Hua Xu, Son Doan, Kelly A Birdwell, James D Cowan, Andrew J Vincz, David W Haas, Melissa A Basford, Joshua C Denny
{"title":"An automated approach to calculating the daily dose of tacrolimus in electronic health records.","authors":"Hua Xu, Son Doan, Kelly A Birdwell, James D Cowan, Andrew J Vincz, David W Haas, Melissa A Basford, Joshua C Denny","doi":"","DOIUrl":null,"url":null,"abstract":"<p><p>Clinical research often requires extracting detailed drug information, such as medication names and dosages, from Electronic Health Records (EHR). Since medication information is often recorded as both structured and unstructured formats in the EHR, extracting all the relevant drug mentions and determining the daily dose of a medication for a selected patient at a given date can be a challenging and time-consuming task. In this paper, we present an automated approach using natural language processing to calculate daily doses of medications mentioned in clinical text, using tacrolimus as a test case. We evaluated this method using data sets from four different types of unstructured clinical data. Our results showed that the system achieved precisions of 0.90-1.00 and recalls of 0.81-1.00.</p>","PeriodicalId":89276,"journal":{"name":"Summit on translational bioinformatics","volume":"2010 ","pages":"71-5"},"PeriodicalIF":0.0000,"publicationDate":"2010-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3041548/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Summit on translational bioinformatics","FirstCategoryId":"1085","ListUrlMain":"","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
Clinical research often requires extracting detailed drug information, such as medication names and dosages, from Electronic Health Records (EHR). Since medication information is often recorded as both structured and unstructured formats in the EHR, extracting all the relevant drug mentions and determining the daily dose of a medication for a selected patient at a given date can be a challenging and time-consuming task. In this paper, we present an automated approach using natural language processing to calculate daily doses of medications mentioned in clinical text, using tacrolimus as a test case. We evaluated this method using data sets from four different types of unstructured clinical data. Our results showed that the system achieved precisions of 0.90-1.00 and recalls of 0.81-1.00.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
