Total knee arthroplasty after a prior knee arthroscopy has higher complication rates: a systematic review

Arthroscopic Procedures Are Performed in 5% of Patients With Knee Osteoarthritis 1 Year Preceding Total Knee Arthroplasty and Are Associated With Increased Stiffness and Increased Costs

Purpose

To describe the different types of arthroscopic procedures that patients undergo in the year prior to total knee arthroplasty (TKA), reveal the cost associated with these procedures, and understand the relationship between preoperative arthroscopy and clinical outcomes after TKA.

Methods

An observational cohort study was conducted using the IBM Watson Health MarketScan databases. Patients with knee osteoarthritis who underwent unilateral isolated primary TKA between January 1, 2018, and September 30, 2019, were included. Knee arthroscopic procedures performed in the 1-year period before a primary TKA was identified. The primary outcomes of interest were cost of these procedures and the risk of 90-day postoperative complications.

Results

In total, 2,904 patients, representing 5.2% of the analyzed cohort, underwent arthroscopic procedures in the year prior to TKA. The most common procedure and diagnosis were meniscectomy and meniscal tear, respectively, with procedures performed an average of 7.2 ± 3.0 months before TKA. Average per patient costs were $9,716 ± $5,500 in the highest payment quartile vs $1,789 ± 636 in the lowest payment quartile. Patients with a history of arthroscopy were more likely to develop postoperative stiffness (P = .001), while no difference was found in the risk of 90-day periprosthetic joint infection (PJI).

Conclusions

Of the patients, 5.2% underwent knee arthroscopy in the year prior to TKA. While no association was seen with PJI risk, the costs associated with these procedures are high and may increase the overall cost of management of knee osteoarthritis.

Level of Evidence

Level III, retrospective comparative study.

The utilization of artificial neural networks for the prediction of 90-day unplanned readmissions following total knee arthroplasty

BACKGROUND

A reliable predictive tool to predict unplanned readmissions has the potential to lower readmission rates through targeted pre-operative counseling and intervention with respect to modifiable risk factors. This study aimed to develop and internally validate machine learning models for the prediction of 90-day unplanned readmissions following total knee arthroplasty.

METHODS

A total of 10,021 consecutive patients underwent total knee arthroplasty. Patient charts were manually reviewed to identify patient demographics and surgical variables that may be associated with 90-day unplanned hospital readmissions. Four machine learning algorithms (artificial neural networks, support vector machine, k-nearest neighbor, and elastic-net penalized logistic regression) were developed to predict 90-day unplanned readmissions following total knee arthroplasty and these models were evaluated using ROC AUC statistics as well as calibration and decision curve analysis.

RESULTS

Within the study cohort, 644 patients (6.4%) were readmitted within 90 days. The factors most significantly associated with 90-day unplanned hospital readmissions included drug abuse, surgical operative time, and American Society of Anaesthesiologist Physical Status (ASA) score. The machine learning models all achieved excellent performance across discrimination (AUC > 0.82), calibration, and decision curve analysis.

CONCLUSION

This study developed four machine learning models for the prediction of 90-day unplanned hospital readmissions in patients following total knee arthroplasty. The strongest predictors for unplanned hospital readmissions were drug abuse, surgical operative time, and ASA score. The study findings show excellent model performance across all four models, highlighting the potential of these models for the identification of high-risk patients prior to surgery for whom coordinated care efforts may decrease the risk of subsequent hospital readmission.

LEVEL OF EVIDENCE

Level III, case-control retrospective analysis.