Machine Learning Models in Type 2 Diabetes Risk Prediction: Results from a Cross-sectional Retrospective Study in Chinese Adults

Abstract

Type 2 diabetes mellitus (T2DM) has become a prevalent health problem in China, especially in urban areas. Early prevention strategies are needed to reduce the associated mortality and morbidity. We applied the combination of rules and different machine learning techniques to assess the risk of development of T2DM in an urban Chinese adult population. A retrospective analysis was performed on 8000 people with non-diabetes and 3845 people with T2DM in Nanjing. Multilayer Perceptron (MLP), AdaBoost (AD), Trees Random Forest (TRF), Support Vector Machine (SVM), and Gradient Tree Boosting (GTB) machine learning techniques with 10 cross validation methods were used with the proposed model for the prediction of the risk of development of T2DM. The performance of these models was evaluated with accuracy, precision, sensitivity, specificity, and area under receiver operating characteristic (ROC) curve (AUC). After comparison, the prediction accuracy of the different five machine models was 0.87, 0.86, 0.86, 0.86 and 0.86 respectively. The combination model using the same voting weight of each component was built on T2DM, which was performed better than individual models. The findings indicate that, combining machine learning models could provide an accurate assessment model for T2DM risk prediction.

Keywords

type 2 diabetes / risk prediction / machine learning

References

[1] WangL, GaoP, ZhangM, et al.. Prevalence and Ethnic Pattern of Diabetes and Prediabetes in China in 2013. JAMA, 2017, 317(24): 2515-2523

[2] YangW, LuJ, WengJ, et al.. Prevalence of diabetes among men and women in China. N Engl J Med, 2010, 362(12): 1090-1101

[3] XuY, WangL, HeJ, et al.. Prevalence and control of diabetes in Chinese adults. JAMA, 2013, 310(9): 948-959

[4] PanXR, YangWY, LiGW, et al.. Prevalence of diabetes and its risk factors in China, 1994. National Diabetes Prevention and Control Cooperative Group. Diabetes Care, 1997, 20(11): 1664-1669

[5] LiG, ZhangP, WangJ, et al.. The long-term effect of lifestyle interventions to prevent diabetes in the China Da Qing Diabetes Prevention Study: a 20-year follow-up study. Lancet, 2008, 371(9626): 1783-1789

[6] LindstromJ, Ilanne-ParikkaP, PeltonenM, et al.. Sustained reduction in the incidence of type 2 diabetes by lifestyle intervention: follow-up of the Finnish Diabetes Prevention Study. Lancet, 20061673-1679

[7] KnowlerWC, Barrett-ConnorE, FowlerSE, et al.. Reduction in the incidence of type 2 diabetes with lifestyle intervention or metformin. N Engl J Med, 2002, 346(6): 393-403

[8] KnowlerWC, FowlerSE, HammanRF, et al.. 10-year follow-up of diabetes incidence and weight loss in the Diabetes Prevention Program Outcomes Study. Lancet, 2009, 374(9702): 1677-1686

[9] BuijsseB, SimmonsRK, GriffinSJ, et al.. Risk assessment tools for identifying individuals at risk of developing type 2 diabetes. Epidemiol Rev, 2011, 33: 46-62

[10] ThoopputraT, NewbyD, SchneiderJ, et al.. Survey of diabetes risk assessment tools: concepts, structure and performance. Diabetes Metab Res Rev, 2012, 28(6): 485-498

[11] AbbasiA, PeelenLM, CorpeleijnE, et al.. Prediction models for risk of developing type 2 diabetes: systematic literature search and independent external validation study. BMJ, 2012, 345: e5900

[12] CollinsGS, MallettS, OmarO, et al.. Developing risk prediction models for type 2 diabetes: a systematic review of methodology and reporting. BMC Med, 2011, 9: 103

[13] NobleD, MathurR, DentT, et al.. Risk models and scores for type 2 diabetes: systematic review. BMJ, 2011, 343: d7163

[14] YooI, AlafaireetP, MarinovM, et al.. Data mining in healthcare and biomedicine: a survey of the literature. J Med Syst, 2012, 36(4): 2431-2448

[15] BarberSR, DaviesMJ, KhuntiK, et al.. Risk assessment tools for detecting those with pre-diabetes: a systematic review. Diabetes Res Clin Pract, 2014, 105(1): 1-13

[16] Shankaracharya, OdedraD, SamantaS, et al.. Computational intelligence in early diabetes diagnosis: a review. Rev Diabet Stud, 2010, 7(4): 252-262

[17] Choi SB, Kim WJ, Yoo TK, et al. Screening for prediabetes using machine learning models. Comput Math Methods Med, 2014, 2014:618976

[18] WangC, LiL, WangL, et al.. Evaluating the risk of type 2 diabetes mellitus using artificial neural network: an effective classification approach. Diabetes Res Clin Pract, 2013, 00(1): 111-118

[19] MansourR, EghbalZ, AmirhosseinH. Comparison of Artificial Neural Network, Logistic Regression and Discriminant Analysis Efficiency in Determining Risk Factors of Type 2 Diabetes. World Appl Sci J, 2013, 23(11): 1522-1529

[20] MengXH, HuangYX, RaoDP, et al.. Comparison of three data mining models for predicting diabetes or prediabetes by risk factors. Kaohsiung J Med Sci, 2013, 29(2): 93-99

[21] QuinlanJR. Induction of decision trees. Machine Learning, 1986, 1(1): 81-106

[22] SeniG, ElderJ. Ensemble Methods in Data Mining: Improving Accuracy Through Combining Predictions, 2010, USA, Morgan & Claypool Publishers

[23] PatelP, MacerolloA. Diabetes mellitus: diagnosis and screening.. Am Fam Physician., 2010, 81(7): 863-870

[24] American Diabetes Association.. 2. Classification and Diagnosis of Diabetes: Standards of Medical Care in Diabetes-2018. Diabetes Care, 2018, 1(Suppl1): S13-S27

[25] GardnerMW, DorlingSR. Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmos Environ, 1998, 32(14–15): 2627-2636

[26] FerreiraAJ, FigueiredoMAT. Boosting Algorithms: A Review of Methods, Theory, and Applications. Ensemble Machine Learning, 201235-85

[27] BreimanL. Random Forests. Machine Learning, 2001, 45(1): 5-32

[28] NazariZ, KangD. Density Based Support Vector Machines for Classification. IJARAI, 2015, 4(4): 64-76

[29] GersteinHC, YusufS, BoschJ, et al.. Effect of rosiglitazone on the frequency of diabetes in patients with impaired glucose tolerance or impaired fasting glucose: a randomised controlled trial. Lancet, 2006, 368(9541): 1096-1105

[30] NorrisSL, KansagaraD, BougatsosC, et al.. Screening adults for type 2 diabetes: a review of the evidence for the U.S. Preventive Services Task Force. Ann Intern Med, 2008, 148(11): 855-868

[31] Montazeri M, Nezamabadi-Pour H, editors. Automatic extraction of eye field from a gray intensity image using intensity filtering and hybrid projection function. International Conference on Communications, Computing and Control Applications. 2011.

[32] MontazeriM, Nezamabadi-pourH, MontazeriM. Automatically Eye Detection with Different Gray Intensity Image Conditions. Computer Technol Appl, 2012525-532

[33] Mitra M, Bahrololoum A, Nezamabadi-Pour H, et al, editors. Cooperating of Local Searches based Hyperheuristic Approach for Solving Traveling Salesman Problem. Ijcci, 2011.

[34] HashemianAH, BeiranvandB, RezaeiM, et al.. Comparison of Artificial Neural Networks and Cox Regression Models in Prediction of Kidney Transplant Survival. Neuropharmacology, 2012, 62(4): 1717-1729

[35] BangH, EdwardsAM, BombackAS, et al.. Development and Validation of a Patient Self-assessment Score for Diabetes Risk. Ann Intern Med, 2009, 151(11): 775-783

[36] LindströmJ, TuomilehtoJ. The diabetes risk score: a practical tool to predict type 2 diabetes risk. Diabetes Care, 2003, 26(3): 725-731

[37] Diabetes Care, 2007, 30(8):

[38] GlümerC, CarstensenB, SandbækA, et al.. A Danish diabetes risk score for targeted screening: the Inter99 study. Diabetes Care, 2004, 27(3): 727-733

[39] KahnHS, ChengYJ, ThompsonTJ, et al.. Two risk-scoring systems for predicting incident diabetes mellitus in U.S. adults age 45 to 64 years. Ann Intern Med, 2009, 150(11): 741-751

[40] RamachandranA, SnehalathaC, VijayV, et al.. Derivation and validation of diabetes risk score for urban Asian Indians. Diabetes Res Clin Pr, 2005, 70(1): 63-70

[41] AekplakornW, BunnagP, WoodwardM, et al.. A Risk Score for Predicting Incident Diabetes in the Thai Population. Diabetes Care, 2006, 29(29): 1872-1877

[42] GaoWG, DongYH, PangZC, et al.. A simple Chinese risk score for undiagnosed diabetes. Diabetic Med, 2010, 27(3): 274-281

[43] GlümerC, VistisenD, BorchjohnsenK, et al.. Risk Scores for Type 2 Diabetes Can Be Applied in Some Populations but Not All. Diabetes Care, 2006, 29(2): 410-414

[44] HabibiS, AhmadiM, AlizadehS. Type 2 Diabetes Mellitus Screening and Risk Factors Using Decision Tree: Results of Data Mining. Glob J Health Sci, 2015, 7(5): 304-310