Machine learning finds key factors affecting fasting blood glucose levels
Using Machine Learning to Investigate Predictors of Fasting Blood Glucose: Insights into Circadian Timing and Age Interactions
Machine Learning
Summary
Problems with blood sugar can lead to diabetes and other health issues. The authors used machine learning to predict fasting blood sugar based on a wide range of health and lifestyle factors, including age and circadian rhythms, which relate to the body's internal clock. They found that common medical measures like glycohemoglobin and insulin are strong predictors, but age combined with sleep timing also plays a smaller, consistent role. This suggests that how our body clock changes with age might affect blood sugar control.
What this means in practice
- •For clinical data analysts: Improve prediction models for patient blood sugar to enhance diabetes risk assessment by integrating metabolic and circadian variables.
- •For health app developers: Incorporate age and sleep timing interactions into health tracking apps to provide personalized blood sugar guidance.
Tested on one dataset.
Authors
Viktoriya Bu-Dager, Silvia Cirstea
Abstract
Impaired glucose regulation is a major contributor to metabolic dysfunction and type 2 diabetes. This study developed an interpretable machine-learning framework to predict log-transformed fasting blood glucose using metabolic, hormonal, lifestyle, demographic, nutritional, and circadian variables from the National Health and Nutrition Examination Survey 2017--2020 pre-pandemic dataset. After merging multiple NHANES sub-datasets, data processing used a leakage-resistant pipeline in which imputation, scaling, and one-hot encoding were performed only after dataset splitting and within training folds. Elastic Net, LASSO, and XGBoost models were evaluated using 94 candidate predictors and engineered circadian interaction terms. Performance was assessed using mean absolute error, root mean squared error, coefficient of determination, calibration, and Shapley Additive Explanations. The final interaction-augmented XGBoost model achieved strong performance on the independent test set, with a mean absolute error of 0.0804, a root mean squared error of 0.1148, and a coefficient of determination of 0.7761, using 10 predictors. Glycohemoglobin was the dominant predictor, followed by insulin, diabetes diagnosis, gamma-glutamyl transferase, age, race, and gender. Among the engineered interaction terms, sleep midpoint multiplied by age was consistently retained in repeated random-split analyses, although its contribution remained modest relative to dominant glycaemic predictors. These findings support further investigation of circadian-age interactions in metabolic health.