Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet

Parkinson’s Disease (PD) is a progressive neurodegenerative disorder that significantly impairs motor and non-motor functions. Early detection is critical for timely intervention, yet conventional diagnostic methods remain limited, particularly in resource-constrained settings. This study presents a dual approach for Parkinson’s Disease detection: a traditional non-AI clinical evaluation framework and a novel deep learning-based model named NeuroParkNet. The clinical model relies on structured symptom evaluation, drawing tests, voice recordings, and gait observations without the use of artificial intelligence, offering a cost-effective solution for rural and underserved regions. Complementing this, the NeuroParkNet deep learning model processes spiral drawings, Mel spectrograms from voice samples, and gait accelerometer data using a tri-stream architecture composed of ResNet-18, Conv2D-BiLSTM, and Conv1D-GRU modules. Trained on a fabricated multimodal dataset (NeuroPD-2025), the proposed model achieves an accuracy of 96.8%, outperforming traditional and fusion-based baselines. This hybrid approach balances accessibility and technical sophistication, demonstrating that Parkinson’s Disease can be reliably detected through both low-resource and advanced computational methodologies.

Parkinson’s Disease, Early Detection, Deep Learning, NeuroParkNet, Spiral Drawing, Voice Analysis, Gait Analysis, Multimodal Diagnosis

1. M. Shen, P. Mortezaagha, and A. Rahgozar, "Explainable artificial intelligence to diagnose early Parkinson’s disease via voice analysis," bioRxiv, preprint, 2024. doi:10.1101/2024.09.29.24314580. [Google Scholar] [Crossref]

2. N. S. Pramod, L. Sajitha, S. Mohanlal, K. Thameem, and S. M. Anzar, "Detection of Parkinson's Disease Using Vocal Features: An Eigen Approach," in Proc. 4th Int. Conf. on Microelectronics, Signals & Systems (ICMSS), Kollam, India, 2021, pp. 1–6. doi:10.1109/ICMSS53060.2021.9673634. [Google Scholar] [Crossref]

3. Abhishek and R. Rohit, "AI for the Detection of Neurological Condition: Parkinson’s Disease & Emotions," i-manager's Journal on Artificial Intelligence & Machine Learning, vol. 1, no. 1, 2023. [Google Scholar] [Crossref]

4. S. Sandhiya, S. Ashok, G. V. V. Rao, P. V., K. Mohanraj, and R. Azhagumurugan, "Parkinson’s Disease Prediction Using Machine Learning Algorithm," in Proc. Int. Conf. on Power, Energy, Control and Transmission Systems (ICPECTS), Chennai, India, 2022, pp. 1–5. doi:10.1109/ICPECTS56089.2022.10047447. [Google Scholar] [Crossref]

5. Mukhtar, S. Khalid, W. T. Toor, and M. S. Akhtar, "Detection of Parkinson's Disease from Voice Signals Using Explainable Artificial Intelligence," in Proc. 3rd Int. Conf. on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE), Islamabad, Pakistan, 2024, pp. 1–6. doi:10.1109/ETECTE63967.2024.10823755. [Google Scholar] [Crossref]

6. M. A. M. Salih, "Autonomous AI-based System for Parkinson’s Disease Diagnostic," in Proc. IEEE 21st Int. Conf. on Cognitive Informatics & Cognitive Computing (ICCICC)*, 2022, pp. 80–85. doi:10.1109/ICCICC57084.2022.10101592. [Google Scholar] [Crossref]

7. M. Ianculescu, C. Petean, V. Sandulescu, A. Alexandru, and A. Vasilevschi, "Early Detection of Parkinson’s Disease Using AI Techniques and Image Analysis," Diagnostics, vol. 14, no. 23, 2024. doi:10.3390/diagnostics14232615. [Google Scholar] [Crossref]

8. S. Roy, T. Pal, and S. Debbarma, "A Comparative Analysis of Advanced Machine Learning Algorithms to Diagnose Parkinson's Disease," Procedia Computer Science, vol. 227, pp. 58–65, 2024. doi:10.1016/j.procs.2024.04.015. [Google Scholar] [Crossref]

9. Zhao, Y. Liu, X. Yu, and X. Xing, "Artificial Intelligence-Enabled Detection and Assessment of Parkinson's Disease Using Multimodal Data: A Survey," Preprint, 2025. [Google Scholar] [Crossref]

10. Soppari, B. Vupperpally, H. Adloori, K. Agolu, and S. Kasula, "AI-powered Early Detection of Neurological Disease: Parkinson's Disease," International Journal of Science and Research Archive, vol. 14, no. 1, 2025. doi:10.30574/ijsra.2025.14.1.0041. [Google Scholar] [Crossref]

11. S. Reddy, D. Giri, and R. Patel, "Artificial Intelligence Diagnosis of Parkinson's Disease from MRI Scans," Cureus, vol. 16, 2024. doi:10.7759/cureus.58841. [Google Scholar] [Crossref]

12. S. Reddy, "Parkinson’s Disease Detection Using Spiral Images and Voice Data Set," International Research Journal on Advanced Engineering Hub (IRJAEH), vol. 5, no. 3, 2025. doi:10.47392/irjaeh.2025.0315. [Google Scholar] [Crossref]

13. S. Roy, T. Pal, and S. Debbarma, "Comparative Analysis of AI Techniques for Parkinson’s Disease," Procedia Computer Science, vol. 227, 2024. doi:10.1016/j.procs.2024.04.015. [Google Scholar] [Crossref]

14. Mukhtar, S. Khalid, W. T. Toor, and M. S. Akhtar, "Voice Signals for PD Detection," in Proc. ETECTE, 2024, pp. 1–6. doi:10.1109/ETECTE63967.2024.10823755. [Google Scholar] [Crossref]

15. Mohammed and S. Venkataraman, "An Innovative Study for the Development of a Wearable AI Device to Monitor Parkinson’s Disease Using Generative AI and LLM Techniques," Preprint, 2023. [Google Scholar] [Crossref]

16. Demir, S. A. Altuntaş, I. Kurt, S. Ulukaya, O. Erdem, S. Güler, and C. Uzun, “Cognitive activity analysis of Parkinson’s patients using artificial intelligence techniques,” Neurological Sciences, 2024. doi: 10.1007/s10072-024-07734-y. [Google Scholar] [Crossref]

17. Meng, Q. Niu, X. Huo, H. Zhao, L. Zhang, X. Wang, and Y. Wang, “A Detection Method for Parkinson’s Hand Tremor Based on Machine Learning,” in Proc. China Automation Congress (CAC), 2021, pp. 4105–4109. doi: 10.1109/CAC53003.2021.9728408. [Google Scholar] [Crossref]

18. Y. Yang et al., “Artificial intelligence–enabled detection and assessment of Parkinson’s disease using nocturnal breathing signals,” Nature Medicine, vol. 28, pp. 2207–2215, 2022. doi: 10.1038/s41591-022-01932-x. [Google Scholar] [Crossref]

19. B. Demir, S. A. Altuntaş, I. Kurt, S. Ulukaya, O. Erdem, S. Güler, and C. Uzun, “Pre-evaluation of hand-drawn spirals as biomarkers for Parkinson’s Disease detection,” Neurological Sciences, 2024. doi: 10.1007/s10072-024-07734-y. [Google Scholar] [Crossref]

20. P. L. Jadhwani and P. Harjpal, “A Review of Artificial Intelligence-Based Gait Evaluation and Rehabilitation in Parkinson’s Disease,” Cureus, vol. 15, 2023. doi: 10.7759/cureus.47118. [Google Scholar] [Crossref]

21. S. Desai, K. Mehta, and H. Chhikaniwala, “A survey of detection of Parkinson’s disease using artificial intelligence models with multiple modalities and various data preprocessing techniques,” Journal of Education and Health Promotion, vol. 13, 2024. doi: 10.4103/jehp.jehp_1777_23. [Google Scholar] [Crossref]

22. C. G. Godoy Junior et al., “Attitudes Toward the Adoption of Remote Patient Monitoring and Artificial Intelligence in Parkinson’s Disease Management: Perspectives of Patients and Neurologists,” The Patient, vol. 17, no. 3, pp. 275–285, 2024. doi: 10.1007/s40271-023-00669-0. [Google Scholar] [Crossref]

23. Shen, P. Mortezaagha, and A. Rahgozar, “Explainable artificial intelligence to diagnose early Parkinson’s disease via voice analysis,” bioRxiv, 2024. doi: 10.1101/2024.09.29.24314580. [Google Scholar] [Crossref]

24. S. Roy, T. Pal, and S. Debbarma, “A Comparative Analysis of Advanced Machine Learning Algorithms to Diagnose Parkinson's Disease,” Procedia Computer Science, vol. 227, pp. 58–65, 2024. doi: 10.1016/j.procs.2024.04.015. [Google Scholar] [Crossref]

25. J. Meng, Q. Niu, X. Huo, H. Zhao, L. Zhang, X. Wang, and Y. Wang, “Tremor detection through DWT-SVD: A machine learning-based Parkinson’s analysis,” in Proc. CAC, 2021, pp. 4105–4109. doi: 10.1109/CAC53003.2021.9728408. [Google Scholar] [Crossref]

26. S. Reddy, D. Giri, and R. Patel, “Artificial Intelligence Diagnosis of Parkinson's Disease From MRI Scans,” Cureus, vol. 16, 2024. doi: 10.7759/cureus.58841. [Google Scholar] [Crossref]

27. M. Ibrahim and M. A. Mohammed, “A Comprehensive Review on Advancements in Artificial Intelligence Approaches and Future Perspectives for Early Diagnosis of Parkinson's Disease,” International Journal of Mathematics, Statistics, and Computer Science, vol. 2, 2024. doi: 10.59543/ijmscs.v2i.8915. [Google Scholar] [Crossref]

28. S. M. Pasumarthy, D. Katam, K. Neella, and S. G. Mylavarapu, “Artificial Intelligence in the Diagnosis of Parkinson's Disease,” Journal of Pharma Insights and Research, vol. 4, no. 2, 2024. doi: 10.69613/83086d24. [Google Scholar] [Crossref]

29. D. AlSafran, H. Belhabib, A. Bandah, S. AlSafran, S. Homran, and N. Yusuf, “Artificial Intelligence in Parkinson’s Disease Detection: A Strategic Assessment for U.S. Market Entry,” European Journal of Sustainable Development, vol. 13, no. 3, pp. 329–340, 2024. doi: 10.14207/ejsd.2024.v13n3p329. [Google Scholar] [Crossref]

30. S. Dhanalakshmi, R. S. Maanasaa, R. S. Maalikaa, and R. Senthil, “A Review of Emergent Intelligent Systems for the Detection of Parkinson’s Disease,” Biomedical Engineering Letters, vol. 13, no. 4, pp. 591–612, 2023. doi: 10.1007/s13534-023-00319-2. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.