{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T14:36:45Z","timestamp":1791815805131,"version":"4.3.4"},"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research & Development Program of China","award":["2023YFE0209700"],"award-info":[{"award-number":["2023YFE0209700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82373653"],"award-info":[{"award-number":["82373653"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82103903"],"award-info":[{"award-number":["82103903"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82002344"],"award-info":[{"award-number":["82002344"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Projects in Guangzhou","award":["SL2023A04J02586"],"award-info":[{"award-number":["SL2023A04J02586"]}]},{"name":"Key development projects of the Sichuan Provincial Science and Technology Plan","award":["2024YFFK0298"],"award-info":[{"award-number":["2024YFFK0298"]}]},{"name":"Chengdu Medical Research Project","award":["2024487"],"award-info":[{"award-number":["2024487"]}]}],"content-domain":{"domain":["www.plosmedicine.org"],"crossmark-restriction":false},"short-container-title":["PLoS Med"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>Knee osteoarthritis (KOA) worsens both structurally and symptomatically, yet no model predicts KOA progression using Magnetic Resonance Image (MRI) radiomics and biomarkers. This study aimed to develop and test the longitudinal Load-Bearing Tissue Radiomic plus Biochemical biomarker and Clinical variable Model (LBTRBC-M) to predict KOA progression.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods and findings<\/jats:title>\n<jats:p>Data from the Foundation of the National Institutes of Health Osteoarthritis Biomarkers Consortium were used. We selected 594 participants with Kellgren-Lawrence grades 1\u20133 and complete biomarker data. The mean age was 61.6\u2009\u00b1\u20098.9 years, 58.8% were female, and the racial distribution was 79.3% White or White, 18.0% Black or African American, and 2.7% Asian or other non-White. A total of 1,753 knee MRIs were included across the study period, comprising 594 at baseline, 575 at 1-year follow-up, and 584 at 2-year follow-up. Outcomes included (1) both Joint Space Narrowing (JSN) and pain progression (<jats:italic>n<\/jats:italic>\u2009=\u2009567), (2) only JSN progression (<jats:italic>n<\/jats:italic>\u2009=\u2009303), (3) only pain progression (<jats:italic>n<\/jats:italic>\u2009=\u2009295), and (4) non-progression (JSN or pain) (<jats:italic>n<\/jats:italic>\u2009=\u2009588), corresponding to an approximate ratio of 2:1:1:2. JSN progression was defined as a minimum joint space width (JSW) loss of \u22650.7\u00a0mm, and pain progression as a sustained (\u22652 time points) increase of \u22659 points on the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) pain subscale (0\u2013100 scale). Using the eXtreme Gradient BOOSTing (XGBOOST) algorithm, the model was developed in the total development cohort (<jats:italic>n<\/jats:italic>\u2009=\u2009877) and tested in the total test cohort (<jats:italic>n<\/jats:italic>\u2009=\u2009876). In the total test cohort, the Area Under the receiver operating characteristic Curve (AUC) of LBTRBC-M for predicting JSN and pain progression, JSN progression, pain progression, and non-progression were 0.880 (95% confidence interval (CI) [0.853, 0.903]), 0.913 (95% CI [0.881, 0.937]), 0.886 (95% CI [0.856, 0.910]), and 0.909 (95% CI [0.888, 0.926]), respectively. The overall accuracy of LBTRBC-M was 70.1%. With LBTRBC-M assistance, the prognostic accuracy of resident physicians (<jats:italic>n<\/jats:italic>\u2009=\u20097) improved from 44.7%\u201349.0% to 64.4%\u201366.5%. The main limitations include the use of a non-routine MRI sequence, the lack of external validation in independent cohorts, and limited incorporation of all knee joint structures in radiomic feature extraction.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>In this study, we observed that longitudinal MRI radiomic features of load-bearing knee joint tissues provide potentially informative markers for predicting knee osteoarthritis progression. These findings may help guide future efforts toward early risk stratification and personalized management of KOA.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pmed.1004665","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:21:42Z","timestamp":1755796902000},"page":"e1004665","update-policy":"https:\/\/doi.org\/10.1371\/journal.pmed.corrections_policy","source":"Crossref","is-referenced-by-count":22,"title":["Predicting knee osteoarthritis progression using neural network with longitudinal MRI radiomics, and biochemical biomarkers: A modeling study"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1309-0194","authenticated-orcid":true,"given":"Ting","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1273-4468","authenticated-orcid":true,"given":"Hao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peihua","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3572-3690","authenticated-orcid":true,"given":"Jia","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangfeng","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9126-4922","authenticated-orcid":true,"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3895-1384","authenticated-orcid":true,"given":"Xiaoshuai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Dang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengdi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Tack","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3197-752X","authenticated-orcid":true,"given":"David","family":"Hunter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9479-730X","authenticated-orcid":true,"given":"Changhai","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6801-7102","authenticated-orcid":true,"given":"Shengfa","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"issue":"10182","key":"pmed.1004665.ref001","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.1016\/S0140-6736(19)30417-9","article-title":"Osteoarthritis","volume":"393","author":"DJ Hunter","year":"2019","journal-title":"Lancet"},{"issue":"12","key":"pmed.1004665.ref002","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1038\/s41584-020-00518-6","article-title":"Emerging pharmaceutical therapies for osteoarthritis","volume":"16","author":"A Latourte","year":"2020","journal-title":"Nat Rev Rheumatol"},{"issue":"10053","key":"pmed.1004665.ref003","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1016\/S0140-6736(16)31678-6","article-title":"Global, regional, and national incidence, prevalence, and years lived with disability for 310 diseases and injuries, 1990\u20132015: a systematic analysis for the Global Burden of Disease Study 2015","volume":"388","year":"2016","journal-title":"Lancet"},{"issue":"6","key":"pmed.1004665.ref004","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1136\/annrheumdis-2019-216515","article-title":"Global, regional and national burden of osteoarthritis 1990\u20132017: a systematic analysis of the Global Burden of Disease Study 2017","volume":"79","author":"S Safiri","year":"2020","journal-title":"Ann Rheum Dis"},{"key":"pmed.1004665.ref005","volume-title":"Osteoarthritis: Structural Endpoints for the Development of Drugs, Devices, and Biological Products for Treatment Guidance for Industry","author":"Administration UFD","year":"2018"},{"issue":"5","key":"pmed.1004665.ref006","doi-asserted-by":"crossref","first-page":"385","DOI":"10.2106\/JBJS.L.00206","article-title":"Estimating the burden of total knee replacement in the United States","volume":"95","author":"AM Weinstein","year":"2013","journal-title":"J Bone Joint Surg Am"},{"key":"pmed.1004665.ref007","doi-asserted-by":"crossref","DOI":"10.1016\/j.joca.2003.10.002","article-title":"Pathophysiology of osteoarthritis","volume":"12","author":"J Martel-Pelletier","year":"2004","journal-title":"Osteoarthr Cartil"},{"issue":"7","key":"pmed.1004665.ref008","doi-asserted-by":"crossref","first-page":"1142","DOI":"10.1002\/acr.24557","article-title":"Multivariable modeling of biomarker data from the phase I Foundation for the National Institutes of Health Osteoarthritis Biomarkers Consortium","volume":"74","author":"DJ Hunter","year":"2022","journal-title":"Arthritis Care Res (Hoboken)"},{"issue":"10","key":"pmed.1004665.ref009","doi-asserted-by":"crossref","first-page":"2422","DOI":"10.1002\/art.39731","article-title":"Semiquantitative imaging biomarkers of knee osteoarthritis progression: data from the Foundation for the National Institutes of Health Osteoarthritis Biomarkers Consortium","volume":"68","author":"JE Collins","year":"2016","journal-title":"Arthritis Rheumatol"},{"issue":"1","key":"pmed.1004665.ref010","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1002\/art.40348","article-title":"Predictive validity of radiographic trabecular bone texture in knee osteoarthritis: the Osteoarthritis Research Society International\/Foundation for the National Institutes of Health Osteoarthritis Biomarkers Consortium","volume":"70","author":"VB Kraus","year":"2018","journal-title":"Arthritis Rheumatol"},{"issue":"1","key":"pmed.1004665.ref011","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1186\/s12891-021-04620-y","article-title":"Novel nomogram for predicting the progression of osteoarthritis based on 3D-MRI bone shape: data from the FNIH OA biomarkers consortium","volume":"22","author":"Y Sun","year":"2021","journal-title":"BMC Musculoskelet Disord"},{"issue":"1","key":"pmed.1004665.ref012","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1136\/annrheumdis-2016-209252","article-title":"Predictive validity of biochemical biomarkers in knee osteoarthritis: data from the FNIH OA Biomarkers Consortium","volume":"76","author":"VB Kraus","year":"2017","journal-title":"Ann Rheum Dis"},{"key":"pmed.1004665.ref013","doi-asserted-by":"crossref","DOI":"10.1109\/ISBI52829.2022.9761458","volume-title":"Predicting Knee Osteoarthritis Progression from Structural MRI using Deep Learning","author":"E Panfilov","year":"2022"},{"issue":"3","key":"pmed.1004665.ref014","doi-asserted-by":"crossref","DOI":"10.3390\/biomedicines12030666","article-title":"Performance of radiological and biochemical biomarkers in predicting radio-symptomatic knee osteoarthritis progression","volume":"12","author":"A Almhdie-Imjabbar","year":"2024","journal-title":"Biomedicines"},{"issue":"10","key":"pmed.1004665.ref015","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0258855","article-title":"Towards novel osteoarthritis biomarkers: multi-criteria evaluation of 46,996 segmented knee MRI data from the osteoarthritis initiative","volume":"16","author":"A Tack","year":"2021","journal-title":"PLoS One"},{"key":"pmed.1004665.ref016","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.media.2018.11.009","article-title":"Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: data from the osteoarthritis initiative","volume":"52","author":"F Ambellan","year":"2019","journal-title":"Med Image Anal"},{"issue":"5","key":"pmed.1004665.ref017","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1016\/j.joca.2018.02.907","article-title":"Knee menisci segmentation using convolutional neural networks: data from the osteoarthritis initiative","volume":"26","author":"A Tack","year":"2018","journal-title":"Osteoarthr Cartil"},{"issue":"1","key":"pmed.1004665.ref018","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.berh.2014.01.007","article-title":"Biomarkers for osteoarthritis: current position and steps towards further validation","volume":"28","author":"DJ Hunter","year":"2014","journal-title":"Best Pract Res Clin Rheumatol"},{"issue":"6","key":"pmed.1004665.ref019","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1016\/j.joca.2008.11.001","article-title":"Location specific radiographic joint space width for osteoarthritis progression","volume":"17","author":"G Neumann","year":"2009","journal-title":"Osteoarthr Cartil"},{"issue":"1","key":"pmed.1004665.ref020","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1136\/annrheumdis-2016-209253","article-title":"Establishment of reference intervals for osteoarthritis-related soluble biomarkers: the FNIH\/OARSI OA Biomarkers Consortium","volume":"76","author":"VB Kraus","year":"2017","journal-title":"Ann Rheum Dis"},{"issue":"4","key":"pmed.1004665.ref021","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1136\/ard.16.4.494","article-title":"Radiological assessment of osteo-arthrosis","volume":"16","author":"JH Kellgren","year":"1957","journal-title":"Ann Rheum Dis"},{"issue":"1","key":"pmed.1004665.ref022","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.joca.2012.10.017","article-title":"Direct comparison of fixed flexion, radiography and MRI in knee osteoarthritis: responsiveness data from the osteoarthritis initiative","volume":"21","author":"W Wirth","year":"2013","journal-title":"Osteoarthr Cartil"},{"issue":"12","key":"pmed.1004665.ref023","doi-asserted-by":"crossref","first-page":"1433","DOI":"10.1016\/j.joca.2008.06.016","article-title":"The osteoarthritis initiative: report on the design rationale for the magnetic resonance imaging protocol for the knee","volume":"16","author":"CG Peterfy","year":"2008","journal-title":"Osteoarthr Cartil"},{"issue":"2","key":"pmed.1004665.ref024","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1148\/radiol.09090596","article-title":"Patellar cartilage: T2 values and morphologic abnormalities at 3.0-T MR imaging in relation to physical activity in asymptomatic subjects from the osteoarthritis initiative","volume":"254","author":"C Stehling","year":"2010","journal-title":"Radiology"},{"issue":"1","key":"pmed.1004665.ref025","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.joca.2010.10.023","article-title":"Vastus lateralis\/vastus medialis cross-sectional area ratio impacts presence and degree of knee joint abnormalities and cartilage T2 determined with 3T MRI \u2013 an analysis from the incidence cohort of the osteoarthritis initiative","volume":"19","author":"J Pan","year":"2011","journal-title":"Osteoarthr Cartil"},{"key":"pmed.1004665.ref026","article-title":"Integrating radiomics and neural networks for knee osteoarthritis incidence prediction","author":"S Li","year":"2024","journal-title":"Arthritis Rheumatology"},{"issue":"2","key":"pmed.1004665.ref027","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping","volume":"295","author":"A Zwanenburg","year":"2020","journal-title":"Radiology"},{"key":"pmed.1004665.ref028","author":"S Ashrafinia","year":"2019"},{"key":"pmed.1004665.ref029","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"T Hastie","year":"2009"},{"issue":"1","key":"pmed.1004665.ref030","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1109\/TPAMI.2022.3145392","article-title":"Deep ROC analysis and AUC as balanced average accuracy, for improved classifier selection, audit and explanation","volume":"45","author":"AM Carrington","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"pmed.1004665.ref031","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s13075-017-1226-z","article-title":"Sex differences in the association of skin advanced glycation endproducts with knee osteoarthritis progression","volume":"19","author":"CB Eaton","year":"2017","journal-title":"Arthritis Res Ther"},{"issue":"4","key":"pmed.1004665.ref032","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/j.joca.2018.01.020","article-title":"Natural history of pain and disability among African\u2013Americans and Whites with or at risk for knee osteoarthritis: A longitudinal study","volume":"26","author":"ER Vina","year":"2018","journal-title":"Osteoarthr Cartil"},{"issue":"1","key":"pmed.1004665.ref033","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1186\/s12891-021-04580-3","article-title":"Osteoporosis is associated with varus deformity in postmenopausal women with knee osteoarthritis: a cross-sectional study","volume":"22","author":"C Zhang","year":"2021","journal-title":"BMC Musculoskelet Disord"},{"issue":"6","key":"pmed.1004665.ref034","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1007\/s10067-015-3128-2","article-title":"Individuals with incident accelerated knee osteoarthritis have greater pain than those with common knee osteoarthritis progression: data from the Osteoarthritis Initiative","volume":"35","author":"JB Driban","year":"2016","journal-title":"Clin Rheumatol"},{"issue":"8","key":"pmed.1004665.ref035","doi-asserted-by":"crossref","first-page":"4852","DOI":"10.21037\/qims-22-1251","article-title":"DeepKOA: a deep-learning model for predicting progression in knee osteoarthritis using multimodal magnetic resonance images from the osteoarthritis initiative","volume":"13","author":"J Hu","year":"2023","journal-title":"Quant Imaging Med Surg"},{"issue":"6","key":"pmed.1004665.ref036","doi-asserted-by":"crossref","first-page":"3564","DOI":"10.1007\/s00330-020-07512-2","article-title":"Conventional MRI-based subchondral trabecular biomarkers as predictors of knee osteoarthritis progression: data from the Osteoarthritis Initiative","volume":"31","author":"F Pishgar","year":"2021","journal-title":"Eur Radiol"},{"issue":"9","key":"pmed.1004665.ref037","doi-asserted-by":"crossref","first-page":"1220","DOI":"10.1016\/j.joca.2020.05.008","article-title":"Association of knee OA structural phenotypes to risk for progression: a secondary analysis from the Foundation for National Institutes of Health Osteoarthritis Biomarkers study (FNIH)","volume":"28","author":"FW Roemer","year":"2020","journal-title":"Osteoarthritis Cartilage"},{"issue":"9","key":"pmed.1004665.ref038","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1136\/annrheumdis-2015-207602","article-title":"Longitudinal validation of periarticular bone area and 3D shape as biomarkers for knee OA progression? Data from the FNIH OA Biomarkers Consortium","volume":"75","author":"D Hunter","year":"2016","journal-title":"Ann Rheum Dis"},{"issue":"12","key":"pmed.1004665.ref039","doi-asserted-by":"crossref","first-page":"3184","DOI":"10.1002\/art.39324","article-title":"Brief report: cartilage thickness change as an imaging biomarker of knee osteoarthritis progression: data from the Foundation for the National Institutes of Health Osteoarthritis Biomarkers Consortium","volume":"67","author":"F Eckstein","year":"2015","journal-title":"Arthritis Rheumatol"},{"issue":"2","key":"pmed.1004665.ref040","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1007\/s00330-016-4393-4","article-title":"Prediction of medial tibiofemoral compartment joint space loss progression using volumetric cartilage measurements: data from the FNIH OA biomarkers consortium","volume":"27","author":"N Hafezi-Nejad","year":"2017","journal-title":"Eur Radiol"}],"container-title":["PLOS Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pmed.1004665","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:21:52Z","timestamp":1755796912000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pmed.1004665"}},"subtitle":[],"editor":[{"given":"Christelle","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":40,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pmed.1004665","relation":{},"ISSN":["1549-1676"],"issn-type":[{"value":"1549-1676","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,21]]}}}