{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T16:23:08Z","timestamp":1794932588019,"version":"4.9.1"},"reference-count":27,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2020,7,22]],"date-time":"2020-07-22T00:00:00Z","timestamp":1595376000000},"content-version":"unspecified","delay-in-days":21,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003141","name":"Consejo Nacional de Ciencia y Tecnolog\u00eda","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003141","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009066","name":"Instituto Carlos Slim de la Salud","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009066","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open Diab Res Care"],"accepted":{"date-parts":[[2020,6,14]]},"published-print":{"date-parts":[[2020,7]]},"abstract":"<jats:sec>\n                  <jats:title>Introduction<\/jats:title>\n                  <jats:p>Previous reports in European populations demonstrated the existence of five data-driven adult-onset diabetes subgroups. Here, we use self-normalizing neural networks (SNNN) to improve reproducibility of these data-driven diabetes subgroups in Mexican cohorts to extend its application to more diverse settings.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Research design and methods<\/jats:title>\n                  <jats:p>We trained SNNN and compared it with k-means clustering to classify diabetes subgroups in a multiethnic and representative population-based National Health and Nutrition Examination Survey (NHANES) datasets with all available measures (training sample: NHANES-III, n=1132; validation sample: NHANES 1999\u20132006, n=626). SNNN models were then applied to four Mexican cohorts (SIGMA-UIEM, n=1521; Metabolic Syndrome cohort, n=6144; ENSANUT 2016, n=614\u2009and CAIPaDi, n=1608) to characterize diabetes subgroups in Mexicans according to treatment response, risk for chronic complications and risk factors for the incidence of each subgroup.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>SNNN yielded four reproducible clinical profiles (obesity related, insulin deficient, insulin resistant, age related) in NHANES and Mexican cohorts even without C-peptide measurements. We observed in a population-based survey a high prevalence of the insulin-deficient form (41.25%, 95%\u2009CI 41.02% to 41.48%), followed by obesity-related (33.60%, 95%\u2009CI 33.40% to 33.79%), age-related (14.72%, 95%\u2009CI 14.63% to 14.82%) and severe insulin-resistant groups. A significant association was found between the SLC16A11 diabetes risk variant and the obesity-related subgroup (OR 1.42, 95%\u2009CI 1.10 to 1.83, p=0.008). Among incident cases, we observed a greater incidence of mild obesity-related diabetes (n=149, 45.0%). In a diabetes outpatient clinic cohort, we observed increased 1-year risk (HR 1.59, 95%\u2009CI 1.01 to 2.51) and 2-year risk (HR 1.94, 95%\u2009CI 1.13 to 3.31) for incident retinopathy in the insulin-deficient group and decreased 2-year diabetic retinopathy risk for the obesity-related subgroup (HR 0.49, 95%\u2009CI 0.27 to 0.89).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Diabetes subgroup phenotypes are reproducible using SNNN; our algorithm is available as web-based tool. Application of these models allowed for better characterization of diabetes subgroups and risk factors in Mexicans that could have clinical applications.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1136\/bmjdrc-2020-001550","type":"journal-article","created":{"date-parts":[[2020,7,23]],"date-time":"2020-07-23T02:09:40Z","timestamp":1595470180000},"page":"e001550","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":79,"title":["Clinical characterization of data-driven diabetes subgroups in Mexicans using a reproducible machine learning approach"],"prefix":"10.1136","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3093-937X","authenticated-orcid":false,"given":"Omar Yaxmehen","family":"Bello-Chavolla","sequence":"first","affiliation":[{"name":"Unidad de Investigaci\u00f3n de Enfermedades Metab\u00f3licas, Instituto Nacional de Ciencias M\u00e9dicas y Nutrici\u00f3n Salvador Zubiran, Tlalpan, Mexico"},{"name":"Division of Research, Instituto Nacional de Geriatr\u00eda, Mexico City, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jessica Paola","family":"Bahena-L\u00f3pez","sequence":"additional","affiliation":[{"name":"MD\/PhD (PECEM) Program, Facultad de Medicina, Universidad Nacional Aut\u00f3noma de M\u00e9xico, Coyoacan, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arsenio","family":"Vargas-V\u00e1zquez","sequence":"additional","affiliation":[{"name":"Unidad de Investigaci\u00f3n de Enfermedades Metab\u00f3licas, Instituto Nacional de Ciencias M\u00e9dicas y Nutrici\u00f3n Salvador Zubiran, Tlalpan, Mexico"},{"name":"MD\/PhD (PECEM) Program, Facultad de Medicina, Universidad Nacional Aut\u00f3noma de M\u00e9xico, Coyoacan, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neftali Eduardo","family":"Antonio-Villa","sequence":"additional","affiliation":[{"name":"Unidad de Investigaci\u00f3n de Enfermedades Metab\u00f3licas, Instituto Nacional de Ciencias M\u00e9dicas y Nutrici\u00f3n Salvador Zubiran, Tlalpan, Mexico"},{"name":"MD\/PhD (PECEM) Program, Facultad de Medicina, Universidad Nacional Aut\u00f3noma de M\u00e9xico, Coyoacan, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandro","family":"M\u00e1rquez-Salinas","sequence":"additional","affiliation":[{"name":"MD\/PhD (PECEM) Program, Facultad de Medicina, Universidad Nacional Aut\u00f3noma de M\u00e9xico, Coyoacan, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5627-8851","authenticated-orcid":false,"given":"Carlos A","family":"Ferm\u00edn-Mart\u00ednez","sequence":"additional","affiliation":[{"name":"MD\/PhD (PECEM) Program, Facultad de Medicina, Universidad Nacional Aut\u00f3noma de M\u00e9xico, Coyoacan, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rosalba","family":"Rojas","sequence":"additional","affiliation":[{"name":"Instituto Nacional de Salud Publica, Cuernavaca, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roopa","family":"Mehta","sequence":"additional","affiliation":[{"name":"Unidad de Investigaci\u00f3n de Enfermedades Metab\u00f3licas, Instituto Nacional de Ciencias M\u00e9dicas y Nutrici\u00f3n Salvador Zubiran, Tlalpan, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivette","family":"Cruz-Bautista","sequence":"additional","affiliation":[{"name":"Unidad de Investigaci\u00f3n de Enfermedades Metab\u00f3licas, Instituto Nacional de Ciencias M\u00e9dicas y Nutrici\u00f3n Salvador Zubiran, Tlalpan, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergio","family":"Hern\u00e1ndez-Jim\u00e9nez","sequence":"additional","affiliation":[{"name":"Center of Comprehensive Care for the Patient with Diabetes, Instituto Nacional de Ciencias M\u00e9dicas y Nutrici\u00f3n Salvador Zubir\u00e1n, Mexico City, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ana Cristina","family":"Garc\u00eda-Ulloa","sequence":"additional","affiliation":[{"name":"Center of Comprehensive Care for the Patient with Diabetes, Instituto Nacional de Ciencias M\u00e9dicas y Nutrici\u00f3n Salvador Zubir\u00e1n, Mexico City, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paloma","family":"Almeda-Valdes","sequence":"additional","affiliation":[{"name":"Department of Endocrinology and Metabolism, Salvador Zubiran National Institute of Medical Sciences and Nutrition, Tlalpan, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8517-0241","authenticated-orcid":false,"given":"Carlos Alberto","family":"Aguilar-Salinas","sequence":"additional","affiliation":[{"name":"Unidad de Investigaci\u00f3n de Enfermedades Metab\u00f3licas, Instituto Nacional de Ciencias M\u00e9dicas y Nutrici\u00f3n Salvador Zubiran, Tlalpan, Mexico"},{"name":"Department of Endocrinology and Metabolism, Salvador Zubiran National Institute of Medical Sciences and Nutrition, Tlalpan, Mexico"},{"name":"Escuela de Medicina y Ciencias de la Salud, Tecnologico de Monterrey, Nuevo Leon, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"the Metabolic Syndrome Study Group","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2020,7,22]]},"reference":[{"key":"2025073113143030000_8.1.e001550.1","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/S2213-8587(18)30051-2","article-title":"Novel subgroups of adult-onset diabetes and their association with outcomes: a data-driven cluster analysis of six variables","volume":"6","author":"Ahlqvist","year":"2018","journal-title":"Lancet Diabetes Endocrinol"},{"key":"2025073113143030000_8.1.e001550.2","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1016\/S2213-8587(19)30187-1","article-title":"Risk of diabetes-associated diseases in subgroups of patients with recent-onset diabetes: a 5-year follow-up study","volume":"7","author":"Zaharia","year":"2019","journal-title":"Lancet Diabetes Endocrinol"},{"key":"2025073113143030000_8.1.e001550.3","doi-asserted-by":"publisher","DOI":"10.1210\/jc.2002-021864"},{"key":"2025073113143030000_8.1.e001550.4","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/s13679-019-00349-x","article-title":"Ethnic disparities in adiposity: focus on non-alcoholic fatty liver disease, visceral, and generalized obesity","volume":"8","author":"Agbim","year":"2019","journal-title":"Curr Obes Rep"},{"key":"2025073113143030000_8.1.e001550.5","doi-asserted-by":"crossref","DOI":"10.1016\/j.diabres.2019.107915","article-title":"Epidemiology of diabetes phenotypes and prevalent cardiovascular risk factors and diabetes complications in the National Health and Nutrition Examination Survey 2003-2014","volume":"158","author":"Bancks","year":"2019","journal-title":"Diabetes Res Clin Pract"},{"key":"2025073113143030000_8.1.e001550.6","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1002654","article-title":"Type 2 diabetes genetic loci informed by multi-trait associations point to disease mechanisms and subtypes: a soft clustering analysis","volume":"15","author":"Udler","year":"2018","journal-title":"PLoS Med"},{"key":"2025073113143030000_8.1.e001550.7","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1348\/000711007X184849","article-title":"Stability analysis in k-means clustering","volume":"61","author":"Steinley","year":"2008","journal-title":"Br J Math Stat Psychol"},{"key":"2025073113143030000_8.1.e001550.8","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2105-14-S1-S8","article-title":"Finding reproducible cluster partitions for the k-means algorithm","volume":"14(Suppl 1)","author":"Lisboa","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"2025073113143030000_8.1.e001550.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmva.2006.11.013"},{"key":"2025073113143030000_8.1.e001550.10","unstructured":"Klambauer G , Unterthiner T , Mayr A , et al . Self-Normalizing neural networks. arXiv. 1706.02515v5 [cs.LG]."},{"key":"2025073113143030000_8.1.e001550.11","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1016\/S2213-8587(19)30087-7","article-title":"Disease progression and treatment response in data-driven subgroups of type 2 diabetes compared with models based on simple clinical features: an analysis using clinical trial data","volume":"7","author":"Dennis","year":"2019","journal-title":"Lancet Diabetes Endocrinol"},{"key":"2025073113143030000_8.1.e001550.12","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/S2213-8587(18)30316-4","article-title":"Novel subgroups of patients with adult-onset diabetes in Chinese and US populations","volume":"7","author":"Zou","year":"2019","journal-title":"Lancet Diabetes Endocrinol"},{"key":"2025073113143030000_8.1.e001550.13","doi-asserted-by":"crossref","DOI":"10.1016\/j.clnu.2019.07.012","article-title":"Metabolic score for visceral fat (METS-VF), a novel estimator of intra-abdominal fat content and cardio-metabolic health","volume":"39","author":"Bello-Chavolla","year":"2020","journal-title":"Clin Nutr"},{"key":"2025073113143030000_8.1.e001550.14","doi-asserted-by":"publisher","DOI":"10.1530\/EJE-17-0883"},{"key":"2025073113143030000_8.1.e001550.15","doi-asserted-by":"crossref","DOI":"10.1186\/s12902-019-0361-8","article-title":"Development and validation of a predictive model for incident type 2 diabetes in middle-aged Mexican adults: the metabolic syndrome cohort","volume":"19","author":"Arellano-Campos","year":"2019","journal-title":"BMC Endocr Disord"},{"key":"2025073113143030000_8.1.e001550.16","doi-asserted-by":"crossref","first-page":"50","DOI":"10.21149\/10752","article-title":"[Prevalence of diabetes and poor glycemic control in Mexico: results from Ensanut 2016.]","volume":"62","author":"Basto-Abreu","year":"2020","journal-title":"Salud Publica Mex"},{"key":"2025073113143030000_8.1.e001550.17","doi-asserted-by":"publisher","DOI":"10.1186\/1471-230X-6-33"},{"key":"2025073113143030000_8.1.e001550.18","doi-asserted-by":"publisher","DOI":"10.1038\/nature12828"},{"key":"2025073113143030000_8.1.e001550.19","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1530\/EJE-18-0677","article-title":"The SLC16A11 risk haplotype is associated with decreased insulin action, higher transaminases and large-size adipocytes","volume":"180","author":"Almeda-Valdes","year":"2019","journal-title":"Eur J Endocrinol"},{"key":"2025073113143030000_8.1.e001550.20","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.diabres.2019.04.009","article-title":"Long-Term effectiveness of a type 2 diabetes comprehensive care program. The CAIPaDi model","volume":"151","author":"Hern\u00e1ndez-Jim\u00e9nez","year":"2019","journal-title":"Diabetes Res Clin Pract"},{"key":"2025073113143030000_8.1.e001550.21","doi-asserted-by":"crossref","DOI":"10.3389\/fendo.2019.00185","article-title":"Artificial intelligence and machine learning in endocrinology and metabolism: the dawn of a new era","volume":"10","author":"Gubbi","year":"2019","journal-title":"Front Endocrinol"},{"key":"2025073113143030000_8.1.e001550.22","doi-asserted-by":"publisher","DOI":"10.1093\/nutrit\/nuw030"},{"key":"2025073113143030000_8.1.e001550.23","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/S2213-8587(18)30050-0","article-title":"Effect of diabetes duration and glycaemic control on 14-year cause-specific mortality in Mexican adults: a blood-based prospective cohort study","volume":"6","author":"Herrington","year":"2018","journal-title":"Lancet Diabetes Endocrinol"},{"key":"2025073113143030000_8.1.e001550.24","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-019-43452-8","article-title":"The role of membrane excitability in pancreatic \u03b2-cell glucotoxicity","volume":"9","author":"Shyr","year":"2019","journal-title":"Sci Rep"},{"key":"2025073113143030000_8.1.e001550.25","doi-asserted-by":"publisher","DOI":"10.1111\/j.1464-5491.1994.tb00275.x"},{"key":"2025073113143030000_8.1.e001550.26","doi-asserted-by":"publisher","DOI":"10.3109\/07435800.2015.1136934"},{"key":"2025073113143030000_8.1.e001550.27","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1007\/s00592-018-1241-9","article-title":"High prevalence of humoral autoimmunity in first-degree relatives of Mexican type 1 diabetes patients","volume":"55","author":"Segovia-Gamboa","year":"2018","journal-title":"Acta Diabetol"}],"container-title":["BMJ Open Diabetes Research &amp; Care"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjdrc-2020-001550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T20:14:40Z","timestamp":1753992880000},"score":1,"resource":{"primary":{"URL":"https:\/\/drc.bmj.com\/lookup\/doi\/10.1136\/bmjdrc-2020-001550"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2020,7,22]]},"published-print":{"date-parts":[[2020,7]]}},"alternative-id":["10.1136\/bmjdrc-2020-001550"],"URL":"https:\/\/doi.org\/10.1136\/bmjdrc-2020-001550","relation":{},"ISSN":["2052-4897"],"issn-type":[{"value":"2052-4897","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7]]}}}