{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:43:12Z","timestamp":1786120992410,"version":"build-2736575974"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005760","name":"University of Gothenburg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005760","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Musculoskelet Disord"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Over 100,000 patients undergo ACLR each year in the United States, providing rich electronic medical record data to improve outcomes, but manual chart review can be time-consuming and expensive. Natural language processing (NLP) methods have been successfully used to extract information for other orthopaedic operative procedures (e.g., hip and knee arthroplasties). Different subspecialities, however, use diverse terminology or \u201csublanguages\u201d to describe clinical concepts and NLP models perform better concept extraction when trained on specialty-specific texts. Therefore, the purpose of this study was to develop and validate a reliable NLP pipeline to extract meaningful clinical data elements (e.g., graft type, meniscal involvement) from ACLR operative reports.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Operative reports for a training and test set were randomly selected based on surgeon volume and year from individuals who underwent ACLR within a single healthcare system between 2013 and 2021. Clinical Language Annotation, Modeling, and Processing Toolkit (CLAMP) was utilized to train a domain-specific model and build a pipeline for data extraction of clinically meaningful data elements, including injury-related factors and surgical factors. Relevancy metrics were calculated using values identified by a single clinician as the gold standard.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Overall, the individuals selected for the training and test sets (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009437 total) were 26.6 \u00b1 10.9 years old, and 43.5% were female, similar to the age (26.7 \u00b1 11.5 years) and proportion of females (43.0%) in the full data set (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u20095,818). Priority entities, including the side of surgery, ACL graft type, ACL procedure, and meniscal involvement, were identified with F1 scores between 0.87-1.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>F1 scores of 0.87-1 were attained for several priority entities using a modest set of annotated ACL operative reports to train the model and an NLP tool designed for non-expert use. The NLP pipelines have the potential to extract relevant operative information for a large cohort of patients to support clinical research, such as identifying predictors of subsequent surgery after ACLR. This work can also inform the planning of future studies using larger training sets and more advanced NLP methods.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12891-026-10091-w","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:46:25Z","timestamp":1786063585000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of natural language processing pipelines to extract injury and surgery-related data elements from ACL reconstruction operative reports"],"prefix":"10.1186","volume":"27","author":[{"given":"Kathleen M.","family":"Poploski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bicen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott","family":"Rothenberger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Galen","family":"Switzer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sahil","family":"Dadoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Cong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin J.","family":"Greiner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan D.","family":"Hughes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Volker","family":"Musahl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James J.","family":"Irrgang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard D.","family":"Boyce","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,7]]},"reference":[{"issue":"7","key":"10091_CR1","doi-asserted-by":"publisher","first-page":"1534","DOI":"10.1177\/0363546513490277","volume":"41","author":"CM Hettrich","year":"2013","unstructured":"Hettrich CM, Dunn WR, Reinke EK, Spindler KP. The rate of subsequent surgery and predictors after anterior cruciate ligament reconstruction: two- and 6-year follow-up results from a multicenter cohort. Am J Sports Med. 2013;41(7):1534\u201340.","journal-title":"Am J Sports Med"},{"issue":"10","key":"10091_CR2","doi-asserted-by":"publisher","first-page":"2418","DOI":"10.1177\/0363546520935867","volume":"48","author":"JP Sullivan","year":"2020","unstructured":"Sullivan JP, Huston LJ, Zajichek A, Reinke EK, Andrish JT, Brophy RH, et al. Incidence and predictors of subsequent surgery after anterior cruciate ligament reconstruction: a 6-year follow-up study. Am J Sports Med. 2020;48(10):2418\u201328.","journal-title":"Am J Sports Med"},{"issue":"12","key":"10091_CR3","doi-asserted-by":"publisher","first-page":"2894","DOI":"10.1177\/0363546518790507","volume":"46","author":"TL Sanders","year":"2018","unstructured":"Sanders TL, Pareek A, Desai VS, Hewett TE, Levy BA, Stuart MJ, et al. Low accuracy of diagnostic codes to identify anterior cruciate ligament tear in orthopaedic database research. Am J Sports Med. 2018;46(12):2894\u20138.","journal-title":"Am J Sports Med"},{"issue":"4","key":"10091_CR4","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1007\/s00167-022-07272-0","volume":"31","author":"JA Pruneski","year":"2023","unstructured":"Pruneski JA, Pareek A, Nwachukwu BU, Martin RK, Kelly BT, Karlsson J, et al. Natural language processing: using artificial intelligence to understand human language in orthopedics. Knee Surg Sports Traumatol Arthrosc. 2023;31(4):1203\u201311.","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"key":"10091_CR5","doi-asserted-by":"crossref","unstructured":"Shah RF, Bini S, Vail T. Data for registry and quality review can be retrospectively collected using natural language processing from unstructured charts of arthroplasty patients. Bone Joint J. 2020;102-b(7_Supple_B):99\u2013104.","DOI":"10.1302\/0301-620X.102B7.BJJ-2019-1574.R1"},{"issue":"3","key":"10091_CR6","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1016\/j.arth.2020.09.029","volume":"36","author":"E Sagheb","year":"2021","unstructured":"Sagheb E, Ramazanian T, Tafti AP, Fu S, Kremers WK, Berry DJ, et al. Use of natural language processing algorithms to identify common data elements in operative notes for knee arthroplasty. J Arthroplasty. 2021;36(3):922\u20136.","journal-title":"J Arthroplasty"},{"issue":"21","key":"10091_CR7","doi-asserted-by":"publisher","first-page":"1931","DOI":"10.2106\/JBJS.19.00071","volume":"101","author":"CC Wyles","year":"2019","unstructured":"Wyles CC, Tibbo ME, Fu S, Wang Y, Sohn S, Kremers WK, et al. Use of natural language processing algorithms to identify common data elements in operative notes for total hip arthroplasty. J Bone Joint Surg Am. 2019;101(21):1931\u20138.","journal-title":"J Bone Joint Surg Am"},{"key":"10091_CR8","first-page":"737","volume":"2015","author":"Y Kim","year":"2015","unstructured":"Kim Y, Riloff E, Hurdle JF. A study of concept extraction across different types of clinical notes. AMIA Annu Symp Proc. 2015;2015:737\u201346.","journal-title":"AMIA Annu Symp Proc"},{"issue":"4","key":"10091_CR9","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1093\/jamia\/ocab204","volume":"29","author":"S Visweswaran","year":"2022","unstructured":"Visweswaran S, McLay B, Cappella N, Morris M, Milnes JT, Reis SE, et al. An atomic approach to the design and implementation of a research data warehouse. J Am Med Inf Assoc. 2022;29(4):601\u20138.","journal-title":"J Am Med Inf Assoc"},{"issue":"3","key":"10091_CR10","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1093\/jamia\/ocx132","volume":"25","author":"E Soysal","year":"2018","unstructured":"Soysal E, Wang J, Jiang M, Wu Y, Pakhomov S, Liu H, et al. CLAMP - a toolkit for efficiently building customized clinical natural language processing pipelines. J Am Med Inf Assoc. 2018;25(3):331\u20136.","journal-title":"J Am Med Inf Assoc"},{"issue":"10","key":"10091_CR11","doi-asserted-by":"publisher","first-page":"2459","DOI":"10.1007\/s11999-017-5278-9","volume":"475","author":"BT Samuelsen","year":"2017","unstructured":"Samuelsen BT, Webster KE, Johnson NR, Hewett TE, Krych AJ. Hamstring autograft versus patellar tendon autograft for ACL reconstruction: is there a difference in graft failure rate? A meta-analysis of 47,613 patients. Clin Orthop Relat Res. 2017;475(10):2459\u201368.","journal-title":"Clin Orthop Relat Res"},{"issue":"2","key":"10091_CR12","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.knee.2019.12.003","volume":"27","author":"R Rahardja","year":"2020","unstructured":"Rahardja R, Zhu M, Love H, Clatworthy MG, Monk AP, Young SW. Factors associated with revision following anterior cruciate ligament reconstruction: A systematic review of registry data. Knee. 2020;27(2):287\u201399.","journal-title":"Knee"},{"issue":"3","key":"10091_CR13","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1177\/0363546513511416","volume":"42","author":"RP Csintalan","year":"2014","unstructured":"Csintalan RP, Inacio MC, Funahashi TT, Maletis GB. Risk factors of subsequent operations after primary anterior cruciate ligament reconstruction. Am J Sports Med. 2014;42(3):619\u201325.","journal-title":"Am J Sports Med"},{"issue":"14","key":"10091_CR14","doi-asserted-by":"publisher","first-page":"3216","DOI":"10.1177\/0363546517721685","volume":"45","author":"BR Davis","year":"2017","unstructured":"Davis BR, Chen J, Inacio MCS, Love R, Prentice HA, Maletis GB. The incidence of subsequent meniscal murgery is higher in the anterior cruciate ligament-reconstructed knee than in the contralateral knee. Am J Sports Med. 2017;45(14):3216\u201322.","journal-title":"Am J Sports Med"},{"key":"10091_CR15","doi-asserted-by":"publisher","unstructured":"Shen X, Qin Y, Zuo J, Liu T, Xiao J. A systematic review of risk factors for anterior cruciate ligament reconstruction failure. Int J Sports Med. 2021. https:\/\/doi.org\/10.1055\/a-1393-6282.","DOI":"10.1055\/a-1393-6282"},{"issue":"11","key":"10091_CR16","doi-asserted-by":"publisher","first-page":"3441","DOI":"10.1007\/s00167-019-05389-3","volume":"27","author":"M Sarraj","year":"2019","unstructured":"Sarraj M, Coughlin RP, Solow M, Ekhtiari S, Simunovic N, Krych AJ, et al. Anterior cruciate ligament reconstruction with concomitant meniscal surgery: a systematic review and meta-analysis of outcomes. Knee Surg Sports Traumatol Arthrosc. 2019;27(11):3441\u201352.","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"issue":"5","key":"10091_CR17","doi-asserted-by":"publisher","first-page":"1296","DOI":"10.1177\/0363546521997101","volume":"49","author":"EP Young","year":"2021","unstructured":"Young EP, Chan PH, Prentice HA, Amar K, Hurvitz AP, Khan NA. Aseptic revision and reoperation risk after meniscectomy at the time of anterior cruciate ligament reconstruction. Am J Sports Med. 2021;49(5):1296\u2013304.","journal-title":"Am J Sports Med"},{"key":"10091_CR18","doi-asserted-by":"publisher","unstructured":"Hassanpour S, Langlotz CP, Amrhein TJ, Befera NT, Lungren MP. Performance of a machine learning classifier of knee MRI reports in two large academic radiology practices: a tool to estimate diagnostic yield. AJR Am J Roentgenol. 2017(4):750\u20133. https:\/\/doi.org\/10.2214\/AJR.16.16128.","DOI":"10.2214\/AJR.16.16128"},{"issue":"8","key":"10091_CR19","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1097\/RLI.0000000000000664","volume":"55","author":"C Germann","year":"2020","unstructured":"Germann C, Marbach G, Civardi F, Fucentese SF, Fritz J, Sutter R, et al. Deep convolutional neural network\u2013based diagnosis of anterior cruciate ligament tears: performance comparison of homogenous versus heterogeneous knee MRI cohorts with different pulse sequence protocols and 1.5-T and 3-T magnetic field strengths. Invest Radiol. 2020;55(8):499.","journal-title":"Invest Radiol"},{"key":"10091_CR20","doi-asserted-by":"publisher","first-page":"102847","DOI":"10.1016\/j.artmed.2024.102847","volume":"151","author":"N Tavabi","year":"2024","unstructured":"Tavabi N, Pruneski J, Golchin S, Singh M, Sanborn R, Heyworth B, et al. Building large-scale registries from unstructured clinical notes using a low-resource natural language processing pipeline. Artif Intell Med. 2024;151:102847.","journal-title":"Artif Intell Med"},{"key":"10091_CR21","doi-asserted-by":"publisher","unstructured":"Poploski KM, Wang B, Dadoo S, Moorhead J, Rothenberger S, Switzer G, Hughes JD, Musahl V, Boyce RD, Irrgang JJ. Predicting risk of unplanned subsequent knee surgery following ACL reconstruction. BMC Musculoskelet Disord. 2026. https:\/\/doi.org\/10.1186\/s12891-026-09925-4.","DOI":"10.1186\/s12891-026-09925-4"}],"container-title":["BMC Musculoskeletal Disorders"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12891-026-10091-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12891-026-10091-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12891-026-10091-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T02:25:29Z","timestamp":1786069529000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12891-026-10091-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,7]]},"references-count":21,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["10091"],"URL":"https:\/\/doi.org\/10.1186\/s12891-026-10091-w","relation":{},"ISSN":["1471-2474"],"issn-type":[{"value":"1471-2474","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,7]]},"assertion":[{"value":"24 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The Institutional Review Board at the University of Pittsburgh reviewed and determined the study meets the regulatory requirements for exempt research under 45 CFR 46.104 (IRB: STUDY21030078). Per the aforementioned institutional review board guidelines and review, informed consent to participate was not required from study participants. The present study adhered to the guidelines and principles of the Declaration of Helsinki.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"James J. Irrgang is President of the Board of Directors for the Journal of Orthopaedic and Sports Physical Therapy. Volker Musahl reports a relationship with Smith and Nephew Inc. that includes consulting or advisory, funding grants, and speaking and lecture fees. Volker Musahl reports a relationship with Arthrex Inc. that includes funding grants. Volker Musahl reports a relationship with DePuy Synthes that includes funding grants. Volker Musahl reports a relationship with International Society of Arthroscopy Knee Surgery and Orthopaedic Sports Medicine that includes board membership. Volker Musahl is deputy editor of Knee Surgery, Sports Traumatology, Arthroscopy. Jonathan D. Hughes is on the editorial board of Knee Surgery, Sports Traumatology, Arthroscopy. Jonathan D. Hughes reports educational funding from Smith and Nephew, Arthrex, and MidAtlantic Solutions. The remaining authors declare no conflicts of interest.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"659"}}