Classification of subtask types and skill levels in robot-assisted surgery using EEG, eye-tracking, and machine learning.

BACKGROUND: Objective and standardized evaluation of surgical skills in robot-assisted surgery (RAS) holds critical importance for both surgical education and patient safety. This study introduces machine learning (ML) techniques using features derived from electroencephalogram (EEG) and eye-tracking data to identify surgical subtasks and classify skill levels. METHOD: The efficacy of this approach was assessed using a comprehensive dataset encompassing nine distinct classes, each representing a unique combination of three surgical subtasks executed by surgeons while performing operations on pigs. Four ML models, logistic regression, random forest, gradient boosting, and extreme gradient boosting (XGB) were used for multi-class classification. To develop the models, 20% of data samples were randomly allocated to a test set, with the remaining 80% used for training and validation. Hyperparameters were optimized through grid search, using fivefold stratified cross-validation repeated five times. Model reliability was ensured by performing train-test split over 30 iterations, with average measurements reported. RESULTS: The findings revealed that the proposed approach outperformed existing methods for classifying RAS subtasks and skills; the XGB and random forest models yielded high accuracy rates (88.49% and 88.56%, respectively) that were not significantly different (two-sample t-test; P-value = 0.9). CONCLUSION: These results underscore the potential of ML models to augment the objectivity and precision of RAS subtask and skill evaluation. Future research should consider exploring ways to optimize these models, particularly focusing on the classes identified as challenging in this study. Ultimately, this study marks a significant step towards a more refined, objective, and standardized approach to RAS training and competency assessment.

Prediction of Robotic Anastomosis Competency Evaluation (RACE) metrics during vesico-urethral anastomosis using electroencephalography, eye-tracking, and machine learning.

Residents learn the vesico-urethral anastomosis (VUA), a key step in robot-assisted radical prostatectomy (RARP), early in their training. VUA assessment and training significantly impact patient outcomes and have high educational value. This study aimed to develop objective prediction models for the Robotic Anastomosis Competency Evaluation (RACE) metrics using electroencephalogram (EEG) and eye-tracking data. Data were recorded from 23 participants performing robot-assisted VUA (henceforth 'anastomosis') on plastic models and animal tissue using the da Vinci surgical robot. EEG and eye-tracking features were extracted, and participants' anastomosis subtask performance was assessed by three raters using the RACE tool and operative videos. Random forest regression (RFR) and gradient boosting regression (GBR) models were developed to predict RACE scores using extracted features, while linear mixed models (LMM) identified associations between features and RACE scores. Overall performance scores significantly differed among inexperienced, competent, and experienced skill levels (P value < 0.0001). For plastic anastomoses, R2 values for predicting unseen test scores were: needle positioning (0.79), needle entry (0.74), needle driving and tissue trauma (0.80), suture placement (0.75), and tissue approximation (0.70). For tissue anastomoses, the values were 0.62, 0.76, 0.65, 0.68, and 0.62, respectively. The models could enhance RARP anastomosis training by offering objective performance feedback to trainees.

Surgical skill level classification model development using EEG and eye-gaze data and machine learning algorithms.

The aim of this study was to develop machine learning classification models using electroencephalogram (EEG) and eye-gaze features to predict the level of surgical expertise in robot-assisted surgery (RAS). EEG and eye-gaze data were recorded from 11 participants who performed cystectomy, hysterectomy, and nephrectomy using the da Vinci robot. Skill level was evaluated by an expert RAS surgeon using the modified Global Evaluative Assessment of Robotic Skills (GEARS) tool, and data from three subtasks were extracted to classify skill levels using three classification models-multinomial logistic regression (MLR), random forest (RF), and gradient boosting (GB). The GB algorithm was used with a combination of EEG and eye-gaze data to classify skill levels, and differences between the models were tested using two-sample t tests. The GB model using EEG features showed the best performance for blunt dissection (83% accuracy), retraction (85% accuracy), and burn dissection (81% accuracy). The combination of EEG and eye-gaze features using the GB algorithm improved the accuracy of skill level classification to 88% for blunt dissection, 93% for retraction, and 86% for burn dissection. The implementation of objective skill classification models in clinical settings may enhance the RAS surgical training process by providing objective feedback about performance to surgeons and their teachers.

Developing surgical skill level classification model using visual metrics and a gradient boosting algorithm.

Objective: Assessment of surgical skills is crucial for improving training standards and ensuring the quality of primary care. This study aimed to develop a gradient boosting classification model (GBM) to classify surgical expertise into inexperienced, competent, and experienced levels in robot-assisted surgery (RAS) using visual metrics. Methods: Eye gaze data were recorded from 11 participants performing four subtasks; blunt dissection, retraction, cold dissection, and hot dissection using live pigs and the da Vinci robot. Eye gaze data were used to extract the visual metrics. One expert RAS surgeon evaluated each participant's performance and expertise level using the modified Global Evaluative Assessment of Robotic Skills (GEARS) assessment tool. The extracted visual metrics were used to classify surgical skill levels and to evaluate individual GEARS metrics. Analysis of Variance (ANOVA) was used to test the differences for each feature across skill levels. Results: Classification accuracies for blunt dissection, retraction, cold dissection, and burn dissection were 95%, 96%, 96%, and 96%, respectively. The time to complete only the retraction was significantly different among the 3 skill levels (p-value = 0.04). Performance was significantly different for 3 categories of surgical skill level for all subtasks (p-values<0.01). The extracted visual metrics were strongly associated with GEARS metrics (R2>0.7 for GEARS metrics evaluation models). Conclusions: Machine learning (ML) algorithms trained by visual metrics of RAS surgeons can classify surgical skill levels and evaluate GEARS measures. The time to complete a surgical subtask may not be considered a stand-alone factor for skill level assessment.

Ultrarestrictive Opioid Prescription Protocol for Pain Management After Gynecologic and Abdominal Surgery.

Importance: Opioids are routinely prescribed for postoperative home pain management for most patients in the United States, with limited evidence of the amount needed to be dispensed. Opioid-based treatment often adversely affects recovery. Prescribed opioids increase the risk of chronic opioid use, abuse, and diversion and contribute to the current opioid epidemic. Objective: To evaluate whether after hospital discharge, postsurgical acute pain can be effectively managed with a markedly reduced number of opioid doses. Design, Setting, and Participants: In this case-control cohort study, an ultrarestrictive opioid prescription protocol (UROPP) was designed and implemented from June 26, 2017, through June 30, 2018, at a single tertiary-care comprehensive cancer center. All patients undergoing gynecologic oncology surgery were included. Patients undergoing ambulatory or minimally invasive surgery (laparoscopic or robotic approach) were not prescribed opioids at discharge unless they required more than 5 doses of oral or intravenous opioids while in the hospital. Patients who underwent a laparotomy were provided a 3-day opioid pain medication supply at discharge. Main Outcomes and Measures: Total number of opioid pain medications prescribed in the 60-day perioperative period, requests for opioid prescription refills, and postoperative pain scores and complications were evaluated. Factors associated with increased postoperative pain, preoperative and postoperative pain scores, inpatient status, prior opioid use, and all opioid prescriptions within the 60-day perioperative window were monitored among the case patients and compared with those from consecutive control patients treated at the center in the 12 months before the UROPP was implemented. Results: Patient demographics and procedure characteristics were not statistically different between the 2 cohorts of women (605 cases: mean [SD] age, 56.3 [14.5] years; 626 controls: mean [SD] age, 55.5 [13.9] years). The mean (SD) number of opioid tablets given at discharge after a laparotomy was 43.6 (17.0) before implementation of the UROPP and 12.1 (8.9) after implementation (P < .001). For patients who underwent laparoscopic or robotic surgery, the mean (SD) number of opioid tablets given at discharge was 38.4 (17.4) before implementation of the UROPP and 1.3 (3.7) after implementation (P < .001). After ambulatory surgery, the mean (SD) number of opioid tablets given at discharge was 13.9 (16.6) before implementation of the UROPP and 0.2 (2.1) after implementation (P < .001). The mean (SD) perioperative oral morphine equivalent dose was reduced to 64.3 (207.2) mg from 339.4 (674.4) mg the year prior for all opioid-naive patients (P < .001). The significant reduction in the number of dispensed opioids was not associated with an increase the number of refill requests (104 patients [16.6%] in the pre-UROPP group vs 100 patients [16.5%] in the post-UROPP group; P = .99), the mean (SD) postoperative visit pain scores (1.1 [2.2] for the post-UROPP group vs 1.4 [2.3] for pre-UROPP group; P = .06), or the number of complications (29 cases [4.8%] in the post-UROPP group vs 42 cases [6.7%] in the pre-UROPP group; P = .15). Conclusions and Relevance: Implementation of a UROPP was associated with a significant decrease in the overall amount of opioids prescribed to patients after gynecologic and abdominal surgery at the time of discharge for all patients, and for the entire perioperative time for opioid-naive patients without changes in pain scores, complications, or medication refill requests.

Surgical treatment of intestinal complications of graft versus host disease in the pediatric population: Case series and review of literature.

BACKGROUND/PURPOSE: Intestinal complications of acute graft-versus-host disease (aGVHD) include hemorrhage and perforation in the short-term, and stricture with bowel obstruction in the long-term. As medical management of severe aGVHD has improved, more patients are surviving even advanced stages of intestinal aGVHD. This review summarizes the available pediatric literature on surgical treatment of complications of intestinal GVHD. METHODS: A systematic review was performed using PubMed, Cochrane, Embase, and Scopus databases. Any publication that addressed surgical treatment of acute and chronic intestinal GVHD in the pediatric population was reviewed in detail. Furthermore, we included information on 5 additional patients from the institutions of this review's authors, which had not been previously published. RESULTS: We identified 8 studies, comprising 13 patients. Surgical interventions were undertaken for a variety of intestinal GVHD complications, including small bowel obstruction owing to stricture (n=8), enterocutaneous fistulae (n=2), gastrointestinal hemorrhage/perforation (n=1 each), and esophageal stricture (n=1). Among eight patients with bowel obstruction as an indication, pathology revealed ulceration with fibrosis in all but one; 3 had signs of persistent GVHD. Surgical mortality was reported in 4 patients (31%) at an average of 6weeks postoperatively. The median overall follow-up time was 20months (IQR, 2-21). CONCLUSIONS: Although intestinal aGVHD management is almost exclusively medical, a small subset of patients develops complications of intestinal GVHD that require surgical intervention. With expanding indications for stem cell transplantation as well as improved survival after previously fatal bouts of intestinal aGVHD, it is likely that surgical intervention will become more common in these complicated patients. SYSTEMATIC REVIEW: Level of Evidence: Level IV.