{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T08:48:52Z","timestamp":1792226932774,"version":"4.4.0"},"reference-count":88,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2024,2,4]],"date-time":"2024-02-04T00:00:00Z","timestamp":1707004800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2024,2,4]],"date-time":"2024-02-04T00:00:00Z","timestamp":1707004800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"},{"start":{"date-parts":[[2024,2,4]],"date-time":"2024-02-04T00:00:00Z","timestamp":1707004800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,2,4]],"date-time":"2024-02-04T00:00:00Z","timestamp":1707004800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/100007307","name":"Arthrex","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007307","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008542","name":"Arthroscopy Association of North America","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.fr","clinicalkey.jp","arthroscopyjournal.org","clinicalkey.es","clinicalkey.com.au","clinicalkey.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Arthroscopy"],"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To (1) review definitions and concepts necessary to interpret applications of deep learning (DL; a domain of artificial intelligence that leverages neural networks to make predictions on media inputs such as images) and (2) identify knowledge and translational gaps in the literature to provide insight into specific areas for improvement as adoption of this technology continues.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A comprehensive search of the literature was performed in December 2023 for articles regarding the use of DL in sports medicine. For each study, information regarding the joint of focus, specific anatomic structure\/pathology to which DL was applied, imaging modality utilized, source of images used for model training and testing, data set size, model performance, and whether the DL model was externally validated was recorded. A numerical scale was used to rate each DL model\u2019s clinical impact, with 1 corresponding to proof\u2010of\u2010concept studies with little to no direct clinical impact and 5 corresponding to practice\u2010changing clinical impact and ready for clinical deployment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Fifty\u2010five studies were identified, all of which were published within the past 5 years, while 82% were published within the past 3 years. Of the DL models identified, 84% were developed for classification tasks, 9% for automated measurements, and 7% for segmentation. A total of 62% of studies utilized magnetic resonance imaging as the imaging modality, 25% radiographs, and 7% ultrasound, while 1 study each used computed tomography, arthroscopic images, or arthroscopic video. Sixty\u2010five percent of studies focused on the detection of tears (anterior cruciate ligament [ACL], rotator cuff [RC], and meniscus). The diagnostic performance of ACL tears, as determined by the area under the receiver operator curve (AUROC), ranged from 0.81 to 0.99 for ACL tears (excellent to near perfect), 0.83 to 0.94 for RC tears (excellent), and from 0.75 to 0.96 for meniscus tears (acceptable to excellent). In addition, 3 studies focused on detection of cartilage lesions had AUROC ranging from 0.90 to 0.92 (excellent performance). However, only 4 (7%) studies externally validated their models, suggesting that they may not be generalizable or may not perform well when applied to populations other than that used to develop the model. Finally, the mean clinical impact score was 2 (range, 1\u20103) on scale of 1 to 5, corresponding to limited clinical applicability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>DL models in orthopaedic sports medicine show generally excellent performance (high internal validity) but require external validation to facilitate clinical deployment. In addition, current models have low clinical applicability and fail to advance the field due to a focus on routine tasks and a narrow conceptual framework.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of Evidence<\/jats:title>\n                    <jats:p>Level IV, scoping review of Level I to IV studies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1016\/j.arthro.2024.01.043","type":"journal-article","created":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T12:35:08Z","timestamp":1707136508000},"page":"455-472","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":23,"title":["Medical Imaging Applications Developed Using Artificial Intelligence Demonstrate High Internal Validity Yet Are Limited in Scope and Lack External Validation"],"prefix":"10.1002","volume":"41","author":[{"given":"Jacob F.","family":"Oeding","sequence":"first","affiliation":[{"name":"Mayo Clinic Alix School of Medicine Rochester Minnesota U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron J.","family":"Krych","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery Mayo Clinic Rochester Minnesota U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew D.","family":"Pearle","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery Hospital for Special Surgery New York New York U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bryan T.","family":"Kelly","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery Hospital for Special Surgery New York New York U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyle N.","family":"Kunze","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery Hospital for Special Surgery New York New York U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,2,4]]},"reference":[{"key":"e_1_2_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arthro.2022.04.016"},{"key":"e_1_2_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arthro.2020.08.009"},{"key":"e_1_2_2_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104803"},{"key":"e_1_2_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arthro.2020.09.012"},{"key":"e_1_2_2_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0316-z"},{"key":"e_1_2_2_7_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2018.11029"},{"key":"e_1_2_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2023.03.087"},{"key":"e_1_2_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00167-022-07213-x"},{"key":"e_1_2_2_10_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.30617"},{"key":"e_1_2_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2022.10.003"},{"key":"e_1_2_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00256-021-03879-5"},{"key":"e_1_2_2_13_2","doi-asserted-by":"publisher","DOI":"10.1097\/CORR.0000000000002385"},{"key":"e_1_2_2_14_2","doi-asserted-by":"publisher","DOI":"10.1097\/CORR.0000000000002705"},{"key":"e_1_2_2_15_2","doi-asserted-by":"publisher","DOI":"10.1302\/2633-1462.31.BJO-2021-0123.R1"},{"key":"e_1_2_2_16_2","doi-asserted-by":"publisher","DOI":"10.7326\/M18-0850"},{"key":"e_1_2_2_17_2","doi-asserted-by":"publisher","DOI":"10.1002\/9781118548387"},{"key":"e_1_2_2_18_2","doi-asserted-by":"publisher","DOI":"10.2106\/JBJS.21.01229"},{"key":"e_1_2_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2023.08.063"},{"key":"e_1_2_2_20_2","first-page":"1649","article-title":"THA\u2010AID: Deep learning tool for total hip arthroplasty automatic implant detection with uncertainty and outlier quantification","volume":"104","author":"Rouzrokh P.","year":"2023","journal-title":"J Arthroplasty"},{"key":"e_1_2_2_21_2","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210206"},{"key":"e_1_2_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2021.02.026"},{"key":"e_1_2_2_23_2","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230085"},{"key":"e_1_2_2_24_2","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.220067"},{"key":"e_1_2_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2022.12.013"},{"key":"e_1_2_2_26_2","article-title":"Deep\u2010learning automation of preoperative radiographic parameters associated with early periprosthetic femur fracture after total hip arthroplasty","author":"Jang S.J.","year":"2023","journal-title":"J Arthroplasty."},{"key":"e_1_2_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2023.03.006"},{"key":"e_1_2_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2023.02.015"},{"key":"e_1_2_2_29_2","doi-asserted-by":"publisher","DOI":"10.1302\/2633-1462.310.BJO-2022-0082.R1"},{"key":"e_1_2_2_30_2","doi-asserted-by":"publisher","DOI":"10.1002\/ksa.12018"},{"key":"e_1_2_2_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2015.07.010"},{"key":"e_1_2_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2017.01.003"},{"key":"e_1_2_2_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2022.100911"},{"key":"e_1_2_2_34_2","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210064"},{"key":"e_1_2_2_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.02.010"},{"key":"e_1_2_2_36_2","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018172986"},{"key":"e_1_2_2_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2019.02.007"},{"key":"e_1_2_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-019-00193-4"},{"key":"e_1_2_2_39_2","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180091"},{"key":"e_1_2_2_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00256-020-03410-2"},{"key":"e_1_2_2_41_2","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27266"},{"key":"e_1_2_2_42_2","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000664"},{"key":"e_1_2_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3081355"},{"key":"e_1_2_2_44_2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/4076175"},{"key":"e_1_2_2_45_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics11010105"},{"key":"e_1_2_2_46_2","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021200165"},{"key":"e_1_2_2_47_2","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2021.747217"},{"key":"e_1_2_2_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-022-08923-z"},{"key":"e_1_2_2_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00256-022-04081-x"},{"key":"e_1_2_2_50_2","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/7872500"},{"key":"e_1_2_2_51_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12891-022-05524-1"},{"key":"e_1_2_2_52_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12891-022-05468-6"},{"key":"e_1_2_2_53_2","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000031510"},{"key":"e_1_2_2_54_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102508"},{"key":"e_1_2_2_55_2","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph20126059"},{"key":"e_1_2_2_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2022.10.010"},{"key":"e_1_2_2_57_2","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.28284"},{"key":"e_1_2_2_58_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00167-023-07644-0"},{"key":"e_1_2_2_59_2","doi-asserted-by":"publisher","DOI":"10.1177\/23259671231215820"},{"key":"e_1_2_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00264-022-05676-8"},{"key":"e_1_2_2_61_2","article-title":"A deep learning model enhances clinicians\u2019 diagnostic accuracy to more than 96% for anterior cruciate ligament ruptures on magnetic resonance imaging","author":"Wang D.Y.","year":"2023","journal-title":"Arthroscopy."},{"key":"e_1_2_2_62_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00256-020-03463-3"},{"key":"e_1_2_2_63_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-72357-0"},{"key":"e_1_2_2_64_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06639-1"},{"key":"e_1_2_2_65_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-93026-w"},{"key":"e_1_2_2_66_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07070-7"},{"key":"e_1_2_2_67_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-08034-1"},{"key":"e_1_2_2_68_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00256-021-03740-9"},{"key":"e_1_2_2_69_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00256-022-04041-5"},{"key":"e_1_2_2_70_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00256-022-04008-6"},{"key":"e_1_2_2_71_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2022.103864"},{"key":"e_1_2_2_72_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-022-02502-6"},{"key":"e_1_2_2_73_2","doi-asserted-by":"publisher","DOI":"10.4103\/jmu.jmu_182_21"},{"key":"e_1_2_2_74_2","doi-asserted-by":"publisher","DOI":"10.3390\/jpm12010109"},{"key":"e_1_2_2_75_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xrrt.2022.03.002"},{"key":"e_1_2_2_76_2","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000951"},{"key":"e_1_2_2_77_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13018-023-03909-z"},{"key":"e_1_2_2_78_2","doi-asserted-by":"publisher","DOI":"10.1177\/03635465231189201"},{"key":"e_1_2_2_79_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.otsr.2023.103648"},{"key":"e_1_2_2_80_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e15804"},{"key":"e_1_2_2_81_2","article-title":"Deep learning to automatically classify very large sets of preoperative and postoperative shoulder arthroplasty radiographs","author":"Yang L.","year":"2023","journal-title":"J Shoulder Elbow Surg."},{"key":"e_1_2_2_82_2","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.220132"},{"key":"e_1_2_2_83_2","article-title":"Deep learning\u2010based screening tool for rotator cuff tears on shoulder radiography","author":"Iio R.","year":"2023","journal-title":"J Orthop Sci."},{"key":"e_1_2_2_84_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1070499"},{"key":"e_1_2_2_85_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jse.2023.03.028"},{"key":"e_1_2_2_86_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2023.10.010"},{"key":"e_1_2_2_87_2","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.28069"},{"key":"e_1_2_2_88_2","doi-asserted-by":"publisher","DOI":"10.52312\/jdrs.2023.996"},{"key":"e_1_2_2_89_2","doi-asserted-by":"publisher","DOI":"10.1177\/03635465221142280"}],"container-title":["Arthroscopy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0749806324000999?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0749806324000999?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/arthroscopyjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1016\/j.arthro.2024.01.043","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/arthroscopyjournals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1016\/j.arthro.2024.01.043","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/arthroscopyjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1016\/j.arthro.2024.01.043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T08:52:29Z","timestamp":1773564749000},"score":1,"resource":{"primary":{"URL":"https:\/\/arthroscopyjournals.onlinelibrary.wiley.com\/doi\/10.1016\/j.arthro.2024.01.043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,4]]},"references-count":88,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["10.1016\/j.arthro.2024.01.043"],"URL":"https:\/\/doi.org\/10.1016\/j.arthro.2024.01.043","archive":["Portico"],"relation":{},"ISSN":["0749-8063","1526-3231"],"issn-type":[{"value":"0749-8063","type":"print"},{"value":"1526-3231","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Medical Imaging Applications Developed Using Artificial Intelligence Demonstrate High Internal Validity Yet Are Limited in Scope and Lack External Validation","name":"articletitle","label":"Article Title"},{"value":"Arthroscopy: The Journal of Arthroscopic & Related Surgery","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.arthro.2024.01.043","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 by the Arthroscopy Association of North America","name":"copyright","label":"Copyright"}]}}