Article Text

Download PDFPDF

Clinical characterization of data-driven diabetes subgroups in Mexicans using a reproducible machine learning approach
  1. Omar Yaxmehen Bello-Chavolla1,2,
  2. Jessica Paola Bahena-López3,
  3. Arsenio Vargas-Vázquez1,3,
  4. Neftali Eduardo Antonio-Villa1,3,
  5. Alejandro Márquez-Salinas3,
  6. Carlos A Fermín-Martínez3,
  7. Rosalba Rojas4,
  8. Roopa Mehta1,
  9. Ivette Cruz-Bautista1,
  10. Sergio Hernández-Jiménez5,
  11. Ana Cristina García-Ulloa5,
  12. Paloma Almeda-Valdes6,
  13. Carlos Alberto Aguilar-Salinas1,6,7,
  14. the Metabolic Syndrome Study Group
  15. Group of Study CAIPaDi
      1. 1Unidad de Investigación de Enfermedades Metabólicas, Instituto Nacional de Ciencias Médicas y Nutrición Salvador Zubiran, Tlalpan, Mexico
      2. 2Division of Research, Instituto Nacional de Geriatría, Mexico City, Mexico
      3. 3MD/PhD (PECEM) Program, Facultad de Medicina, Universidad Nacional Autónoma de México, Coyoacan, Mexico
      4. 4Instituto Nacional de Salud Publica, Cuernavaca, Mexico
      5. 5Center of Comprehensive Care for the Patient with Diabetes, Instituto Nacional de Ciencias Médicas y Nutrición Salvador Zubirán, Mexico City, Mexico
      6. 6Department of Endocrinology and Metabolism, Salvador Zubiran National Institute of Medical Sciences and Nutrition, Tlalpan, Mexico
      7. 7Escuela de Medicina y Ciencias de la Salud, Tecnologico de Monterrey, Nuevo Leon, Mexico
      1. Correspondence to Dr Carlos Alberto Aguilar-Salinas; caguilarsalinas{at}yahoo.com

      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.

      • insulin resistance
      • type 2 diabetes mellitus
      • ethnic groups
      • statistical models
      http://creativecommons.org/licenses/by-nc/4.0/

      This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/.

      Statistics from Altmetric.com

      Footnotes

      • Collaborators The Metabolic Syndrome Study Group: Olimpia Arellano-Campos, Donaji V Gómez-Velasco, Omar Yaxmehen Bello-Chavolla, César Lam-Chung, Ivette Cruz-Bautista, Marco A Melgarejo-Hernandez, Paloma Almeda-Valdés, Alexandro J Martagón, Liliana Muñoz-Hernandez, Luz E Guillén, José de Jesús Garduño-García, Ulices Alvirde, Yukiko Ono-Yoshikawa, Ricardo Choza-Romero, Leobardo Sauque-Reyna, Ma Eugenia Garay-Sevilla, Juan M Malacara-Hernandez, María Teresa Tusié-Luna, Luis Miguel Gutierrez-Robledo, Francisco J Gómez-Pérez, Rosalba Rojas, Carlos A Aguilar-Salinas. Group of Study CAIPaDi: Sergio Hernández-Jiménez, Cristina García-Ulloa, Eder Patiño-Rivera, Denise Arcila-Martínez, Rodrigo Arizmendi-Rodríguez, Oswaldo Briseño-González, Humberto Del Valle-Ramírez, Arturo Flores-García, Fernanda Garnica-Carrillo, Eduardo González-Flores, Mariana Granados-Arcos, Héctor Infanzón-Talango, Victoria Landa-Anell, Claudia Lechuga-Fonseca, Arely López-Reyes, Marco Melgarejo-Hernández, Angélica, Palacios-Vargas, Liliana Pérez-Peralta, Alberto Ramírez-García, David Rivera de la Parra, Sofía Ríos-Villavicencio, Francis Rojas-Torres, Marcela Ruiz-Cervantes, Sandra Sainos-Muñoz, Alejandra Sierra-Esquivel, Erendi Tinoco-Ventura, Luz Elena Urbina-Arronte, María Luisa Velasco-Pérez, Héctor Velázquez-Jurado, Andrea Villegas-Narváez, Verónica Zurita-Cortés, Aída Jiménez-Corona, Enrique Graue-Hernández, Carlos Aguilar-Salinas, Francisco J Gómez-Pérez, David Kershenobich-Stalnikowitz.

      • Contributors Research idea and study design: OYB-C, JPB-L, AV-V, NEA-V, RM, PA-V, CAA-S; data acquisition: PA-V, RM, AV-V, IC-B, RR, SH-J, ACG-U,CAA-S; data analysis/interpretation: OYB-C, JPB-L, CAA-S; statistical analysis and machine learning: OYB-C; manuscript drafting: OYB-C, JPB-L, AV-V, NEA-V, SH-J, ACG-U, RR, RM, PA-V, IC-B, CAA-S; supervision or mentorship: CAA-S. Each author contributed important intellectual content during manuscript drafting or revision and accepts accountability for the overall work by ensuring that questions pertaining to the accuracy or integrity of any portion of the work are appropriately investigated and resolved.

      • Funding The SIGMA-UIEM cohorts were conducted as part of the Slim Initiative for Genomic Medicine, a project funded by the Carlos Slim Health Institute in Mexico and the Consejo Nacional de Ciencia y Tecnologia. Grant Infraestructura 255 096. The Metabolic Syndrome cohort was supported by a grant from the “Consejo Nacional de Ciencia y Tecnología (CONACyT)” (S0008-2009-1-115250) and research grant by Sanofi. The CAIPaDi program has received grants from Astra Zeneca, Fundación Conde de Valenciana, Novartis, Consejo Nacional de Ciencia y Tecnología (214718), Nutrición Médica y Tecnología, NovoNordisk, Boehringer Ingelheim, Dirección General de Calidad y Educación en Salud, Eli Lilly, Merck Serono, MSD, Silanes, Chinoin and Carlos Slim Health Institute.

      • Disclaimer The funding bodies had no roles in the design of the study and collection, analysis, interpretation of data and in writing the manuscript. The sponsors had no role in the conception, development, analyzing, writing or editing of this document.

      • Competing interests JPB-L, AV-V and NEA-V are enrolled at the PECEM program of the Faculty of Medicine at UNAM. JPB-L and AV-V are supported by CONACyT.

      • Patient consent for publication Not required.

      • Provenance and peer review Not commissioned; externally peer reviewed.

      • Data availability statement Data are available upon reasonable request to the corresponding author.

      Request Permissions

      If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.