Key result
Random forest model predicts blood glucose changes during aerobic exercise with ~0.84 AUC.
Why the study?
This study aimed to explore the relationship between blood glucose level changes and body characteristics during exercise and to present six models for predicting blood glucose level changes during exercise.
Can machine learning models using physiological variables predict blood glucose changes during aerobic exercise in healthy adults?
Observational (n=148)
No
Can machine learning models using physiological variables predict blood glucose changes during aerobic exercise in healthy adults?
Machine learning models using easily measurable physiological variables can predict blood glucose changes during aerobic exercise in healthy adults, potentially aiding in non-invasive blood glucose management.
Answers are grounded in this paper and cite their sources.
May aid non-invasive glucose monitoring during exercise in healthy adults; leaves open validation in larger clinical cohorts.
PURPOSE: This study aimed to explore the relationship between blood glucose level changes and body characteristics during exercise and to present six models for predicting changes in blood glucose levels during exercise.METHODS: 148 healthy men and women (age: 31.9±9.7 year, fasting blood glucose: 102.1±14.1 mg/dL, p=.032) participated in the study, and 30 of them participated in the study. Eight variables were selected to build two prediction models: 24-hour ingested carbohydrates, age, blood glucose, heart rate changes, sex, skeletal muscle mass, heart rate recovery after exercise, and resting heart rate. Logistic regression and random forest classifier models were used to predict the changes in blood glucose levels during exercise.RESULTS: A total of six models were created for all participants, male and female. Random forest classification (training set: AUC=0.837, Youden index=0.66; validation set: AUC=0.730, Youden index=0.53) and logistic regression classification models (training set: AUC=0.807, Youden index=0.55; validation set: AUC=0.735, Youden index=0.57) were built.CONCLUSION: The random forest model showed good performance in classifying internal data, whereas the logistic regression classification model demonstrated relatively good performance in classifying validation data.
No takes yet. Share an insight, caveat, or question.
Oyama et al. (2023) conducted an observational in Healthy adults (n=148). Machine learning prediction models (Random Forest and Logistic Regression) was evaluated on Prediction of blood glucose change during exercise (AUC of Random Forest model) (AUC 0.837). A random forest classification model successfully predicted blood glucose changes during aerobic exercise with an AUC of 0.837 in the training set and 0.730 in the validation set.
Synapse has enriched 10 related papers. Consider them for comparative context: