CoChat
Sign Up
Cited by 36Artificial Intelligence in HealthcareDiabetes, Cardiovascular Risks, and LipoproteinsMachine Learning in Healthcare

Prediction model for cardiovascular disease in patients with diabetes using machine learning derived and validated in two independent Korean cohorts

Open access
Sang, Hyunji, Lee, Hojae, Lee, Myeongcheol, Park, Jaeyu, Kim, Sunyoung, Woo, Ho Geol, Rahmati, Masoud, Koyanagi, Ai +7 more·2024·Scientific Reports
DOI 10.1038/s41598-024-63798-yPMC PMC11213851
Open this paper in CoChat — free accountOpen PDF

Abstract

This study aimed to develop and validate a machine learning (ML) model tailored to the Korean population with type 2 diabetes mellitus (T2DM) to provide a superior method for predicting the development of cardiovascular disease (CVD), a major chronic complication in these patients. We used data from two cohorts, namely the discovery (one hospital; n = 12,809) and validation (two hospitals; n = 2019) cohorts, recruited between 2008 and 2022. The outcome of interest was the presence or absence of CVD at 3 years. We selected various ML-based models with hyperparameter tuning in the discovery cohort and performed area under the receiver operating characteristic curve (AUROC) analysis in the validation cohort. CVD was observed in 1238 (10.2%) patients in the discovery cohort. The random forest (RF) model exhibited the best overall performance among the models, with an AUROC of 0.830 (95% confidence interval [CI] 0.818–0.842) in the discovery dataset and 0.722 (95% CI 0.660–0.783) in the validation dataset. Creatinine and glycated hemoglobin levels were the most influential factors in the RF model. This study introduces a pioneering ML-based model for predicting CVD in Korean patients with T2DM, outperforming existing prediction tools and providing a groundbreaking approach for early personalized preventive medicine.

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/s41598-024-63798-y

Cites

Statistics

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.

The citation lists haven’t been fetched yet

References 43 · Cited by 36

Research works printed but not linked: 39

  1. [1]Dinh A Miertschin S Young A Mohanty SD A data-driven approach to predicting diabetes and cardiovascular disease with machine learning BMC Med. Inform. Decis. Mak. 2019 19 211 10.1186/s12911-019-0918-5 31694707 PMC6836338 · DOI
  2. [4]Lindstrom J Improved lifestyle and decreased diabetes risk over 13 years: Long-term follow-up of the randomised Finnish Diabetes Prevention Study (DPS) Diabetologia 2013 56 284 293 10.1007/s00125-012-2752-5 23093136 · DOI · Paper page
  3. [5]American Diabetes Association Professional Practice Committee. 10. Cardiovascular Disease and Risk Management: Standards of Care in Diabetes—2024. Diabetes Care47, S179–S218. 10.2337/dc24-S010 (2024). PMC10725811 38078592 · DOI · Paper page
  4. [6]Zhao H Jiang L Jin X Du H Li X Constant time texture filtering Vis. Comput. 2016 34 83 92 10.1007/s00371-016-1315-z · DOI
  5. [8]Rhee SY Development and validation of a deep learning based diabetes prediction system using a nationwide population-based cohort Diabet. Metab. J. 2021 45 515 525 10.4093/dmj.2020.0081 PMC8369223 33631067 · DOI
  6. [9]Jing L A machine learning approach to management of heart failure populations JACC Heart Fail 2020 8 578 587 10.1016/j.jchf.2020.01.012 32387064 · DOI
  7. [10]Shi B Prediction of recurrent spontaneous abortion using evolutionary machine learning with joint self-adaptive sime mould algorithm Comput. Biol. Med. 2022 148 105885 10.1016/j.compbiomed.2022.105885 35930957 · DOI
  8. [11]Shaik NS Cherukuri TK Transfer learning based novel ensemble classifier for COVID-19 detection from chest CT-scans Comput. Biol. Med. 2022 141 105127 10.1016/j.compbiomed.2021.105127 34915332 PMC8665658 · DOI
  9. [12]Shi H ToxMVA: An end-to-end multi-view deep autoencoder method for protein toxicity prediction Comput. Biol. Med. 2022 151 106322 10.1016/j.compbiomed.2022.106322 36435057 · DOI
  10. [13]Kavakiotis I Machine learning and data mining methods in diabetes research Comput. Struct. Biotechnol. J. 2017 15 104 116 10.1016/j.csbj.2016.12.005 28138367 PMC5257026 · DOI · Paper page
  11. [14]DeFilippis AP Risk score overestimation: The impact of individual cardiovascular risk factors and preventive therapies on the performance of the American Heart Association-American College of Cardiology-Atherosclerotic Cardiovascular Disease risk score in a modern multi-ethnic cohort Eur. Heart. J. 2017 38 598 608 10.1093/eurheartj/ehw301 27436865 PMC5837662 · DOI
  12. [15]Bohula EA Atherothrombotic risk stratification and ezetimibe for secondary prevention J. Am. Coll. Cardiol. 2017 69 911 921 10.1016/j.jacc.2016.11.070 28231942 · DOI · Paper page
  13. [16]Weng SF Reps J Kai J Garibaldi JM Qureshi N Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLoS ONE 2017 12 e0174944 10.1371/journal.pone.0174944 28376093 PMC5380334 · DOI · Paper page
  14. [17]Lagani V Development and validation of risk assessment models for diabetes-related complications based on the DCCT/EDIC data J. Diabet. Complic. 2015 29 479 487 10.1016/j.jdiacomp.2015.03.001 25772254 · DOI · Paper page
  15. [18]Jonnagaddala J Identification and progression of heart disease risk factors in diabetic patients from longitudinal electronic health records Biomed. Res. Int. 2015 2015 636371 10.1155/2015/636371 26380290 PMC4561944 · DOI
  16. [19]Eum S Rhee SY Age, ethnic, and sex disparity in body mass index and waist circumference: a bi-national large-scale study in South Korea and the United States Life Cycle 2023 3 e4 10.54724/lc.2023.e4 36930486 · DOI
  17. [20]Lee SW Regression analysis for continuous independent variables in medical research: Statistical standard and guideline of Life Cycle Committee Life Cycle 2022 2 e3 10.54724/lc.2022.e3 · DOI
  18. [21]Kim J Kim SC Kang D Yon DK Kim JG Classification of Alzheimer's disease stage using machine learning for left and right oxygenation difference signals in the prefrontal cortex: A patient-level, single-group, diagnostic interventional trial Eur. Rev. Med. Pharmacol. Sci. 2022 26 7734 7741 36394721
  19. [22]Collins GS Reitsma JB Altman DG Moons KG Transparent reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): The TRIPOD statement Ann. Intern. Med. 2015 162 55 63 10.7326/m14-0697 25560714 · DOI · Paper page
  20. [23]Goff DC Jr 2013 ACC/AHA guideline on the assessment of cardiovascular risk: A report of the American College of Cardiology/American Heart Association Task Force on Practice Guidelines Circulation 2014 129 S49 73 10.1161/01.cir.0000437741.48606.98 24222018 · DOI · Paper page
  21. [24]Basu S Sussman JB Berkowitz SA Hayward RA Yudkin JS Development and validation of Risk Equations for Complications Of type 2 Diabetes (RECODe) using individual participant data from randomised trials Lancet Diabet. Endocrinol. 2017 5 788 798 10.1016/S2213-8587(17)30221-8 PMC5769867 28803840 · DOI · Paper page
  22. [25]Chowdhury MZI Yeasmin F Rabi DM Ronksley PE Turin TC Prognostic tools for cardiovascular disease in patients with type 2 diabetes: A systematic review and meta-analysis of C-statistics J. Diabet. Complic. 2019 33 98 111 10.1016/j.jdiacomp.2018.10.010 30446478 · DOI
  23. [26]van Dieren S Prediction models for the risk of cardiovascular disease in patients with type 2 diabetes: A systematic review Heart 2012 98 360 369 10.1136/heartjnl-2011-300734 22184101 · DOI
  24. [27]Damen JA Prediction models for cardiovascular disease risk in the general population: Systematic review BMJ 2016 353 i2416 10.1136/bmj.i2416 27184143 PMC4868251 · DOI · Paper page
  25. [28]Kee OT Cardiovascular complications in a diabetes prediction model using machine learning: A systematic review Cardiovasc. Diabetol. 2023 22 13 10.1186/s12933-023-01741-7 36658644 PMC9854013 · DOI · Paper page
  26. [29]Lindner T Puck J Verbeke A Beyond addressing multicollinearity: Robust quantitative analysis and machine learning in international business research J. Int. Bus. Stud. 2022 53 1307 1314 10.1057/s41267-022-00549-z · DOI
  27. [30]Drobnič F Kos A Pustišek M On the interpretability of machine learning models and experimental feature selection in case of multicollinear data Electronics 2020 9 761 10.3390/electronics9050761 · DOI
  28. [31]Chowdhury, S., Lin, Y., Liaw, B. & Kerby, L. in 2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA). 17–25.
  29. [32]Go AS Chertow GM Fan D McCulloch CE Hsu CY Chronic kidney disease and the risks of death, cardiovascular events, and hospitalization N. Engl. J. Med. 2004 351 1296 1305 10.1056/NEJMoa041031 15385656 · DOI · Paper page
  30. [33]Joshi S Viljoen A Renal biomarkers for the prediction of cardiovascular disease Curr. Opin. Cardiol. 2015 30 454 460 10.1097/HCO.0000000000000177 26049396 · DOI
  31. [34]Chicco D Jurman G Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone BMC Med. Inform. Decis. Mak. 2020 20 16 10.1186/s12911-020-1023-5 32013925 PMC6998201 · DOI
  32. [35]Suzuki A Visit-to-visit variability in estimated glomerular filtration rate predicts hospitalization and death due to cardiovascular events Clin. Exp. Nephrol. 2019 23 661 668 10.1007/s10157-019-01695-9 30687876 PMC6469650 · DOI
  33. [36]Ceriello A HbA1c variability predicts cardiovascular complications in type 2 diabetes regardless of being at glycemic target Cardiovasc. Diabetol. 2022 21 13 10.1186/s12933-022-01445-4 35073913 PMC8788128 · DOI
  34. [37]Shen Y Association between visit-to-visit HbA1c variability and the risk of cardiovascular disease in patients with type 2 diabetes Diabet. Obes. Metab. 2021 23 125 135 10.1111/dom.14201 PMC9092602 32965068 · DOI
  35. [38]Cho EJ Han K Lee SP Shin DW Yu SJ Liver enzyme variability and risk of heart disease and mortality: A nationwide population-based study Liver Int. 2020 40 1292 1302 10.1111/liv.14432 32153096 · DOI
  36. [39]Wan EYF Greater variability in lipid measurements associated with cardiovascular disease and mortality: A 10-year diabetes cohort study Diabet. Obes. Metab. 2020 22 1777 1788 10.1111/dom.14093 PMC7540339 32452623 · DOI · Paper page
  37. [40]Lee JS Effects of ten year body weight variability on cardiovascular risk factors in Japanese middle-aged men and women Int. J. Obes. Relat. Metab. Disord. 2001 25 1063 1067 10.1038/sj.ijo.0801633 11443507 · DOI
  38. [41]Youk TM Kang MJ Song SO Park EC Effects of BMI and LDL-cholesterol change pattern on cardiovascular disease in normal adults and diabetics BMJ Open Diabet. Res. Care 2020 8 e001340 10.1136/bmjdrc-2020-001340 PMC7757466 33355207 · DOI
  39. [42]Johnsen SH Mathiesen EB Carotid plaque compared with intima-media thickness as a predictor of coronary and cerebrovascular disease Curr. Cardiol. Rep. 2009 11 21 27 10.1007/s11886-009-0004-1 19091171 · DOI

Authors
Sang, H., Lee, H., Lee, M., Park, J., Kim, S., Woo, H. G., Rahmati, M., Koyanagi, A., Smith, L., Lee, S., Hwang, Y.-C., Park, T. S., Lim, H., Yon, D. K., & Rhee, S. Y.
Affiliations
  • Kyung Hee University (KR)
  • Aix-Marseille Université (FR)
  • Parc Sanitari Sant Joan de Déu (ES)
  • Anglia Ruskin University (GB)
  • Gachon University (KR)
  • Kyung Hee University Hospital at Gangdong (KR)
  • Jeonbuk National University Hospital (KR)
Corresponding author
  • Yon, Dong Keon
  • Rhee, Sang Youl
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2024-06-28
Volume
14
Issue
1
Pages
14966-14966
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-024-63798-y
PMC
PMC11213851
OpenAlex
W4400108944
Cited by
36
References
43
Citations by year
2026: 13 · 2025: 18 · 2024: 4 · 2018: 1
FWCI
10.69
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Figshare (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Korean Diabetes Association
  • Korea Disease Control and Prevention Agency
  • National Institutes of Health
Topics
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes, Cardiovascular Risks, and Lipoproteins
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
cardiovascular disease prediction, type 2 diabetes, Korean patients, random forest, machine learning prediction models, creatinine, HbA1c, chronic complications of diabetes, cardiovascular risk stratification
MeSH terms
Machine Learning, Aged, Cardiovascular Diseases, Diabetes Mellitus, Type 2, Female, Humans, Male, Middle Aged, Risk Factors, ROC Curve, Cohort Studies, Republic of Korea

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