{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T16:59:45Z","timestamp":1790701185904,"version":"4.1.0"},"reference-count":37,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["esskajournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Knee surg. sports traumatol. arthrosc."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Previous knee injury increases the risk of subsequent injury, even after functional recovery, yet residual gait, running or load alterations often go undetected in routine assessment. Wearable inertial measurement units (IMUs) may enable scalable detection of such alterations outside laboratory settings. The primary aim of this study was to determine whether IMU\u2010derived gait and running features can distinguish physically active individuals with a history of knee injury from uninjured controls using machine learning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this cross\u2010sectional study, 108 sports science students completed injury\u2010history questionnaires and a walking\u2010running\u2010walking protocol on a 400\u2009m track while wearing four IMUs. Of 90 participants with complete data, 23 reported prior knee injury and 67 were uninjured controls. Left\u2010 and right\u2010side sensor data were combined into one per\u2010participant feature vector. The model classified any prior knee injury (yes\/no), not limb\u2010specific injury. From 220 candidate features covering baseline gait, post\u2010run changes, walk\u2010to\u2010run transitions, inter\u2010limb asymmetry, variability and composite indices\u2014a fixed pipeline (e.g., median imputation, mutual\u2010information selection) was applied within leave\u2010one\u2010out cross\u2010validation (primary) and repeated stratified five\u2010fold cross\u2010validation (secondary).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Leave\u2010one\u2010out cross\u2010validation correctly classified 76\/90 participants (65\/67 true negatives, 11\/23 true positives), yielding an area under the receiver operating characteristic curve of 0.74, balanced accuracy of 0.72, sensitivity of 0.48, specificity of 0.97, positive predictive value (PPV) of 0.85 and negative predictive value of 0.84. Five\u2010fold cross\u2010validation produced more variable estimates, indicating substantial model instability across resampling partitions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>As a proof of concept, IMU\u2010derived features distinguished individuals with previous knee injury at high specificity but limited sensitivity. High specificity and PPV depend on the classification threshold and injury prevalence in this selected sample, not intrinsic model properties. Because predictors were not aligned to the injured side, findings cannot be interpreted biomechanically. Potential applications (e.g., targeted monitoring) require prospective external validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of Evidence<\/jats:title>\n                    <jats:p>Level II.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/ksa.70631","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T16:07:26Z","timestamp":1790698046000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Detection of previous knee injuries using lower limb\u2010worn inertial measurement units: A cross\u2010sectional machine\u2010learning study"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0591-2942","authenticated-orcid":false,"given":"Christina","family":"Valle","sequence":"first","affiliation":[{"name":"Department of Orthopaedics and Sports Orthopaedics TUM University Hospital Munich Germany"},{"name":"Clinic for Orthopaedic Rehabilitation, Medical Park Chiemsee Bernau\u2010Felden Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9774-8602","authenticated-orcid":false,"given":"Matthias","family":"Cotic","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics and Sports Orthopaedics TUM University Hospital Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maximilian","family":"Bartelt","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics and Sports Orthopaedics TUM University Hospital Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Seeberger","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics and Sports Orthopaedics TUM University Hospital Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Birgit","family":"Waschulzik","sequence":"additional","affiliation":[{"name":"Chair for AI in Healthcare and Medicine Technical University of Munich (TUM) and TUM University Hospital Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Siebenlist","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics and Sports Orthopaedics TUM University Hospital Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4014-424X","authenticated-orcid":false,"given":"Michael T.","family":"Hirschmann","sequence":"additional","affiliation":[{"name":"Department of Orthopedic Surgery and Traumatology Kantonsspital Baselland Bruderholz Switzerland"},{"name":"Department of Clinical Research, Research Group Michael T. Hirschmann, Regenerative Medicine and Biomechanics University of Basel Basel Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5105-5875","authenticated-orcid":false,"given":"Georg","family":"Matziolis","sequence":"additional","affiliation":[{"name":"Orthopaedics, Campus Waldkliniken Eisenberg University Hospital Jena, Friedrich Schiller University Jena Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2352-1357","authenticated-orcid":false,"given":"R\u00fcdiger","family":"von Eisenhart\u2010Rothe","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics and Sports Orthopaedics TUM University Hospital Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Rueckert","sequence":"additional","affiliation":[{"name":"Chair for AI in Healthcare and Medicine Technical University of Munich (TUM) and TUM University Hospital Munich Germany"},{"name":"Department of Computing Imperial College London, South Kensington Campus London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0273-0643","authenticated-orcid":false,"given":"Florian","family":"Hinterwimmer","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics and Sports Orthopaedics TUM University Hospital Munich Germany"},{"name":"Chair for AI in Healthcare and Medicine Technical University of Munich (TUM) and TUM University Hospital Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9825-302X","authenticated-orcid":false,"given":"Ricardo Smits","family":"Serena","sequence":"additional","affiliation":[{"name":"Department of Orthopaedics and Sports Orthopaedics TUM University Hospital Munich Germany"},{"name":"Chair for AI in Healthcare and Medicine Technical University of Munich (TUM) and TUM University Hospital Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"issue":"2","key":"e_1_2_13_2_1","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1177\/0363546520980079","article-title":"Quadriceps strength symmetry does not modify gait mechanics after anterior cruciate ligament reconstruction, rehabilitation, and return\u2010to\u2010sport training","volume":"49","author":"Arhos EK","year":"2021","journal-title":"Am J Sports Med"},{"key":"e_1_2_13_3_1","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.gaitpost.2022.09.002","article-title":"Objective gait assessment in individuals with knee osteoarthritis using inertial sensors: a systematic review and meta\u2010analysis","volume":"98","author":"Boekesteijn RJ","year":"2022","journal-title":"Gait Posture"},{"issue":"6","key":"e_1_2_13_4_1","doi-asserted-by":"crossref","first-page":"642","DOI":"10.3390\/healthcare12060642","article-title":"Exploring the relationship between running\u2010related technology use and running\u2010related injuries: a cross\u2010sectional study of recreational and elite long\u2010distance runners","volume":"12","author":"Chowdhary K","year":"2024","journal-title":"Healthcare"},{"key":"e_1_2_13_5_1","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins GS","year":"2024","journal-title":"BMJ"},{"issue":"1","key":"e_1_2_13_6_1","doi-asserted-by":"crossref","first-page":"40","DOI":"10.2519\/jospt.2022.10959","article-title":"The \u201cSHRed Injuries Basketball\u201d neuromuscular training warm\u2010up program reduces ankle and knee injury rates by 36% in youth basketball","volume":"52","author":"Emery CA","year":"2022","journal-title":"J Orthop Sports Phys Ther"},{"issue":"6","key":"e_1_2_13_7_1","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1177\/0363546521999109","article-title":"Clinical risk profile for a second anterior cruciate ligament injury in female soccer players after anterior cruciate ligament reconstruction","volume":"49","author":"F\u00e4ltstr\u00f6m A","year":"2021","journal-title":"Am J Sports Med"},{"issue":"10","key":"e_1_2_13_8_1","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1136\/bjsports-2015-094797","article-title":"Knee kinematics and joint moments during gait following anterior cruciate ligament reconstruction: a systematic review and meta\u2010analysis","volume":"50","author":"Hart HF","year":"2016","journal-title":"Br J Sports Med"},{"key":"e_1_2_13_9_1","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.clinbiomech.2018.07.007","article-title":"Accelerations from wearable accelerometers reflect knee loading during running after anterior cruciate ligament reconstruction","volume":"58","author":"Havens KL","year":"2018","journal-title":"Clin Biomech"},{"issue":"11","key":"e_1_2_13_10_1","doi-asserted-by":"crossref","first-page":"1843","DOI":"10.1002\/jor.23414","article-title":"Mechanisms, prediction, and prevention of ACL injuries: cut risk with three sharpened and validated tools","volume":"34","author":"Hewett TE","year":"2016","journal-title":"J Orthop Res"},{"issue":"1","key":"e_1_2_13_11_1","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1177\/19417381211065443","article-title":"Injury history and perceived knee function as risk factors for knee injury in youth team\u2010sports athletes","volume":"15","author":"Hietamo J","year":"2023","journal-title":"Sports Health"},{"issue":"11","key":"e_1_2_13_12_1","doi-asserted-by":"crossref","first-page":"2917","DOI":"10.1177\/03635465221112095","article-title":"Predicting ACL injury using machine learning on data from an extensive screening test battery of 880 female elite athletes","volume":"50","author":"Jauhiainen S","year":"2022","journal-title":"Am J Sports Med"},{"issue":"2","key":"e_1_2_13_13_1","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1055\/a-1231-5304","article-title":"New machine learning approach for detection of injury risk factors in young team sport athletes","volume":"42","author":"Jauhiainen S","year":"2021","journal-title":"Int J Sports Med"},{"issue":"6","key":"e_1_2_13_14_1","doi-asserted-by":"crossref","first-page":"2268","DOI":"10.1002\/ksa.70374","article-title":"Machine learning applications for anterior cruciate ligament injury prediction and rehabilitation in sports: a scoping review with evidence synthesis","volume":"34","author":"Kumar R","year":"2026","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"issue":"7","key":"e_1_2_13_15_1","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1136\/bjsports-2024-108576","article-title":"Machine learning approaches to injury risk prediction in sport: a scoping review with evidence synthesis","volume":"59","author":"Leckey C","year":"2025","journal-title":"Br J Sports Med"},{"issue":"4","key":"e_1_2_13_16_1","doi-asserted-by":"crossref","DOI":"10.1002\/jeo2.70081","article-title":"Machine learning in knee injury sequelae detection: unravelling the role of psychological factors and preventing long\u2010term sequelae","volume":"11","author":"Lipps Lene C","year":"2024","journal-title":"J Exp Orthop"},{"issue":"4","key":"e_1_2_13_17_1","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.jsams.2024.02.001","article-title":"What exercise programme is the most appropriate to mitigate anterior cruciate ligament injury risk in football (soccer) players? A systematic review and network meta\u2010analysis","volume":"27","author":"Maga\u00f1a\u2010Ram\u00edrez M","year":"2024","journal-title":"J Sci Med Sport"},{"key":"e_1_2_13_18_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ptsp.2022.01.004","article-title":"The use of wearable technology as an assessment tool to identify between\u2010limb differences during functional tasks following ACL reconstruction. A scoping review","volume":"55","author":"Marques JB","year":"2022","journal-title":"Phys Ther Sport"},{"issue":"11","key":"e_1_2_13_19_1","doi-asserted-by":"crossref","first-page":"1044","DOI":"10.1016\/j.jsams.2020.04.021","article-title":"Using machine learning to improve our understanding of injury risk and prediction in elite male youth football players","volume":"23","author":"Oliver JL","year":"2020","journal-title":"J Sci Med Sport"},{"issue":"1","key":"e_1_2_13_20_1","doi-asserted-by":"crossref","first-page":"887","DOI":"10.3390\/s140100887","article-title":"An ambulatory method of identifying anterior cruciate ligament reconstructed gait patterns","volume":"14","author":"Patterson M","year":"2014","journal-title":"Sensors"},{"issue":"6","key":"e_1_2_13_21_1","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1123\/jsr.2021-0128","article-title":"Arthrogenic muscle inhibition following anterior cruciate ligament injury","volume":"31","author":"Pietrosimone B","year":"2022","journal-title":"J Sport Rehabil"},{"issue":"10","key":"e_1_2_13_22_1","doi-asserted-by":"crossref","first-page":"3460","DOI":"10.3390\/s18103460","article-title":"Inertial sensor angular velocities reflect dynamic knee loading during single limb loading in individuals following anterior cruciate ligament reconstruction","volume":"18","author":"Pratt KA","year":"2018","journal-title":"Sensors"},{"issue":"6","key":"e_1_2_13_23_1","doi-asserted-by":"crossref","first-page":"411","DOI":"10.2519\/jospt.2017.6912","article-title":"Knee loading deficits during dynamic tasks in individuals following anterior cruciate ligament reconstruction","volume":"47","author":"Pratt KA","year":"2017","journal-title":"J Orthop Sports Phys Ther"},{"issue":"24","key":"e_1_2_13_24_1","doi-asserted-by":"crossref","first-page":"8221","DOI":"10.3390\/s21248221","article-title":"A systematic review of diagnostic accuracy and clinical applications of wearable movement sensors for knee joint rehabilitation","volume":"21","author":"Prill R","year":"2021","journal-title":"Sensors"},{"key":"e_1_2_13_25_1","volume-title":"R: a language and environment for statistical computing","author":"R Core Team","year":"2025"},{"issue":"1","key":"e_1_2_13_26_1","doi-asserted-by":"crossref","first-page":"2202","DOI":"10.1038\/s41598-023-29126-6","article-title":"The effects of core stabilization exercises on the neuromuscular function of athletes with ACL reconstruction","volume":"13","author":"Saki F","year":"2023","journal-title":"Sci Rep"},{"key":"e_1_2_13_27_1","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1002\/ksa.12431","article-title":"Machine\u2010learning models for shoulder rehabilitation exercises classification using a wearable system","volume":"33","author":"Sassi M","year":"2025","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"issue":"4","key":"e_1_2_13_28_1","doi-asserted-by":"crossref","first-page":"1524","DOI":"10.1002\/ksa.70332","article-title":"Deep learning of wrist accelerometry from UK Biobank data identifies early movement signatures of knee osteoarthritis up to 5 years before diagnosis","volume":"34","author":"Smits Serena R","year":"2026","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"issue":"1","key":"e_1_2_13_29_1","doi-asserted-by":"crossref","DOI":"10.1177\/24730114211057886","article-title":"Epidemiology of lower leg soft tissue injuries in high school athletes","volume":"7","author":"Spitnale MJ","year":"2022","journal-title":"Foot Ankle Orthop"},{"key":"e_1_2_13_30_1","doi-asserted-by":"crossref","DOI":"10.2196\/59042","article-title":"25 Years of digital health toward universal health coverage in low\u2010 and middle\u2010income countries: rapid systematic review","volume":"27","author":"Sylla B","year":"2025","journal-title":"J Med Internet Res"},{"issue":"9","key":"e_1_2_13_31_1","doi-asserted-by":"crossref","first-page":"3141","DOI":"10.3390\/s21093141","article-title":"A machine\u2010learning approach to measure the anterior cruciate ligament injury risk in female basketball players","volume":"21","author":"Taborri J","year":"2021","journal-title":"Sensors"},{"issue":"11","key":"e_1_2_13_32_1","doi-asserted-by":"crossref","first-page":"3029","DOI":"10.3390\/s20113029","article-title":"Motion sensors\u2010based machine learning approach for the identification of anterior cruciate ligament gait patterns in on\u2010the\u2010field activities in rugby players","volume":"20","author":"Tedesco S","year":"2020","journal-title":"Sensors"},{"issue":"12","key":"e_1_2_13_33_1","doi-asserted-by":"crossref","first-page":"1629","DOI":"10.26603\/001c.126270","article-title":"Neurocognitive and neuromuscular rehabilitation techniques after ACL injury\u2014Part 2: maximizing performance in the advanced return to sport phase","volume":"19","author":"Thomas ZM","year":"2024","journal-title":"Int J Sports Phys Ther"},{"issue":"1","key":"e_1_2_13_34_1","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s40634-021-00346-x","article-title":"Machine learning methods in sport injury prediction and prevention: a systematic review","volume":"8","author":"Van Eetvelde H","year":"2021","journal-title":"J Exp Orthop"},{"issue":"7624","key":"e_1_2_13_35_1","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1136\/bmj.39335.541782.AD","article-title":"Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies","volume":"335","author":"Elm E","year":"2007","journal-title":"BMJ"},{"key":"e_1_2_13_36_1","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.86132","article-title":"Digital wearable insole\u2010based identification of knee arthropathies and gait signatures using machine learning","volume":"13","author":"Wipperman MF","year":"2024","journal-title":"eLife"},{"issue":"2","key":"e_1_2_13_37_1","doi-asserted-by":"crossref","DOI":"10.1177\/23259671261416130","article-title":"Epidemiology of pediatric lower\u2010extremity injuries in the 5 most popular US sports: a 10\u2010year analysis of National Injury Data (2015\u20132024)","volume":"14","author":"Wong L","year":"2026","journal-title":"Orthop J Sports Med"},{"issue":"9","key":"e_1_2_13_38_1","doi-asserted-by":"crossref","first-page":"3218","DOI":"10.1002\/ksa.12675","article-title":"Wearable health technology finds improvements in daily physical activity levels following total knee arthroplasty: a prospective study","volume":"33","author":"Wu KA","year":"2025","journal-title":"Knee Surg Sports Traumatol Arthrosc"}],"container-title":["Knee Surgery, Sports Traumatology, Arthroscopy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/esskajournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ksa.70631","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/esskajournals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/ksa.70631","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/esskajournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ksa.70631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T16:07:32Z","timestamp":1790698052000},"score":1,"resource":{"primary":{"URL":"https:\/\/esskajournals.onlinelibrary.wiley.com\/doi\/10.1002\/ksa.70631"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":37,"alternative-id":["10.1002\/ksa.70631"],"URL":"https:\/\/doi.org\/10.1002\/ksa.70631","archive":["Portico"],"relation":{},"ISSN":["0942-2056","1433-7347"],"issn-type":[{"value":"0942-2056","type":"print"},{"value":"1433-7347","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]},"assertion":[{"value":"2026-05-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"ksa.70631"}}