Analysis of the most influential factors affecting outcomes of lung transplant recipients: a multivariate prediction model based on UNOS Data

Abstract

Objectives: In lung transplantation (LTx), a priority is assigned to each candidate on the waiting list. Our primary objective was to identify the key factors that influence the allocation of priorities in LTx using machine learning (ML) techniques to enhance the process of prioritising patients.

Design: Developing a prediction model.

Setting and participants: Our data were retrieved from the United Network for Organ Sharing (UNOS) open-source database of transplant patients between 2005 and 2023.

Interventions: After the preprocessing process, a feature engineering technique was employed to select the most relevant features. Then, six ML models with optimised hyperparameters including multiple linear regression, random forest regressor (RF), support vector machine regressor, XGBoost regressor, a multilayer perceptron model and a deep learning model were developed based on the UNOS dataset.

Primary and secondary outcome measures: The performance of each model was evaluated using R-squared (R²) and other error rate metrics. Next, the Shapley Additive Explanations (SHAP) technique was used to identify the most important features in the prediction.

Results: The raw dataset contains 196 270 records with 545 features in all organs. After preprocessing, 32 966 records with 15 features remain. Among various models, the RF model achieved a high R² score. Additionally, the RF model exhibited the lowest error values, indicating its superior precision compared with other regression models. The SHAP technique in conjunction with the RF model revealed the 11 most important features for priority allocation. Subsequently, we developed a web-based decision support tool using Python and the Streamlit framework based on the best-fine-tuned model.

Conclusion: The deployment of the ML model has the potential to act as an automated tool to aid physicians in assessing the priority of lung transplants and identifying significant factors that play a role in patient survival.

Keywords: Machine Learning; Pulmonary Disease; Transplant medicine.

Figure 1. Schematic diagram illustrating the proposed methodology for developing machine learning models. The process includes data preprocessing, feature engineering, model training and evaluation, followed by a systematic comparison of multiple models using performance metrics to identify and select the optimal model for deployment. DL, deep learning; MLP, multilayer perceptron; MLR, multiple linear regression; RF, random forest; SHAP, Shapley Additive Explanations; SVM, support vector machine; UNOS, United Network for Organ Sharing; XGB, XGBoost.

Figure 2. (A) SHAP summary plot of the top 11 features for predicting lung allocation score using random forest regressor and (B) SHAP values to explain the predicted probabilities. SHAP, Shapley Additive Explanations.

Figure 3. Interactive web-based interface for the machine learning model, developed using the Streamlit framework. The tool allows users to input data, visualise predictions and explore model performance metrics in real-time, providing an accessible platform for researchers and practitioners to interact with the developed algorithm.