CoChat
Sign Up
Cited by 28Artificial Intelligence in HealthcareDiabetes, Cardiovascular Risks, and LipoproteinsMachine Learning in Healthcare

Machine Learning for Predicting the 3-Year Risk of Incident Diabetes in Chinese Adults

Open access
Wu, Yang, Hu, Haofei, Cai, Jinlin, Chen, Runtian, Zuo, Xin, Cheng, Heng, Yan, Dewen·2021·Frontiers in Public Health
DOI 10.3389/fpubh.2021.626331PMC PMC8275929
Open this paper in CoChat — free accountOpen PDF

Abstract

Purpose: We aimed to establish and validate a risk assessment system that combines demographic and clinical variables to predict the 3-year risk of incident diabetes in Chinese adults. Methods: A 3-year cohort study was performed on 15,928 Chinese adults without diabetes at baseline. All participants were randomly divided into a training set (n = 7,940) and a validation set (n = 7,988). XGBoost method is an effective machine learning technique used to select the most important variables from candidate variables. And we further established a stepwise model based on the predictors chosen by the XGBoost model. The area under the receiver operating characteristic curve (AUC), decision curve and calibration analysis were used to assess discrimination, clinical use and calibration of the model, respectively. The external validation was performed on a cohort of 11,113 Japanese participants. Result: In the training and validation sets, 148 and 145 incident diabetes cases occurred. XGBoost methods selected the 10 most important variables from 15 candidate variables. Fasting plasma glucose (FPG), body mass index (BMI) and age were the top 3 important variables. And we further established a stepwise model and a prediction nomogram. The AUCs of the stepwise model were 0.933 and 0.910 in the training and validation sets, respectively. The Hosmer-Lemeshow test showed a perfect fit between the predicted diabetes risk and the observed diabetes risk (p = 0.068 for the training set, p = 0.165 for the validation set). Decision curve analysis presented the clinical use of the stepwise model and there was a wide range of alternative threshold probability spectrum. And there were almost no the interactions between these predictors (most P-values for interaction >0.05). Furthermore, the AUC for the external validation set was 0.830, and the Hosmer-Lemeshow test for the external validation set showed no statistically significant difference between the predicted diabetes risk and observed diabetes risk (P = 0.824). Conclusion: We established and validated a risk assessment system for characterizing the 3-year risk of incident diabetes.

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 · 10.3389/fpubh.2021.626331

Cites

3 of 3 references verified0 citation errors · 0 not checkable

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?

  • Although the same XGBoost algorithm was implemented, each of the three studies used different risk predictors and datasets, resulting in widely disparate AUC values of 0.91, 0.83, and 0.679-11.

    “Although the same algorithm was implemented, each study used different risk predictors and datasets, which resulted in widely disparate AUC values of 0.91, 0.83, and 0.679–11.”

    From AI-based diabetes care: risk prediction models and implementation concerns (2024) · cites this paper as [11]

    The Results (Development of XGBoost Model) confirm that this study used XGBoost, but report XGBoost AUCs of 0.977 and 0.920, not the values listed in the citing sentence. The Results (Performance of the Stepwise Model; External Validation) report 0.910 and 0.830 for a stepwise model based on XGBoost-selected predictors, not for XGBoost itself. This paper does not establish that differences in predictors and datasets caused the disparities across three studies. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 63

  1. [1]Cho NH Shaw JE Karuranga S Huang Y Da RFJ Ohlrogge AW. IDF diabetes atlas: global estimates of diabetes prevalence for 2017 and projections for 2045. Diabetes Res Clin Pract. (2018) 138: 271– 81. 10.1016/j.diabres.2018.02.023 29496507 · DOI · Paper page
  2. [2]Li Y Teng D Shi X Qin G Qin Y Quan H. Prevalence of diabetes recorded in mainland China using 2018 diagnostic criteria from the American Diabetes Association: national cross sectional study. BMJ. (2020) 369: m997. 10.1136/bmj.m997 32345662 PMC7186854 · DOI
  3. [3]Thomas MC Brownlee M Susztak K Sharma K Jandeleit-Dahm KA Zoungas S. Diabetic kidney disease. Nat Rev Dis Primers. (2015) 1: 15018. 10.1038/nrdp.2015.70 27188921 PMC7724636 · DOI
  4. [4]Cheung N Mitchell P Wong TY. Diabetic retinopathy. Lancet. (2010) 376: 124– 36. 10.1016/S0140-6736(09)62124-3 20580421 · DOI · Paper page
  5. [5]Feldman EL Callaghan BC Pop-Busui R Zochodne DW Wright DE Bennett DL. Diabetic neuropathy. Nat Rev Dis Primers. (2019) 5: 42. 10.1038/s41572-019-0092-1 31197183 PMC7096070 · DOI · Paper page
  6. [7]Hardigan T Ward R Ergul A. Cerebrovascular complications of diabetes: focus on cognitive dysfunction. Clin Sci. (2016) 130: 1807– 22. 10.1042/CS20160397 27634842 PMC5599301 · DOI
  7. [8]Li Y Wang DD Ley SH Vasanti M Howard AG He Y. Time trends of dietary and lifestyle factors and their potential impact on diabetes burden in China. Diabetes Care. (2017) 40: 1685– 94. 10.2337/dc17-0571 29046327 PMC5862128 · DOI
  8. [9]Le Roux CW Astrup A Fujioka K Greenway F Lau D Van Gaal L. 3 years of liraglutide versus placebo for type 2 diabetes risk reduction and weight management in individuals with prediabetes: a randomised, double-blind trial. Lancet. (2017) 389: 1399– 409. 10.1016/S0140-6736(17)30069-7 28237263 · DOI · Paper page
  9. [10]Gregg EW Chen H Wagenknecht LE Clark JM Delahanty LM Bantle J. Association of an intensive lifestyle intervention with remission of type 2 diabetes. JAMA. (2012) 308: 2489– 96. 10.1001/jama.2012.67929 23288372 PMC4771522 · DOI · Paper page
  10. [11]Brito JP Montori VM Davis AM. Metabolic surgery in the treatment algorithm for type 2 diabetes: a joint statement by international diabetes organizations. JAMA. (2017) 317: 635– 6. 10.1001/jama.2016.20563 28196240 PMC5557277 · DOI
  11. [12]Shi X Shi Y Chen N Lin M Su W Zhang H. Effect of exenatide after short-time intensive insulin therapy on glycaemic remission maintenance in type 2 diabetes patients: a randomized controlled trial. Sci Rep. (2017) 7: 2383. 10.1038/s41598-017-02631-1 28539618 PMC5443840 · DOI
  12. [13]Camacho DM Collins KM Powers RK Costello JC Collins JJ. Next-generation machine learning for biological networks. Cell. (2018) 173: 1581– 92. 10.1016/j.cell.2018.05.015 29887378 · DOI
  13. [14]Libbrecht MW Noble WS. Machine learning applications in genetics and genomics. Nat Rev Genet. (2015) 16: 321– 32. 10.1038/nrg3920 25948244 PMC5204302 · DOI
  14. [15]Dwyer DB Falkai P Koutsouleris N. Machine learning approaches for clinical psychology and psychiatry. Annu Rev Clin Psychol. (2018) 14: 91– 118. 10.1146/annurev-clinpsy-032816-045037 29401044 · DOI · Paper page
  15. [16]Jordan MI Mitchell TM. Machine learning: trends, perspectives, and prospects. Science. (2015) 349: 255– 60. 10.1126/science.aaa8415 26185243 · DOI · Paper page
  16. [17]Lagani V Koumakis L Chiarugi F Lakasing E Tsamardinos I. A systematic review of predictive risk models for diabetes complications based on large scale clinical studies. J Diabetes Complicat. (2013) 27: 407– 13. 10.1016/j.jdiacomp.2012.11.003 23273850 · DOI
  17. [18]Xiong XL Zhang RX Bi Y Zhou WH Yu Y Zhu DL. Machine learning models in type 2 diabetes risk prediction: results from a cross-sectional retrospective study in Chinese adults. Curr Med Sci. (2019) 39: 582– 8. 10.1007/s11596-019-2077-4 31346994 · DOI
  18. [19]Zou Q Qu K Luo Y Yin D Ju Y Tang H. Predicting diabetes mellitus with machine learning techniques. Front Genet. (2018) 9: 515. 10.3389/fgene.2018.00515 30459809 PMC6232260 · DOI
  19. [20]Perveen S Shahbaz M Keshavjee K Guergachi A. Prognostic modeling and prevention of diabetes using machine learning technique. Sci Rep. (2019) 9: 13805. 10.1038/s41598-019-49563-6 31551457 PMC6760163 · DOI
  20. [21]Zhang L Wang Y Niu M Wang C Wang Z. Machine learning for characterizing risk of type 2 diabetes mellitus in a rural Chinese population: the Henan Rural Cohort Study. Sci Rep. (2020) 10: 4406. 10.1038/s41598-020-61123-x 32157171 PMC7064542 · DOI
  21. [22]Zhao X Wu S Fang N Sun X Fan J. Evaluation of single-cell classifiers for single-cell RNA sequencing data sets. Brief Bioinform. (2020) 21: 1581– 595. 10.1093/bib/bbz096 31675098 PMC7947964 · DOI
  22. [23]Polano M Chierici M Dal Bo M Gentilini D Di Cintio F Baboci L. A pan-cancer approach to predict responsiveness to immune checkpoint inhibitors by machine learning. Cancers. (2019) 11: 1562. 10.3390/cancers11101562 31618839 PMC6827166 · DOI
  23. [24]Zhang Z Ho KM Hong Y. Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care. Crit Care. (2019) 23: 112. 10.1186/s13054-019-2411-z 30961662 PMC6454725 · DOI
  24. [25]Wang K Zuo P Liu Y Zhang M Zhao X Xie S. Clinical and laboratory predictors of in-hospital mortality in patients with COVID-19: a cohort study in Wuhan, China. Clin Infect Dis. (2020) 71: 2079– 88. 10.2139/ssrn.3546115 32361723 PMC7197616 · DOI
  25. [26]Tahmassebi A Wengert GJ Helbich TH Bago-Horvath Z Alaei S Bartsch R. Impact of machine learning with multiparametric magnetic resonance imaging of the breast for early prediction of response to neoadjuvant chemotherapy and survival outcomes in breast cancer patients. Invest Radiol. (2019) 54: 110– 7. 10.1097/RLI.0000000000000518 30358693 PMC6310100 · DOI
  26. [27]Chen Y Zhang XP Yuan J Cai B Wang XL Wu XL. Association of body mass index and age with incident diabetes in Chinese adults: a population-based cohort study. BMJ Open. (2018) 8: e21768. 10.1136/bmjopen-2018-021768 30269064 PMC6169758 · DOI
  27. [28]Wang K Gong M Xie S Zhang M Zheng H Zhao X. Nomogram prediction for the 3-year risk of type 2 diabetes in healthy mainland China residents. EPMA J. (2019) 10: 227– 37. 10.1007/s13167-019-00181-2 31462940 PMC6695459 · DOI
  28. [29]Geleris J Sun Y Platt J Zucker J Baldwin M Hripcsak G. Observational study of hydroxychloroquine in hospitalized patients with Covid-19. N Engl J Med. (2020) 382: 2411– 8. 10.1056/NEJMoa2012410 32379955 PMC7224609 · DOI · Paper page
  29. [30]Chen T Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: 2016. San Francisco, CA: ACM (2016). p. 785– 94.
  30. [31]Lundberg S Lee S. A unified approach to interpreting model predictions. Advances in neural information processing systems. Long Beach, CA: Neural Information Processing Systems (2017). p. 4765– 74.
  31. [32]Collignon O Monnez J. Clustering of the values of a response variable and simultaneous covariate selection using a stepwise algorithm. Appl. Math. (2016) 7: 1639– 48. 10.4236/am.2016.715141 · DOI
  32. [33]Lei Z Li J Wu D Xia Y Wang Q Si A. Nomogram for preoperative estimation of microvascular invasion risk in hepatitis B virus-related hepatocellular carcinoma within the milan criteria. JAMA Surg. (2016) 151: 356– 63. 10.1001/jamasurg.2015.4257 26579636 · DOI
  33. [34]Sun F Tao Q Zhan S. An accurate risk score for estimation 5-year risk of type 2 diabetes based on a health screening population in Taiwan. Diabetes Res Clin Pract. (2009) 85: 228– 34. 10.1016/j.diabres.2009.05.005 19500871 · DOI
  34. [35]Fitzgerald M Saville BR Lewis RJ. Decision curve analysis. JAMA. (2015) 313: 409– 10. 10.1001/jama.2015.37 25626037 · DOI
  35. [36]Okamura T Hashimoto Y Hamaguchi M Obora A Kojima T Fukui M. Ectopic fat obesity presents the greatest risk for incident type 2 diabetes: a population-based longitudinal study. Int J Obes. (2019) 43: 139– 48. 10.1038/s41366-018-0076-3 29717276 · DOI
  36. [37]Collins GS Reitsma JB Altman DG Moons KG. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ. (2015) 350: g7594. 10.1136/bmj.g7594 25569120 · DOI · Paper page
  37. [38]Kengne AP Beulens JW Peelen LM Moons KG van der Schouw YT Schulze MB. Non-invasive risk scores for prediction of type 2 diabetes (EPIC-InterAct): a validation of existing models. Lancet Diabetes Endocrinol. (2014) 2: 19– 29. 10.1016/S2213-8587(13)70103-7 24622666 · DOI
  38. [39]Kriegeskorte N Golan T. Neural network models and deep learning. Curr Biol. (2019) 29: R231– 6. 10.1016/j.cub.2019.02.034 30939301 · DOI
  39. [40]Allalou A Nalla A Prentice KJ Liu Y Zhang M Dai FF. A predictive metabolic signature for the transition from gestational diabetes mellitus to type 2 diabetes. Diabetes. (2016) 65: 2529– 39. 10.2337/db15-1720 27338739 PMC5001181 · DOI
  40. [41]Li Y Zhang T. Deep neural mapping support vector machines. Neural Netw. (2017) 93: 185– 94. 10.1016/j.neunet.2017.05.010 28646763 · DOI
  41. [42]Song H Thiagarajan JJ Sattigeri P Spanias A. Optimizing kernel machines using deep learning. IEEE Trans Neural Netw Learn Syst. (2018) 29: 5528– 40. 10.1109/TNNLS.2018.2804895 29993616 · DOI
  42. [43]Wiggins M Saad A Litt B Vachtsevanos G. Evolving a Bayesian classifier for ECG-based age classification in medical applications. Appl Soft Comput. (2008) 8: 599– 608. 10.1016/j.asoc.2007.03.009 22010038 PMC3193938 · DOI
  43. [44]Mao S Lin W Jiao L Gou S Chen JW. End-to-end ensemble learning by exploiting the correlation between individuals and weights. IEEE Trans Cybern. (2021) 51: 2835– 46. 10.1109/TCYB.2019.2931071 31425063 · DOI
  44. [45]Tang J Deng C Huang GB. Extreme learning machine for multilayer perceptron. IEEE Trans Neural Netw Learn Syst. (2016) 27: 809– 21. 10.1109/TNNLS.2015.2424995 25966483 · DOI
  45. [46]Ngiam KY Khor IW. Big data and machine learning algorithms for health-care delivery. Lancet Oncol. (2019) 20: e262– 73. 10.1016/S1470-2045(19)30149-4 31044724 · DOI · Paper page
  46. [47]Cahn A Shoshan A Sagiv T Yesharim R Goshen R Shalev V. Prediction of progression from pre-diabetes to diabetes: development and validation of a machine learning model. Diabetes Metab Res Rev. (2020) 36: e3252. 10.1002/dmrr.3252 31943669 · DOI
  47. [48]Farran B Channanath AM Behbehani K Thanaraj TA. Predictive models to assess risk of type 2 diabetes, hypertension and comorbidity: machine-learning algorithms and validation using national health data from Kuwait–a cohort study. BMJ Open. (2013) 3: e002457. 10.1136/bmjopen-2012-002457 PMC3657675 23676796 · DOI
  48. [49]Cho SB Kim SC Chung MG. Identification of novel population clusters with different susceptibilities to type 2 diabetes and their impact on the prediction of diabetes. Sci Rep. (2019) 9: 3329. 10.1038/s41598-019-40058-y 30833619 PMC6399283 · DOI
  49. [50]Lee BJ Kim JY. Identification of type 2 diabetes risk factors using phenotypes consisting of anthropometry and triglycerides based on machine learning. IEEE J Biomed Health Inform. (2016) 20: 39– 46. 10.1109/JBHI.2015.2396520 25675467 · DOI
  50. [51]Alghamdi M Al-Mallah M Keteyian S Brawner C Ehrman J Sakr S. Predicting diabetes mellitus using SMOTE and ensemble machine learning approach: the Henry Ford ExercIse Testing (FIT) project. PLoS ONE. (2017) 12: e179805. 10.1371/journal.pone.0179805 28738059 PMC5524285 · DOI
  51. [52]Ji X Tong W Liu Z Shi T. Five-feature model for developing the classifier for synergistic vs. antagonistic drug combinations built by XGBoost. Front Genet. (2019) 10: 600. 10.3389/fgene.2019.00600 31338106 PMC6629777 · DOI
  52. [53]Chen T Li X Li Y Xia E Qin Y Liang S. Prediction and risk stratification of kidney outcomes in IgA nephropathy. Am J Kidney Dis. (2019) 74: 300– 9. 10.1053/j.ajkd.2019.02.016 31031086 · DOI
  53. [54]Xiao J Ding R Xu X Guan H Feng X Sun T. Comparison and development of machine learning tools in the prediction of chronic kidney disease progression. J Transl Med. (2019) 17: 119. 10.1186/s12967-019-1860-0 30971285 PMC6458616 · DOI
  54. [55]Khemasuwan D Sorensen J Griffin DC. Predictive variables for failure in administration of intrapleural tissue plasminogen activator/deoxyribonuclease in patients with complicated parapneumonic effusions/empyema. Chest. (2018) 154: 550– 6. 10.1016/j.chest.2018.01.037 29425674 · DOI
  55. [57]Nichols GA Hillier TA Brown JB. Progression from newly acquired impaired fasting glusose to type 2 diabetes. Diabetes Care. (2007) 30: 228– 33. 10.2337/dc06-1392 17259486 PMC1851903 · DOI
  56. [58]Arnlov J Sundstrom J Ingelsson E Lind L. Impact of BMI and the metabolic syndrome on the risk of diabetes in middle-aged men. Diabetes Care. (2011) 34: 61– 5. 10.2337/dc10-0955 20852030 PMC3005442 · DOI
  57. [59]Tirosh A Shai I Afek A Dubnov-Raz G Ayalon N Gordon B. Adolescent BMI trajectory and risk of diabetes versus coronary disease. N Engl J Med. (2011) 364: 1315– 25. 10.1056/NEJMoa1006992 21470009 PMC4939259 · DOI
  58. [60]Vozarova B Stefan N Lindsay RS Saremi A Pratley RE Bogardus C. High alanine aminotransferase is associated with decreased hepatic insulin sensitivity and predicts the development of type 2 diabetes. Diabetes. (2002) 51: 1889– 95. 10.2337/diabetes.51.6.1889 12031978 · DOI · Paper page
  59. [61]Meijnikman AS Gerdes VE Nieuwdorp M Herrema H. Evaluating causality of gut microbiota in obesity and diabetes in humans. Endocr Rev. (2018) 39: 133– 53. 10.1210/er.2017-00192 29309555 · DOI
  60. [62]Wu L Parhofer KG. Diabetic dyslipidemia. Metabolism. (2014) 63: 1469– 79. 10.1016/j.metabol.2014.08.010 25242435 · DOI
  61. [63]Qiao Q Hu G Tuomilehto J Nakagami T Balkau B Borch-Johnsen K. Age- and sex-specific prevalence of diabetes and impaired glucose regulation in 11 Asian cohorts. Diabetes Care. (2003) 26: 1770– 80. 10.2337/diacare.26.6.1770 12766108 · DOI
  62. [64]Chang AM Halter JB. Aging and insulin secretion. Am J Physiol Endocrinol Metab. (2003) 284: E7– 12. 10.1152/ajpendo.00366.2002 12485807 · DOI · Paper page
  63. [66]Segar MW Vaduganathan M Patel KV McGuire DK Butler J Fonarow GC. Machine learning to predict the risk of incident heart failure hospitalization among patients with diabetes: the WATCH-DM risk score. Diabetes Care. (2019) 42: 2298– 306. 10.2337/dc19-0587 31519694 PMC7364669 · DOI

Cited by

Sorted by citations

Authors
Wu, Y., Hu, H., Cai, J., Chen, R., Zuo, X., Cheng, H., & Yan, D.
Affiliations
  • Shenzhen University (CN)
  • Shenzhen Third People’s Hospital (CN)
Corresponding author
Yan, Dewen
ORCID
Venue
Frontiers in Public Health
Publisher
Frontiers Media SA
Published
2021-06-29
Volume
9
Pages
626331-626331
ISSN
2296-2565 (ISSN-L)
DOI
10.3389/fpubh.2021.626331
PMC
PMC8275929
OpenAlex
W3174030102
Cited by
28
References
3
Citations by year
2026: 2 · 2025: 5 · 2024: 4 · 2023: 6 · 2022: 10 · 2021: 1
FWCI
4.58
Type
journal article
Language
en
Open access
Licence
Locations
  • Frontiers in Public Health (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
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
new-onset diabetes, diabetes risk prediction, risk assessment model, XGBoost, nomogram, fasting blood glucose, body mass index, Chinese adults, external validation, Japanese cohort, model calibration
MeSH terms
Machine Learning, Adult, China, Diabetes Mellitus, Humans, Random Allocation, Cohort Studies, Risk Assessment

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