Leveraging large, real-world data through machine-learning to increase efficiency in robotic-assisted total knee arthroplasty

Trends of robotic total joint arthroplasty utilization in the United States from 2010 to 2022: a nationwide assessment

The adoption of robotic assistance in total knee arthroplasty (TKA) and total hip arthroplasty (THA) is growing rapidly worldwide. This study aims to evaluate recent trends in the utilization of robotic-assisted TKA and THA across the United States spanning a 12-year period. This retrospective analysis utilized the PearlDiver All Payer Claims Database to identify patients who underwent primary, elective primary TKA or THA between 2010 and 2022. Procedures were categorized as conventional or robot assisted based on International Classification of Diseases (ICD-9), ICD-10, and Current Procedural Technology (CPT) codes. Patient demographics were captured including age, sex, and comorbidities. Annual usage trends for each modality were analyzed. Simple linear regressions were utilized to evaluate changes in the proportion of annual robot-assisted TJA performed over time relative to total procedures. P values < 0.05 were significant. Of the 2,294,076 total TKAs performed between 2010 and 2022, 1.58% were robotic assisted. Similarly, of the 1,235,577 total THAs performed, 1.26% utilized robotic assistance. Robotic TKA accounted for a steadily increasing percentage of total TKA procedures, significantly growing from 0.35% in 2010 to 3.45% in 2022, peaking at 4.39% in 2019 (P < 0.001). Similarly, robotic THA utilization showed significant growth, increasing from 0.26% in 2010 to 2.36% in 2022, peaking at 3.59% in 2019 (P < 0.001). The use of robotic-assisted TKA and THA has seen significant growth across the United States. Robotic TKA and THA have become increasingly utilized technologies, with steady growth in adoption since 2010.Level of evidence: III.

Artificial Intelligence in Commercial Industry: Serving the End-to-End Patient Experience Across the Digital Ecosystem

The purpose of this article is to evaluate the application of artificial intelligence (AI) from the perspective of the orthopaedic industry with respect to the specific opportunities offered by AI. It is clear that AI has the potential to impact the entire continuum of musculoskeletal and orthopaedic care. The following areas may experience improvements from integrating AI into surgical applications: surgical trainees can learn more easily at lower costs in extended reality simulations; physicians can receive support in decision-making and case planning; efficiencies can be driven with improved case management and hospital episodes; performing surgery, which until recently was the only element industry engaged with, can benefit from intraoperative AI-derived inputs; and postoperative care can be tailored to the individual patient and their circumstances. AI delivers the potential for industry to offer valuable augments to patient experience and enhanced surgical insights along the digital episode of care. However, the true value is in considering not just how AI can be applied in each silo but also across the patient's entire continuum of care. This opportunity was first opened with the advent of robotics. The data derived from the robotic systems have added something akin to a black box flight recorder to the operation, which now offers 2 critical outcomes for industry. First, together we can now start to stitch preoperative elements like demographics, morphological phenotyping, and pathology that can be integrated with intraoperative elements to produce surgical plans and on-the-fly anatomic data like ligament tension. Second, postoperative elements such as recovery protocols and outcomes can be considered through the lens of the intraoperative experience. In forming this bridge, AI can accelerate the development of a truly integrated digital ecosystem, facilitating a shift from providing implants to providing patient experience pathways. LEVEL OF EVIDENCE: Level V, expert opinion.

Lack of Validity of Absolute Percentage Errors in Estimated Operating Room Case Durations as a Measure of Operating Room Performance: A Focused Narrative Review

Commonly reported end points for operating room (OR) and surgical scheduling performance are the percentages of estimated OR times whose absolute values differ from the actual OR times by ≥15%, or by various intervals from ≥5 to ≥60 minutes. We show that these metrics are invalid assessments of OR performance. Specifically, from 19 relevant articles, multiple OR management decisions that would increase OR efficiency or productivity would also increase the absolute percentage error of the estimated case durations. Instead, OR managers should check the mean bias of estimated OR times (ie, systematic underestimation or overestimation), a valid and reliable metric.

Adverse events related to robotic-assisted knee arthroplasty: a cross-sectional study from the MAUDE database

BACKGROUND

Robotic-assisted surgical technique has been clinically available for decades, yet real-world adverse events (AEs) and complications associated with primary knee arthroplasty remain unclear.

METHODS

In March 2023, we searched the FDA website and extracted AEs related to robotic assisted knee arthroplasty (RAKA) from the MAUDE database over the past 10 years. The "Brand Name" function queried major robotic platforms, including active and semi-active systems. The overall incidence of AEs was estimated based on annual surgical volume from the current American Joint Replacement Registry (AJRR). Two authors independently collected data on event date, event type, device problem, and patient problem.

RESULTS

Of 839 eligible reports, device malfunction comprised mechanical failure (343/839, 40.88%) and software failure (261/839, 31.11%). For surgical complications, inappropriate bone resection (115/839, 13.71%) was most frequent, followed by bone/soft tissue damage (83/839, 9.89%). Notably, over-resection exceeding 2 mm (88/839, 10.49%), joint infection (25/839, 2.98%), and aseptic loosening (1/839, 0.12%) were major complications. Only two track pins related AEs were found. Moreover, the distribution of these AEs differed substantially between robot manufacturers. According to the AEs volume and AJRR data, the overall incidences of AEs related to RAKAs were calculated with 0.83% (839/100,892) between November 2010 and March 2023.

CONCLUSION

Our analysis shows that while reported AEs might be increasing for RAKAs, the overall rate remains relatively low. Reassuringly, device malfunction was the most commonly AEs observed, with a minor impact on postoperative outcomes. Furthermore, our data provide a benchmark for patients, surgeons, and manufacturers to evaluate RAKA performance, though continued improvement in reducing serious AEs incidence is warranted.

Machine learning models to predict surgical case duration compared to current industry standards: scoping review

BACKGROUND

Surgical waiting lists have risen dramatically across the UK as a result of the COVID-19 pandemic. The effective use of operating theatres by optimal scheduling could help mitigate this, but this requires accurate case duration predictions. Current standards for predicting the duration of surgery are inaccurate. Artificial intelligence (AI) offers the potential for greater accuracy in predicting surgical case duration. This study aimed to investigate whether there is evidence to support that AI is more accurate than current industry standards at predicting surgical case duration, with a secondary aim of analysing whether the implementation of the models used produced efficiency savings.

METHOD

PubMed, Embase, and MEDLINE libraries were searched through to July 2023 to identify appropriate articles. PRISMA extension for scoping reviews and the Arksey and O'Malley framework were followed. Study quality was assessed using a modified version of the reporting guidelines for surgical AI papers by Farrow et al. Algorithm performance was reported using evaluation metrics.

RESULTS

The search identified 2593 articles: 14 were suitable for inclusion and 13 reported on the accuracy of AI algorithms against industry standards, with seven demonstrating a statistically significant improvement in prediction accuracy (P < 0.05). The larger studies demonstrated the superiority of neural networks over other machine learning techniques. Efficiency savings were identified in a RCT. Significant methodological limitations were identified across most studies.

CONCLUSION

The studies suggest that machine learning and deep learning models are more accurate at predicting the duration of surgery; however, further research is required to determine the best way to implement this technology.