Ran Xu, Wenqi Shi, Yue Yu, Yuchen Zhuang, Bowen Jin, May D. Wang, Joyce C. Ho, Carl Yang
{"title":"RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records","authors":"Ran Xu, Wenqi Shi, Yue Yu, Yuchen Zhuang, Bowen Jin, May D. Wang, Joyce C. Ho, Carl Yang","doi":"arxiv-2403.00815","DOIUrl":null,"url":null,"abstract":"We present RAM-EHR, a Retrieval AugMentation pipeline to improve clinical\npredictions on Electronic Health Records (EHRs). RAM-EHR first collects\nmultiple knowledge sources, converts them into text format, and uses dense\nretrieval to obtain information related to medical concepts. This strategy\naddresses the difficulties associated with complex names for the concepts.\nRAM-EHR then augments the local EHR predictive model co-trained with\nconsistency regularization to capture complementary information from patient\nvisits and summarized knowledge. Experiments on two EHR datasets show the\nefficacy of RAM-EHR over previous knowledge-enhanced baselines (3.4% gain in\nAUROC and 7.2% gain in AUPR), emphasizing the effectiveness of the summarized\nknowledge from RAM-EHR for clinical prediction tasks. The code will be\npublished at \\url{https://github.com/ritaranx/RAM-EHR}.","PeriodicalId":501219,"journal":{"name":"arXiv - QuanBio - Other Quantitative Biology","volume":"48 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuanBio - Other Quantitative Biology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2403.00815","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
We present RAM-EHR, a Retrieval AugMentation pipeline to improve clinical
predictions on Electronic Health Records (EHRs). RAM-EHR first collects
multiple knowledge sources, converts them into text format, and uses dense
retrieval to obtain information related to medical concepts. This strategy
addresses the difficulties associated with complex names for the concepts.
RAM-EHR then augments the local EHR predictive model co-trained with
consistency regularization to capture complementary information from patient
visits and summarized knowledge. Experiments on two EHR datasets show the
efficacy of RAM-EHR over previous knowledge-enhanced baselines (3.4% gain in
AUROC and 7.2% gain in AUPR), emphasizing the effectiveness of the summarized
knowledge from RAM-EHR for clinical prediction tasks. The code will be
published at \url{https://github.com/ritaranx/RAM-EHR}.