Novel multi-modal obstruction module for diabetes mellitus classification using explainable machine learning

• Autorzy: Shaik Reehana , Siddique Ibrahim

Identyfikatory

DOI

10.35784/acs-2024-39

• Języki publikacji: EN

Abstrakty

EN

Diabetes Mellitus (DM) is a persistent metabolic disorder which is characterized by increased blood glucose level in the blood stream. Initially, DM occurs while the insulin secretion in the pancreas has a disability to secrete or to use hormone for the metabolic process. Moreover, there are different types of DM depending on the physiological process, and the types include Type1 DM, Type2 DM and Gestational DM. Electrocardiography (ECG) waves are used to detect the abnormal heartbeats and cannot directly detect DM, but the wave abnormality can indicate the possibility and presence of DM. Whereas the Photoplethysmography (PPG) signals are a non-invasive method used to detect changes in blood volume that can monitor BG changes. Furthermore, the detection and classification of DM using PPG and ECG can involve analyzing the functional performance of these modalities. By extracting the features like R wave (W1) and QRS complex (W2) in the ECG signals and Pulse Width (S1) and Pulse Amplitude Variation (S2) can detect DM and can be classified into DM and Non-DM. The authors propose a Novel architecture in the basis of Encoder Decoder structure named as Obstructive Encoder Decoder module. This module extracts the specific features and the proposed novel Obstructive Erasing Module remove the remaining artifacts and then the extracted features are fed into the Multi-Uni-Net for the fusion of the two modalities and the fused image is classified using EXplainable Machine Learning (EX-ML). From this classification the performance metrics like Accuracy, Precision, Recall, F1-Score and AUC can be determined.

Słowa kluczowe

EN

diabetes mellitus; explainable ML; electrocardiogram; non-invasive method; photoplethysmography; feature extraction

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2024
• Tom: Vol. 20, no. 4
• Strony: 39--62
• Opis fizyczny: Bibliogr. 27 poz., fig., tab.

Twórcy

autor

Shaik Reehana

• VIT-AP University, India

• https://orcid.org/0000-0002-2189-3616

autor

Siddique Ibrahim

• VIT-AP University, India

• https://orcid.org/0000-0003-3310-6090

Bibliografia

• [1] Ahamed, A. K. A., Lalitha, K., Saravanan, S., & Muthu Kumar, S. (2023). Enhanced Deep Learning based non-invasive anomaly detection of ECG signals with emphasis on diabetes. International Journal of Intelligent Systems and Applications in Engineering, 11(6s), 284-294.
• [2] Cordeiro, R., Karimian, N., & Park, Y. (2021). Hyperglycemia identification using ECG in Deep Learning era. Sensors, 21(18), 6263. https://doi.org/10.3390/s21186263
• [3] Dave, D., Vyas, K., Branan, K., McKay, S., DeSalvo, D. J., Gutierrez-Osuna, R., Cote, G. L., & Erraguntla, M. (2024). Detection of hypoglycemia and hyperglycemia using noninvasive wearable sensors: Electrocardiograms and accelerometry. Journal of Diabetes Science and Technology, 18(2), 351–362. https://doi.org/10.1177/19322968221116393
• [4] Gupta, S., Singh, A., Sharma, A., & Tripathy, R. K. (2022). dSVRI: A PPG-based novel feature for early diagnosis of type-II diabetes mellitus. IEEE Sensors Letters, 6(9), 1-4. https://doi.org/10.1109/LSENS.2022.3203609
• [5] Hina, A., & Saadeh, W. (2022). A 186μW photoplethysmography-based noninvasive glucose sensing SoC. IEEE Sensors Journal, 22(14), 14185-14195. https://doi.org/10.1109/JSEN.2022.3180893
• [6] Jain, A., Verma, A., & Verma, A. K. (2023). Non-invasive and automatic identification of diabetes using ECG signals. International Journal of Electrical and Electronics Research, 11(2), 418-425. https://doi.org/10.37391/ijeer.110223
• [7] Khan, M., Kumar Singh, B., & Nirala, N. (2023). Expert diagnostic system for detection of hypertension and diabetes mellitus using discrete wavelet decomposition of photoplethysmogram signal and machine learning technique. Medicine in Novel Technology and Devices, 19, 100251. https://doi.org/10.1016/j.medntd.2023.100251
• [8] Kulkarni, A. R., Patel, A. A., Pipal, K. V., Jaiswal, S. G., Jaisinghani, M. T., Thulkar, V., Gajbhiye, L., Gondane, P., Patel, A. B., Mamtani, M., & Kulkarni, H. (2023). Machine-Learning algorithm to non-invasively detect diabetes and pre-diabetes from electrocardiogram. BMJ Innovations, 9(1), 32-42. https://doi.org/10.1136/bmjinnov-2021-000759
• [9] Lee, P.-L., Wang, K.-W., & Hsiao, C.-Y. (2023). A noninvasive blood glucose estimation system using dual-channel PPGs and pulse-arrival velocity. IEEE Sensors Journal, 23(19), 23570-23582. https://doi.org/10.1109/JSEN.2023.3306343
• [10] Li, J., Ma, J., Omisore, O. M., Liu, Y., Tang, H., Ao, P., Yan, Y., Wang, L., & Nie, Z. (2024). Noninvasive blood glucose monitoring using spatiotemporal ECG and PPG feature fusion and weight-based choquet Integral multimodel approach. IEEE Transactions on Neural Networks and Learning Systems, 35(10), 14491-14505. https://doi.org/10.1109/TNNLS.2023.3279383
• [11] Li, J., Tobore, I., Liu, Y., Kandwal, A., Wang, L., & Nie, Z. (2021). Non-invasive monitoring of three glucose ranges based on ECG by using DBSCAN-CNN. IEEE Journal of Biomedical and Health Informatics, 25(9), 3340-3350. https://doi.org/10.1109/JBHI.2021.3072628
• [12] Mishra, B., & Nirala, N. (2023). Type2 diabetes classification from short photoplethysmogram signal using multiple domain features and Machine Learning techniques. Research on Biomedical Engineering, 39(3), 541-560. https://doi.org/10.1007/s42600-023-00287-7
• [13] Mishra, B., Nirala, N., & Singh, B. K. (2024). Type-2 diabetes identification from toe-photoplethysmography using Fourier decomposition method. Neural Computing and Applications, 36(5), 2429-2443. https://doi.org/10.1007/s00521-023-09208-2
• [14] Navaneethakrishna, M., & Manuskandan, S. R. (2021). Analysis of heart rate variability in normal and diabetic ECG signals using fragmentation approach. 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 1112-1115). IEEE. https://doi.org/10.1109/EMBC46164.2021.9631076
• [15] Pal, P., & Mahadevappa, M. (2023). Adaptive multidimensional dual attentive DCNN for detecting cardiac morbidities using fused ECG-PPG signals. IEEE Transactions on Artificial Intelligence, 4(5), 1225-1235. https://doi.org/10.1109/TAI.2022.3184656
• [16] Prabha, A., Yadav, J., Rani, A., & Singh, V. (2021). Design of intelligent diabetes mellitus detection system using hybrid feature selection based XGBoost classifier. Computers in Biology and Medicine, 136, 104664. https://doi.org/10.1016/j.compbiomed.2021.104664
• [17] Prabha, A., Yadav, J., Rani, A., & Singh, V. (2022). Intelligent estimation of blood glucose level using wristband PPG signal and physiological parameters. Biomedical Signal Processing and Control, 78, 103876. https://doi.org/10.1016/j.bspc.2022.103876
• [18] Sathish, D., Poojary, S. S., Shetty, S., Acharya, P. H., & Kabekody, S. (2024). Non-invasive diabetes detection system using photoplethysmogram signals. In S. Tiwari, M. C. Trivedi, M. L. Kolhe, & B. K. Singh (Eds.), Advances in Data and Information Sciences (Vol. 796, pp. 457–467). Springer Nature Singapore. https://doi.org/10.1007/978-981-99-6906-7_39
• [19] Sen Gupta, S., Kwon, T.-H., Hossain, S., & Kim, K.-D. (2021). Towards non-invasive blood glucose measurement using machine learning: An all-purpose PPG system design. Biomedical Signal Processing and Control, 68, 102706. https://doi.org/10.1016/j.bspc.2021.102706
• [20] Shaan, B., Prabha, A., & Yadav, J. (2023). Pulse decomposition analysis based non-invasive diabetes detection system. In S. M. Thampi, J. Mukhopadhyay, M. Paprzycki, & K.-C. Li (Eds.), International Symposium on Intelligent Informatics (Vol. 333, pp. 291-302). Springer Nature Singapore. https://doi.org/10.1007/978-981-19-8094-7_22
• [21] Shaan, B., Yadav, J., & Prabha, A. (2022). ML based non-invasive diabetes detection system using pulse decomposition analysis of PPG signal. 2022 8th International Conference on Signal Processing and Communication (ICSC) (pp. 417-422). IEEE. https://doi.org/10.1109/ICSC56524.2022.10009195
• [22] Shashikant, R., Chaskar, U., Phadke, L., & Patil, C. (2021). Gaussian process-based kernel as a diagnostic model for prediction of type 2 diabetes mellitus risk using non-linear heart rate variability features. Biomedical Engineering Letters, 11(3), 273-286. https://doi.org/10.1007/s13534-021-00196-7
• [23] Singha, S. K., & Ahmad, M. (2021). Noninvasive heart rate and blood glucose level estimation using photoplethysmography. 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD) (pp. 151-155). IEEE. https://doi.org/10.1109/ICICT4SD50815.2021.9396849
• [24] Srinivasan, V. B., & Foroozan, F. (2021). Deep Learning based non-invasive diabetes predictor using Photoplethysmography signals. 2021 29th European Signal Processing Conference (EUSIPCO) (pp. 1256-1260). IEEE. https://doi.org/10.23919/EUSIPCO54536.2021.9616351
• [25] Susana, E., Ramli, K., Murfi, H., & Apriantoro, N. H. (2022). Non-invasive classification of blood glucose level for early detection diabetes based on photoplethysmography signal. Information, 13(2), 59. https://doi.org/10.3390/info13020059
• [26] Susana, E., Ramli, K., Purnamasari, P. D., & Apriantoro, N. H. (2023). Non-invasive classification of blood glucose level based on photoplethysmography using time-frequency analysis. Information, 14(3), 145. https://doi.org/10.3390/info14030145
• [27] Zanelli, S., Yacoubi, M. A. E., Hallab, M., & Ammi, M. (2023). Type 2 diabetes detection with light CNN from single raw PPG wave. IEEE Access, 11, 57652-57665. https://doi.org/10.1109/ACCESS.2023.3274484

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).