RESUMO
The objective of this study was to apply a machine learning method to evaluate 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. First, 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 statistical significance were selected by univariate analysis and least absolute shrinkage and selection operator (LASSO) analysis. Finally, using the risk factors after the LASSO analysis as covariates, a nomogram based on a 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), and ensemble model based on seven 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) was used to evaluate the model performance. A total of 94 SAE patients were identified in our samples. Risk factors of SAEs were the number of triggers, length of stay, age, number of combined drugs, ADEs occurred in previous chemotherapy, and sex. In the test cohort, a nomogram based on the logistic model owns the AUROC of 0.799 and owns the AUPR of 0.527. The GBDT has the best predicting abilities (AUROC = 0.832 and AUPR = 0.557) among the eight machine learning models and was better than the nomogram and was chosen to establish the prediction webpage. This study provides a novel method to accurately predict SAE occurrence in cancer inpatients.
RESUMO
Magnesium isoglycyrrhizinate (MI) has been complementarily used for restoring the hepatic impairments caused by taxol plus platinum based chemotherapies in China. Due to the hepatic dependence of paclitaxel elimination, this pilot clinical study aimed to investigate the influence of MI on the pharmacokinetics of paclitaxel in epithelial ovarian cancer patients. During the standard chemotherapy of intravenous paclitaxel (125 mg/m(2) infused over a 3-h period) and intraperitoneal cisplatin (60 mg/m(2)) for patients with FIGO stage II epithelial ovarian cancer, 9 each of total 18 patients were respectively treated with intravenous MI (100 mg) or vehicle control for 4 days. Plasma paclitaxel was analyzed by HPLC and the pharmacokinetic parameters were calculated with non-compartmental analysis. The hematological, hepatic and renal status was monitored before and 3 days after paclitaxel administration. It was observed the terminal t 1/2 and MRT of paclitaxel were significantly (p = 0.002 and 0.001) reduced by MI, respectively, from 11.0 ± 2.2 and 5.6 ± 1.0 h to 7.7 ± 1.7 and 4.0 ± 0.3 h. Hematological toxicity indicated by platelet count and hepatic events marked with ALT, AST and γ-GT were significant in both groups. In spite of the insignificance of decreased system exposure of paclitaxel and recovered hepatic function by MI, they did correlate with each other. It was therefore deduced that the liver toxicities of paclitaxel plus cisplatin chemotherapy potentially decrease hepatic elimination and increase system exposure of paclitaxel, and the recovery of liver function by MI helps to restore hepatic clearance of paclitaxel. The clinical significance of this pharmacokinetic interaction requires further studies with larger population size.
