Surgical gestures to evaluate apical dissection of robot-assisted radical prostatectomy.

Previously, our group established a surgical gesture classification system that deconstructs robotic tissue dissection into basic surgical maneuvers. Here, we evaluate gestures by correlating the metric with surgeon experience and technical skill assessment scores in the apical dissection (AD) of robotic-assisted radical prostatectomy (RARP). Additionally, we explore the association between AD performance and early continence recovery following RARP. 78 AD surgical videos from 2016 to 2018 across two international institutions were included. Surgeons were grouped by median robotic caseload (range 80-5,800 cases): less experienced group (< 475 cases) and more experienced (≥ 475 cases). Videos were decoded with gestures and assessed using Dissection Assessment for Robotic Technique (DART). Statistical findings revealed more experienced surgeons (n = 10) used greater proportions of cold cut (p = 0.008) and smaller proportions of peel/push, spread, and two-hand spread (p < 0.05) than less experienced surgeons (n = 10). Correlations between gestures and technical skills assessments ranged from - 0.397 to 0.316 (p < 0.05). Surgeons utilizing more retraction gestures had lower total DART scores (p < 0.01), suggesting less dissection proficiency. Those who used more gestures and spent more time per gesture had lower efficiency scores (p < 0.01). More coagulation and hook gestures were found in cases of patients with continence recovery compared to those with ongoing incontinence (p < 0.04). Gestures performed during AD vary based on surgeon experience level and patient continence recovery duration. Significant correlations were demonstrated between gestures and dissection technical skills. Gestures can serve as a novel method to objectively evaluate dissection performance and anticipate outcomes.

Human visual explanations mitigate bias in AI-based assessment of surgeon skills.

Artificial intelligence (AI) systems can now reliably assess surgeon skills through videos of intraoperative surgical activity. With such systems informing future high-stakes decisions such as whether to credential surgeons and grant them the privilege to operate on patients, it is critical that they treat all surgeons fairly. However, it remains an open question whether surgical AI systems exhibit bias against surgeon sub-cohorts, and, if so, whether such bias can be mitigated. Here, we examine and mitigate the bias exhibited by a family of surgical AI systems-SAIS-deployed on videos of robotic surgeries from three geographically-diverse hospitals (USA and EU). We show that SAIS exhibits an underskilling bias, erroneously downgrading surgical performance, and an overskilling bias, erroneously upgrading surgical performance, at different rates across surgeon sub-cohorts. To mitigate such bias, we leverage a strategy -TWIX-which teaches an AI system to provide a visual explanation for its skill assessment that otherwise would have been provided by human experts. We show that whereas baseline strategies inconsistently mitigate algorithmic bias, TWIX can effectively mitigate the underskilling and overskilling bias while simultaneously improving the performance of these AI systems across hospitals. We discovered that these findings carry over to the training environment where we assess medical students' skills today. Our study is a critical prerequisite to the eventual implementation of AI-augmented global surgeon credentialing programs, ensuring that all surgeons are treated fairly.

CABOSEQ: The Effectiveness of Cabozantinib in Patients With Treatment Refractory Advanced Renal Cell Carcinoma: Results From the International Metastatic Renal Cell Carcinoma Database Consortium (IMDC).

BACKGROUND: There are limited data evaluating the activity of cabozantinib (CABO) as second line (2L) therapy post standard of care ipilimumab-nivolumab (IPI-NIVO) or immuno-oncology(IO)/vascular endothelial growth factor inhibitor (VEGFi) combinations (IOVE). MATERIALS AND METHODS: Using the IMDC database, we sought to identify the objective response rate, time to treatment failure (TTF) and overall survival (OS) of 2L CABO after IPI-NIVO, IOVE combinations, pazopanib or sunitinib (PAZ/SUN) or other first line (1L) therapies. Multivariable Cox regression, adjusted for underlying differences in IMDC groups, was used to compare differences in OS for 2L CABO based on preceding therapy. RESULTS: Three hundred and forty-six patients received 2L CABO (78 post IPI NIVO, 46 post IOVE, 161 post PAZ/SUN, 61 post Other). Of the entire cohort, 12.6%, 62.6%, and 24.8% were IMDC favourable, intermediate, and poor risk, respectively. Patients that received 1L IPI-NIVO had a median OS of 21.4 (95% CI, 12.1 - NE [Not evaluable]) months compared to 15.7 (95% CI, 9.3 - NE) months in 1L IOVE and 20.7 (95% CI, 15.6 - 35.6) months in 1L PAZ/SUN, P = .28. Median TTF from the initiation of 2L CABO in the overall population was 7.6 (95% CI, 6.6 - 9.0) months. We were unable to detect a significant difference in 2L CABO OS based on type of 1L therapy received: 1L IPI-NIVO (reference group) vs. 1L IOVE HR 1.73 (95% CI, 0.83 - 3.62 P = .14), 1L PAZ/SUN 1.16 (95% CI, 0.67 - 2.00 P = .60), however given the retrospective observational nature of this work a lack of sufficient power may contribute to this. CONCLUSION: In a large real world dataset, we identified clinically meaningful activity of 2L CABO after all evaluated contemporary 1L therapies, irrespective of whether the 1L regimen included a VEGFi. These are real world benchmarks with which to counsel our patients.

Surgical gestures as a method to quantify surgical performance and predict patient outcomes.

How well a surgery is performed impacts a patient's outcomes; however, objective quantification of performance remains an unsolved challenge. Deconstructing a procedure into discrete instrument-tissue "gestures" is a emerging way to understand surgery. To establish this paradigm in a procedure where performance is the most important factor for patient outcomes, we identify 34,323 individual gestures performed in 80 nerve-sparing robot-assisted radical prostatectomies from two international medical centers. Gestures are classified into nine distinct dissection gestures (e.g., hot cut) and four supporting gestures (e.g., retraction). Our primary outcome is to identify factors impacting a patient's 1-year erectile function (EF) recovery after radical prostatectomy. We find that less use of hot cut and more use of peel/push are statistically associated with better chance of 1-year EF recovery. Our results also show interactions between surgeon experience and gesture types-similar gesture selection resulted in different EF recovery rates dependent on surgeon experience. To further validate this framework, two teams independently constructe distinct machine learning models using gesture sequences vs. traditional clinical features to predict 1-year EF. In both models, gesture sequences are able to better predict 1-year EF (Team 1: AUC 0.77, 95% CI 0.73-0.81; Team 2: AUC 0.68, 95% CI 0.66-0.70) than traditional clinical features (Team 1: AUC 0.69, 95% CI 0.65-0.73; Team 2: AUC 0.65, 95% CI 0.62-0.68). Our results suggest that gestures provide a granular method to objectively indicate surgical performance and outcomes. Application of this methodology to other surgeries may lead to discoveries on methods to improve surgery.