Abstract

The problem of initial and reliable analysis of Parkinson disease (PD) is caused by the heterogeneous nature of its clinical manifestation and indistinct neurobiological alterations of prodromal and early stages of the disease. The study hypothesizes an explainable Deep Learning (DL) framework of automated analysis and detection of PD through multimodal neuroimaging. The clinical data from the Parkinson’s Progression Markers Initiative (PPMI), Structural Magnetic Resonance Imaging (MRI) (T1-weighted), resting-state functional Magnetic Resonance Imaging (fMRI), and Diffusion Tensor Imaging (DTI) were jointly leveraged to capture complementary morphological, functional, and microstructural biomarkers. Structural MRI was Z-score normalized, fMRI underwent wavelet denoising, and DTI was corrected for eddy currents to reduce noise, standardize intensities, and enhance reliable multimodal feature extraction. 3D Sobel filtering was applied to MRI, fMRI, and DTI to enhance structural edges and anatomical boundaries. A multimodal fusion architecture integrating 3D Residual Networks with vision transformers (3D RN-ViT) was developed to diagnose PD. To ensure clinical transparency, Explainable Artificial Intelligence (XAI) techniques were employed to localize disease-relevant neuroanatomical regions and quantify modality-wise contributions. A Multi-Layer Perceptron (MLP) head was employed for final classification on the extracted multimodal features. Satin Bowerbird Optimization (SBO) was employed for optimal feature selection to classify the best discriminative multimodal structures while reducing redundancy and dimensionality. Experiments were carried out in the Python framework using PyTorch. The proposed 3D RN-ViT attained 99.2% accuracy, 99.2% precision, and a 99.34% sensitivity. Overall, the proposed approach provides a transparent and scalable pathway for the analysis of PD, supporting biomarker discovery and serving as a promising proof-of-concept for AI-assisted neuroimaging systems. Future external cross-cohort validation will be required prior to clinical deployment.

Keywords

Explainable AI, Multimodal Neuroimaging, Deep Learning, Parkinson’s disease, Biomarkers,

Downloads

Download data is not yet available.

References

  1. M. Alalayah, E.M. Senan, H.F. Atlam, I.A. Ahmed, H.S.A. Shatnawi, Automatic and Early Detection of Parkinson's Disease by Analyzing Acoustic Signals using Classification Algorithms based on recursive feature Elimination Method. Diagnostics, 13(11), (2023) 1924. https://doi.org/10.3390/diagnostics13111924
  2. E.H. Kwon, S. Tennagels, R. Gold, K. Gerwert, L. Beyer, L. Tönges, Update on CSF Biomarkers in Parkinson’s Disease. Biomolecules, 12(2), (2022) 329. https://doi.org/10.3390/biom12020329
  3. M. Alrawis, S. Al-Ahmadi, F. Mohammad, Bridging Modalities: A Multimodal Machine Learning Approach for Parkinson’s disease Diagnosis using EEG and MRI Data. Applied Sciences, 14(9), (2024) 3883. https://doi.org/10.3390/app14093883
  4. M. Bongianni, M. Catalan, D. Perra, E. Fontana, F. Janes, C. Bertolotti, L. Sacchetto, S. Capaldi, M. Tagliapietra, P. Polverino, V. Tommasini, Olfactory Swab Sampling Optimization for α-Synuclein Aggregate Detection in Patients with Parkinson’s Disease. Translational Neurodegeneration, 11(1), (2022) 37. https://doi.org/10.1186/s40035-022-00311-3
  5. A.E. Lang, R.A. Hauser, L.V. Kalia, B. Hersh, Z. Berger, R. Llorens Arenas, C. Paisan-Ruiz, K. Fraser, D. Jennings, J.H. Kluss, S. Huntwork-Rodriguez, A.G. Henry, & J.T. Greenamyre, “LRRK2 as a potential disease‐modifying target in sporadic Parkinson's disease” Movement Disorders, 41(2) (2026) 297-314. https://doi.org/10.1002/mds.70100
  6. S. Prange, H. Klinger, C. Laurencin, T. Danaila, S. Thobois, Depression in Patients with Parkinson’s Disease: Current Understanding of its Neurobiology and Implications for Treatment. Drugs & Aging, 39(6), (2022) 417–439. https://doi.org/10.1007/s40266-022-00942-1
  7. J. Rutledge, B. Lehallier, P. Zarifkar, P.M. Losada, M. Shahid-Besanti, D. Western, P. Gorijala, S. Ryman, M. Yutsis, G.K. Deutsch, E. Mormino, Comprehensive Proteomics of CSF, Plasma, and Urine Identify DDC and Other Biomarkers of Early Parkinson’s Disease. Acta Neuropathologica, 147(1), (2024) 52. https://doi.org/10.1007/s00401-024-02706-0
  8. M. Alissa, M.A. Lones, J. Cosgrove, J.E. Alty, S. Jamieson, S.L. Smith, M. Vallejo, Parkinson’s Disease Diagnosis using Convolutional Neural Networks and Figure-Copying Tasks. Neural Computing and Applications, 34(2), (2022) 1433–1453. https://doi.org/10.1007/s00521-021-06469-7
  9. S.M. Abdullah, T. Abbas, M.H. Bashir, I.A. Khaja, M. Ahmad, N.F. Soliman, W. El-Shafai, Deep Transfer Learning based Parkinson’s Disease Detection using Optimized Feature Selection. IEEE Access, IEEE, 11, (2023) 3511–3524. https://doi.org/10.3934/Neuroscience.2023017
  10. K. Chen, H. Wang, I. Ilyas, A. Mahmood, L. Hou, Microglia and Astrocytes Dysfunction and Key Neuroinflammation-Based Biomarkers in Parkinson’s Disease. Brain Sciences, 13(4), (2023) 634. https://doi.org/10.3390/brainsci13040634
  11. B. Majhi, A. Kashyap, S.S. Mohanty, S. Dash, S. Mallik, A. Li, Z. Zhao, An Improved Method for Diagnosis of Parkinson’s Disease using Deep Learning Models enhanced with Metaheuristic Algorithm. BMC Medical Imaging, 24(1), (2024) 156. https://doi.org/10.1186/s12880-024-01335-z
  12. L. Nechushtai, D. Frenkel, R. Pinkas-Kramarski, Autophagy in Parkinson’s disease. Biomolecules, 13(10), (2023) 1435. https://doi.org/10.3390/biom13101435
  13. S. Saravanan, K. Ramkumar, K. Narasimhan, S. Vairavasundaram, K. Kotecha, A. Abraham, Explainable Artificial Intelligence (EXAI) Models for Early Prediction of Parkinson’s Disease based on Spiral and Wave Drawings. IEEE Access, IEEE, 11, (2023) 68366–68378. https://doi.org/10.1109/ACCESS.2023.3291406
  14. M. Camacho, M. Wilms, P. Mouches, H. Almgren, R. Souza, R. Camicioli, Z. Ismail, O. Monchi, N.D. Forkert, Explainable Classification of Parkinson’s Disease using Deep Learning Trained on a Large Multi-Center Database of T1-Weighted MRI Datasets. NeuroImage: Clinical, 38, (2023) 103405. https://doi.org/10.1016/j.nicl.2023.103405
  15. G. Costantini, V. Cesarini, P. Di Leo, F. Amato, A. Suppa, F. Asci, A. Pisani, A. Calculli, G. Saggio, Artificial Intelligence-based Voice Assessment of Patients with Parkinson’s disease off and on Treatment: Machine vs. Deep-Learning Comparison. Sensors, 23(4), (2023) 2293. https://doi.org/10.3390/s23042293
  16. A. Rana, A. Dumka, R. Singh, M. Rashid, N. Ahmad, M.K. Panda, An Efficient Machine Learning Approach for Diagnosing Parkinson’s Disease by Utilizing Voice features. Electronics, 11(22), (2022) 3782. https://doi.org/10.3390/electronics11223782
  17. M. Aljalal, S.A. Aldosari, K. AlSharabi, A.M. Abdurraqeeb, F.A. Alturki, Parkinson’s Disease Detection from Resting-State EEG Signals using Common Spatial Pattern, Entropy, and Machine Learning Techniques. Diagnostics, 12(5), (2022) 1033. https://doi.org/10.3390/diagnostics12051033
  18. A. Rehman, T. Saba, M. Mujahid, F.S. Alamri, N. ElHakim, Parkinson’s disease detection using hybrid LSTM-GRU deep learning model. Electronics, 12(13), (2023) 2856. https://doi.org/10.3390/electronics12132856
  19. T. Aşuroğlu, H. Oğul, A Deep Learning Approach for Parkinson’s Disease Severity Assessment. Health and Technology, 12(5), (2022) 943–953. https://doi.org/10.1007/s12553-022-00698-z
  20. R.R. Ileșan, C.G. Cordoș, L.I. Mihăilă, R. Fleșar, A.S. Popescu, L. Perju-Dumbravă, P. Faragó, Proof of Concept in Artificial-Intelligence-based Wearable Gait Monitoring for Parkinson’s Disease Management Optimization. Biosensors, 12(4), (2022) 189. https://doi.org/10.3390/bios12040189
  21. D. Trabassi, M. Serrao, T. Varrecchia, A. Ranavolo, G. Coppola, R. De Icco, C. Tassorelli, S.F. Castiglia, Machine Learning Approach to Support the Detection of Parkinson’s Disease in IMU-based Gait Analysis. Sensors, 22(10), (2022) 3700. https://doi.org/10.3390/s22103700
  22. M. Hosseinzadeh, A. Gorji, A. Fathi Jouzdani, S.M. Rezaeijo, A. Rahmim, M.R. Salmanpour, Prediction of Cognitive Decline in Parkinson’s Disease using Clinical and DAT SPECT Imaging Features, and Hybrid Machine Learning Systems. Diagnostics, 13(10), (2023) 1691. https://doi.org/10.3390/diagnostics13101691
  23. R. Pratihar, R. Sankar, Integrative Federated Learning Framework for Multimodal Parkinson’s Disease Biomarker Fusion. Computers, 14(9), (2025) 388. https://doi.org/10.3390/computers14090388
  24. Y. Chang, J. Liu, S. Sun, T. Chen, R. Wang, Deep Learning for Parkinson’s Disease Classification using Multimodal and Multi-Sequences PET/MR Images. EJNMMI Research, 15(1), (2025) 55. https://doi.org/10.1186/s13550-025-01245-3
  25. T. Meindl, A. Hapfelmeier, T. Mantel, A. Jochim, J. Deppe, S. Zwirner, J.S. Kirschke, Y. Li, B. Haslinger, Assisted Parkinsonism Diagnosis Using Multimodal MRI—The Role of Clinical Insights. Brain and Behavior, 15(1), (2025) e70274. https://doi.org/10.1002/brb3.70274
  26. H. Pang, Z. Yu, H. Yu, M. Chang, J. Cao, Y. Li, M. Guo, Y. Liu, K. Cao, G. Fan, Multimodal Striatal Neuromarkers in Distinguishing Parkinsonian Variant of Multiple System Atrophy from Idiopathic Parkinson's Disease. CNS Neuroscience & Therapeutics, 28(12), (2022) 2172–2182. https://doi.org/10.1111/cns.13959
  27. M. Khedimi, T. Zhang, C. Dehmani, X. Zhao, Y. Geng, A Unified Deep Learning Ensemble Framework for Voice-Based Parkinson’s Disease Detection and Motor Severity Prediction. Bioengineering, 12(7), (2025) 699. https://doi.org/10.3390/bioengineering12070699
  28. A. Kurmi, S. Biswas, S. Sen, A. Sinitca, D. Kaplun, R. Sarkar, An Ensemble of CNN Models for Parkinson’s Disease Detection using DaTscan Images. Diagnostics, 12(5), (2022) 1173. https://doi.org/10.3390/diagnostics12051173
  29. A.O. Esan, D.B. Olawade, A.A. Soladoye, B.A. Omodunbi, I.A. Adeyanju, N. Aderinto, Explainable AI for Parkinson’s Disease Prediction: a Machine Learning Approach with Interpretable Models. Current Research in Translational Medicine, 73(4), (2025) 103541. https://doi.org/10.1016/j.retram.2025.103541
  30. S.S. Hussain, X. Degang, P.M. Shah, S.U. Islam, M. Alam, I.A. Khan, F.A. Awwad, E.A. Ismail, Classification of Parkinson’s Disease in Patch-based MRI of Substantia Nigra. Diagnostics, 13(17), (2023) 2827. https://doi.org/10.3390/diagnostics13172827