An integrated machine learning and fractional calculus approach to predicting diabetes risk in women
This study presents a novel dual approach for diabetes risk prediction in women, combining machine learning classification with fractional-order physiological modeling. We employ seven machine learning algorithms: Decision Tree, Logistic Regression, Support Vector Machine (SVM), Random Forest, Bagge...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Healthcare Analytics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772442525000218 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849471075126083584 |
|---|---|
| author | David Amilo Khadijeh Sadri Evren Hincal Muhammad Farman Kottakkaran Sooppy Nisar Mohamed Hafez |
| author_facet | David Amilo Khadijeh Sadri Evren Hincal Muhammad Farman Kottakkaran Sooppy Nisar Mohamed Hafez |
| author_sort | David Amilo |
| collection | DOAJ |
| description | This study presents a novel dual approach for diabetes risk prediction in women, combining machine learning classification with fractional-order physiological modeling. We employ seven machine learning algorithms: Decision Tree, Logistic Regression, Support Vector Machine (SVM), Random Forest, Bagged Trees, Naive Bayes, and XGBoost, to identify key risk factors, with XGBoost demonstrating higher performance. Glucose levels, BMI, blood pressure, and Diabetes Pedigree Function emerged as the most significant predictors across all models. Complementing these data-driven insights, we develop a Caputo fractional-order model that captures the temporal dynamics of glucose-insulin regulation, BMI, and blood pressure. Through fixed-point theorem analysis, we prove the existence and uniqueness of solutions, while numerical implementations using Lagrange polynomial interpolation reveal how varying fractional orders affect metabolic response patterns. This mathematical framework provides unique insights into the progression of diabetes, particularly through its ability to model memory effects and long-term physiological changes. The practical implementation of our research features an intuitive graphical user interface (GUI) that integrates both approaches, enabling real-time risk assessment with dynamic feedback. Our analysis of the Pima Indians dataset confirms important physiological relationships, including age-pregnancy and BMI-skin thickness correlations. This dual-method framework offers clinicians a comprehensive tool for diabetes management, combining the immediate predictive power of machine learning with the longitudinal perspective of fractional-order modeling. The machine learning component provides accurate short-term risk stratification, while the fractional-order model enhances understanding of long-term disease progression. Together, they enable more personalized and proactive care strategies, advancing both the theory and practice of diabetes risk assessment. |
| format | Article |
| id | doaj-art-b705271a1e3045aab6f62feb1333a9b3 |
| institution | Kabale University |
| issn | 2772-4425 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Healthcare Analytics |
| spelling | doaj-art-b705271a1e3045aab6f62feb1333a9b32025-08-20T03:24:56ZengElsevierHealthcare Analytics2772-44252025-12-01810040210.1016/j.health.2025.100402An integrated machine learning and fractional calculus approach to predicting diabetes risk in womenDavid Amilo0Khadijeh Sadri1Evren Hincal2Muhammad Farman3Kottakkaran Sooppy Nisar4Mohamed Hafez5Department of Mathematics, Near East University, TRNC, Mersin 10, Nicosia 99138, Turkey; Mathematics Research Center, Near East University, TRNC, Mersin 10, Nicosia 99138, TurkeyDepartment of Mathematics, Near East University, TRNC, Mersin 10, Nicosia 99138, Turkey; Mathematics Research Center, Near East University, TRNC, Mersin 10, Nicosia 99138, TurkeyDepartment of Mathematics, Near East University, TRNC, Mersin 10, Nicosia 99138, Turkey; Mathematics Research Center, Near East University, TRNC, Mersin 10, Nicosia 99138, Turkey; Research Center of Applied Mathematics, Khazar University, Baku, AzerbaijanDepartment of Mathematics, Near East University, TRNC, Mersin 10, Nicosia 99138, Turkey; Research Center of Applied Mathematics, Khazar University, Baku, Azerbaijan; Corresponding author at: Department of Mathematics, Near East University, TRNC, Mersin 10, Nicosia 99138, Turkey.Department of Mathematics, College of Science and Humanities in Alkharj, Prince Sattam Bin Abdulaziz University, Alkharj 11942, Saudi Arabia; Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, 19111, Amman, JordanFaculty of Engineering and Quantity Surviving, INTI International University Colleges, Nilai, Malaysia; Faculty of Mangement, Shinawatra, Pathum Thani, ThailandThis study presents a novel dual approach for diabetes risk prediction in women, combining machine learning classification with fractional-order physiological modeling. We employ seven machine learning algorithms: Decision Tree, Logistic Regression, Support Vector Machine (SVM), Random Forest, Bagged Trees, Naive Bayes, and XGBoost, to identify key risk factors, with XGBoost demonstrating higher performance. Glucose levels, BMI, blood pressure, and Diabetes Pedigree Function emerged as the most significant predictors across all models. Complementing these data-driven insights, we develop a Caputo fractional-order model that captures the temporal dynamics of glucose-insulin regulation, BMI, and blood pressure. Through fixed-point theorem analysis, we prove the existence and uniqueness of solutions, while numerical implementations using Lagrange polynomial interpolation reveal how varying fractional orders affect metabolic response patterns. This mathematical framework provides unique insights into the progression of diabetes, particularly through its ability to model memory effects and long-term physiological changes. The practical implementation of our research features an intuitive graphical user interface (GUI) that integrates both approaches, enabling real-time risk assessment with dynamic feedback. Our analysis of the Pima Indians dataset confirms important physiological relationships, including age-pregnancy and BMI-skin thickness correlations. This dual-method framework offers clinicians a comprehensive tool for diabetes management, combining the immediate predictive power of machine learning with the longitudinal perspective of fractional-order modeling. The machine learning component provides accurate short-term risk stratification, while the fractional-order model enhances understanding of long-term disease progression. Together, they enable more personalized and proactive care strategies, advancing both the theory and practice of diabetes risk assessment.http://www.sciencedirect.com/science/article/pii/S2772442525000218Machine learningFractional modelingDiabetes predictionPhysiological dynamicsRisk assessmentWomen health |
| spellingShingle | David Amilo Khadijeh Sadri Evren Hincal Muhammad Farman Kottakkaran Sooppy Nisar Mohamed Hafez An integrated machine learning and fractional calculus approach to predicting diabetes risk in women Healthcare Analytics Machine learning Fractional modeling Diabetes prediction Physiological dynamics Risk assessment Women health |
| title | An integrated machine learning and fractional calculus approach to predicting diabetes risk in women |
| title_full | An integrated machine learning and fractional calculus approach to predicting diabetes risk in women |
| title_fullStr | An integrated machine learning and fractional calculus approach to predicting diabetes risk in women |
| title_full_unstemmed | An integrated machine learning and fractional calculus approach to predicting diabetes risk in women |
| title_short | An integrated machine learning and fractional calculus approach to predicting diabetes risk in women |
| title_sort | integrated machine learning and fractional calculus approach to predicting diabetes risk in women |
| topic | Machine learning Fractional modeling Diabetes prediction Physiological dynamics Risk assessment Women health |
| url | http://www.sciencedirect.com/science/article/pii/S2772442525000218 |
| work_keys_str_mv | AT davidamilo anintegratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen AT khadijehsadri anintegratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen AT evrenhincal anintegratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen AT muhammadfarman anintegratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen AT kottakkaransooppynisar anintegratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen AT mohamedhafez anintegratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen AT davidamilo integratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen AT khadijehsadri integratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen AT evrenhincal integratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen AT muhammadfarman integratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen AT kottakkaransooppynisar integratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen AT mohamedhafez integratedmachinelearningandfractionalcalculusapproachtopredictingdiabetesriskinwomen |