{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T01:10:17Z","timestamp":1790557817943,"version":"4.1.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T00:00:00Z","timestamp":1719360000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T00:00:00Z","timestamp":1719360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin Municipality","doi-asserted-by":"publisher","award":["21JCZDJC01000"],"award-info":[{"award-number":["21JCZDJC01000"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Our main objective was to use machine learning methods to identify significant structural factors associated with pain severity in knee osteoarthritis patients. Additionally, we assessed the potential of various classes of imaging data using machine learning techniques to gauge knee pain severity. The data of semi-quantitative assessments of knee radiographs, semi-quantitative assessments of knee magnetic resonance imaging (MRI), and MRI images from 567 individuals in the Osteoarthritis Initiative (OAI) were utilized to train a series of machine learning models. Models were constructed using five machine learning methods: random forests (RF), support vector machines (SVM), logistic regression (LR), decision tree (DT), and Bayesian (Bayes). Employing tenfold cross-validation, we selected the best-performing models based on the area under the curve (AUC). The study results indicate no significant difference in performance among models using different imaging data. Subsequently, we employed a convolutional neural network (CNN) to extract features from magnetic resonance imaging (MRI), and class activation mapping (CAM) was utilized to generate saliency maps, highlighting regions associated with knee pain severity. A radiologist reviewed the images, identifying specific lesions colocalized with the CAM. The review of 421 knees revealed that effusion\/synovitis (30.9%) and cartilage loss (30.6%) were the most frequent abnormalities associated with pain severity. Our study suggests cartilage loss and synovitis\/effusion lesions as significant structural factors affecting pain severity in patients with knee osteoarthritis. Furthermore, our study highlights the potential of machine learning for assessing knee pain severity using radiographs.<\/jats:p>","DOI":"10.1038\/s41598-024-65613-0","type":"journal-article","created":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T07:02:43Z","timestamp":1719385363000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Identifying significant structural factors associated with knee pain severity in patients with osteoarthritis using machine learning"],"prefix":"10.1038","volume":"14","author":[{"given":"Zhengkuan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingkuan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,6,26]]},"reference":[{"key":"65613_CR1","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1001\/jama.2020.22171","volume":"325","author":"JN Katz","year":"2021","unstructured":"Katz, J. N., Arant, K. R. & Loeser, R. F. Diagnosis and treatment of hip and knee osteoarthritis: A review. JAMA 325, 568\u2013578 (2021).","journal-title":"JAMA"},{"key":"65613_CR2","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/S0140-6736(14)60802-3","volume":"386","author":"S Glyn-Jones","year":"2015","unstructured":"Glyn-Jones, S. et al. Osteoarthritis. Lancet 386, 376\u2013387 (2015).","journal-title":"Lancet"},{"key":"65613_CR3","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1136\/annrheumdis-2013-204763","volume":"73","author":"M Cross","year":"2014","unstructured":"Cross, M. et al. The global burden of hip and knee osteoarthritis: Estimates from the global burden of disease 2010 study. Ann. Rheum. Dis. 73, 1323\u20131330 (2014).","journal-title":"Ann. Rheum. Dis."},{"key":"65613_CR4","doi-asserted-by":"publisher","first-page":"4346","DOI":"10.1109\/TMI.2020.3017007","volume":"39","author":"HH Nguyen","year":"2020","unstructured":"Nguyen, H. H., Saarakkala, S., Blaschko, M. B. & Tiulpin, A. Semixup: In- and out-of-manifold regularization for deep semi-supervised knee osteoarthritis severity grading from plain radiographs. IEEE Trans. Med. Imaging 39, 4346\u20134356 (2020).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"65613_CR5","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/j.joca.2013.03.018","volume":"21","author":"T Neogi","year":"2013","unstructured":"Neogi, T. The epidemiology and impact of pain in osteoarthritis. Osteoarth. Cartil. 21, 1145\u20131153 (2013).","journal-title":"Osteoarth. Cartil."},{"key":"65613_CR6","doi-asserted-by":"publisher","first-page":"21989","DOI":"10.1038\/s41598-021-01111-x","volume":"11","author":"AG Morales","year":"2021","unstructured":"Morales, A. G. et al. Uncovering associations between data-driven learned qMRI biomarkers and chronic pain. Sci. Rep. 11, 21989 (2021).","journal-title":"Sci. Rep."},{"key":"65613_CR7","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s11914-018-0477-1","volume":"16","author":"TW O\u2019Neill","year":"2018","unstructured":"O\u2019Neill, T. W. & Felson, D. T. Mechanisms of osteoarthritis (OA) pain. Curr. Osteoporos. Rep. 16, 611\u2013616 (2018).","journal-title":"Curr. Osteoporos. Rep."},{"key":"65613_CR8","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1016\/j.joca.2013.05.017","volume":"21","author":"DJ Hunter","year":"2013","unstructured":"Hunter, D. J., Guermazi, A., Roemer, F., Zhang, Y. & Neogi, T. Structural correlates of pain in joints with osteoarthritis. Osteoarth. Cartil. 21, 1170\u20131178 (2013).","journal-title":"Osteoarth. Cartil."},{"key":"65613_CR9","doi-asserted-by":"publisher","first-page":"541","DOI":"10.7326\/0003-4819-134-7-200104030-00007","volume":"134","author":"DT Felson","year":"2001","unstructured":"Felson, D. T. et al. The association of bone marrow lesions with pain in knee osteoarthritis. Ann. Intern. Med. 134, 541\u2013549 (2001).","journal-title":"Ann. Intern. Med."},{"key":"65613_CR10","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1002\/art.30148","volume":"63","author":"Y Zhang","year":"2011","unstructured":"Zhang, Y. et al. Fluctuation of knee pain and changes in bone marrow lesions, effusions, and synovitis on magnetic resonance imaging. Arthritis Rheum 63, 691\u2013699 (2011).","journal-title":"Arthritis Rheum"},{"key":"65613_CR11","doi-asserted-by":"publisher","first-page":"1599","DOI":"10.1136\/ard.2006.067470","volume":"66","author":"CL Hill","year":"2007","unstructured":"Hill, C. L. et al. Synovitis detected on magnetic resonance imaging and its relation to pain and cartilage loss in knee osteoarthritis. Ann. Rheum. Dis. 66, 1599\u20131603 (2007).","journal-title":"Ann. Rheum. Dis."},{"key":"65613_CR12","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1007\/s00330-005-0004-5","volume":"16","author":"CM Phan","year":"2006","unstructured":"Phan, C. M. et al. MR imaging findings in the follow-up of patients with different stages of knee osteoarthritis and the correlation with clinical symptoms. Eur. Radiol. 16, 608\u2013618 (2006).","journal-title":"Eur. Radiol."},{"key":"65613_CR13","doi-asserted-by":"publisher","first-page":"1886","DOI":"10.1007\/s11999-016-4732-4","volume":"474","author":"MD Kohn","year":"2016","unstructured":"Kohn, M. D., Sassoon, A. A. & Fernando, N. D. Classifications in brief: Kellgren-Lawrence classification of osteoarthritis. Clin. Orthop. Relat. Res. 474, 1886\u20131893 (2016).","journal-title":"Clin. Orthop. Relat. Res."},{"key":"65613_CR14","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1136\/annrheumdis-2020-217160","volume":"80","author":"MA Bowes","year":"2021","unstructured":"Bowes, M. A. et al. Machine-learning, MRI bone shape and important clinical outcomes in osteoarthritis: Data from the Osteoarthritis Initiative. Ann. Rheum. Dis. 80, 502\u2013508 (2021).","journal-title":"Ann. Rheum. Dis."},{"key":"65613_CR15","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1002\/jor.23010","volume":"34","author":"W Waldstein","year":"2016","unstructured":"Waldstein, W. et al. OARSI osteoarthritis cartilage histopathology assessment system: A biomechanical evaluation in the human knee. J. Orthop. Res. 34, 135\u2013140 (2016).","journal-title":"J. Orthop. Res."},{"key":"65613_CR16","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1136\/ard.2007.079020","volume":"67","author":"D Schiphof","year":"2008","unstructured":"Schiphof, D., Boers, M. & Bierma-Zeinstra, S. M. A. Differences in descriptions of Kellgren and Lawrence grades of knee osteoarthritis. Ann. Rheum. Dis. 67, 1034\u20131036 (2008).","journal-title":"Ann. Rheum. Dis."},{"key":"65613_CR17","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1038\/s41584-018-0010-z","volume":"14","author":"FW Roemer","year":"2018","unstructured":"Roemer, F. W., Kwoh, C. K., Hayashi, D., Felson, D. T. & Guermazi, A. The role of radiography and MRI for eligibility assessment in DMOAD trials of knee OA. Nat. Rev. Rheumatol. 14, 372\u2013380 (2018).","journal-title":"Nat. Rev. Rheumatol."},{"key":"65613_CR18","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1016\/j.joca.2011.05.004","volume":"19","author":"DJ Hunter","year":"2011","unstructured":"Hunter, D. J. et al. Evolution of semi-quantitative whole joint assessment of knee OA: MOAKS (MRI Osteoarthritis Knee Score). Osteoarth. Cartil. 19, 990\u20131002 (2011).","journal-title":"Osteoarth. Cartil."},{"key":"65613_CR19","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1038\/nrrheum.2012.223","volume":"9","author":"A Guermazi","year":"2013","unstructured":"Guermazi, A., Roemer, F. W., Haugen, I. K., Crema, M. D. & Hayashi, D. MRI-based semiquantitative scoring of joint pathology in osteoarthritis. Nat. Rev. Rheumatol. 9, 236\u2013251 (2013).","journal-title":"Nat. Rev. Rheumatol."},{"key":"65613_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ocarto.2020.100069","volume":"2","author":"C Kokkotis","year":"2020","unstructured":"Kokkotis, C., Moustakidis, S., Papageorgiou, E., Giakas, G. & Tsaopoulos, D. E. Machine learning in knee osteoarthritis: A review. Osteoarthr. Cartil. Open 2, 100069 (2020).","journal-title":"Osteoarthr. Cartil. Open"},{"key":"65613_CR21","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1038\/s41584-018-0130-5","volume":"15","author":"A Jamshidi","year":"2019","unstructured":"Jamshidi, A., Pelletier, J.-P. & Martel-Pelletier, J. Machine-learning-based patient-specific prediction models for knee osteoarthritis. Nat. Rev. Rheumatol. 15, 49\u201360 (2019).","journal-title":"Nat. Rev. Rheumatol."},{"key":"65613_CR22","doi-asserted-by":"publisher","DOI":"10.1136\/rmdopen-2021-001998","volume":"8","author":"M Binvignat","year":"2022","unstructured":"Binvignat, M. et al. Use of machine learning in osteoarthritis research: A systematic literature review. RMD Open 8, e001998 (2022).","journal-title":"RMD Open"},{"key":"65613_CR23","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41591-020-01192-7","volume":"27","author":"E Pierson","year":"2021","unstructured":"Pierson, E., Cutler, D. M., Leskovec, J., Mullainathan, S. & Obermeyer, Z. An algorithmic approach to reducing unexplained pain disparities in underserved populations. Nat. Med. 27, 136\u2013140 (2021).","journal-title":"Nat. Med."},{"key":"65613_CR24","doi-asserted-by":"publisher","first-page":"3538","DOI":"10.1007\/s00330-020-06658-3","volume":"30","author":"GH Chang","year":"2020","unstructured":"Chang, G. H. et al. Assessment of knee pain from MR imaging using a convolutional Siamese network. Eur. Radiol. 30, 3538\u20133548 (2020).","journal-title":"Eur. Radiol."},{"key":"65613_CR25","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.arth.2020.07.026","volume":"36","author":"AHS Harris","year":"2021","unstructured":"Harris, A. H. S. et al. Can machine learning methods produce accurate and easy-to-use preoperative prediction models of one-year improvements in pain and functioning after knee arthroplasty?. J. Arthroplast. 36, 112-117.e6 (2021).","journal-title":"J. Arthroplast."},{"key":"65613_CR26","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens, G. et al. A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60\u201388 (2017).","journal-title":"Med. Image Anal."},{"key":"65613_CR27","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"65613_CR28","doi-asserted-by":"publisher","first-page":"36879","DOI":"10.1109\/ACCESS.2021.3062709","volume":"9","author":"OL Usman","year":"2021","unstructured":"Usman, O. L., Muniyandi, R. C., Omar, K. & Mohamad, M. Advance machine learning methods for dyslexia biomarker detection: A review of implementation details and challenges. IEEE Access 9, 36879\u201336897 (2021).","journal-title":"IEEE Access"},{"key":"65613_CR29","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0245579","volume":"16","author":"OL Usman","year":"2021","unstructured":"Usman, O. L., Muniyandi, R. C., Omar, K. & Mohamad, M. Gaussian smoothing and modified histogram normalization methods to improve neural-biomarker interpretations for dyslexia classification mechanism. PLOS ONE 16, e0245579 (2021).","journal-title":"PLOS ONE"},{"key":"65613_CR30","doi-asserted-by":"publisher","first-page":"1433","DOI":"10.1016\/j.joca.2008.06.016","volume":"16","author":"CG Peterfy","year":"2008","unstructured":"Peterfy, C. G., Schneider, E. & Nevitt, M. The osteoarthritis initiative: Report on the design rationale for the magnetic resonance imaging protocol for the knee. Osteoarth. Cartil. 16, 1433\u20131441 (2008).","journal-title":"Osteoarth. Cartil."},{"key":"65613_CR31","doi-asserted-by":"publisher","first-page":"4048","DOI":"10.1002\/art.23071","volume":"56","author":"M Englund","year":"2007","unstructured":"Englund, M. et al. Effect of meniscal damage on the development of frequent knee pain, aching, or stiffness. Arth. Rheum. 56, 4048\u20134054 (2007).","journal-title":"Arth. Rheum."},{"key":"65613_CR32","first-page":"1218","volume":"61","author":"F Eckstein","year":"2009","unstructured":"Eckstein, F. et al. Magnetic resonance imaging-based cartilage loss in painful contralateral knees with and without radiographic joint space narrowing: Data from the Osteoarthritis Initiative. Arth. Rheum 61, 1218\u20131225 (2009).","journal-title":"Arth. Rheum"},{"key":"65613_CR33","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1016\/j.joca.2011.02.008","volume":"19","author":"J Cibere","year":"2011","unstructured":"Cibere, J. et al. Natural history of cartilage damage and osteoarthritis progression on magnetic resonance imaging in a population-based cohort with knee pain. Osteoarth. Cartil. 19, 683\u2013688 (2011).","journal-title":"Osteoarth. Cartil."},{"key":"65613_CR34","doi-asserted-by":"publisher","first-page":"1422","DOI":"10.1016\/j.joca.2011.09.002","volume":"19","author":"HA Kim","year":"2011","unstructured":"Kim, H. A. et al. The association between meniscal and cruciate ligament damage and knee pain in community residents. Osteoarth. Cartil. 19, 1422\u20131428 (2011).","journal-title":"Osteoarth. Cartil."},{"key":"65613_CR35","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1186\/1471-2474-11-80","volume":"11","author":"P Kersten","year":"2010","unstructured":"Kersten, P., White, P. J. & Tennant, A. The visual analogue WOMAC 3.0 scale\u2014internal validity and responsiveness of the VAS version. BMC Musculoskelet. Disord. 11, 80 (2010).","journal-title":"BMC Musculoskelet. Disord."},{"key":"65613_CR36","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/S1063-4584(03)00089-X","volume":"11","author":"F Salaffi","year":"2003","unstructured":"Salaffi, F. et al. Reliability and validity of the western ontario and Mcmaster Universities (WOMAC) Osteoarthritis index in Italian patients with osteoarthritis of the knee. Osteoarth. Cartil. 11, 551\u2013560 (2003).","journal-title":"Osteoarth. Cartil."},{"key":"65613_CR37","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.b2844","volume":"339","author":"T Neogi","year":"2009","unstructured":"Neogi, T. et al. Association between radiographic features of knee osteoarthritis and pain: Results from two cohort studies. BMJ 339, b2844 (2009).","journal-title":"BMJ"},{"key":"65613_CR38","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1016\/j.joca.2006.03.015","volume":"14","author":"L Torres","year":"2006","unstructured":"Torres, L. et al. The relationship between specific tissue lesions and pain severity in persons with knee osteoarthritis. Osteoarth. Cartil. 14, 1033\u20131040 (2006).","journal-title":"Osteoarth. Cartil."},{"key":"65613_CR39","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0176833","volume":"12","author":"EC Sayre","year":"2017","unstructured":"Sayre, E. C. et al. Associations between MRI features versus knee pain severity and progression: Data from the Vancouver Longitudinal Study of Early Knee Osteoarthritis. PLoS One 12, e0176833 (2017).","journal-title":"PLoS One"},{"key":"65613_CR40","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/nrrheum.2010.159","volume":"6","author":"J Sellam","year":"2010","unstructured":"Sellam, J. & Berenbaum, F. The role of synovitis in pathophysiology and clinical symptoms of osteoarthritis. Nat. Rev. Rheumatol. 6, 625\u2013635 (2010).","journal-title":"Nat. Rev. Rheumatol."},{"key":"65613_CR41","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1136\/annrheumdis-2020-217363","volume":"79","author":"K Bacon","year":"2020","unstructured":"Bacon, K., LaValley, M. P., Jafarzadeh, S. R. & Felson, D. Does cartilage loss cause pain in osteoarthritis and if so, how much?. Ann. Rheum. Dis. 79, 1105\u20131110 (2020).","journal-title":"Ann. Rheum. Dis."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-65613-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-65613-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-65613-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T08:02:51Z","timestamp":1719388971000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-65613-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,26]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["65613"],"URL":"https:\/\/doi.org\/10.1038\/s41598-024-65613-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,26]]},"assertion":[{"value":"5 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"14705"}}