International Journal of Electronics and Computer Applications

Volume: 2 Issue: 1

  • Open Access
  • Original Article

Neural Network Based Diabetes Detection Using ECG Signals

Ved Shringarpure1, Ganesh Shivshankar1, Pranav More1, P M Chavan1∗, K R Joshi1

1Department of Electronics and Computer Engineering, PES Modern College of Engineering, Pune, Maharashtra, India

* Corresponding author. Email: [email protected]

Year: 2025, Page: 12-22, Doi: https://doi.org/10.70968/ijeaca.v2i1.D1012

Received: Feb. 10, 2025 Accepted: June 25, 2025 Published: June 30, 2025

Abstract

Millions of people throughout the world suffer with diabetes mellitus, a common chronic illness. Reducing the chance of serious consequences requires prompt diagnosis and efficient treatment. This paper presents a novel approach to real-time diabetes monitoring by combining deep neural networks with electrocardiogram (ECG) signal analysis. ECG is a non-invasive technique that captures the electrical activity of the heart, which can indicate physiological alterations associated with diabetes. To accurately classify people as diabetes or non-diabetic, a deep learning model was created to effectively extract important elements from ECG data. A large dataset of ECG recordings from both groups was used to train the model. A safe and effective data transfer architecture enables real-time application, making it simple for users to view their diabetes status. The results validate the accuracy and feasibility of using deep learning with ECG for diabetes monitoring, offering a useful tool for improving diabetes management by giving patients and healthcare professionals timely information.

Keywords: Neural Network Based Diabetes Detection Using ECG Signals

References

  1. Zanelli S, Ammi M, Hallab M, Yacoubi MAE. Diabetes Detection and Management through Photoplethysmographic and Electrocardiographic Signals Analysis: A Systematic ReviewSensors. 2022;22(13):4890. Available from: https://dx.doi.org/10.3390/s22134890

  2. San PP, Ling SH, Nguyen HT. Deep learning framework for detection of hypoglycemic episodes in children with type 1 diabetes. In: 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). (pp. 3503-3506) IEEE. 2016.

  3. Chaki J, Ganesh ST, Cidham SK, Theertan SA. Machine learning and artificial intelligence based Diabetes Mellitus detection and self-management: A systematic reviewJournal of King Saud University - Computer and Information Sciences. 2022;34(6):3204–3225. Available from: https://dx.doi.org/10.1016/j.jksuci.2020.06.013

  4. Husain K, Zahid MSM, Hassan SU, Hasbullah S, Mandala S. Advances of ECG Sensors from Hardware, Software and Format Interoperability PerspectivesElectronics. 2021;10(2):105. Available from: https://dx.doi.org/10.3390/electronics10020105

  5. Kumar R, Swarnkar M, Singal G, Kumar N. IoT Network Traffic Classification Using Machine Learning Algorithms: An Experimental AnalysisIEEE Internet of Things Journal. 2022;9(2):989–1008. Available from: https://dx.doi.org/10.1109/jiot.2021.3121517

  6. Panwar M, Gautam A, Dutt R, Acharyya A. CardioNet: Deep Learning Framework for Prediction of CVD Risk Factors2020 IEEE International Symposium on Circuits and Systems (ISCAS). 2020;p. 1–5. Available from: https://doi.org/10.1109/ISCAS45731.2020.9180636

  7. Swapna G, Soman KP, Vinayakumar R. Automated detection of diabetes using CNN and CNN-LSTM network and heart rate signalsProcedia Computer Science. 2018;132:1253–1262. Available from: https://dx.doi.org/10.1016/j.procs.2018.05.041

  8. Shahin OR, Alshammari HH, Alzahrani AA, Alkhiri H, Taloba AI. A robust deep neural network framework for the detection of diabetesAlexandria Engineering Journal. 2023;74:715–724. Available from: https://dx.doi.org/10.1016/j.aej.2023.05.072

  9. Rabie O, Alghazzawi D, Asghar J, Saddozai FK, Asghar MZ. A Decision Support System for Diagnosing Diabetes Using Deep Neural NetworkFrontiers in Public Health. 2022;10:1–13. Available from: https://dx.doi.org/10.3389/fpubh.2022.861062

  10. García-Ordás MT, Benavides C, Benítez-Andrades JA, Alaiz-Moretón H, García-Rodríguez I. Diabetes detection using deep learning techniques with oversampling and feature augmentationComputer Methods and Programs in Biomedicine. 2021;202:105968. Available from: https://doi.org/10.1016/j.cmpb.2021.105968

  11. Wang L, Mu Y, Zhao J, Wang X, Che H. IGRNet: A Deep Learning Model for Non-Invasive, Real-Time Diagnosis of Prediabetes through ElectrocardiogramsSensors. 2020;20(9):2556. Available from: https://dx.doi.org/10.3390/s20092556

  12. Ashiquzzaman A, Tushar AK, Islam MR, Kim J. Reduction of Overfitting in Diabetes Prediction Using Deep Learning Neural NetworkLecture Notes in Electrical Engineering. In book: IT Convergence and Security 2017. Volume 1. 2018;p. 35–43. Available from: http://dx.doi.org/10.1007/978-981-10-6451-7_5

  13. Naz H, Ahuja S. Deep learning approach for diabetes prediction using PIMA Indian datasetJournal of Diabetes & Metabolic Disorders. 2020;19(1):391–403. Available from: https://dx.doi.org/10.1007/s40200-020-00520-5

  14. Hosseinzadehketilateh M, Adami B, Karimian N. Advancements in Continuous Glucose Monitoring: Integrating Deep Learning and ECG Signal. 2024. Available from: https://arxiv.org/html/2403.07296v1

  15. Ribeiro AH, Ribeiro MH, Paixão GMM, Oliveira DM, Gomes PR, Canazart JA, et al. Automatic diagnosis of the 12-lead ECG using a deep neural networkNature Communications. 2020;11(1):1760. Available from: https://doi.org/10.1038/s41467-020-15432-4

  16. Haleem MS, Cisuelo O, Andellini M, Castaldo R, Angelini M, Ritrovato M, et al. A Self-Attention Deep Neural Network Regressor for real time blood glucose estimation in paediatric population using physiological signalsBiomedical Signal Processing and Control. 2024;92:106065. Available from: https://dx.doi.org/10.1016/j.bspc.2024.106065

  17. Cisuelo O, Stokes K, Oronti IB, Haleem MS, Barber TM, Weickert MO, et al. Development of an artificial intelligence system to identify hypoglycaemia via ECG in adults with type 1 diabetes: protocol for data collection under controlled and free-living conditionsBMJ Open. 2023;13(4):e067899. Available from: https://dx.doi.org/10.1136/bmjopen-2022-067899

  18. Prasad AS, Kavanashree N. ECG Monitoring System Using AD8232 Sensor. In: 2019 International Conference on Communication and Electronics Systems (ICCES). (pp. 976-980) IEEE. 2019.

  19. Coronado D, Shahin O, Taloba A. Real-Time Deep Learning System for Diabetes Detection Using Heartbeat Signal ClassificationBiomedical Signal Processing and Control. 2023;84:104796.

  20. Mostayed A, Luo J, Shu X, Wee W. Classification of 12-Lead ECG Signals with Bi-directional LSTM Network. 2018. Available from: https://doi.org/10.48550/arXiv.1811.02090

  21. Alam MR, Haque MM, Rahman MM, Islam MT, Faruk O. Deep learning-based long-term risk evaluation of incident type 2 diabetes from ECGeClinicalMedicine. 2024;67.

  22. Wang H, Wang X, Ma Y, Che H. Hyperglycemia Identification Using ECG in Deep Learning EraSensors. 2021;21(3).

  23. Saadatnejad S, Oveisi M, Hashemi M. LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable DevicesIEEE Journal of Biomedical and Health Informatics. 2020;24(2):515–523. Available from: https://dx.doi.org/10.1109/jbhi.2019.2911367

  24. Mohsen H, Shah J, El-Sappagh S. ECG-DiaNet: Multimodal Neural Network leveraging ECG and clinical factors for T2DM prediction. 2024.

Cite this article

Shringarpure V, Shivshankar G, More P, Chavan PM, Joshi KR. (2025). Neural Network Based Diabetes Detection Using ECG Signals. International Journal of Electronics and Computer Applications. 2(1): 12-22. https://doi.org/10.70968/ijeaca.v2i1.D1012

Views
7
Downloads
2
Citations