RESUMO
INTRODUCTION: Avascular necrosis of the humeral head (AVN) is characterized by osteonecrosis secondary to disrupted blood flow to the glenohumeral joint. Following collapse of the humeral head, arthroplasty, namely total shoulder arthroplasty (TSA) or humeral head arthroplasty (hemiarthroplasty) is recommended standard of care. The literature is limited to underpowered and small sample sizes in comparing arthroplasty modalities. Therefore, the aims of this study were (1) to compare the 10-year survivorship of TSA and hemiarthroplasty in the treatment of AVN of the humeral head and (2) to identify differences in their revision etiologies. METHODS: Patients who underwent primary TSA and hemiarthroplasty for AVN were identified using the PearlDiver database. TSA patients were matched by age, gender, and Charlson Comorbidity Index (CCI) to the hemiarthroplasty cohort in a 4:1 ratio since TSA patients were generally older, sicker, and more often female. The 10-year cumulative incidence rate of all-cause revision was determined using Kaplan-Meier survival analysis. Multivariable analysis was conducted using Cox Proportional Hazard modeling. Chi-squared analysis was conducted to compare the indications for revisions between matched cohorts including periprosthetic joint infection (PJI), dislocation, mechanical loosening, broken implants, periprosthetic fracture, and stiffness. RESULTS: In total, 4,825 patients undergoing TSA and 1,969 patients undergoing hemiarthroplasty for AVN were included in this study. The unmatched 10-year cumulative incidence of revision for patients who underwent TSA and hemiarthroplasty was 7.0% and 7.7%, respectively. The matched 10-year cumulative incidence of revision for patients who underwent TSA and hemiarthroplasty was 6.7% and 8.0%, respectively. When comparing the unmatched cohorts, TSA patients were at significantly higher risk of 10-year all-cause revision (HR: 1.39; P = 0.017) when compared to hemiarthroplasty patients. After matching, there was no significant difference in risk of 10-year all-cause revision (HR: 1.29; P = 0.148) and no difference in the observed etiologies for revision (P > 0.05 for all). CONCLUSION: After controlling for confounders, only 6.7% of TSA and 8.0% hemiarthroplasties for humeral head AVN were revised within 10-years of index surgery. The demonstrated high and comparable long-term survivorship for both modalities supports the utilization of either for the AVN induced humeral head collapse.
RESUMO
PURPOSE: Lumbar discectomy is among the most common spine procedures in the US, with 300,000 procedures performed each year. Like other surgical procedures, this procedure is not excluded from potential complications. This paper presents a video annotation methodology for microdiscectomy including the development of a surgical workflow. In future work, this methodology could be combined with computer vision and machine learning models to predict potential adverse events. These systems would monitor the intraoperative activities and possibly anticipate the outcomes. METHODS: A necessary step in supervised machine learning methods is video annotation, which involves labeling objects frame-by-frame to make them recognizable for machine learning applications. Microdiscectomy video recordings of spine surgeries were collected from a multi-center research collaborative. These videos were anonymized and stored in a cloud-based platform. Videos were uploaded to an online annotation platform. An annotation framework was developed based on literature review and surgical observations to ensure proper understanding of the instruments, anatomy, and steps. RESULTS: An annotated video of microdiscectomy was produced by a single surgeon. Multiple iterations allowed for the creation of an annotated video complete with labeled surgical tools, anatomy, and phases. In addition, a workflow was developed for the training of novice annotators, which provides information about the annotation software to assist in the production of standardized annotations. CONCLUSIONS: A standardized workflow for managing surgical video data is essential for surgical video annotation and machine learning applications. We developed a standard workflow for annotating surgical videos for microdiscectomy that may facilitate the quantitative analysis of videos using supervised machine learning applications. Future work will demonstrate the clinical relevance and impact of this workflow by developing process modeling and outcome predictors.