Prediction of Metabolic Parameters of Diabetic Patients Depending on Body Weight Variation Using Machine Learning Techniques

<b>Background/Objectives</b>: Obesity is a major risk factor for diabetes mellitus, a metabolic disease characterized by elevated fasting blood glucose and glycosylated hemoglobin levels. Predicting the percentage and absolute variations in key medical parameters based on weight changes...

Full description

Saved in:
Bibliographic Details
Main Authors: Oana Vîrgolici, Daniela Lixandru, Andrada Mihai, Diana Simona Ștefan, Cristian Guja, Horia Vîrgolici, Bogdana Virgolici
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Biomedicines
Subjects:
Online Access:https://www.mdpi.com/2227-9059/13/5/1116
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850128076488310784
author Oana Vîrgolici
Daniela Lixandru
Andrada Mihai
Diana Simona Ștefan
Cristian Guja
Horia Vîrgolici
Bogdana Virgolici
author_facet Oana Vîrgolici
Daniela Lixandru
Andrada Mihai
Diana Simona Ștefan
Cristian Guja
Horia Vîrgolici
Bogdana Virgolici
author_sort Oana Vîrgolici
collection DOAJ
description <b>Background/Objectives</b>: Obesity is a major risk factor for diabetes mellitus, a metabolic disease characterized by elevated fasting blood glucose and glycosylated hemoglobin levels. Predicting the percentage and absolute variations in key medical parameters based on weight changes can help patients stay motivated to lose weight and assist doctors in making informed lifestyle and treatment recommendations. This study aims to assess the extent to which weight variation influences the absolute and percentage changes in various clinical parameters. <b>Methods</b>: The dataset includes medical records from patients in Bucharest hospitals, collected between 2012 and 2016. Several machine learning models, namely linear regression, polynomial regression, Gradient Boosting, and Extreme Gradient Boosting, were employed to predict changes in medical parameters as a function of body weight variation. Model performance was evaluated using Mean Squared Error, Mean Absolute Error, and R<sup>2</sup> score. <b>Results</b>: Almost all models demonstrated promising predictive performance. Quantitative predictions were made for each parameter, highlighting the relationship between weight loss and improvements in clinical indicators. <b>Conclusions</b>: Weight loss led to significant improvements in dysglycemia, dyslipidemia, inflammation, uric acid levels, liver enzymes, thyroid hormones, and blood pressure, with reductions ranging from 5% to 30%, depending on the parameter.
format Article
id doaj-art-e38ea7cd3244487a808085818a7d0610
institution OA Journals
issn 2227-9059
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Biomedicines
spelling doaj-art-e38ea7cd3244487a808085818a7d06102025-08-20T02:33:30ZengMDPI AGBiomedicines2227-90592025-05-01135111610.3390/biomedicines13051116Prediction of Metabolic Parameters of Diabetic Patients Depending on Body Weight Variation Using Machine Learning TechniquesOana Vîrgolici0Daniela Lixandru1Andrada Mihai2Diana Simona Ștefan3Cristian Guja4Horia Vîrgolici5Bogdana Virgolici6Academy of Economic Studies, 010374 Bucharest, RomaniaFaculty of Midwifery and Nursing, ”Carol Davila” University of Medicine and Pharmacy, 050474 Bucharest, RomaniaFaculty of Medicine, ”Carol Davila” University of Medicine and Pharmacy, 050474 Bucharest, RomaniaNational Institute of Diabetes, Nutrition and Metabolic Disease “N. Paulescu”, 020475 Bucharest, RomaniaFaculty of Medicine, ”Carol Davila” University of Medicine and Pharmacy, 050474 Bucharest, RomaniaFaculty of Medicine, ”Carol Davila” University of Medicine and Pharmacy, 050474 Bucharest, RomaniaFaculty of Medicine, ”Carol Davila” University of Medicine and Pharmacy, 050474 Bucharest, Romania<b>Background/Objectives</b>: Obesity is a major risk factor for diabetes mellitus, a metabolic disease characterized by elevated fasting blood glucose and glycosylated hemoglobin levels. Predicting the percentage and absolute variations in key medical parameters based on weight changes can help patients stay motivated to lose weight and assist doctors in making informed lifestyle and treatment recommendations. This study aims to assess the extent to which weight variation influences the absolute and percentage changes in various clinical parameters. <b>Methods</b>: The dataset includes medical records from patients in Bucharest hospitals, collected between 2012 and 2016. Several machine learning models, namely linear regression, polynomial regression, Gradient Boosting, and Extreme Gradient Boosting, were employed to predict changes in medical parameters as a function of body weight variation. Model performance was evaluated using Mean Squared Error, Mean Absolute Error, and R<sup>2</sup> score. <b>Results</b>: Almost all models demonstrated promising predictive performance. Quantitative predictions were made for each parameter, highlighting the relationship between weight loss and improvements in clinical indicators. <b>Conclusions</b>: Weight loss led to significant improvements in dysglycemia, dyslipidemia, inflammation, uric acid levels, liver enzymes, thyroid hormones, and blood pressure, with reductions ranging from 5% to 30%, depending on the parameter.https://www.mdpi.com/2227-9059/13/5/1116machine learningbody mass indexdiabetes mellitusdiet and nutritionmetabolic healthweight loss
spellingShingle Oana Vîrgolici
Daniela Lixandru
Andrada Mihai
Diana Simona Ștefan
Cristian Guja
Horia Vîrgolici
Bogdana Virgolici
Prediction of Metabolic Parameters of Diabetic Patients Depending on Body Weight Variation Using Machine Learning Techniques
Biomedicines
machine learning
body mass index
diabetes mellitus
diet and nutrition
metabolic health
weight loss
title Prediction of Metabolic Parameters of Diabetic Patients Depending on Body Weight Variation Using Machine Learning Techniques
title_full Prediction of Metabolic Parameters of Diabetic Patients Depending on Body Weight Variation Using Machine Learning Techniques
title_fullStr Prediction of Metabolic Parameters of Diabetic Patients Depending on Body Weight Variation Using Machine Learning Techniques
title_full_unstemmed Prediction of Metabolic Parameters of Diabetic Patients Depending on Body Weight Variation Using Machine Learning Techniques
title_short Prediction of Metabolic Parameters of Diabetic Patients Depending on Body Weight Variation Using Machine Learning Techniques
title_sort prediction of metabolic parameters of diabetic patients depending on body weight variation using machine learning techniques
topic machine learning
body mass index
diabetes mellitus
diet and nutrition
metabolic health
weight loss
url https://www.mdpi.com/2227-9059/13/5/1116
work_keys_str_mv AT oanavirgolici predictionofmetabolicparametersofdiabeticpatientsdependingonbodyweightvariationusingmachinelearningtechniques
AT danielalixandru predictionofmetabolicparametersofdiabeticpatientsdependingonbodyweightvariationusingmachinelearningtechniques
AT andradamihai predictionofmetabolicparametersofdiabeticpatientsdependingonbodyweightvariationusingmachinelearningtechniques
AT dianasimonastefan predictionofmetabolicparametersofdiabeticpatientsdependingonbodyweightvariationusingmachinelearningtechniques
AT cristianguja predictionofmetabolicparametersofdiabeticpatientsdependingonbodyweightvariationusingmachinelearningtechniques
AT horiavirgolici predictionofmetabolicparametersofdiabeticpatientsdependingonbodyweightvariationusingmachinelearningtechniques
AT bogdanavirgolici predictionofmetabolicparametersofdiabeticpatientsdependingonbodyweightvariationusingmachinelearningtechniques