دورية أكاديمية
Data-driven automated classification algorithms for acute health conditions: applying PheNorm to COVID-19 disease.
| العنوان: | Data-driven automated classification algorithms for acute health conditions: applying PheNorm to COVID-19 disease. |
|---|---|
| المؤلفون: | Smith JC; Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN 37203, United States., Williamson BD; Kaiser Permanente Washington Health Research Institute, Seattle, WA 98101, United States., Cronkite DJ; Kaiser Permanente Washington Health Research Institute, Seattle, WA 98101, United States., Park D; Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN 37203, United States., Whitaker JM; Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN 37203, United States., McLemore MF; Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN 37203, United States., Osmanski JT; Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN 37203, United States., Winter R; Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN 37203, United States., Ramaprasan A; Kaiser Permanente Washington Health Research Institute, Seattle, WA 98101, United States., Kelley A; Kaiser Permanente Washington Health Research Institute, Seattle, WA 98101, United States., Shea M; Kaiser Permanente Washington Health Research Institute, Seattle, WA 98101, United States., Wittayanukorn S; Center for Drug Evaluation and Research, US Food and Drug Administration, Silver Spring, MD 20903, United States., Stojanovic D; Center for Drug Evaluation and Research, US Food and Drug Administration, Silver Spring, MD 20903, United States., Zhao Y; Center for Drug Evaluation and Research, US Food and Drug Administration, Silver Spring, MD 20903, United States., Toh S; Harvard Pilgrim Health Care Institute, Boston, MA 02215, United States., Johnson KB; Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, PA 19104, United States., Aronoff DM; Department of Medicine, Indiana University School of Medicine, Indianapolis, IN 46202, United States., Carrell DS; Kaiser Permanente Washington Health Research Institute, Seattle, WA 98101, United States. |
| المصدر: | Journal of the American Medical Informatics Association : JAMIA [J Am Med Inform Assoc] 2024 Feb 16; Vol. 31 (3), pp. 574-582. |
| نوع المنشور: | Journal Article; Research Support, N.I.H., Extramural; Research Support, U.S. Gov't, Non-P.H.S. |
| 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: | Algorithms* , COVID-19*, Humans ; Electronic Health Records ; Machine Learning ; Natural Language Processing |
| مستخلص: | Objectives: Automated phenotyping algorithms can reduce development time and operator dependence compared to manually developed algorithms. One such approach, PheNorm, has performed well for identifying chronic health conditions, but its performance for acute conditions is largely unknown. Herein, we implement and evaluate PheNorm applied to symptomatic COVID-19 disease to investigate its potential feasibility for rapid phenotyping of acute health conditions. Materials and Methods: PheNorm is a general-purpose automated approach to creating computable phenotype algorithms based on natural language processing, machine learning, and (low cost) silver-standard training labels. We applied PheNorm to cohorts of potential COVID-19 patients from 2 institutions and used gold-standard manual chart review data to investigate the impact on performance of alternative feature engineering options and implementing externally trained models without local retraining. Results: Models at each institution achieved AUC, sensitivity, and positive predictive value of 0.853, 0.879, 0.851 and 0.804, 0.976, and 0.885, respectively, at quantiles of model-predicted risk that maximize F1. We report performance metrics for all combinations of silver labels, feature engineering options, and models trained internally versus externally. Discussion: Phenotyping algorithms developed using PheNorm performed well at both institutions. Performance varied with different silver-standard labels and feature engineering options. Models developed locally at one site also worked well when implemented externally at the other site. Conclusion: PheNorm models successfully identified an acute health condition, symptomatic COVID-19. The simplicity of the PheNorm approach allows it to be applied at multiple study sites with substantially reduced overhead compared to traditional approaches. (© The Author(s) 2023. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.) |
| References: | Clin Pharmacol Ther. 2016 Mar;99(3):265-8. (PMID: 26667601) Drug Saf. 2022 May;45(5):493-510. (PMID: 35579813) NPJ Digit Med. 2021 Dec 20;4(1):170. (PMID: 34931012) J Am Med Inform Assoc. 2013 Dec;20(e2):e226-31. (PMID: 23956018) Clin Epidemiol. 2021 Oct 27;13:1011-1018. (PMID: 34737645) J Am Med Inform Assoc. 2021 Jun 12;28(6):1265-1269. (PMID: 33594412) J Am Med Inform Assoc. 2016 Nov;23(6):1166-1173. (PMID: 27174893) J Am Med Inform Assoc. 2018 Jan 1;25(1):54-60. (PMID: 29126253) N Engl J Med. 2018 Nov 29;379(22):2091-2093. (PMID: 30485777) J Am Med Inform Assoc. 2017 Apr 01;24(e1):e143-e149. (PMID: 27632993) J Am Med Inform Assoc. 2015 Sep;22(5):993-1000. (PMID: 25929596) Artif Intell Med. 2020 Apr;104:101822. (PMID: 32499001) J Am Med Inform Assoc. 2024 Feb 16;31(3):574-582. (PMID: 38109888) J Am Med Inform Assoc. 2020 May 1;27(5):793-797. (PMID: 32279080) Am Heart J. 2004 Jul;148(1):99-104. (PMID: 15215798) J Pers Med. 2016 Feb 26;6(1):. (PMID: 26927184) J Am Med Inform Assoc. 2019 Nov 1;26(11):1255-1262. (PMID: 31613361) J Am Med Inform Assoc. 2020 Nov 1;27(11):1675-1687. (PMID: 32974638) Fed Regist. ;82(12):7149-274. (PMID: 28106360) PLoS One. 2019 Jul 8;14(7):e0218919. (PMID: 31283787) |
| معلومات مُعتمدة: | UL1 TR002243 United States TR NCATS NIH HHS; United States NH NIH HHS; United States FD FDA HHS |
| فهرسة مساهمة: | Keywords: COVID-19; electronic health records; machine learning; natural language processing; phenotyping |
| تواريخ الأحداث: | Date Created: 20231218 Date Completed: 20240219 Latest Revision: 20240820 |
| رمز التحديث: | 20240820 |
| مُعرف محوري في PubMed: | PMC10873852 |
| DOI: | 10.1093/jamia/ocad241 |
| PMID: | 38109888 |
| قاعدة البيانات: | MEDLINE |
| تدمد: | 1527-974X |
|---|---|
| DOI: | 10.1093/jamia/ocad241 |