Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes Management
Developing reliable noninvasive diagnostic and monitoring systems for diabetes remains a significant challenge, especially in the e-healthcare domain, due to computational inefficiencies and limited predictive accuracy in current approaches. The current study integrates machine learning with a molec...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Biosensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-6374/15/3/152 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850089713731371008 |
|---|---|
| author | Pardis Sadeghi Shahriar Noroozizadeh Rania Alshawabkeh Nian Xiang Sun |
| author_facet | Pardis Sadeghi Shahriar Noroozizadeh Rania Alshawabkeh Nian Xiang Sun |
| author_sort | Pardis Sadeghi |
| collection | DOAJ |
| description | Developing reliable noninvasive diagnostic and monitoring systems for diabetes remains a significant challenge, especially in the e-healthcare domain, due to computational inefficiencies and limited predictive accuracy in current approaches. The current study integrates machine learning with a molecularly imprinted polymer biosensor for detecting D-glucose in the exhaled breath condensate or aerosol. Advanced models, such as Convolutional Neural Networks and Recurrent Neural Networks, were used to analyze resistance signals, while classical algorithms served as benchmarks. To address challenges like data imbalance, limited samples, and inter-sensor variability, synthetic data generation methods like Synthetic Minority Oversampling Technique and Generative Adversarial Networks were employed. This framework aims to classify clinically relevant glucose levels accurately, enabling non-invasive diabetes monitoring. |
| format | Article |
| id | doaj-art-6096ec7f4ceb41a38fcbc34e037b98aa |
| institution | DOAJ |
| issn | 2079-6374 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biosensors |
| spelling | doaj-art-6096ec7f4ceb41a38fcbc34e037b98aa2025-08-20T02:42:42ZengMDPI AGBiosensors2079-63742025-03-0115315210.3390/bios15030152Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes ManagementPardis Sadeghi0Shahriar Noroozizadeh1Rania Alshawabkeh2Nian Xiang Sun3Electrical & Computer Engineering, W.M. Keck Laboratory for Integrated Ferroics, Northeastern University, Boston, MA 02115, USAMachine Learning Department, Carnegie Mellon University, Pittsburgh, PA 15213, USAElectrical & Computer Engineering, W.M. Keck Laboratory for Integrated Ferroics, Northeastern University, Boston, MA 02115, USAElectrical & Computer Engineering, W.M. Keck Laboratory for Integrated Ferroics, Northeastern University, Boston, MA 02115, USADeveloping reliable noninvasive diagnostic and monitoring systems for diabetes remains a significant challenge, especially in the e-healthcare domain, due to computational inefficiencies and limited predictive accuracy in current approaches. The current study integrates machine learning with a molecularly imprinted polymer biosensor for detecting D-glucose in the exhaled breath condensate or aerosol. Advanced models, such as Convolutional Neural Networks and Recurrent Neural Networks, were used to analyze resistance signals, while classical algorithms served as benchmarks. To address challenges like data imbalance, limited samples, and inter-sensor variability, synthetic data generation methods like Synthetic Minority Oversampling Technique and Generative Adversarial Networks were employed. This framework aims to classify clinically relevant glucose levels accurately, enabling non-invasive diabetes monitoring.https://www.mdpi.com/2079-6374/15/3/152diabetesD-glucoseCNNsRNNsGANsSMOTE |
| spellingShingle | Pardis Sadeghi Shahriar Noroozizadeh Rania Alshawabkeh Nian Xiang Sun Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes Management Biosensors diabetes D-glucose CNNs RNNs GANs SMOTE |
| title | Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes Management |
| title_full | Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes Management |
| title_fullStr | Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes Management |
| title_full_unstemmed | Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes Management |
| title_short | Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes Management |
| title_sort | machine learning driven d glucose prediction using a novel biosensor for non invasive diabetes management |
| topic | diabetes D-glucose CNNs RNNs GANs SMOTE |
| url | https://www.mdpi.com/2079-6374/15/3/152 |
| work_keys_str_mv | AT pardissadeghi machinelearningdrivendglucosepredictionusinganovelbiosensorfornoninvasivediabetesmanagement AT shahriarnoroozizadeh machinelearningdrivendglucosepredictionusinganovelbiosensorfornoninvasivediabetesmanagement AT raniaalshawabkeh machinelearningdrivendglucosepredictionusinganovelbiosensorfornoninvasivediabetesmanagement AT nianxiangsun machinelearningdrivendglucosepredictionusinganovelbiosensorfornoninvasivediabetesmanagement |