This study evaluates the relationship between Hemoglobin A1c (HbA1c) and metabolic indicators – fasting blood sugar (FBS), triglycerides (TG), body mass index (BMI), total cholesterol (TC), and low-density lipoprotein (LDL) – using nonparametric regression techniques. HbA1c was modelled as the dependent variable, leveraging R Studio to capture complex non-linear interactions beyond traditional methods. A framework combining nonparametric regression and multilayer feedforward neural networks (MLFFNN) was constructed and validated. The dataset was split into training (70%) and testing (30%) sets, with performance metrics assessed via RMSE, MAE, RMSPE, and MedAE. The proposed method achieved high predictive accuracy, with RMSE and MAE of 0.0417 and MedAE of 95.83, demonstrating its robustness. This integration of statistical and machine learning methods offers a reliable tool for predicting HbA1c levels and emphasizes the potential of advanced analytics in healthcare.

non-parametric regression, glycated hemoglobin (HbA1c), triglycerides, body mass index, cholesterol, LDL

Received: January 11, 2025; Accepted: January 30, 2025; Publihsed: February 17, 2025

How to cite this article: Seng Fei Hong, Wan Muhamad Amir W Ahmad, Mohamad Nasarudin Adnan, Nor Farid Mohd Noor, Farah Muna Mohamad Ghazali and Nor Azlida Aleng, Advanced health assessment of HbA1c through nonparametric regression: investigating TG, FBS, BMI, TC, and LDL interactions, JP Journal of Biostatistics 25(1) (2025), 215-221. https://doi.org/10.17654/0973514325010

This Open Access Article is Licensed under Creative Commons Attribution 4.0 International License

References:
[1] C. Chen and J. L. Dai, Triglyceride to high-density lipoprotein cholesterol (HDL-C) ratio and arterial stiffness in Japanese population: a secondary analysis based on a cross-sectional study, Lipids Health Dis. 17 (2018), 130.
doi: 10.1186/s12944-018-0776-7.
[2] S. I. Sherwani, H. A. Khan, A. Ekhzaimy, A. Masood and M. K. Sakharkar, Significance of HbA1c test in diagnosis and prognosis of diabetic patients, Biomark Insights 11 (2016), 95-104. doi: 10.4137/BMI.S38440.
[3] A. Forbes, T. Murrells, H. Mulnier and A. J. Sinclair, Mean HbA1c, HbA1c variability, and mortality in people with diabetes aged 70 years and older: a retrospective cohort study, Lancet Diabetes Endocrinol 6 (2018), 476-486.
doi: 10.1016/S2213-8587(18)30048-2.
[4] H. Chehregosha, M. E. Khamseh, M. Malek, F. Hosseinpanah and F. Ismail-Beigi, A view beyond HbA1c: Role of continuous glucose monitoring, Diabetes Therapy 10 (2019), 853-863. doi: 10.1007/s13300-019-0619-1.
[5] N. E. Poveda, M. F. Garcés, A. E. Darghan, et al., Triglycerides/glucose and triglyceride/high-density lipoprotein cholesterol indices in normal and preeclamptic pregnancies: A longitudinal study, Int. J. Endocrinol 2018 (2018), 8956404. doi: 10.1155/2018/8956404.
[6] P. C. Liao, M. S. Chen, M. J. Jhou, T. C. Chen, C. T. Yang and C. J. Lu, Integrating health data-driven machine learning algorithms to evaluate risk factors of early stage hypertension at different levels of HDL and LDL cholesterol, Diagnostics (Basel) 12 (2022), 1965. doi: 10.3390/diagnostics12081965.
[7] Z. Chen, H. Qin, S. Qiu, G. Chen and Y. Chen, Correlation of triglyceride to high-density lipoprotein cholesterol ratio with nonalcoholic fatty liver disease among the non-obese Chinese population with normal blood lipid levels: a retrospective cohort research, Lipids Health Dis. 18 (2019), 162.
doi: 10.1186/s12944-019-1104-6.