CoChat
Sign Up
Cited by 82Artificial Intelligence in HealthcareMachine Learning in HealthcareDiabetes, Cardiovascular Risks, and Lipoproteins

Cardiovascular complications in a diabetes prediction model using machine learning: a systematic review

Open access
Kee, Ooi Ting, Harun, Harmiza, Mustafa, Norlaila, Abdul Murad, Nor Azian, Chin, Siok Fong, Jaafar, Rosmina, Abdullah, Noraidatulakma·2023·Cardiovascular Diabetology
DOI 10.1186/s12933-023-01741-7PMC PMC9854013
Open this paper in CoChat — free accountOpen PDF

Abstract

Prediction model has been the focus of studies since the last century in the diagnosis and prognosis of various diseases. With the advancement in computational technology, machine learning (ML) has become the widely used tool to develop a prediction model. This review is to investigate the current development of prediction model for the risk of cardiovascular disease (CVD) among type 2 diabetes (T2DM) patients using machine learning. A systematic search on Scopus and Web of Science (WoS) was conducted to look for relevant articles based on the research question. The risk of bias (ROB) for all articles were assessed based on the Prediction model Risk of Bias Assessment Tool (PROBAST) statement. Neural network with 76.6% precision, 88.06% sensitivity, and area under the curve (AUC) of 0.91 was found to be the most reliable algorithm in developing prediction model for cardiovascular disease among type 2 diabetes patients. The overall concern of applicability of all included studies is low. While two out of 10 studies were shown to have high ROB, another studies ROB are unknown due to the lack of information. The adherence to reporting standards was conducted based on the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) standard where the overall score is 53.75%. It is highly recommended that future model development should adhere to the PROBAST and TRIPOD assessment to reduce the risk of bias and ensure its applicability in clinical settings. Potential lipid peroxidation marker is also recommended in future cardiovascular disease prediction model to improve overall model applicability.

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 · 10.1186/s12933-023-01741-7

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?

  • Existing machine learning models for cardiovascular risk prediction generally carry a high risk of bias.

    “Despite excellent algorithmic results in many studies, systematic evaluations have revealed a high prevalence of risk of bias, primarily stemming from deficiencies in the participant selection domain, outcome measurement domain, and analysis domain (6, 7).”

    From AI-driven cardiovascular risk prediction in patients with diabetes: bridging algorithmic innovation to equitable clinical application (2026) · cites this paper as [6]

    The Results, under “Risk of bias assessment,” report that none of the ten studies had low overall risk of bias and identify concerns in the participant and analysis domains. But only two studies were rated high risk overall; eight were rated unclear, and the outcome domain was described as having minimal risk or unclear risk, not generally high risk. The review is also limited to cardiovascular prediction models for people with type 2 diabetes. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

  • Inadequate representation of Asian and other non-Western groups directly compromises clinical applicability in high-burden regions.

    “A large proportion of studies rely on populations from Europe and North America, with inadequate representation of Asian and other non-Western groups, directly compromising clinical applicability in high-burden regions (6, 7).”

    From AI-driven cardiovascular risk prediction in patients with diabetes: bridging algorithmic innovation to equitable clinical application (2026) · cites this paper as [6]

    The Results and Discussion (page not available) say that most included studies used European/Caucasian populations, only two studied Chinese populations, and none studied Malay or Indian populations. The Discussion calls for prediction-model studies in Malaysia and other Asian countries, but does not establish that underrepresentation directly compromises clinical applicability there; its risk-of-bias assessment reports low applicability concern for the models relative to the review question. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

  • A large proportion of diabetes-related cardiovascular risk prediction studies rely on populations from Europe and North America, with inadequate representation of Asian and other non-Western groups.

    “A large proportion of studies rely on populations from Europe and North America, with inadequate representation of Asian and other non-Western groups, directly compromising clinical applicability in high-burden regions (6, 7).”

    From AI-driven cardiovascular risk prediction in patients with diabetes: bridging algorithmic innovation to equitable clinical application (2026) · cites this paper as [6]

    The Results report that most of the ten included studies used European/Caucasian populations, including studies from Europe and the United States, while only two used Chinese populations. The Discussion notes the absence of Malay and Indian populations and calls for prediction-model studies in Asian countries. The paper does not establish that this imbalance directly compromises clinical applicability in high-burden regions; its risk-of-bias assessment rates applicability concerns for the included models as low. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

  • Neural networks and gradient boosting machines exhibit superior discriminative ability over traditional methods in predicting cardiovascular complications in diabetes.

    “Numerous studies have demonstrated that algorithms such as neural networks and gradient boosting machines exhibit superior discriminative ability over traditional methods in predicting cardiovascular complications in diabetes (6–8).”

    From AI-driven cardiovascular risk prediction in patients with diabetes: bridging algorithmic innovation to equitable clinical application (2026) · cites this paper as [6]

  • Compliance with the TRIPOD checklist averaged only 53.75% across reviewed machine learning studies.

    “A particularly concerning issue is the low adherence to transparent reporting standards: compliance with the TRIPOD checklist averaged only 53.75% across reviewed studies (6).”

    From AI-driven cardiovascular risk prediction in patients with diabetes: bridging algorithmic innovation to equitable clinical application (2026) · cites this paper as [6]

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 59 · Cited by 82

Research works printed but not linked: 51

  1. [1]Chatterjee S Khunti K Davies MJ Type 2 diabetes Lancet 2017 389 10085 2239 2251 10.1016/S0140-6736(17)30058-2 28190580 · DOI · Paper page
  2. [2]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 1 211 10.1186/s12911-019-0918-5 31694707 PMC6836338 · DOI
  3. [3]Goldstein BA Navar AM Carter RE Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges Eur Heart J 2017 38 23 1805 1814 27436868 PMC5837244
  4. [4]Churpek MM Yuen TC Winslow C Meltzer DO Kattan MW Edelson DP Multicenter comparison of machine learning methods and conventional regression for predicting clinical deterioration on the wards Crit Care Med 2016 44 2 368 374 10.1097/CCM.0000000000001571 26771782 PMC4736499 · DOI · Paper page
  5. [5]Gupta S Saluja K Goyal A Vajpayee A Tiwari V Comparing the performance of machine learning algorithms using estimated accuracy Meas Sens 2022 24 100432 10.1016/j.measen.2022.100432 · DOI
  6. [6]Joseph JJ Deedwania P Acharya T Aguilar D Bhatt DL Chyun DA Comprehensive management of cardiovascular risk factors for adults with type 2 diabetes: a scientific statement from the American Heart Association Circulation 2022 145 9 e722 e759 10.1161/CIR.0000000000001040 35000404 · DOI · Paper page
  7. [7]Ayala A Muñoz MF Argüelles S Lipid peroxidation: production, metabolism, and signaling mechanisms of malondialdehyde and 4-hydroxy-2-nonenal Oxidative Med Cell Longev 2014 2014 360438 10.1155/2014/360438 PMC4066722 24999379 · DOI
  8. [8]Kayama Y Raaz U Jagger A Adam M Schellinger IN Sakamoto M Diabetic cardiovascular disease induced by oxidative stress Int J Mol Sci 2015 16 10 25234 25263 10.3390/ijms161025234 26512646 PMC4632800 · DOI
  9. [11]Zielinski ZAM Pratt DA Lipid peroxidation: kinetics, mechanisms, and products J Org Chem 2017 82 6 2817 2825 10.1021/acs.joc.7b00152 28248497 · DOI
  10. [12]Ito F Sono Y Ito T Measurement and clinical significance of lipid peroxidation as a biomarker of oxidative stress: oxidative stress in diabetes, atherosclerosis, and chronic inflammation Antioxidants 2019 8 3 72 10.3390/antiox8030072 30934586 PMC6466575 · DOI · Paper page
  11. [13]Dalakleidi K Zarkogianni K Thanopoulou A Nikita K Comparative assessment of statistical and machine learning techniques towards estimating the risk of developing type 2 diabetes and cardiovascular complications Expert Syst 2017 34 6 e12214 10.1111/exsy.12214 · DOI
  12. [14]Nicolucci A Romeo L Bernardini M Vespasiani M Rossi MC Petrelli M Prediction of complications of type 2 diabetes: a machine learning approach Diabetes Res Clin Pract 2022 190 110013 10.1016/j.diabres.2022.110013 35870573 · DOI · Paper page
  13. [15]Li Q Campan A Ren A Eid WE Automating and improving cardiovascular disease prediction using machine learning and EMR data features from a regional healthcare system Int J Med Inform 2022 163 104786 10.1016/j.ijmedinf.2022.104786 35512622 · DOI
  14. [16]Edward JA Josey K Bahn G Caplan L Reusch JEB Reaven P Heterogeneous treatment effects of intensive glycemic control on major adverse cardiovascular events in the ACCORD and VADT trials: a machine-learning analysis Cardiovasc Diabetol 2022 21 1 58 10.1186/s12933-022-01496-7 35477454 PMC9047276 · DOI
  15. [17]Jiang Y Yang Z-G Wang J Shi R Han P-L Qian W-L Unsupervised machine learning based on clinical factors for the detection of coronary artery atherosclerosis in type 2 diabetes mellitus Cardiovasc Diabetol 2022 21 1 259 10.1186/s12933-022-01700-8 36443722 PMC9706943 · DOI
  16. [18]Drożdż K Nabrdalik K Kwiendacz H Hendel M Olejarz A Tomasik A Risk factors for cardiovascular disease in patients with metabolic-associated fatty liver disease: a machine learning approach Cardiovasc Diabetol 2022 21 1 240 10.1186/s12933-022-01672-9 36371249 PMC9655870 · DOI
  17. [19]Hahn S-J Kim S Choi YS Lee J Kang J Prediction of type 2 diabetes using genome-wide polygenic risk score and metabolic profiles: a machine learning analysis of population-based 10-year prospective cohort study eBioMedicine 2022 86 104383 10.1016/j.ebiom.2022.104383 36462406 PMC9713286 · DOI
  18. [20]Damen JAAG Hooft L Schuit E Debray TPA Collins GS Tzoulaki I 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
  19. [22]Riva JJ Malik KMP Burnie SJ Endicott AR Busse JW What is your research question? An introduction to the PICOT format for clinicians J Can Chiropr Assoc 2012 56 3 167 171 22997465 PMC3430448
  20. [24]Collins GS Reitsma JB Altman DG Moons KGM Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement Ann Intern Med 2015 162 1 55 63 10.7326/M14-0697 25560714 · DOI · Paper page
  21. [25]Moons KGM Altman DG Reitsma JB Ioannidis JPA Macaskill P Steyerberg EW Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): explanation and elaboration Ann Intern Med 2015 162 1 W1 W73 10.7326/M14-0698 25560730 · DOI · Paper page
  22. [26]Wolff RF Moons KGM Riley RD Whiting PF Westwood M Collins GS PROBAST: a tool to assess the risk of bias and applicability of prediction model studies Ann Intern Med 2019 170 1 51 58 10.7326/M18-1376 30596875 · DOI · Paper page
  23. [27]Parfitt VJ Desomeaux K Bolton CH Hartog M Effects of high monounsaturated and polyunsaturated fat diets on plasma lipoproteins and lipid peroxidation in type 2 diabetes mellitus Diabet Med 1994 11 1 85 91 10.1111/j.1464-5491.1994.tb00235.x 8181259 · DOI
  24. [28]Chu H Chen L Yang X Qiu X Qiao Z Song X Roles of anxiety and depression in predicting cardiovascular disease among patients with type 2 diabetes mellitus: a machine learning approach Front Psychol 2021 12 1189 10.3389/fpsyg.2021.645418 PMC8113686 33995200 · DOI · Paper page
  25. [29]Zarkogianni K Athanasiou M Thanopoulou AC Comparison of machine learning approaches toward assessing the risk of developing cardiovascular disease as a long-term diabetes complication IEEE J Biomed Health Inform 2018 22 5 1637 1647 10.1109/JBHI.2017.2765639 29990007 · DOI
  26. [30]Derevitskii IV Kovalchuk SV Machine learning-based predictive modeling of complications of chronic diabetes Procedia Comput Sci 2020 178 274 283 10.1016/j.procs.2020.11.029 · DOI
  27. [31]Athanasiou M, Sfrintzeri K, Zarkogianni K, Thanopoulou AC, Nikita KS. An explainable XGBoost-based approach towards assessing the risk of cardiovascular disease in patients with Type 2 diabetes mellitus. ArXiv. 2020. arXiv:2009.06629. · arXiv
  28. [32]Dworzynski P Aasbrenn M Rostgaard K Melbye M Gerds TA Hjalgrim H Nationwide prediction of type 2 diabetes comorbidities Sci Rep 2020 10 1 1776 10.1038/s41598-020-58601-7 32019971 PMC7000818 · DOI
  29. [33]Mei J Xia E Knowledge learning symbiosis for developing risk prediction models from regional EHR repositories Stud Health Technol Inform 2019 264 258 262 31437925
  30. [34]Nowak C Carlsson AC Ostgren CJ Nystrom FH Alam M Feldreich T Multiplex proteomics for prediction of major cardiovascular events in type 2 diabetes Diabetologia 2018 61 8 1748 1757 10.1007/s00125-018-4641-z 29796748 PMC6061158 · DOI
  31. [35]Hossain ME Uddin S Khan A Network analytics and machine learning for predictive risk modelling of cardiovascular disease in patients with type 2 diabetes Expert Syst Appl 2021 164 113918 10.1016/j.eswa.2020.113918 · DOI
  32. [36]Miao L, Guo X, Abbas HT, Qaraqe KA, Abbasi QH, editors. Using machine learning to predict the future development of disease. In: 2020 international conference on UK-China emerging technologies (UCET), 2020 20–21 Aug; 2020.
  33. [39]Khan MAB Hashim MJ King JK Govender RD Mustafa H Al Kaabi J Epidemiology of type 2 diabetes—global burden of Disease and Forecasted Trends J Epidemiol Glob Health 2020 10 1 107 111 10.2991/jegh.k.191028.001 32175717 PMC7310804 · DOI
  34. [41]He H Garcia EA Learning from imbalanced data IEEE Trans Knowl Data Eng 2009 21 9 1263 1284 10.1109/TKDE.2008.239 · DOI · Paper page
  35. [42]Holte RC, Acker L, Porter BW, editors. Concept learning and the problem of small disjuncts. In: IJCAI; 1989.
  36. [44]Garcia MJ McNamara PM Gordon T Kannel WB Morbidity and mortality in diabetics in the Framingham population. Sixteen year follow-up study Diabetes 1974 23 2 105 111 10.2337/diab.23.2.105 4359625 · DOI · Paper page
  37. [45]Kannel WB Hjortland M Castelli WP Role of diabetes in congestive heart failure: the Framingham study Am J Cardiol 1974 34 1 29 34 10.1016/0002-9149(74)90089-7 4835750 · DOI · Paper page
  38. [46]Williams BA Geba D Cordova JM Shetty SS A risk prediction model for heart failure hospitalization in type 2 diabetes mellitus Clin Cardiol 2020 43 3 275 283 10.1002/clc.23298 31837035 PMC7068070 · DOI
  39. [47]Pylypchuk R Wells S Kerr A Poppe K Harwood M Mehta S Cardiovascular risk prediction in type 2 diabetes before and after widespread screening: a derivation and validation study Lancet 2021 397 10291 2264 2274 10.1016/S0140-6736(21)00572-9 34089656 · DOI
  40. [48]Chhatwal J Alagoz O Lindstrom MJ Kahn CE Jr Shaffer KA Burnside ES A logistic regression model based on the national mammography database format to aid breast cancer diagnosis AJR Am J Roentgenol 2009 192 4 1117 1127 10.2214/AJR.07.3345 19304723 PMC2661033 · DOI
  41. [49]Dahlrot RH Bangsø JA Petersen JK Rosager AM Sørensen MD Reifenberger G Prognostic role of Ki-67 in glioblastomas excluding contribution from non-neoplastic cells Sci Rep 2021 11 1 17918 10.1038/s41598-021-95958-9 34504133 PMC8429554 · DOI
  42. [50]Fuster-Garcia E Lorente Estellés D Álvarez-Torres MDM Juan-Albarracín J Chelebian E Rovira A MGMT methylation may benefit overall survival in patients with moderately vascularized glioblastomas Eur Radiol 2021 31 3 1738 1747 10.1007/s00330-020-07297-4 33001310 PMC7880975 · DOI
  43. [51]Bzdok D Altman N Krzywinski M Statistics versus machine learning Nat Methods 2018 15 4 233 234 10.1038/nmeth.4642 30100822 PMC6082636 · DOI · Paper page
  44. [52]Ortega FB Lavie CJ Blair SN Obesity and cardiovascular disease Circul Res 2016 118 11 1752 1770 10.1161/CIRCRESAHA.115.306883 27230640 · DOI
  45. [53]Ley SH Hamdy O Mohan V Hu FB Prevention and management of type 2 diabetes: dietary components and nutritional strategies Lancet 2014 383 9933 1999 2007 10.1016/S0140-6736(14)60613-9 24910231 PMC4751088 · DOI · Paper page
  46. [54]Gray N Picone G Sloan F Yashkin A Relation between BMI and diabetes mellitus and its complications among US older adults South Med J 2015 108 1 29 36 10.14423/SMJ.0000000000000214 25580754 PMC4457375 · DOI
  47. [55]Kolber MR Scrimshaw C Family history of cardiovascular disease Can Fam Physician 2014 60 11 1016 25392442 PMC4229162
  48. [56]Valerio L Peters RJ Zwinderman AH Pinto-Sietsma SJ Association of family history with cardiovascular disease in hypertensive individuals in a multiethnic population J Am Heart Assoc 2016 5 12 e004260 10.1161/JAHA.116.004260 28003252 PMC5210427 · DOI
  49. [57]Vona R Gambardella L Cittadini C Straface E Pietraforte D Biomarkers of oxidative stress in metabolic syndrome and associated diseases Oxidative Med Cell Longev 2019 2019 8267234 10.1155/2019/8267234 PMC6525823 31191805 · DOI
  50. [58]Lundberg WO Lipids of biologic importance: peroxidation products and inclusion compounds of lipids Am J Clin Nutr 1958 6 6 601 603 10.1093/ajcn/6.6.601 13594887 · DOI
  51. [59]Bigagli E Lodovici M Circulating oxidative stress biomarkers in clinical studies on type 2 diabetes and its complications Oxidative Med Cell Longev 2019 2019 5953685 10.1155/2019/5953685 PMC6535859 31214280 · DOI

Authors
Kee, O. T., Harun, H., Mustafa, N., Abdul Murad, N. A., Chin, S. F., Jaafar, R., & Abdullah, N.
Affiliations
National University of Malaysia (MY)
Corresponding author
Abdullah, Noraidatulakma
ORCID
Venue
Cardiovascular Diabetology
Publisher
Springer Science and Business Media LLC
Published
2023-01-19
Volume
22
Issue
1
Pages
13-13
ISSN
1475-2840 (ISSN-L)
DOI
10.1186/s12933-023-01741-7
PMC
PMC9854013
OpenAlex
W4317438932
Cited by
82
References
59
Citations by year
2026: 16 · 2025: 28 · 2024: 22 · 2023: 16
FWCI
3.21
Type
journal article
Language
en
Open access
Licence
Locations
  • Cardiovascular Diabetology (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Research University Grant, Universiti Kebangsaan Malaysia (GUP-2020-077)
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, Cardiovascular Risks, and Lipoproteins
Keywords
cardiovascular risk prediction, type 2 diabetes, machine learning prediction models, cardiovascular complications, artificial neural networks, risk of bias, model applicability
MeSH terms
Machine Learning, Cardiovascular Diseases, Diabetes Mellitus, Type 2, Humans, Prognosis

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