Artificial intelligence and machine learning | applications in musculoskeletal physiotherapy.

INTRODUCTION Artificial intelligence (AI) is a field of mathematical engineering which has potential to enhance healthcare through new care delivery strategies, informed decision making and facilitation of patient engagement. Machine learning (ML) is a form of narrow artificial intelligence which can be used to automate decision making and make predictions based upon patient data. PURPOSE This review outlines key applications of supervised and unsupervised machine learning in musculoskeletal medicine; such as diagnostic imaging, patient measurement data, and clinical decision support. The current literature base is examined to identify areas where ML performs equal to or more accurately than human levels. IMPLICATIONS Potential is apparent for intelligent machines to enhance various areas of physiotherapy practice through automization of tasks which involve data analysis, classification and prediction. Changes to service provision through applications of ML, should encourage physiotherapists to increase their awareness of and experiences with emerging technologies. Data literacy should be a component of professional development plans to assist physiotherapists in the application of ML and the preparation of information technology systems to use these techniques.

[1]  Andrew Zisserman,et al.  ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist , 2017, European Spine Journal.

[2]  S. Mackey,et al.  Central neuroimaging of pain. , 2013, The journal of pain : official journal of the American Pain Society.

[3]  B. Beynnon,et al.  Risk factors for lower extremity injury: a review of the literature , 2003, British journal of sports medicine.

[4]  Emeran A. Mayer,et al.  Preliminary structural MRI based brain classification of chronic pelvic pain: A MAPP network study , 2014, PAIN®.

[5]  C. Krittanawong,et al.  The rise of artificial intelligence and the uncertain future for physicians. , 2017, European journal of internal medicine.

[6]  Rezvan Kianifar,et al.  Automated Assessment of Dynamic Knee Valgus and Risk of Knee Injury During the Single Leg Squat , 2017, IEEE Journal of Translational Engineering in Health and Medicine.

[7]  Ricky Mullis,et al.  A primary care back pain screening tool: identifying patient subgroups for initial treatment. , 2008, Arthritis and rheumatism.

[8]  Hermie Hermens,et al.  Design of a Web-based Clinical Decision Support System for Guiding Patients with Low Back Pain to the Best Next Step in Primary Healthcare , 2016, HEALTHINF.

[9]  Roland Staud,et al.  Biomarkers for Musculoskeletal Pain Conditions: Use of Brain Imaging and Machine Learning , 2017, Current Rheumatology Reports.

[10]  Kirsten Jack,et al.  Barriers to treatment adherence in physiotherapy outpatient clinics: A systematic review , 2010, Manual therapy.

[11]  A. Watson.  Impact of the Digital Age on Transforming Healthcare , 2016 .

[12]  R. Marx,et al.  Effectiveness of physical therapy in treating atraumatic full-thickness rotator cuff tears: a multicenter prospective cohort study. , 2013, Journal of shoulder and elbow surgery.

[13]  Tor D. Wager,et al.  Towards a neurophysiological signature for fibromyalgia , 2017, Pain.

[14]  Mary K Obenshain.  Application of Data Mining Techniques to Healthcare Data , 2004, Infection Control & Hospital Epidemiology.

[15]  Stan Franklin,et al.  A Foundational Architecture for Artificial General Intelligence , 2007, AGI.

[16]  A. Razavian,et al.  Artificial intelligence for analyzing orthopedic trauma radiographs , 2017, Acta orthopaedica.

[17]  Chronic Pain Challenge: A Statistical Machine-learning Method for Chronic Pain Assessment , 2016 .

[18]  Matthew P Buman,et al.  Wearable Technology and Physical Activity in Chronic Disease: Opportunities and Challenges. , 2018, American journal of preventive medicine.

[19]  Kevin A. Johnson,et al.  Multivariate classification of structural MRI data detects chronic low back pain. , 2014, Cerebral cortex.

[20]  K. Luk,et al.  A Machine Learning-based Surface Electromyography Topography Evaluation for Prognostic Prediction of Functional Restoration Rehabilitation in Chronic Low Back Pain , 2017, Spine.

[21]  E. Shortliffe.  Clinical decision-support systems , 1990 .

[22]  Daniel Callan,et al.  A Tool for Classifying Individuals with Chronic Back Pain: Using Multivariate Pattern Analysis with Functional Magnetic Resonance Imaging Data , 2014, PloS one.

[23]  Alfred Ultsch,et al.  Machine learning in pain research , 2017, Pain.

[24]  Will intelligent machine learning revolutionize orthopedic imaging? , 2017, Acta orthopaedica.

[25]  P. Croft,et al.  Prevalence of chronic pain in the UK: a systematic review and meta-analysis of population studies , 2016, BMJ Open.

[26]  J. Boissoneault,et al.  (337) MRI based classification of chronic fatigue, fibromyalgia patients and healthy controls using machine learning algorithms: a comparison study. , 2016, The journal of pain : official journal of the American Pain Society.

[27]  Muhammad Imran Razzak,et al.  Deep Learning for Medical Image Processing: Overview, Challenges and Future , 2017, ArXiv.

[28]  J. Kvedar,et al.  Artificial intelligence powers digital medicine , 2018, npj Digital Medicine.

[29]  Patrick Henry,et al.  Shoulder physiotherapy exercise recognition: machine learning the inertial signals from a smartwatch , 2018, Physiological measurement.

[30]  L. Becerra,et al.  Phenotyping central nervous system circuitry in chronic pain using functional MRI: Considerations and potential implications in the clinic , 2007, Current pain and headache reports.

[31]  I. Goldberg,et al.  Predicting early symptomatic osteoarthritis in the human knee using machine learning classification of magnetic resonance images from the osteoarthritis initiative , 2017, Journal of orthopaedic research : official publication of the Orthopaedic Research Society.

[32]  Catharina G. M. Groothuis-Oudshoorn,et al.  Evaluation of three machine learning models for self-referral decision support on low back pain in primary care , 2018, Int. J. Medical Informatics.

[33]  R. Cowen,et al.  Assessing pain objectively: the use of physiological markers , 2015, Anaesthesia.

[34]  Elissa J Chesler,et al.  Identification and ranking of genetic and laboratory environment factors influencing a behavioral trait, thermal nociception, via computational analysis of a large data archive , 2002, Neuroscience & Biobehavioral Reviews.

[35]  Carlo Combi,et al.  Thirty years of artificial intelligence in medicine (AIME) conferences: A review of research themes , 2015, Artif. Intell. Medicine.

[36]  Ralf Baron,et al.  Deconstructing the Neuropathic Pain Phenotype to Reveal Neural Mechanisms , 2012, Neuron.

[37]  M. Pandy,et al.  Are Knee Biomechanics Different in Those With and Without Patellofemoral Osteoarthritis After Anterior Cruciate Ligament Reconstruction? , 2014, Arthritis care & research.

[38]  Paul Fergus,et al.  Evaluation of machine learning methods to predict knee loading from the movement of body segments , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[39]  Martin Descarreaux,et al.  Chronic low back pain clinical outcomes present higher associations with the STarT Back Screening Tool than with physiologic measures: a 12-month cohort study , 2015, BMC Musculoskeletal Disorders.

[40]  Iain E. Buchan,et al.  Clinical code set engineering for reusing EHR data for research: A review , 2017, AMIA.

[41]  Roland Staud,et al.  Comparison of machine classification algorithms for fibromyalgia: neuroimages versus self-report. , 2015, The journal of pain : official journal of the American Pain Society.

[42]  Sionnadh McLean,et al.  Recommendations for exercise adherence measures in musculoskeletal settings: a systematic review and consensus meeting (protocol) , 2014, Systematic Reviews.

[43]  Jacob D. Furst,et al.  Identifying Defining Aspects of Chronic Fatigue Syndrome via Unsupervised Machine Learning and Feature Selection , 2014 .