CoChat
Sign Up
Cited by 369Artificial Intelligence in HealthcareMachine Learning in HealthcareDiabetes Management and Research

The DOI matches its Crossref record; 49 of the 50 references it cites were found in a registry or an index.

Early detection of type 2 diabetes mellitus using machine learning-based prediction models

Open access
Kopitar, Leon, Kocbek, Primoz, Cilar, Leona, Sheikh, Aziz, Stiglic, Gregor·2020·Scientific Reports
DOI 10.1038/s41598-020-68771-zPMC PMC7371679
Open this paper in CoChat — free accountOpen PDF

Abstract

Most screening tests for T2DM in use today were developed using multivariate regression methods that are often further simplified to allow transformation into a scoring formula. The increasing volume of electronically collected data opened the opportunity to develop more complex, accurate prediction models that can be continuously updated using machine learning approaches. This study compares machine learning-based prediction models (i.e. Glmnet, RF, XGBoost, LightGBM) to commonly used regression models for prediction of undiagnosed T2DM. The performance in prediction of fasting plasma glucose level was measured using 100 bootstrap iterations in different subsets of data simulating new incoming data in 6-month batches. With 6 months of data available, simple regression model performed with the lowest average RMSE of 0.838, followed by RF (0.842), LightGBM (0.846), Glmnet (0.859) and XGBoost (0.881). When more data were added, Glmnet improved with the highest rate (+ 3.4%). The highest level of variable selection stability over time was observed with LightGBM models. Our results show no clinically relevant improvement when more sophisticated prediction models were used. Since higher stability of selected variables over time contributes to simpler interpretation of the models, interpretability and model calibration should also be considered in development of clinical prediction models.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1038/s41598-020-68771-z

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Flow diagram of data pre-processing.
Figure 1 Flow diagram of data pre-processing.CC BY · PubMed Central
Figure 2 Variable importance. Ranking of variables for Glmnet (A), LightGBM (B), Random Forest (C) and XGBoost (D) over the observed period (T6–T30).
Figure 2 Variable importance. Ranking of variables for Glmnet (A), LightGBM (B), Random Forest (C) and XGBoost (D) over the observed period (T6–T30).CC BY · PubMed Central
Figure 3 Actual vs. predicted plots. Visualisation of actual vs. predicted values for all predictive models (lm, Glmnet, LightGBM, RF, XGBoost) in three time points (T6, T18 and T30) reveal discrepancies in calibration of the compared models. Additional classification performance results in terms of TP, FP, TN and FN are provided where it can be seen that lm, Glmnet and RF outperformed both boosting based methods by identifying more TP as well as TN cases. Model-time point combinations are represented in the following way: lm 6, 18 and 30 months (A–C), Glmnet 6, 18 and 30 months (D–F), LightGBM 6, 18 and 30 months (G–I), RF 6, 18 and 30 months (J–L), XGBoost 6, 8 and 30 months (M–O).
Figure 3 Actual vs. predicted plots. Visualisation of actual vs. predicted values for all predictive models (lm, Glmnet, LightGBM, RF, XGBoost) in three time points (T6, T18 and T30) reveal discrepancies in calibration of the compared models. Additional classification performance results in terms of TP, FP, TN and FN are provided where it can be seen that lm, Glmnet and RF outperformed both boosting based methods by identifying more TP as well as TN cases. Model-time point combinations are represented in the following way: lm 6, 18 and 30 months (A–C), Glmnet 6, 18 and 30 months (D–F), LightGBM 6, 18 and 30 months (G–I), RF 6, 18 and 30 months (J–L), XGBoost 6, 8 and 30 months (M–O).CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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 50 references

Research works printed but not linked: 2

  1. Ziegel, E. R. & Harville, D. A. Matrix Algebra From a Statisticians Perspective (Springer, New York, 1997).
  2. Breiman, L. Random forests. Mach. Learn. 45, 5–32. https://doi.org/10.1023/A:1010933404324 (2001). · DOI · Paper page

Cited by

Sorted by citations

See all 369

Related

Metadata

Authors
Kopitar, L., Kocbek, P., Cilar, L., Sheikh, A., & Stiglic, G.
Affiliations
  • University of Primorska (SI)
  • University of Maribor (SI)
  • Brigham and Women's Hospital (US)
Corresponding author
Kopitar, Leon
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2020-07-20
Volume
10
Issue
1
Pages
11981-11981
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-020-68771-z
PMC
PMC7371679
OpenAlex
W3043363778
Cited by
369
References
50
Citations by year
2026: 37 · 2025: 71 · 2024: 77 · 2023: 80 · 2022: 69 · 2021: 32 · 2020: 3
FWCI
40.61
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, other-oa)
Funders
  • European Commission (2014‐2020, P2-0057)
  • Javna Agencija za Raziskovalno Dejavnost RS (N2-0101, P2-0057)
  • Univerza v Mariboru
  • European Social Fund (20142020)
Topics
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Management and Research
Keywords
type 2 diabetes, early detection, diabetes screening, prediction model, machine learning, fasting blood glucose, regression models, model interpretability, model calibration, LightGBM, XGBoost, random forest, glmnet
MeSH terms
Machine Learning, Blood Glucose, Calibration, Diabetes Mellitus, Type 2, Fasting, Female, Humans, Male, Middle Aged, Models, Biological, Area Under Curve, Early Diagnosis

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