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 Replacement: Multicenter Cohort Study
BackgroundCurrently, there is a paucity of literature addressing personalized risk stratification using multimodal data in patients with symptomatic aortic stenosis and heart failure with preserved ejection fraction (HFpEF) following transcatheter aortic valve replacement (TA...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2025-05-01
|
| Series: | Journal of Medical Internet Research |
| Online Access: | https://www.jmir.org/2025/1/e70587 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850196369133797376 |
|---|---|
| author | Jun Wang Jiajun Zhu Hui Li Shili Wu Siyang Li Zhuoya Yao Tongjian Zhu Bi Tang Shengxing Tang Jinjun Liu |
| author_facet | Jun Wang Jiajun Zhu Hui Li Shili Wu Siyang Li Zhuoya Yao Tongjian Zhu Bi Tang Shengxing Tang Jinjun Liu |
| author_sort | Jun Wang |
| collection | DOAJ |
| description |
BackgroundCurrently, there is a paucity of literature addressing personalized risk stratification using multimodal data in patients with symptomatic aortic stenosis and heart failure with preserved ejection fraction (HFpEF) following transcatheter aortic valve replacement (TAVR).
ObjectiveThis study aimed to enhance the performance of risk assessment models in this patient population by developing a predictive model for adverse outcomes using various machine learning (ML) techniques.
MethodsThis multicenter cohort study included 326 patients diagnosed with severe AS and HFpEF who underwent TAVR between January 2017 and December 2023. Patients were allocated to training (n=195) and independent validation (n=131) sets based on hospital affiliation. A dual-phase feature selection process, combining least absolute shrinkage and selection operator logistic regression and the Boruta algorithm, was used to identify relevant variables from the multimodal dataset. A total of 5 ML model-decision trees, K-nearest neighbors, random forest, support vector machine, and extreme gradient boosting were used to construct a visualization and explainable predictive framework to elucidate model decision-making processes.
ResultsThe primary features identified included age, N-terminal pro-brain natriuretic peptide, fasting blood glucose, triglyceride/high-density lipoprotein cholesterol ratio, triglyceride glucose index, triglyceride glucose-BMI index, atherogenic index of plasma index, and Apolipoprotein B. Among the 5 models, the support vector machine demonstrated the best predictive performance for major adverse cardiovascular and cerebrovascular events in patients with severe AS and HFpEF following TAVR, achieving an area under the curve of 0.756 (95% CI 0.631-0.881) in the independent validation set. The model exhibited good calibration and robust predictive power in both training and validation sets and demonstrated the highest net benefit in decision curve analysis compared to other models. To extract significant variables influencing the algorithm and ensure model appropriateness, we interpreted cohort and personalized model predictions using Shapley Additive Explanations values.
ConclusionsOur 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. |
| format | Article |
| id | doaj-art-c43acbd377554e5fa49bbbd702b49272 |
| institution | OA Journals |
| issn | 1438-8871 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | Journal of Medical Internet Research |
| spelling | doaj-art-c43acbd377554e5fa49bbbd702b492722025-08-20T02:13:27ZengJMIR PublicationsJournal of Medical Internet Research1438-88712025-05-0127e7058710.2196/70587Multimodal 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 Replacement: Multicenter Cohort StudyJun Wanghttps://orcid.org/0000-0002-7863-0331Jiajun Zhuhttps://orcid.org/0009-0006-0714-8579Hui Lihttps://orcid.org/0009-0004-9579-1921Shili Wuhttps://orcid.org/0000-0002-6656-8884Siyang Lihttps://orcid.org/0009-0009-8093-931XZhuoya Yaohttps://orcid.org/0000-0002-4336-7713Tongjian Zhuhttps://orcid.org/0000-0002-7932-4950Bi Tanghttps://orcid.org/0000-0001-6059-6713Shengxing Tanghttps://orcid.org/0000-0003-2700-5728Jinjun Liuhttps://orcid.org/0009-0009-1799-2708 BackgroundCurrently, there is a paucity of literature addressing personalized risk stratification using multimodal data in patients with symptomatic aortic stenosis and heart failure with preserved ejection fraction (HFpEF) following transcatheter aortic valve replacement (TAVR). ObjectiveThis study aimed to enhance the performance of risk assessment models in this patient population by developing a predictive model for adverse outcomes using various machine learning (ML) techniques. MethodsThis multicenter cohort study included 326 patients diagnosed with severe AS and HFpEF who underwent TAVR between January 2017 and December 2023. Patients were allocated to training (n=195) and independent validation (n=131) sets based on hospital affiliation. A dual-phase feature selection process, combining least absolute shrinkage and selection operator logistic regression and the Boruta algorithm, was used to identify relevant variables from the multimodal dataset. A total of 5 ML model-decision trees, K-nearest neighbors, random forest, support vector machine, and extreme gradient boosting were used to construct a visualization and explainable predictive framework to elucidate model decision-making processes. ResultsThe primary features identified included age, N-terminal pro-brain natriuretic peptide, fasting blood glucose, triglyceride/high-density lipoprotein cholesterol ratio, triglyceride glucose index, triglyceride glucose-BMI index, atherogenic index of plasma index, and Apolipoprotein B. Among the 5 models, the support vector machine demonstrated the best predictive performance for major adverse cardiovascular and cerebrovascular events in patients with severe AS and HFpEF following TAVR, achieving an area under the curve of 0.756 (95% CI 0.631-0.881) in the independent validation set. The model exhibited good calibration and robust predictive power in both training and validation sets and demonstrated the highest net benefit in decision curve analysis compared to other models. To extract significant variables influencing the algorithm and ensure model appropriateness, we interpreted cohort and personalized model predictions using Shapley Additive Explanations values. ConclusionsOur 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.https://www.jmir.org/2025/1/e70587 |
| spellingShingle | Jun Wang Jiajun Zhu Hui Li Shili Wu Siyang Li Zhuoya Yao Tongjian Zhu Bi Tang Shengxing Tang Jinjun Liu 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 Replacement: Multicenter Cohort Study Journal of Medical Internet Research |
| title | 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 Replacement: Multicenter Cohort Study |
| title_full | 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 Replacement: Multicenter Cohort Study |
| title_fullStr | 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 Replacement: Multicenter Cohort Study |
| title_full_unstemmed | 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 Replacement: Multicenter Cohort Study |
| title_short | 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 Replacement: Multicenter Cohort Study |
| title_sort | 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 replacement multicenter cohort study |
| url | https://www.jmir.org/2025/1/e70587 |
| work_keys_str_mv | AT junwang multimodalvisualizationandexplainablemachinelearningdrivenmarkersenableearlyidentificationandprognosispredictionforsymptomaticaorticstenosisandheartfailurewithpreservedejectionfractionaftertranscatheteraorticvalvereplacementmulticentercohortstudy AT jiajunzhu multimodalvisualizationandexplainablemachinelearningdrivenmarkersenableearlyidentificationandprognosispredictionforsymptomaticaorticstenosisandheartfailurewithpreservedejectionfractionaftertranscatheteraorticvalvereplacementmulticentercohortstudy AT huili multimodalvisualizationandexplainablemachinelearningdrivenmarkersenableearlyidentificationandprognosispredictionforsymptomaticaorticstenosisandheartfailurewithpreservedejectionfractionaftertranscatheteraorticvalvereplacementmulticentercohortstudy AT shiliwu multimodalvisualizationandexplainablemachinelearningdrivenmarkersenableearlyidentificationandprognosispredictionforsymptomaticaorticstenosisandheartfailurewithpreservedejectionfractionaftertranscatheteraorticvalvereplacementmulticentercohortstudy AT siyangli multimodalvisualizationandexplainablemachinelearningdrivenmarkersenableearlyidentificationandprognosispredictionforsymptomaticaorticstenosisandheartfailurewithpreservedejectionfractionaftertranscatheteraorticvalvereplacementmulticentercohortstudy AT zhuoyayao multimodalvisualizationandexplainablemachinelearningdrivenmarkersenableearlyidentificationandprognosispredictionforsymptomaticaorticstenosisandheartfailurewithpreservedejectionfractionaftertranscatheteraorticvalvereplacementmulticentercohortstudy AT tongjianzhu multimodalvisualizationandexplainablemachinelearningdrivenmarkersenableearlyidentificationandprognosispredictionforsymptomaticaorticstenosisandheartfailurewithpreservedejectionfractionaftertranscatheteraorticvalvereplacementmulticentercohortstudy AT bitang multimodalvisualizationandexplainablemachinelearningdrivenmarkersenableearlyidentificationandprognosispredictionforsymptomaticaorticstenosisandheartfailurewithpreservedejectionfractionaftertranscatheteraorticvalvereplacementmulticentercohortstudy AT shengxingtang multimodalvisualizationandexplainablemachinelearningdrivenmarkersenableearlyidentificationandprognosispredictionforsymptomaticaorticstenosisandheartfailurewithpreservedejectionfractionaftertranscatheteraorticvalvereplacementmulticentercohortstudy AT jinjunliu multimodalvisualizationandexplainablemachinelearningdrivenmarkersenableearlyidentificationandprognosispredictionforsymptomaticaorticstenosisandheartfailurewithpreservedejectionfractionaftertranscatheteraorticvalvereplacementmulticentercohortstudy |