Clinical characterization of data-driven diabetes subgroups in Mexicans using a reproducible machine learning approach. Issue 1 (22nd July 2020)

• Record Type: Journal Article
• Authors: Bello-Chavolla, Omar Yaxmehen; Bahena-López, Jessica Paola; Vargas-Vázquez, Arsenio; Antonio-Villa, Neftali Eduardo; Márquez-Salinas, Alejandro; Fermín-Martínez, Carlos A; Rojas, Rosalba; Mehta, Roopa; Cruz-Bautista, Ivette; Hernández-Jiménez, Sergio; García-Ulloa, Ana Cristina; Almeda-Valdes, Paloma; Aguilar-Salinas, Carlos Alberto
• Other Names: author non-byline.; Arellano-Campos Olimpia author non-byline.; Gómez-Velasco Donaji V author non-byline.; Bello-Chavolla Omar Yaxmehen author non-byline.; Lam-Chung César author non-byline.; Cruz-Bautista Ivette author non-byline.; Melgarejo-Hernandez Marco A author non-byline.; Almeda-Valdés Paloma author non-byline.; Martagón Alexandro J author non-byline.; Muñoz-Hernandez Liliana author non-byline.; Guillén Luz E author non-byline.; Garduño-García José de Jesús author non-byline.; Alvirde Ulices author non-byline.; Ono-Yoshikawa Yukiko author non-byline.; Choza-Romero Ricardo author non-byline.; Sauque-Reyna Leobardo author non-byline.; Garay-Sevilla Ma Eugenia author non-byline.; Malacara-Hernandez Juan M author non-byline.; Tusié-Luna María Teresa author non-byline.; Gutierrez-Robledo Luis Miguel author non-byline.; Gómez-Pérez Francisco J author non-byline.; Rojas Rosalba author non-byline.; Aguilar-Salinas Carlos A author non-byline.; author non-byline.; Hernández-Jiménez Sergio author non-byline.; García-Ulloa Cristina author non-byline.; Patiño-Rivera Eder author non-byline.; Arcila-Martínez Denise author non-byline.; Arizmendi-Rodríguez Rodrigo author non-byline.; Briseño-González Oswaldo author non-byline.; Valle-Ramírez Humberto Del author non-byline.; Flores-García Arturo author non-byline.; Garnica-Carrillo Fernanda author non-byline.; González-Flores Eduardo author non-byline.; Granados-Arcos Mariana author non-byline.; Infanzón-Talango Héctor author non-byline.; Landa-Anell Victoria author non-byline.; Lechuga-Fonseca Claudia author non-byline.; López-Reyes Arely author non-byline.; Melgarejo-Hernández Marco author non-byline.; Angélica Palacios-Vargas author non-byline.; Pérez-Peralta Liliana author non-byline.; Ramírez-García Alberto author non-byline.; Parra David Rivera de la author non-byline.; Ríos-Villavicencio Sofía author non-byline.; Rojas-Torres Francis author non-byline.; Ruiz-Cervantes Marcela author non-byline.; Sainos-Muñoz Sandra author non-byline.; Sierra-Esquivel Alejandra author non-byline.; Tinoco-Ventura Erendi author non-byline.; Urbina-Arronte Luz Elena author non-byline.; Velasco-Pérez María Luisa author non-byline.; Velázquez-Jurado Héctor author non-byline.; Villegas-Narváez Andrea author non-byline.; Zurita-Cortés Verónica author non-byline.; Aída Jiménez-Corona Enrique Graue-Hernández author non-byline.; Aguilar-Salinas Carlos A. author non-byline.; Gómez-Pérez Francisco J author non-byline.; Kershenobich-Stalnikowitz David author non-byline.;
• Is Part Of: BMJ open diabetes research and care. Volume 8:Issue 1(2020)
• Publication Date: 2020-07-22
• Subjects: insulin resistance -- type 2 diabetes mellitus -- ethnic groups -- statistical models; Diabetes -- Periodicals; 616.462005
• DOI: 10.1136/bmjdrc-2020-001550
• Languages: English
• ISSNs: 2052-4897

Abstract

Abstract : Introduction: 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. Research design and methods: 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 1999–2006, n=626). SNNN models were then applied to four Mexican cohorts (SIGMA-UIEM, n=1521; Metabolic Syndrome cohort, n=6144; ENSANUT 2016, n=614 and 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. Results: 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% CI 41.02% to 41.48%), followed by obesity-related (33.60%, 95% CI 33.40% to 33.79%), age-related (14.72%, 95% CI 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% CI 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% CI 1.01 to 2.51) and 2-year risk (HR 1.94, 95% CI 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% CI 0.27 to 0.89). Conclusions: 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.