG-gated cardiac CT without requiring specialized radiologists.
Does the Cardioverse-BAV AI platform applied to ECG-gated cardiac CT improve the diagnostic detection of Type 0-bicuspid aortic valve compared to transthoracic echocardiography and standard confirmation methods?
Observational (n=18,662)
Yes
Does the Cardioverse-BAV AI platform applied to ECG-gated cardiac CT improve the diagnostic detection of Type 0-bicuspid aortic valve compared to transthoracic echocardiography and standard confirmation methods?
The Cardioverse-BAV deep learning platform accurately detects Type 0-bicuspid aortic valve on ECG-gated cardiac CT with 99.2% accuracy and significantly higher recall than transthoracic echocardiography (94.6% vs 13.5%), enabling effective population-wide screening.
Answers are grounded in this paper and cite their sources.
Supports AI-CT screening for Type 0-BAV over TTE; leaves open outcome benefits and need for prospective trials before adoption.
Background We developed Cardioverse-BAV, an AI platform for population-wide Type 0-bicuspid aortic valve (BAV) screening. It leverages ECG-gated cardiac CT (CTA) while circumventing its need for specialized radiologists. Methods Derived from the Three-Province transcatheter aortic valve replacement (TAVR) Registry, Cardioverse-BAV platform leverages a deep learning model trained on 1156 core lab-confirmed ECG-gated CTAs from 1156 TAVR patients. The development set was randomly assigned to training and internal test sets at a 7:3 ratio. Its diagnostic performance was validated in an external surgical aortic valve replacement (SAVR) cohort from a Hospital University between Jan 2018 and Sept 2025 (n=736 with both preoperative ECG-gated CTA and surgical confirmation) and a large-scale cohort receiving screening coronary CTA and transthoracic echocardiography (TTE) (n=16,770) from two tertiary hospitals between Jan 2020 and Aug 2025. Results In the internal test set, Cardioverse-BAV platform accurately predicted BAV (AI model: 32.2% vs. core lab: 30.0%), achieving weighted aggregated scores as follows: accuracy 98.9%, recall 96.7%, specificity 100%, precision 100%, and F1-score 98.3%. In external test sets, the AI model identified BAV in 5.3% of cases, outperforming TTE (2.4%) and comparable to surgical confirmation (5.0%). It achieved 99.2% accuracy, with recall of 94.6%, specificity of 99.4%, precision of 89.7%, and F1-score of 92.1%. Compared to TTE, the AI model showed a significant improvement in recall (+81.1%, P < 0.001), achieving 94.6% recall vs. 13.5% for TTE. While its specificity (99.4%) was slightly higher than TTE (98.1%), the difference did not reach statistical significance (P = 0.999). In a cohort of 16,770 patients, ECG-gated CTA identified BAV in 1.3% of cases versus 0.4% by TTE (P < 0.001), with weak agreement between methods (kappa = 0.193). Conclusion The Cardioverse-BAV platform is a tool for BAV diagnosis with the potential to enhance early detection, as evidenced by its validation in multiple distinct cohorts.
No takes yet. Share an insight, caveat, or question.
Hu et al. (2026) conducted an observational in Type 0-bicuspid aortic valve (BAV) (n=18,662). Cardioverse-BAV AI platform on ECG-gated cardiac CT vs. Core lab CTA confirmation, surgical confirmation, and transthoracic echocardiography (TTE) was evaluated on Diagnostic recall (sensitivity) for Type 0-bicuspid aortic valve (BAV) detection in external validation (p=<0.001). Cardioverse-BAV AI platform on cardiac CT detected Type 0-BAV with 99.2% accuracy and 94.6% recall in external validation, outperforming TTE recall of 13.5%.
Synapse has enriched 10 related papers. Consider them for comparative context: