Explainable machine learning models for predicting 30-day readmission in pediatric pulmonary hypertension: A multicenter, retrospective study

Abstract

Background: Short-term readmission for pediatric pulmonary hypertension (PH) is associated with a substantial social and personal burden. However, tools to predict individualized readmission risk are lacking. This study aimed to develop machine learning models to predict 30-day unplanned readmission in children with PH.

Methods: This study collected data on pediatric inpatients with PH from the Chongqing Medical University Medical Data Platform from January 2012 to January 2019. Key clinical variables were selected by the least absolute shrinkage and the selection operator. Prediction models were selected from 15 machine learning algorithms with excellent performance, which was evaluated by area under the operating characteristic curve (AUC). The outcome of the predictive model was interpreted by SHapley Additive exPlanations (SHAP).

Results: A total of 5,913 pediatric patients with PH were included in the final cohort. The CatBoost model was selected as the predictive model with the greatest AUC for 0.81 (95% CI: 0.77-0.86), high accuracy for 0.74 (95% CI: 0.72-0.76), sensitivity 0.78 (95% CI: 0.69-0.87), and specificity 0.74 (95% CI: 0.72-0.76). Age, length of stay (LOS), congenital heart surgery, and nonmedical order discharge showed the greatest impact on 30-day readmission in pediatric PH, according to SHAP results.

Conclusions: This study developed a CatBoost model to predict the risk of unplanned 30-day readmission in pediatric patients with PH, which showed more significant performance compared with traditional logistic regression. We found that age, LOS, congenital heart surgery, and nonmedical order discharge were important factors for 30-day readmission in pediatric PH.

Keywords: machine learning; pediatric pulmonary hypertension; prediction; readmission; risk factors.

Figure 1

The flowchart of the patient selection.

Figure 2

Twelve features with non-zero regression coefficients. LOS, length of stay; PDE-5i, phosphodiesterase 5 inhibitors; CHD, congenital heart disease.

Figure 3

Receiver operating characteristic (ROC) curve for five machine learning-based prediction models. ROC, receiver operating characteristic curve; LightGBM, Light Gradient Boosting Machine; XGBoost, eXtreme gradient boosting; LR, logistic regression.

Figure 4

Importance score ranking of features in 4 readmission-predicting algorithms. (A) CatBoost. (B) Light Gradient Boosting Machine. (C) eXtreme gradient boosting. (D) Random forest.

Figure 5

Shapley Additive Explanations (SHAP) for the CatBoost model. (A) shows the most impactful features on prediction (ranked from most to least important). (B) shows the distribution of the impacts of each feature on the model output. Within each row, each dot represents a patient. The colors of the dots represent the feature values: red for larger values and blue for lower. (C, D) show the individualized predictions for two patients. The bars in red and blue represent risk factors and protective factors, respectively; longer bars represent greater feature importance. LOS, length of stay; PDE-5i, phosphodiesterase 5 inhibitors; CHD, congenital heart disease.