AUTHOR=Zhang Ni , Pan Ling-Yun , Chen Wan-Yi , Ji Huan-Huan , Peng Gui-Qin , Tang Zong-Wei , Wang Hui-Lai , Jia Yun-Tao , Gong Jun TITLE=A Risk-Factor Model for Antineoplastic Drug-Induced Serious Adverse Events in Cancer Inpatients: A Retrospective Study Based on the Global Trigger Tool and Machine Learning JOURNAL=Frontiers in Pharmacology VOLUME=Volume 13 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2022.896104 DOI=10.3389/fphar.2022.896104 ISSN=1663-9812 ABSTRACT=The objective of this study was to apply machine learning method to evaluated the risk factors associated with serious adverse events (SAEs) and predict the occurrence of SAEs in cancer inpatients using antineoplastic drugs. A retrospective review of the medical records of 499 patients diagnosed with cancer admitted between January 1, and December 31, 2017 was performed. Firstly, the global trigger tool (GTT) was used to actively monitor adverse drug events (ADEs) and SAEs caused by antineoplastic drugs and take the number of positive triggers as an intermediate variable. Subsequently, risk factors with statistically significant were selected by univariate analysis and least absolute shrinkage and selection operator (LASSO) analysis. Finally, using the risk factors after LASSO analysis as covariates, nomogram based on logistic model, extreme gradient boosting (XGBoost), categorical boosting (CatBoost), adaptive boosting (AdaBoost), light gradient boosting machine (LightGBM), random forest (RF), gradient boosting decision tree (GBDT), decision tree (DT), ensemble model based on 7 algorithms were used to establish the prediction models. A series of indicators such as the area under the ROC curve (AUROC) and the area under the PR curve (AUPR) were used to evaluate the model performance. 94 SAEs patients were identified in our samples. Risk factors of SAEs were number of triggers, length of stay, age, number of combined drugs, ADEs occurred in previous chemotherapy and sex. In the test cohort, nomogram based on logistic model own the AUROC of 0.799 and own the AUPR of 0.527. GBDT has the best predicting abilities (AUROC=0.832, AUPR = 0.557) among the 8 machine learning models and better than nomogram, and was chosen to establish the prediction webpage. This study provides a novel method to accurately predict SAEs occurrence in cancer inpatients.