{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:14:51Z","timestamp":1788808491335,"version":"build-2803163510"},"reference-count":55,"publisher":"Georg Thieme Verlag KG","issue":"02","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Knee Surg"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Periprosthetic joint infection (PJI) following revision total knee arthroplasty (TKA) for aseptic failure is associated with poor outcomes, patient morbidity, and high health care expenditures. The aim of this study was to develop novel machine learning algorithms for the prediction of PJI following revision TKA for patients with aseptic indications for revision surgery. A single-institution database consisting of 1,432 consecutive revision TKA patients with aseptic etiologies was retrospectively identified. The patient cohort included 208 patients (14.5%) who underwent re-revision surgery for PJI. Three machine learning algorithms (artificial neural networks, support vector machines, k-nearest neighbors) were developed to predict this outcome and these models were assessed by discrimination, calibration, and decision curve analysis. This is a retrospective study. Among the three machine learning models, the neural network model achieved the best performance across discrimination (area under the receiver operating characteristic curve\u2009=\u20090.78), calibration, and decision curve analysis. The strongest predictors for PJI following revision TKA for aseptic reasons were prior open procedure prior to revision surgery, drug abuse, obesity, and diabetes. This study utilized machine learning as a tool for the prediction of PJI following revision TKA for aseptic failure with excellent performance. The validated machine learning models can aid surgeons in patient-specific risk stratifying to assist in preoperative counseling and clinical decision making for patients undergoing aseptic revision TKA.<\/jats:p>","DOI":"10.1055\/s-0043-1761259","type":"journal-article","created":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T23:48:03Z","timestamp":1675381683000},"page":"158-166","source":"Crossref","is-referenced-by-count":24,"title":["The Use of Artificial Intelligence for the Prediction of Periprosthetic Joint Infection Following Aseptic Revision Total Knee Arthroplasty"],"prefix":"10.1055","volume":"37","author":[{"given":"Christian","family":"Klemt","sequence":"additional","affiliation":[{"name":"Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ingwon","family":"Yeo","sequence":"additional","affiliation":[{"name":"Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Harvey","sequence":"additional","affiliation":[{"name":"Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jillian C","family":"Burns","sequence":"additional","affiliation":[{"name":"Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Melnic","sequence":"additional","affiliation":[{"name":"Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akachimere Cosmas","family":"Uzosike","sequence":"additional","affiliation":[{"name":"Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young-Min","family":"Kwon","sequence":"additional","affiliation":[{"name":"Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"194","published-online":{"date-parts":[[2023,2,2]]},"reference":[{"issue":"04","key":"ref1","doi-asserted-by":"crossref","first-page":"780","DOI":"10.2106\/00004623-200704000-00012","article-title":"Projections of primary and revision hip and knee arthroplasty in the United States from 2005 to 2030","volume":"89","author":"S Kurtz","year":"2007","journal-title":"J Bone Joint Surg Am"},{"issue":"07","key":"ref2","doi-asserted-by":"crossref","first-page":"2088","DOI":"10.1016\/j.arth.2017.02.046","article-title":"Current epidemiology of revision total hip arthroplasty in the United States: national inpatient sample 2009 to 2013","volume":"32","author":"C U Gwam","year":"2017","journal-title":"J Arthroplasty"},{"issue":"09","key":"ref3","doi-asserted-by":"crossref","first-page":"2663","DOI":"10.1016\/j.arth.2017.03.066","article-title":"Current epidemiology of revision total knee arthroplasty in the United States","volume":"32","author":"R E Delanois","year":"2017","journal-title":"J Arthroplasty"},{"issue":"01","key":"ref4","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/j.arth.2020.07.012","article-title":"Single-stage revision of the infected total knee arthroplasty is associated with improved functional outcomes: a propensity score-matched cohort study","volume":"36","author":"C Klemt","year":"2021","journal-title":"J Arthroplasty"},{"issue":"06","key":"ref5","doi-asserted-by":"crossref","first-page":"2131","DOI":"10.1016\/j.arth.2021.01.068","article-title":"Septic revision total knee arthroplasty is associated with significantly higher mortality than aseptic revisions: long-term single-center study (1254 patients)","volume":"36","author":"H E Matar","year":"2021","journal-title":"J Arthroplasty"},{"issue":"08","key":"ref6","first-page":"1746","article-title":"The impact of infection after total hip arthroplasty on hospital and surgeon resource utilization","volume":"87","author":"K J Bozic","year":"2005","journal-title":"J Bone Joint Surg Am"},{"issue":"01","key":"ref7","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s11999-009-0945-0","article-title":"The epidemiology of revision total knee arthroplasty in the United States","volume":"468","author":"K J Bozic","year":"2010","journal-title":"Clin Orthop Relat Res"},{"issue":"08","key":"ref8","doi-asserted-by":"crossref","first-page":"1373","DOI":"10.1007\/s00402-020-03698-8","article-title":"Infection and periprosthetic fracture are the leading causes of failure after aseptic revision total knee arthroplasty","volume":"141","author":"J A Meyer","year":"2021","journal-title":"Arch Orthop Trauma Surg"},{"issue":"01","key":"ref9","doi-asserted-by":"crossref","first-page":"706","DOI":"10.1186\/s12891-021-04597-8","article-title":"Cost of septic and aseptic revision total knee arthroplasty: a systematic review","volume":"22","author":"C Okafor","year":"2021","journal-title":"BMC Musculoskelet Disord"},{"issue":"12","key":"ref10","doi-asserted-by":"crossref","first-page":"3661","DOI":"10.1016\/j.arth.2020.06.089","article-title":"Risk of prosthetic joint infection increases following early aseptic revision surgery of total hip and knee arthroplasty","volume":"35","author":"N D Quinlan","year":"2020","journal-title":"J Arthroplasty"},{"issue":"12","key":"ref11","doi-asserted-by":"crossref","first-page":"3565","DOI":"10.1007\/s00402-021-03948-3","article-title":"Periprosthetic joint infection is the main reason for failure in patients following periprosthetic fracture treated with revision arthroplasty","volume":"142","author":"J van den Kieboom","year":"2022","journal-title":"Arch Orthop Trauma Surg"},{"issue":"10","key":"ref12","doi-asserted-by":"crossref","first-page":"2220","DOI":"10.1016\/j.arth.2019.05.034","article-title":"Deep learning preoperatively predicts value metrics for primary total knee arthroplasty: development and validation of an artificial neural network model","volume":"34","author":"P N Ramkumar","year":"2019","journal-title":"J Arthroplasty"},{"issue":"06","key":"ref13","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1007\/s00167-019-05602-3","article-title":"Transfusion after total knee arthroplasty can be predicted using the machine learning algorithm","volume":"28","author":"C Jo","year":"2019","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"issue":"05","key":"ref14","doi-asserted-by":"crossref","first-page":"1694","DOI":"10.1016\/j.arthro.2020.08.009","article-title":"Clinical and research medical applications of artificial intelligence","volume":"37","author":"P N Ramkumar","year":"2021","journal-title":"Arthroscopy"},{"issue":"06","key":"ref15","first-page":"235","article-title":"Artificial intelligence for the orthopaedic surgeon: an overview of potential benefits, limitations, and clinical applications","volume":"29","author":"E C Makhni","year":"2021","journal-title":"J Am Acad Orthop Surg"},{"issue":"09","key":"ref16","doi-asserted-by":"crossref","first-page":"2325967120953404","DOI":"10.1177\/2325967120953404","article-title":"Machine learning outperforms logistic regression analysis to predict next-season NHL player injury: an analysis of 2322 players from 2007 to 2017","volume":"8","author":"B C Luu","year":"2020","journal-title":"Orthop J Sports Med"},{"issue":"11","key":"ref17","doi-asserted-by":"crossref","first-page":"2325967120963046","DOI":"10.1177\/2325967120963046","article-title":"Machine learning outperforms regression analysis to predict next-season Major League Baseball player injuries: epidemiology and validation of 13,982 player-years from performance and injury profile trends, 2000-2017","volume":"8","author":"J M Karnuta","year":"2020","journal-title":"Orthop J Sports Med"},{"issue":"12","key":"ref18","doi-asserted-by":"crossref","first-page":"2910","DOI":"10.1177\/0363546520950743","article-title":"Radiographic indices are not predictive of clinical outcomes among 1735 patients indicated for hip arthroscopic surgery: a machine learning analysis","volume":"48","author":"P N Ramkumar","year":"2020","journal-title":"Am J Sports Med"},{"issue":"08","key":"ref19","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1007\/s00256-020-03410-2","article-title":"Deep convolutional neural network-based detection of meniscus tears: comparison with radiologists and surgery as standard of reference","volume":"49","author":"B Fritz","year":"2020","journal-title":"Skeletal Radiol"},{"issue":"06","key":"ref20","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1007\/s10278-019-00193-4","article-title":"Deep learning for detection of complete anterior cruciate ligament tear","volume":"32","author":"P D Chang","year":"2019","journal-title":"J Digit Imaging"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"S290, 294.e1","DOI":"10.1016\/j.arth.2020.10.021","article-title":"Artificial intelligence to identify arthroplasty implants from radiographs of the hip","volume":"36","author":"J M Karnuta","year":"2021","journal-title":"J Arthroplasty"},{"issue":"07","key":"ref22","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.1002\/jor.24617","article-title":"Detecting total hip replacement prosthesis design on plain radiographs using deep convolutional neural network","volume":"38","author":"A Borjali","year":"2020","journal-title":"J Orthop Res"},{"issue":"10","key":"ref23","doi-asserted-by":"crossref","first-page":"2253","DOI":"10.1016\/j.arth.2019.05.021","article-title":"Remote patient monitoring using mobile health for total knee arthroplasty: validation of a wearable and machine learning-based surveillance platform","volume":"34","author":"P N Ramkumar","year":"2019","journal-title":"J Arthroplasty"},{"issue":"06","key":"ref24","doi-asserted-by":"crossref","first-page":"2805","DOI":"10.1007\/s00402-022-04453-x","article-title":"Can machine learning models predict failure of revision total hip arthroplasty?","volume":"143","author":"C Klemt","year":"2023","journal-title":"Arch Orthop Trauma Surg"},{"issue":"11","key":"ref25","doi-asserted-by":"crossref","first-page":"2385","DOI":"10.1016\/j.jse.2020.04.009","article-title":"The value of artificial neural networks for predicting length of stay, discharge disposition, and inpatient costs after anatomic and reverse shoulder arthroplasty","volume":"29","author":"J M Karnuta","year":"2020","journal-title":"J Shoulder Elbow Surg"},{"issue":"09","key":"ref26","doi-asserted-by":"crossref","first-page":"2761","DOI":"10.1016\/j.arthro.2022.04.014","article-title":"Meaningless applications and misguided methodologies in artificial intelligence-related orthopaedic research propagates hype over hope","volume":"38","author":"P N Ramkumar","year":"2022","journal-title":"Arthroscopy"},{"issue":"11","key":"ref27","doi-asserted-by":"crossref","first-page":"2992","DOI":"10.1007\/s11999-011-2102-9","article-title":"New definition for periprosthetic joint infection: from the Workgroup of the Musculoskeletal Infection Society","volume":"469","author":"J Parvizi","year":"2011","journal-title":"Clin Orthop Relat Res"},{"issue":"08","key":"ref28","first-page":"2556","volume":"30","author":"C Klemt","year":"2022"},{"issue":"06","key":"ref29","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1016\/j.spinee.2019.01.009","article-title":"Machine learning for prediction of sustained opioid prescription after anterior cervical discectomy and fusion","volume":"19","author":"A V Karhade","year":"2019","journal-title":"Spine J"},{"issue":"08","key":"ref30","doi-asserted-by":"crossref","first-page":"2573","DOI":"10.1007\/s00167-021-06812-4","article-title":"Machine learning algorithms predict extended postoperative opioid use in primary total knee arthroplasty","volume":"30","author":"C Klemt","year":"2022","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"issue":"06","key":"ref31","doi-asserted-by":"crossref","first-page":"3299","DOI":"10.1007\/s00402-022-04588-x","article-title":"Predicting surgical operative time in primary total knee arthroplasty utilizing machine learning models","volume":"143","author":"I Yeo","year":"2023","journal-title":"Arch Orthop Trauma Surg"},{"issue":"02","key":"ref32","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1016\/j.arth.2020.08.004","article-title":"Development of a preoperative risk calculator for reinfection following revision surgery for periprosthetic joint infection","volume":"36","author":"C Klemt","year":"2021","journal-title":"J Arthroplasty"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1107\/S2052252519012661","article-title":"Throughput and resolution with a next-generation direct electron detector","volume":"6","author":"J H Mendez","year":"2019","journal-title":"IUCrJ"},{"issue":"04","key":"ref34","first-page":"328","article-title":"Insurance payer type affects outcomes after revision total joint arthroplasty: a matched cohort analysis","volume":"10","author":"V Tirumala","year":"2022","journal-title":"Arch Bone Jt Surg"},{"issue":"07","key":"ref35","first-page":"576","article-title":"Outcome of two-stage revision total hip and knee arthroplasty as a salvage procedure for deep infection of peri-articular fracture fixation: propensity score-matched study","volume":"10","author":"J van den Kieboom","year":"2022","journal-title":"Arch Bone Jt Surg"},{"issue":"11","key":"ref36","doi-asserted-by":"crossref","first-page":"3447","DOI":"10.1109\/TBME.2021.3075041","article-title":"An anatomical atlas-based scaling study for quantifying muscle and hip joint contact forces in above and through-knee amputees using validated musculoskeletal modelling","volume":"68","author":"D Toderita","year":"2021","journal-title":"IEEE Trans Biomed Eng"},{"issue":"13","key":"ref37","doi-asserted-by":"crossref","first-page":"e580","DOI":"10.5435\/JAAOS-D-19-00395","article-title":"A novel machine learning model developed to assist in patient selection for outpatient total shoulder arthroplasty","volume":"28","author":"D R Biron","year":"2020","journal-title":"J Am Acad Orthop Surg"},{"issue":"03","key":"ref38","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/j.spinee.2019.10.007","article-title":"Can a machine learning model accurately predict patient resource utilization following lumbar spinal fusion?","volume":"20","author":"J M Karnuta","year":"2020","journal-title":"Spine J"},{"issue":"09","key":"ref39","doi-asserted-by":"crossref","first-page":"830","DOI":"10.2106\/JBJS.19.01128","article-title":"Artificial intelligence and orthopaedics: an introduction for clinicians","volume":"102","author":"T G Myers","year":"2020","journal-title":"J Bone Joint Surg Am"},{"issue":"08","key":"ref40","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1086\/666641","article-title":"The Mayo prosthetic joint infection risk score: implication for surgical site infection reporting and risk stratification","volume":"33","author":"E F Berbari","year":"2012","journal-title":"Infect Control Hosp Epidemiol"},{"issue":"10","key":"ref41","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.1016\/j.arth.2015.05.004","article-title":"Predicting infections after total joint arthroplasty using a prescription based comorbidity measure","volume":"30","author":"M CS Inacio","year":"2015","journal-title":"J Arthroplasty"},{"issue":"09","key":"ref42","doi-asserted-by":"crossref","first-page":"777","DOI":"10.2106\/JBJS.16.01435","article-title":"Development and evaluation of a preoperative risk calculator for periprosthetic joint infection following total joint arthroplasty","volume":"100","author":"T L Tan","year":"2018","journal-title":"J Bone Joint Surg Am"},{"issue":"02","key":"ref43","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1097\/CORR.0000000000000601","article-title":"Can machine learning methods produce accurate and easy-to-use prediction models of 30-day complications and mortality after knee or hip arthroplasty?","volume":"477","author":"A HS Harris","year":"2019","journal-title":"Clin Orthop Relat Res"},{"key":"ref44","first-page":"786418","article-title":"Predicting postoperative vomiting for orthopedic patients receiving patient-controlled epidural analgesia with the application of an artificial neural network","volume":"2014","author":"C SA Gong","year":"2014","journal-title":"BioMed Res Int"},{"issue":"06","key":"ref45","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1016\/j.jspd.2018.03.003","article-title":"Predicting surgical complications in patients undergoing elective adult spinal deformity procedures using machine learning","volume":"6","author":"J S Kim","year":"2018","journal-title":"Spine Deform"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1302\/0301-620X.101B1.BJJ-2018-0233.R1","article-title":"The prevention of infection: 12 modifiable risk factors","volume":"101-B","author":"V K Alamanda","year":"2019","journal-title":"Bone Joint J"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"S255","DOI":"10.1016\/j.arth.2018.09.010","article-title":"Hip and knee section, prevention, host related: proceedings of international consensus on orthopedic infections","volume":"34","author":"Z Cizmic","year":"2019","journal-title":"J Arthroplasty"},{"issue":"03","key":"ref48","doi-asserted-by":"crossref","first-page":"1094","DOI":"10.1016\/j.arth.2020.09.012","article-title":"Outcomes and risk factors associated with 2-stage reimplantation requiring an interim spacer exchange for periprosthetic joint infection","volume":"36","author":"C Klemt","year":"2021","journal-title":"J Arthroplasty"},{"issue":"08","key":"ref49","doi-asserted-by":"crossref","first-page":"2358","DOI":"10.1016\/j.arth.2018.02.067","article-title":"Artificial intelligence, machine learning, deep learning, and cognitive computing: what do these terms mean and how will they impact health care?","volume":"33","author":"S A Bini","year":"2018","journal-title":"J Arthroplasty"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"A Esteva","year":"2017","journal-title":"Nature"},{"issue":"01","key":"ref51","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","article-title":"Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"A Y Hannun","year":"2019","journal-title":"Nat Med"},{"issue":"10","key":"ref52","doi-asserted-by":"crossref","first-page":"2272.e1","DOI":"10.1016\/j.arth.2019.06.013","article-title":"Development of machine learning algorithms for prediction of sustained postoperative opioid prescriptions after total hip arthroplasty","volume":"34","author":"A V Karhade","year":"2019","journal-title":"J Arthroplasty"},{"issue":"08","key":"ref53","doi-asserted-by":"crossref","first-page":"1157","DOI":"10.1007\/s00264-010-1134-1","article-title":"Failure following revision total knee arthroplasty: infection is the major cause","volume":"35","author":"S M Mortazavi","year":"2011","journal-title":"Int Orthop"},{"issue":"01","key":"ref54","first-page":"93","volume":"3","author":"K N Kunze","year":"2022"},{"issue":"09","key":"ref55","doi-asserted-by":"crossref","first-page":"821","DOI":"10.2106\/JBJS.21.00717","article-title":"Efficacy and applications of artificial intelligence and machine learning analyses in total joint arthroplasty: a call for improved reporting","volume":"104","author":"E M Polce","year":"2022","journal-title":"J Bone Joint Surg Am"}],"container-title":["The Journal of Knee Surgery"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.thieme-connect.de\/products\/ejournals\/pdf\/10.1055\/s-0043-1761259.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T14:11:22Z","timestamp":1730815882000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.thieme-connect.de\/DOI\/DOI?10.1055\/s-0043-1761259"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,2]]},"references-count":55,"journal-issue":{"issue":"02","published-online":{"date-parts":[[2024,1,19]]},"published-print":{"date-parts":[[2024,1]]}},"URL":"https:\/\/doi.org\/10.1055\/s-0043-1761259","archive":["Portico","CLOCKSS"],"relation":{},"ISSN":["1538-8506","1938-2480"],"issn-type":[{"value":"1538-8506","type":"print"},{"value":"1938-2480","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,2]]}}}