2020 Frank Stinchfield Award: Identifying who will fail following irrigation and debridement for prosthetic joint infection

Abstract

Aims Failure of irrigation and debridement (I&D) for prosthetic joint infection (PJI) is influenced by numerous host, surgical, and pathogen-related factors. We aimed to develop and validate a practical, easy-to-use tool based on machine learning that may accurately predict outcome following I&D surgery taking into account the influence of numerous factors. Methods This was an international, multicentre retrospective study of 1,174 revision total hip (THA) and knee arthroplasties (TKA) undergoing I&D for PJI between January 2005 and December 2017. PJI was defined using the Musculoskeletal Infection Society (MSIS) criteria. A total of 52 variables including demographics, comorbidities, and clinical and laboratory findings were evaluated using random forest machine learning analysis. The algorithm was then verified through cross-validation. Results Of the 1,174 patients that were included in the study, 405 patients (34.5%) failed treatment. Using random forest analysis, an algorithm that provides the probability for failure for each specific patient was created. By order of importance, the ten most important variables associated with failure of I&D were serum CRP levels, positive blood cultures, indication for index arthroplasty other than osteoarthritis, not exchanging the modular components, use of immunosuppressive medication, late acute (haematogenous) infections, methicillin-resistant Staphylococcus aureus infection, overlying skin infection, polymicrobial infection, and older age. The algorithm had good discriminatory capability (area under the curve = 0.74). Cross-validation showed similar probabilities comparing predicted and observed failures indicating high accuracy of the model. Conclusion This is the first study in the orthopaedic literature to use machine learning as a tool for predicting outcomes following I&D surgery. The developed algorithm provides the medical profession with a tool that can be employed in clinical decision-making and improve patient care. Future studies should aid in further validating this tool on additional cohorts. Cite this article: Bone Joint J 2020;102-B(7 Supple B):11–19.

One-year infection control rates of a DAIR (debridement, antibiotics and implant retention) procedure after primary and prosthetic-joint-infection-related revision arthroplasty – a retrospective cohort study

“…Byren and colleagues reported a failure rate of 35 % and a 3.1 times increase in hazard ratio for failure of DAIR if it is performed after revision arthroplasty compared to after primary arthroplasty (Byren et al, 2009). Shohat and colleagues found no significant difference in the success rate if DAIR was performed after primary or revision arthroplasty (p = 0.182) (Shohat et al, 2020). Lastly, Wouthuyzen-Bakker and colleagues found unadjusted and adjusted odds ratios of 1.65 (p = 0.04) and 0.96 (p = 0.90), respectively, for failure of a DAIR performed on revised prostheses with late prosthetic joint infections .…”

“…The most common clinical signs of acute and hematogenous PJI include acute pain, erythema and fever (Barrett and Atkins, 2014;Zimmerli, 2006). A debridement, antibiotics and implant retention (DAIR) procedure is the treatment of choice for acute PJI of the hip and knee (Chotanaphuti et al, 2019;Sukeik and Haddad, 2019;. A recent systematic review and meta-analysis reported a wide range of success percentages for DAIR procedures from 11 % to 100 % (Kunutsor et al, 2018;Tsang et al, 2017).…”

“…The success rate of DAIR for early postoperative infection is better than for hematogenous infections (Volpin et al, 2016;Wouthuyzen-Bakker et al, 2020). There is no place for DAIR in the treatment of chronic infections (Sukeik and Haddad, 2019). Prior infection in another prosthetic joint and prior two-stage exchange for PJI of the same joint are both reported to worsen the infection eradication rate of a repeated revision procedure compared to a first revision (Chalmers et al, 2019;Khan et al, 2019).…”

To DAIR or not to DAIR: Decision-making in the management of acute prosthetic joint infection � A narrative review

“…The observed heterogeneity across studies addressing the efficacy of DAIR also underlines the importance of focusing on adjustable risk factors, such as optimization of the patient's baseline conditions before and after DAIR treatment, using biofilm-active antimicrobials when possible, and thorough performance of surgical debridement. Several studies in this respect observed a better prognosis when the removable components of the prosthesis were exchanged during debridement 12,25,32,50,55,56 .…”

Risk Scores and Machine Learning to Identify Patients With Acute Periprosthetic Joints Infections That Will Likely Fail Classical Irrigation and Debridement

“…Machine learning has become more and more popular in infection management (33). Recently, Shohat et al used random forest analysis as a machine learning model to predict DAIR failure (34). The authors of this study analyzed more than 1,000 patients that underwent irrigation and debridement of a hip or knee prosthesis for acute PJI.…”