A methodology for customizing clinical tests for esophageal cancer based on patient preferences

作者：

Highlights：

• Method to suggest personalized clinical tests for esophaegal cancer based on lifestyle, medical history, etc.

• Kernel methods for prediction of Esophageal cancer with accuracy of 99.18 %.

• Method for selecting probability threshold for achieveing almost zero false normal rate.

• Budget and cost / comfort preferences based formulation for choice of best set of clinical tests.

摘要

•Method to suggest personalized clinical tests for esophaegal cancer based on lifestyle, medical history, etc.•Kernel methods for prediction of Esophageal cancer with accuracy of 99.18 %.•Method for selecting probability threshold for achieveing almost zero false normal rate.•Budget and cost / comfort preferences based formulation for choice of best set of clinical tests.

论文关键词：Personalized diagnosis,Personalized test selection,Esophageal cancer,Classification with costs,Unbalanced classification,Electronic health record (EHR),Electronic medical record (EMR)

论文评审过程：Received 7 December 2016, Revised 2 May 2018, Accepted 2 August 2018, Available online 29 September 2018, Version of Record 20 March 2019.

论文官网地址：https://doi.org/10.1016/j.artmed.2018.08.001