Artificial neural networks in neurorehabilitation: A scoping review

BACKGROUND: Advances in medical technology produce highly complex datasets in neurorehabilitation clinics and research laboratories. Artificial neural networks (ANNs) have been utilized to analyze big and complex datasets in various fields, but the use of ANNs in neurorehabilitation is limited. OBJECTIVE: To explore the current use of ANNs in neurorehabilitation. METHODS: PubMed, CINAHL, and Web of Science were used for literature search. Studies in the scoping review (1) utilized ANNs, (2) examined populations with neurological conditions, and (3) focused rehabilitation outcomes. The initial search identified 1,136 articles. A total of 19 articles were included. RESULTS: ANNs were used for prediction of functional outcomes and mortality (n = 11) and classification of motor symptoms and cognitive status (n = 8). Most ANN-based models outperformed regression or other machine learning models (n = 11) and showed accurate performance (n = 6; no comparison with other models) in predicting clinical outcomes and accurately classifying different neurological impairments. CONCLUSIONS: This scoping review provides encouraging evidence to use ANNs for clinical decision-making of complex datasets in neurorehabilitation. However, more research is needed to establish the clinical utility of ANNs in diagnosing, monitoring, and rehabilitation of individuals with neurological conditions.

[1]  C. Gielen,et al.  Detection and assessment of the severity of Levodopa‐induced dyskinesia in patients with Parkinson's disease by neural networks , 2000, Movement disorders : official journal of the Movement Disorder Society.

[2]  K Ann McKibbon,et al.  Health Information Technology to Facilitate Communication Involving Health Care Providers, Caregivers, and Pediatric Patients: A Scoping Review , 2010, Journal of medical Internet research.

[3]  Josh Bongard,et al.  C L I N I C a L a R T I C L E , 2022 .

[4]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[5]  Richard Goldstein,et al.  The Accuracy of Artificial Neural Networks in Predicting Long‐term Outcome After Traumatic Brain Injury , 2006, The Journal of head trauma rehabilitation.

[6]  Christophe Lemetre,et al.  An introduction to artificial neural networks in bioinformatics - application to complex microarray and mass spectrometry datasets in cancer studies , 2008, Briefings Bioinform..

[7]  L. Wishart,et al.  The Application of Motor Learning Strategies Within Functionally Based Interventions for Children with Neuromotor Conditions , 2009, Pediatric physical therapy : the official publication of the Section on Pediatrics of the American Physical Therapy Association.

[8]  L. Ohno-Machado,et al.  Neural network applications in physical medicine and rehabilitation. , 1999, American journal of physical medicine & rehabilitation.

[9]  Moncef Gabbouj,et al.  Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.

[10]  M. Salgueiro,et al.  An artificial neural network approach for predicting functional outcome in fibromyalgia syndrome after multidisciplinary pain program. , 2013, Pain medicine.

[11]  D. Levac,et al.  Scoping studies: advancing the methodology , 2010, Implementation science : IS.

[12]  Alfredo Robles,et al.  Using artificial neural networks in clinical neuropsychology: High performance in mild cognitive impairment and Alzheimer's disease , 2012, Journal of clinical and experimental neuropsychology.

[13]  K. Kaczmarczyk,et al.  Gait classification in post-stroke patients using artificial neural networks. , 2009, Gait & posture.

[14]  Anders Larsson,et al.  Global, regional, and national burden of neurological disorders during 1990–2015: a systematic analysis for the Global Burden of Disease Study 2015 , 2017, The Lancet Neurology.

[15]  Jacek Tabor,et al.  Processing of missing data by neural networks , 2018, NeurIPS.

[16]  H. Arksey,et al.  Scoping studies: towards a methodological framework , 2005 .

[17]  Eyal Oren,et al.  Global, regional, and national burden of neurological disorders, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016 , 2017, The Lancet. Neurology.

[18]  Alberto Landi,et al.  Artificial Neural Networks for nonlinear regression and classification , 2010, 2010 10th International Conference on Intelligent Systems Design and Applications.

[19]  W. Oczkowski,et al.  Neural network modeling accurately predicts the functional outcome of stroke survivors with moderate disabilities. , 1997, Archives of physical medicine and rehabilitation.

[20]  Jui-Chang Tsai,et al.  Predicting Long-Term Outcome After Traumatic Brain Injury Using Repeated Measurements of Glasgow Coma Scale and Data Mining Methods , 2015, Journal of Medical Systems.

[21]  Louise Robinson,et al.  Dementia: timely diagnosis and early intervention , 2015, BMJ : British Medical Journal.

[22]  David Mascharka,et al.  Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Ivan Nunes da Silva,et al.  Artificial Neural Network Architectures and Training Processes , 2017 .

[24]  C. Donnelly,et al.  Models for integrating rehabilitation and primary care: a scoping study. , 2009, Archives of physical medicine and rehabilitation.

[25]  J. Cameron,et al.  Optimizing Stroke Systems of Care by Enhancing Transitions Across Care Environments , 2008, Stroke.

[26]  S. Gielen,et al.  Automatic assessment of levodopa‐induced dyskinesias in daily life by neural networks , 2003, Movement disorders : official journal of the Movement Disorder Society.

[27]  Ivan Nunes da Silva,et al.  Artificial Neural Networks , 2017 .

[28]  Hossam M. Hammady,et al.  Rayyan—a web and mobile app for systematic reviews , 2016, Systematic Reviews.

[29]  Julian D. Olden,et al.  Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks , 2002 .

[30]  C Scheffer,et al.  Inertial motion capture in conjunction with an artificial neural network can differentiate the gait patterns of hemiparetic stroke patients compared with able-bodied counterparts , 2012, Computer methods in biomechanics and biomedical engineering.

[31]  A. Cieza,et al.  The International Classification of Functioning, Disability and Health (ICF): a unifying model for the conceptual description of the rehabilitation strategy. , 2007, Journal of rehabilitation medicine.

[32]  Chun-An Cheng,et al.  Prediction of the Prognosis of Ischemic Stroke Patients after Intravenous Thrombolysis Using Artificial Neural Networks , 2014, ICIMTH.

[33]  Todd C. Hollon,et al.  Rapid intraoperative histology of unprocessed surgical specimens via fibre-laser-based stimulated Raman scattering microscopy , 2017, Nature Biomedical Engineering.

[34]  Bethlyn Houlihan,et al.  Developing Artificial Neural Network Models to Predict Functioning One Year After Traumatic Spinal Cord Injury. , 2016, Archives of physical medicine and rehabilitation.

[35]  J. McGowan,et al.  PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation , 2018, Annals of Internal Medicine.

[36]  Saeedeh Pourahmad,et al.  Identifying Important Attributes for Prognostic Prediction in Traumatic Brain Injury Patients , 2016, Methods of Information in Medicine.

[37]  S. Sonoda,et al.  Changes in impairment and disability from the third to the sixth month after stroke and its relationship evaluated by an artificial neural network. , 1997, American journal of physical medicine & rehabilitation.

[38]  Barbara Homann,et al.  The impact of neurological disorders on the risk for falls in the community dwelling elderly: a case-controlled study , 2013, BMJ Open.

[39]  Etienne E. Pracht,et al.  The burden of neurological disease in the United States: A summary report and call to action , 2017, Annals of neurology.

[40]  F. Cheriet,et al.  Deep feature learning for automatic tissue classification of coronary artery using optical coherence tomography. , 2017, Biomedical optics express.

[41]  Nida Shahid,et al.  Applications of artificial neural networks in health care organizational decision-making: A scoping review , 2019, PloS one.

[42]  N. Jetté,et al.  The international incidence and prevalence of neurologic conditions , 2014, Neurology.

[43]  Hon-Yi Shi,et al.  In-hospital mortality after traumatic brain injury surgery: a nationwide population-based comparison of mortality predictors used in artificial neural network and logistic regression models. , 2013, Journal of neurosurgery.

[44]  Ahmed Hosny,et al.  Artificial intelligence in radiology , 2018, Nature Reviews Cancer.

[45]  Alan D. Lopez,et al.  The Global Burden of Disease Study , 2003 .

[46]  Peter K. Sharpe,et al.  Dealing with missing values in neural network-based diagnostic systems , 1995, Neural Computing & Applications.

[47]  P Lukowicz,et al.  Wearable Systems for Health Care Applications , 2004, Methods of Information in Medicine.

[48]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[49]  K J Ottenbacher,et al.  Comparison of logistic regression and neural networks to predict rehospitalization in patients with stroke. , 2001, Journal of clinical epidemiology.

[50]  K. Lyons,et al.  Assessment of the effects of subthalamic stimulation in Parkinson disease patients by artificial neural network , 2008, Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[51]  Paulo J. G. Lisboa,et al.  A review of evidence of health benefit from artificial neural networks in medical intervention , 2002, Neural Networks.

[52]  T. Helbich,et al.  Stand-Alone Artificial Intelligence for Breast Cancer Detection in Mammography: Comparison With 101 Radiologists. , 2019, Journal of the National Cancer Institute.

[53]  Ameet Talwalkar,et al.  Foundations of Machine Learning , 2012, Adaptive computation and machine learning.

[54]  Carmelo J. A. Bastos Filho,et al.  Using artificial neural networks to select the parameters for the prognostic of mild cognitive impairment and dementia in elderly individuals , 2017, Comput. Methods Programs Biomed..

[55]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[56]  Achille Fokoue,et al.  An effective algorithm for hyperparameter optimization of neural networks , 2017, IBM J. Res. Dev..

[57]  Ahmad Ihsan Mohd Yassin,et al.  Statistical analysis of parkinson disease gait classification using Artificial Neural Network , 2011, 2011 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).