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

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.

[1]  Young-Min Kwon,et al.  Predicting surgical operative time in primary total knee arthroplasty utilizing machine learning models , 2022, Archives of Orthopaedic and Trauma Surgery.

[2]  Young-Min Kwon,et al.  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. , 2022, The Archives of Bone & Joint Surgery.

[3]  W. Cohen-Levy,et al.  Can machine learning models predict failure of revision total hip arthroplasty? , 2022, Archives of Orthopaedic and Trauma Surgery.

[4]  Teja S. Polisetty,et al.  Meaningless Applications and Misguided Methodologies in Artificial Intelligence-Related Orthopaedic Research Propagates Hype Over Hope. , 2022, Arthroscopy : the journal of arthroscopic & related surgery : official publication of the Arthroscopy Association of North America and the International Arthroscopy Association.

[5]  P. Sculco,et al.  Efficacy and Applications of Artificial Intelligence and Machine Learning Analyses in Total Joint Arthroplasty , 2022, The Journal of bone and joint surgery. American volume.

[6]  Young-Min Kwon,et al.  Machine learning algorithms predict extended postoperative opioid use in primary total knee arthroplasty , 2022, Knee Surgery, Sports Traumatology, Arthroscopy.

[7]  Young-Min Kwon,et al.  Insurance Payer Type Affects Outcomes after Revision Total Joint Arthroplasty: A Matched Cohort Analysis. , 2021, The Archives of Bone & Joint Surgery.

[8]  B. Hodgkinson,et al.  Cost of septic and aseptic revision total knee arthroplasty: a systematic review , 2021, BMC Musculoskeletal Disorders.

[9]  Young-Min Kwon,et al.  Periprosthetic joint infection is the main reason for failure in patients following periprosthetic fracture treated with revision arthroplasty , 2021, Archives of Orthopaedic and Trauma Surgery.

[10]  Anthony M. J. Bull,et al.  An Anatomical Atlas-Based Scaling Study for Quantifying Muscle and Hip Joint Contact Forces in Above and Through-Knee Amputees Using Validated Musculoskeletal Modelling , 2021, IEEE Transactions on Biomedical Engineering.

[11]  Jacob T. Munro,et al.  Infection and periprosthetic fracture are the leading causes of failure after aseptic revision total knee arthroplasty , 2021, Archives of Orthopaedic and Trauma Surgery.

[12]  H. Matar,et al.  Septic Revision Total Knee Arthroplasty Is Associated With Significantly Higher Mortality Than Aseptic Revisions: Long-Term Single-Center Study (1254 Patients). , 2021, The Journal of arthroplasty.

[13]  E. Makhni,et al.  Artificial Intelligence for the Orthopaedic Surgeon: An Overview of Potential Benefits, Limitations, and Clinical Applications. , 2020, The Journal of the American Academy of Orthopaedic Surgeons.

[14]  E. Makhni,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 , 2020, Orthopaedic journal of sports medicine.

[15]  Antonia F. Chen,et al.  Artificial Intelligence to Identify Arthroplasty Implants From Radiographs of the Knee. , 2020, The Journal of arthroplasty.

[16]  Evan J. Smith,et al.  Outcomes and Risk Factors Associated With 2-Stage Reimplantation Requiring an Interim Spacer Exchange for Periprosthetic Joint Infection. , 2020, The Journal of arthroplasty.

[17]  Benedict U. Nwachukwu,et al.  Radiographic Indices Are Not Predictive of Clinical Outcomes Among 1735 Patients Indicated for Hip Arthroscopic Surgery: A Machine Learning Analysis , 2020, The American journal of sports medicine.

[18]  Benedict U. Nwachukwu,et al.  Machine Learning Outperforms Logistic Regression Analysis to Predict Next-Season NHL Player Injury: An Analysis of 2322 Players From 2007 to 2017 , 2020, Orthopaedic journal of sports medicine.

[19]  Benedict U. Nwachukwu,et al.  Clinical and Research Medical Applications of Artificial Intelligence , 2020, Arthroscopy: The Journal of Arthroscopic & Related Surgery.

[20]  Evan J. Smith,et al.  Development of a Preoperative Risk Calculator for Reinfection Following Revision Surgery for Periprosthetic Joint Infection. , 2020, The Journal of arthroplasty.

[21]  Young-Min Kwon,et al.  Single-Stage Revision of the Infected Total Knee Arthroplasty Is Associated With Improved Functional Outcomes: A Propensity Score-Matched Cohort Study. , 2020, The Journal of arthroplasty.

[22]  B. Werner,et al.  Risk of Prosthetic Joint Infection Increases Following Early Aseptic Revision Surgery of Total Hip and Knee Arthroplasty. , 2020, The Journal of arthroplasty.

[23]  Benedict U. Nwachukwu,et al.  The value of artificial neural networks for predicting length of stay, discharge disposition, and inpatient costs after anatomic and reverse shoulder arthroplasty. , 2020, Journal of shoulder and elbow surgery.

[24]  B. Ricciardi,et al.  Artificial Intelligence and Orthopaedics: An Introduction for Clinicians. , 2020, The Journal of bone and joint surgery. American volume.

[25]  C. Pfirrmann,et al.  Deep convolutional neural network-based detection of meniscus tears: comparison with radiologists and surgery as standard of reference , 2020, Skeletal Radiology.

[26]  B. Ricciardi,et al.  Artificial Intelligence and Orthopaedics: An Introduction for Clinicians. , 2020, The Journal of bone and joint surgery. American volume.

[27]  O. Muratoglu,et al.  Detecting total hip replacement prosthesis design on plain radiographs using deep convolutional neural network , 2019, Journal of orthopaedic research : official publication of the Orthopaedic Research Society.

[28]  V. Krebs,et al.  Can a Machine Learning Model Accurately Predict Patient Resource Utilization Following Lumbar Spinal Fusion? , 2020, The spine journal : official journal of the North American Spine Society.

[29]  Dustin R. Biron,et al.  A Novel Machine Learning Model Developed to Assist in Patient Selection for Outpatient Total Shoulder Arthroplasty. , 2019, The Journal of the American Academy of Orthopaedic Surgeons.

[30]  G. Scuderi**,et al.  Deep Learning Preoperatively Predicts Value Metrics for Primary Total Knee Arthroplasty: Development and Validation of an Artificial Neural Network Model. , 2019, The Journal of arthroplasty.

[31]  M. Lee,et al.  Transfusion after total knee arthroplasty can be predicted using the machine learning algorithm , 2019, Knee Surgery, Sports Traumatology, Arthroscopy.

[32]  Aditya V. Karhade,et al.  Development of Machine Learning Algorithms for Prediction of Sustained Postoperative Opioid Prescriptions After Total Hip Arthroplasty. , 2019, The Journal of arthroplasty.

[33]  J. Mao,et al.  Machine learning for prediction of sustained opioid prescription after anterior cervical discectomy and fusion. , 2019, The spine journal : official journal of the North American Spine Society.

[34]  Michael A Mont,et al.  Remote Patient Monitoring Using Mobile Health for Total Knee Arthroplasty: Validation of a Wearable and Machine Learning-Based Surveillance Platform. , 2019, The Journal of arthroplasty.

[35]  Scott M. Stagg,et al.  Throughput and resolution with a next-generation direct electron detector , 2019, bioRxiv.

[36]  Peter D Chang,et al.  Deep Learning for Detection of Complete Anterior Cruciate Ligament Tear , 2019, Journal of Digital Imaging.

[37]  A. Trickey,et al.  Can Machine Learning Methods Produce Accurate and Easy-to-use Prediction Models of 30-day Complications and Mortality After Knee or Hip Arthroplasty? , 2019, Clinical orthopaedics and related research.

[38]  Z. Čizmić,et al.  Hip and Knee Section, Prevention, Host Related: Proceedings of International Consensus on Orthopedic Infections. , 2019, The Journal of arthroplasty.

[39]  B. Springer,et al.  The prevention of infection: 12 MODIFIABLE RISK FACTORS , 2019, The bone & joint journal.

[40]  Masoumeh Haghpanahi,et al.  Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network , 2019, Nature Medicine.

[41]  Jun S. Kim,et al.  Predicting Surgical Complications in Patients Undergoing Elective Adult Spinal Deformity Procedures Using Machine Learning , 2018, Spine deformity.

[42]  S. Bini.  Artificial Intelligence, Machine Learning, Deep Learning, and Cognitive Computing: What Do These Terms Mean and How Will They Impact Health Care? , 2018, The Journal of arthroplasty.

[43]  J. Parvizi,et al.  Development and Evaluation of a Preoperative Risk Calculator for Periprosthetic Joint Infection Following Total Joint Arthroplasty , 2018, The Journal of bone and joint surgery. American volume.

[44]  Michael A Mont,et al.  Current Epidemiology of Revision Total Knee Arthroplasty in the United States. , 2017, The Journal of arthroplasty.

[45]  Michael A Mont,et al.  Current Epidemiology of Revision Total Hip Arthroplasty in the United States: National Inpatient Sample 2009 to 2013. , 2017, The Journal of arthroplasty.

[46]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[47]  E. Roughead,et al.  Predicting Infections After Total Joint Arthroplasty Using a Prescription Based Comorbidity Measure. , 2015, The Journal of arthroplasty.

[48]  M. Tsou,et al.  Predicting Postoperative Vomiting for Orthopedic Patients Receiving Patient-Controlled Epidural Analgesia with the Application of an Artificial Neural Network , 2014, BioMed research international.

[49]  J. Eckel-Passow,et al.  The Mayo Prosthetic Joint Infection Risk Score: Implication for Surgical Site Infection Reporting and Risk Stratification , 2012, Infection Control & Hospital Epidemiology.

[50]  J. Parvizi,et al.  New Definition for Periprosthetic Joint Infection: From the Workgroup of the Musculoskeletal Infection Society , 2011, Clinical orthopaedics and related research.

[51]  Javad Parvizi,et al.  Failure following revision total knee arthroplasty: infection is the major cause , 2011, International Orthopaedics.

[52]  Steven M. Kurtz,et al.  The Epidemiology of Revision Total Knee Arthroplasty in the United States , 2009, Clinical orthopaedics and related research.

[53]  S. Kurtz,et al.  Projections of primary and revision hip and knee arthroplasty in the United States from 2005 to 2030. , 2007, The Journal of bone and joint surgery. American volume.

[54]  K. Bozic,et al.  The impact of infection after total hip arthroplasty on hospital and surgeon resource utilization. , 2005, The Journal of bone and joint surgery. American volume.