AUTHOR=Duan Minjie , Shu Tingting , Zhao Binyi , Xiang Tianyu , Wang Jinkui , Huang Haodong , Zhang Yang , Xiao Peilin , Zhou Bei , Xie Zulong , Liu Xiaozhu 

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

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2022.919224

DOI=10.3389/fcvm.2022.919224

ISSN=2297-055X

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 of pediatric PH inpatients from Chongqing Medical University Medical Data Platform from January 2012 to January 2019. Key clinical variables were selected by the least absolute shrinkage and 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 predictive model was interpreted by SHapley Additive exPlanations (SHAP).
Results: A total of 5913 pediatric PH patients 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 to 0.86), high accuracy for 0.74 (95% CI: 0.72 to 0.76), sensitivity 0.78 (95% CI: 0.69 to 0.87), and specificity 0.74 (95% CI: 0.72 to 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 PH patients, which showed more significant performance compared to traditional logistic regression. We found age, LOS, congenital heart surgery, and nonmedical order discharge were important factors for 30-day readmission in pediatric PH.