Objective  To develop and validate data extraction and patient identification algorithms for cutaneous lupus erythematosus (CLE) and its two subtypes, discoid lupus erythematosus (DLE) and subacute cutaneous lupus erythematosus (SCLE), and to enable high-efficiency patient identification in large-scale electronic health databases.

Methods This study utilized data from the 2013-2017 National Insurance Claims for Epidemiological Research (NICER) to construct data extraction and rapid patient identification algorithms. The manual verification results were used as gold standard to assess the sensitivity and specificity of the algorithms. Additionally, the basic characteristics of the identified patients were analyzed.

Results  Initially, standardized expressions were developed based on medical terminology and diagnostic codes. These were further refined with input from clinicians to include potential synonyms and common misspellings, improving the preliminary screening expressions. Through iterative verification by clinicians and data management engineers, a final disease-specific screening algorithm was established. The developed extraction and identification algorithms for all 3 targeted disease demonstrated strong performance, with sensitivity values of 0.985, 1.000, and 0.991, and specificity values of 0.997, 0.999, and 0.998 for CLE, DLE, and SCLE, respectively. A total of 34,554 CLE cases, including 2,879 DLE cases, and 623 SCLE cases were identified between 2013 and 2017, with a higher prevalence among females than males.

Conclusion  This study developed and validated an identification algorithm for CLE patients based on medical insurance databases, demonstrating high performance. The proposed algorithm provides a methodological framework and empirical evidence for designing and optimizing big data-driven rapid patient identification algorithms in dermatology research.

1.中华医学会皮肤性病学分会红斑狼疮研究中心. 皮肤型红斑狼疮诊疗指南（2019版）[J]. 中华皮肤科杂志, 2019, 52(3): 149-155. [Centre for Lupus Erythematosus Research, Chinese Society of Dermatology. Guideline for diagnosis and treatment of cutaneous lupus erythematosus(2019)[J]. Chinese Journal of Dermatology, 2019, 52(3): 149-155.] DOI: 10.3760/cma.j.issn.0412-4030.2019.03.001.

2.Stull C, Sprow G, Werth VP. Cutaneous involvement in systemic lupus erythematosus: a review for the rheumatologist[J]. J Rheumatol, 2023, 50(1): 27-35. DOI: 10.3899/jrheum.220089.

3.Curtiss P, Walker AM, Chong BF. A systematic review of the progression of cutaneous lupus to systemic lupus erythematosus[J]. Front Immunol, 2022, 13: 866319. DOI: 10.3389/fimmu.2022. 866319.

4.Lu Q, Long H, Chow S, et al. Guideline for the diagnosis, treatment and long-term management of cutaneous lupus erythematosus[J]. J Autoimmun, 2021, 123: 102707. DOI: 10.1016/j.jaut.2021. 102707.

5.Gronhagen CM, Fored CM, Granath F, et al. Cutaneous lupus erythematosus and the association with systemic lupus erythematosus: a population-based cohort of 1088 patients in Sweden[J]. Br J Dermatol, 2011, 164(6): 1335-1341. DOI: 10.1111/j.1365-2133.2011.10272.x.

6.Gilliam JN, Sontheimer RD. Distinctive cutaneous subsets in the spectrum of lupus erythematosus[J]. J Am Acad Dermatol, 1981, 4(4): 471-475. DOI: 10.1016/s0190-9622(81)80261-7.

7.Chang YC, Werth VP. Update on epidemiology and clinical assessment tools of cutaneous lupus erythematosus and dermatomyositis[J]. Curr Dermatol Rep, 2013, 2(1): 48-57. DOI: 10.1007/s13671-012-0037-3.

8.Tebbe B, Orfanos CE. Epidemiology and socioeconomic impact of skin disease in lupus erythematosus[J]. Lupus, 1997, 6(2): 96-104. DOI: 10.1177/096120339700600204.

9.Fernández Ávila DG, Rivera Maldonado M, Charry Anzola LP. Epidemiology and demographics of cutaneous lupus erythematosus in Colombia between 2015 and 2019[J]. Reumatismo, 2023, 75(1): 23-27. DOI: 10.4081/reumatismo.2023.1568.

10.Mathai SC, Hemnes AR, Manaker S, et al. Identifying patients with pulmonary arterial hypertension using administrative claims algorithms[J]. Ann Am Thorac Soc, 2019, 16(7): 797-806. DOI: 10.1513/AnnalsATS.201810-672CME.

11.Park JS, Lee CH. Clinical study using healthcare claims database[J]. J Rheum Dis, 2021, 28(3): 119-125. DOI: 10.4078/jrd.2021.28.3.119.

12.Tian Y, Liu H, Si Y, et al. Association between temperature variability and daily hospital admissions for cause-specific cardiovascular disease in urban China: a national time-series study[J]. PLoS Med, 2019, 16(1): e1002738. DOI: 10.1371/journal.pmed.1002738.

13.Li M, Li C, Cao M, et al. Incidence and prevalence of systemic lupus erythematosus in urban China, 2013-2017: a nationwide population-based study[J]. Sci Bull (Beijing), 2024, 69(19): 3089-3097. DOI: 10.1016/j.scib.2024.04.075.

14.Zhang C, Feng J, Wang S, et al. Incidence of and trends in hip fracture among adults in urban China: a nationwide retrospective cohort study[J]. PLoS Med, 2020, 17(8): e1003180. DOI: 10.1371/journal.pmed.1003180.

15.Li Y, Malik V, Hu FB. Health insurance in China: after declining in the 1990s, coverage rates rebounded to near-universal levels by 2011[J]. Health Aff (Millwood), 2017, 36(8): 1452-1460. DOI: 10.1377/hlthaff.2016.1658.

16.Vale ECSD, Garcia LC. Cutaneous lupus erythematosus: a review of etiopathogenic, clinical, diagnostic and therapeutic aspects[J]. An Bras Dermatol, 2023, 98(3): 355-372. DOI: 10.1016/j.abd. 2022.09.005.

17.国家卫生健康委. 疾病分类与代码（GB/T 14396-2016）[S/OL]. (2016-10-13) [2025-05-29]. https://openstd.samr.gov.cn/bzgk/std/newGbInfo?hcno=8127A7785CA677952F9DA062463CBC41.

18.Worm M, Zidane M, Eisert L, et al. S2k guideline: diagnosis and management of cutaneous lupus erythematosus-Part 1: Classification, diagnosis, prevention, activity scores[J]. J Dtsch Dermatol Ges, 2021, 19(8): 1236-1247. DOI: 10.1111/ddg.14492.

19.Yan S, Melnick K, He X, et al. Developing a computable phenotype for glioblastoma[J]. Neuro Oncol, 2024, 26(6): 1163-1170. DOI: 10.1093/neuonc/noad249.

20.Tian H, Yang W, Hu Y, et al. Estimating cancer incidence based on claims data from medical insurance systems in two areas lacking cancer registries in China[J]. EClinicalMedicine, 2020, 20: 100312. DOI: 10.1016/j.eclinm.2020.100312.

21.Cho SK, Vazquez T, Werth VP. Litifilimab (BIIB059), a promising investigational drug for cutaneous lupus erythematosus[J]. Expert Opin Investig Drugs, 2023, 32(5): 345-353. DOI: 10.1080/13543784.2023.2212154.

22.Xie L, Lopes Almeida Gomes L, Stone CJ, et al. An update on clinical trials for cutaneous lupus erythematosus[J]. J Dermatol, 2024, 51(7): 885-894. DOI: 10.1111/1346-8138.17161.

23.Cho YM, Furie R. The development of litifilimab (BIIB 059) for cutaneous and systemic lupus erythematosus[J]. Immunotherapy, 2024, 16(1): 15-20. DOI: 10.2217/imt-2023-0086.

24.Sherman RE, Anderson SA, Dal Pan GJ, et al. Real-world evidence-What is it and what can it tell us?[J]. N Engl J Med, 2016, 375(23): 2293-2297. DOI: 10.1056/NEJMsb1609216.

25.Girman CJ, Ritchey ME, Lo Re V 3rd. Real-world data: assessing electronic health records and medical claims data to support regulatory decision-making for drug and biological products[J]. Pharmacoepidemiol Drug Saf, 2022, 31(7): 717-720. DOI: 10.1002/pds.5444.

26.Wang HY, Du J, Yang Y, et al. Rapid identification of chronic kidney disease in electronic health record database using computable phenotype combining a common data model[J]. Chin Med J (Engl), 2023, 136(7): 874-876. DOI: 10.1097/cm9.0000000000002168.

27.Dawwas GK, Weiss A, Constant BD, et al. Development and validation of claims-based definitions to identify incident and prevalent inflammatory bowel disease in administrative healthcare databases[J]. Inflamm Bowel Dis, 2023, 29(12): 1993-1996. DOI: 10.1093/ibd/izad053.

28.McBrien KA, Souri S, Symonds NE, et al. Identification of validated case definitions for medical conditions used in primary care electronic medical record databases: a systematic review[J]. J Am Med Inform Assoc, 2018, 25(11): 1567-1578. DOI: 10.1093/jamia/ocy094.

29.Hirsch AG, Scheck McAlearney A. Measuring diabetes care performance using electronic health record data: the impact of diabetes definitions on performance measure outcomes[J]. Am J Med Qual, 2014, 29(4): 292-299. DOI: 10.1177/1062860613500808.

30.Barnado A, Casey C, Carroll RJ, et al. Developing electronic health record algorithms that accurately identify patients with systemic lupus erythematosus[J]. Arthritis Care Res (Hoboken), 2017, 69(5): 687-693. DOI: 10.1002/acr.22989.

31.Swerdel JN, Ramcharran D, Hardin J. Using a data-driven approach for the development and evaluation of phenotype algorithms for systemic lupus erythematosus[J]. PLoS One, 2023, 18(2): e0281929. DOI: 10.1371/journal.pone.0281929.

32.Goetz I, Choong C, Winnie J, et al. Development of a claims-based flare algorithm for systemic lupus erythematosus[J]. Curr Med Res Opin, 2022, 38(9): 1641-1649. DOI: 10.1080/03007995. 2022.2101804.

33.Wu SS, Perry A, Zimmerman NM, et al. Predictors of flare-related inpatient or emergency department stay in systemic lupus erythematosus: a real-world analysis of Medicaid claims in the United States[J]. J Manag Care Spec Pharm, 2024, 30(1): 61-70. DOI: 10.18553/jmcp.2024.30.1.61.

34.Tang M, Goldstein BA, He J, et al. Performance of a computable phenotype for pediatric asthma using the problem list[J]. Ann Allergy Asthma Immunol, 2020, 125(5): 611-613. e1. DOI: 10.1016/j.anai.2020.07.009.

35.Graham J, Iverson A, Monteiro J, et al. Applying computable phenotypes within a common data model to identify heart failure patients for an implantable cardiac device registry[J]. Int J Cardiol Heart Vasc, 2022, 39: 100974. DOI: 10.1016/j.ijcha.2022.100974.

36.Baek YS, Park SH, Baek J, et al. Cutaneous lupus erythematosus and its association with systemic lupus erythematosus: a nationwide population-based cohort study in Korea[J]. J Dermatol, 2020, 47(2): 163-165. DOI: 10.1111/1346-8138.15162.

37.Moores KG, Sathe NA. A systematic review of validated methods for identifying systemic lupus erythematosus (SLE) using administrative or claims data[J]. Vaccine, 2013, 31 Suppl 10: K62-73. DOI: 10.1016/j.vaccine.2013.06.104.

38.Maillet M, Tounkara BS, Vagner D, et al. Epidemiology of isolated cutaneous lupus erythematosus in the multiethnic population of Reunion Island (France): a retrospective multicentric study[J]. J Rheumatol, 2025, 52(3): 251-256. DOI: 10.3899/jrheum.2024-0661.

39.Petersen MP, Möller S, Bygum A, et al. Epidemiology of cutaneous lupus erythematosus and the associated risk of systemic lupus erythematosus: a nationwide cohort study in Denmark[J]. Lupus, 2018, 27(9): 1424-1430. DOI: 10.1177/0961203318777103.

40.Durosaro O, Davis MD, Reed KB, et al. Incidence of cutaneous lupus erythematosus, 1965-2005: a population-based study[J]. Arch Dermatol, 2009, 145(3): 249-253. DOI: 10.1001/archdermatol.2009.21.

41.Maillet M, Tounkara BS, Vagner D, et al. Epidemiology of isolated cutaneous lupus erythematosus in the multiethnic population of Reunion Island: a retrospective multicenter study[J]. J Rheumatol, 2025, 52(3): 251-256. DOI: 10.3899/jrheum.2024-0661.

42.Lusk JB, Choi S, Clark AG, et al. Dementia and Parkinson's disease diagnoses in electronic health records vs. medicare claims data: a study of 101,980 linked patients[J]. BMC Neurol, 2023, 23(1): 325. DOI: 10.1186/s12883-023-03361-w.

43.Choi YC, Zhang D, Tyczynski JE. Comparison between health insurance claims and electronic health records (EHRs) for metastatic non-small-cell lung cancer (NSCLC) patient characteristics and treatment patterns: a retrospective cohort study[J]. Drugs Real World Outcomes, 2021, 8(4): 577-587. DOI: 10.1007/s40801-021-00269-0.

44.Laws MB, Michaud J, Shield R, et al. Comparison of electronic health record-based and claims-based diabetes care quality measures: causes of discrepancies[J]. Health Serv Res, 2018, 53 (Suppl 1): 2988-3006. DOI: 10.1111/1475-6773.12819.

45.Carrell DS, Gruber S, Floyd JS, et al. Improving methods of identifying anaphylaxis for medical product safety surveillance using natural language processing and machine learning[J]. Am J Epidemiol, 2023, 192(2): 283-295. DOI: 10.1093/aje/kwac182.