Kinematic metrics and surgeon experience in robotic cholecystectomies: a pilot study on breaking down technical performance.

BACKGROUND: Recent studies have correlated surgical skill measured by video-based assessment with improved clinical outcomes. Certain automated measures of operative performance in robotic surgery can be gathered beyond video review called objective performance indicators (OPIs). We explore the relationship between OPIs, surgeon experience, and postoperative recovery, hypothesizing that more efficient dissection will be associated with experience. METHODS: Fifty-six robotic cholecystectomies between February 2022 and March 2023 were recorded at a large tertiary referral center. Surgeon experience and clinical outcomes data from the EMR were obtained for all 56 cases with 10 completing the QOL survey. Two steps of robotic cholecystectomies were reviewed: dissection of Calot's triangle (DCT) and dissection of the gallbladder from the liver (DGL). Postoperative recovery was measured using the SF-36 well-being survey. Univariate analysis was conducted using Pearson's coefficient. RESULTS: Increased operative experience was associated with more efficient camera and instrument movements. DCT had 7 and DGL had 31 of 41 OPIs that correlated with experience. With respect to DGL, more experienced surgeons had reduced step duration and instrument path length and increased camera and instrument speeds. CONCLUSIONS: Several OPIs correlate with surgical experience and may form the basis of more instructive feedback for trainees and less experienced surgeons in improving intraoperative technique.

Bringing Artificial Intelligence to the operating room: edge computing for real-time surgical phase recognition.

BACKGROUND: Automation of surgical phase recognition is a key effort toward the development of Computer Vision (CV) algorithms, for workflow optimization and video-based assessment. CV is a form of Artificial Intelligence (AI) that allows interpretation of images through a deep learning (DL)-based algorithm. The improvements in Graphic Processing Unit (GPU) computing devices allow researchers to apply these algorithms for recognition of content in videos in real-time. Edge computing, where data is collected, analyzed, and acted upon in close proximity to the collection source, is essential meet the demands of workflow optimization by providing real-time algorithm application. We implemented a real-time phase recognition workflow and demonstrated its performance on 10 Robotic Inguinal Hernia Repairs (RIHR) to obtain phase predictions during the procedure. METHODS: Our phase recognition algorithm was developed with 211 videos of RIHR originally annotated into 14 surgical phases. Using these videos, a DL model with a ResNet-50 backbone was trained and validated to automatically recognize surgical phases. The model was deployed to a GPU, the Nvidia® Jetson Xavier™ NX edge computing device. RESULTS: This model was tested on 10 inguinal hernia repairs from four surgeons in real-time. The model was improved using post-recording processing methods such as phase merging into seven final phases (peritoneal scoring, mesh placement, preperitoneal dissection, reduction of hernia, out of body, peritoneal closure, and transitionary idle) and averaging of frames. Predictions were made once per second with a processing latency of approximately 250 ms. The accuracy of the real-time predictions ranged from 59.8 to 78.2% with an average accuracy of 68.7%. CONCLUSION: A real-time phase prediction of RIHR using a CV deep learning model was successfully implemented. This real-time CV phase segmentation system can be useful for monitoring surgical progress and be integrated into software to provide hospital workflow optimization.

Outcome prediction in bariatric surgery through video-based assessment.

INTRODUCTION: The relationship between intraoperative surgical performance scores and patient outcomes has not been demonstrated at a single-case level. The GEARS score is a Likert-based scale that quantifies robotic surgical proficiency in 5 domains. Given that even highly skilled surgeons can have variability in their skill among their cases, we hypothesized that at a patient level, higher surgical skill as determined by the GEARS score will predict individual patient outcomes. METHODS: Patients undergoing robotic sleeve gastrectomy between July 2018 and January 2021 at a single-health care system were captured in a prospective database. Bivariate Pearson's correlation was used to compare continuous variables, one-way ANOVA for categorical variables compared with a continuous variable, and chi-square for two categorical variables. Significant variables in the univariable screen were included in a multivariable linear regression model. Two-tailed p-value < 0.05 was considered significant. RESULTS: Of 162 patients included, 9 patients (5.5%) experienced a serious morbidity within 30 days. The average excess weight loss (EWL) was 72 ± 12% at 6 months and 74 ± 15% at 12 months. GEARS score was not significantly correlated with EWL at 6 months (p = 0.349), 12 months (p = 0.468), or serious morbidity (p = 0.848) on unadjusted analysis. After adjusting, total GEARS score was not correlated with serious morbidity (p = 0.914); however, GEARS score did predict EWL at 6 (p < 0.001) and 12 months (p < 0.001). All GEARS subcomponent scores, bimanual dexterity, depth perception, efficiency, force sensitivity, and robotic control were predictive of EWL at 6 months (p < 0.001) and 12 months (p < 0.001) on multivariable analysis. CONCLUSION: For patients undergoing sleeve gastrectomy, surgical skill as assessed by the GEARS score was correlated with EWL, suggesting that better performance of a sleeve gastrectomy can result in improved postoperative weight loss.

SAGES video acquisition framework-analysis of available OR recording technologies by the SAGES AI task force.

BACKGROUND: Surgical video recording provides the opportunity to acquire intraoperative data that can subsequently be used for a variety of quality improvement, research, and educational applications. Various recording devices are available for standard operating room camera systems. Some allow for collateral data acquisition including activities of the OR staff, kinematic measurements (motion of surgical instruments), and recording of the endoscopic video streams. Additional analysis through computer vision (CV), which allows software to understand and perform predictive tasks on images, can allow for automatic phase segmentation, instrument tracking, and derivative performance-geared metrics. With this survey, we summarize available surgical video acquisition technologies and associated performance analysis platforms. METHODS: In an effort promoted by the SAGES Artificial Intelligence Task Force, we surveyed the available video recording technology companies. Of thirteen companies approached, nine were interviewed, each over an hour-long video conference. A standard set of 17 questions was administered. Questions spanned from data acquisition capacity, quality, and synchronization of video with other data, availability of analytic tools, privacy, and access. RESULTS: Most platforms (89%) store video in full-HD (1080p) resolution at a frame rate of 30 fps. Most (67%) of available platforms store data in a Cloud-based databank as opposed to institutional hard drives. CV powered analysis is featured in some platforms: phase segmentation in 44% platforms, out of body blurring or tool tracking in 33%, and suture time in 11%. Kinematic data are provided by 22% and perfusion imaging in one device. CONCLUSION: Video acquisition platforms on the market allow for in depth performance analysis through manual and automated review. Most of these devices will be integrated in upcoming robotic surgical platforms. Platform analytic supplementation, including CV, may allow for more refined performance analysis to surgeons and trainees. Most current AI features are related to phase segmentation, instrument tracking, and video blurring.

Kinematic data profile and clinical outcomes in robotic inguinal hernia repairs: a pilot study.

BACKGROUND: Surgical training requires clinical knowledge and technical skills to operate safely and optimize clinical outcomes. Technical skills are hard to measure. The Intuitive Data Recorder (IDR), (Sunnyvale, CA) allows for the measurement of technical skills using objective performance indicators (OPIs) from kinematic event data. Our goal was to determine whether OPIs improve with surgeon experience and whether they are correlated with clinical outcomes for robotic inguinal hernia repair (RIHR). METHODS: The IDR was used to record RIHRs from six surgeons. Data were obtained from 98 inguinal hernia repairs from February 2022 to February 2023. Patients were called on postoperative days 5-10 and asked to take the Carolina Comfort Scale (CCS) survey to evaluate acute clinical outcomes. A Pearson test was run to determine correlations between OPIs from the IDR with a surgeon's yearly RIHR experience and with CCS scores. Linear regression was then run for correlated OPIs. RESULTS: Multiple OPIs were correlated with surgeon experience. Specifically, for the task of peritoneal flap exploration, we found that 23 OPIs were significantly correlated with surgeons' 1-year RIHR case number. Total angular motion distance of the left arm instrument had a correlation of - 0.238 (95% CI - 0.417, - 0.042) for RIHR yearly case number. Total angular motion distance of right arm instrument was also negatively correlated with RIHR in 1 year with a correlation of - 0.242 (95% CI - 0.420, - 0.046). For clinical outcomes, wrist articulation of the surgeon's console positively correlated with acute sensation scores from the CCS with a correlation of 0.453 (95% CI 0.013, 0.746). CONCLUSIONS: This study defines multiple OPIs that correlate with surgeon experience and with outcomes. Using this knowledge, surgical simulation platforms can be designed to teach patterns to surgical trainees that are associated with increased surgical experience and with improved postoperative outcomes.

Objective assessment of robotic surgical skills: review of literature and future directions.

BACKGROUND: Evaluation of robotic surgical skill has become increasingly important as robotic approaches to common surgeries become more widely utilized. However, evaluation of these currently lacks standardization. In this paper, we aimed to review the literature on robotic surgical skill evaluation. METHODS: A review of literature on robotic surgical skill evaluation was performed and representative literature presented over the past ten years. RESULTS: The study of reliability and validity in robotic surgical evaluation shows two main assessment categories: manual and automatic. Manual assessments have been shown to be valid but typically are time consuming and costly. Automatic evaluation and simulation are similarly valid and simpler to implement. Initial reports on evaluation of skill using artificial intelligence platforms show validity. Few data on evaluation methods of surgical skill connect directly to patient outcomes. CONCLUSION: As evaluation in surgery begins to incorporate robotic skills, a simultaneous shift from manual to automatic evaluation may occur given the ease of implementation of these technologies. Robotic platforms offer the unique benefit of providing more objective data streams including kinematic data which allows for precise instrument tracking in the operative field. Such data streams will likely incrementally be implemented in performance evaluations. Similarly, with advances in artificial intelligence, machine evaluation of human technical skill will likely form the next wave of surgical evaluation.

Blinded intraoperative skill evaluations avoid gender-based bias.

INTRODUCTION: Gender bias has been identified consistently in written performance evaluations. Qualitative tools may provide a standardized way to evaluate surgical skill and minimize gender bias. We hypothesized that there is no difference in operative time or GEARS scores in robotic hysterectomy for men vs women surgeons. METHODS: Patients undergoing robotic hysterectomies performed between June 2019 and March 2020 at 8 hospitals within the same hospital system were captured into a prospective database. GEARS scores were assigned by crowd-sourced evaluators by a third party blinded to any surgeon- or patient-identifying information. One-way ANOVA was used to compare the mean operative time and GEARS scores for each group, and significant variables were included in a one-way ANCOVA to control for confounders. Two-tailed p-value < 0.05 was considered significant. RESULTS: Seventeen women and 13 men performed a total of 188 hysterectomies; women performed 34 (18%) and men performed 153 (81%). Women surgeons had a higher mean operative time (133 ± 58 vs 86.3 ± 46 min, p = 0.024); after adjustment, there were no significant differences in operative time (p = 0.607). There was no significant difference between the genders in total GEARS score (20.0 ± 0.77 vs 20.2 ± 0.70, p = 0.415) or GEARS subcomponent scores: bimanual dexterity (3.98 ± 0.03 vs 4.00 ± 0.03, p = 0.705); depth perception (4.04 ± 0.04 vs 4.05 ± 0.02, p = 0.799); efficiency (3.79 ± 0.02 vs 3.82 ± 0.02, p = 0.437); force sensitivity (4.01 ± 0.04 vs 4.05 ± 0.05, p = 0.533); or robotic control (4.16 ± 0.03 vs 4.26 ± 0.01, p = 0.079). CONCLUSION: There was no difference in GEARS score between men vs women surgeons performing robotic hysterectomies. Video-based blinded assessment of skills may minimize gender biases when evaluating surgical skill for competency evaluation and credentialing.

Ileostomy reversal after subtotal colectomy in Crohn's disease: a single institutional experience at a high-volume center.

PURPOSE: Our aim was to evaluate factors leading to ostomy reversal among a group of 44 patients with Crohn's disease (CD) who underwent subtotal colectomy (STC) between June 2011 and September 2018. METHODS: Our study design was a retrospective chart review. Patients with CD who underwent STC were included. Logistic regression analysis was used to evaluate several risk factors for non-reversal including medications received prior to surgery and indication for STC. RESULTS: Of 44 STCs performed, 31 (70.5%) were completed laparoscopically and 13 required an open approach (29.5%). Nine patients (20.4%) underwent ostomy reversal, and the mean time to reversal was 8.4 months. Preoperative therapy with an immunomodulator or biologic was associated with ostomy reversal (OR and CI: 0.43, 0.09-0.93; 0.47, 0.10-0.96), as was a diagnosis of intraabdominal abscess (0.43, 0.09-0.93). CONCLUSION: Ileostomy reversal after STC in Crohn's disease is uncommon. Certain treatment regimens and diagnostic factors may impact the likelihood of ostomy reversal. Based on the available data, patients with CD whose disease is severe enough to require STC should be counseled that their ostomy will most likely be permanent. However, due to the low incidence of this procedure for CD, more data is needed.

Description and evaluation of an intraoral cervical plexus anesthetic technique.

Unsuccessful anesthesia of the inferior alveolar nerve (IAN) may be due to supplementary innervations of mandibular molars from other branches, namely the cervical plexus (CP). The purpose of this prospective, randomized, double-blind, controlled trial was to determine the effectiveness of an intraoral cervical plexus anesthetic technique (ICPAT) in mandibular molars with symptomatic irreversible pulpitis (SIR) when the IAN and lingual nerve (LN) blocks failed, and to provide a description of the technique. Forty patients diagnosed with SIR received IAN and LN block anesthesia prior to treatment. After clinical signs of anesthesia, patients were subjected to an electrical pulp test (EPT) at 2-min cycles for 10 min post-injection. The anesthesia was considered unsuccessful if there was a positive EPT response ten minutes following profound lip numbness. The experimental group (n = 20) were administered 2% Lidocaine with 1:100,000 epinephrine using the ICPAT. The control group (n = 20) were administered 0.9% sterile saline using the ICPAT. Success was defined as no response on two consecutive readings from an EPT. In the experimental group, 60% of subjects showed successful anesthesia, whereas none of the subjects in the control group had successful anesthesia. A multiple logistic regression analysis showed that the anesthesia success rate using the ICPAT method was significantly higher (P < 0.05) than in the control group, irrespective of molar tooth type. The ICPAT method may be useful as a supplementary anesthetic technique for mandibular molars with SIR in subjects whom the IAN and LN blocks do not provide adequate anesthesia.

The Surgical Learning Curve: Does Robotic Technical Skill Explain Differences in Operative Performance?

Background: Prior studies on technical skills use small collections of videos for assessment. However, there is likely heterogeneity of performance among surgeons and likely improvement after training. If technical skill explains these differences, then it should vary among practicing surgeons and improve over time. Materials and Methods: Sleeve gastrectomy cases (n = 162) between July 2018 and January 2021 at one health system were included. Global evaluative assessment of robotic skills (GEARS) scores were assigned by crowdsourced evaluators. Videos were manually annotated. Analysis of variance was used to compare continuous variables between surgeons. Tamhane's post hoc test was used to define differences between surgeons with the eta-squared value for effect size. Linear regression was used for temporal changes. A P value <.05 was considered significant. Results: Variations in operative time discriminated between individuals (e.g., between 2 surgeons, means were 91 and 112 minutes, Tamhane's = 0.001). Overall, GEARS scores did not vary significantly (e.g., between those 2 surgeons, means were 20.32 and 20.6, Tamhane's = 0.151). Operative time and total GEARS score did not change over time (R2 = 0.0001-0.096). Subcomponent scores showed idiosyncratic temporal changes, although force sensitivity increased among all (R2 = 0.172-0.243). For a novice surgeon, phase-adjusted operative time (R2 = 0.24), but not overall GEARS scores (R2 = 0.04), improved over time. Conclusions: GEARS scores showed less variability and did not improve with time for a novice surgeon. Improved technical skill does not explain the learning curve of a novice surgeon or variation among surgeons. More work could define valid surrogate metrics for performance analysis.

Surgical Phase Recognition in Inguinal Hernia Repair-AI-Based Confirmatory Baseline and Exploration of Competitive Models.

Video-recorded robotic-assisted surgeries allow the use of automated computer vision and artificial intelligence/deep learning methods for quality assessment and workflow analysis in surgical phase recognition. We considered a dataset of 209 videos of robotic-assisted laparoscopic inguinal hernia repair (RALIHR) collected from 8 surgeons, defined rigorous ground-truth annotation rules, then pre-processed and annotated the videos. We deployed seven deep learning models to establish the baseline accuracy for surgical phase recognition and explored four advanced architectures. For rapid execution of the studies, we initially engaged three dozen MS-level engineering students in a competitive classroom setting, followed by focused research. We unified the data processing pipeline in a confirmatory study, and explored a number of scenarios which differ in how the DL networks were trained and evaluated. For the scenario with 21 validation videos of all surgeons, the Video Swin Transformer model achieved ~0.85 validation accuracy, and the Perceiver IO model achieved ~0.84. Our studies affirm the necessity of close collaborative research between medical experts and engineers for developing automated surgical phase recognition models deployable in clinical settings.

Does Surgeon Experience Correlate with Crowd-Sourced Skill Assessment in Robotic Bariatric Surgery?

BACKGROUND: The Global Evaluative Assessment of Robotic Skills (GEARS) rubric provides a measure of skill in robotic surgery. We hypothesize surgery performed by more experienced operators will be associated with higher GEARS scores. METHOD: Patients undergoing sleeve gastrectomy from 2016 to 2020 were analyzed. Three groups were defined by time in practice: less than 5, between 5 and 15, and more than 15 years. Continuous variables were compared with ANOVA and multivariable regression was performed. RESULTS: Fourteen operators performing 154 cases were included. More experienced surgeons had higher GEARS scores and shorter operative times. On multivariable regression, operative time (P = 0.027), efficiency (P = .022), depth perception (P = 0.033), and bimanual dexterity (P = 0.047) were associated with experience. CONCLUSIONS: In our video-based assessment (VBA) model, operative time and several GEARS subcomponent scores were associated with surgical experience. Further studies should determine the association between these metrics and surgical outcomes.

Is preoperative anemia a significant risk factor for splenectomy patients? A NSQIP analysis.

BACKGROUND: Prior literature has examined the association between preoperative anemia and complications across surgical settings; however, evidence is lacking for splenectomy patients. We investigated the association between preoperative hematocrit and 30-day postoperative outcomes in this population using a national database. METHODS: Patients who underwent splenectomy (2012-2017) were identified from the American College of Surgeons National Surgical Quality Improvement Program database. Analyses were performed for the overall cohort and elective versus emergent subsets, adjusting for transfusion among other covariates. RESULTS: Our sample included 5,580 patients. As hematocrit decreased, complication rates increased incrementally in both the univariate and multivariate analyses. Adjusted odds ratios (and 95% confidence intervals) for moderate anemia (26% ≤ hematocrit < 30%) as compared to no anemia (hematocrit ≥ 38%) were readmission = 1.5 (1.1-1.8), sepsis = 2.2 (1.6-3.0), and composite outcome = 1.8 (1.0-3.2). Parameter estimates (standard error, P value) for the moderate versus no anemia group were length of stay = 3.0 (0.5, P < .001) and days to discharge = 1.2 (0.3; P < .001). CONCLUSION: Our results demonstrate a dose-response relationship between increasing degree of anemia and odds of various postoperative adverse outcomes after adjusting for several potential confounders. The subset analysis further suggests that elective splenectomy cases are more likely to have poor outcomes when in the presence of anemia or when transfusions are performed as compared to emergent cases. This suggests that the harm associated with transfusion may offset the benefit of optimizing anemia in an elective splenectomy case.

Does renal mass biopsy influence multidisciplinary treatment recommendations?

Purpose: To examine how a multidisciplinary team approach incorporating renal mass biopsy (RMB) into decision making changes the management strategy.Methods: A multidisciplinary team comprised of a radiology proceduralist, a pathologist and urologists convened monthly for renal mass conference with a structured presentation of patient demographics, co-mborbidities, tumor pathology, laboratory and radiographic features. Biopsy protocol was standardized to an 18-gauge core needle biopsy using a sheathed apparatus under renal ultrasound guidance. Biopsy diagnostic rate, and concordance with nephrectomy specimens were summarized. Descriptive statistics were used to evaluate influence of RMB on management decisions.Results: A total of 83 patients with a ≤4 cm mass were discussed, and 66% of patients underwent RMB. Of those, 87% were diagnostic with 9% of core biopsies showing benign pathology. Active surveillance (AS) was recommended for 34% of patients with biopsy data as compared to 64% of those without biopsy. Ablation was recommended for 38% of the biopsy cohort compared to 7% without biopsy. Partial nephrectomy rates were similar for both cohorts, approximately 17% and 22%, respectively. Our complication rate was 1.5%, with only 1 Clavien-Dindo Grade 2 complication. Histology was concordant in 93% of patients that ultimately underwent partial nephrectomy after biopsy.Conclusions: Over half of our SRM patients underwent a RMB that provided a diagnosis in 85% of cases. RMB aided in shared decision making by providing insight into the biology of renal masses, which helps to guide multidisciplinary management and consideration of nephron sparing options.

Remote Development of Tumor-to-Tumor Metastasis of Breast Adenocarcinoma in a Renal Oncocytoma.

Tumor-to-tumor metastasis (TTM) is a rare phenomenon where a focus of distinct metastatic disease is discovered with a second primary tumor. Although renal cell carcinoma is the most frequent recipient of metastatic tumor cells, oncocytomas have also previously been described. We present the case of a patient with incidentally detected mammary adenocarcinoma within an oncocytoma 16 years following primary treatment. The mass was treated with partial nephrectomy, with the surgical pathology specimen showing clear delineation of the pleomorphic lobular carcinoma and oncocytoma cells.

Does Robotic Surgical Simulator Performance Correlate With Surgical Skill?

OBJECTIVE: To assess the relationship between robotic surgical simulation performance and the real-life surgical skill of attending surgeons. We hypothesized that simulation performance would not correlate with real-life robotic surgical skill in attending surgeons. DESIGN: In 2013, Birkmeyer et al. demonstrated an association between laparoscopic surgical performance as determined by expert review of video clips and surgical outcomes. Using that model of expert review, we studied the relationship between robotic simulator performance and real-life surgical skill. Ten attending robotic surgeons performed 4 tasks on the da Vinci Skills Simulator (Camera Targeting 1, Ring Walk 3, Suture Sponge 3, and Energy Dissection 3). Two video clips of a robotic-assisted operation were then recorded for each surgeon. Three expert robotic surgeons reviewed the recordings and rated surgical technique using the Global Evaluative Assessment of Robotic Skills. SETTING: University of Virginia; Charlottesville, VA; tertiary hospital PARTICIPANTS: All attending surgeons who perform robotic-assisted surgery at our institution were enrolled and completed the study. RESULTS: The surgeons had a median of 7.25 years of robotic surgical experience with a median of 91 cases (ranging: 20-346 cases) in the last 4 years. Median scores for each simulator task were 87.5%, 39.0%, 77.5%, and 81.5%. Using Pearson's correlation, scores for each of the individual tasks correlated poorly with expert review of intraoperative performance. There was also no correlation (r = -0.0304) between overall simulation score (mean: 70.7 ± 9.6%) and expert video ratings (mean: 3.66 ± 0.32 points). CONCLUSIONS: There was no correlation between attending surgeons' simulator performance and expert ratings of intraoperative videos based on the Global Evaluative Assessment of Robotic Skills scale. Although novice surgeons may put considerable effort into training on robotic simulators, performance on a simulator may not correlate with attending robotic surgical performance. Development of simulation exercises that guide novice surgeons toward expert performance is needed.

Neglected malignant medulloepithelioma of the eye.

Intraocular medulloepithelioma is a rare tumor usually arising from the ciliary body and presenting in childhood. We recently managed a case of an advanced medulloepithelioma in a 45-year-old man that went untreated for several years. The patient had an exenteration after the tumor destroyed the eye and extended into the central nervous system. The initial pathologic diagnosis was complicated by the undifferentiated nature of the tumor which mimicked a lymphoma on fine needle aspiration biopsy (FNAB) as well as on initial permanent sections. The diagnosis was established by immunohistochemical stains indicating a neuroepithelial origin; the relationship of the tumor to the ciliary body and pigmented ciliary epithelium indicated the site of origin.