Machine learning models accurately predict recurrent infection following revision total knee arthroplasty for periprosthetic joint infection

2021 ◽  
Author(s):  
Christian Klemt ◽  
Samuel Laurencin ◽  
Akachimere Cosmas Uzosike ◽  
Jillian C. Burns ◽  
Timothy G. Costales ◽  
...  
Keyword(s):  
Machine Learning ◽  
Total Knee Arthroplasty ◽  
Knee Arthroplasty ◽  
Periprosthetic Joint Infection ◽  
Joint Infection ◽  
Recurrent Infection ◽  
Revision Total Knee Arthroplasty ◽  
Learning Models ◽  
Total Knee ◽  
Machine Learning Models

Outcomes of single- and two-stage revision total knee arthroplasty for chronic periprosthetic joint infection

2021 ◽  
Vol 103-B (8) ◽  
pp. 1373-1379
Author(s):  
Hosam E. Matar ◽  
Benjamin V. Bloch ◽  
Susan E. Snape ◽  
Peter J. James
Keyword(s):  
Total Knee Arthroplasty ◽  
Knee Arthroplasty ◽  
Joint Infection ◽  
Recurrent Infection ◽  
Primary Outcome Measure ◽  
Revision Total Knee Arthroplasty ◽  
Single Stage ◽  
Two Stage ◽  
Joint Infections ◽  
Total Knee

Aims Single-stage revision total knee arthroplasty (rTKA) is gaining popularity in treating chronic periprosthetic joint infections (PJIs). We have introduced this approach to our clinical practice and sought to evaluate rates of reinfection and re-revision, along with predictors of failure of both single- and two-stage rTKA for chronic PJI. Methods A retrospective comparative cohort study of all rTKAs for chronic PJI between 1 April 2003 and 31 December 2018 was undertaken using prospective databases. Patients with acute infections were excluded; rTKAs were classified as single-stage, stage 1, or stage 2 of two-stage revision. The primary outcome measure was failure to eradicate or recurrent infection. Variables evaluated for failure by regression analysis included age, BMI, American Society of Anesthesiologists grade, infecting organisms, and the presence of a sinus. Patient survivorship was also compared between the groups. Results A total of 292 consecutive first-time rTKAs for chronic PJI were included: 82 single-stage (28.1%); and 210 two-stage (71.9%) revisions. The mean age was 71 years (27 to 90), with 165 females (57.4%), and a mean BMI of 30.9 kg/m2 (20 to 53). Significantly more patients with a known infecting organism were in the single-stage group (93.9% vs 80.47%; p = 0.004). The infecting organism was identified preoperatively in 246 cases (84.2%). At a mean follow-up of 6.3 years (2.0 to 17.6), the failure rate was 6.1% in the single-stage, and 12% in the two-stage groups. All failures occurred within four years of treatment. The presence of a sinus was an independent risk factor for failure (odds ratio (OR) 4.97; 95% confidence interval (CI) 1.593 to 15.505; p = 0.006), as well as age > 80 years (OR 5.962; 95% CI 1.156 to 30.73; p = 0.033). The ten-year patient survivorship rate was 72% in the single-stage group compared with 70.5% in the two-stage group. This difference was not significant (p = 0.517). Conclusion Single-stage rTKA is an effective strategy with a high success rate comparable to two-stage approach in appropriately selected patients. Cite this article: Bone Joint J 2021;103-B(8):1373–1379.

Logistic Regression and Machine Learning Models Cannot Discriminate Between Satisfied and Dissatisfied Total Knee Arthroplasty Patients

2021 ◽  
Author(s):  
Joseph S. Munn ◽  
Brent A. Lanting ◽  
Steven J. MacDonald ◽  
Lyndsay E. Somerville ◽  
Jacquelyn D. Marsh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Total Knee Arthroplasty ◽  
Logistic Regression ◽  
Knee Arthroplasty ◽  
Learning Models ◽  
Total Knee ◽  
Machine Learning Models

scholarly journals Two-Stage Revision Total Knee Arthroplasty in Cases of Periprosthetic Joint Infection: An Analysis of 50 Cases

2015 ◽  
Vol 9 (1) ◽  
pp. 49-56 ◽  
Author(s):  
Leif Claassen ◽  
Christian Plaass ◽  
Kiriakos Daniilidis ◽  
Tilman Calliess ◽  
Gabriela von Lewinski
Keyword(s):  
Total Knee Arthroplasty ◽  
Success Rate ◽  
Knee Arthroplasty ◽  
Periprosthetic Joint Infection ◽  
Persistent Infection ◽  
Joint Infection ◽  
Revision Total Knee Arthroplasty ◽  
Two Stage ◽  
Comorbidity Index ◽  
Total Knee

Objectives: A periprosthetic joint infection (PJI) is a significant complication after total knee arthroplasty (TKA). Still there is no agreement on a perfect diagnosis and treatment algorithm. The aim of this study was to evaluate the success and revision rates after two-stage revision total knee arthroplasty (TKA) and factors that affect the success rate.Material and Methods:50 consecutive two-stage revision TKAs were performed between January 2011 and December 2012. We retrospectively reviewed study patient's charts including demographics, prior surgeries, comorbidities, incidence of persistent infection and revisions. At the final follow-up examination the patient's satisfaction, pain level and disorders were evaluated. A successful clinical outcome was defined as a functioning prosthesis without wound healing disorders, no sinuses tracts or other clinical evidence of a persistent infection.Results: Re-implantation of prosthesis was performed in 47 cases; three patients received a septic arthrodesis. Twelve patients had a persistent infection despite two-stage re-implantation resulting in a success rate of 76.0%. In eight of these twelve patients an infecting germ was isolated during second-stage procedure. Three patients received another two-stage revision arthroplasty and one patient an above knee amputation. A revision was performed in 23 of 50 patients (46.0%). Factors that diminish the success rate were further operations after primary TKA (p = 0.048), prior revision arthroplasties after TKA (p = 0.045), nicotine abuse (p = 0.048), Charlson comorbidity index above a score of 2 (p = 0.031) and a mixed flora during first-stage procedure (p < 0.001). Age, sex, immune status, chronic anticoagulant use, rheumatoid arthritis, body mass index and the presence of multidrug resistant germs showed no significant effect on success rate (p > 0.05).Conclusion: We found that patients who required surgery after the primary TKA, had a higher Charlson comorbidity index or were found to have mixed flora during explantation. The treatment of PJI remains difficult, both for the patient and for the treating surgeons.

scholarly journals High Rates of Aseptic Loosening After Revision Total Knee Arthroplasty for Periprosthetic Joint Infection

2020 ◽  
Vol 5 (3) ◽  
pp. e20.00026-e20.00026
Author(s):  
Arne Kienzle ◽  
Sandy Walter ◽  
Philipp von Roth ◽  
Michael Fuchs ◽  
Tobias Winkler ◽  
...  
Keyword(s):  
Total Knee Arthroplasty ◽  
Aseptic Loosening ◽  
Knee Arthroplasty ◽  
Periprosthetic Joint Infection ◽  
Joint Infection ◽  
Revision Total Knee Arthroplasty ◽  
Total Knee

scholarly journals Two-stage revision total knee arthroplasty with antibiotic-impregnated hydroxyapatite

2020 ◽  
Author(s):  
Masahiro Hasegawa ◽  
Shine Tone ◽  
Yohei Naito ◽  
Hiroki Wakabayashi ◽  
Akihiro Sudo
Keyword(s):  
Total Knee Arthroplasty ◽  
Knee Arthroplasty ◽  
Joint Infection ◽  
Recurrent Infection ◽  
Clinical Results ◽  
Joint Space ◽  
Revision Total Knee Arthroplasty ◽  
Two Stage ◽  
Total Knee ◽  
Revision Tka

Abstract Background: Antibiotic-impregnated hydroxyapatite (HA) has been used as a new drug delivery system for the treatment of periprosthetic joint infection (PJI) of the knee. The aim of this study was to evaluate the clinical results of this treatment in patients with PJI. Methods: Fourteen consecutive cases of PJI of the knee who were scheduled to undergo two-stage knee revision were enrolled. In the first stage, all components were removed with thorough debridement, and antibiotic-impregnated HA was inserted in the bone and joint space. In the second stage, revision total knee arthroplasty (TKA) was performed after eradication of infection. The mean period from removal of all components and treatment with antibiotic-impregnated HA to revision TKA was 3.4 months. Clinical and radiographic evaluations were performed after a mean follow-up of 5.1 years following revision TKA. Predictors of reinfection were evaluated. Results: Eleven patients had no recurrent infection, whereas 3 patients showed recurrent infection. No knees had osteolysis or loosening after revision TKA. The present study demonstrated no predictors for reinfection. Conclusion: Antibiotic-impregnated HA could be effective for the treatment of infected knee arthroplasty.

scholarly journals Subtask Segmentation of Timed Up and Go Test for Mobility Assessment of Perioperative Total Knee Arthroplasty

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6302
Author(s):  
Chia-Yeh Hsieh ◽  
Hsiang-Yun Huang ◽  
Kai-Chun Liu ◽  
Kun-Hui Chen ◽  
Steen Jun-Ping Hsu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Total Knee Arthroplasty ◽  
Knee Arthroplasty ◽  
Window Size ◽  
Learning Models ◽  
Timed Up And Go ◽  
Knee Oa ◽  
Segmentation Approach ◽  
Total Knee ◽  
Machine Learning Models

Total knee arthroplasty (TKA) is one of the most common treatments for people with severe knee osteoarthritis (OA). The accuracy of outcome measurements and quantitative assessments for perioperative TKA is an important issue in clinical practice. Timed up and go (TUG) tests have been validated to measure basic mobility and balance capabilities. A TUG test contains a series of subtasks, including sit-to-stand, walking-out, turning, walking-in, turning around, and stand-to-sit tasks. Detailed information about subtasks is essential to aid clinical professionals and physiotherapists in making assessment decisions. The main objective of this study is to design and develop a subtask segmentation approach using machine-learning models and knowledge-based postprocessing during the TUG test for perioperative TKA. The experiment recruited 26 patients with severe knee OA (11 patients with bilateral TKA planned and 15 patients with unilateral TKA planned). A series of signal-processing mechanisms and pattern recognition approaches involving machine learning-based multi-classifiers, fragmentation modification and subtask inference are designed and developed to tackle technical challenges in typical classification algorithms, including motion variability, fragmentation and ambiguity. The experimental results reveal that the accuracy of the proposed subtask segmentation approach using the AdaBoost technique with a window size of 128 samples is 92%, which is an improvement of at least 15% compared to that of the typical subtask segmentation approach using machine-learning models only.

scholarly journals External fixator arthrodesis antibiotic spacer in two-stage revision total knee arthroplasty for eradication of periprosthetic joint infection

2019 ◽  
Vol 5 (3) ◽  
pp. 309-313
Author(s):  
Brian P. Chalmers ◽  
Nicholas M. Hernandez ◽  
Brandon J. Yuan ◽  
Matthew P. Abdel ◽  
David G. Lewallen ◽  
...  
Keyword(s):  
Total Knee Arthroplasty ◽  
Knee Arthroplasty ◽  
External Fixator ◽  
Periprosthetic Joint Infection ◽  
Joint Infection ◽  
Revision Total Knee Arthroplasty ◽  
Two Stage ◽  
Total Knee ◽  
Antibiotic Spacer

scholarly journals Detailed Revision Risk Analysis after Single- vs. Two-Stage Revision Total Knee Arthroplasty in Periprosthetic Joint Infection: A Retrospective Tertiary Center Analysis

Antibiotics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1177
Author(s):  
Lars-Rene Tuecking ◽  
Julia Silligmann ◽  
Peter Savov ◽  
Mohamed Omar ◽  
Henning Windhagen ◽  
...  
Keyword(s):  
Total Knee Arthroplasty ◽  
Knee Arthroplasty ◽  
Periprosthetic Joint Infection ◽  
Revision Rate ◽  
Joint Infection ◽  
Revision Total Knee Arthroplasty ◽  
Implant Survival ◽  
Two Stage ◽  
Tertiary Center ◽  
Total Knee

Periprosthetic joint infection (PJI) remains one of the most common causes of revision knee arthroplasty. Controversy continues to surround the proper operative technique of PJI in knee arthroplasty with single- or two-stage replacement. Significant variations are seen in the eradication rates of PJI and in implant survival rates. This detailed retrospective analysis of a single tertiary center is intended to provide further data and insight comparing single- and two-stage revision surgery. A retrospective analysis of all revision total knee arthroplasty (TKA) surgeries from 2013 to 2019 was performed and screened with respect to single- or two-stage TKA revisions. Single- and two-stage revisions were analyzed with regard to implant survival, revision rate, microbiological spectrum, and other typical demographic characteristics. A total of 63 patients were included, with 15 patients undergoing single-stage revision and 48 patients undergoing two-stage revision. The mean follow-up time was 40.7 to 43.7 months. Statistically, no difference was found between both groups in overall survival (54.4% vs. 70.1%, p = 0.68) and implant survival with respect to reinfection (71.4% vs. 82.4%, p = 0.48). Further, high reinfection rates were found for patients with difficult-to-treat organisms and low- to semi-constrained implant types, in comparison to constrained implant types. A statistically comparable revision rate for recurrence of infection could be shown for both groups, although a tendency to higher reinfection rate for single-stage change was evident. The revision rate in this single-center study was comparably high, which could be caused by the high comorbidity and high proportion of difficult-to-treat bacteria in patients at a tertiary center. In this patient population, the expectation of implant survival should be critically discussed with patients.

Sign in / Sign up

Export Citation Format

Share Document