A dynamic prediction engine to prevent chemotherapy-induced nausea and vomiting
作者：
Highlights：
• We described a single framework that can perform prediction query without losing the sensitivity to each context (i.e., combination of phases and emetogenicity levels).
• The system discovers how the patient-related variables and the emetogenicity of chemotherapy are associated with the risk of CINV for each phase.
• The prediction performance of the system outperformed many popular prediction methods.
• A real clinical problem was addressed so that the gap between clinical practices and evidence-based guidelines are shortened.
• The approach proposed in this project can be adapted for any other clinical predictions.
摘要
•We described a single framework that can perform prediction query without losing the sensitivity to each context (i.e., combination of phases and emetogenicity levels).•The system discovers how the patient-related variables and the emetogenicity of chemotherapy are associated with the risk of CINV for each phase.•The prediction performance of the system outperformed many popular prediction methods.•A real clinical problem was addressed so that the gap between clinical practices and evidence-based guidelines are shortened.•The approach proposed in this project can be adapted for any other clinical predictions.
论文关键词：Chemotherapy,CINV,Side effects,Data mining,Data science,Prediction,Clinical decision support
论文评审过程：Received 20 April 2018, Revised 2 March 2020, Accepted 2 July 2020, Available online 3 July 2020, Version of Record 22 September 2020.
论文官网地址：https://doi.org/10.1016/j.artmed.2020.101925
