دورية أكاديمية
A broadly applicable approach to enrich electronic-health-record cohorts by identifying patients with complete data: a multisite evaluation.
| العنوان: | A broadly applicable approach to enrich electronic-health-record cohorts by identifying patients with complete data: a multisite evaluation. |
|---|---|
| المؤلفون: | Klann JG; Department of Medicine, Massachusetts General Hospital, Boston, MA 02114, United States.; Department of Medicine, Harvard Medical School, Boston, MA 02115, United States., Henderson DW; Institute of Biomedical Informatics, University of Kentucky, Lexington, KY 40506, United States., Morris M; Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA 15260, United States., Estiri H; Department of Medicine, Massachusetts General Hospital, Boston, MA 02114, United States.; Department of Medicine, Harvard Medical School, Boston, MA 02115, United States., Weber GM; Beth Israel Deaconess Medical Center, Boston, MA 02115, United States.; Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, United States., Visweswaran S; Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA 15260, United States., Murphy SN; Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, United States.; Department of Neurology, Massachusetts General Hospital, Boston, MA 02114, United States.; Research Information Science and Computing, Mass General Brigham, Somerville, MA 02145, United States. |
| المصدر: | Journal of the American Medical Informatics Association : JAMIA [J Am Med Inform Assoc] 2023 Nov 17; Vol. 30 (12), pp. 1985-1994. |
| نوع المنشور: | Journal Article; Research Support, N.I.H., Extramural |
| اللغة: | English |
| بيانات الدورية: | Publisher: Oxford University Press Country of Publication: England NLM ID: 9430800 Publication Model: Print Cited Medium: Internet ISSN: 1527-974X (Electronic) Linking ISSN: 10675027 NLM ISO Abbreviation: J Am Med Inform Assoc Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: 2015- : Oxford : Oxford University Press Original Publication: Philadelphia, PA : Hanley & Belfus, c1993- |
| مواضيع طبية MeSH: | Electronic Health Records* , Algorithms*, Humans ; Machine Learning ; Delivery of Health Care ; Electronics |
| مستخلص: | Objective: Patients who receive most care within a single healthcare system (colloquially called a "loyalty cohort" since they typically return to the same providers) have mostly complete data within that organization's electronic health record (EHR). Loyalty cohorts have low data missingness, which can unintentionally bias research results. Using proxies of routine care and healthcare utilization metrics, we compute a per-patient score that identifies a loyalty cohort. Materials and Methods: We implemented a computable program for the widely adopted i2b2 platform that identifies loyalty cohorts in EHRs based on a machine-learning model, which was previously validated using linked claims data. We developed a novel validation approach, which tests, using only EHR data, whether patients returned to the same healthcare system after the training period. We evaluated these tools at 3 institutions using data from 2017 to 2019. Results: Loyalty cohort calculations to identify patients who returned during a 1-year follow-up yielded a mean area under the receiver operating characteristic curve of 0.77 using the original model and 0.80 after calibrating the model at individual sites. Factors such as multiple medications or visits contributed significantly at all sites. Screening tests' contributions (eg, colonoscopy) varied across sites, likely due to coding and population differences. Discussion: This open-source implementation of a "loyalty score" algorithm had good predictive power. Enriching research cohorts by utilizing these low-missingness patients is a way to obtain the data completeness necessary for accurate causal analysis. Conclusion: i2b2 sites can use this approach to select cohorts with mostly complete EHR data. (© The Author(s) 2023. Published by Oxford University Press on behalf of the American Medical Informatics Association.) |
| References: | EGEMS (Wash DC). 2014 Sep 11;2(2):1074. (PMID: 25848608) Nat Commun. 2020 Oct 6;11(1):5009. (PMID: 33024121) J Am Med Inform Assoc. 2013 Jan 1;20(1):117-21. (PMID: 22955496) NPJ Digit Med. 2021 Oct 11;4(1):147. (PMID: 34635760) EGEMS (Wash DC). 2016 Sep 11;4(1):1244. (PMID: 27713905) J Biomed Inform. 2013 Oct;46(5):830-6. (PMID: 23820016) J Am Med Inform Assoc. 2020 Dec 9;27(12):1999-2010. (PMID: 33166397) J Am Med Inform Assoc. 2018 Jan 1;25(1):17-24. (PMID: 29069394) J Am Med Inform Assoc. 2019 Jul 1;26(7):637-645. (PMID: 30925587) J Am Med Inform Assoc. 2022 Jul 12;29(8):1334-1341. (PMID: 35511151) NPJ Digit Med. 2023 May 27;6(1):98. (PMID: 37244963) J Am Med Inform Assoc. 2014 Jul-Aug;21(4):615-20. (PMID: 24821734) BMC Med Res Methodol. 2021 Oct 27;21(1):234. (PMID: 34706667) N Engl J Med. 2019 Aug 15;381(7):668-676. (PMID: 31412182) JAMA Netw Open. 2021 Feb 1;4(2):e210184. (PMID: 33635321) J Am Med Inform Assoc. 2020 Apr 1;27(4):505-513. (PMID: 32049329) Philos Trans A Math Phys Eng Sci. 2009 Jan 28;367(1887):411-29. (PMID: 18936019) Am J Epidemiol. 2011 May 1;173(9):1059-68. (PMID: 21430193) Cancer. 1950 Jan;3(1):32-5. (PMID: 15405679) BMJ. 2018 Apr 30;361:k1479. (PMID: 29712648) J Am Med Inform Assoc. 2021 Mar 1;28(3):427-443. (PMID: 32805036) Med Care. 2015 Sep;53(9):e65-72. (PMID: 23703645) J Med Internet Res. 2021 Mar 2;23(3):e22219. (PMID: 33600347) J Am Med Inform Assoc. 2022 Jun 14;29(7):1225-1232. (PMID: 35357470) J Am Med Inform Assoc. 2009 Sep-Oct;16(5):624-30. (PMID: 19567788) J Biomed Inform. 2014 Dec;52:43-54. (PMID: 24524889) NPJ Digit Med. 2020 Aug 19;3:109. (PMID: 32864472) JAMIA Open. 2021 Apr 19;4(2):ooab036. (PMID: 34113801) J Am Med Inform Assoc. 2015 Sep;22(5):1072-80. (PMID: 26104741) Clin Epidemiol. 2020 Feb 04;12:133-141. (PMID: 32099479) Curr Epidemiol Rep. 2017 Dec;4(4):346-352. (PMID: 31223556) J Adv Nurs. 2005 Mar;49(6):616-23. (PMID: 15737222) J Am Med Inform Assoc. 2018 Oct 1;25(10):1331-1338. (PMID: 30085008) Proc AAAI Conf Artif Intell. 2015 Jan;2015:446-453. (PMID: 27182460) J Am Med Inform Assoc. 2020 Jul 1;27(9):1411-1419. (PMID: 32989459) Sci Rep. 2021 Mar 5;11(1):5322. (PMID: 33674708) J Am Med Inform Assoc. 2010 Mar-Apr;17(2):124-30. (PMID: 20190053) PLoS One. 2013;8(3):e55811. (PMID: 23533569) Clin Pharmacol Ther. 2018 May;103(5):899-905. (PMID: 28865143) J Am Med Inform Assoc. 2017 Nov 01;24(6):1134-1141. (PMID: 29016972) J Am Med Inform Assoc. 2016 Sep;23(5):909-15. (PMID: 26911824) Nat Biotechnol. 2015 Apr;33(4):360-3. (PMID: 25850061) J Am Med Inform Assoc. 2022 Oct 7;29(11):1890-1898. (PMID: 35927974) J Am Med Inform Assoc. 2018 Jan 1;25(1):54-60. (PMID: 29126253) JAMIA Open. 2018 Oct;1(2):147-152. (PMID: 30474072) |
| معلومات مُعتمدة: | U24 TR004111 United States NH NIH HHS; R01 LM013345 United States NH NIH HHS; R01 LM013345 United States LM NLM NIH HHS; R01 AI165535 United States AI NIAID NIH HHS; U24 TR004111 United States TR NCATS NIH HHS |
| فهرسة مساهمة: | Keywords: clinical data warehousing; clinical research informatics; data completeness; electronic health records; i2b2; loyalty cohort |
| تواريخ الأحداث: | Date Created: 20230826 Date Completed: 20231120 Latest Revision: 20240314 |
| رمز التحديث: | 20240314 |
| مُعرف محوري في PubMed: | PMC10654861 |
| DOI: | 10.1093/jamia/ocad166 |
| PMID: | 37632234 |
| قاعدة البيانات: | MEDLINE |
| تدمد: | 1527-974X |
|---|---|
| DOI: | 10.1093/jamia/ocad166 |