دورية أكاديمية
أعرض في EDS

Developing and optimizing a computable phenotype for incident venous thromboembolism in a longitudinal cohort of patients with cancer.

التفاصيل البيبلوغرافية
العنوان: Developing and optimizing a computable phenotype for incident venous thromboembolism in a longitudinal cohort of patients with cancer.
المؤلفون: Li A; Section of Hematology-Oncology Baylor College of Medicine Houston Texas USA., da Costa WL Jr; Section of Epidemiology and Population Science Baylor College of Medicine Houston Texas USA., Guffey D; Institute for Clinical and Translational Research Baylor College of Medicine Houston Texas USA., Milner EM; School of Medicine Baylor College of Medicine Houston Texas USA., Allam AK; School of Medicine Baylor College of Medicine Houston Texas USA., Kurian KM; School of Medicine Baylor College of Medicine Houston Texas USA., Novoa FJ; School of Medicine Baylor College of Medicine Houston Texas USA., Poche MD; School of Medicine Baylor College of Medicine Houston Texas USA., Bandyo R; Bluetree Network Inc Madison Wisconsin USA.; Harris Health System Houston Texas USA., Granada C; Section of Hematology-Oncology Baylor College of Medicine Houston Texas USA., Wallace CD; Harris Health System Houston Texas USA., Zakai NA; Departments of Medicine and Pathology and Laboratory Medicine Larner College of Medicine at the University of Vermont Burlington Vermont USA., Amos CI; Section of Epidemiology and Population Science Baylor College of Medicine Houston Texas USA.; Institute for Clinical and Translational Research Baylor College of Medicine Houston Texas USA.
المصدر: Research and practice in thrombosis and haemostasis [Res Pract Thromb Haemost] 2022 May 25; Vol. 6 (4), pp. e12733. Date of Electronic Publication: 2022 May 25 (Print Publication: 2022).
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Elsevier Country of Publication: United States NLM ID: 101703775 Publication Model: eCollection Cited Medium: Internet ISSN: 2475-0379 (Electronic) Linking ISSN: 24750379 NLM ISO Abbreviation: Res Pract Thromb Haemost Subsets: PubMed not MEDLINE
أسماء مطبوعة: Publication: 2023- : [New York] : Elsevier
Original Publication: Hoboken, NJ : John Wiley & Sons, Inc., [2017]-
مستخلص: Background: Research on venous thromboembolism (VTE) that relies only on the International Classification of Diseases (ICD) can misclassify outcomes. Our study aims to discover and validate an improved VTE computable phenotype for people with cancer.
Methods: We used a cancer registry electronic health record (EHR)-linked longitudinal database. We derived three algorithms that were ICD/medication based, natural language processing (NLP) based, or all combined. We then randomly sampled 400 patients from patients with VTE codes (n = 1111) and 400 from those without VTE codes (n = 7396). Weighted sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated on the entire sample using inverse probability weighting, followed by bootstrapped receiver operating curve analysis to calculate the concordance statistic (c statistic).
Results: Among 800 patients sampled, 280 had a confirmed acute VTE during the first year after cancer diagnosis. The ICD/medication algorithm had a weighted PPV of 95% and a weighted sensitivity of 81%, with a c statistic of 0.90 (95% confidence interval [CI], 0.89-0.91). Adding Current Procedural Terminology codes for inferior vena cava filter removal or early death did not improve the performance. The NLP algorithm had a weighted PPV of 80% and a weighted sensitivity of 90%, with a c statistic of 0.93 (95% CI, 0.92-0.94). The combined algorithm had a weighted PPV of 98% at the higher cutoff and a weighted sensitivity of 96% at the lower cutoff, with a c statistic of 0.98 (95% CI, 0.97-0.98).
Conclusions: Our ICD/medication-based algorithm can accurately identify VTE phenotype among patients with cancer with a high PPV of 95%. The combined algorithm should be considered in EHR databases that have access to such capabilities.
(© 2022 The Authors. Research and Practice in Thrombosis and Haemostasis published by Wiley Periodicals LLC on behalf of International Society on Thrombosis and Haemostasis (ISTH).)
References: Res Pract Thromb Haemost. 2022 May 25;6(4):e12733. (PMID: 35647478)
Pharmacoepidemiol Drug Saf. 2012 Jan;21 Suppl 1:154-62. (PMID: 22262602)
J Am Med Inform Assoc. 2013 Dec;20(e2):e226-31. (PMID: 23956018)
JAMA Intern Med. 2017 Sep 1;177(9):1373-1374. (PMID: 28692712)
Oncologist. 2013;18(12):1321-9. (PMID: 24212499)
Thromb Res. 2010 Jul;126(1):61-7. (PMID: 20430419)
Thromb Res. 2015 Apr;135(4):616-20. (PMID: 25613924)
J Am Med Inform Assoc. 2015 Mar;22(2):465-71. (PMID: 25342181)
Med Care. 2017 Dec;55(12):e137-e143. (PMID: 29135777)
J Am Med Inform Assoc. 2018 Mar 1;25(3):331-336. (PMID: 29186491)
J Biomed Inform. 2009 Apr;42(2):377-81. (PMID: 18929686)
J Clin Monit Comput. 2022 Apr;36(2):397-405. (PMID: 33558981)
Biometrics. 1983 Mar;39(1):207-15. (PMID: 6871349)
J Biomed Inform. 2019 Jul;95:103208. (PMID: 31078660)
AMIA Annu Symp Proc. 2013 Nov 16;2013:975-83. (PMID: 24551388)
معلومات مُعتمدة: K23 HL159271 United States HL NHLBI NIH HHS
فهرسة مساهمة: Keywords: administrative claims; health care; natural language processing; neoplasms; venous thromboembolism; venous thrombosis
تواريخ الأحداث: Date Created: 20220601 Latest Revision: 20230328
رمز التحديث: 20231215
مُعرف محوري في PubMed: PMC9130880
DOI: 10.1002/rth2.12733
PMID: 35647478
قاعدة البيانات: MEDLINE
الوصف
تدمد:2475-0379
DOI:10.1002/rth2.12733