{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T05:41:20Z","timestamp":1781329280450,"version":"3.54.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T00:00:00Z","timestamp":1740960000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T00:00:00Z","timestamp":1740960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Hasso-Plattner-Institut f\u00fcr Digital Engineering gGmbH"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Background<\/jats:title>\n            <jats:p>Duration of surgery (DOS) varies substantially for patients with hip and knee arthroplasty (HA\/KA) and is a major risk factor for adverse events. We therefore aimed (1) to identify whether machine learning can predict DOS in HA\/KA patients using retrospective data available before surgery with reasonable performance, (2) to compare whether machine learning is able to outperform multivariable regression in predictive performance and (3) to identify the most important predictor variables for DOS both in a multi- and single-hospital context.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>eXtreme Gradient Boosting (XGBoost) and multivariable linear regression were used for predictions. Both models were applied to both the whole dataset which included multiple hospitals (3,704 patients), and a single-hospital dataset (1,815 patients) of the hospital with the highest case-volumes of our sample. Data was split into training (75%) and test data (25%) for both datasets. Models were trained using 5-fold cross-validation (CV) on the training datasets and applied to test data for performance comparison.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>On test data in the multi-hospital setting, the mean absolute error (MAE) was 12.13\u00a0min (HA) \/ 13.61\u00a0min (KA) for XGBoost. In the single-hospital analysis, performance on test data was MAE 10.87\u00a0min (HA) \/ MAE 12.53\u00a0min (KA) for XGBoost. Predictive ability of XGBoost was tended to be better than of regression in all setting, however not statistically significantly. Important predictors for XGBoost were physician experience, age, body mass index, patient reported outcome measures and, for the multi-hospital analysis, the hospital.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>Machine learning can predict DOS in both a multi-hospital and single-hospital setting with reasonable performance. Performance between regression and machine learning differed slightly, however insignificantly, while larger datasets may improve predictive performance. The study found that hospital indicators matter in the multi-hospital setting despite controlling for various variables, highlighting potential quality differences between hospitals.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Trial registration<\/jats:title>\n            <jats:p>The study was registered at the German Clinical Trials Register (DRKS) under DRKS00019916.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1186\/s12911-025-02927-7","type":"journal-article","created":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T13:05:02Z","timestamp":1741007102000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Leveraging machine learning for duration of surgery prediction in knee and hip arthroplasty \u2013 a development and validation study"],"prefix":"10.1186","volume":"25","author":[{"given":"Benedikt","family":"Langenberger","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Schrednitzki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Halder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reinhard","family":"Busse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph","family":"Pross","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,3]]},"reference":[{"key":"2927_CR1","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1186\/s12891-016-1025-8","volume":"17","author":"LL Jasper","year":"2016","unstructured":"Jasper LL, Jones CA, Mollins J, Pohar SL, Beaupre LA. Risk factors for revision of total knee arthroplasty: a scoping review. BMC Musculoskelet Disord. 2016;17:182.","journal-title":"BMC Musculoskelet Disord"},{"key":"2927_CR2","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1302\/0301-620X.101B6.BJJ-2018-1400.R1","volume":"101\u2013B","author":"LL Nowak","year":"2019","unstructured":"Nowak LL, Schemitsch EH. Duration of surgery affects the risk of complications following total hip arthroplasty. bone Joint J. 2019;101\u2013B:51\u20136.","journal-title":"bone Joint J"},{"key":"2927_CR3","doi-asserted-by":"crossref","unstructured":"Triantafyllopoulos G, Stundner O, Memtsoudis S, Poultsides LA. Patient, Surgery, and Hospital Related Risk Factors for Surgical Site Infections following Total Hip Arthroplasty. TheScientificWorldJournal. 2015;2015:979560.","DOI":"10.1155\/2015\/979560"},{"key":"2927_CR4","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.eclinm.2019.09.015","volume":"16","author":"B Ravi","year":"2019","unstructured":"Ravi B, Jenkinson R, O\u2019Heireamhoin S, Austin PC, Aktar S, Leroux TS, et al. Surgical duration is associated with an increased risk of periprosthetic infection following total knee arthroplasty: a population-based retrospective cohort study. EClinicalMedicine. 2019;16:74\u201380.","journal-title":"EClinicalMedicine"},{"key":"2927_CR5","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1186\/s12891-017-1915-4","volume":"18","author":"M Badawy","year":"2017","unstructured":"Badawy M, Espehaug B, Fenstad AM, Indrekvam K, Dale H, Havelin LI, et al. Patient and surgical factors affecting procedure duration and revision risk due to deep infection in primary total knee arthroplasty. BMC Musculoskelet Disord. 2017;18:544.","journal-title":"BMC Musculoskelet Disord"},{"key":"2927_CR6","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.arth.2010.04.008","volume":"25","author":"SM Jafari","year":"2010","unstructured":"Jafari SM, Huang R, Joshi A, Parvizi J, Hozack WJ. Renal impairment following total joint arthroplasty: who is at risk? J Arthroplast. 2010;25:49\u201353. 53.e1-2.","journal-title":"J Arthroplast"},{"key":"2927_CR7","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s12911-022-01751-7","volume":"22","author":"B Langenberger","year":"2022","unstructured":"Langenberger B, Thoma A, Vogt V. Can minimal clinically important differences in patient reported outcome measures be predicted by machine learning in patients with total knee or hip arthroplasty? A systematic review. BMC Med Inf Decis Mak. 2022;22:18.","journal-title":"BMC Med Inf Decis Mak"},{"key":"2927_CR8","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1302\/2046-3758.129.BJR-2023-0070.R2","volume":"12","author":"B Langenberger","year":"2023","unstructured":"Langenberger B, Schrednitzki D, Halder AM, Busse R, Pross CM. Predicting whether patients will achieve minimal clinically important differences following hip or knee arthroplasty. Bone Joint Res. 2023;12:512\u201321.","journal-title":"Bone Joint Res"},{"key":"2927_CR9","doi-asserted-by":"publisher","first-page":"100111","DOI":"10.1016\/j.ibmed.2023.100111","volume":"8","author":"B Langenberger","year":"2023","unstructured":"Langenberger B. Who will stay a little longer? Predicting length of stay in hip and knee arthroplasty patients using machine learning. Intelligence-Based Med. 2023;8:100111.","journal-title":"Intelligence-Based Med"},{"key":"2927_CR10","doi-asserted-by":"crossref","unstructured":"Houserman DJ, Berend KR, Lombardi AV, Duhaime EP, Jain A, Crawford DA. The viability of an Artificial Intelligence\/Machine Learning Prediction Model to determine candidates for knee arthroplasty. The Journal of arthroplasty 2022.","DOI":"10.1016\/j.arth.2022.04.003"},{"key":"2927_CR11","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1016\/j.artd.2021.01.006","volume":"8","author":"EM Polce","year":"2021","unstructured":"Polce EM, Kunze KN, Paul KM, Levine BR. Machine learning predicts femoral and Tibial Implant Size Mismatch for Total Knee Arthroplasty. Arthroplasty Today. 2021;8:268\u2013e2772.","journal-title":"Arthroplasty Today"},{"key":"2927_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/2573234X.2021.1873078","volume":"4","author":"E Mortaz","year":"2021","unstructured":"Mortaz E, Dag A, Hutzler L, Gharibo C, Anzisi L, Bosco J. Short-term prediction of opioid prescribing patterns for orthopaedic surgical procedures: a machine learning framework. J Bus Analytics. 2021;4:1\u201313.","journal-title":"J Bus Analytics"},{"key":"2927_CR13","doi-asserted-by":"publisher","first-page":"E39","DOI":"10.1097\/NNR.0000000000000602","volume":"71","author":"AA\u00d8 Buus","year":"2022","unstructured":"Buus AA\u00d8, Udsen FW, Laugesen B, El-Galaly A, Laursen M, Hejlesen OK. Patient-reported outcomes for function and Pain in total knee arthroplasty patients. Nurs Res. 2022;71:E39\u201347.","journal-title":"Nurs Res"},{"key":"2927_CR14","doi-asserted-by":"publisher","first-page":"104670","DOI":"10.1016\/j.ijmedinf.2021.104670","volume":"158","author":"A Abbas","year":"2022","unstructured":"Abbas A, Mosseri J, Lex JR, Toor J, Ravi B, Khalil EB, et al. Machine learning using preoperative patient factors can predict duration of surgery and length of stay for total knee arthroplasty. Int J Med Informatics. 2022;158:104670.","journal-title":"Int J Med Informatics"},{"key":"2927_CR15","doi-asserted-by":"crossref","unstructured":"Panch T, Szolovits P, Atun R. Artificial intelligence, machine learning and health systems. J Global Health;8.","DOI":"10.7189\/jogh.08.020303"},{"key":"2927_CR16","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1186\/s12874-020-01046-3","volume":"20","author":"JJ Levy","year":"2020","unstructured":"Levy JJ, O\u2019Malley AJ. Don\u2019t dismiss logistic regression: the case for sensible extraction of interactions in the era of machine learning. BMC Med Res Methodol. 2020;20:171.","journal-title":"BMC Med Res Methodol"},{"key":"2927_CR17","doi-asserted-by":"crossref","unstructured":"Lazic I, Hinterwimmer F, Langer S, Pohlig F, Suren C, Seidl F et al. Prediction of complications and surgery duration in primary total hip arthroplasty using machine learning: the necessity of modified algorithms and Specific Data. Journal of clinical medicine 2022;11.","DOI":"10.3390\/jcm11082147"},{"key":"2927_CR18","doi-asserted-by":"crossref","unstructured":"Hinterwimmer F, Lazic I, Langer S, Suren C, Charitou F, Hirschmann MT et al. Prediction of complications and surgery duration in primary TKA with high accuracy using machine learning with arthroplasty-specific data. Knee surgery, sports traumatology, arthroscopy official journal of the ESSKA 2022.","DOI":"10.1007\/s00167-022-06957-w"},{"key":"2927_CR19","doi-asserted-by":"crossref","unstructured":"Yeo I, Klemt C, Melnic CM, Pattavina MH, de Oliveira BMC, Kwon Y-M. Predicting surgical operative time in primary total knee arthroplasty utilizing machine learning models. Archives of orthopaedic and trauma surgery; 2022.","DOI":"10.1007\/s00402-022-04588-x"},{"key":"2927_CR20","doi-asserted-by":"publisher","first-page":"85","DOI":"10.3389\/fmed.2017.00085","volume":"4","author":"ER Edelman","year":"2017","unstructured":"Edelman ER, van Kuijk SMJ, Hamaekers AEW, de Korte MJM, van Merode GG, Buhre WFFA. Improving the Prediction of Total Surgical Procedure Time using Linear regression modeling. Front Med. 2017;4:85.","journal-title":"Front Med"},{"key":"2927_CR21","volume-title":"The elements of statistical learning: data mining, inference, and prediction","author":"T Hastie","year":"2017","unstructured":"Hastie T, Tibshirani R, Friedman JH. The elements of statistical learning: data mining, inference, and prediction. New York, NY: Springer; 2017."},{"key":"2927_CR22","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost. In: Krishnapuram B, Shah M, Smola A, Aggarwal C, Shen D, Rastogi R, editors. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY, USA: ACM; 2016, pp. 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"2927_CR23","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1186\/s13063-020-04252-y","volume":"21","author":"D Kuklinski","year":"2020","unstructured":"Kuklinski D, Oschmann L, Pross C, Busse R, Geissler A. The use of digitally collected patient-reported outcome measures for newly operated patients with total knee and hip replacements to improve post-treatment recovery: study protocol for a randomized controlled trial. Trials. 2020;21:322.","journal-title":"Trials"},{"key":"2927_CR24","first-page":"112","volume":"28","author":"DJ Stekhoven","year":"2012","unstructured":"Stekhoven DJ, B\u00fchlmann P. MissForest\u2013non-parametric missing value imputation for mixed-type data. Bioinf (Oxford England). 2012;28:112\u20138.","journal-title":"Bioinf (Oxford England)"},{"key":"2927_CR25","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10916-022-01798-z","volume":"46","author":"CG Simmons","year":"2022","unstructured":"Simmons CG, Alvey NJ, Kaizer AM, Williamson K, Faruki AA, Kacmar RM, et al. Benchmarking of Anesthesia and Surgical Control Times by current procedural terminology (CPT\u00ae) codes. J Med Syst. 2022;46:19.","journal-title":"J Med Syst"},{"key":"2927_CR26","doi-asserted-by":"crossref","unstructured":"Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Statist. 2001;29.","DOI":"10.1214\/aos\/1013203451"},{"key":"2927_CR27","doi-asserted-by":"crossref","unstructured":"Berrar D. Cross-Validation. In: Encyclopedia of Bioinformatics and Computational Biology: Elsevier; 2019, pp. 542\u2013545.","DOI":"10.1016\/B978-0-12-809633-8.20349-X"},{"key":"2927_CR28","volume-title":"Congress on Evolutionary Computation","author":"IEEE","year":"2021","unstructured":"2021 IEEE. Congress on Evolutionary Computation. (CEC): IEEE; 2021."},{"key":"2927_CR29","doi-asserted-by":"publisher","first-page":"5481","DOI":"10.5194\/gmd-15-5481-2022","volume":"15","author":"TO Hodson","year":"2022","unstructured":"Hodson TO. Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not. Geosci Model Dev. 2022;15:5481\u20137.","journal-title":"Geosci Model Dev"},{"key":"2927_CR30","doi-asserted-by":"publisher","first-page":"105405","DOI":"10.1016\/j.aap.2019.105405","volume":"136","author":"AB Parsa","year":"2020","unstructured":"Parsa AB, Movahedi A, Taghipour H, Derrible S, Mohammadian AK. Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis. Accid Anal Prev. 2020;136:105405.","journal-title":"Accid Anal Prev"},{"key":"2927_CR31","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/978-3-031-04083-2_2","volume-title":"xxAI - beyond explainable AI","author":"A Holzinger","year":"2022","unstructured":"Holzinger A, Saranti A, Molnar C, Biecek P, Samek W, Explainable AI. Methods - A brief overview. In: Holzinger A, Goebel R, Fong R, Moon T, M\u00fcller K-R, Samek W, editors. xxAI - beyond explainable AI. Cham: Springer International Publishing; 2022. pp. 13\u201338."},{"key":"2927_CR32","doi-asserted-by":"publisher","first-page":"e0273831","DOI":"10.1371\/journal.pone.0273831","volume":"17","author":"O Babayoff","year":"2022","unstructured":"Babayoff O, Shehory O, Shahoha M, Sasportas R, Weiss-Meilik A. Surgery duration: optimized prediction and causality analysis. PLoS ONE. 2022;17:e0273831.","journal-title":"PLoS ONE"},{"key":"2927_CR33","doi-asserted-by":"publisher","first-page":"2768","DOI":"10.1016\/j.arth.2016.05.038","volume":"31","author":"A Wu","year":"2016","unstructured":"Wu A, Huang C-C, Weaver MJ, Urman RD. Use of Historical Surgical Times To Predict Duration of Primary Total Knee Arthroplasty. J Arthroplast. 2016;31:2768\u201372.","journal-title":"J Arthroplast"},{"key":"2927_CR34","doi-asserted-by":"crossref","unstructured":"Abbou B, Tal O, Frenkel G, Rubin R, Rappoport N. Optimizing Operation Room Utilization\u2014A Prediction Model BDCC. 2022;6:76.","DOI":"10.3390\/bdcc6030076"},{"key":"2927_CR35","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1097\/ALN.0b013e3181c294c2","volume":"112","author":"MJC Eijkemans","year":"2010","unstructured":"Eijkemans MJC, van Houdenhoven M, Nguyen T, Boersma E, Steyerberg EW, Kazemier G. Predicting the unpredictable: a new prediction model for operating room times using individual characteristics and the surgeon\u2019s estimate. Anesthesiology. 2010;112:41\u20139.","journal-title":"Anesthesiology"},{"key":"2927_CR36","doi-asserted-by":"crossref","unstructured":"Silva SJ, Keller CA, Hardin J. Using an Explainable Machine Learning Approach to Characterize Earth System Model errors: application of SHAP analysis to modeling lightning flash occurrence. J Adv Model Earth Syst 2022;14.","DOI":"10.1029\/2021MS002881"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-02927-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-025-02927-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-02927-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T13:05:10Z","timestamp":1741007110000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-025-02927-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,3]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2927"],"URL":"https:\/\/doi.org\/10.1186\/s12911-025-02927-7","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,3]]},"assertion":[{"value":"18 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study was approved by the lead Charit\u00e9 Ethics Committee, Berlin (EA4\/169\/19). Assent was given by the other responsible ethical review committees (Medical Association Hamburg, Medical Association Schleswig-Holstein, Hannover Medical School, Friedrich-Schiller University Jena, and the Medical Association Brandenburg). The study is registered at the German Clinical Trials Register (DRKS) under DRKS00019916. All potentially eligible participants will be approached to offer their informed consent to participate in the study. Additionally, they can accept to release their hospital administrative data in an optional consent form. For patients insured by participating sickness funds, a third consent form is handed out to ask for permission to process their insurance claims data at the end of the study period. Patients will be free to withdraw from either of the three consents without stating a reason. If the patients withdraw from the consent for participation, all their data will be deleted.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not Applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"D. Schrednitzki reports payments for lectures and courses on knee arthroplasty and robotics from Zimmer Biomet, unrelated to this study. R. Busse reports institutional grants from Roche and Stryker, and speaker payments from AbbVie, all of which are unrelated to this study. R. Busse is also involved with the Government Commission on Hospital Reform. A. Halder reports royalties or licenses, speaker payments, and support for attending meetings and\/or travel from Zimmer Biomet and DePuy, unrelated to this study. A. Halder is also President of the German Orthopaedic Society (DGOOC) 2022 Board Member European Knee Society. C. Pross is employed by Stryker, and reports stock in Stryker, unrelated to this study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"106"}}