CoChat

Development and validation of a model for predicting incident type 2 diabetes using quantitative clinical data and a Bayesian logistic model: A nationwide cohort and modeling study

Open access

The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.

Abstract

BACKGROUND: Obesity is closely related to the development of insulin resistance and type 2 diabetes (T2D). The prevention of T2D has become imperative to stem the rising rates of this disease. Weight loss is highly effective in preventing T2D; however, the at-risk pool is large, and a clinically meaningful metric for risk stratification to guide interventions remains a challenge. The objective of this study is to predict T2D risk using full-information continuous analysis of nationally sampled data from white and black American adults age ≥45 years. METHODS AND FINDINGS: A sample of 12,043 black (33%) and white individuals from a population-based cohort, REasons for Geographic And Racial Differences in Stroke (REGARDS) (enrolled 2003-2007), was observed through 2013-2016. The mean participant age was 63.12 ± 8.62 years, and 43.7% were male. Mean BMI was 28.55 ± 5.61 kg/m2. Risk factors for T2D regularly recorded in the primary care setting were used to evaluate future T2D risk using Bayesian logistic regression. External validation was performed using 9,710 participants (19% black) from Atherosclerotic Risk in Communities (ARIC) (enrolled 1987-1989), observed through 1996-1998. The mean participant age in this cohort was 53.86 ± 5.65 years, and 44.6% were male. Mean BMI was 27.15 ± 4.92 kg/m2. Predictive performance was assessed using the receiver operating characteristic (ROC) curves and area under the curve (AUC) statistics. The primary outcome was incident T2D. By 2016 in REGARDS, there were 1,602 incident cases of T2D. Risk factors used to predict T2D progression included age, sex, race, BMI, triglycerides, high-density lipoprotein, blood pressure, and blood glucose. The Bayesian logistic model (AUC = 0.79) outperformed the Framingham risk score (AUC = 0.76), the American Diabetes Association risk score (AUC = 0.64), and a cardiometabolic disease system (using Adult Treatment Panel III criteria) (AUC = 0.75). Validation in ARIC was robust (AUC = 0.85). Main limitations include the limited generalizability of the REGARDS sample to black and white, older Americans, and no time to diagnosis for T2D. CONCLUSIONS: Our results show that a Bayesian logistic model using full-information continuous predictors has high predictive discrimination, and can be used to quantify race- and sex-specific T2D risk, providing a new, powerful predictive tool. This tool can be used for T2D prevention efforts including weight loss therapy by allowing clinicians to target high-risk individuals in a manner that could be used to optimize outcomes.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pmed.1003232

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig 1 Odds ratios of incident type 2 diabetes for individual risk factors used to construct the fitted main-effect logistic model. The points and lines present the estimated values and 95% CIs, respectively. Odds ratios are as follows: systolic blood pressure (SBP), 1.006 (95% CI 1.001 to 1.011); diastolic blood pressure (DBP), 1.003 (95% CI 0.995 to 1.012); blood glucose (BG), 1.064 (95% CI 1.059 to 1.069); BMI, 1.055 (95% CI 1.044 to 1.066); high-density lipoprotein (HDL) cholesterol, 0.982 (95% CI 0.979 to 0.987); triglycerides (TG), 1.001 (95% CI 1.001 to 1.002); age, 0.987 (95% CI 0.979 to 0.994); white race (raceW), 0.628 (95% CI 0.556 to 0.709); male sex (sexM), 0.919 (95% CI 0.808 to 1.046). The references for the binary predictors race and sex are black and female, respectively.
Fig 1 Odds ratios of incident type 2 diabetes for individual risk factors used to construct the fitted main-effect logistic model. The points and lines present the estimated values and 95% CIs, respectively. Odds ratios are as follows: systolic blood pressure (SBP), 1.006 (95% CI 1.001 to 1.011); diastolic blood pressure (DBP), 1.003 (95% CI 0.995 to 1.012); blood glucose (BG), 1.064 (95% CI 1.059 to 1.069); BMI, 1.055 (95% CI 1.044 to 1.066); high-density lipoprotein (HDL) cholesterol, 0.982 (95% CI 0.979 to 0.987); triglycerides (TG), 1.001 (95% CI 1.001 to 1.002); age, 0.987 (95% CI 0.979 to 0.994); white race (raceW), 0.628 (95% CI 0.556 to 0.709); male sex (sexM), 0.919 (95% CI 0.808 to 1.046). The references for the binary predictors race and sex are black and female, respectively.CC BY · PubMed Central
Fig 2 Receiver operating characteristic curves for the Bayesian logistic model (BhGLM), the CMDS score based on discontinuous ATP III criteria, the Framingham risk score, and the American Diabetes Association risk score in the REGARDS cohort. The Bayesian score included the following risk factors: age, sex, race, BMI, triglycerides, HDL cholesterol, blood pressure, and blood glucose. The CMDS score using ATP III criteria thresholds included sex, race, BMI, triglycerides, HDL cholesterol, blood pressure, and blood glucose using binary ATP III criteria. The Framingham risk score was a simple clinical score using fasting glucose, BMI, HDL cholesterol, triglycerides, and blood pressure. The American Diabetes Association risk score included age, sex, blood pressure, BMI, and physical activity. ATP III, Adult Treatment Panel III; CMDS, cardiometabolic disease staging; HDL, high-density lipoprotein; REGARDS, REasons for Geographic And Racial Differences in Stroke.
Fig 2 Receiver operating characteristic curves for the Bayesian logistic model (BhGLM), the CMDS score based on discontinuous ATP III criteria, the Framingham risk score, and the American Diabetes Association risk score in the REGARDS cohort. The Bayesian score included the following risk factors: age, sex, race, BMI, triglycerides, HDL cholesterol, blood pressure, and blood glucose. The CMDS score using ATP III criteria thresholds included sex, race, BMI, triglycerides, HDL cholesterol, blood pressure, and blood glucose using binary ATP III criteria. The Framingham risk score was a simple clinical score using fasting glucose, BMI, HDL cholesterol, triglycerides, and blood pressure. The American Diabetes Association risk score included age, sex, blood pressure, BMI, and physical activity. ATP III, Adult Treatment Panel III; CMDS, cardiometabolic disease staging; HDL, high-density lipoprotein; REGARDS, REasons for Geographic And Racial Differences in Stroke.CC BY · PubMed Central
Fig 3 Predicted probabilities for each predictor associated with type 2 diabetes by sex and race. (A) By sex. (B) By race. B, black; F, female; HDL, high-density lipoprotein; M, male; W, white.
Fig 3 Predicted probabilities for each predictor associated with type 2 diabetes by sex and race. (A) By sex. (B) By race. B, black; F, female; HDL, high-density lipoprotein; M, male; W, white.CC BY · PubMed Central
Fig 4 Validity of predictions of incident type 2 diabetes in the development sample for white and black populations. The distribution of predicted probabilities is shown at the bottom of the graphs. The mean and median of the predicted probability are also shown. The triangles indicate the observed frequencies by deciles of predicted probability.
Fig 4 Validity of predictions of incident type 2 diabetes in the development sample for white and black populations. The distribution of predicted probabilities is shown at the bottom of the graphs. The mean and median of the predicted probability are also shown. The triangles indicate the observed frequencies by deciles of predicted probability.CC BY · PubMed Central

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Show all 35 references

Research works printed but not linked: 1

  1. Centers for Disease Control and Prevention, 2017, National diabetes statistics report 2017: estimates of diabetes and its burden in the United States

Cited by

Metadata

Authors
Wilkinson, L., Yi, N., Mehta, T., Judd, S., & Garvey, W. T.
Affiliations
University of Alabama at Birmingham (US)
Corresponding author
Wilkinson, Lua
Venue
PLOS Medicine
Published
2020-08-07
Volume
17
Issue
8
Pages
e1003232
ISSN
  • 1549-1277 (ISSN-L)
  • 1549-1676
OpenAlex
W3047734392
Cited by
47
References
35
Citations by year
2026: 9 · 2025: 8 · 2024: 2 · 2023: 12 · 2022: 9 · 2021: 7
FWCI
5.28
Type
journal article
Language
en
Open access
Locations
  • PLoS Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Institute of Neurological Disorders and Stroke (NS041588)
  • National Institute on Aging (NS041588)
  • National Institute of Diabetes and Digestive and Kidney Diseases (DK062710, DK056336)
  • American Heart Association (17SFRN33610070)
  • Merit Review Program (I01CX000432)
  • UAB Diabetes Research Center (P30 DK079626)
Topics
  • Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes, Cardiovascular Risks, and Lipoproteins
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
type 2 diabetes, diabetes risk prediction, Bayesian logistic regression, obesity, insulin resistance, risk stratification, weight loss, REGARDS cohort, ARIC cohort, Framingham risk score, Atherosclerosis Risk in Communities Study, triglycerides, HDL cholesterol, blood pressure, blood glucose, racial differences, Black people, White adults, middle-aged and older adults, external validation, cardiometabolic risk
MeSH terms
Aged, Aged, 80 and over, Bayes Theorem, Black or African American, Blood Glucose, Data Interpretation, Statistical, Diabetes Mellitus, Type 2, Female, Follow-Up Studies, Humans, Insulin Resistance, Longitudinal Studies, Male, Middle Aged, Obesity, Predictive Value of Tests, Reproducibility of Results, Cohort Studies, Incidence, Logistic Models, White People

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.