Nutritional intake of micronutrient and macronutrient and type 2 diabetes: machine learning schemes
Abstract Background Diabetes mellitus, an endocrine system disease, is a common disease involving many patients worldwide. Many studies are performed to evaluate the correlation between micronutrients/macronutrients on diabetes but few of them have a high statistical population and a long follow-up...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | Journal of Health, Population and Nutrition |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41043-024-00712-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Background Diabetes mellitus, an endocrine system disease, is a common disease involving many patients worldwide. Many studies are performed to evaluate the correlation between micronutrients/macronutrients on diabetes but few of them have a high statistical population and a long follow-up period. We aimed to investigate the relationship between intake of macro/micronutrients and the incidence of type 2 diabetes (T2D) using logistic regression (LR) and a decision tree (DT) algorithm for machine learning. Method Our research explores supervised machine learning models to identify T2D patients using the Mashhad Cohort Study dataset. The study population comprised 9704 individuals aged 35–65 years were enrolled regarding their T2D status, and those with T2D history. 15% of individuals are diabetic and 85% of them are non-diabetic. For ten years (until 2020), the participants in the study were monitored to determine the incidence of T2D. LR is a statistical model applied in dichotomous response variable modeling. All data were analyzed by SPSS (Version 22) and SAS JMP software. Result Nutritional intake in the T2D group showed that potassium, calcium, magnesium, zinc, iodine, carotene, vitamin D, tryptophan, and vitamin B12 had an inverse correlation with the incidence of diabetes (p < 0.05). While phosphate, iron, and chloride had a positive relationship with the risk of T2D (p < 0.05). Also, the T2D group significantly had higher carbohydrate and protein intake (p-value < 0.05). Conclusion Machine learning models can identify T2D risk using questionnaires and blood samples. These have implications for electronic health records that can be explored further. |
|---|---|
| ISSN: | 2072-1315 |