Multimodal Visualization and Explainable Machine Learning–Driven Markers Enable Early Identification and Prognosis Prediction for Symptomatic Aortic Stenosis and Heart Failure With Preserved Ejection Fraction After Transcatheter Aortic Valve Replacem
Our ML-based multimodal model, incorporating 8 readily accessible predictors, demonstrated robust predictive capability for 12 months of major adverse cardiovascular and cerebrovascular events risk. This model can be used to identify high-risk individuals with AS and HFpEF following TAVR, potentially aiding in risk stratification and personalized treatment strategies.
Authors
- Jinjun Liu
- Tongjian Zhu (ORCID: https://orcid.org/0000-0002-7932-4950)
- Bi Tang (ORCID: https://orcid.org/0000-0001-6059-6713)
- Jun Wang (ORCID: https://orcid.org/0000-0002-7863-0331)
- Siyang Li
- Shengxing Tang (ORCID: https://orcid.org/0000-0003-2700-5728)
- Shouling Wu (ORCID: https://orcid.org/0000-0002-6656-8884)
- Jiajun Zhu (ORCID: https://orcid.org/0009-0006-0714-8579)
- Hui Li (ORCID: https://orcid.org/0009-0000-9778-2456)
- Zhuoya Yao (ORCID: https://orcid.org/0000-0002-4336-7713)
Institutions
- Wannan Medical College (CN)
- Xinjiang Medical University (CN)
- Bengbu Medical College (CN)
- First Affiliated Hospital of Xinjiang Medical University (CN)
- Bozhou People's Hospital (CN)
- Xiangyang Central Hospital (CN)
- First Affiliated Hospital of Bengbu Medical College (CN)
- First Affiliated Hospital of Wannan Medical College (CN)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-05-01
- DOI
- https://doi.org/10.2196/70587
- Citations
- 9
- Primary Topic
- Cardiac Valve Diseases and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 12.49