Automated detection and classification of type 1 versus type 2 diabetes using electronic health record data

Michael Klompas, Emma Eggleston, Jason McVetta, Ross Lazarus, Lingling Li, Richard Platt, Michael Klompas, Emma Eggleston, Jason McVetta, Ross Lazarus, Lingling Li, Richard Platt

Abstract

Objective: To create surveillance algorithms to detect diabetes and classify type 1 versus type 2 diabetes using structured electronic health record (EHR) data.

Research design and methods: We extracted 4 years of data from the EHR of a large, multisite, multispecialty ambulatory practice serving ∼700,000 patients. We flagged possible cases of diabetes using laboratory test results, diagnosis codes, and prescriptions. We assessed the sensitivity and positive predictive value of novel combinations of these data to classify type 1 versus type 2 diabetes among 210 individuals. We applied an optimized algorithm to a live, prospective, EHR-based surveillance system and reviewed 100 additional cases for validation.

Results: The diabetes algorithm flagged 43,177 patients. All criteria contributed unique cases: 78% had diabetes diagnosis codes, 66% fulfilled laboratory criteria, and 46% had suggestive prescriptions. The sensitivity and positive predictive value of ICD-9 codes for type 1 diabetes were 26% (95% CI 12-49) and 94% (83-100) for type 1 codes alone; 90% (81-95) and 57% (33-86) for two or more type 1 codes plus any number of type 2 codes. An optimized algorithm incorporating the ratio of type 1 versus type 2 codes, plasma C-peptide and autoantibody levels, and suggestive prescriptions flagged 66 of 66 (100% [96-100]) patients with type 1 diabetes. On validation, the optimized algorithm correctly classified 35 of 36 patients with type 1 diabetes (raw sensitivity, 97% [87-100], population-weighted sensitivity, 65% [36-100], and positive predictive value, 88% [78-98]).

Conclusions: Algorithms applied to EHR data detect more cases of diabetes than claims codes and reasonably discriminate between type 1 and type 2 diabetes.

Figures

Figure 1
Figure 1
Screenshot of the Electronic medical record Support for Public health (ESP) live EHR-based public health surveillance and reporting system. The map depicts the prevalence of type 2 diabetes by zip code among Atrius Health patients in Eastern Massachusetts. The system automatically detects diabetes and classifies patients as type 1 versus type 2 using data refreshed and analyzed nightly using the algorithms described in this article.

References

    1. Klompas M, McVetta J, Lazarus R, et al. Integrating clinical practice and public health surveillance using electronic medical record systems. Am J Prev Med 2012;42(6 Suppl. 2):S154–S162
    1. Vehik K, Hamman RF, Lezotte D, et al. Increasing incidence of type 1 diabetes in 0- to 17-year-old Colorado youth. Diabetes Care 2007;30:503–509
    1. Borchers AT, Uibo R, Gershwin ME. The geoepidemiology of type 1 diabetes. Autoimmun Rev 2010;9:A355–A365
    1. Dabelea D, Bell RA, D’Agostino RB, Jr, et al. Writing Group for the SEARCH for Diabetes in Youth Study Group Incidence of diabetes in youth in the United States. JAMA 2007;297:2716–2724
    1. TODAY Study Group; Zeitler P, Hirst K, Pyle L, et al. A clinical trial to maintain glycemic control in youth with type 2 diabetes. N Engl J Med 2012;366:2247–2256
    1. Petitti DB, Klingensmith GJ, Bell RA, et al. Glycemic control in youth with diabetes: the SEARCH for diabetes in Youth Study. J Pediatr 2009;155:668–672e1–3
    1. Rewers A, Klingensmith G, Davis C, et al. Presence of diabetic ketoacidosis at diagnosis of diabetes mellitus in youth: the Search for Diabetes in Youth Study. Pediatrics 2008;121:e1258–e1266
    1. American Diabetes Association Diagnosis and classification of diabetes mellitus. Diabetes Care 2011;34(Suppl. 1):S62–S69
    1. Lazarus R, Klompas M, Campion FX, et al. Electronic Support for Public Health: validated case finding and reporting for notifiable diseases using electronic medical data. J Am Med Inform Assoc 2009;16:18–24
    1. Blumenthal D, Tavenner M. The “meaningful use” regulation for electronic health records. N Engl J Med 2010;363:501–504
    1. Ng E, Dasgupta K, Johnson JA. An algorithm to differentiate diabetic respondents in the Canadian Community Health Survey. Health Rep 2008;19:71–79
    1. Chowdhury P, Balluz L, Town M, et al. Centers for Disease Control and Prevention (CDC) Surveillance of certain health behaviors and conditions among states and selected local areas - Behavioral Risk Factor Surveillance System, United States, 2007. MMWR Surveill Summ 2010;59:1–220
    1. Vanderloo SE, Johnson JA, Reimer K, et al. Validation of classification algorithms for childhood diabetes identified from administrative data. Pediatr Diabetes 2012;13:229–234
    1. Dabelea D, Pihoker C, Talton JW, et al. SEARCH for Diabetes in Youth Study Etiological approach to characterization of diabetes type: the SEARCH for Diabetes in Youth Study. Diabetes Care 2011;34:1628–1633
    1. Adler-Milstein J, Bates DW, Jha AKUS. U.S. Regional health information organizations: progress and challenges. Health Aff (Millwood) 2009;28:483–492
    1. Adler-Milstein J, DesRoches CM, Jha AK. Health information exchange among US hospitals. Am J Manag Care 2011;17:761–768
    1. Adler-Milstein J, Jha AK. Sharing clinical data electronically: a critical challenge for fixing the health care system. JAMA 2012;307:1695–1696
    1. Greenbaum CJ. Dead or alive? Diabetes Care 2012;35:459–460
    1. Amed S, Vanderloo SE, Metzger D, et al. Validation of diabetes case definitions using administrative claims data. Diabet Med 2011;28:424–427

Source: PubMed

Sponsorer og samarbejdspartnere

Medicinske tilstande

Narkotikainterventioner

3
Abonner