Key result
Wrist PPG machine learning incorporating AC-to-DC ratios improves HbA1c estimation without needing BMI or SpO2.
Why the study?
Invasive HbA1c testing carries inconvenience and infection risk, prompting interest in non-invasive wrist photoplethysmography and machine learning estimation methods.
Can machine learning algorithms using wrist PPG data accurately estimate HbA1c?
Can machine learning algorithms using wrist PPG data accurately estimate HbA1c?
Wrist-based PPG combined with machine learning algorithms, particularly using AC-to-DC ratio features, shows promise for non-invasive HbA1c monitoring.
May support non-invasive HbA1c estimation via wrist PPG; hypothesis-generating and requires prospective validation before clinical use.
Due to the inconvenience of drawing blood and the possibility of infection associated with invasive methods, research on non-invasive glycated hemoglobin (HbA1c) measurement methods is increasing. Utilizing wrist photoplethysmography (PPG) with machine learning to estimate HbA1c can be a promising method for non-invasive HbA1c monitoring in diabetic patients. This study aims to develop a HbA1c estimation system based on machine learning algorithms using PPG signals obtained from the wrist. We used a PPG based dataset of 22 subjects and algorithms such as extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), Categorical Boost (CatBoost) and random forest (RF) to estimate the HbA1c values. Note that the AC-to-DC ratios for three wavelengths were newly adopted as features in addition to the previously acquired 15 features from the PPG signal and a comparative analysis was performed between the performances of several algorithms. We showed that feature-importance-based selection can improve performance while reducing computational complexity. We also showed that AC-to-DC ratio (AC/DC) features play a dominant role in improving HbA1c estimation performance and, furthermore, a good performance can be obtained without the need for external features such as BMI and SpO2. These findings may help shape the future of wrist-based HbA1c estimation (e.g., via a wristwatch or wristband), which could increase the scope of noninvasive and effective monitoring techniques for diabetic patients.
No takes yet. Share an insight, caveat, or question.
Satter et al. (2023) studied Diabetes (n=22). Machine learning algorithms using wrist PPG data was evaluated on HbA1c estimation performance. Machine learning algorithms using wrist PPG data, particularly incorporating AC-to-DC ratio features, improved HbA1c estimation performance without needing external features like BMI and SpO2.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: