Download PDF
J Knee Surg 2024; 37(02): 158-166
DOI: 10.1055/s-0043-1761259
Original Article

The Use of Artificial Intelligence for the Prediction of Periprosthetic Joint Infection Following Aseptic Revision Total Knee Arthroplasty

Christian Klemt
1   Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
,
Ingwon Yeo
1   Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
,
Michael Harvey
1   Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
,
Jillian C Burns
1   Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
,
Christopher Melnic
1   Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
,
Akachimere Cosmas Uzosike
1   Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
,
Young-Min Kwon
1   Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
› Author Affiliations Funding This study did not receive any funding.
› Further Information
    Permissions and Reprints

Abstract

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 = 0.78), 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.

Keywords

revision TKA - periprosthetic joint infection - machine learning - artificial intelligence


Publication History

Received: 22 October 2022

Accepted: 16 December 2022

Article published online:
02 February 2023

© 2023. Thieme. All rights reserved.

Thieme Medical Publishers, Inc.
333 Seventh Avenue, 18th Floor, New York, NY 10001, USA

 

  • References

  • 1 Kurtz S, Ong K, Lau E, Mowat F, Halpern M. Projections of primary and revision hip and knee arthroplasty in the United States from 2005 to 2030. J Bone Joint Surg Am 2007; 89 (04) 780-785
    CrossrefPubMedGoogle Scholar
  • 2 Gwam CU, Mistry JB, Mohamed NS. et al. Current epidemiology of revision total hip arthroplasty in the United States: national inpatient sample 2009 to 2013. J Arthroplasty 2017; 32 (07) 2088-2092
    CrossrefPubMedGoogle Scholar
  • 3 Delanois RE, Mistry JB, Gwam CU, Mohamed NS, Choksi US, Mont MA. Current epidemiology of revision total knee arthroplasty in the United States. J Arthroplasty 2017; 32 (09) 2663-2668
    CrossrefPubMedGoogle Scholar
  • 4 Klemt C, Tirumala V, Oganesyan R, Xiong L, van den Kieboom J, Kwon Y-M. Single-stage revision of the infected total knee arthroplasty is associated with improved functional outcomes: a propensity score-matched cohort study. J Arthroplasty 2021; 36 (01) 298-304
    CrossrefPubMedGoogle Scholar
  • 5 Matar HE, Bloch BV, Snape SE, James PJ. Septic revision total knee arthroplasty is associated with significantly higher mortality than aseptic revisions: long-term single-center study (1254 patients). J Arthroplasty 2021; 36 (06) 2131-2136
    CrossrefPubMedGoogle Scholar
  • 6 Bozic KJ, Ries MD. The impact of infection after total hip arthroplasty on hospital and surgeon resource utilization. J Bone Joint Surg Am 2005; 87 (08) 1746-1751
    PubMedGoogle Scholar
  • 7 Bozic KJ, Kurtz SM, Lau E. et al. The epidemiology of revision total knee arthroplasty in the United States. Clin Orthop Relat Res 2010; 468 (01) 45-51
    CrossrefPubMedGoogle Scholar
  • 8 Meyer JA, Zhu M, Cavadino A, Coleman B, Munro JT, Young SW. Infection and periprosthetic fracture are the leading causes of failure after aseptic revision total knee arthroplasty. Arch Orthop Trauma Surg 2021; 141 (08) 1373-1383
    CrossrefPubMedGoogle Scholar
  • 9 Okafor C, Hodgkinson B, Nghiem S, Vertullo C, Byrnes J. Cost of septic and aseptic revision total knee arthroplasty: a systematic review. BMC Musculoskelet Disord 2021; 22 (01) 706
    CrossrefPubMedGoogle Scholar
  • 10 Quinlan ND, Werner BC, Brown TE, Browne JA. Risk of prosthetic joint infection increases following early aseptic revision surgery of total hip and knee arthroplasty. J Arthroplasty 2020; 35 (12) 3661-3667
    CrossrefPubMedGoogle Scholar
  • 11 van den Kieboom J, Tirumala V, Xiong L, Klemt C, Kwon Y-M. Periprosthetic joint infection is the main reason for failure in patients following periprosthetic fracture treated with revision arthroplasty. Arch Orthop Trauma Surg 2022; 142 (12) 3565-3574
    CrossrefPubMedGoogle Scholar
  • 12 Ramkumar PN, Karnuta JM, Navarro SM. et al. Deep learning preoperatively predicts value metrics for primary total knee arthroplasty: development and validation of an artificial neural network model. J Arthroplasty 2019; 34 (10) 2220-2227.e1
    CrossrefPubMedGoogle Scholar
  • 13 Jo C, Ko S, Shin WC. et al. Transfusion after total knee arthroplasty can be predicted using the machine learning algorithm. Knee Surg Sports Traumatol Arthrosc 2019; 28 (06) 1757-1764
    CrossrefPubMedGoogle Scholar
  • 14 Ramkumar PN, Kunze KN, Haeberle HS. et al. Clinical and research medical applications of artificial intelligence. Arthroscopy 2021; 37 (05) 1694-1697
    CrossrefPubMedGoogle Scholar
  • 15 Makhni EC, Makhni S, Ramkumar PN. Artificial intelligence for the orthopaedic surgeon: an overview of potential benefits, limitations, and clinical applications. J Am Acad Orthop Surg 2021; 29 (06) 235-243
    CrossrefPubMedGoogle Scholar
  • 16 Luu BC, Wright AL, Haeberle HS. et al. Machine learning outperforms logistic regression analysis to predict next-season NHL player injury: an analysis of 2322 players from 2007 to 2017. Orthop J Sports Med 2020; 8 (09) 2325967120953404
    CrossrefPubMedGoogle Scholar
  • 17 Karnuta JM, Luu BC, Haeberle HS. et al. 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. Orthop J Sports Med 2020; 8 (11) 2325967120963046
    CrossrefPubMedGoogle Scholar
  • 18 Ramkumar PN, Karnuta JM, Haeberle HS. et al. Radiographic indices are not predictive of clinical outcomes among 1735 patients indicated for hip arthroscopic surgery: a machine learning analysis. Am J Sports Med 2020; 48 (12) 2910-2918
    CrossrefPubMedGoogle Scholar
  • 19 Fritz B, Marbach G, Civardi F, Fucentese SF, Pfirrmann CWA. Deep convolutional neural network-based detection of meniscus tears: comparison with radiologists and surgery as standard of reference. Skeletal Radiol 2020; 49 (08) 1207-1217
    CrossrefPubMedGoogle Scholar
  • 20 Chang PD, Wong TT, Rasiej MJ. Deep learning for detection of complete anterior cruciate ligament tear. J Digit Imaging 2019; 32 (06) 980-986
    CrossrefPubMedGoogle Scholar
  • 21 Karnuta JM, Haeberle HS, Luu BC. et al. Artificial intelligence to identify arthroplasty implants from radiographs of the hip. J Arthroplasty 2021; 36 7s S290, 294.e1
    CrossrefPubMedGoogle Scholar
  • 22 Borjali A, Chen AF, Muratoglu OK, Morid MA, Varadarajan KM. Detecting total hip replacement prosthesis design on plain radiographs using deep convolutional neural network. J Orthop Res 2020; 38 (07) 1465-1471
    CrossrefPubMedGoogle Scholar
  • 23 Ramkumar PN, Haeberle HS, Ramanathan D. et al. Remote patient monitoring using mobile health for total knee arthroplasty: validation of a wearable and machine learning-based surveillance platform. J Arthroplasty 2019; 34 (10) 2253-2259
    CrossrefPubMedGoogle Scholar
  • 24 Klemt C, Cohen-Levy WB, Robinson MG. et al. Can machine learning models predict failure of revision total hip arthroplasty?. Arch Orthop Trauma Surg 2023; 143 (06) 2805-2812
    CrossrefPubMedGoogle Scholar
  • 25 Karnuta JM, Churchill JL, Haeberle HS. et al. The value of artificial neural networks for predicting length of stay, discharge disposition, and inpatient costs after anatomic and reverse shoulder arthroplasty. J Shoulder Elbow Surg 2020; 29 (11) 2385-2394
    CrossrefPubMedGoogle Scholar
  • 26 Ramkumar PN, Pang M, Polisetty T, Helm JM, Karnuta JM. Meaningless applications and misguided methodologies in artificial intelligence-related orthopaedic research propagates hype over hope. Arthroscopy 2022; 38 (09) 2761-2766
    CrossrefPubMedGoogle Scholar
  • 27 Parvizi J, Zmistowski B, Berbari EF. et al. New definition for periprosthetic joint infection: from the Workgroup of the Musculoskeletal Infection Society. Clin Orthop Relat Res 2011; 469 (11) 2992-2994
    CrossrefPubMedGoogle Scholar
  • 28 Klemt C, Tirumala V, Barghi A, Cohen-Levy WB, Robinson MG, Kwon Y-M. Artificial intelligence algorithms accurately predict prolonged length of stay following revision total knee arthroplasty Knee Surg Sports Traumatol Arthrosc 2022; 30 (08) 2556-2564
    PubMed
  • 29 Karhade AV, Ogink PT, Thio QCBS. et al Machine learning for prediction of sustained opioid prescription after anterior cervical discectomy and fusion. Spine J 2019; 19 (06) 976-983
    CrossrefPubMedGoogle Scholar
  • 30 Klemt C, Harvey MJ, Robinson MG, Esposito JG, Yeo I, Kwon Y-M. Machine learning algorithms predict extended postoperative opioid use in primary total knee arthroplasty. Knee Surg Sports Traumatol Arthrosc 2022; 30 (08) 2573-2581
    CrossrefPubMedGoogle Scholar
  • 31 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. Arch Orthop Trauma Surg 2023; 143 (06) 3299-3307
    CrossrefPubMedGoogle Scholar
  • 32 Klemt C, Tirumala V, Smith EJ, Padmanabha A, Kwon Y-M. Development of a preoperative risk calculator for reinfection following revision surgery for periprosthetic joint infection. J Arthroplasty 2021; 36 (02) 693-699
    CrossrefPubMedGoogle Scholar
  • 33 Mendez JH, Mehrani A, Randolph P, Stagg S. Throughput and resolution with a next-generation direct electron detector. IUCrJ 2019; 6 (Pt 6): 1007-1013
    CrossrefPubMedGoogle Scholar
  • 34 Tirumala V, Klemt C, Esposito JG, Robinson MG, Barghi A, Kwon Y-M. Insurance payer type affects outcomes after revision total joint arthroplasty: a matched cohort analysis. Arch Bone Jt Surg 2022; 10 (04) 328-338
    PubMedGoogle Scholar
  • 35 van den Kieboom J, Tirumala V, Klemt C, Kwon Y-M. 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. Arch Bone Jt Surg 2022; 10 (07) 576-584
    PubMedGoogle Scholar
  • 36 Toderita D, Henson DP, Klemt C, Ding Z, Bull AMJ. An anatomical atlas-based scaling study for quantifying muscle and hip joint contact forces in above and through-knee amputees using validated musculoskeletal modelling. IEEE Trans Biomed Eng 2021; 68 (11) 3447-3456
    CrossrefPubMedGoogle Scholar
  • 37 Biron DR, Sinha I, Kleiner JE. et al A novel machine learning model developed to assist in patient selection for outpatient total shoulder arthroplasty. J Am Acad Orthop Surg 2020; 28 (13) e580-e585
    CrossrefPubMedGoogle Scholar
  • 38 Karnuta JM, Golubovsky JL, Haeberle HS. et al Can a machine learning model accurately predict patient resource utilization following lumbar spinal fusion?. Spine J 2020; 20 (03) 329-336
    CrossrefPubMedGoogle Scholar
  • 39 Myers TG, Ramkumar PN, Ricciardi BF, Urish KL, Kipper J, Ketonis C. Artificial intelligence and orthopaedics: an introduction for clinicians. J Bone Joint Surg Am 2020; 102 (09) 830-840
    CrossrefPubMedGoogle Scholar
  • 40 Berbari EF, Osmon DR, Lahr B. et al The Mayo prosthetic joint infection risk score: implication for surgical site infection reporting and risk stratification. Infect Control Hosp Epidemiol 2012; 33 (08) 774-781
    CrossrefPubMedGoogle Scholar
  • 41 Inacio MCS, Pratt NL, Roughead EE, Graves SE. Predicting infections after total joint arthroplasty using a prescription based comorbidity measure. J Arthroplasty 2015; 30 (10) 1692-1698
    CrossrefPubMedGoogle Scholar
  • 42 Tan TL, Maltenfort MG, Chen AF. et al Development and evaluation of a preoperative risk calculator for periprosthetic joint infection following total joint arthroplasty. J Bone Joint Surg Am 2018; 100 (09) 777-785
    CrossrefPubMedGoogle Scholar
  • 43 Harris AHS, Kuo AC, Weng Y, Trickey AW, Bowe T, Giori NJ. Can machine learning methods produce accurate and easy-to-use prediction models of 30-day complications and mortality after knee or hip arthroplasty?. Clin Orthop Relat Res 2019; 477 (02) 452-460
    CrossrefPubMedGoogle Scholar
  • 44 Gong CSA, Yu L, Ting CK. et al Predicting postoperative vomiting for orthopedic patients receiving patient-controlled epidural analgesia with the application of an artificial neural network. BioMed Res Int 2014; 2014: 786418
    PubMedGoogle Scholar
  • 45 Kim JS, Arvind V, Oermann EK. et al Predicting surgical complications in patients undergoing elective adult spinal deformity procedures using machine learning. Spine Deform 2018; 6 (06) 762-770
    CrossrefPubMedGoogle Scholar
  • 46 Alamanda VK, Springer BD. The prevention of infection: 12 modifiable risk factors. Bone Joint J 2019; 101-B (1_Supple_A): 3-9
    CrossrefPubMedGoogle Scholar
  • 47 Cizmic Z, Feng JE, Huang R. et al. Hip and knee section, prevention, host related: proceedings of international consensus on orthopedic infections. J Arthroplasty 2019; 34 2s S255-S270
    CrossrefPubMedGoogle Scholar
  • 48 Klemt C, Smith EJ, Tirumala V, Bounajem G, van den Kieboom J, Kwon Y-M. Outcomes and risk factors associated with 2-stage reimplantation requiring an interim spacer exchange for periprosthetic joint infection. J Arthroplasty 2021; 36 (03) 1094-1100
    CrossrefPubMedGoogle Scholar
  • 49 Bini SA. Artificial intelligence, machine learning, deep learning, and cognitive computing: what do these terms mean and how will they impact health care?. J Arthroplasty 2018; 33 (08) 2358-2361
    CrossrefPubMedGoogle Scholar
  • 50 Esteva A, Kuprel B, Novoa RA. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017; 542 7639 115-118
    CrossrefPubMedGoogle Scholar
  • 51 Hannun AY, Rajpurkar P, Haghpanahi M. et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med 2019; 25 (01) 65-69
    CrossrefPubMedGoogle Scholar
  • 52 Karhade AV, Schwab JH, Bedair HS. Development of machine learning algorithms for prediction of sustained postoperative opioid prescriptions after total hip arthroplasty. J Arthroplasty 2019; 34 (10) 2272.e1-2277.e1
    CrossrefPubMedGoogle Scholar
  • 53 Mortazavi SM, Molligan J, Austin MS, Purtill JJ, Hozack WJ, Parvizi J. Failure following revision total knee arthroplasty: infection is the major cause. Int Orthop 2011; 35 (08) 1157-1164
    CrossrefPubMedGoogle Scholar
  • 54 Kunze KN, Orr M, Krebs V, Bhandari M, Piuzzi NS. Potential benefits, unintended consequences, and future roles of artificial intelligence in orthopaedic surgery research Bone Jt Open 2022; 3 (01) 93-97
    PubMed
  • 55 Polce EM, Kunze KN, Dooley MS, Piuzzi NS, Boettner F, Sculco PK. Efficacy and applications of artificial intelligence and machine learning analyses in total joint arthroplasty: a call for improved reporting. J Bone Joint Surg Am 2022; 104 (09) 821-832
    CrossrefPubMedGoogle Scholar