Authors : Utsha Sarker; Aman Singh; Archy Biswas; Santosh Rai; Vikash Prajapati

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/4uy33uxy

Scribd : https://tinyurl.com/3chts2bz

DOI : https://doi.org/10.38124/ijisrt/26mar007

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Parkinson's disease (PD) is a progressive degenerating disease with motor manifestations that include resting tremor, bradykinesia and rigidity. Accurate assessment of tremor is still very much reliant on subjective clinical scale criteria (Unified Parkinson's Disease Rating Scale (UPDRS)) that may not represent minor fluctuations or real world variability. This restriction highlights an obvious lack of objective, ongoing and comprehended tremor monitoring solutions to help with early diagnosis and personalized disease management. In this study, an explainable deep learning framework used for tremor classification based on wearable sensor fusion is proposed. Wrist worn accelerometer signals and gyroscope signals are fused and processed using the hybrid system of 1-D Convolution Neural Networks (1-D CNN) merged with the Bidirectional Long Short-Term Memory (BiLSTM) which can capture both the local motion patterns and long-term temporal dependencies. More transparency is provided by explainable AI methods (Grad-CAM and SHAP) to explain important segments of the time, as well as the role of the sensor in the prediction of the model. Experiments were performed on a data set containing 62 subjects (38 PD patients and 24 healthy subject), which was recorded at 100 Hz. Signals were divided in 1.28 sec overlapped t ime windows, and were labeled as tremor or not tremor, PD or control. The proposed model showed 94.3%, 93.8%, 0.96 AUC, 92.5%, 95.1% accuracy, F1-score, sensitivity, and specificity, respectively, which are much better than conventional CNN and SVM approximations with accuracy improvements of 6-9%. Explainability analysis showed an overriding influence of tremor-related oscillatory components (4-6 Hz) in the prediction, which led to clinically meaningful explainability of the predictions, and gives extra confidence to the model for use in the real world.

Keywords : Parkinson's Disease, Wearable Sensors, Deep Neural Network, Tremor Detection, Explainable Artificial Intelligence (XAI), Sensor Fusion.

References :

1. M. Chen, Z. Sun, T. Xin, Y. Chen, and F. Su, “An Interpretable Deep Learning Optimized Wearable Daily Detection System for Parkinson’s Disease,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 31, pp. 3937–3946, 2023, doi: 10.1109/TNSRE.2023.3314100.
2. Y. X. Teo, R. E. Lee, S. G. Nurzaman, C. P. Tan, and P. Y. Chan, “Action tremor features discovery for essential tremor and Parkinson’s disease with explainable multilayer BiLSTM,” Comput. Biol. Med., vol. 180, Art. no. 108957, Sep. 2024, doi: 10.1016/j.compbiomed.2024.108957.
3. T. Sil et al., “Sensor-based data-driven differentiation between Parkinson’s tremor and essential tremor,” Expert Syst. Appl., vol. 299, pt. D, Art. no. 130336, Mar. 2026, doi: 10.1016/j.eswa.2025.130336.
4. X. Liu et al., “Automated UPDRS Gait Scoring Using Wearable Sensor Fusion and Deep Learning,” Bioengineering, vol. 12, no. 7, Art. no. 686, 2025, doi: 10.3390/bioengineering12070686.
5. M. Sakib et al., “TremorFusion: AI-driven feature extraction for multi-class Parkinson’s tremor classification using CSVM and DeepK-CNN,” Biomed. Eng. Lett., Dec. 2025, doi: 10.1007/s13534-025-00526-z.
6. R. P. Bremm et al., “Sensor-Based Quantification of MDS-UPDRS III Subitems in Parkinson’s Disease Using Machine Learning,” Sensors, vol. 24, no. 7, Art. no. 2195, 2024, doi: 10.3390/s24072195.
7. R. Atri et al., “Deep Learning for Daily Monitoring of Parkinson’s Disease Outside the Clinic Using Wearable Sensors,” Sensors, vol. 22, no. 18, Art. no. 6831, 2022, doi: 10.3390/s22186831.
8. E. Rastegari, H. Ali, and V. Marmelat, “Detection of Parkinson’s disease using wrist accelerometer data and passive monitoring,” Sensors, vol. 22, no. 23, Art. no. 9122, 2022, doi: 10.3390/s22239122.
9. D. Trabassi et al., “Machine learning approach to support the detection of Parkinson’s disease in IMU-based gait analysis,” Sensors, vol. 22, no. 10, Art. no. 3700, 2022, doi: 10.3390/s22103700.
10. S. Lin et al., “Wearable sensor-based gait analysis to discriminate early Parkinson’s disease from essential tremor,” J. Neurol., vol. 270, no. 4, pp. 2283–2301, 2023, doi: 10.1007/s00415 023-11577-6.
11. A.-K. Schalkamp et al., “Wearable movement-tracking data identify Parkinson’s disease years before clinical diagnosis,” Nat. Med., vol. 29, no. 8, pp. 2048–2056, 2023, doi: 10.1038/s41591-023-02440-2.
12. J. Varghese et al., “Machine Learning in the Parkinson’s disease smartwatch (PADS) dataset,” npj Parkinson’s Dis., vol. 10, Art. no. 9, 2024, doi: 10.1038/s41531-023-00625-7.
13. C. Moreau et al., “Overview on wearable sensors for the management of Parkinson’s disease,” npj Parkinson’s Dis., vol. 9, no. 1, Art. no. 153, 2023, doi: 10.1038/s41531-023-00585-y.
14. H. Mughal, A. R. Javed, M. Rizwan, A. S. Almadhor, and N. Kryvinska, “Parkinson’s disease management via wearable sensors: a systematic review,” IEEE Access, vol. 10, pp. 35219–35237, 2022, doi: 10.1109/ACCESS.2022.3162844.
15. L. Sigcha et al., “Deep learning and wearable sensors for the diagnosis and monitoring of Parkinson’s disease: A systematic review,” Expert Syst. Appl., vol. 229, Art. no. 120541, 2023, doi: 10.1016/j.eswa.2023.120541.
16. Esan et al., “Explainable AI for Parkinson’s disease prediction: A machine learning approach with interpretable models,” Curr. Res. Transl. Med., vol. 73, no. 4, Art. no. 103541, Dec. 2025, doi: 10.1016/j.retram.2025.103541.
17. (Wearable + interpretability, clinical XAI angle) “An Interpretable Approach Using Convolutional Neural Networks and GRU for Parkinson’s Disease Detection from Wearables,” Front. Neurol., 2024, doi: 10.3389/fneur.2024.1387477.
18. Mirelman et al., “Digital mobility measures: a window into real-world severity and progression of Parkinson’s disease,” Mov. Disord., vol. 39, no. 2, pp. 328–338, 2024, doi: 10.1002/mds.29689.
19. Brzenczek et al., “Integrating digital gait data with metabolomics and clinical data to predict outcomes in Parkinson’s disease,” npj Digit. Med., 2024, doi: 10.1038/s41746-024 01236-z.
20. Shcherbak, E. Kovalenko, and A. Somov, “Detection and classification of early stages of Parkinson’s disease through wearable sensors and machine learning,” IEEE Trans. Instrum. Meas., 2023, doi: 10.1109/TIM.2023.3284944.