Deep Learning Model Approach to Predict Diabetes Type 2 Based on Clinical, Biochemical, and Gut Microbiota Profiles
Source abstract
Abstract
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%.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Diet and metabolism studies · Gut microbiota and health · Metabolomics and Mass Spectrometry Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Maimónides Biomedical Research Institute of Córdoba (IMIBIC), 14004 Córdoba, Spain
Department of Biochemistry and Molecular Biology, Universidad of Córdoba, 14004 Córdoba, Spain
Clinical Analyses Service, Reina Sofía University Hospital, 14004 Córdoba, Spain
Lipids and Atherosclerosis Unit, Department of Internal Medicine, Reina Sofía University Hospital, 14004 Córdoba, Spain
Department of Medical and Surgical Sciences, University of Córdoba, 14004 Córdoba, Spain
CIBER Fisiopatología de la Obesidad y Nutrición (CIBEROBN), Instituto de Salud Carlos III, 28029 Madrid, Spain
Funding
Fundación Patrimonio Comunal Olivarero · CEAS (Centro de Excelencia en Investigación sobre Aceite de Oliva) · Junta de Andalucía (Consejería de Salud, Consejería de Agricultura y Pesca, Consejería de innovación, Ciencia y Empresa) · Diputaciones de Jaén y Córdoba · Ministerio de Medio Ambiente, Medio Rural y Marino · Spanish Government · Ministerio de Ciencia e Innovación, Spain · MCIN/AEI/10.13039/501100011033 · Instituto de Salud Carlos III · Consejería de Salud y Familias, Junta de Andalucía · Junta de Andalucía
References (35)
Show source-provided references
1. (2024). American Diabetes Association Professional Practice Committee. 2. Diagnosis and Classification of Diabetes: Standards of Care in Diabetes—2024. Diabetes Care, 47, S20–S42.10.2337/dc24-S002 ↗
2. Epidemiology of Diabetes and Diabetes-Related Complications10.2522/ptj.20080020 ↗
3. Cardiovascular risk in diabetes mellitus: Epidemiology, assessment and prevention10.1038/s41569-023-00877-z ↗
4. Gut microbiome and type 2 diabetes: Where we are and where to go?10.1016/j.jnutbio.2018.10.003 ↗
5. Twenty years of participation of racialised groups in type 2 diabetes randomised clinical trials: A meta-epidemiological review10.1007/s00125-023-06052-w ↗
6. American Diabetes Association Professional Practice Committee (2024). 4. Comprehensive Medical Evaluation and Assessment of Comorbidities: Standards of Care in Diabetes—2024. Diabetes Care, 47, S52–S76.
7. American Diabetes Association Professional Practice Committee (2024). 5. Facilitating Positive Health Behaviors and Well-being to Improve Health Outcomes: Standards of Care in Diabetes—2024. Diabetes Care, 47, S77–S110.10.2337/dc24-S005 ↗
8. Interrelationships Among Gut Microbiota and Host: Paradigms, Role in Neurodegenerative Diseases and Future Prospects
9. Diet–microbiota interactions and personalized nutrition10.1038/s41579-019-0256-8 ↗
10. Gut microbiome and type 2 diabetes10.1016/bs.pmbts.2022.06.029 ↗
11. Role of the gut microbiota in type 2 diabetes and related diseases10.1016/j.metabol.2021.154712 ↗
12. Gurung, M., Li, Z., You, H., Rodrigues, R., Jump, D.B., Morgun, A., and Shulzhenko, N. (2020). Role of gut microbiota in type 2 diabetes pathophysiology. EBioMedicine, 51.10.1016/j.ebiom.2019.11.051 ↗
13. Iatcu, C.O., Steen, A., and Covasa, M. (2021). Gut Microbiota and Complications of Type-2 Diabetes. Nutrients, 14.10.3390/nu14010166 ↗
14. Scheithauer, T.P.M., Rampanelli, E., Nieuwdorp, M., Vallance, B.A., Verchere, C.B., van Raalte, D.H., and Herrema, H. (2020). Gut Microbiota as a Trigger for Metabolic Inflammation in Obesity and Type 2 Diabetes. Front. Immunol., 11.10.3389/fimmu.2020.571731 ↗
15. Role of branched-chain amino acid metabolism in the pathogenesis of obesity and type 2 diabetes-related metabolic disturbances BCAA metabolism in type 2 diabetes10.1038/s41387-022-00213-3 ↗
16. Microbiota-gut-brain axis: Relationships among the vagus nerve, gut microbiota, obesity, and diabetes10.1007/s00592-023-02088-x ↗
17. Interpretable prediction model for assessing diabetes complication risks in Chinese sufferers10.1016/j.diabres.2024.111560 ↗
18. A novel prediction model of the risk of pancreatic cancer among diabetes patients using multiple clinical data and machine learning10.1002/cam4.6547 ↗
19. González-Martín, J.M., Torres-Mata, L.B., Cazorla-Rivero, S., Fernández-Santana, C., Gómez-Bentolila, E., Clavo, B., and Rodríguez-Esparragón, F. (2023). An Artificial Intelligence Prediction Model of Insulin Sensitivity, Insulin Resistance, and Diabetes Using Genes Obtained through Differential Expression. Genes, 14.10.3390/genes14122119 ↗
20. Use of a K-nearest neighbors model to predict the development of type 2 diabetes within 2 years in an obese, hypertensive population10.1007/s11517-020-02132-w ↗
21. Edeh, M.O., Khalaf, O.I., Tavera, C.A., Tayeb, S., Ghouali, S., Abdulsahib, G.M., Richard-Nnabu, N.E., and Louni, A. (2022). A Classification Algorithm-Based Hybrid Diabetes Prediction Model. Front. Public Health, 10.10.3389/fpubh.2022.829519 ↗
22. Design of Machine Learning Algorithms and Internal Validation of a Kidney Risk Prediction Model for Type 2 Diabetes Mellitus10.2147/IJGM.S449397 ↗
23. Diabetes risk prediction model based on community follow-up data using machine learning10.1016/j.pmedr.2023.102358 ↗
24. Diabetes prediction model for unbalanced community follow-up data set based on optimal feature selection and scorecard
25. Unlocking Potential: Personalized Lifestyle Therapy for Type 2 Diabetes Through a Predictive Algorithm-Driven Digital Therapeutic10.1177/19322968241266821 ↗
26. A machine learning-based algorithm to identify U-500R insulin candidates among adults with type 2 diabetes10.1080/03007995.2023.2293116 ↗
27. Application of machine learning tools: Potential and useful approach for the prediction of type 2 diabetes mellitus based on the gut microbiome profile10.3892/etm.2022.11234 ↗
28. Rivas-Garcia, L., Quintana-Navarro, G.M., Alcala-Díaz, J.F., Torres-Peña, J.D., Arenas-de Larriva, A.P., Rangel-Zuñiga, O.A., López-Moreno, A., Malagon, M.M., Katsiki, N., and Perez-Martinez, P. (2024). Association between Diet Quality and Risk of Type 2 Diabetes Mellitus in Patients with Coronary Heart Disease: Findings from the CORDIOPREV Study. Nutrients, 16.10.3390/nu16081249 ↗
29. Del Río-Moreno, M., Luque, R.M., Rangel-Zúñiga, O.A., Alors-Pérez, E., Alcalá-Diaz, J.F., Roncero-Ramos, I., Camargo, A., Gahete, M.D., López-Miranda, J., and Castaño, J.P. (2020). Dietary Intervention Modulates the Expression of Splicing Machinery in Cardiovascular Patients at High Risk of Type 2 Diabetes Development: From the CORDIOPREV Study. Nutrients, 12.10.3390/nu12113528 ↗
30. Chronodisruption and diet associated with increased cardiometabolic risk in coronary heart disease patients: The CORDIOPREV study10.1016/j.trsl.2021.11.001 ↗
31. Long-term secondary prevention of cardiovascular disease with a Mediterranean diet and a low-fat diet (CORDIOPREV): A randomised controlled trial10.1016/S0140-6736(22)00122-2 ↗
32. American Diabetes Association Professional Practice Committee (2025). 2. Diagnosis and Classification of Diabetes: Standards of Care in Diabetes—2025. Diabetes Care, 48, S27–S49.10.2337/dc25-S002 ↗
33. A Diet-Dependent Microbiota Profile Associated with Incident Type 2 Diabetes: From the CORDIOPREV Study10.1002/mnfr.202000730 ↗
34. An altered microbiota pattern precedes Type 2 diabetes mellitus development: From the CORDIOPREV study
35. The gut microbial community in metabolic syndrome patients is modified by diet10.1016/j.jnutbio.2015.08.011 ↗