Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML
Abstract Accurate and continuous blood glucose monitoring is essential for effective diabetes management, yet traditional finger pricking methods are often inconvenient and painful. To address this issue, photoplethysmography (PPG) presents a promising non-invasive alternative for estimating blood g...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84265-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559590094766080 |
|---|---|
| author | Mahdi Zeynali Khalil Alipour Bahram Tarvirdizadeh Mohammad Ghamari |
| author_facet | Mahdi Zeynali Khalil Alipour Bahram Tarvirdizadeh Mohammad Ghamari |
| author_sort | Mahdi Zeynali |
| collection | DOAJ |
| description | Abstract Accurate and continuous blood glucose monitoring is essential for effective diabetes management, yet traditional finger pricking methods are often inconvenient and painful. To address this issue, photoplethysmography (PPG) presents a promising non-invasive alternative for estimating blood glucose levels. In this study, we propose an innovative 1-second signal segmentation method and evaluate the performance of three advanced deep learning models using a novel dataset to estimate blood glucose levels from PPG signals. We also extend our testing to additional datasets to assess the robustness of our models against unseen distributions, thereby providing a comprehensive evaluation of the models’ generalizability and specificity and accuracy. Initially, we analyzed 10-second PPG segments; however, our newly developed 1-second signal segmentation technique proved to significantly enhance accuracy and computational efficiency. The selected model, after being optimized and deployed on an embedded device, achieved immediate blood glucose estimation with a processing time of just 6.4 seconds, demonstrating the method’s practical applicability. The method demonstrated strong generalizability across different populations. Training data was collected during surgery and anesthesia, and the method also performed successfully in normal states using a separate test dataset. The results showed an average root mean squared error (RMSE) of 19.7 mg/dL, with 76.6% accuracy within the A zone and 23.4% accuracy within the B zone of the Clarke Error Grid Analysis (CEGA), indicating a 100% clinical acceptance. These findings demonstrate that blood glucose estimation using 1-second PPG signal segments not only outperforms the traditional 10-second segments, but also provides a more convenient and accurate alternative to conventional monitoring methods. The study’s results highlight the potential of this approach for non-invasive, accurate, and convenient diabetes management, ultimately offering improved health management. |
| format | Article |
| id | doaj-art-3453ebd59a92462a8256654400d61a94 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-3453ebd59a92462a8256654400d61a942025-01-05T12:20:58ZengNature PortfolioScientific Reports2045-23222025-01-0115112310.1038/s41598-024-84265-8Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyMLMahdi Zeynali0Khalil Alipour1Bahram Tarvirdizadeh2Mohammad Ghamari3Advanced Service Robots (ASR) Laboratory, Department of Mechatronics Engineering, School of Intelligent Systems Engineering, College of Interdisciplinary Science and Technology, University of TehranAdvanced Service Robots (ASR) Laboratory, Department of Mechatronics Engineering, School of Intelligent Systems Engineering, College of Interdisciplinary Science and Technology, University of TehranAdvanced Service Robots (ASR) Laboratory, Department of Mechatronics Engineering, School of Intelligent Systems Engineering, College of Interdisciplinary Science and Technology, University of TehranDepartment of Electrical Engineering, California Polytechnic State UniversityAbstract Accurate and continuous blood glucose monitoring is essential for effective diabetes management, yet traditional finger pricking methods are often inconvenient and painful. To address this issue, photoplethysmography (PPG) presents a promising non-invasive alternative for estimating blood glucose levels. In this study, we propose an innovative 1-second signal segmentation method and evaluate the performance of three advanced deep learning models using a novel dataset to estimate blood glucose levels from PPG signals. We also extend our testing to additional datasets to assess the robustness of our models against unseen distributions, thereby providing a comprehensive evaluation of the models’ generalizability and specificity and accuracy. Initially, we analyzed 10-second PPG segments; however, our newly developed 1-second signal segmentation technique proved to significantly enhance accuracy and computational efficiency. The selected model, after being optimized and deployed on an embedded device, achieved immediate blood glucose estimation with a processing time of just 6.4 seconds, demonstrating the method’s practical applicability. The method demonstrated strong generalizability across different populations. Training data was collected during surgery and anesthesia, and the method also performed successfully in normal states using a separate test dataset. The results showed an average root mean squared error (RMSE) of 19.7 mg/dL, with 76.6% accuracy within the A zone and 23.4% accuracy within the B zone of the Clarke Error Grid Analysis (CEGA), indicating a 100% clinical acceptance. These findings demonstrate that blood glucose estimation using 1-second PPG signal segments not only outperforms the traditional 10-second segments, but also provides a more convenient and accurate alternative to conventional monitoring methods. The study’s results highlight the potential of this approach for non-invasive, accurate, and convenient diabetes management, ultimately offering improved health management.https://doi.org/10.1038/s41598-024-84265-8photoplethysmographyblood glucose level estimationdeep learningResNetTinyML |
| spellingShingle | Mahdi Zeynali Khalil Alipour Bahram Tarvirdizadeh Mohammad Ghamari Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML Scientific Reports photoplethysmography blood glucose level estimation deep learning ResNet TinyML |
| title | Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML |
| title_full | Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML |
| title_fullStr | Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML |
| title_full_unstemmed | Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML |
| title_short | Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML |
| title_sort | non invasive blood glucose monitoring using ppg signals with various deep learning models and implementation using tinyml |
| topic | photoplethysmography blood glucose level estimation deep learning ResNet TinyML |
| url | https://doi.org/10.1038/s41598-024-84265-8 |
| work_keys_str_mv | AT mahdizeynali noninvasivebloodglucosemonitoringusingppgsignalswithvariousdeeplearningmodelsandimplementationusingtinyml AT khalilalipour noninvasivebloodglucosemonitoringusingppgsignalswithvariousdeeplearningmodelsandimplementationusingtinyml AT bahramtarvirdizadeh noninvasivebloodglucosemonitoringusingppgsignalswithvariousdeeplearningmodelsandimplementationusingtinyml AT mohammadghamari noninvasivebloodglucosemonitoringusingppgsignalswithvariousdeeplearningmodelsandimplementationusingtinyml |