Predictive Modeling of Diabetes Status Based on Vitamin D Levels and Clinical Parameters: A Machine Learning Investigation

Yıl 2025, Cilt: 8 Sayı: 6, 1985 - 1997, 15.11.2025

Kübra Sertbakan , Yavuz Selim Balcıoğlu , Bülent Sezen , Tayfun Garip , Çağlayan Aslanbaş

https://doi.org/10.34248/bsengineering.1649690

Öz

Vitamin D deficiency has been associated with impaired glucose metabolism, but its predictive value for diabetes status remains incompletely characterized. We applied machine learning methodologies to investigate this relationship and develop predictive models based on vitamin D levels and clinical parameters. This cross-sectional study analyzed data from 817 patients with concurrent measurements of 25-hydroxyvitamin D and HbA1c. Patients were classified as having normal glucose metabolism (HbA1c<5.7%), prediabetes (HbA1c 5.7-6.4%), or diabetes (HbA1c≥6.5%). Logistic regression models of increasing complexity were developed to predict diabetes status, and various vitamin D thresholds were evaluated to determine the optimal cutoff for diabetes prediction. Mean vitamin D levels differed significantly across glycemic categories (normal: 24.57 ng/mL, prediabetes: 25.41 ng/mL, diabetes: 21.85 ng/mL; ANOVA: F(2,814)=4.68, P<0.01). Model-specific performance analysis revealed limited discriminative ability across all models: basic vitamin D model (AUC: 0.55, 95% CI: 0.51-0.59), demographic model incorporating age and gender (AUC: 0.58, 95% CI: 0.54-0.62), and comprehensive model with additional biomarkers (AUC: 0.62, 95% CI: 0.56-0.68). In the logistic regression model, each 1 ng/mL increase in vitamin D was associated with a 4% decrease in diabetes odds (OR: 0.96, 95% CI: 0.93-0.99). The statistically optimal vitamin D threshold for diabetes prediction was 14.0 ng/mL (sensitivity: 31.9%, specificity: 89.3%), differing from the conventional clinical cutoff of 20 ng/mL. However, the weak discriminative ability indicates that vitamin D has limited standalone predictive value for diabetes status and should be considered only as part of comprehensive risk assessment frameworks. The cross-sectional design precludes causal inferences, and the modest performance suggests limited immediate clinical applicability as an isolated predictor.

Anahtar Kelimeler

Vitamin D deficiency , Diabetes mellitus , HbA1c , Machine learning , Predictive modeling

Etik Beyan

Ethical approval for this study was obtained from the Gebze Technical University Rectorate, Ethics Committee for Human Research (Approval Date: March 28, 2024; Approval Number: 2024-05/07) and from the T.C. Istanbul Medipol University Health Education, Application and Research Center – Pendik Unit Ethics Committee (Approval Date: April 15, 2024; Approval Number: 48430706-259). The study utilized anonymized clinical data with no patient identifiers. All procedures were conducted in accordance with the ethical standards of the institutional research committees and with the 1964 Helsinki Declaration and its later amendments. As this was a retrospective analysis of anonymized data, the requirement for individual patient consent was waived by the institutional review boards.

Kaynakça

• Alvarez JA, Ashraf AP. 2009. Role of vitamin D in insulin secretion and insulin sensitivity for glucose homeostasis. Int J Endocrinol, 2010: 351385.
• Angellotti E, D’Alessio DA, Dawson-Hughes B, Nelson J, Cohen RM, Gastaldelli A, Pittas AG. 2018. Vitamin D supplementation in patients with type 2 diabetes: The vitamin D for established type 2 diabetes (DDM2) study. J Endocr Soc, 2(4): 310-321.
• Argano C, Mirarchi L, Amodeo S, Orlando V, Torres A, Corrao S. 2023. The role of vitamin D and its molecular bases in insulin resistance, diabetes, metabolic syndrome, and cardiovascular disease: state of the art. Int J Mol Sci, 24(20): 15485.
• Casey CF, Slawson DC, Neal LR. 2010. Vitamin D supplementation in infants, children, and adolescents. Am Fam Physician, 81(6): 745-748.
• Hilbert K, Lueken U. 2020. Prädiktive analytik aus der perspektive der klinischen psychologie und psychotherapie. Verhaltenstherapie, 30(1): 8-17.
• Karagöl A, Atak N. 2016. D vitamini ve Tip 2 diyabet. Türk Halk Sağlığı Derg, 14(3): 167-177.
• Kartal Baykan E, Yıldırımer Y, Durmazatar İ. 2022. Tip 2 diyabetli bireylerde serum vitamin D düzeyleri ile mikroalbüminüri arasındaki ilişkinin değerlendirilmesi. Ege Tıp Derg, 61(1): 73-79.
• Orhanoğlu T. 2024. Diyabetik hastalarda trombosit dağılım genişliği (PDW), ortalama trombosit hacmi (MPV) ve vitamin D düzeyi arasındaki ilişkinin incelenmesi. İst Gelişim Üniv Sağlık Bilim Derg, 24: 1081-1090.
• Papatheodorou K, Banach M, Bekiari E, Rizzo M, Edmonds M. 2018. Complications of diabetes 2017. J Diabetes Res, 2018: 3086167.
• Saadatmand K, Khan S, Hassan Q, Hautamaki RC, Ashouri R, Lua J, Doré S. 2021. Benefits of vitamin D supplementation to attenuate TBI secondary injury? Transl Neurosci, 12(1): 533-544.
• Saeedi P, Petersohn I, Ke C, Malanda B, Karuranga S, Unwin N, Colagiuri S, Guariguata L, Motala AA, Ogurtsova K, Shaw JE, Bright D, Williams R. 2019. Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: Results from the International Diabetes Federation Diabetes Atlas, 9th edition. Diabetes Res Clin Pract, 157: 107843.
• Tekin Karacaer N, Tuncer SÇ. 2022. Tip 2 diyabetik hastalarda glisemik kontrolün D vitamini, B12 vitamini ve lipid profili üzerini etkilerinin araştırılması: Bir retrospektif çalışma. Aksaray Üniv Tıp Bilim Derg, 3(3): 10-14.
• Xu K, Li Y, Liu C, Liu X, Hao X, Gao J, Maropoulos P. 2020. Advanced data collection and analysis in data-driven manufacturing process. Chin J Mech Eng, 33(1): 43.