AUTHOR=Zhu Xiao , Peng Bo , Yi QiFeng , Liu Jia , Yan Jin 

TITLE=Prediction Model of Immunosuppressive Medication Non-adherence for Renal Transplant Patients Based on Machine Learning Technology

JOURNAL=Frontiers in Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2022.796424

DOI=10.3389/fmed.2022.796424

ISSN=2296-858X

ABSTRACT=Objectives:Predicting adherence to immunosuppressive medication(IM) is important to improving and designing future prospective, personalized interventions in Chinese renal transplant patients (RTPs).Methods:A retrospective, multicenter, cross-sectional study was performed in 1191 RTPs from October 2020 to February 2021 in China. The BAASIS was used as the standard to determine the adherence of the patients. Variables of the combined theory, including the general data, the HBM, the TPB, the BMQ, the PSSS and the GSES, were used to build the models. The machine learning(ML) models included LR, RF,MLP, SVM and XGBoost. The SHAP method was used to evaluate the contribution of predictors to predicting the risk of IM nonadherence in RTPs.
Results:The IM nonadherence rate in the derivation cohort was 38.5%. 10 predictors were screened to build the model based on the database.Tthe SVM model had the best performance with sensitivity of 0.59, specificity of 0.73, and average AUC of 0.70. The SHAP analysis showed that age, marital status, HBM-perceived barriers, pill box use after transplantation, and PSSS family support were the most important parameters in the prediction model. All of the models had good performance validated by external data.Conclusions:The IM nonadherence rate of RTPs was high, and it is important to improve IM adherence. The model developed by ML technology could identify high-risk patients and provide a basis for the development of relevant improvement measures.