Robust and Explainable Bicuspid Aortic Valve Diagnosis Using Stacked Ensembles on Echocardiography
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913124073865216 |
|---|---|
| author | Nikolaidis, Christos Chrysanthos Sachpekidis, Vasileios Moustakidis, Nikolas Moustakidis, Theofilos Efraimidis, Pavlos S. |
| author_facet | Nikolaidis, Christos Chrysanthos Sachpekidis, Vasileios Moustakidis, Nikolas Moustakidis, Theofilos Efraimidis, Pavlos S. |
| contents | Transthoracic echocardiography (TTE) is the first-line imaging modality for diagnosing bicuspid aortic valve (BAV), yet diagnostic performance varies with operator expertise and image quality. We developed an explainable AI model that distinguishes BAV from tricuspid aortic valves (TAV) using routinely acquired parasternal long-axis (PLAX) cine loops. A multi-backbone video ensemble was trained and evaluated using a leakage-aware, stratified outer cross-validation protocol on $N{=}90$ patient studies (48 BAV, 42 TAV). Across fixed outer splits and 10 random seeds, the calibrated stacked ensemble achieved an outer-CV F1-score of $0.907$ and recall of $0.877$. Frame-level Grad-CAM localized salient evidence to the aortic root and leaflet plane, while globally aggregated SHAP values quantified each video backbone's contribution to the stacked prediction, enabling transparent, case-level auditability. These findings indicate that PLAX-based video ensembles can support reliable BAV/TAV classification from routine echocardiographic cine loops and may facilitate earlier detection in non-specialist or resource-limited clinical settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13730 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Robust and Explainable Bicuspid Aortic Valve Diagnosis Using Stacked Ensembles on Echocardiography Nikolaidis, Christos Chrysanthos Sachpekidis, Vasileios Moustakidis, Nikolas Moustakidis, Theofilos Efraimidis, Pavlos S. Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Transthoracic echocardiography (TTE) is the first-line imaging modality for diagnosing bicuspid aortic valve (BAV), yet diagnostic performance varies with operator expertise and image quality. We developed an explainable AI model that distinguishes BAV from tricuspid aortic valves (TAV) using routinely acquired parasternal long-axis (PLAX) cine loops. A multi-backbone video ensemble was trained and evaluated using a leakage-aware, stratified outer cross-validation protocol on $N{=}90$ patient studies (48 BAV, 42 TAV). Across fixed outer splits and 10 random seeds, the calibrated stacked ensemble achieved an outer-CV F1-score of $0.907$ and recall of $0.877$. Frame-level Grad-CAM localized salient evidence to the aortic root and leaflet plane, while globally aggregated SHAP values quantified each video backbone's contribution to the stacked prediction, enabling transparent, case-level auditability. These findings indicate that PLAX-based video ensembles can support reliable BAV/TAV classification from routine echocardiographic cine loops and may facilitate earlier detection in non-specialist or resource-limited clinical settings. |
| title | Robust and Explainable Bicuspid Aortic Valve Diagnosis Using Stacked Ensembles on Echocardiography |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.13730 |