State‐of‐the‐art machine learning algorithms for the prediction of outcomes after contemporary heart transplantation: Results from the UNOS database

Abstract

We sought to develop and validate machine learning (ML) models to increase the predictive accuracy of mortality after heart transplantation (HT). Methods and results:We included adult HT recipients from the United Network for Organ Sharing (UNOS) database between 2010 and 2018 using solely pre-transplant variables. The study cohort comprised 18 625 patients (53 ± 13 years, 73% males) and was randomly split into a derivation and a validation cohort with a 3:1 ratio. At 1-year after HT, there were 2334 (12.5%) deaths. Out of a total of 134 pre-transplant variables, 39 were selected as highly predictive of 1-year mortality via feature selection algorithm and were used to train five ML models. AUC for the prediction of 1-year survival was .689, .642, .649, .637, .526 for the Adaboost, Logistic Regression, Decision Tree, Support Vector Machine, and K-nearest neighbor models, respectively, whereas the Index for Mortality Prediction after Cardiac Transplantation (IMPACT) score had an AUC of .569. Local interpretable model-agnostic explanations (LIME) analysis was used in the best performing model to identify the relative impact of key predictors.ML models for 3-and 5-year survival as well as acute rejection were also developed in a secondary analysis and yielded AUCs of .629, .609, and .610 using 27, 31, and 91 selected variables respectively. Conclusion:Machine learning models showed good predictive accuracy of outcomes after heart transplantation.

The promise of machine learning applications in solid organ transplantation

“…Moreover, recent research also strives to make ML models more interpretable in terms of identifying features playing a key role during the prediction tasks. Some recent methods including SHapley Additive exPlanations (SHAP) as used for evaluating feature importance and explain the predictions made by ML algorithms toward post-LT AKI 57 , Local Interpretable Model-Agnostic Explanations (LIME) used to assess relative impact of key predictors in post-transplant patient survival 58 , and integrated gradients used to identify important predictors in diagnosing allograft rejection 59 , make ML models more explainable. However, further validation of their results using multicenter prospectively collected data is important before wider application of these algorithms in daily clinical practice.…”

Prediction of Injuries in CrossFit Training: A Machine Learning Perspective

“…The classification performance of the competing ML models was evaluated with respect to a number of evaluation criteria that are extracted on the basis of the confusion matrix. Specifically, precision, sensitivity, specificity and classification accuracy have been widely utilized in the recent literature to assess the predictive performance of ML techniques in various health applications [45][46][47][48]. The aforementioned metrics are shortly described below.…”

Patient selection for heart transplant: balancing risk

“…The most well recognized are the Seattle Heart Failure Model (SHFM), the Heart Failure Survival Score (HFSS), and the Interagency Registry for Mechanically Assisted Circulatory Support (INTER-MACS) [4,30]. The application of machine learning to clinical registry to predict posttransplant outcomes is an active area of research [31].…”