The Use of Artificial Neural Networks for the Prediction of Surgical Site Infection Following TKA.

This is a retrospective study. Surgical site infection (SSI) is associated with adverse postoperative outcomes following total knee arthroplasty (TKA). However, accurately predicting SSI remains a clinical challenge due to the multitude of patient and surgical factors associated with SSI. This study aimed to develop and validate machine learning models for the prediction of SSI following primary TKA. This is a retrospective study for patients who underwent primary TKA. Chart review was performed to identify patients with superficial or deep SSIs, defined in concordance with the criteria of the Musculoskeletal Infection Society. All patients had a minimum follow-up of 2 years (range: 2.1-4.7 years). Five machine learning algorithms were developed to predict this outcome, and model assessment was performed by discrimination, calibration, and decision curve analysis. A total of 10,021 consecutive primary TKA patients was included in this study. At an average follow-up of 2.8 ± 1.1 years, SSIs were reported in 404 (4.0%) TKA patients, including 223 superficial SSIs and 181 deep SSIs. The neural network model achieved the best performance across discrimination (area under the receiver operating characteristic curve = 0.84), calibration, and decision curve analysis. The strongest predictors of the occurrence of SSI following primary TKA, in order, were Charlson comorbidity index, obesity (BMI >30 kg/m2), and smoking. The neural network model presented in this study represents an accurate method to predict patient-specific superficial and deep SSIs following primary TKA, which may be employed to assist in clinical decision-making to optimize outcomes in at-risk patients.

Can machine learning models predict failure of revision total hip arthroplasty?

INTRODUCTION: Revision total hip arthroplasty (THA) represents a technically demanding surgical procedure which is associated with significant morbidity and mortality. Understanding risk factors for failure of revision THA is of clinical importance to identify at-risk patients. This study aimed to develop and validate novel machine learning algorithms for the prediction of re-revision surgery for patients following revision total hip arthroplasty. METHODS: A total of 2588 consecutive patients that underwent revision THA was evaluated, including 408 patients (15.7%) with confirmed re-revision THA. Electronic patient records were manually reviewed to identify patient demographics, implant characteristics and surgical variables that may be associated with re-revision THA. Machine learning algorithms were developed to predict re-revision THA and these models were assessed by discrimination, calibration and decision curve analysis. RESULTS: The strongest predictors for re-revision THA as predicted by the four validated machine learning models were the American Society of Anaesthesiology score, obesity (> 35 kg/m2) and indication for revision THA. The four machine learning models all achieved excellent performance across discrimination (AUC > 0.80), calibration and decision curve analysis. Higher net benefits for all machine learning models were demonstrated, when compared to the default strategies of changing management for all patients or no patients. CONCLUSION: This study developed four machine learning models for the prediction of re-revision surgery for patients following revision total hip arthroplasty. The study findings show excellent model performance, highlighting the potential of these computational models to assist in preoperative patient optimization and counselling to improve revision THA patient outcomes. LEVEL OF EVIDENCE: Level III, case-control retrospective analysis.

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

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 artificial 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 defined as patients with prolonged LOS. Three artificial intelligence algorithms were developed to predict prolonged LOS following revision TKA and these models were assessed by discrimination, calibration and decision curve analysis. RESULTS: The 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/m2; p < 0.001). The three artificial intelligence algorithms all achieved excellent performance across discrimination (AUC > 0.84) and decision curve analysis (p < 0.01). CONCLUSION: The study findings demonstrate excellent performance on discrimination, calibration and decision curve analysis for all three candidate algorithms. This highlights the potential of these artificial intelligence algorithms to assist in the preoperative identification of patients with an increased risk of prolonged LOS following revision TKA, which may aid in strategic discharge planning. LEVEL OF EVIDENCE: IV.

Machine learning algorithms predict extended postoperative opioid use in primary total knee arthroplasty.

PURPOSE: Adequate postoperative pain control following total knee arthroplasty (TKA) is required to achieve optimal patient recovery. However, the postoperative recovery may lead to an unnaturally extended opioid use, which has been associated with adverse outcomes. This study hypothesizes that machine learning models can accurately predict extended opioid use following primary TKA. METHODS: A total of 8873 consecutive patients that underwent primary TKA were evaluated, including 643 patients (7.2%) with extended postoperative opioid use (> 90 days). Electronic patient records were manually reviewed to identify patient demographics and surgical variables associated with prolonged postoperative opioid use. Five machine learning algorithms were developed, encompassing the breadth of state-of-the-art machine learning algorithms available in the literature, to predict extended opioid use following primary TKA, and these models were assessed by discrimination, calibration, and decision curve analysis. RESULTS: The strongest predictors for prolonged opioid prescription following primary TKA were preoperative opioid duration (100% importance; p < 0.01), drug abuse (54% importance; p < 0.01), and depression (47% importance; p < 0.01). The five machine learning models all achieved excellent performance across discrimination (AUC > 0.83), calibration, and decision curve analysis. Higher net benefits for all machine learning models were demonstrated, when compared to the default strategies of changing management for all patients or no patients. CONCLUSION: The study findings show excellent model performance for the prediction of extended postoperative opioid use following primary total knee arthroplasty, highlighting the potential of these models to assist in preoperatively identifying at risk patients, and allowing the implementation of individualized peri-operative counselling and pain management strategies to mitigate complications associated with prolonged opioid use. LEVEL OF EVIDENCE: IV.