A Prediction Model for Uncontrolled Type 2 Diabetes Mellitus Incorporating Area-level Social Determinants of Health
Abstract
Background Social determinants of health (SDH) at the area level are understood to influence the likelihood of having poor glycemic control for patients with type 2 diabetes mellitus (T2DM). Objectives To develop a model for predicting whether a person with T2DM has uncontrolled diabetes (hemoglobin A1c ≥9%), incorporating individual and area-level (census tract) covariates. Research design Development and validation of machine learning models. Subjects Total of N=1,015,808 privately insured persons in claims data with T2DM. Measures C-statistic, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. Results A standard logistic regression model selecting among the available individual-level covariates and area-level SDH covariates (at the census tract level) performed poorly, with a C-statistic of 0.685, sensitivity of 25.6%, specificity of 90.1%, positive predictive value of 56.9%, negative predictive value of 70.4%, and accuracy of 68.4% on a 25% held-out validation subset of the data. By contrast, machine learning models improved upon risk prediction, with the highest performance from a random forest algorithm with a C-statistic of 0.928, sensitivity of 68.5%, specificity of 94.6%, positive predictive value of 69.8%, negative predictive value of 94.3%, and accuracy of 90.6%. SDH variables alone explained 16.9% of variation in uncontrolled diabetes. Conclusions A predictive model developed through a machine learning approach may assist…
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Researchers and clinicians are using artificial intelligence to integrate electronic health records and social risk factors, such as neighborhood characteristics, to predict outcomes important to individuals with diabetes, including poor control.
“researchers and clinicians are using artificial intelligence (AI) to integrate electronic health records (EHRs) and social risk factors, such as neighborhood characteristics, to predict outcomes important to individuals with diabetes, including poor control [17-22].”
From An Assessment of How Clinicians and Staff Members Use a Diabetes Artificial Intelligence Prediction Tool: Mixed Methods Study (2023) · cites this paper as [17]
Models integrating both clinical and SDoH data may more effectively predict adverse events such as ED visits.
“Models integrating both clinical and SDoH data may more effectively predict adverse events such as ED visits [35–37].”
From Machine learning-driven risk prediction for post-hospitalization diabetes case management: Integrating clinical and social determinants of health (2026) · cites this paper as [36]
These findings suggest that predictive modeling benefits from capturing both scales of SDoH, with area-level indices providing broad contextual signals and individual-level measures offering more actionable insights for tailoring case management interventions.
“These findings suggest that predictive modeling benefits from capturing both scales of SDoH, with area-level indices providing broad contextual signals and individual-level measures offering more actionable insights for tailoring case management interventions [33,36,37].”
From Machine learning-driven risk prediction for post-hospitalization diabetes case management: Integrating clinical and social determinants of health (2026) · cites this paper as [36]
Cites
The Social Determinants of Health: Coming of Age
Braveman, P., Egerter, S., & Williams, D. R. (2011) · Annual Review of Public Health · doi:10.1146/annurev-publhealth-031210-101218 · Cited by 2,476 · see citing works
Recursive partitioning for heterogeneous causal effects
Athey, S., & Imbens, G. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1510489113 · Cited by 1,586 · see citing works
Neighborhoods, obesity, and diabetes—a randomized social experiment.
Ludwig, J., Sanbonmatsu, L., Gennetian, L., Adam, E., Duncan, G. J., Katz, L. F., Kessler, R. C., Kling, J. R., Lindau, S. T., Whitaker, R. C., et al. (2011) · New England Journal of Medicine · doi:10.1056/nejmsa1103216 · Cited by 964 · see citing works
Addressing Unmet Basic Resource Needs as Part of Chronic Cardiometabolic Disease Management
Berkowitz, S. A., Hulberg, A. C., Standish, S., Reznor, G., & Atlas, S. J. (2017) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2016.7691 · Cited by 237 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Early detection of type 2 diabetes mellitus using machine learning-based prediction models
Kopitar, L., Kocbek, P., Cilar, L., Sheikh, A., & Stiglic, G. (2020) · Scientific Reports · doi:10.1038/s41598-020-68771-z · Cited by 369 · see citing works
Chiu, Y. M., Courteau, J., Dufour, I., Vanasse, A., & Hudon, C. (2023) · Scientific Reports · doi:10.1038/s41598-023-27568-6 · Cited by 20 · see citing works
Liaw, W. R., Ramos Silva, Y., Soltero, E. G., Krist, A., & Stotts, A. L. (2023) · JMIR AI · doi:10.2196/45032 · Cited by 14 · see citing works
“To meet these goals, researchers and clinicians are using artificial intelligence (AI) to integrate electronic health records (EHRs) and social risk factors, such as neighborhood characteristics, to predict outcomes important to individuals with diabetes, including poor control [17-22].”
BackgroundLee, S.-Y., Saleem, M., Land, A. M., DeLaney, E. W., Garretson, A. R., Patel, M., Hall, A. G., Westrick, S., Ovalle, F., Cherrington, A. L., et al. (2026) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2026.106604
- Authors
- Basu, S., & Narayanaswamy, R.
- Affiliations
- Harvard University (US)
- KPMG (United States) (US)
- Corresponding author
- Basu, Sanjay
- ORCID
- Basu, Sanjay
- Venue
- Medical Care
- Published
- 2019-08
- Volume
- 57
- Issue
- 8
- Pages
- 592-600
- ISSN
- 0025-7079 (ISSN-L)
- OpenAlex
- W2954466797
- Cited by
- 33
- References
- 4
- Citations by year
- 2026: 1 · 2025: 6 · 2024: 4 · 2023: 11 · 2022: 2 · 2021: 6 · 2020: 3
- FWCI
- 2.23
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Medical Care (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Institutes of Health (1r21md012867-01)
- National Institute on Minority Health and Health Disparities (R21 MD012867)
- Topics
- Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Management and Research
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- type 2 diabetes, uncontrolled diabetes, glycemic control, HbA1c, social determinants of health, census tracts, risk prediction model, random forest, risk adjustment, privately insured patients
- MeSH terms
- Machine Learning, Aged, Diabetes Mellitus, Type 2, Female, Glycated Hemoglobin, Humans, Male, Middle Aged, Risk Factors, Models, Statistical, Logistic Models, Risk Assessment, Social Determinants of Health
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
