Related Experiment Video
Updated: Jul 28, 2025
A Simplified Stepwise Approach to Echo Guidance during Percutaneous Mitral Valve Repair
Published on: October 16, 2021
Machine learning vs. conventional methods for prediction of 30-day readmission following percutaneous mitral
Samian Sulaiman1, Akram Kawsara1, Abdallah El Sabbagh2
1Division of Cardiology, West Virginia University, Morgantown, WV, United States of America.
Background:
Identifying predictors of readmissions after mitral valve transcatheter edge-to-edge repair (MV-TEER) is essential for risk stratification and optimization of clinical outcomes.
Aims:
We investigated the performance of machine learning [ML] algorithms vs. logistic regression in predicting readmissions after MV-TEER.
Methods:
We utilized the National-Readmission-Database to identify patients who underwent MV-TEER between 2015 and 2018. The database was randomly split into training (70 %) and testing (30 %) sets. Lasso regression was used to remove non-informative variables and rank informative ones. The top 50 informative predictors were tested using 4 ML models: ML-logistic regression [LR], Naive Bayes [NB], random forest [RF], and artificial neural network [ANN]/For comparison, we used a traditional statistical method (principal component analysis logistic regression PCA-LR).
Results:
A total of 9425 index hospitalizations for MV-TEER were included. Overall, the 30-day readmission rate was 14.6 %, and heart failure was the most common cause of readmission (32 %). The readmission cohort had a higher burden of comorbidities (median Elixhauser score 5 vs. 3) and frailty score (3.7 vs. 2.9), longer hospital stays (3 vs. 2 days), and higher rates of non-home discharges (17.4 % vs. 8.5 %). The traditional PCA-LR model yielded a modest predictive value (area under the curve [AUC] 0.615 [0.587-0.644]). Two ML algorithms demonstrated superior performance than the traditional PCA-LR model; ML-LR (AUC 0.692 [0.667-0.717]), and NB (AUC 0.724 [0.700-0.748]). RF (AUC 0.62 [0.592-0.677]) and ANN (0.65 [0.623-0.677]) had modest performance.
Conclusion:
Machine learning algorithms may provide a useful tool for predicting readmissions after MV-TEER using administrative databases.
Insights
Machine learning models show promise in predicting 30-day readmissions after mitral valve transcatheter edge-to-edge repair (MV-TEER). Algorithms like Naive Bayes and ML-logistic regression outperformed traditional methods, aiding in patient risk stratification.
Area of Science:
- Cardiology
- Medical Informatics
- Health Services Research
Background:
- Predicting readmissions after mitral valve transcatheter edge-to-edge repair (MV-TEER) is crucial for patient care.
- Identifying key predictors aids in risk stratification and optimizing outcomes.
Purpose of the Study:
- To compare the predictive performance of machine learning (ML) algorithms against traditional logistic regression for MV-TEER readmissions.
- To identify optimal ML models for predicting post-MV-TEER readmissions using administrative data.
Main Methods:
- Utilized the National Readmission Database (2015-2018) for patients undergoing MV-TEER.
- Applied Lasso regression for variable selection, testing 4 ML models (ML-LR, Naive Bayes, RF, ANN) and PCA-LR.
- Split data into 70% training and 30% testing sets.
Main Results:
- Included 9,425 index hospitalizations; 30-day readmission rate was 14.6%, with heart failure as the primary cause.
- ML-logistic regression (AUC 0.692) and Naive Bayes (AUC 0.724) significantly outperformed traditional PCA-LR (AUC 0.615).
- Readmitted patients had higher comorbidity and frailty scores, longer stays, and more non-home discharges.
Conclusions:
- Machine learning algorithms demonstrate superior ability in predicting 30-day readmissions post-MV-TEER compared to traditional methods.
- ML models offer a valuable tool for risk stratification using large administrative databases.
- Further development of ML tools can enhance clinical decision-making for MV-TEER patients.
