Vigdorchik, Jonathan M.

Literature surrounding artificial intelligence (AI)-related applications for hip and knee arthroplasty has proliferated. However, meaningful advances that fundamentally transform the practice and delivery of joint arthroplasty are yet to be realized, despite the broad range of applications as we continue to search for meaningful and appropriate use of AI. AI literature in hip and knee arthroplasty between 2018 and 2021 regarding image-based analyses, value-based care, remote patient monitoring, and augmented reality was reviewed. Concerns surrounding meaningful use and appropriate methodological approaches of AI in joint arthroplasty research are summarized. Of the 233 AI-related orthopaedics articles published, 178 (76%) constituted original research, while the rest consisted of editorials or reviews. A total of 52% of original AI-related research concerns hip and knee arthroplasty (n = 92), and a narrative review is described. Three studies were externally validated. Pitfalls surrounding present-day research include conflating vernacular (“AI/machine learning”), repackaging limited registry data, prematurely releasing internally validated prediction models, appraising model architecture instead of inputted data, withholding code, and evaluating studies using antiquated regression-based guidelines. While AI has been applied to a variety of hip and knee arthroplasty applications with limited clinical impact, the future remains promising if the question is meaningful, the methodology is rigorous and transparent, the data are rich, and the model is externally validated. Simple checkpoints for meaningful AI adoption include ensuring applications focus on: administrative support over clinical evaluation and management; necessity of the advanced model; and the novelty of the question being answered. Cite this article: Bone Joint J 2022;104-B(12):1292–1303.

Aims While previously underappreciated, factors related to the spine contribute substantially to the risk of dislocation following total hip arthroplasty (THA). These factors must be taken into consideration during preoperative planning for revision THA due to recurrent instability. We developed a protocol to assess the functional position of the spine, the significance of these findings, and how to address different pathologies at the time of revision THA. Patients and Methods Prospectively collected data on 111 patients undergoing revision THA for recurrent instability from January 2014 to January 2017 at two institutions were included (protocol group) and matched 1:1 to 111 revisions specifically performed for instability not using this protocol (control group). Mean follow-up was 2.8 years. Protocol patients underwent standardized preoperative imaging including supine and standing anteroposterior (AP) pelvis and lateral radiographs. Each case was scored according to the Hip-Spine Classification in Revision THA. Results Survival free of dislocation at two years was 97% in the protocol group (three dislocations, all within three months of surgery) versus 84% in the control group (18 patients). Furthermore, 77% of the inappropriately positioned acetabular components would have been unrecognized by supine AP pelvis imaging alone. Conclusion Using the Hip-Spine Classification System in revision THA, we demonstrated a significant decrease in the risk of recurrent instability compared with a control group. Without the use of this algorithm, 77% of inappropriately positioned acetabular components would have been unrecognized and incorrect treatment may have been instituted. Cite this article: Bone Joint J 2019;101-B:817–823.

Background Peer-to-peer advisory among colleagues in orthopedic surgery is commonplace in academic medical centers. In the private practice setting, however, it becomes more difficult for surgeons to discuss complex cases among peers. Purpose/Questions We sought to study the effect of peer-to-peer mentorship on surgeons’ decision-making and on patient care across academic and private adult joint reconstruction practices via the use of group secured messages. Methods From 2013 to 2016, we established a messaging system that was compliant with the Health Insurance Portability and Accountability Act (HIPAA) among five previous adult hip and knee reconstruction co-fellows in order to discuss complex cases. Data collected from each case included patient demographics (age and sex), history and physical examination, relevant imaging in orthogonal planes, and preliminary diagnosis and treatment plans. Data collected from group responses included nature of additional inquiries, literature citations, operative recommendations, and sample imaging of similar cases previously treated. Results The group consisted of two private practice surgeons and three academic surgeons. Data was collected on 283 cases discussed during the study period. None of the patients had any HIPAA violations. The mean number of reviewers who commented on a case was 2.4, with at least one response in 97% of cases. In 33% of the cases, the peers confirmed the initial treatment plan, and in 67% of the cases, an alternative treatment plan was recommended and executed. The case distribution was 94 primary and 189 revision procedures, including 173 hips, 103 knees, three ankles, two shoulders, and two pelvises. Conclusion In the majority of cases exchanged between young surgeons via a group messaging system, a significant impact on patient care was appreciated. In a technology-driven era, peer-to-peer advisory for difficult cases via a rapid feedback method may allow for substantial improvement in patient care, particularly for surgeons not practicing at a large academic medical center with access to several partners and multiple opinions.