Use of machine learning in osteoarthritis research: a systematic literature review

Objective The aim of this systematic literature review was to provide a comprehensive and exhaustive overview of the use of machine learning (ML) in the clinical care of osteoarthritis (OA). Methods A systematic literature review was performed in July 2021 using MEDLINE PubMed with key words and MeSH terms. For each selected article, the number of patients, ML algorithms used, type of data analysed, validation methods and data availability were collected. Results From 1148 screened articles, 46 were selected and analysed; most were published after 2017. Twelve articles were related to diagnosis, 7 to prediction, 4 to phenotyping, 12 to severity and 11 to progression. The number of patients included ranged from 18 to 5749. Overall, 35% of the articles described the use of deep learning And 74% imaging analyses. A total of 85% of the articles involved knee OA and 15% hip OA. No study investigated hand OA. Most of the studies involved the same cohort, with data from the OA initiative described in 46% of the articles and the MOST and Cohort Hip and Cohort Knee cohorts in 11% and 7%. Data and source codes were described as publicly available respectively in 54% and 22% of the articles. External validation was provided in only 7% of the articles. Conclusion This review proposes an up-to-date overview of ML approaches used in clinical OA research and will help to enhance its application in this field.

[1]  Yasunobu Nohara,et al.  Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospital , 2021, Comput. Methods Programs Biomed..

[2]  Anubhav Jain,et al.  Best practices in machine learning for chemistry , 2021, Nature Chemistry.

[3]  Matthew B. A. McDermott,et al.  Reproducibility in machine learning for health research: Still a ways to go , 2021, Science Translational Medicine.

[4]  Albert Swiecicki,et al.  Deep learning-based algorithm for assessment of knee osteoarthritis severity in radiographs matches performance of radiologists , 2021, Comput. Biol. Medicine.

[5]  Iqbal H. Sarker.  Machine Learning: Algorithms, Real-World Applications and Research Directions , 2021, SN Computer Science.

[6]  M. Dougados,et al.  The DIGICOD cohort: a hospital-based observational prospective cohort of patients with hand osteoarthritis - methodology and baseline characteristics of the population. , 2021, Joint bone spine.

[7]  Ali Mobasheri,et al.  The future of deep phenotyping in osteoarthritis: How can high throughput omics technologies advance our understanding of the cellular and molecular taxonomy of the disease? , 2021, Osteoarthritis and cartilage open.

[8]  I. Scott,et al.  Clinician checklist for assessing suitability of machine learning applications in healthcare , 2021, BMJ Health & Care Informatics.

[9]  Sotiris Kotsiantis,et al.  Explainable AI: A Review of Machine Learning Interpretability Methods , 2020, Entropy.

[10]  Research, reuse, repeat , 2020, Nature Machine Intelligence.

[11]  Pauline Mouches,et al.  Supervised machine learning tools: a tutorial for clinicians , 2020, Journal of neural engineering.

[12]  Y. Ku,et al.  A machine learning-based diagnostic model associated with knee osteoarthritis severity , 2020, Scientific Reports.

[13]  Shadpour Demehri,et al.  Enabling early detection of osteoarthritis from presymptomatic cartilage texture maps via transport-based learning , 2020, Proceedings of the National Academy of Sciences.

[14]  Cecilia S Lee,et al.  Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension , 2020, Nature Medicine.

[15]  A. Mobasheri,et al.  Cohort profile: The Applied Public-Private Research enabling OsteoArthritis Clinical Headway (IMI-APPROACH) study: a 2-year, European, cohort study to describe, validate and predict phenotypes of osteoarthritis using clinical, imaging and biochemical markers , 2020, BMJ Open.

[16]  Adam Bohr,et al.  The rise of artificial intelligence in healthcare applications , 2020, Artificial Intelligence in Healthcare.

[17]  Krzysztof J. Geras,et al.  Prediction of Total Knee Replacement and Diagnosis of Osteoarthritis by Using Deep Learning on Knee Radiographs: Data from the Osteoarthritis Initiative. , 2020, Radiology.

[18]  J. Pelletier,et al.  Serum adipokines/related inflammatory factors and ratios as predictors of infrapatellar fat pad volume in osteoarthritis: Applying comprehensive machine learning approaches , 2020, Scientific Reports.

[19]  Giannis Giakas,et al.  Machine learning in knee osteoarthritis: A review , 2020, Osteoarthritis and cartilage open.

[20]  Matthew R. Neville,et al.  Can a Convolutional Neural Network Classify Knee Osteoarthritis on Plain Radiographs as Accurately as Fellowship-Trained Knee Arthroplasty Surgeons? , 2020, The Journal of arthroplasty.

[21]  Y. Bilgili,et al.  Detection of hip osteoarthritis by using plain pelvic radiographs with deep learning methods , 2020, Skeletal Radiology.

[22]  Valentina Pedoia,et al.  Machine Learning and Artificial Intelligence , 2020, Osteoarthritis and Cartilage.

[23]  Matthew B. Blaschko,et al.  Semixup: In- and Out-of-Manifold Regularization for Deep Semi-Supervised Knee Osteoarthritis Severity Grading From Plain Radiographs , 2020, IEEE Transactions on Medical Imaging.

[24]  Sharmila Majumdar,et al.  Deep Learning Predicts Total Knee Replacement from Magnetic Resonance Images , 2020, Scientific Reports.

[25]  J. Boedecker,et al.  Applied machine learning and artificial intelligence in rheumatology , 2020, Rheumatology advances in practice.

[26]  J. H. Sohn,et al.  Development and Validation of a Multitask Deep Learning Model for Severity Grading of Hip Osteoarthritis Features on Radiographs. , 2020, Radiology.

[27]  Viktor E. Krebs,et al.  Machine Learning and Artificial Intelligence: Definitions, Applications, and Future Directions , 2020, Current Reviews in Musculoskeletal Medicine.

[28]  Jianxu Luo,et al.  Toward automatic quantification of knee osteoarthritis severity using improved Faster R-CNN , 2020, International Journal of Computer Assisted Radiology and Surgery.

[29]  A. Pandit,et al.  Machine learning in rheumatology approaches the clinic , 2020, Nature Reviews Rheumatology.

[30]  Marzyeh Ghassemi,et al.  Challenges to the Reproducibility of Machine Learning Models in Health Care. , 2020, JAMA.

[31]  Tim Cootes,et al.  An automated workflow based on hip shape improves personalized risk prediction for hip osteoarthritis in the CHECK study. , 2020, Osteoarthritis and cartilage.

[32]  A. Mobasheri,et al.  Multi-classifier prediction of knee osteoarthritis progression from incomplete imbalanced longitudinal data , 2019, Scientific Reports.

[33]  Bidyut Baran Chaudhuri,et al.  diffGrad: An Optimization Method for Convolutional Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[34]  J. Arokoski,et al.  Eight-year trajectories of changes in health-related quality of life in knee osteoarthritis: Data from the Osteoarthritis Initiative (OAI) , 2019, PloS one.

[35]  Xiaoshuang Shi,et al.  Fully automatic knee osteoarthritis severity grading using deep neural networks with a novel ordinal loss , 2019, Comput. Medical Imaging Graph..

[36]  J. Marron,et al.  A machine learning approach to knee osteoarthritis phenotyping: data from the FNIH Biomarkers Consortium. , 2019, Osteoarthritis and cartilage.

[37]  D. Gómez-Cabrero,et al.  EULAR points to consider for the use of big data in rheumatic and musculoskeletal diseases , 2019, Annals of the rheumatic diseases.

[38]  Simo Saarakkala,et al.  Multimodal Machine Learning-based Knee Osteoarthritis Progression Prediction from Plain Radiographs and Clinical Data , 2019, Scientific Reports.

[39]  Noel E. O'Connor,et al.  Predicting knee osteoarthritis severity: comparative modeling based on patient’s data and plain X-ray images , 2019, Scientific Reports.

[40]  P. Widera.  A machine learning “APPROACH” to recruitment in OA , 2019, Osteoarthritis and Cartilage.

[41]  E. Lespessailles,et al.  A decision support tool for early detection of knee OsteoArthritis using X-ray imaging and machine learning: Data from the OsteoArthritis Initiative , 2019, Comput. Medical Imaging Graph..

[42]  Jungyoon Kim,et al.  A Deep Neural Network-Based Method for Early Detection of Osteoarthritis Using Statistical Data , 2019, International journal of environmental research and public health.

[43]  M. Nevitt,et al.  Pain Susceptibility Phenotypes in Those Free of Knee Pain With or at Risk of Knee Osteoarthritis: The Multicenter Osteoarthritis Study , 2019, Arthritis & rheumatology.

[44]  Jenni A. M. Sidey-Gibbons,et al.  Machine learning in medicine: a practical introduction , 2019, BMC Medical Research Methodology.

[45]  Atul J. Butte,et al.  Assessment of a Deep Learning Model Based on Electronic Health Record Data to Forecast Clinical Outcomes in Patients With Rheumatoid Arthritis , 2019, JAMA network open.

[46]  Harrie Weinans,et al.  Bone Texture Analysis for Prediction of Incident Radio-graphic Hip Osteoarthritis Using Machine Learning: Data from the Cohort Hip and Cohort Knee (CHECK) study , 2019, Osteoarthritis and cartilage.

[47]  R. Yeung,et al.  Patterns of joint involvement in juvenile idiopathic arthritis and prediction of disease course: A prospective study with multilayer non-negative matrix factorization , 2019, PLoS medicine.

[48]  The Lancet Respiratory Medicine.  Opening the black box of machine learning. , 2018, The Lancet. Respiratory medicine.

[49]  Sharmila Majumdar,et al.  3D convolutional neural networks for detection and severity staging of meniscus and PFJ cartilage morphological degenerative changes in osteoarthritis and anterior cruciate ligament subjects , 2018, Journal of magnetic resonance imaging : JMRI.

[50]  Thomas M. Link,et al.  Applying Densely Connected Convolutional Neural Networks for Staging Osteoarthritis Severity from Plain Radiographs , 2018, Journal of Digital Imaging.

[51]  Sharmila Majumdar,et al.  Using multidimensional topological data analysis to identify traits of hip osteoarthritis , 2018, Journal of magnetic resonance imaging : JMRI.

[52]  Ming Zhang,et al.  A Novel Method to Predict Knee Osteoarthritis Progression on MRI Using Machine Learning Methods , 2018, IEEE Transactions on NanoBioscience.

[53]  R. Darnell,et al.  Identification of Three Rheumatoid Arthritis Disease Subtypes by Machine Learning Integration of Synovial Histologic Features and RNA Sequencing Data , 2018, Arthritis & rheumatology.

[54]  Ting Hu,et al.  An evolutionary learning and network approach to identifying key metabolites for osteoarthritis , 2018, PLoS Comput. Biol..

[55]  Adam R Ferguson,et al.  MRI and biomechanics multidimensional data analysis reveals R2‐R1ρ as an early predictor of cartilage lesion progression in knee osteoarthritis , 2018, Journal of magnetic resonance imaging : JMRI.

[56]  S. Bierma-Zeinstra,et al.  A machine learning approach for the identification of new biomarkers for knee osteoarthritis development in overweight and obese women. , 2017, Osteoarthritis and cartilage.

[57]  Simo Saarakkala,et al.  Automatic Knee Osteoarthritis Diagnosis from Plain Radiographs: A Deep Learning-Based Approach , 2017, Scientific Reports.

[58]  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.

[59]  M. Reijnierse,et al.  Do Comorbidities Play a Role in Hand Osteoarthritis Disease Burden? Data from the Hand Osteoarthritis in Secondary Care Cohort , 2017, The Journal of Rheumatology.

[60]  K. Magnusson,et al.  A hospital-based observational cohort study exploring pain and biomarkers in patients with hand osteoarthritis in Norway: The Nor-Hand protocol , 2017, BMJ Open.

[61]  Longbing Cao,et al.  Data Science , 2017, ACM Comput. Surv..

[62]  Rongguo Zhang,et al.  A preliminary examination of the diagnostic value of deep learning in hip osteoarthritis , 2017, PloS one.

[63]  L. Price,et al.  Development of a clinical prediction algorithm for knee osteoarthritis structural progression in a cohort study: value of adding measurement of subchondral bone density , 2017, Arthritis Research & Therapy.

[64]  Lynsey D. Duffell,et al.  Detecting knee osteoarthritis and its discriminating parameters using random forests , 2017, Medical engineering & physics.

[65]  Paul J Thornalley,et al.  Protein oxidation, nitration and glycation biomarkers for early-stage diagnosis of osteoarthritis of the knee and typing and progression of arthritic disease , 2016, Arthritis Research & Therapy.

[66]  Marco Tulio Ribeiro,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, HLT-NAACL Demos.

[67]  Soo Beom Choi,et al.  Simple Scoring System and Artificial Neural Network for Knee Osteoarthritis Risk Prediction: A Cross-Sectional Study , 2016, PloS one.

[68]  M. Viergever,et al.  Cohort Profile: Cohort Hip and Cohort Knee (CHECK) study. , 2016, International journal of epidemiology.

[69]  S. Bierma-Zeinstra,et al.  Distinct subtypes of knee osteoarthritis: data from the Osteoarthritis Initiative. , 2015, Rheumatology.

[70]  P. Nandy,et al.  Osteoarthritis disease progression model using six year follow‐up data from the osteoarthritis initiative , 2015, Journal of clinical pharmacology.

[71]  J. Rosvold,et al.  A computational method to differentiate normal individuals, osteoarthritis and rheumatoid arthritis patients using serum biomarkers , 2014, Journal of The Royal Society Interface.

[72]  Neil A Segal,et al.  The Multicenter Osteoarthritis Study: Opportunities for Rehabilitation Research , 2013, PM & R : the journal of injury, function, and rehabilitation.

[73]  M. Lillholm,et al.  Diagnosis of osteoarthritis and prognosis of tibial cartilage loss by quantification of tibia trabecular bone from MRI , 2013, Magnetic resonance in medicine.

[74]  J. Dai,et al.  Identification of Osteoarthritis Biomarkers by Proteomic Analysis of Synovial Fluid , 2012, The Journal of international medical research.

[75]  Marek Kurzynski,et al.  A dissimilarity-based multiple classifier system for trabecular bone texture in detection and prediction of progression of knee osteoarthritis , 2012, Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine.

[76]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[77]  David Moher,et al.  An international registry of systematic-review protocols , 2011, The Lancet.

[78]  S P Moustakidis,et al.  A fuzzy decision tree-based SVM classifier for assessing osteoarthritis severity using ground reaction force measurements. , 2010, Medical engineering & physics.

[79]  L. Ferrucci,et al.  Early detection of radiographic knee osteoarthritis using computer-aided analysis. , 2009, Osteoarthritis and cartilage.

[80]  J. Ioannidis,et al.  The PRISMA statement for reporting systematic reviews and meta-analyses of studies that evaluate healthcare interventions: explanation and elaboration , 2009, BMJ : British Medical Journal.

[81]  D. Moher,et al.  Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement , 2009, BMJ : British Medical Journal.

[82]  Erika Schneider,et al.  The osteoarthritis initiative: report on the design rationale for the magnetic resonance imaging protocol for the knee. , 2008, Osteoarthritis and cartilage.

[83]  Alex A. T. Bui,et al.  Evaluation of a Dynamic Bayesian Belief Network to Predict Osteoarthritic Knee Pain Using Data from the Osteoarthritis Initiative , 2008, AMIA.

[84]  Lior Shamir,et al.  WND-CHARM: Multi-purpose image classification using compound image transforms , 2008, Pattern Recognit. Lett..

[85]  L Costaridou,et al.  Assessing hip osteoarthritis severity utilizing a probabilistic neural network based classification scheme. , 2007, Medical engineering & physics.

[86]  Longbing Cao,et al.  Data Science , 2017, ACM Comput. Surv..

[87]  John DeNero,et al.  Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations , 2016, North American Chapter of the Association for Computational Linguistics.