Latent Features-based Rule Generation for Early Detection of Diabetes Cardiac Autonomic Neuropathy (DCAN) using Deep Belief Neural Network
Latent Features-based Rule Generation for Early Detection of Diabetes Cardiac Autonomic Neuropathy (DCAN) using Deep Belief Neural Network |
||
 |
 |
|
| © 2025 by IJETT Journal | ||
| Volume-73 Issue-5 |
||
| Year of Publication : 2025 | ||
| Author : Mayura Nagara, Pooja Raundaleb |
||
| DOI : 10.14445/22315381/IJETT-V73I5P107 | ||
How to Cite?
Mayura Nagara, Pooja Raundaleb, "Latent Features-based Rule Generation for Early Detection of Diabetes Cardiac Autonomic Neuropathy (DCAN) using Deep Belief Neural Network," International Journal of Engineering Trends and Technology, vol. 73, no. 5, pp.58-69, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I5P107
Abstract
Diabetic Cardiac Autonomic Neuropathy (DCAN) is one of the deadliest complications of diabetes. The diagnosis is frequently delayed due to the absence of symptoms, and it is associated with a high cardiovascular risk. The overwhelming rise in diabetics combined with negligence in detecting DCAN remains a significantly underdiagnosed preliminary due to the delicacy of its symptoms and the invasive approach of traditional diagnosis methods. The main research gap identified here is a lack of an interpretable, noninvasive, robust predictive model that can detect DCAN at its early stages. In response to this gap, this research has introduced a novel hybrid approach that integrates Deep Belief Neural Networks (DBNN) for latent feature extraction combined with explainable rule generation techniques. This system implements unique detection capabilities for early DCAN risk assessment together with human-understandable rules. This research training on a large, newly collected dataset of Indian patients from the multi-speciality hospital “All is well,” MP. The model produces easily comprehensible and actionable predictions by incorporating Explainable AI (XAI) strategies. These latent features provide a rule-based framework that provides an efficient, precise, and noninvasive tool for diagnosis that may be utilized rapidly in healthcare environments. This work makes a substantial contribution to the field by introducing a novel, state-of-the-art, noninvasive technique that helps medical practitioners to predict and identify DCAN early, additionally alerting patients to becoming aware of them well in advance of possible consequences. This strategy could save many lives by facilitating early intervention, making it a crucial tool in the fight against complications associated with diabetes.
Keywords
Diabetic cardiac autonomic neuropathy, DCAN, Deep belief networks, Latent feature extraction, Explainable AI, Non-invasive diagnosis, Early detection, Rule-based prediction, Clinical interpretability, Diabetes complications.
References
[1] Ahmad Shaker Abdalrada et al., “Prediction of Cardiac Autonomic Neuropathy Using a Machine Learning Model in Patients with Diabetes,” Therapeutic Advances in Endocrinology and Metabolism, vol. 13, pp. 1-10, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Mahin Chowdhury et al., “Cardiac Autonomic Neuropathy and Risk of Cardiovascular Disease and Mortality in Type 1 and Type 2 Diabetes: A Meta-Analysis,” BMJ Publishing Group, vol. 9, no. 2, pp. 1-8, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Paolo Castiglioni et al., “Heart Rate Variability for the Early Detection of Cardiac Autonomic Dysfunction in Type 1 Diabetes,” Frontiers in Physiology, vol. 13, pp. 1-10, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Barbara H. Braffett et al., “Risk Factors for Diabetic Peripheral Neuropathy and Cardiovascular Autonomic Neuropathy in the Diabetes Control and Complications Trial/Epidemiology of Diabetes Interventions and Complications (DCCT/EDIC) Study,” Diabetes, vol. 69, no. 5, pp. 1000-1010, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Susumu Z. Sudo et al., “Diabetes-Induced Cardiac Autonomic Neuropathy: Impact on Heart Function and Prognosis,” Biomedicines, vol. 10, no. 12, pp. 1-13, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Xiaopu Lin et al., “Peripheral Nerve Conduction and Sympathetic Skin Response Are Reliable Methods to Detect Diabetic Cardiac Autonomic Neuropathy,” Frontiers in Endocrinology, vol. 12, pp. 1-8, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Yu Peng et al., “Evaluation of the Degree of Agreement of Four Methods for Diagnosing Diabetic Autonomic Neuropathy,” Frontiers in Neurology, vol. 12, pp. 1-9, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Mayura Nagar et al., “A Systematic Literature Review: Role of AI Algorithms for Automated Diagnosis of Diabetic Cardiac Autonomic Neuropathy [DCAN],” 2022 9th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, pp. 669-673, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Syed Arslan Ali et al., “An Optimally Configured and Improved Deep Belief Network (OCI-DBN) Approach for Heart Disease Prediction Based on Ruzzo-Tompa and Stacked Genetic Algorithm,” IEEE Access, vol. 8, pp. 65947-65958, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Benjamin T. Nebgen et al., “A Neural Network for Determination of Latent Dimensionality in Nonnegative Matrix Factorization,” Machine Learning: Science Technology, vol. 2, no. 2, pp. 1-12, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Syed Immamul Ansarullah et al., “Significance of Visible Non-Invasive Risk Attributes for the Initial Prediction of Heart Disease Using Different Machine Learning Techniques,” Computational Intelligence and Neuroscience, vol. 2022, pp. 1-12, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] María Teresa García-Ordás et al., “Diabetes Detection Using Deep Learning Techniques with Oversampling and Feature Augmentation,” Computer Methods and Programs in Biomedicine, vol. 202, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Rafiul Hassan et al., “Early Detection of Cardiovascular Autonomic Neuropathy: A Multi-Class Classification Model Based on Feature Selection and Deep Learning Feature Fusion,” Information Fusion, vol. 77, pp. 70-80, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Thippa Reddy Gadekallu et al., “Deep Neural Networks to Predict Diabetic Retinopathy,” Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 5, pp. 5407-5420, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Mohanad Alkhodari et al., “Screening Cardiovascular Autonomic Neuropathy in Diabetic Patients with Microvascular Complications Using Machine Learning: A 24-Hour Heart Rate Variability Study,” IEEE Access, vol. 9, pp. 119171-119187, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Hassan Tariq et al., “Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic Retinopathy,” Sensors, vol. 22, no. 1, pp. 1-15, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Vaishali Deshmukh et al., “Validation of Tele-HRV: A Novel Digital Health Solution for Cardiovascular Risk Detection in Diabetes,” American Heart Journal, vol. 267, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Andra-Elena Nica et al., “The Relationship between the Ewing Test, Sudoscan Cardiovascular Autonomic Neuropathy Score and Cardiovascular Risk Score Calculated with SCORE2-Diabetes,” Medicina, vol. 60, no. 5, pp. 1-11, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Yun-Ru Lai et al., “Predictive Value of Heart Rate Variability and Electrochemical Skin Conductance Measurements for Cardiovascular Autonomic Neuropathy Persistence in Type 2 Diabetes and Prediabetes: A 3-Year Follow-Up Study,” Neurophysiologie Clinique, vol. 54, no. 3, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Hiruni Gunathilaka et al., “Non-Invasive Diagnostic Approach for Diabetes Using Pulse Wave Analysis and Deep Learning,” Informatics, vol. 11, no. 3, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Lynn Ang et al., “Inflammatory Markers and Measures of Cardiovascular Autonomic Neuropathy in Type 1 Diabetes,” Journal of the American Heart Association, vol. 14, no. 1, pp. 1-11, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Tallat Naz et al., “Noninvasive Exploration of Cardiac Autonomic Neuropathy by Heart Rate and Blood Pressure Variability Analysis in Type 2 Diabetic Patients,” Pakistan Journal of Medical Sciences, vol. 37, no. 4, pp. 1020-1024, 2021.
[CrossRef] [Google Scholar] [Publisher Link]