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

Klemt, Christian; Laurencin, Samuel J.; Uzosike, Akachimere; Burns, Jillian C.; Costales, Timothy; Yeo, I; Habibi, Yasamin; Kwon, Young‐Min

doi:10.1007/s00167-021-06794-3

Cited by 24 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Li et al developed a XGBoost model to predict the length of stay after TKA based on 1,826 cases in a single centre and yielded an AUC of 0.74, concluding an improved prediction in comparison to logistic regression models [21]. Recently, Klemt et al investigated four different ML models on 618 consecutive patients who underwent revision TKA for periprosthetic joint infection to predict recurrent infection and achieved excellent performance across discrimination (AUC range 0.81–0.84) [17]. Kunze et al examined in a multicentre approach 430 patients and evaluated a Five supervised machine learning algorithms to identify factors for predicting dissatisfaction after primary TKA, yielding a Brier score of 0.082 [19].…”

Section: Discussionmentioning

confidence: 99%

Prediction of complications and surgery duration in primary TKA with high accuracy using machine learning with arthroplasty-specific data

Hinterwimmer

Lazic

Langer

et al. 2022

Knee Surg Sports Traumatol Arthrosc

View full text Add to dashboard Cite

Purpose The number of primary total knee arthroplasties (TKA) is expected to rise constantly. For patients and healthcare providers, the early identification of risk factors therefore becomes increasingly fundamental in the context of precision medicine. Others have already investigated the detection of risk factors by conducting literature reviews and applying conventional statistical methods. Since the prediction of events has been moderately accurate, a more comprehensive approach is needed. Machine learning (ML) algorithms have had ample success in many disciplines. However, these methods have not yet had a significant impact in orthopaedic research. The selection of a data source as well as the inclusion of relevant parameters is of utmost importance in this context. In this study, a standardized approach for ML in TKA to predict complications during surgery and an irregular surgery duration using data from two German arthroplasty-specific registries was evaluated. Methods The dataset is based on two initiatives of the German Society for Orthopaedics and Orthopaedic Surgery. A problem statement and initial parameters were defined. After screening, cleaning and preparation of these datasets, 864 cases of primary TKA (2016–2019) were gathered. The XGBoost algorithm was chosen and applied with a hyperparameter search, a cross validation and a loss weighting to cope with class imbalance. For final evaluation, several metrics (accuracy, sensitivity, specificity, AUC) were calculated. Results An accuracy of 92.0%, sensitivity of 34.8%, specificity of 95.8%, and AUC of 78.0% were achieved for predicting complications in primary TKA and 93.4%, 74.0%, 96.3%, and 91.6% for predicting irregular surgery duration, respectively. While traditional statistics (correlation coefficient) could not find any relevant correlation between any two parameters, the feature importance revealed several non-linear outcomes. Conclusion In this study, a feasible ML model to predict outcomes of primary TKA with very promising results was built. Complex correlations between parameters were detected, which could not be recognized by conventional statistical analysis. Arthroplasty-specific data were identified as relevant by the ML model and should be included in future clinical applications. Furthermore, an interdisciplinary interpretation as well as evaluation of the results by a data scientist and an orthopaedic surgeon are of paramount importance. Level of evidence Level IV.

show abstract

Section: Discussionmentioning

confidence: 99%

Prediction of complications and surgery duration in primary TKA with high accuracy using machine learning with arthroplasty-specific data

Hinterwimmer

Lazic

Langer

et al. 2022

Knee Surg Sports Traumatol Arthrosc

View full text Add to dashboard Cite

show abstract

“…Third, informatic features include demographics, comorbidities, clinical and laboratory test results, and based on work done by the Shock Trauma team, a postoperative infection risk score model [20] showed good prediction on infection risks. Current applications using informatic features as predictive tools are mainly in periprosthetic joint infection prediction [21,22].…”

Section: Introductionmentioning

confidence: 99%

Risk prediction on orthopaedic trauma patients for fracture-associated infection using dynamic contrast enhanced-fluorescence imaging

Han

Bateman²,

Werth³

et al. 2023

Molecular-Guided Surgery: Molecules, Devices, and Applications IX

View full text Add to dashboard Cite

Debridement of the surgical site during open fracture reduction and internal fixation is important for preventing surgical site infection; the risk of subsequent fracture-associated infection for a particular area of tissue is assessed by the surgeon based on multi-level variables, including demographics and laboratory results. Intraoperative fluorescence imaging can contribute additional information at a more localized level. Here we present a fluorescence-based predictive model using features from dynamic contrast enhanced-fluorescence imaging (DCE-FI), as well as patient-level variables associated with infection risk. Regions-of-interest were selected from thirty-eight enrolled open fracture patients. Spatial and kinetic features were extracted from DCE-FI, and combined with patient infection risk factor describing the possibility of getting surgical-site-infection. The model was evaluated for ability to predict composite outcome scores—intra-operative surgeon assessment coupled with post-operative confirmed infection outcome. This proposed model demonstrates high predictive performance with an accuracy of 0.86, evaluated with a cross-validation approach, and is a promising approach for early and quick identification of tissue prone to infection.

show abstract

“…Artiicial intelligence (AI) algorithms, such as artiicial neural networks (ANN), represent valuable tools for analyzing and interpreting large and complex datasets, thus these were applied in many medical ields [4,23]. Although AI algorithms were used in prior literature to predict clinical and functional outcomes for patients following arthroplasty surgery [15][16][17], AI algorithms have yet to be used for the prediction of prolonged length of stay. Therefore, the aim of this study was to develop and validate artiicial intelligence algorithms for identifying patients at higher risk of prolonged length of stay following revision total knee arthroplasty.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence algorithms accurately predict prolonged length of stay following revision total knee arthroplasty

Klemt

Tirumala

Barghi

et al. 2022

Knee Surg Sports Traumatol Arthrosc

Self Cite

View full text Add to dashboard Cite

Purpose Although the average length of hospital stay following revision total knee arthroplasty (TKA) has decreased over recent years due to improved perioperative and intraoperative techniques and planning, prolonged length of stay (LOS) continues to be a substantial driver of hospital costs. The purpose of this study was to develop and validate artiicial intelligence algorithms for the prediction of prolonged length of stay for patients following revision TKA. Methods A total of 2512 consecutive patients who underwent revision TKA were evaluated. Those patients with a length of stay greater than 75th percentile for all length of stays were deined as patients with prolonged LOS. Three artiicial intelligence algorithms were developed to predict prolonged LOS following revision TKA and these models were assessed by discrimination, calibration and decision curve analysis. ResultsThe strongest predictors for prolonged length of stay following revision TKA were age (> 75 years; p < 0.001), Charlson Comorbidity Index (> 6; p < 0.001) and body mass index (> 35 kg/m 2 ; p < 0.001). The three artiicial intelligence algorithms all achieved excellent performance across discrimination (AUC > 0.84) and decision curve analysis (p < 0.01). ConclusionThe study indings demonstrate excellent performance on discrimination, calibration and decision curve analysis for all three candidate algorithms. This highlights the potential of these artiicial intelligence algorithms to assist in the preoperative identiication of patients with an increased risk of prolonged LOS following revision TKA, which may aid in strategic discharge planning. Level of evidence IV.

show abstract

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

Cited by 24 publications

References 31 publications

Prediction of complications and surgery duration in primary TKA with high accuracy using machine learning with arthroplasty-specific data

Prediction of complications and surgery duration in primary TKA with high accuracy using machine learning with arthroplasty-specific data

Risk prediction on orthopaedic trauma patients for fracture-associated infection using dynamic contrast enhanced-fluorescence imaging

Artificial intelligence algorithms accurately predict prolonged length of stay following revision total knee arthroplasty

Contact Info

Product

Resources

About