Related Experiment Videos
Prediction of 1-year mortality after heart transplantation using machine learning approaches: A single-center study
Ying Zhou1, Si Chen1, Zhenqi Rao1
1Department of Cardiovascular Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
Insights
Machine learning models predict heart transplant (HTx) survival. The Random Forest model shows high accuracy, identifying high-risk patients for personalized care and reducing organ waste.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- Heart transplantation (HTx) is the standard treatment for end-stage heart failure.
- Accurate prognosis assessment is crucial for optimizing patient outcomes.
- Machine learning offers novel approaches for predictive modeling in healthcare.
Purpose of the Study:
- To develop and validate a machine learning-based risk prediction model for 1-year mortality after heart transplantation.
- To identify key predictors of post-transplant mortality.
- To enhance personalized treatment strategies for HTx recipients.
Main Methods:
- Utilized data from 381 consecutive orthotopic heart transplant recipients (2015-2018).
- Employed Least Absolute Shrinkage and Selection Operator (LASSO) for variable selection.
- Developed and compared seven machine learning models, including Random Forest (RF) and Gradient Boosting Machine (GBM), with bootstrap validation.
- Applied Shapley Additive exPlanations (SHAP) for model interpretability.
Main Results:
- Albumin, recipient age, and left atrium diameter were the most significant predictors of 1-year mortality.
- The Random Forest (RF) model achieved the highest discrimination, with an Area Under the Curve (AUC) of 0.801.
- Gradient Boosting Machine (GBM) demonstrated the best sensitivity (0.271).
- SHAP analysis provided individual-level insights into RF model predictions.
Conclusions:
- A validated machine learning risk-prediction model for heart transplantation prognosis was successfully established.
- The RF model exhibits superior predictive performance for 1-year mortality.
- This model can aid in identifying high-risk patients, tailoring therapies, and minimizing organ wastage.
Background:
Heart transplantation (HTx) remains the gold-standard treatment for end-stage heart failure. The aim of this study was to establish a risk-prediction model for assessing prognosis of HTx using machine-learning approach.
Methods:
Consecutive recipients of orthotopic HTx at our institute between January 1st, 2015 and December 31st, 2018 were included in this study. The primary outcome was 1-year mortality. Least absolute shrinkage and selection operator method was used to select variables and seven different machine-learning approaches were employed to develop the risk-prediction model. Bootstrap method was used for model validation. Shapley Additive exPlanations (SHAP) method was used for model interpretation.
Results:
381 recipients were included with average age of 43.783 years old. Albumin, recipient age and left atrium diameter ranked top three most important variables that affected the 1-year mortality of HTx. Other important variables included red blood cell, hemoglobin, lymphocyte%, smoking history, use of lyophilized rhBNP, use of Levosimendan, hypertension, cardiac surgery history, malignancy and endotracheal intubation history. Random Forest (RF) model achieved the best area under curves (AUC) of 0.801 and gradient boosting machine (GBM) showed the best sensitivity of 0.271. SHAP method was introduced to display the RF model's predicting processes of "survival" or "death" in individual level.
Conclusions:
We established the risk-prediction model for postoperative prognosis of HTx patients by using machine learning method and demonstrated that the RF model performed the highest discrimination with the largest AUC when validated. This prediction model could help to recognize high-risk HTx recipients, provide personalized therapy plan and reduce organ wastage.