Decision Tree Induction for the Screening of Patients at Risk of Moderately Emetogenic Chemotherapy-Induced Nausea and Vomiting During Delayed Phase

Chemotherapy-Induced Nausea and Vomiting (CINV) are the most feared and common side-effects of chemotherapy for cancer patients. The main care plan for CINV consists of preventative care using antiemetics before chemotherapy. CINV considerably impairs the life quality of cancer patients and increases the healthcare cost due to extended hospitalization or re-hospitalization. Thus, it is imperative to identify the patients at high-risk of CINV and provide sufficient antiemetic prophylaxis before chemotherapy. Several recent studies demonstrated that patient-related factors also significantly affect the risk of CINV but how those factors altogether affect the risk of CINV is an unknown fact. This is more applicable for the moderately emetogenic chemotherapy (MEC) risk-group since it has been classified as a broader risk-group (i.e., chances of emetogenecity ranges from 30% to 90%). In this study, we built a decision tree model to classify the patients at high-risk vs. low-risk for the MEC during delayed phase. This tree model can be implemented as a standalone-software or integrated with a clinical decision support system.