Advancing Precision Neurology and Wearable Electrophysiology: A Review on the Pivotal Role of Medical Physicists in Signal Processing, AI, and Prognostic Modeling
Abstract
1. Introduction
2. Pathophysiological Framework: Linking EPs to Neurological Disorders
3. The Expertise of Medical Physicists and Biophysicists
3.1. Precision in Measurement Techniques
3.2. Advantages and Disadvantages of Wavelet Packet Decomposition
3.3. Wavelet Packet Decomposition Implementation
Algorithm 1: Wavelet Packet Decomposition |
[ c_{j,k} = \int s(t) \psi_{j,k}(t), dt ] where (\psi_{j,k}(t)) is the wavelet function scaled and shifted at level (j) and position (k). |
[ T_j = \sigma_j \sqrt{2 \ln N_j} ] where (\sigma_j) is the sub-band variance and (N_j) is the length. Soft thresholding is applied as: [ W_{j,k} = \sign(W_{j,k}) \cdot \max(|W_{j,k}| − T_j, 0) ] Algorithm: Wavelet Packet Decomposition for EEG Denoising Input: Raw EEG signal (x(t)), sampling rate (f_s) Output: Denoised EEG signal (x_d(t)) Initialize Daubechies-4 wavelet (db4) |
|
3.4. Adaptive Noise Cancellation for ECG
Algorithm 2: Adaptive Noise Cancellation |
[ e(n) = s(n) − y(n) = s(n) − \sum_{i = 0}^{M − 1} w_i(n) r(n − i) ] Weight update using LMS algorithm: [ w_i(n + 1) = w_i(n) + \mu e(n) r(n − i) ] Algorithm: Adaptive Noise Cancellation for ECG Input: Noisy ECG (s(n)), reference noise (r(n)) Output: Clean ECG (e(n)) |
|
3.5. Uncertainty Calculations and Statistical Rigor
3.5.1. Reasons for 94.2% Accuracy in AI-Driven Arrhythmia Detection
3.5.2. Reasons for 79.2% Accuracy in ML for SCI/MS Prognosis
3.6. Computational Intelligence in Physiological Measurements
Algorithm 3: Monte Carlo Dropout |
[ p = 0.5 ] Variance (\sigma) is: [ \sigma = \frac{1}{T} \sum_{t = 1}^{T} (y_t − \bar{y})^2 ] Algorithm: Monte Carlo Dropout for EEG Uncertainty Input: EEG data (x), trained CNN (M), dropout rate (p) Output: Prediction (y), uncertainty (\sigma)
|
3.7. Federated Learning for EP-Based ML Models
Algorithm 4: CNN for Arrhythmia Detection |
model = Sequential() model.add(Conv1D(filters = 32, kernel_size = 5, activation = ‘relu’, input_shape = (128, 1))) model.add(MaxPooling1D(pool_size = 2)) model.add(Conv1D(filters = 64, kernel_size = 3, activation = ‘relu’)) model.add(MaxPooling1D(pool_size = 2)) model.add(Flatten()) model.add(Dense(128, activation = ‘relu’)) model.add(Dense(5, activation = ‘softmax’)) # 5 arrhythmia classes model.compile(optimizer = ‘adam’, loss = ‘categorical_crossentropy’, metrics = [‘accuracy’]) |
def federated_train(local_models, global_model): global_weights = global_model.get_weights() for client in clients: local_model = local_models [client] local_model.train_on_local_data() local_weights = local_model.get_weights() global_weights = aggregate_weights(global_weights, local_weights, client_weight) global_model.set_weights(global_weights) return global_model |
3.8. Explainable AI for EP-Based Models
3.9. Imaging Correlations: Complementing EPs with Structural Insights
Algorithm 5: SHAP for EP-Based ML |
Input: EP data (x), ML model (M) Output: SHAP values (\phi)
|
3.10. Role of Medical Physicists in Electrophysiological Applications
3.11. Quantum Sensors for High-Resolution EEG
4. Meta-Analysis: Methodology and Findings
Impact on Clinical Outcomes
5. Challenges and Future Directions
6. Limitations
7. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
Abbreviations
AI | Artificial Intelligence |
ASIA | American Spinal Injury Association |
AUC | Area Under the Curve |
BAEP | Brainstem Auditory Evoked Potentials |
CNN | Convolutional Neural Network |
DBS | Deep Brain Stimulation |
DT | Decision Tree |
DTI | Diffusion Tensor Imaging |
ECG | Electrocardiography |
EDSS | Expanded Disability Status Scale |
EEG | Electroencephalography |
EP | Evoked Potential |
FA | Fractional Anisotropy |
FIR | Finite Impulse Response |
GUM | Guide to the Expression of Uncertainty in Measurement |
IAEA | International Atomic Energy Agency |
IEC | International Electrotechnical Commission |
IL | Interleukin |
k-NN | k-Nearest Neighbors |
LL | Log Loss |
LSTM | Long Short-Term Memory |
MAE | Mean Absolute Error |
MAPE | Mean Absolute Percentage Error |
MCC | Matthews Correlation Coefficient |
MEP | Motor Evoked Potential |
ML | Machine Learning |
MLR | Multiple Linear Regression |
MRS | Magnetic Resonance Spectroscopy |
MS | Multiple Sclerosis |
MTI | Magnetization Transfer Imaging |
NB | Naïve Bayes |
NN | Neural Network |
NPV | Negative Predictive Value |
OCT | Optical Coherence Tomography |
PET | Positron Emission Tomography |
PPV | Positive Predictive Value |
PR | Precision–Recall |
RF | Random Forest |
RMSE | Root Mean Square Error |
RR | Relapsing-Remitting |
SCI | Spinal Cord Injury |
SHAP | SHapley Additive exPlanations |
SNR | Signal-to-Noise Ratio |
SP | Secondary Progressive |
SSEP | Somatosensory Evoked Potential |
SVM | Support Vector Machine |
TNF-α | Tumor Necrosis Factor-alpha |
VEP | Visual Evoked Potential |
WPD | Wavelet Packet Decomposition |
XAI | Explainable Artificial Intelligence |
References
- European Federation of Organisations for Medical Physics. EFOMP Policy Statement 20: Physiological Measurements and Medical Physicists. 2022. Available online: https://www.efomp.org/index.php?r=news/view&id=290 (accessed on 1 September 2024).
- Koutsojannis, C.; Chrysanthakopoulou, D. Predictive performance of machine learning with evoked potentials for SCI and MS prognosis: A meta-analysis. Clin. Transl. Neurophysiol. 2025, 9, 26. [Google Scholar] [CrossRef]
- Li, W.; Long, Y.; Yan, Y.; Sun, K.; Xu, Q. Wearable photonic smart wristband for cardiorespiratory function assessment and biometric identification. Opto-Electron. Adv. 2025, 8, 240254. [Google Scholar] [CrossRef]
- International Atomic Energy Agency. Roles and Responsibilities, and Education and Training Requirements for Clinically Qualified Medical Physicists (Human Health Series No. 25); International Atomic Energy Agency: Vienna, Austria, 2013; ISBN 978-92-0-142010-7. [Google Scholar]
- Kakulas, B.A. Neuropathology: The foundation for new treatments in spinal cord injury. Spinal Cord 2004, 42, 604–610. [Google Scholar] [CrossRef]
- Compston, A.; Coles, A. Multiple sclerosis. Lancet 2008, 372, 1502–1517. [Google Scholar] [CrossRef]
- Curt, A.; Dietz, V. Traumatic cervical spinal cord injury: Relation between somatosensory evoked potentials, neurological deficit, and hand function. Arch. Phys. Med. Rehabil. 1996, 77, 48–53. [Google Scholar] [CrossRef]
- Leocani, L.; Medaglini, S.; Comi, G. Evoked potentials in monitoring multiple sclerosis. Neurol. Sci. 2000, 21 (Suppl. 2), S889–S891. [Google Scholar] [CrossRef] [PubMed]
- Wuschek, A.; Bussas, M.; El Husseini, M.; Harabacz, L.; Pineker, V.; Pongratz, V.; Berthele, A.; Riederer, I.; Zimmer, C.; Hemmer, B.; et al. Somatosensory evoked potentials and magnetic resonance imaging of the central nervous system in early multiple sclerosis. J. Neurol. 2023, 270, 824–830. [Google Scholar] [CrossRef]
- European Federation of Organisations for Medical Physics. What Is Medical Physics? (n.d.) Available online: https://www.efomp.org/index.php?r=pages&id=public (accessed on 1 June 2025).
- Chen, W.; Jaques, N.; Taylor, S.; Sano, A.; Fedor, S.; Picard, R.W. Wavelet-based motion artifact removal for electrodermal activity. In Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy, 25–29 August 2015; Volume 2015, pp. 6223–6226. [Google Scholar] [CrossRef]
- Norton, J.J.S.; Lee, D.S.; Lee, J.W.; Lee, W.; Kwon, O.; Won, P.; Jung, S.-Y.; Cheng, H.; Jeong, J.-W.; Akce, A.; et al. Soft, curved electrode systems capable of integration on the auricle as a persistent brain–computer interface. Proc. Natl. Acad. Sci. USA 2015, 112, 3920–3925. [Google Scholar] [CrossRef]
- Ravì, D.; Wong, C.; Deligianni, F.; Berthelot, M.; Andreu-Perez, J.; Lo, B. Deep learning for health informatics. IEEE J. Biomed. Health Inform. 2016, 21, 4–21. [Google Scholar] [CrossRef]
- IEC 60601-2-47; Medical Electrical Equipment—Part 2-47: Wearable Cardiac Monitors. International Electrotechnical Commission: Geneva, Switzerland, 2021; ISBN 978-288-912-911-9.
- Elshekhidris, I.H.; MohamedAmien, M.B.; Fragoon, A. Wavelet transforms for EEG signal denoising and decomposition. Int. J. Adv. Signal Image Sci. 2023, 9, 11–28. [Google Scholar] [CrossRef]
- Guo, T.; Zhang, T.; Lim, E.; Lopez-Benitez, M.; Ma, F.; Yu, L. A review of wavelet analysis and its applications: Challenges and opportunities. IEEE Access 2022, 10, 58869–58903. [Google Scholar] [CrossRef]
- Nikesh, B. Wavelets for EEG Analysis. 2020. Available online: https://www.intechopen.com/chapters/74032 (accessed on 2 September 2025).
- Grobbelaar, M.; Phadikar, S.; Ghaderpour, E.; Struck, A.F.; Sinha, N.; Ghosh, R.; Ahmed, M.Z.I. A Survey on Denoising Techniques of Electroencephalogram Signals Using Wavelet Transform. Signals 2022, 3, 577–586. [Google Scholar] [CrossRef]
- Singh, A.K.; Krishnan, S. ECG Signal feature extraction trends in methods and applications. Biomed. Eng. Online 2023, 22, 22. [Google Scholar] [CrossRef]
- Noro, M.; Anzai, D.; Wang, J. Common-mode noise cancellation circuit for wearable ECG. Healthc. Technol. Lett. 2017, 4, 2053–3713. [Google Scholar] [CrossRef]
- Peeters, M.; Yperman, J.; Becker, T.; Valkenborg, D.; Popescu, V.; Van Wijmeersch, B.; Hellings, N. Machine learning analysis of motor evoked potential time series to predict disability progression in multiple sclerosis. BMC Neurol. 2020, 20, 105. [Google Scholar] [CrossRef]
- Jain, A.; Raja, R.; Kumar, M. A novel classification of meditation techniques via optimized chi-squared 1D-CNN method based on complexity, continuity and connectivity features. Connect. Sci. 2025, 37, 2467387. [Google Scholar] [CrossRef]
- Seccia, R.; Romano, S.; Salvetti, M.; Crisanti, A.; Palagi, L.; Grassi, F. Machine Learning Use for Prognostic Purposes in Multiple Sclerosis. Life 2021, 11, 122. [Google Scholar] [CrossRef]
- Cui, H.; Wang, Y.; Li, G.; Huang, Y.; Hu, Y. Exploration of Cervical Myelopathy Location from Somatosensory Evoked Potentials Using Random Forests Classification. IEEE Trans. Neural Syst. Rehabil. Eng. 2019, 27, 2254–2262. [Google Scholar] [CrossRef]
- Perez, M.V.; Mahaffey, K.W.; Hedlin, H.; Rumsfeld, J.S.; Garcia, A.; Ferris, T. Large-scale assessment of a smartwatch to detect atrial fibrillation. N. Engl. J. Med. 2019, 381, 1909–1917. [Google Scholar] [CrossRef]
- Bentes, C.; Martins, H.; Peralta, A.R.; Morgado, C.; Casimiro, C.; Franco, A.C.; Fonseca, A.C.; Geraldes, R.; Canhão, P.; Pinho, E.; et al. Early EEG predicts poststroke epilepsy. Epilepsia Open 2018, 3, 203–212. [Google Scholar] [CrossRef] [PubMed]
- JCGM. Evaluation of Measurement Data—Guide to the Expression of Uncertainty in Measurement (GUM); JCGM: Sèvres, France, 2008. [Google Scholar] [CrossRef]
- International Atomic Energy Agency. Medical Physics. In Human Health Campus; International Atomic Energy Agency: Vienna, Austria, 2022; Available online: https://www.iaea.org/resources/hhc/medical-physics (accessed on 1 May 2025).
- IEC 60601-2-26:2012; Medical Electrical Equipment—Part 2-26: Particular Requirements for the Basic Safety and Essential Performance of Electroencephalographs. Available online: https://webstore.iec.ch/en/publication/2637 (accessed on 2 September 2025).
- Maki, S.; Furuya, T.; Katsumi, K.; Nakajima, H.; Honjoh, K.; Watanabe, S.; Kaito, T.; Takenaka, S.; Kanie, Y.; Iwasaki, M.; et al. Multimodal Deep Learning-based Radiomics Approach for Predicting Surgical Outcomes in Patients with Cervical Ossification of the Posterior Longitudinal Ligament. Spine 2024, 49, 1561–1569. [Google Scholar] [CrossRef] [PubMed]
- Beniczky, S.; Trinka, E.; Wirrell, E.; Abdulla, F.; Al Baradie, R.; Vanegas, M.A.; Auvin, S.; Singh, M.B.; Blumenfeld, H.; Fressola, A.B.; et al. Updated classification of epileptic seizures: Position paper of the International League Against Epilepsy. Epilepsia 2025, 23, 1804–1823. [Google Scholar] [CrossRef]
- Szynal, M.; Kowalewski, M.; Napierala, M. Correlation of somatosensory evoked potentials with magnetic resonance imaging in spinal cord injuries. J. Neurotrauma 2020, 37, 1421–1428. [Google Scholar] [CrossRef]
- Caruana, C.J.; Tsapaki, V.; Damilakis, J.; Brambilla, M.; Martín, G.M.; Dimov, A.; Bosmans, H.; Egan, G.; Bacher, K.; McClean, B. EFOMP policy statement 16: The role and competences of medical physicists and medical physics experts under 2013/59/EURATOM. Phys. Medica 2018, 48, 162–168. [Google Scholar] [CrossRef]
- Rieke, N.; Hancox, J.; Li, W.; Milletari, F.; Roth, H.R.; Albarqouni, S. The future of digital health with federated learning. Npj Digit. Med. 2020, 3, 119. [Google Scholar] [CrossRef] [PubMed]
- Chrysanthakopoulou, D.; Matzaroglou, C.; Trachani, E.; Koutsojannis, C. Machine Learning Introduces Electrophysiology Assessment as the Best Predictor for the Recovery Prognosis of Spinal Cord Injury Patients for Personalized Rehabilitation Approaches. Appl. Sci. 2025, 15, 4578. [Google Scholar] [CrossRef]
- Lundberg, S.M.; Erion, G.; Lee, S.I. A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 2020, 33, 4765–4774. [Google Scholar] [CrossRef]
- Zhao, Y.; Healy, B.C.; Rotstein, D.; Guttmann, C.R.; Bakshi, R.; Weiner, H.L.; Brodley, C.E.; Chitnis, T. Exploration of machine learning techniques in predicting multiple sclerosis disease course. PLoS ONE 2017, 12, e0174866. [Google Scholar] [CrossRef]
- IOMP. What Is Medical Physics. Available online: https://www.iomp.org/medical-physics/ (accessed on 1 June 2025).
- Tai, C.-H.; Chou, S.-C.; Lin, Y.-C.; Wu, R.-M.; Hsieh, C.-J.; Tseng, S.-H. The responses of subthalamic beta oscillations during voluntary movement in patients with Parkinson’s disease. Deep Brain Stimul. 2025, 8, 6–13. [Google Scholar] [CrossRef]
- Espay, A.J.; Bonato, P.; Nahab, F.B.; Maetzler, W.; Dean, J.M.; Klucken, J. Technology in Parkinson’s disease: Challenges and opportunities. Mov. Disord. 2018, 33, 307–316. [Google Scholar] [CrossRef]
- Su Yoo, H.-J.; Lee, K.-S.; Koo, B.; Yong, C.-W.; Kim, C.-W. Deep Learning-Based Prediction Model for Gait Recovery after a Spinal Cord Injury. Diagnostics 2024, 14, 579. [Google Scholar] [CrossRef]
- FDA-NIH Biomarker Working Group. Qualification of Digital Motor Biomarkers for Parkinson’s Disease Trials [White Paper]; Food and Drug Administration: Rockville, MD, US, 2022; Available online: https://www.ema.europa.eu/en/documents/regulatory-procedural-guideline/qualification-opinion-dopamine-transporter-imaging-enrichment-biomarker-parkinsons-disease-clinical-trials-patients-early-parkinsonian-symptoms_en.pdf (accessed on 20 May 2025).
- Pazzaglia, C.; Valeriani, M. Brain-evoked potentials as a tool for diagnosing neuropathic pain. Expert Rev. Neurother. 2009, 9, 759–771. [Google Scholar] [CrossRef]
- Barry, J.F.; Schloss, J.M.; Bauch, E.; Turner, M.J.; Hart, C.A.; Pham, L.M.; Walsworth, R.L. Sensitivity optimization for NV-diamond magnetometry. Rev. Mod. Phys. 2020, 92, 015004. [Google Scholar] [CrossRef]
- Boto, E.; Holmes, N.; Leggett, J.; Roberts, G.; Shah, V.; Meyer, S.S.; Muñoz, L.D.; Mullinger, K.J.; Tierney, T.M.; Bestmann, S.; et al. Moving magnetoencephalography towards real-world applications with a wearable system. Nature 2018, 555, 657–661. [Google Scholar] [CrossRef] [PubMed]
- Mishra, B.; Fatima, S.; Agarwal, A.; Radhakrishnan, D.M.; Garg, A.; Srivastava, A.K. Dystonia and Myelopathy in a Case of Stress-Induced Childhood-Onset Neurodegeneration with Ataxia and Seizures (CONDSIAS). Mov. Disord. Clin. Pract. 2021, 8, 156–158. [Google Scholar] [CrossRef]
- Small, S.L. Precision neurology. Ageing Res. Rev. 2025, 104, 102632. [Google Scholar] [CrossRef]
- Koulouris, S.; Cascella, M. Electrophysiologic study interpretation. In StatPearls; StatPearls Publishing: Treasure Island, FL, USA, 2024. [Google Scholar]
Study | Population | EP Type | ML Model | Outcome | Accuracy (%) | AUC |
---|---|---|---|---|---|---|
[2] | MS, n = 125 | SSEP | Random Forest | EDSS progression | 75.0 (70.2–79.8) | 0.78 (0.73–0.83) |
[2] | SCI, n = 123 | SSEP | Random Forest | ASIA recovery | 83.0 (78.4–87.6) | 0.87 (0.83–0.91) |
[21] | MS, n = 80 | MEP | Random Forest | EDSS progression | 70.0 (64.8–75.2) | 0.75 (0.70–0.80) |
[24] | SCI, n = 32 | SSEP | Random Forest | Injury location | 84.7 (79.9–89.5) | 0.85 (0.80–0.90) |
[41] | SCI, n = 80 | SSEP | Deep Learning | ASIA recovery | 81.2 (76.0–86.4) | 0.83 (0.79–0.87) |
[23] | MS, n = 740 | Clinical/MEP | Neural Network | RR-to-SP conversion | 98.0 (95.0–99.0) | 0.98 (0.95–0.99) |
[6] | MS, n = 500 | MRI/EP | CNN | EDSS > 3 | 85.0 (80.0–90.0) | 0.89 (0.85–0.93) |
Feature | Importance (Mean ± SD) | Application |
---|---|---|
SSEP Latency | 0.42 ± 0.08 | SCI/MS prognosis |
MEP Time Series | 0.35 ± 0.06 | SCI/MS prognosis |
SSEP Amplitude | 0.18 ± 0.04 | SCI prognosis |
MRI Fractional Anisotropy | 0.05 ± 0.02 | SCI prognosis |
Source | I2 (%) | Impact |
---|---|---|
EP Type (SSEP vs. MEP) | 58 | Moderate |
ML Model Type | 62 | High |
Sample Size | 56 | Moderate |
Scenario | Condition | Description |
---|---|---|
1 | Spinal Cord Injury | A 35-year-old with a C6 incomplete injury undergoes SSEP assessment. An ML model predicts 83% likelihood of ASIA score improvement, guiding intensive physiotherapy and transcranial stimulation [35]. |
2 | Multiple Sclerosis | A 42-year-old with relapsing–remitting MS shows prolonged SSEP latency. An ML model predicts 70% probability of EDSS worsening, prompting early ozanimod initiation [21] |
3 | Epilepsy | A 27-year-old with focal epilepsy uses a wearable EEG, detecting 41% more spikes, refining surgical planning [31]. |
4 | Cardiac | A 60-year-old with suspected atrial fibrillation uses a wearable ECG with edge-AI, achieving 94.2% accuracy, enabling timely anticoagulation [25]. |
5 | Stroke Monitoring | A 55-year-old post-stroke patient uses wearable EEG with AI, detecting epileptiform activity (80% sensitivity), guiding levetiracetam therapy to prevent seizures [26]. |
6 | Atrial Fibrillation in Elderly | An 83-year-old frail patient uses a wearable ECG for 72 h monitoring, with edge-AI detecting paroxysmal atrial fibrillation (92% specificity), supporting apixaban initiation [25]. |
7 | Chronic Pain in SCI | A 40-year-old with SCI undergoes SSEP testing. An ML model predicts 75% likelihood of neuropathic pain, recommending spinal cord stimulation [43]. |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Koutsojannis, C.; Fouras, A.; Chrysanthakopoulou, D. Advancing Precision Neurology and Wearable Electrophysiology: A Review on the Pivotal Role of Medical Physicists in Signal Processing, AI, and Prognostic Modeling. Biophysica 2025, 5, 40. https://doi.org/10.3390/biophysica5030040
Koutsojannis C, Fouras A, Chrysanthakopoulou D. Advancing Precision Neurology and Wearable Electrophysiology: A Review on the Pivotal Role of Medical Physicists in Signal Processing, AI, and Prognostic Modeling. Biophysica. 2025; 5(3):40. https://doi.org/10.3390/biophysica5030040
Chicago/Turabian StyleKoutsojannis, Constantinos, Athanasios Fouras, and Dionysia Chrysanthakopoulou. 2025. "Advancing Precision Neurology and Wearable Electrophysiology: A Review on the Pivotal Role of Medical Physicists in Signal Processing, AI, and Prognostic Modeling" Biophysica 5, no. 3: 40. https://doi.org/10.3390/biophysica5030040
APA StyleKoutsojannis, C., Fouras, A., & Chrysanthakopoulou, D. (2025). Advancing Precision Neurology and Wearable Electrophysiology: A Review on the Pivotal Role of Medical Physicists in Signal Processing, AI, and Prognostic Modeling. Biophysica, 5(3), 40. https://doi.org/10.3390/biophysica5030040