{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T11:50:59Z","timestamp":1781783459029,"version":"3.54.5"},"reference-count":29,"publisher":"BMJ","issue":"6","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"unspecified","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2026,5,26]]},"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To evaluate the feasibility of using wearable inertial measurement units (IMUs; small body-worn sensors that capture linear acceleration and angular velocity) combined with machine learning (ML) to identify anterior cruciate ligament (ACL) injuries during clinical knee joint laxity assessments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>Prospective exploratory feasibility study using a case\u2013control design. A feed-forward neural network classifier was trained on time-normalised IMU signals recorded during Lachman and Anterior Drawer tests to distinguish ACL-injured from healthy knees. Model performance was assessed using 10-fold participant-level cross-validation and reported at repetition-wise and subject-wise levels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Biomechanics laboratory within a secondary care setting in London, UK. Recruitment occurred through an acute soft-tissue injury management clinic.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>50 participants were recruited: 26 healthy controls and 24 individuals with an MRI-confirmed ACL injury (partial or complete) sustained within the current injury episode. Healthy controls contributed 52 uninjured legs and ACL-injured participants contributed 25 injured and 23 contralateral uninjured legs (including 1 bilateral injury). Inclusion criteria for the injured group were acute knee injury, MRI-confirmed ACL tear and ability to bear weight. Controls were \u226518 years with no history of knee ligament injury. Exclusion criteria included age &lt;18\u2009or &gt;45, chronic joint conditions, non-weightbearing status, pregnancy, allergy to adhesives or inability to provide informed consent. All participants completed the study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Interventions<\/jats:title>\n                    <jats:p>Not applicable. Participants underwent standardised clinical Lachman and Anterior Drawer tests performed by a specialist physiotherapist while IMUs were mounted on the femur and tibia using a custom three-dimensional-printed rig.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary and secondary outcome measures<\/jats:title>\n                    <jats:p>The primary outcome was diagnostic accuracy of an ML model classifying ACL injury status (injured vs healthy) based on IMU-derived linear acceleration and angular velocity (three axes per sensor). Secondary outcomes included sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under the receiver operating characteristic curve (AUROC) and F1 score. Planned model assessments (repetition-wise and subject-wise) were completed as intended. Hyperparameter adjustments were made post hoc to address overfitting when expanding to the full dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Across the full dataset (n=50), the comparative leg model (method 2) achieved a subject-wise diagnostic accuracy of 81%, sensitivity 83%, specificity 79%, PPV 80% and NPV 83% using 10-fold participant-level cross-validation. Repetition-wise accuracy was 71%. Discriminative performance was moderate (AUROC 0.773), with an F1 score of 0.889. The individual leg model (method 1) showed lower performance (subject-wise accuracy 70%; sensitivity 43%; specificity 81%).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study supports the feasibility of wearable sensors to be used in the clinical assessment of ACL injury to assist in capturing movement features associated with joint laxity. More work should be done to increase generalisability and validate findings further.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2025-107409","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T10:50:50Z","timestamp":1781779850000},"page":"e107409","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Wearable sensor technology and machine learning for anterior cruciate ligament injury diagnosis: an exploratory feasibility study"],"prefix":"10.1136","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3033-6387","authenticated-orcid":false,"given":"Natasha E.H","family":"Allott","sequence":"first","affiliation":[{"name":"Department of Surgery and Cancer, Imperial College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Metin","family":"Bicer","sequence":"additional","affiliation":[{"name":"Department of Surgery and Cancer, Imperial College London, London, UK"},{"name":"Institute of Informatics, Hacettepe University, Ankara, Turkey"},{"name":"Faculty of Medical Science, Newcastle University Translational and Clinical Research Institute, Newcastle upon Tyne, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Korgaonkar","sequence":"additional","affiliation":[{"name":"Department of Surgery and Cancer, Imperial College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rhidian","family":"Thomas","sequence":"additional","affiliation":[{"name":"Department of Surgery and Cancer, Imperial College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6672-5379","authenticated-orcid":false,"given":"Matthew S.","family":"Banger","sequence":"additional","affiliation":[{"name":"Department of Surgery and Cancer, Imperial College London, London, UK"},{"name":"Surgery and Cancer\/Human Performance Group, Imperial College London, White City Campus, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alison H","family":"McGregor","sequence":"additional","affiliation":[{"name":"Surgery and Cancer\/Human Performance Group, Imperial College London, White City Campus, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,6,18]]},"reference":[{"key":"2026061803501930000_16.6.e107409.1","doi-asserted-by":"crossref","unstructured":"Adesida Y , Papi E , McGregor AH . Exploring the Role of Wearable Technology in Sport Kinematics and Kinetics: A Systematic Review. Sensors (Basel) 2019;19. doi:10.3390\/s19071597","DOI":"10.3390\/s19071597"},{"key":"2026061803501930000_16.6.e107409.2","doi-asserted-by":"crossref","first-page":"2064","DOI":"10.1007\/s00167-013-2610-0","article-title":"Use of a gyroscope sensor to quantify tibial motions during a pivot shift test","volume":"22","author":"Borgstrom","year":"2014","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"key":"2026061803501930000_16.6.e107409.3","doi-asserted-by":"crossref","first-page":"2330","DOI":"10.1007\/s00167-014-3056-8","article-title":"Quantitative pivot shift assessment using combined inertial and magnetic sensing","volume":"23","author":"Labb\u00e9","year":"2015","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"key":"2026061803501930000_16.6.e107409.4","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1053\/j.oto.2008.12.010","article-title":"Measurement of Knee Laxity and Pivot-Shift Kinematics With Magnetic Sensors","volume":"18","author":"Amis","year":"2008","journal-title":"Oper Tech Orthop"},{"key":"2026061803501930000_16.6.e107409.5","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1002\/jor.20966","article-title":"Pivot-shift test: analysis and quantification of knee laxity parameters using a navigation system","volume":"28","author":"Lopomo","year":"2010","journal-title":"J Orthop Res"},{"key":"2026061803501930000_16.6.e107409.6","doi-asserted-by":"crossref","first-page":"2377","DOI":"10.1007\/s00167-015-3740-3","article-title":"Evaluation of pivot shift phenomenon while awake and under anaesthesia by different manoeuvres using triaxial accelerometer","volume":"25","author":"Nakamura","year":"2017","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"key":"2026061803501930000_16.6.e107409.7","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/j.knee.2021.04.007","article-title":"Acute knee clinics are effective in reducing delay to diagnosis following anterior cruciate ligament injury","volume":"30","author":"Clifford","year":"2021","journal-title":"Knee"},{"key":"2026061803501930000_16.6.e107409.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.csm.2012.08.017"},{"key":"2026061803501930000_16.6.e107409.9","doi-asserted-by":"crossref","DOI":"10.1186\/s12891-022-05595-0","article-title":"Evaluating the diagnostic pathway for acute ACL injuries in trauma centres: a systematic review","volume":"23","author":"Allott","year":"2022","journal-title":"BMC Musculoskelet Disord"},{"key":"2026061803501930000_16.6.e107409.10","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1016\/j.jemermed.2019.09.003","article-title":"Implementing the Lever Sign in the Emergency Department: Does it Assist in Acute Anterior Cruciate Ligament Rupture Diagnosis? A Pilot Study","volume":"57","author":"McQuivey","year":"2019","journal-title":"J Emerg Med"},{"key":"2026061803501930000_16.6.e107409.11","doi-asserted-by":"publisher","DOI":"10.1016\/0020-1383(96)00033-2"},{"key":"2026061803501930000_16.6.e107409.12","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.knee.2015.09.016","article-title":"Anterior cruciate ligament injury: A persistently difficult diagnosis","volume":"23","author":"Parwaiz","year":"2016","journal-title":"Knee"},{"key":"2026061803501930000_16.6.e107409.13","doi-asserted-by":"crossref","unstructured":"Borgstrom PH , et al . Use of inertial sensors for quantifying the pivot shift maneuver. In: Rotatory Knee Instability: An Evidence Based Approach. 2016: 299\u2013307.","DOI":"10.1007\/978-3-319-32070-0_25"},{"key":"2026061803501930000_16.6.e107409.14","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1007\/s12178-016-9333-z","article-title":"Assessment of the pivot shift using inertial sensors","volume":"9","author":"Zaffagnini","year":"2016","journal-title":"Curr Rev Musculoskelet Med"},{"key":"2026061803501930000_16.6.e107409.15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/2325967113487855","article-title":"Differences in Knee Kinematics Between Awake and Anesthetized Patients During the Lachman and Pivot-Shift Tests for Anterior Cruciate Ligament Deficiency","volume":"1","author":"Matsushita","year":"2013","journal-title":"Orthop J Sports Med"},{"key":"2026061803501930000_16.6.e107409.16","doi-asserted-by":"crossref","first-page":"1862","DOI":"10.1016\/j.injury.2013.07.024","article-title":"Anterior cruciate ligament rupture: Delay to diagnosis","volume":"44","author":"Perera","year":"2013","journal-title":"Injury"},{"key":"2026061803501930000_16.6.e107409.17","first-page":"1078","article-title":"Diagnosis of anterior cruciate ligament rupture in an emergency department","volume":"65","author":"Guillodo","year":"2008","journal-title":"J Trauma"},{"key":"2026061803501930000_16.6.e107409.18","unstructured":"van Eck CF , et al . Methods to diagnose acute anterior cruciate ligament rupture: a meta-analysis of instrumented knee laxity tests. 2013.1433\u20137347."},{"key":"2026061803501930000_16.6.e107409.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.annemergmed.2017.08.005"},{"key":"2026061803501930000_16.6.e107409.20","doi-asserted-by":"publisher","DOI":"10.1016\/J.IJIN.2022.05.002"},{"key":"2026061803501930000_16.6.e107409.21","doi-asserted-by":"publisher","DOI":"10.1136\/bmjinnov-2019-000359"},{"key":"2026061803501930000_16.6.e107409.22","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1302\/2046-3758.73.BJR-2017-0147.R1","article-title":"Artificial intelligence, machine learning and the evolution of healthcare","volume":"7","author":"Jones","year":"2018","journal-title":"Bone Joint Res"},{"key":"2026061803501930000_16.6.e107409.23","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-022-00614-9","article-title":"Machine learning generalizability across healthcare settings: insights from multi-site COVID-19 screening","volume":"5","author":"Yang","year":"2022","journal-title":"NPJ Digit Med"},{"key":"2026061803501930000_16.6.e107409.24","first-page":"26","article-title":"Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimizationb","volume":"17","author":"Wu","year":"2019","journal-title":"Journal of Electronic Science and Technology"},{"key":"2026061803501930000_16.6.e107409.25","doi-asserted-by":"crossref","DOI":"10.1155\/2022\/4653923","article-title":"Machine Learning for Healthcare Wearable Devices: The Big Picture","volume":"2022","author":"Sabry","year":"2022","journal-title":"J Healthc Eng"},{"key":"2026061803501930000_16.6.e107409.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.061"},{"key":"2026061803501930000_16.6.e107409.27","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-022-00577-x","article-title":"A high-generalizability machine learning framework for predicting the progression of Alzheimer\u2019s disease using limited data","volume":"5","author":"Wang","year":"2022","journal-title":"NPJ Digit Med"},{"key":"2026061803501930000_16.6.e107409.28","doi-asserted-by":"crossref","DOI":"10.2196\/28856","article-title":"Reliable Prediction Models Based on Enriched Data for Identifying the Mode of Childbirth by Using Machine Learning Methods: Development Study","volume":"23","author":"Ullah","year":"2021","journal-title":"J Med Internet Res"},{"key":"2026061803501930000_16.6.e107409.29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.01.011"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2025-107409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T10:50:57Z","timestamp":1781779857000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2025-107409"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":29,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,18]]},"published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1136\/bmjopen-2025-107409"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2025-107409","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}