{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T21:57:29Z","timestamp":1787003849455,"version":"3.56.0"},"reference-count":91,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T00:00:00Z","timestamp":1613088000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T00:00:00Z","timestamp":1613088000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001804","name":"Canada Research Chairs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000024","name":"Gouvernement du Canada | Canadian Institutes of Health Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Across jurisdictions, government and health insurance providers hold a large amount of data from patient interactions with the healthcare system. We aimed to develop a machine learning-based model for predicting adverse outcomes due to diabetes complications using administrative health data from the single-payer health system in Ontario, Canada. A Gradient Boosting Decision Tree model was trained on data from 1,029,366 patients, validated on 272,864 patients, and tested on 265,406 patients. Discrimination was assessed using the AUC statistic and calibration was assessed visually using calibration plots overall and across population subgroups. Our model predicting three-year risk of adverse outcomes due to diabetes complications (hyper\/hypoglycemia, tissue infection, retinopathy, cardiovascular events, amputation) included 700 features from multiple diverse data sources and had strong discrimination (average test AUC\u2009=\u200977.7, range 77.7\u201377.9). Through the design and validation of a high-performance model to predict diabetes complications adverse outcomes at the population level, we demonstrate the potential of machine learning and administrative health data to inform health planning and healthcare resource allocation for diabetes management.<\/jats:p>","DOI":"10.1038\/s41746-021-00394-8","type":"journal-article","created":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T06:05:04Z","timestamp":1613109904000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":112,"title":["Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data"],"prefix":"10.1038","volume":"4","author":[{"given":"Mathieu","family":"Ravaut","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9715-1635","authenticated-orcid":false,"given":"Hamed","family":"Sadeghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kin Kwan","family":"Leung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maksims","family":"Volkovs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kathy","family":"Kornas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6364-2439","authenticated-orcid":false,"given":"Vinyas","family":"Harish","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8257-4216","authenticated-orcid":false,"given":"Tristan","family":"Watson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gary F.","family":"Lewis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alanna","family":"Weisman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomi","family":"Poutanen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4867-869X","authenticated-orcid":false,"given":"Laura","family":"Rosella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,12]]},"reference":[{"key":"394_CR1","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.diabres.2013.11.002","volume":"103","author":"L Guariguata","year":"2014","unstructured":"Guariguata, L. et al. Global estimates of diabetes prevalence for 2013 and projections for 2035. Diabetes Res. Clin. Pract. 103, 137\u2013149 (2014).","journal-title":"Diabetes Res. Clin. Pract."},{"key":"394_CR2","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.2522\/ptj.20080020","volume":"88","author":"AD Deshpande","year":"2008","unstructured":"Deshpande, A. D., Harris-Hayes, M. & Schootman, M. Epidemiology of diabetes and diabetes-related complications. Phys. Ther. 88, 1254\u20131264 (2008).","journal-title":"Phys. Ther."},{"key":"394_CR3","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s00125-018-4711-2","volume":"62","author":"JL Harding","year":"2019","unstructured":"Harding, J. L., Pavkov, M. E., Magliano, D. J., Shaw, J. E. & Gregg, E. W. Global trends in diabetes complications: a review of current evidence. Diabetologia 62, 3\u201316 (2019).","journal-title":"Diabetologia"},{"key":"394_CR4","doi-asserted-by":"publisher","first-page":"476","DOI":"10.2337\/diacare.25.3.476","volume":"25","author":"JJ Caro","year":"2002","unstructured":"Caro, J. J., Ward, A. J. & O\u2019Brien, J. A. Lifetime costs of complications resulting from type 2 diabetes in the U.S. Diabetes Care 25, 476\u2013481 (2002).","journal-title":"Diabetes Care"},{"key":"394_CR5","first-page":"e62","volume":"21","author":"L Hazel-Fernandez","year":"2015","unstructured":"Hazel-Fernandez, L. et al. Relationship of diabetes complications severity to healthcare utilization and costs among Medicare Advantage beneficiaries. Am. J. Manag. Care 21, e62\u2013e70 (2015).","journal-title":"Am. J. Manag. Care"},{"key":"394_CR6","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1056\/NEJM199309303291401","volume":"329","author":"Diabetes Control and Complications Trial Research Group.","year":"1993","unstructured":"Diabetes Control and Complications Trial Research Group. et al. The effect of intensive treatment of diabetes on the development and progression of long-term complications in insulin-dependent diabetes mellitus. N. Engl. J. Med. 329, 977\u2013986 (1993).","journal-title":"N. Engl. J. Med."},{"key":"394_CR7","doi-asserted-by":"crossref","unstructured":"Turner, R. et al. Tight blood pressure control and risk of macrovascular and microvascular complications in type 2 diabetes: UKPDS 38. UK Prospective Diabetes Study Group. BMJ 317, 703\u2013713 (1998).","DOI":"10.1136\/bmj.317.7160.703"},{"key":"394_CR8","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1016\/S0140-6736(04)16895-5","volume":"364","author":"HM Colhoun","year":"2004","unstructured":"Colhoun, H. M. et al. Primary prevention of cardiovascular disease with atorvastatin in type 2 diabetes in the Collaborative Atorvastatin Diabetes Study (CARDS): multicentre randomised placebo-controlled trial. Lancet 364, 685\u2013696 (2004).","journal-title":"Lancet"},{"key":"394_CR9","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1056\/NEJMoa021778","volume":"348","author":"P Gaede","year":"2003","unstructured":"Gaede, P. et al. Multifactorial intervention and cardiovascular disease in patients with type 2 diabetes. N. Engl. J. Med. 348, 383\u2013393 (2003).","journal-title":"N. Engl. J. Med."},{"key":"394_CR10","doi-asserted-by":"publisher","first-page":"1795","DOI":"10.1161\/CIRCULATIONAHA.115.015220","volume":"132","author":"Pan An","year":"2015","unstructured":"An, Pan, Yeli, Wang, Mohammad, Talaei & Hu Frank, B. Relation of smoking with total mortality and cardiovascular events among patients with diabetes mellitus. Circulation 132, 1795\u20131804 (2015).","journal-title":"Circulation"},{"key":"394_CR11","doi-asserted-by":"publisher","first-page":"23","DOI":"10.2337\/diaspect.14.1.23","volume":"14","author":"JC Zgibor","year":"2001","unstructured":"Zgibor, J. C. & Songer, T. J. External barriers to diabetes care: addressing personal and health systems issues. Diabetes Spectr. 14, 23\u201328 (2001).","journal-title":"Diabetes Spectr."},{"key":"394_CR12","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.annepidem.2011.02.007","volume":"21","author":"AM Secrest","year":"2011","unstructured":"Secrest, A. M. et al. Associations between socioeconomic status and major complications in type 1 diabetes: the Pittsburgh epidemiology of diabetes complication (EDC) Study. Ann. Epidemiol. 21, 374\u2013381 (2011).","journal-title":"Ann. Epidemiol."},{"key":"394_CR13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0176087","volume":"12","author":"M Funakoshi","year":"2017","unstructured":"Funakoshi, M. et al. Socioeconomic status and type 2 diabetes complications among young adult patients in Japan. PLoS ONE 12, e0176087 (2017).","journal-title":"PLoS ONE"},{"key":"394_CR14","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6963-6-124","volume":"6","author":"DM Rabi","year":"2006","unstructured":"Rabi, D. M. et al. Association of socio-economic status with diabetes prevalence and utilization of diabetes care services. BMC Health Serv. Res. 6, 124 (2006).","journal-title":"BMC Health Serv. Res."},{"key":"394_CR15","doi-asserted-by":"publisher","first-page":"2533","DOI":"10.2337\/dc12-0572","volume":"35","author":"LE Egede","year":"2012","unstructured":"Egede, L. E. et al. Medication nonadherence in diabetes: longitudinal effects on costs and potential cost savings from improvement. Diabetes Care 35, 2533\u20132539 (2012).","journal-title":"Diabetes Care"},{"key":"394_CR16","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1038\/nrendo.2014.90","volume":"10","author":"GL Booth","year":"2014","unstructured":"Booth, G. L. & Zinman, B. Diabetes: progress in reducing vascular complications of diabetes. Nat. Rev. Endocrinol. 10, 451\u2013453 (2014).","journal-title":"Nat. Rev. Endocrinol."},{"key":"394_CR17","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1370\/afm.119","volume":"2","author":"AG Mainous 3rd","year":"2004","unstructured":"Mainous, A. G. 3rd, King, D. E., Garr, D. R. & Pearson, W. S. Race, rural residence, and control of diabetes and hypertension. Ann. Fam. Med. 2, 563\u2013568 (2004).","journal-title":"Ann. Fam. Med."},{"key":"394_CR18","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1111\/dme.12801","volume":"33","author":"GL Booth","year":"2016","unstructured":"Booth, G. L. et al. Early specialist care for diabetes: who benefits most? A propensity score-matched cohort study. Diabet. Med. 33, 111\u2013118 (2016).","journal-title":"Diabet. Med."},{"key":"394_CR19","doi-asserted-by":"publisher","first-page":"2211","DOI":"10.1001\/jama.2016.5898","volume":"315","author":"MI Creatore","year":"2016","unstructured":"Creatore, M. I. et al. Association of neighborhood walkability with change in overweight, obesity, and diabetes. JAMA 315, 2211\u20132220 (2016).","journal-title":"JAMA"},{"key":"394_CR20","doi-asserted-by":"crossref","unstructured":"Shah, R., Luo, J., Gerstein, H. C. & Booth, G. Neighborhood walkability and diabetes-related complications. Diabetes 67, Supplement 1 (2018).","DOI":"10.2337\/db18-309-OR"},{"key":"394_CR21","doi-asserted-by":"publisher","first-page":"681","DOI":"10.7326\/M14-0019","volume":"161","author":"MK Ali","year":"2014","unstructured":"Ali, M. K., Bullard, K. M., Gregg, E. W. & Del Rio, C. A cascade of care for diabetes in the United States: visualizing the gaps. Ann. Intern. Med. 161, 681\u2013689 (2014).","journal-title":"Ann. Intern. Med."},{"key":"394_CR22","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.2337\/diacare.24.9.1547","volume":"24","author":"JV Selby","year":"2001","unstructured":"Selby, J. V., Karter, A. J., Ackerson, L. M., Ferrara, A. & Liu, J. Developing a prediction rule from automated clinical databases to identify high-risk patients in a large population with diabetes. Diabetes Care 24, 1547\u20131555 (2001).","journal-title":"Diabetes Care"},{"key":"394_CR23","doi-asserted-by":"publisher","first-page":"1726","DOI":"10.1007\/s00125-013-2933-x","volume":"56","author":"E Pagano","year":"2013","unstructured":"Pagano, E. et al. Prediction of mortality and macrovascular complications in type 2 diabetes: validation of the UKPDS Outcomes Model in the Casale Monferrato Survey, Italy. Diabetologia 56, 1726\u20131734 (2013).","journal-title":"Diabetologia"},{"key":"394_CR24","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1111\/dom.12686","volume":"18","author":"CM Parrinello","year":"2016","unstructured":"Parrinello, C. M. et al. Risk prediction of major complications in individuals with diabetes: the Atherosclerosis Risk in Communities Study. Diabetes Obes. Metab. 18, 899\u2013906 (2016).","journal-title":"Diabetes Obes. Metab."},{"key":"394_CR25","doi-asserted-by":"publisher","first-page":"852","DOI":"10.2337\/dc19-2057","volume":"43","author":"A Aminian","year":"2020","unstructured":"Aminian, A. et al. Predicting 10-year risk of end-organ complications of type 2 diabetes with and without metabolic surgery: a machine learning approach. Diabetes Care 43, 852\u2013859 (2020).","journal-title":"Diabetes Care"},{"key":"394_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-58601-7","volume":"10","author":"P Dworzynski","year":"2020","unstructured":"Dworzynski, P. et al. Nationwide prediction of type 2 diabetes comorbidities. Sci. Rep. 10, 1776 (2020).","journal-title":"Sci. Rep."},{"key":"394_CR27","doi-asserted-by":"publisher","DOI":"10.2196\/15510","volume":"8","author":"X Song","year":"2020","unstructured":"Song, X. et al. Longitudinal risk prediction of chronic kidney disease in diabetic patients using a temporal-enhanced gradient boosting machine: retrospective cohort study. JMIR Med. Inf. 8, e15510 (2020).","journal-title":"JMIR Med. Inf."},{"key":"394_CR28","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.2337\/dc19-0587","volume":"42","author":"MW Segar","year":"2019","unstructured":"Segar, M. W. et al. Machine learning to predict the risk of incident heart failure hospitalization among patients with diabetes: the WATCH-DM risk score. Diabetes Care 42, 2298\u20132306 (2019).","journal-title":"Diabetes Care"},{"key":"394_CR29","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0213653","volume":"14","author":"AM Alaa","year":"2019","unstructured":"Alaa, A. M., Bolton, T., Di Angelantonio, E., Rudd, J. H. F. & van der Schaar, M. Cardiovascular disease risk prediction using automated machine learning: a prospective study of 423,604 UK Biobank participants. PLoS ONE 14, e0213653 (2019).","journal-title":"PLoS ONE"},{"key":"394_CR30","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1111\/cts.12647","volume":"12","author":"V Rodriguez-Romero","year":"2019","unstructured":"Rodriguez-Romero, V. et al. Prediction of nephropathy in type 2 diabetes: an analysis of the ACCORD trial applying machine learning techniques. Clin. Transl. Sci. 12, 519\u2013528 (2019).","journal-title":"Clin. Transl. Sci."},{"key":"394_CR31","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-48263-5","volume":"9","author":"M Makino","year":"2019","unstructured":"Makino, M. et al. Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learning. Sci. Rep. 9, 11862 (2019).","journal-title":"Sci. Rep."},{"key":"394_CR32","doi-asserted-by":"publisher","first-page":"3667","DOI":"10.1177\/0962280218810911","volume":"28","author":"TS Brisimi","year":"2019","unstructured":"Brisimi, T. S., Xu, T., Wang, T., Dai, W. & Paschalidis, I. C. Predicting diabetes-related hospitalizations based on electronic health records. Stat. Methods Med. Res. 28, 3667\u20133682 (2019).","journal-title":"Stat. Methods Med. Res."},{"key":"394_CR33","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1177\/1932296817706375","volume":"12","author":"A Dagliati","year":"2018","unstructured":"Dagliati, A. et al. Machine learning methods to predict diabetes complications. J. Diabetes Sci. Technol. 12, 295\u2013302 (2018).","journal-title":"J. Diabetes Sci. Technol."},{"key":"394_CR34","doi-asserted-by":"publisher","DOI":"10.4178\/epih.e2016011","volume":"38","author":"M Kazemi","year":"2016","unstructured":"Kazemi, M., Moghimbeigi, A., Kiani, J., Mahjub, H. & Faradmal, J. Diabetic peripheral neuropathy class prediction by multicategory support vector machine model: a cross-sectional study. Epidemiol. Health 38, e2016011 (2016).","journal-title":"Epidemiol. Health"},{"key":"394_CR35","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1093\/ije\/dyp373","volume":"39","author":"DG Manuel","year":"2010","unstructured":"Manuel, D. G. & Rosella, L. C. Commentary: assessing population (baseline) risk is a cornerstone of population health planning-looking forward to address new challenges. Int. J. Epidemiol. 39, 380\u2013382 (2010).","journal-title":"Int. J. Epidemiol."},{"key":"394_CR36","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1007\/s11892-019-1200-z","volume":"19","author":"SM Gruss","year":"2019","unstructured":"Gruss, S. M. et al. Public health approaches to type 2 diabetes prevention: the US National Diabetes Prevention Program and Beyond. Curr. Diab. Rep. 19, 78 (2019).","journal-title":"Curr. Diab. Rep."},{"key":"394_CR37","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1146\/annurev.publhealth.22.1.213","volume":"22","author":"BA Virnig","year":"2001","unstructured":"Virnig, B. A. & McBean, M. Administrative data for public health surveillance and planning. Annu. Rev. Public Health 22, 213\u2013230 (2001).","journal-title":"Annu. Rev. Public Health"},{"key":"394_CR38","doi-asserted-by":"publisher","first-page":"666","DOI":"10.7326\/0003-4819-127-8_Part_2-199710151-00048","volume":"127","author":"LI Iezzoni","year":"1997","unstructured":"Iezzoni, L. I. Assessing quality using administrative data. Ann. Intern. Med. 127, 666\u2013674 (1997).","journal-title":"Ann. Intern. Med."},{"key":"394_CR39","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44\u201356 (2019).","journal-title":"Nat. Med."},{"key":"394_CR40","doi-asserted-by":"publisher","first-page":"e13","DOI":"10.1016\/S2589-7500(19)30002-0","volume":"1","author":"T Panch","year":"2019","unstructured":"Panch, T., Pearson-Stuttard, J., Greaves, F. & Atun, R. Artificial intelligence: opportunities and risks for public health. Lancet Digital Health 1, e13\u2013e14 (2019).","journal-title":"Lancet Digital Health"},{"key":"394_CR41","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.cjca.2012.01.005","volume":"28","author":"H Quan","year":"2012","unstructured":"Quan, H. et al. Mining administrative health databases to advance medical science: geographical considerations and untapped potential in Canada. Can. J. Cardiol. 28, 152\u2013154 (2012).","journal-title":"Can. J. Cardiol."},{"key":"394_CR42","doi-asserted-by":"publisher","first-page":"512","DOI":"10.2337\/diacare.25.3.512","volume":"25","author":"JE Hux","year":"2002","unstructured":"Hux, J. E., Ivis, F., Flintoft, V. & Bica, A. Diabetes in Ontario: determination of prevalence and incidence using a validated administrative data algorithm. Diabetes Care 25, 512\u2013516 (2002).","journal-title":"Diabetes Care"},{"key":"394_CR43","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. ImageNet: a large-scale hierarchical image database. in Proc. 2009 IEEE Conference on Computer Vision and Pattern Recognition 248\u2013255 https:\/\/arxiv.org\/pdf\/1804.07461.pdf (2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"394_CR44","doi-asserted-by":"crossref","unstructured":"Wang, A. et al. GLUE: a multi-task benchmark and analysis platform for natural language understanding. arXiv (2018).","DOI":"10.18653\/v1\/W18-5446"},{"key":"394_CR45","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1186\/s41512-017-0020-3","volume":"1","author":"M Assel","year":"2017","unstructured":"Assel, M., Sjoberg, D. D. & Vickers, A. J. The Brier score does not evaluate the clinical utility of diagnostic tests or prediction models. Diagn. Progn. Res. 1, 19 (2017).","journal-title":"Diagn. Progn. Res."},{"key":"394_CR46","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","volume":"2","author":"SM Lundberg","year":"2020","unstructured":"Lundberg, S. M. et al. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2, 56\u201367 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"394_CR47","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1111\/dme.12858","volume":"33","author":"LC Rosella","year":"2016","unstructured":"Rosella, L. C. et al. Impact of diabetes on healthcare costs in a population-based cohort: a cost analysis. Diabet. Med. 33, 395\u2013403 (2016).","journal-title":"Diabet. Med."},{"key":"394_CR48","doi-asserted-by":"publisher","first-page":"S13","DOI":"10.1007\/s00125-002-0859-9","volume":"45","author":"R Williams","year":"2002","unstructured":"Williams, R., Van Gaal, L. & Lucioni, C., CODE-2 Advisory Board. Assessing the impact of complications on the costs of Type II diabetes. Diabetologia 45, S13\u2013S17 (2002).","journal-title":"Diabetologia"},{"key":"394_CR49","unstructured":"Wodchis, W. P., Bushmeneva, K., Nikitovic, M. & McKillop, I. Guidelines on Person-Level Costing Using Administrative Databases in Ontario. https:\/\/tspace.library.utoronto.ca\/bitstream\/1807\/87373\/1\/Wodchis%20et%20al_2013_Guidelines%20on%20Person-Level%20Costing.pdf (2013)."},{"key":"394_CR50","doi-asserted-by":"publisher","first-page":"3535","DOI":"10.2337\/dc13-0610","volume":"36","author":"KJ Lipska","year":"2013","unstructured":"Lipska, K. J. et al. HbA1c and risk of severe hypoglycemia in type 2 diabetes: the Diabetes and Aging Study. Diabetes Care 36, 3535\u20133542 (2013).","journal-title":"Diabetes Care"},{"key":"394_CR51","doi-asserted-by":"publisher","first-page":"1076","DOI":"10.3389\/fgene.2019.01076","volume":"10","author":"S Perveen","year":"2019","unstructured":"Perveen, S., Shahbaz, M., Ansari, M. S., Keshavjee, K. & Guergachi, A. A hybrid approach for modeling type 2 diabetes mellitus progression. Front. Genet. 10, 1076 (2019).","journal-title":"Front. Genet."},{"key":"394_CR52","doi-asserted-by":"publisher","first-page":"49","DOI":"10.2147\/IJNRD.S194727","volume":"12","author":"T Chen","year":"2019","unstructured":"Chen, T. et al. Prediction of cardiovascular outcomes with machine learning techniques: application to the Cardiovascular Outcomes in Renal Atherosclerotic Lesions (CORAL) study. Int. J. Nephrol. Renovasc. Dis. 12, 49\u201358 (2019).","journal-title":"Int. J. Nephrol. Renovasc. Dis."},{"key":"394_CR53","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-019-1479-y","volume":"44","author":"R Garcia-Carretero","year":"2019","unstructured":"Garcia-Carretero, R., Vigil-Medina, L., Barquero-Perez, O. & Ramos-Lopez, J. Pulse wave velocity and machine learning to predict cardiovascular outcomes in prediabetic and diabetic populations. J. Med. Syst. 44, 16 (2019).","journal-title":"J. Med. Syst."},{"key":"394_CR54","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1016\/S2213-8587(16)30010-9","volume":"4","author":"EW Gregg","year":"2016","unstructured":"Gregg, E. W., Sattar, N. & Ali, M. K. The changing face of diabetes complications. Lancet Diabetes Endocrinol. 4, 537\u2013547 (2016).","journal-title":"Lancet Diabetes Endocrinol."},{"key":"394_CR55","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1001\/jamainternmed.2013.12956","volume":"174","author":"ES Huang","year":"2014","unstructured":"Huang, E. S. et al. Rates of complications and mortality in older patients with diabetes mellitus: the diabetes and aging study. JAMA Intern. Med. 174, 251\u2013258 (2014).","journal-title":"JAMA Intern. Med."},{"key":"394_CR56","doi-asserted-by":"publisher","first-page":"1571","DOI":"10.1093\/ije\/dyy137","volume":"47","author":"S Mehta","year":"2018","unstructured":"Mehta, S. et al. Development and validation of alternative cardiovascular risk prediction equations for population health planning: a routine health data linkage study of 1.7 million New Zealanders. Int. J. Epidemiol. 47, 1571\u20131584 (2018).","journal-title":"Int. J. Epidemiol."},{"key":"394_CR57","doi-asserted-by":"publisher","first-page":"14","DOI":"10.12927\/hcq.2014.23660","volume":"16","author":"BR Shah","year":"2013","unstructured":"Shah, B. R. Diabetes in visible minority populations in Ontario. Healthc. Q 16, 14\u201317 (2013).","journal-title":"Healthc. Q"},{"key":"394_CR58","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1038\/s41591-019-0649-2","volume":"26","author":"IY Chen","year":"2020","unstructured":"Chen, I. Y., Joshi, S. & Ghassemi, M. Treating health disparities with artificial intelligence. Nat. Med. 26, 16\u201317 (2020).","journal-title":"Nat. Med."},{"key":"394_CR59","doi-asserted-by":"publisher","first-page":"9","DOI":"10.2337\/diaspect.25.1.9","volume":"25","author":"L Jack","year":"2012","unstructured":"Jack, L., Jack, N. H. & Hayes, S. C. Social determinants of health in minority populations: a call for multidisciplinary approaches to eliminate diabetes-related health disparities. Diabetes Spectr. 25, 9\u201313 (2012).","journal-title":"Diabetes Spectr."},{"key":"394_CR60","doi-asserted-by":"publisher","DOI":"10.1186\/s12939-015-0245-0","volume":"14","author":"LA Rivera","year":"2015","unstructured":"Rivera, L. A., Lebenbaum, M. & Rosella, L. C. The influence of socioeconomic status on future risk for developing Type 2 diabetes in the Canadian population between 2011 and 2022: differential associations by sex. Int. J. Equity Health 14, 101 (2015).","journal-title":"Int. J. Equity Health"},{"key":"394_CR61","doi-asserted-by":"crossref","unstructured":"Rosella, L. et al. Accumulation of chronic conditions at the time of death increased in Ontario from 1994 to 2013. Health Aff. 37, 464\u2013472 (2018).","DOI":"10.1377\/hlthaff.2017.1150"},{"key":"394_CR62","doi-asserted-by":"crossref","unstructured":"Gilpin, L. H. et al. Explaining explanations: an overview of interpretability of machine learning. arXiv, https:\/\/arxiv.org\/pdf\/1806.00069.pdf (2018).","DOI":"10.1109\/DSAA.2018.00018"},{"key":"394_CR63","doi-asserted-by":"publisher","DOI":"10.1136\/bmjdrc-2020-001224","volume":"8","author":"A Weisman","year":"2020","unstructured":"Weisman, A. et al. Validation of a type 1 diabetes algorithm using electronic medical records and administrative healthcare data to study the population incidence and prevalence of type 1 diabetes in Ontario. Can. BMJ Open Diabetes Res. Care 8, e001224 (2020).","journal-title":"Can. BMJ Open Diabetes Res. Care"},{"key":"394_CR64","doi-asserted-by":"publisher","first-page":"k1479","DOI":"10.1136\/bmj.k1479","volume":"361","author":"D Agniel","year":"2018","unstructured":"Agniel, D., Kohane, I. S. & Weber, G. M. Biases in electronic health record data due to processes within the healthcare system: retrospective observational study. BMJ 361, k1479 (2018).","journal-title":"BMJ"},{"key":"394_CR65","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1080\/09332480.2019.1579578","volume":"32","author":"MA Hern\u00e1n","year":"2019","unstructured":"Hern\u00e1n, M. A., Hsu, J. & Healy, B. A second chance to get causal inference right: a classification of data science tasks. Chance 32, 42\u201349 (2019).","journal-title":"Chance"},{"key":"394_CR66","unstructured":"Chui, T., Flanders, J. & Anderson, T. Immigration and Ethnocultural Diversity in Canada\u2014National Household Survey. https:\/\/www12.statcan.gc.ca\/nhs-enm\/2011\/as-sa\/99-010-x\/99-010-x2011001-eng.pdf (2011)."},{"key":"394_CR67","doi-asserted-by":"publisher","first-page":"S12","DOI":"10.1007\/BF03403823","volume":"103","author":"FI Matheson","year":"2012","unstructured":"Matheson, F. I., Dunn, J. R., Smith, K. L. W., Moineddin, R. & Glazier, R. H. Building the Canadian marginalization index: a new tool for studying inequalities. Can. J. Public Health 103, S12\u2013S16 (2012).","journal-title":"Can. J. Public Health"},{"key":"394_CR68","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-018-3148-0","volume":"18","author":"LL Lipscombe","year":"2018","unstructured":"Lipscombe, L. L. et al. Identifying diabetes cases from administrative data: a population-based validation study. BMC Health Serv. Res. 18, 316 (2018).","journal-title":"BMC Health Serv. Res."},{"key":"394_CR69","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-49563-6","volume":"9","author":"S Perveen","year":"2019","unstructured":"Perveen, S., Shahbaz, M., Keshavjee, K. & Guergachi, A. Prognostic modeling and prevention of diabetes using machine learning technique. Sci. Rep. 9, 13805 (2019).","journal-title":"Sci. Rep."},{"key":"394_CR70","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","volume":"1","author":"A Rajkomar","year":"2018","unstructured":"Rajkomar, A. et al. Scalable and accurate deep learning with electronic health records. npj Digital Med. 1, 18 (2018).","journal-title":"npj Digital Med."},{"key":"394_CR71","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1089\/big.2015.0020","volume":"3","author":"N Razavian","year":"2015","unstructured":"Razavian, N. et al. Population-level prediction of type 2 diabetes from claims data and analysis of risk factors. Big Data 3, 277\u2013287 (2015).","journal-title":"Big Data"},{"key":"394_CR72","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","volume":"572","author":"N Toma\u0161ev","year":"2019","unstructured":"Toma\u0161ev, N. et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature 572, 116\u2013119 (2019).","journal-title":"Nature"},{"key":"394_CR73","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.15997","volume":"2","author":"RB Parikh","year":"2019","unstructured":"Parikh, R. B. et al. Machine learning approaches to predict 6-month mortality among patients with cancer. JAMA Netw. Open 2, e1915997 (2019).","journal-title":"JAMA Netw. Open"},{"key":"394_CR74","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman, J. H. Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189\u20131232 (2001).","journal-title":"Ann. Stat."},{"key":"394_CR75","doi-asserted-by":"crossref","unstructured":"Chen, T. & Guestrin, C. XGBoost: a scalable tree boosting system. arXiv, https:\/\/arxiv.org\/pdf\/1603.02754.pdf (2016).","DOI":"10.1145\/2939672.2939785"},{"key":"394_CR76","unstructured":"Bojer, C. & Meldgaard, J. Learnings from Kaggle\u2019s Forecasting Competitions. arXiv, https:\/\/arxiv.org\/ftp\/arxiv\/papers\/2009\/2009.07701.pdf (2020)."},{"key":"394_CR77","doi-asserted-by":"crossref","unstructured":"Volkovs, M. et al. Two-stage model for automatic playlist continuation at scale. in Proc. ACM Recommender Systems Challenge 1\u20136 (Association for Computing Machinery, 2018).","DOI":"10.1145\/3267471.3267480"},{"key":"394_CR78","doi-asserted-by":"crossref","unstructured":"Volkovs, M., Yu, G. W. & Poutanen, T. Content-based neighbor models for cold start in recommender systems. in Proc. Recommender Systems Challenge 1\u20136 (Association for Computing Machinery, 2017).","DOI":"10.1145\/3124791.3124792"},{"key":"394_CR79","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1038\/s41591-019-0503-6","volume":"25","author":"I Yelin","year":"2019","unstructured":"Yelin, I. et al. Personal clinical history predicts antibiotic resistance of urinary tract infections. Nat. Med. 25, 1143\u20131152 (2019).","journal-title":"Nat. Med."},{"key":"394_CR80","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-24271-9","volume":"8","author":"Z Che","year":"2018","unstructured":"Che, Z., Purushotham, S., Cho, K., Sontag, D. & Liu, Y. Recurrent neural networks for multivariate time series with missing values. Sci. Rep. 8, 6085 (2018).","journal-title":"Sci. Rep."},{"key":"394_CR81","unstructured":"Vaswani, A. et al. in Advances in Neural Information Processing Systems (eds. Guyon, I. et al.) 5998\u20136008 (Curran Associates, Inc., 2017)."},{"key":"394_CR82","unstructured":"Shavitt, I. & Segal, E. Regularization learning networks: deep learning for tabular datasets. arXiv, https:\/\/papers.nips.cc\/paper\/2018\/file\/500e75a036dc2d7d2fec5da1b71d36cc-Paper.pdf (2018)."},{"key":"394_CR83","doi-asserted-by":"publisher","first-page":"3446","DOI":"10.1016\/j.eswa.2011.09.033","volume":"39","author":"I Brown","year":"2012","unstructured":"Brown, I. & Mues, C. An experimental comparison of classification algorithms for imbalanced credit scoring data sets. Expert Syst. Appl. 39, 3446\u20133453 (2012).","journal-title":"Expert Syst. Appl."},{"key":"394_CR84","unstructured":"Ma, J., Gorti, S. K., Volkovs, M., Stanevich, I. & Yu, G. Cross-class relevance learning for temporal concept localization. arXiv, https:\/\/arxiv.org\/pdf\/1911.08548.pdf (2019)."},{"key":"394_CR85","unstructured":"Ling, C. X. & Li, C. Data mining for direct marketing: problems and solutions. in Proc. Fourth International Conference on Knowledge Discovery and Data Mining 73\u201379 (AAAI Press, 1998)."},{"key":"394_CR86","doi-asserted-by":"crossref","unstructured":"Akbani, R., Kwek, S. & Japkowicz, N. in Machine Learning: ECML 39\u201350 (Springer Berlin Heidelberg, 2004).","DOI":"10.1007\/978-3-540-30115-8_7"},{"key":"394_CR87","doi-asserted-by":"crossref","unstructured":"Pozzolo, A. D., Caelen, O., Johnson, R. A. & Bontempi, G. Calibrating probability with undersampling for unbalanced classification. in 2015 IEEE Symposium Series on Computational Intelligence 159\u2013166 (2015).","DOI":"10.1109\/SSCI.2015.33"},{"key":"394_CR88","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","volume":"30","author":"AP Bradley","year":"1997","unstructured":"Bradley, A. P. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn. 30, 1145\u20131159 (1997).","journal-title":"Pattern Recogn."},{"key":"394_CR89","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1126\/science.3287615","volume":"240","author":"JA Swets","year":"1988","unstructured":"Swets, J. A. Measuring the accuracy of diagnostic systems. Science 240, 1285\u20131293 (1988).","journal-title":"Science"},{"key":"394_CR90","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/S1499-2671(10)41005-9","volume":"34","author":"G Doucet","year":"2010","unstructured":"Doucet, G. & Beatty, M. The cost of diabetes in Canada: the economic Tsunami. Can. J. Diabetes 34, 27\u201329 (2010).","journal-title":"Can. J. Diabetes"},{"key":"394_CR91","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1503\/cmaj.150064","volume":"188","author":"WP Wodchis","year":"2016","unstructured":"Wodchis, W. P., Austin, P. C. & Henry, D. A. A 3-year study of high-cost users of health care. CMAJ 188, 182\u2013188 (2016).","journal-title":"CMAJ"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00394-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00394-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00394-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T14:13:11Z","timestamp":1670076791000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00394-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,12]]},"references-count":91,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["394"],"URL":"https:\/\/doi.org\/10.1038\/s41746-021-00394-8","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,12]]},"assertion":[{"value":"18 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"M.R., H.S., K.L., M.V., and T.P. are full-time employees of Layer 6 AI, co-founded by M.V. and T.P., owned by Toronto-Dominion Bank. V.H., K.K., and T.W. are employed at the Dalla Lana School of Public Health. The employers of the authors had no role in the design or funding of this research.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"24"}}