Deep Learning Model Approach to Predict Diabetes Type 2 Based on Clinical, Biochemical, and Gut Microbiota Profiles

Type 2 diabetes mellitus (T2DM) is a chronic metabolic disease. Gut microbiota plays a key role in metabolic homeostasis and the development of T2DM and its complications. With the advance of artificial intelligence (AI), it is possible to develop novel models based on machine learning (ML) that can...

Full description

Saved in:
Bibliographic Details
Main Authors: Pablo Caballero-María, Javier Caballero-Villarraso, Javier Arenas-Montes, Alberto Díaz-Cáceres, Sofía Castañeda-Nieto, Juan F. Alcalá-Díaz, Javier Delgado-Lista, Fernando Rodríguez-Cantalejo, Pablo Pérez-Martínez, José López-Miranda, Antonio Camargo
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/4/2228
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849719074236399616
author Pablo Caballero-María
Javier Caballero-Villarraso
Javier Arenas-Montes
Alberto Díaz-Cáceres
Sofía Castañeda-Nieto
Juan F. Alcalá-Díaz
Javier Delgado-Lista
Fernando Rodríguez-Cantalejo
Pablo Pérez-Martínez
José López-Miranda
Antonio Camargo
author_facet Pablo Caballero-María
Javier Caballero-Villarraso
Javier Arenas-Montes
Alberto Díaz-Cáceres
Sofía Castañeda-Nieto
Juan F. Alcalá-Díaz
Javier Delgado-Lista
Fernando Rodríguez-Cantalejo
Pablo Pérez-Martínez
José López-Miranda
Antonio Camargo
author_sort Pablo Caballero-María
collection DOAJ
description Type 2 diabetes mellitus (T2DM) is a chronic metabolic disease. Gut microbiota plays a key role in metabolic homeostasis and the development of T2DM and its complications. With the advance of artificial intelligence (AI), it is possible to develop novel models based on machine learning (ML) that can predict the risk of developing certain diseases and facilitate their early diagnosis, or even take preventive measures in advance. This can be the case of T2DM, for example. Our objective was to develop a predictive model of the risk of developing T2DM based on clinical, biochemical, and intestinal microbiota parameters, which estimates the time margin for developing this disease. To this end, a Deep Learning Multilayer Perceptron (MLP) algorithm was developed and trained with data from real patients from a current large population epidemiological study. The data were normalised and augmented to increase their diversity and avoid overfitting. The neural network developed was optimised, and the best hyperparameters were chosen for model building by Bayesian optimisation. We succeeded in getting the model to return a numerical result corresponding to the number of months it will take for a particular individual to develop T2DM with an accuracy of 95.2%.
format Article
id doaj-art-c126ba6cbc6244529d2b2d7254fe351c
institution DOAJ
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-c126ba6cbc6244529d2b2d7254fe351c2025-08-20T03:12:12ZengMDPI AGApplied Sciences2076-34172025-02-01154222810.3390/app15042228Deep Learning Model Approach to Predict Diabetes Type 2 Based on Clinical, Biochemical, and Gut Microbiota ProfilesPablo Caballero-María0Javier Caballero-Villarraso1Javier Arenas-Montes2Alberto Díaz-Cáceres3Sofía Castañeda-Nieto4Juan F. Alcalá-Díaz5Javier Delgado-Lista6Fernando Rodríguez-Cantalejo7Pablo Pérez-Martínez8José López-Miranda9Antonio Camargo10Maimónides Biomedical Research Institute of Córdoba (IMIBIC), 14004 Córdoba, SpainMaimónides Biomedical Research Institute of Córdoba (IMIBIC), 14004 Córdoba, SpainMaimónides Biomedical Research Institute of Córdoba (IMIBIC), 14004 Córdoba, SpainMaimónides Biomedical Research Institute of Córdoba (IMIBIC), 14004 Córdoba, SpainClinical Analyses Service, Reina Sofía University Hospital, 14004 Córdoba, SpainMaimónides Biomedical Research Institute of Córdoba (IMIBIC), 14004 Córdoba, SpainMaimónides Biomedical Research Institute of Córdoba (IMIBIC), 14004 Córdoba, SpainMaimónides Biomedical Research Institute of Córdoba (IMIBIC), 14004 Córdoba, SpainMaimónides Biomedical Research Institute of Córdoba (IMIBIC), 14004 Córdoba, SpainMaimónides Biomedical Research Institute of Córdoba (IMIBIC), 14004 Córdoba, SpainMaimónides Biomedical Research Institute of Córdoba (IMIBIC), 14004 Córdoba, SpainType 2 diabetes mellitus (T2DM) is a chronic metabolic disease. Gut microbiota plays a key role in metabolic homeostasis and the development of T2DM and its complications. With the advance of artificial intelligence (AI), it is possible to develop novel models based on machine learning (ML) that can predict the risk of developing certain diseases and facilitate their early diagnosis, or even take preventive measures in advance. This can be the case of T2DM, for example. Our objective was to develop a predictive model of the risk of developing T2DM based on clinical, biochemical, and intestinal microbiota parameters, which estimates the time margin for developing this disease. To this end, a Deep Learning Multilayer Perceptron (MLP) algorithm was developed and trained with data from real patients from a current large population epidemiological study. The data were normalised and augmented to increase their diversity and avoid overfitting. The neural network developed was optimised, and the best hyperparameters were chosen for model building by Bayesian optimisation. We succeeded in getting the model to return a numerical result corresponding to the number of months it will take for a particular individual to develop T2DM with an accuracy of 95.2%.https://www.mdpi.com/2076-3417/15/4/2228deep learningneural networkmachine learningartificial intelligencepredictive modellingdiabetes mellitus
spellingShingle Pablo Caballero-María
Javier Caballero-Villarraso
Javier Arenas-Montes
Alberto Díaz-Cáceres
Sofía Castañeda-Nieto
Juan F. Alcalá-Díaz
Javier Delgado-Lista
Fernando Rodríguez-Cantalejo
Pablo Pérez-Martínez
José López-Miranda
Antonio Camargo
Deep Learning Model Approach to Predict Diabetes Type 2 Based on Clinical, Biochemical, and Gut Microbiota Profiles
Applied Sciences
deep learning
neural network
machine learning
artificial intelligence
predictive modelling
diabetes mellitus
title Deep Learning Model Approach to Predict Diabetes Type 2 Based on Clinical, Biochemical, and Gut Microbiota Profiles
title_full Deep Learning Model Approach to Predict Diabetes Type 2 Based on Clinical, Biochemical, and Gut Microbiota Profiles
title_fullStr Deep Learning Model Approach to Predict Diabetes Type 2 Based on Clinical, Biochemical, and Gut Microbiota Profiles
title_full_unstemmed Deep Learning Model Approach to Predict Diabetes Type 2 Based on Clinical, Biochemical, and Gut Microbiota Profiles
title_short Deep Learning Model Approach to Predict Diabetes Type 2 Based on Clinical, Biochemical, and Gut Microbiota Profiles
title_sort deep learning model approach to predict diabetes type 2 based on clinical biochemical and gut microbiota profiles
topic deep learning
neural network
machine learning
artificial intelligence
predictive modelling
diabetes mellitus
url https://www.mdpi.com/2076-3417/15/4/2228
work_keys_str_mv AT pablocaballeromaria deeplearningmodelapproachtopredictdiabetestype2basedonclinicalbiochemicalandgutmicrobiotaprofiles
AT javiercaballerovillarraso deeplearningmodelapproachtopredictdiabetestype2basedonclinicalbiochemicalandgutmicrobiotaprofiles
AT javierarenasmontes deeplearningmodelapproachtopredictdiabetestype2basedonclinicalbiochemicalandgutmicrobiotaprofiles
AT albertodiazcaceres deeplearningmodelapproachtopredictdiabetestype2basedonclinicalbiochemicalandgutmicrobiotaprofiles
AT sofiacastanedanieto deeplearningmodelapproachtopredictdiabetestype2basedonclinicalbiochemicalandgutmicrobiotaprofiles
AT juanfalcaladiaz deeplearningmodelapproachtopredictdiabetestype2basedonclinicalbiochemicalandgutmicrobiotaprofiles
AT javierdelgadolista deeplearningmodelapproachtopredictdiabetestype2basedonclinicalbiochemicalandgutmicrobiotaprofiles
AT fernandorodriguezcantalejo deeplearningmodelapproachtopredictdiabetestype2basedonclinicalbiochemicalandgutmicrobiotaprofiles
AT pabloperezmartinez deeplearningmodelapproachtopredictdiabetestype2basedonclinicalbiochemicalandgutmicrobiotaprofiles
AT joselopezmiranda deeplearningmodelapproachtopredictdiabetestype2basedonclinicalbiochemicalandgutmicrobiotaprofiles
AT antoniocamargo deeplearningmodelapproachtopredictdiabetestype2basedonclinicalbiochemicalandgutmicrobiotaprofiles