A Next-Generation Feature-Selective Deep Hybrid Architecture for Attention-Driven Parkinson's Disease Classification

Raghuvira Pratap Adimulam; Suresh Annamalai

doi:10.48084/etasr.18067

Authors

Raghuvira Pratap Adimulam Department of Networking and Communications, School of Computing, Faculty of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu District, Tamil Nadu, India
Suresh Annamalai Department of Networking and Communications, School of Computing, Faculty of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu District, Tamil Nadu, India

Volume: 16 | Issue: 3 | Pages: 35881-35887 | June 2026 | https://doi.org/10.48084/etasr.18067

Received: 9 February 2026 | Revised: 21 March 2026 and 3 April 2026 | Accepted: 4 April 2026 | Online: 16 May 2026

Corresponding author: Suresh Annamalai

Abstract

Parkinson's Disease (PD) is among the most widespread neurodegenerative disorders, characterized by cardinal symptoms including bradykinesia, shortened strides, abnormal gait and posture, and other mobility impairments. PD detection primarily relies on clinician observation and evaluation of cardinal motor symptoms. However, conventional diagnostic methods are often constrained by subjectivity, as they depend on interpreting subtle movement alterations, which may lead to misclassification. Meanwhile, non-motor signs of PD may initially be subtle and could be attributed to several other conditions. Thus, these signs are frequently neglected, making the detection of PD at an early stage difficult. To overcome these obstacles and enhance the identification and assessment of PD, artificial intelligence, particularly Machine Learning (ML) and Deep Learning (DL), has been applied. Therefore, this study presents a Robust Parkinson's Disease Classification Framework using Advanced Deep Learning (RPDCF-ADL) model. The aim is to develop a reliable model for the accurate classification of PD patients and healthy control subjects. Initially, raw data undergo preprocessing, including data cleaning and data transformation, to improve data quality and consistency. Following that, a minimum Spearman Maximum Mutual Information (mSMMI) method is utilized to select the most informative features. The selected features are then fed into a hybrid classification model that integrates a Transformer with a Deep Belief Network (T-DBN) to effectively capture complex feature dependencies and non-linear patterns for precise PD classification. Furthermore, the AdamP optimization algorithm is adopted for weight optimization. The experimental validation of the RPDCF-ADL method achieved superior accuracy values of 98.61%, 98.86%, and 97.62% compared with existing models on the PD audio, PD, and HandPD datasets, respectively.

Keywords:

Parkinson's Disease (PD), feature selection, medical data, Deep Learning (DL), AdamP optimization, Transformer network

References

M. Oumaima, B. Achraf, J. Abdelilah, and H. Ahmed, "Non-invasive detection of Parkinson’s disease using voice analysis and machine learning techniques," International Journal of Speech Technology, vol. 29, no. 1, Dec. 2025, Art. no. 3.

X. Bi et al., "Diagnosis of Parkinson’s disease by Archimedes spiral dynamic handwriting analysis based on Dual-head Multimodal Networks," Biomedical Signal Processing and Control, vol. 112, Feb. 2026, Art. no. 108448.

J. Asma Malica, K. Dinesh, P. Elavarasu, K. Devendran, C. Sagana, and R. Manjuladevi, "Prediction of Parkinson’s Disease Using Ensemble Learning," in Proceedings of International Conference on Power Engineering and Intelligent Systems, Srinagar, Uttarakhand, India, 2025, pp. 125–138.

W.-C. Wang, C.-C. Chiu, and S.-J. Yeh, "Deep learning classification for prodromal Parkinson’s disease based on spatiotemporal features of specific finger movements," Biomedical Signal Processing and Control, vol. 113, Mar. 2026, Art. no. 109216.

S. Das, G. Kumar, and R. Sharma, "Prediction of Diabetes, Cardiac and Parkinson’s disease using machine learning and streamlit framework," Multimedia Tools and Applications, vol. 84, no. 24, pp. 28853–28872, July 2025.

W. Xiong, L. Ma, and H. Li, "Efficient Neural Network Classification of Parkinson’s Disease and Schizophrenia Using Resting-State EEG Data," Brain Topography, vol. 38, no. 3, Feb. 2025, Art. no. 32.

Y. Zhang et al., "A novel approach for handwriting recognition in Parkinson’s disease by combining flexible sensing with deep learning technologies," Sensors and Actuators A: Physical, vol. 385, Apr. 2025, Art. no. 116287.

S. Saleh, B. Cherradi, O. El Gannour, S. Hamida, and O. Bouattane, "Predicting patients with Parkinson’s disease using Machine Learning and ensemble voting technique," Multimedia Tools and Applications, vol. 83, no. 11, pp. 33207–33234, Mar. 2024.

N. Singh and P. Tripathi, "An ensemble technique to predict Parkinson’s disease using machine learning algorithms," Speech Communication, vol. 159, Apr. 2024, Art. no. 103067.

H. Taherdoost, "Deep Learning and Neural Networks: Decision-Making Implications," Symmetry, vol. 15, no. 9, Sept. 2023, Art. no. 1723.

M. Alqam, A. Hossen, S. Al-Abri, R. Al-Hmouz, and M. Deveci, "Classification of the Severity of Speech Disorders in Patients with Parkinson’s Disease Using Machine Learning Techniques," International Journal of Computational Intelligence Systems, vol. 19, no. 1, Dec. 2025, Art. no. 31.

S. Abbasi and K. Rezaee, "Deep Learning–Based Prediction of Freezing of Gait in Parkinson’s Disease With the Ensemble Channel Selection Approach," Brain and Behavior, vol. 15, no. 1, 2025, Art. no. e70206.

F. R. Sayem et al., "A novel deep learning approach with feature injection technique for automated gait detection in parkinson’s disease using multi-modal data," International Journal of Data Science and Analytics, vol. 22, no. 1, Jan. 2026, Art. no. 47.

B. Perrone, F. Amato, and G. Olmo, "Voice classification in Parkinson’s disease: A deep learning approach using transformers and error rate metrics," Biomedical Signal Processing and Control, vol. 113, Mar. 2026, Art. no. 108954.

S. A. Ansari, M. Luqman, S. Ali, P. Singh, M. Diwakar, and A. Bijalwan, "A Smart IoT-Based System for Early Prediction of Parkinson’s Disease Using Swarm-Assisted Convolutional Neural Networks," International Journal of Computational Intelligence Systems, vol. 19, no. 1, Jan. 2026, Art. no. 4.

N. Mehra et al., "Hybrid Model for Freezing of Gait Detection in Parkinson’s Disease: Integrating Manual Features and Deep Learning," International Journal of Computational Intelligence Systems, vol. 19, no. 1, Jan. 2026, Art. no. 38.

P. Valarmathi, Y. Suganya, K. R. Saranya, and S. Shanmuga Priya, "Enhancing parkinson disease detection through feature based deep learning with autoencoders and neural networks," Scientific Reports, vol. 15, no. 1, Mar. 2025, Art. no. 8624.

B. Majhi et al., "An improved method for diagnosis of Parkinson’s disease using deep learning models enhanced with metaheuristic algorithm," BMC Medical Imaging, vol. 24, no. 1, June 2024, Art. no. 156.

A. Puviarasu and S. V K, "Enhanced IoT security: privacy-preserving federated learning model for accurate, real-time intrusion detection across devices," Ain Shams Engineering Journal, vol. 17, no. 1, Jan. 2026, Art. no. 103866.

Y. Shi, Y. Zheng, and X. Bai, "A multiple filter-wrapper feature selection algorithm based on process optimization mechanism for high-dimensional omics data analysis," Plos One, vol. 20, no. 12, Dec. 2025, Art. no. e0338051.

A. E. Oskouei, M. Kaveh, F. Hernando-Gallego, and D. Martín, "Hybrid Time Series Transformer–Deep Belief Network for Robust Anomaly Detection in Mobile Communication Networks," Symmetry, vol. 17, no. 11, Oct. 2025, Art. no. 1800.

A. Pasha et al., "Leveraging ANFIS with Adam and PSO optimizers for Parkinson’s disease," Heliyon, vol. 10, no. 9, May 2024, Art. no. e30241.

M. A. Little, P. E. McSharry, E. J. Hunter, J. Spielman, and L. O. Ramig, "Suitability of Dysphonia Measurements for Telemonitoring of Parkinson’s Disease," IEEE Transactions on Biomedical Engineering, vol. 56, no. 4, pp. 1015–1022, Apr. 2009.

"Parkinson’s Disease Data Set." Kaggle. [Online]. Available: https://www.kaggle.com/datasets/vikasukani/parkinsons-disease-data-set.

C. O. Sakar et al., "A comparative analysis of speech signal processing algorithms for Parkinson’s disease classification and the use of the tunable Q-factor wavelet transform," Applied Soft Computing, vol. 74, pp. 255–263, Jan. 2019.

"Parkinson’s Disease (PD) classification." Kaggle. [Online]. Available: https://www.kaggle.com/datasets/dipayanbiswas/parkinsons-disease-speech-signal-features.

C. R. Pereira et al., "A Step Towards the Automated Diagnosis of Parkinson’s Disease: Analyzing Handwriting Movements," in 2015 IEEE 28th International Symposium on Computer-Based Medical Systems, Sao Carlos, Brazil, 2015, pp. 171–176.

"HandPD dataset." Kaggle. [Online]. Available: https://www.kaggle.com/datasets/claytonteybauru/spiral-handpd.

T. Welton et al., "Classification of Parkinson’s disease by deep learning on midbrain MRI," Frontiers in Aging Neuroscience, vol. 16, Aug. 2024, Art. no. 1425095.

Y. Chang, J. Liu, S. Sun, T. Chen, and R. Wang, "Deep learning for Parkinson’s disease classification using multimodal and multi-sequences PET/MR images," EJNMMI Research, vol. 15, no. 1, May 2025, Art. no. 55.

S. Pechetti and B. S. Rao, "Optimized MobileNetV3: a deep learning-based Parkinson’s disease classification using fused images," PeerJ Computer Science, vol. 9, Nov. 2023, Art. no. e1702.

A. Sar, P. S. Puri, H. Naz, S. Aich, T. Choudhury, and L. A. Gabralla, "Multi-modal deep learning framework for early detection of Parkinson’s disease using neurological and physiological data for high-fidelity diagnosis," Scientific Reports, vol. 15, no. 1, Oct. 2025, Art. no. 34835.