Electronic health record phenotyping improves detection and screening of type 2 diabetes in the general United States population: A cross-sectional, unselected, retrospective study
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Objectives An estimated 25% of type two diabetes mellitus (DM2) patients in the United States are undiagnosed due to inadequate screening, because it is prohibitive to administer laboratory tests to everyone. We assess whether electronic health record (EHR) phenotyping could improve DM2 screening compared to conventional models, even when records are incomplete and not recorded systematically across patients and practice locations, as is typically seen in practice. Methods In this cross-sectional, retrospective study, EHR data from 9948 US patients were used to develop a pre-screening tool to predict current DM2, using multivariate logistic regression and a random-forests probabilistic model for out-of-sample validation. We compared (1) a full EHR model containing commonly prescribed medications, diagnoses (as ICD9 categories), and conventional predictors, (2) a restricted EHR DX model which excluded medications, and (3) a conventional model containing basic predictors and their interactions (BMI, age, sex, smoking status, hypertension). Results Using a patient’s full EHR or restricted EHR was superior to using basic covariates alone for detecting individuals with diabetes (hierarchical X2 test, p < 0.001). Migraines, depot medroxyprogesterone acetate, and cardiac dysrhythmias were associated negatively with DM2, while sexual and gender identity disorder diagnosis, viral and chlamydial infections, and herpes zoster were associated positively. Adding EHR phenotypes improved classification; the AUC for the full EHR Model, EHR DX model, and conventional model using logistic regression, were 84.9%, 83.2%, and 75.0% respectively. For random forest machine learning out-of-sample prediction, accuracy also was improved when using EHR phenotypes; the AUC values were 81.3%, 79.6%, and 74.8%, respectively. Improved AUCs reflect better performance for most thresholds that balance sensitivity and specificity. Conclusions EHR phenotyping resulted in markedly superior detection of DM2, even in the face of missing and unsystematically recorded data, based on the ROC curves. EHR phenotypes could more efficiently identify which patients do require, and don’t require, further laboratory screening. When applied to the current number of undiagnosed individuals in the United States, we predict that incorporating EHR phenotype screening would identify an additional 400,000 patients with active, untreated diabetes compared to the conventional pre-screening models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Tuomilehto, J., Lindström, J., Eriksson, J. G., Valle, T. T., Hämäläinen, H., Ilanne-Parikka, P., Keinänen-Kiukaanniemi, S., Laakso, M., Louheranta, A., Rastas, M., et al. (2001) · New England Journal of Medicine · doi:10.1056/nejm200105033441801 · Cited by 10,873
Grundy, S. M., Brewer, H. B., Cleeman, J. I., Smith, S. C., & Lenfant, C. (2004) · Circulation · doi:10.1161/01.cir.0000111245.75752.c6 · Cited by 5,982
Economic Costs of Diabetes in the U.S. in 2002
American Diabetes Association (2003) · Diabetes Care · doi:10.2337/diacare.26.3.917 · Cited by 4,147
On the adaptive control of the false discovery rate in multiple testing with independent statistics
Benjamini, Y., & Hochberg, Y. (2000) · Journal of Educational and Behavioral Statistics · doi:10.3102/10769986025001060 · Cited by 2,015 · cited 1×
“Even though DM2 has been shown to affect innate or acute immunity [23], we are unaware of a strong link between DM2 and allergies, which primarily”
BackgroundInflammation and Activated Innate Immunity in the Pathogenesis of Type 2 Diabetes
Pickup, J. C. (2004) · Diabetes Care · doi:10.2337/diacare.27.3.813 · Cited by 1,414
Lim, E. L., Hollingsworth, K. G., Aribisala, B. S., Chen, M. J., Mathers, J. C., & Taylor, R. (2011) · Diabetologia · doi:10.1007/s00125-011-2204-7 · Cited by 1,164
Hersh, W. R., Weiner, M. G., Embi, P. J., Logan, J. R., Payne, P. R. O., Bernstam, E. V., Lehmann, H. P., Hripcsak, G., Hartzog, T. H., Cimino, J. J., et al. (2013) · Medical Care · doi:10.1097/mlr.0b013e31829b1dbd · Cited by 567
Undiagnosed NIDDM: Clinical and Public Health Issues
Harris, M. I. (1993) · Diabetes Care · doi:10.2337/diacare.16.4.642 · Cited by 460 · cited 1×
“However, given the finding that DM2 was diagnosed most frequently after a patient exhibited at least one complication, and that 25% of patients are unrecorded [28], both early prediction and identification of untreated DM2 are critical to clinical practice.”
BackgroundKahn, R., Alperin, P., Eddy, D., Borch-Johnsen, K., Buse, J., Feigelman, J., Gregg, E., Holman, R. R., Kirkman, M. S., Stern, M., et al. (2010) · The Lancet · doi:10.1016/s0140-6736(09)62162-0 · Cited by 287
Pagano, G., Cavallo-Perin, P., Cassader, M., Bruno, A., Ozzello, A., Masciola, P., Dall'omo, A. M., & Imbimbo, B. (1983) · Journal of Clinical Investigation · doi:10.1172/jci111141 · Cited by 259
Exalto, L. G., Biessels, G. J., Karter, A. J., Huang, E. S., Katon, W. J., Minkoff, J. R., & Whitmer, R. A. (2013) · The Lancet Diabetes & Endocrinology · doi:10.1016/s2213-8587(13)70048-2 · Cited by 244
Tools for Predicting the Risk of Type 2 Diabetes in Daily Practice
Schwarz, P., Li, J., Lindstrom, J., & Tuomilehto, J. (2009) · Hormone and Metabolic Research · doi:10.1055/s-0028-1087203 · Cited by 213
Cited by
Christodoulou, E., Ma, J., Collins, G. S., Steyerberg, E. W., Verbakel, J. Y., & Van Calster, B. (2019) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2019.02.004 · Cited by 2,119
Machine learning and data mining methods in diabetes research
Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I., & Chouvarda, I. (2017) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2016.12.005 · Cited by 1,445
Predicting Type 2 Diabetes Using Logistic Regression and Machine Learning Approaches
Joshi, R. D., & Dhakal, C. K. (2021) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph18147346 · Cited by 260
Predicting the onset of type 2 diabetes using wide and deep learning with electronic health records
Nguyen, B. P., Pham, H. N., Tran, H., Nghiem, N., Nguyen, Q. H., Do, T. T. T., Tran, C. T., & Simpson, C. R. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.105055 · Cited by 158
The War on Diabetic Retinopathy: Where Are We Now?
Wong, T. Y., & Sabanayagam, C. (2019) · Asia-Pacific Journal of Ophthalmology · doi:10.1097/apo.0000000000000267 · Cited by 84
“A retrospective study using large number of EMR data in the United States found that EMRderived phenotypes markedly improved the detection of diabetes even when records are incomplete, and are not recorded systematically across patients and practice locations.(62) Applying the EMR-derived predictive algorithm to the c…”
Metadata
- Authors
- Anderson, A. E., Kerr, W. T., Thames, A., Li, T., Xiao, J., & Cohen, M. S.
- Venue
- Journal of Biomedical Informatics
- Publisher
- Elsevier BV
- Published
- 2016-04
- Volume
- 60
- Pages
- 162-168
- ISSN
- 1532-0464 (ISSN-L)
- OpenAlex
- W1816688868
- Cited by
- 96
- References
- 13
- FWCI
- 6.26
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.