Fagen Xie, Darios Getahun, Virginia P Quinn, Theresa M Im, Richard Contreras, Michael J Silverberg, Tisha C Baird, Rebecca Nash, Lee Cromwell, Douglas Roblin, Trenton Hoffman, Michael Goodman
{"title":"An automated algorithm using free-text clinical notes to improve identification of transgender people.","authors":"Fagen Xie, Darios Getahun, Virginia P Quinn, Theresa M Im, Richard Contreras, Michael J Silverberg, Tisha C Baird, Rebecca Nash, Lee Cromwell, Douglas Roblin, Trenton Hoffman, Michael Goodman","doi":"10.1080/17538157.2020.1828890","DOIUrl":null,"url":null,"abstract":"<p><p>Accurate identification of transgender persons is a critical first step in conducting transgender health studies. To develop an automated algorithm for identifying transgender individuals from electronic medical records (EMR) using free-text clinical notes. The development and validation of the algorithm was based on data from an integrated healthcare system that served as a participating site in the multicenter Study of Transition Outcomes and Gender. The training and test datasets each contained a total of 300 individuals identified between 2006 and 2014. Both datasets underwent a full medical record review by experienced research abstractors. The validated algorithm was then implemented to identify transgender individuals in the EMR using all clinical notes of patients that received care between January 1, 2015 and June 30, 2018. Validation of the algorithm against the full chart review demonstrated a high degree of accuracy with 97% sensitivity, 95% specificity, 94% positive predictive value, and 97% negative predictive value. The algorithm classified 7,409 individuals (3.5%) as \"Definitely transgender\" and 679 individuals (0.3%) as \"Probably transgender\" out of 212,138 candidates with a total of 378,641 clinical notes. The computerized NLP algorithm can support essential efforts to improve the health of transgender people.</p>","PeriodicalId":54984,"journal":{"name":"Informatics for Health & Social Care","volume":"46 1","pages":"18-28"},"PeriodicalIF":2.5000,"publicationDate":"2021-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17538157.2020.1828890","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Informatics for Health & Social Care","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/17538157.2020.1828890","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2020/11/17 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}
引用次数: 6
Abstract
Accurate identification of transgender persons is a critical first step in conducting transgender health studies. To develop an automated algorithm for identifying transgender individuals from electronic medical records (EMR) using free-text clinical notes. The development and validation of the algorithm was based on data from an integrated healthcare system that served as a participating site in the multicenter Study of Transition Outcomes and Gender. The training and test datasets each contained a total of 300 individuals identified between 2006 and 2014. Both datasets underwent a full medical record review by experienced research abstractors. The validated algorithm was then implemented to identify transgender individuals in the EMR using all clinical notes of patients that received care between January 1, 2015 and June 30, 2018. Validation of the algorithm against the full chart review demonstrated a high degree of accuracy with 97% sensitivity, 95% specificity, 94% positive predictive value, and 97% negative predictive value. The algorithm classified 7,409 individuals (3.5%) as "Definitely transgender" and 679 individuals (0.3%) as "Probably transgender" out of 212,138 candidates with a total of 378,641 clinical notes. The computerized NLP algorithm can support essential efforts to improve the health of transgender people.
期刊介绍：
Informatics for Health & Social Care promotes evidence-based informatics as applied to the domain of health and social care. It showcases informatics research and practice within the many and diverse contexts of care; it takes personal information, both its direct and indirect use, as its central focus.
The scope of the Journal is broad, encompassing both the properties of care information and the life-cycle of associated information systems.
Consideration of the properties of care information will necessarily include the data itself, its representation, structure, and associated processes, as well as the context of its use, highlighting the related communication, computational, cognitive, social and ethical aspects.
Consideration of the life-cycle of care information systems includes full range from requirements, specifications, theoretical models and conceptual design through to sustainable implementations, and the valuation of impacts. Empirical evidence experiences related to implementation are particularly welcome.
Informatics in Health & Social Care seeks to consolidate and add to the core knowledge within the disciplines of Health and Social Care Informatics. The Journal therefore welcomes scientific papers, case studies and literature reviews. Examples of novel approaches are particularly welcome. Articles might, for example, show how care data is collected and transformed into useful and usable information, how informatics research is translated into practice, how specific results can be generalised, or perhaps provide case studies that facilitate learning from experience.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
