A machine learning approach for type 2 diabetes diagnosis and prognosis using tailored heterogeneous feature subsets

Type 2 diabetes (T2D) is becoming one of the leading health problems in Western societies, diminishing quality of life and consuming a significant share of healthcare resources. This study presents machine learning models for T2D diagnosis and prognosis, developed using heterogeneous data from a Spanish population dataset ([email protected] study). The models were trained exclusively on individuals classified as controls and undiagnosed diabetics, ensuring that the results are not influenced by treatment effects or behavioral changes due to disease awareness. Two data domains are considered: environmental (patient lifestyle questionnaires and measurements) and clinical (biochemical and anthropometric measurements). The preprocessing pipeline consists of four key steps: geospatial data extraction, feature engineering, missing data imputation, and quasi-constancy filtering. Two working scenarios (Environmental and Healthcare) are defined based on the features used, and applied to two targets (diagnosis and prognosis), resulting in four distinct models. The feature subsets that best predict the target have been identified based on permutation importance and sequential backward selection, reducing the number of features and, consequently, the cost of predictions. In the Environmental scenario, models achieved an AUROC of 0.86 for diagnosis and 0.82 for prognosis. The Healthcare scenario performed better, with an AUROC of 0.96 for diagnosis and 0.88 for prognosis. A partial dependence analysis of the most relevant features is also presented. An online demo page showcasing the Environmental and Healthcare T2D prognosis models is available upon request.

Authors

Institutions

Publication Details

Journal
Medical & Biological Engineering & Computing
Published
2025-04-08
DOI
https://doi.org/10.1007/s11517-025-03355-5
Citations
1
Primary Topic
Artificial Intelligence in Healthcare
Type
article
Field-Weighted Citation Impact
2.94

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A machine learning approach for type 2 diabetes diagnosis and prognosis using tailored heterogeneous feature subsets

Alfonso L. Calle‐Pascual, Juan-Carlos Pérez-Cortés, Josep Franch‐Nadal, Francisco Lara-Hernández et al.
1 citations
Medical & Biological Engineering & Computing
Artificial Intelligence in Healthcare
2.94
article

A machine learning approach for type 2 diabetes diagnosis and prognosis using tailored heterogeneous feature subsets

Alfonso L. Calle‐Pascual, Juan-Carlos Pérez-Cortés, Josep Franch‐Nadal, Francisco Lara-Hernández, Eduard Montanya, Felipe Javier Chaves, Laura Arnal, Gemma Rojo‐Martínez, Rafael Llobet, Elías Delgado, Ana-Bárbara García-García, Sergio Valdés, Luís Castaño, Pedro Fandos Pons, Joaquim Arlandis, María Elena Quiroz-Rodríguez, J. Ramón Navarro-Cerdán, Celeste Moya-Valera
article en
1 citations

Abstract

Type 2 diabetes (T2D) is becoming one of the leading health problems in Western societies, diminishing quality of life and consuming a significant share of healthcare resources. This study presents machine learning models for T2D diagnosis and prognosis, developed using heterogeneous data from a Spanish population dataset ([email protected] study). The models were trained exclusively on individuals classified as controls and undiagnosed diabetics, ensuring that the results are not influenced by treatment effects or behavioral changes due to disease awareness. Two data domains are considered: environmental (patient lifestyle questionnaires and measurements) and clinical (biochemical and anthropometric measurements). The preprocessing pipeline consists of four key steps: geospatial data extraction, feature engineering, missing data imputation, and quasi-constancy filtering. Two working scenarios (Environmental and Healthcare) are defined based on the features used, and applied to two targets (diagnosis and prognosis), resulting in four distinct models. The feature subsets that best predict the target have been identified based on permutation importance and sequential backward selection, reducing the number of features and, consequently, the cost of predictions. In the Environmental scenario, models achieved an AUROC of 0.86 for diagnosis and 0.82 for prognosis. The Healthcare scenario performed better, with an AUROC of 0.96 for diagnosis and 0.88 for prognosis. A partial dependence analysis of the most relevant features is also presented. An online demo page showcasing the Environmental and Healthcare T2D prognosis models is available upon request.

Medical & Biological Engineering & ComputingVol. 63(9)
Universidad Complutense de Madrid (ES), Gobierno del Principado de Asturias (ES), Instituto de Salud Carlos III (ES), Hospital Clínico San Carlos (ES), Institut d'Investigació Biomédica de Bellvitge (ES), BioCruces Health research Institute (ES), Barcelona Graduate School of Mathematics (ES), Centro de Investigación Biomédica en Red Diabetes y Enfermedades Metabólicas Asociadas (ES), Centre for Biomedical Network Research on Rare Diseases (ES), Institut Universitari d'Investigació en Atenció Primària Jordi Gol (ES), Hospital Universitario Central de Asturias (ES), Centro Tecnológico de Investigación, Desarrollo e Innovación en tecnologías de la Información y las Comunicaciones (TIC) (ES), Hospital de Cruces (ES), INCLIVA Health Research Institute (ES), Instituto de Investigación Biomédica de Málaga (ES), Universitat Politècnica de València (ES)
Centro de Investigación Biomédica en Red Diabetes y Enfermedades Metabólicas Asociadas, Universitat Politècnica de València
Responsible consumption and production
Openalex Percentile: Top 10%
Artificial Intelligence in Healthcare
2.94
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.