With the rapidly increasing use of robotic-assisted surgery in gynecology, there is a clear need for a structured robotic hysterectomy curriculum. To develop an effective training program, valid performance metrics that reliably assess skill level is required. As part of robotic curriculum development with IMRA using Kern's framework, this systematic review aims to identify proposed metrics of competence and assess their validity within the context of robotic hysterectomy training. A systematic literature search of OVID MEDLINE and EMBASE was conducted following the PRISMA guidelines, with keywords related to 'hysterectomy', 'robot-assisted', and 'metric'. The study aims, methods, outcomes, description of metrics, measurements of metrics, and metrics validity were extracted and analyzed. The initial search yielded 531 articles, of which 3 were included. Three additional articles were identified through citation and website searching, resulting in a total of six articles being included in this review. Development and identification of both simulator and intraoperative metrics greatly varied between the studies. Several studies utilized an expert consensus-based methodology, such as a modified Delphi methodology, to develop performance metrics. All metrics were assessed for content, construct, and predictive validity. Two studies were able to demonstrate predictive validity; however, there was limited correlation between virtual reality simulator metrics and intraoperative scores. This review highlights the lack of standardized and validated metrics specific to robotic hysterectomy, as well as the inability of established assessment tools to differentiate between robotic surgical skill level. This forms the context for ongoing work at IMRA to develop a granular assessment tool to assess skill acquisition as part of a robotic hysterectomy curriculum.

Surgical learning is a complex process that involves resident characteristics, instructional methods, and technological tools. As surgical residency programs become more diverse, there is a growing need for adaptable training methods that align with various learning styles and backgrounds. Manual dexterity and self-assessment skills are essential for residents, and recent studies highlight those residents with refined manual skills perform better in surgery. Preoperative warm-up is emerging as a potential strategy to improve immediate surgical performance. The study aimed to analyze whether preoperative warm-up in low-cost surgical simulators (training boxes) is related to an immediate improvement in the intraoperative performance of general surgery residents inexperienced in laparoscopy.

The study used a swine model for surgical simulations in a controlled training environment. 105 first-year general surgery residents were divided into 2 groups: the control group (performed procedures without warm-up) and the intervention group (performed a 10-minute preoperative warm-up using a training box).

The Intervention group demonstrated improved efficiency in cholecystectomy (2.97 ± 0.4 vs 2.41 ± 0.91, p = 0.03), with reductions of 41.5% in cholecystectomy dissection time (4.82 ± 4.94 vs 8.23 ± 5.15 minutes, p = 0.02) and 15.6% in left radical nephrectomy dissection time (13.03 ± 4.49 vs 16.77 ± 3.90 minutes, p = 0.012).

Preoperative warm-up using a training box significantly improved the qualitative and quantitative surgical performance of general surgery residents with no prior laparoscopic experience, particularly by increasing efficiency in cholecystectomy and reducing dissection times in both cholecystectomy and left radical nephrectomy.

Laparoscopic surgery training is gaining increasing importance. To release doctors from the burden of manually annotating videos, we proposed an automatic surgical gesture recognition model based on the Fundamentals of Laparoscopic Surgery (FLS) and the Chinese Laparoscopic Skills Testing and Assessment (CLSTA) tools. Furthermore, statistical analysis was conducted based on a gesture vocabulary that had been designed to examine differences between groups at different levels.

Based on the CLSTA, the training process of peg transfer can be represented by a standard sequence of seven surgical gestures defined in our gesture vocabulary. The dataset used for model training and testing included eighty videos recorded at 30 fps. All videos were rated by senior medical professionals from our medical training center. The dataset was processed using cross-validation to ensure robust model performance. The model applied is 3D ResNet-18, a convolutional neural network (CNN). An LSTM neural network was utilized to refine the output sequence.

The overall accuracy for the recognition model was 83.8% and the F1 score was 84%. The LSTM network improved model performance to 85.84% accuracy and an 85% F1 score. Every operative process starts with Gesture 1 (G1) and ends with G5, with wrong placement is labeled as G6. The average training time is 92 s (SD = 36). Variance was observed between groups for G1, G3, and G6, indicating that trainees may benefit from focusing their efforts on these relevant operations, while assisting doctors also in more effectively analyzing the training outcome.

An automatic surgical gesture recognition model was developed for the peg transfer task. We also defined a gesture vocabulary along with the artificial intelligence model to sequentially describe the training operation. This provides an opportunity for artificial intelligence-enabled objective and automatic evaluation based on CLSTA in the clinic implementation.

Most minimally invasive surgery (MIS) training curricula involve practical training (PT) and cognitive learning (CL) to different extents. It has been proven that acquiring and training specific skills through CL can improve MIS skills. This study aimed to discover the most efficient combination of these two approaches and examine their effects on acquiring MIS skills in novices.

Sixty medical students without MIS experience participated in this randomized controlled study and were divided into three groups. The first group received the same amount of PT (50%) as CL (50%). The second group focused on PT (75%) compared to the CL (25%). The third group focused more on CL (75%), with less PT implemented (25%). Before and after training, participants performed an ex vivo laparoscopic cholecystectomy (LCHE). Objective Structured Assessment of Technical Skills (OSATS) and Global Operative Assessment of Laparoscopic Skills (GOALS) scores were used for MIS skill evaluation.

Group 1 improved all four performance assessments (global GOALS 14.3 vs. 18.0, p < 0.001, LCHE-specific GOALS 5.9 vs. 6.9, p = 0.016, global OSATS 19.4 vs. 26.4, p < 0.001, LCHE-specific OSATS 37.9 vs. 46.5, p = 0.004). Group 2 and Group 3 improved three of four performance scores (Group 2: global GOALS 15.0 vs. 18.4, p < 0.001, LCHE-specific GOALS 7.0 vs. 7.7, p = 0.115, global OSATS 19.6 vs. 25.8, p < 0.001, LCHE-specific OSATS 41.3 vs. 50.7, p = 0.001; Group 3: global GOALS 13.8 vs. 17.9, p < 0.001, LCHE-specific GOALS 5.8 vs. 6.6, p = 0.148, global OSATS 18.9 vs. 25.5, p < 0.001, LCHE-specific OSATS 36.8 vs. 43.5, p = 0.034).

A balanced combination of PT and CL seems to offer the most effective training compared to predominantly PT or CL training. All three training modes improved MIS skills in novices.

Learning basic laparoscopic skills can be efficiently performed ex vivo in a safe environment using simulation devices. However, in many countries, the broad and mandatory implementation of ex vivo laparoscopic simulation training in surgical residency is still lacking. The aim of the study was to evaluate the efficacy of laparoscopic basic skills simulation training on the surgical performance of residents during their first laparoscopic procedures in the operating room.

This was a multicenter, prospective, randomized, two-arm, single-blind trial. The study recruited first-year surgical residents (NOVICE) with no previous personal experience in laparoscopic surgery. After the participants had performed their first laparoscopic cholecystectomy, they were randomized into two groups: the intervention group underwent six weeks of standardized laparoscopic basic skills simulation training (Lübeck Toolbox Curriculum), whereas the control group did not. After six weeks, both groups performed a second cholecystectomy. The videotapes of the first and second cholecystectomies were evaluated blinded based on the Global Operative Assessment of Laparoscopic Skill (GOALS) score. The primary endpoint was the changes in the GOALS scores between the first and second cholecystectomies.

22 surgical residents from 11 surgical clinics in Germany were included, and 4 residents dropped out. The median improvement in the LTB-Curriculum group between CHE I and CHE II was 8.5 GOALS score points in contrast to 2 points in the control group. This difference was statistically significant (95%CI: 1-15 points, P = 0.013).

Ex-vivo training in basic laparoscopic skills significantly improved the surgical performance of residents during their first laparoscopic cholecystectomies in the operating room.

Surgery has evolved from a hands-on discipline where skills were acquired via the "learning by doing" principle to a surgical science with attention to patient safety, health care effectiveness and evidence-based research. A variety of simulation modalities have been developed to meet the need for effective resident training. So far, research regarding surgical training for minimally invasive surgery has been extensive but also heterogenous in grade of evidence.

A literature search was conducted to summarize current knowledge about simulation training and to guide research towards evidence-based curricula with translational effects. This was conducted using a variety of terms in PubMed for English articles up to October 2024. Results are presented in a structured narrative review.

For virtual reality simulators, there is sound evidence for effective training outcomes. The required instruments for the development of minimally invasive surgery curricula combining different simulation modalities to create a clinical benefit are known and published.

Surgeons are the main creators for minimally invasive surgery training curricula and often follow a hands-on oriented approach that leaves out equally important aspects of assessment, evaluation, and feedback. Further high-quality research that includes available evidence in this field promises to improve patient safety in surgical disciplines.

Simulation-based training for flexible optical intubation (FOI) is effective but costly and often unavailable in remote areas. Online, hands-on training using affordable, shippable models could be a feasible alternative.

In this noninferiority randomized controlled trial, 30 participants with fewer than 5 FOI experiences were assigned randomly to either remote or on-site hands-on training groups at a 1:1 ratio. The remote group received online theoretical teaching and supervised training and hands-on practice using a modified "Choose-the-Hole" model and a three-dimensional (3D)-printed airway manikin shipped to them. The on-site group received theoretical teaching and hands-on FOI practice in the Eye & ENT Hospital Training Center. Within 1 week after training, all participants performed the FOIs on anesthetized patients with normal airway anatomy. The performances were video recorded and evaluated. The primary outcome was the global rating scale (GRS) scores of the FOI performance on the patient. Secondary outcomes included the checklist scores of FOI performance, first attempt and total success rate, mean intubation time, self-assessment, and training satisfaction.

From July 2022 to December 2022, 30 participants were randomly assigned to receive either remote training (n = 15) or on-site training (n = 15), of whom 28 participants were included in the analyses (17 females, 11 males, average age of 30.0 years). The baseline characteristics of the participants were comparable between 2 groups. No significant difference was found in GRS scores (14.2 ± 3.95 vs. 12.0 ± 3.60, P = .146, mean difference, 2.14, 95% confidence interval [CI], -0.79 - 5.08) between the remote and on-site groups. Statistically similar mean checklist scores (9.32 ± 0.78 vs. 8.89 ± 1.08, P = .238) and intubation time (123 ± 68 vs. 117 ± 54 seconds, P = .780) were noted, respectively, in the remote and on-site groups. The total success rate was 100% in both groups. No significant difference was found in the remote and on-site groups regarding self-assessment and training satisfaction scores.

Remote FOI hands-on training using shippable models was as effective as on-site training, with similar performance, checklist scores, success rate, and intubation time. This suggests that remote training can serve as a viable, cost-effective alternative to traditional on-site methods.

To evaluate the effect of video-based coaching on technical skill development in surgical education.

Randomized controlled trial with video-based coaching (intervention group) in addition to standard surgical curriculum or the standard surgical curriculum alone (control group).

Laparoscopic vaginal vault closure in the operating room at 3 academic hospitals.

Senior Obstetrics and Gynecology residents (year 3-5) on their chief resident or gynecologic oncology rotation.

All residents were recorded performing laparoscopic closure of the vaginal cuff prior to randomization. Surgical coaching sessions followed the Wisconsin Surgical Coaching Framework over 30 minutes on Zoom with one surgical coach. All residents were recorded subsequently performing the same surgical technical skill. Blinded, expert surgeons performed the video assessment using the OSATS, GOALS, and global rating scale. The mean change in operative time and the mean change in video-assessment score between the 2 video-recorded attempts were compared between groups. Qualitative semi-structured interviews were conducted to understand the residents' perspective on video-based surgical coaching.

Twenty residents participated with 10 in the coaching and 10 in the control group. Mean operative time to complete the suturing task was reduced by 32.8% (SD = 21.3%) in the coached group vs 7.2% (SD = 25.1%) in the control group (p = .025). There was no significant change in surgical assessment scores within the coached or control group. Residents identified the core components of a surgical coaching program to include: (1) the resident: focused skill development, (2) the coach: focused on feedback, (3) and the coaching program: a structured activity. Residents envisioned monthly coaching with the opportunity for deliberate practice, the importance of a positive relationship between the coach and coachee, and the importance of faculty development in surgical coaching.

Video-based surgical coaching is an effective tool to enhance technical skill development in surgical education.

The rapid spread of the robotic surgical system has not been accompanied by an equally rapid creation of standardized training courses for the use of this technology.The purpose of our study was to evaluate skill acquisition in the handling and use of the daVinci Xi by comparing two groups of surgical residents. Surgical residents from the University of Turin were enrolled. The participants were divided into two groups: Group A: residents who had participated in at least 8 robotic surgical procedures, and Group B: residents who had never attended robotic surgery. All were administered two instructional videos on the patient cart and console exercises to be performed. Subsequently, the residents were tested and recorded to be evaluated by a senior surgeon experienced in robotic surgery, according to a previously assessed evaluation score. The time of the procedure was also recorded for each test. Patient cart exercises were completed by all participants. We found statistically significant differences between two groups for the first (p = 0.0000) and third (p = 0.0002) patient cart tests and for every test on the surgeon's console except the endoscope handling exercise. Group A scored higher on the patient cart exercises, and the difference reached statistical significance (p = 0.0001). The placement of a single hand-sewn knot on the silicone suture pad was the only exercise that was not fully completed by all participants and showed no statistical difference. The correlation analysis between surgical experience and final score was significant in Group A. The daVinci Xi robotic platform can be properly operated in its basic functions by young surgeons after a short training program even in the absence of previous exposure to robotic clinical procedure.

Currently, there are no validated training models for cystoscopy with ureteral stent placement.

The objectives of this study were to develop and validate a novel endoscopic simulation model for training in ureteral stent placement.

A low-cost, low-fidelity training model was developed to simulate ureteral stent placement. Recruited participants were divided into 3 groups: novices (postgraduate year 3/4 gynecology residents), advanced learners (urogynecology and reconstructive pelvic surgery fellows), and experts (urology residents, urogynecology faculty, and urology faculty). Construct validity was measured using de-identified video-recorded performances on the model, which were evaluated by 2 expert reviewers using validated scales (Global Operative Assessment of Laparoscopic Skills [GOALS], Global Rating Scale [GRS]) and procedure-specific metrics.

The model was created using a hollow Styrofoam sphere, plastic tubing from a retropubic sling, and a silicone pacifier. Thirty-six surgeons were assessed performing the procedure using the model with cystoscopic equipment. The experts (n = 12) performed significantly better than the advanced learners (n = 17) and novices (n = 7) in total scores (max 75, median [IQR]: 75 [75-75], 61 [56.5-68.5], 45 [43-46], respectively; P < 0.001) and within each individual scale domain. Increasing experience with ureteral stent placement had a significant correlation ( P < 0.001) with better performance on the model. A minimum total passing score of 63 was established. On post simulation assessment, most participants "agreed" or "strongly agreed" that the model closely approximates the feel of ureteral stent placement.

This ureteral stenting simulation model is easy to construct, affordable, and reproducible. The model is valid and reliable for practicing the procedure in preparation for live surgery.

Observer-based scoring systems, or automatic methods, based on features or kinematic data analysis, are used to perform surgical skill assessments. These methods have several limitations, observer-based ones are subjective, and the automatic ones mainly focus on technical skills or use data strongly related to technical skills to assess non-technical skills. In this study, we are exploring the use of heart-rate data, a non-technical-related data, to predict values of an observer-based scoring system thanks to random forest regressors.

Heart-rate data from 35 junior resident orthopedic surgeons were collected during the evaluation of a meniscectomy performed on a bench-top simulator. Each participant has been evaluated by two assessors using the Arthroscopic Surgical Skill Evaluation Tool (ASSET) score. A preprocessing stage on heart-rate data, composed of threshold filtering and a detrending method, was considered before extracting 41 features. Then a random forest regressor has been optimized thanks to a randomized search cross-validation strategy to predict each score component.

The prediction of the partially non-technical-related components presents promising results, with the best result obtained for the safety component with a mean absolute error of 0.24, which represents a mean absolute percentage error of 5.76%. The analysis of feature important allowed us to determine which features are the more related to each ASSET component, and therefore determine the underlying impact of the sympathetic and parasympathetic nervous systems.

In this preliminary work, a random forest regressor train on feature extract from heart-rate data could be used for automatic skill assessment and more especially for the partially non-technical-related components. Combined with more traditional data, such as kinematic data, it could help to perform accurate automatic skill assessment.

Many studies display significant heterogeneity in the reliability of artificial intelligence (AI) assessment of minimally invasive surgical (MIS) skills. Our objective is to investigate whether AI systems utilising standardised objective metrics (SOMs) as the basis of skill assessment can provide a clearer understanding of the current state of such technology.

We systematically searched Medline, Embase, Scopus, CENTRAL and Web of Science from March 2023 to September 2023. Results were compiled as a narrative review.

Twenty-four citations were analysed. Overall accuracy of AI systems in predicting overall SOM score of a procedure ranged from 63 ​% to 100 ​%. The most frequently used SOM by AI algorithms were Objective Structured Assessment of Technical Skills (OSATS) (8/24) and Global Evaluative Assessment of Robotic Skills (GEARS) (8/24).

Stratifying for AI studies which employed SOMs to assess surgical skill did not reduce heterogeneity of reported reliability. Our study identifies key issues within the current literature, which, once addressed, could allow more meaningful comparisons between studies.

Several surgical-skill assessment tools emphasize the importance of efficient tissue-dissection, whose assessment relies on human judgment and is thus subject to bias. Automated assessment may help solve this problem. This study aimed to verify the feasibility of surgical-skill assessment using a deep learning-based recognition model.

This retrospective study used multicenter intraoperative videos of laparoscopic colorectal surgery (sigmoidectomy or high anterior resection) for colorectal cancer obtained from 766 cases across Japan. Three groups with different skill levels were distinguished: high-, intermediate-, and low-skill. We developed a model to recognize tissue dissection by the monopolar device using deep learning-based computer-vision technology. Tissue-dissection time per monopolar device appearance time (efficient-dissection time ratio) was extracted as a quantitative parameter describing efficient dissection. We automatically measured the efficient-dissection time ratio using the recognition model of 8 surgical instruments and tissue-dissection on/off classification model. The efficient-dissection time ratio was compared among groups; the feasibility of distinguishing them was explored using the model. The model-calculated parameters were evaluated to determine whether they could differentiate high-, intermediate-, and low-skill groups.

The tissue-dissection recognition model had an overall accuracy of 0.91. There was a moderate correlation (0.542; 95% confidence interval, 0.288-0.724; P < 0.001) between manually and automatically measured efficient-dissection time ratios. Efficient-dissection time ratios by this model were significantly higher in the high-skill than in intermediate-skill (P = 0.0081) and low-skill (P = 0.0249) groups.

An automated efficient-dissection assessment model using a monopolar device was constructed with a feasible automated skill-assessment method.

An advanced curriculum for training Total Laparoscopic Gastropexy (TLG) was developed using the CVLTS-composed simulator based on an ergonomic model of a canine abdominal cavity. The performance of Veterinary surgeons trained in basic laparoscopic surgical skills during 15 training TLG sessions (experimental group, n = 10) was compared to the TLG performance of veterinary surgeons with intermediate (n = 10) or advanced (n = 6) laparoscopic skills. The transfer of surgical skills to a live model was assessed by performing TLG in fattening pigs under operating room conditions using barbed sutures. Experimental group performance after accomplishing the TLG training curriculum and all groups' performance during TLG in the in vivo model were videotaped and evaluated by external Minimally Invasive Surgery (MIS) experts using the GOALS and TLG-specific ranking (SRS) scales. Also, a quantitative assessment comprising time, smoothness of movements, and angular displacement using a Hand Movement Assessment System (HMAS) was performed. Besides, a postmortem biopsy recovered from the gastropexy site three months after surgery to evaluate gross and microscopic characteristics by histopathology was analyzed.

GOALS and SRS scores (P < 0.05), and time, smoothness of movements, and angular displacement during TLG (P < 0.01) significantly improved in the Experimental group after training. They also compared their performance with expert and intermediate groups (P < 0.05) performances. The learning curve for intracorporeal suture stabilized since the tenth (out of 15) training session. Besides, trainees achieved significant TLG skills' in vivo transfer, with no significant difference from the intermediate and expert group performances. The presence of mature collagen (100% of cases), cartilage and bone metaplasia, and foreign body reaction (25% of cases) were found at histopathology evaluation of the gastropexy site, evidencing normal healing.

The TLG training curriculum supported the acquisition of TLG surgical skills in the training box and their transfer to the in vivo model. The experimental group's TLG performance in vivo did not significantly differ from the intermediate and expert groups. The clinical outcome and histopathological findings evidenced complete gastropexy-site healing.

Proper training is necessary to develop the highly specialized skills required to safely perform laparoscopic sacrocolpopexy. Currently, there is no validated training model for laparoscopic sacrocolpopexy that includes dissection of the presacral space, both vaginal and presacral mesh attachments, and peritoneal closure.

This study aimed to create a procedure specific hierarchical task analysis for laparoscopic sacrocolpopexy and then develop and validate a corresponding laparoscopic sacrocolpopexy pelvic training model for the simulation environment.

This was an observational simulation study that was divided into 5 phases: (1) development of hierarchical task analysis, (2) model construction, (3) participant recruitment and simulation testing, (4) reliability and validity testing, and (5) creation of a standard passing performance measure.

Construct, face, and content validity were established for this model. According to the participating experts, the model was able to replicate the steps of presacral dissection, anterior vaginal and sacral mesh attachment, and peritoneal closure. Thirteen trainees and 5 experts completed the simulation, and all "agreed" or "strongly agreed" that the model seemed useful for improving suturing technique and learning the procedure. Additionally, a passing performance measure was determined through contrasting groups methodology.

We developed a novel, reusable, and validated training model that can be utilized as a training resource for the many critical skills necessary to safely and efficiently perform laparoscopic sacrocolpopexy.

Assessing surgical skills is vital for training surgeons, but creating objective, automated evaluation systems is challenging, especially in robotic surgery. Surgical procedures generally involve dissection and exposure (D/E), and their duration and proportion can be used for skill assessment. This study aimed to develop an AI model to acquire D/E parameters in robot-assisted radical prostatectomy (RARP) and verify if these parameters could distinguish between novice and expert surgeons.

This retrospective study used 209 RARP videos from 18 Japanese institutions. Dissection time was defined as the duration of forceps energy activation, and exposure time as the combined duration of manipulating the third arm and camera. To measure these times, an AI-based interface recognition model was developed to automatically extract instrument status from the da Vinci Surgical System® UI. We compared novices and experts by measuring dissection and exposure times from the model's output.

The overall accuracies of the UI recognition model for recognizing the forceps type, energy activation status, and camera usage status were 0.991, 0.998, and 0.991, respectively. Dissection time was 45.2 vs. 35.1 s (novice vs. expert, p = 0.374), exposure time was 195.7 vs. 89.7 s (novice vs. expert, p < 0.001), and the D/E ratio was 0.174 vs. 0.315 (novice vs. expert, p = 0.003).

We successfully developed a model to automatically acquire dissection and exposure parameters for RARP. Exposure time may serve as an objective parameter to distinguish between novices and experts in RARP, and automated technical evaluation in RARP is feasible.

This study was approved by the Institutional Review Board of the National Cancer Center Hospital East (No.2020 - 329) on January 28, 2021.

Obtaining the critical view of safety (CVS) is considered an important step to reduce bile duct injuries during laparoscopic cholecystectomy (LC). However, existing literature suggests that few surgeons obtain adequate CVS when LC videos are directly evaluated by experts. This discrepancy calls for effective, standardized CVS teaching methods. While self-assessment (SA) remains the principal tool utilized by practicing surgeons for performance improvement, its effectiveness is controversial. The aim of this study was to compare surgeon SAs of repeated LC performance and attainment of the CVS with that of expert raters.

Multi-institutional study of surgeon members from the Society of American Gastrointestinal and Endoscopic Surgeons who volunteered to participate. All surgeons were asked to submit an LC video and complete a SA of the CVS quality using the Strasberg scale (0-6 score with ≥5 score indicating appropriate CVS). The same videos were reviewed by two blinded expert raters, members of the Society of American Gastrointestinal and Endoscopic Surgeons safe cholecystectomy task force, who had received prior rater training. Surgeon self-ratings and expert ratings were compared with a Wilcoxon signed-rank test.

Twenty-five surgeon-participants were recruited, 13 of whom submitted an LC video. Surgeons did not achieve adequate CVS in their first submitted video based on expert ratings. Surgeons in the SA group overestimated their performance across all four scales: Operative Performance Rating System (z = -0.36, P = 0.715), Global Operative Assessment of Laparoscopic Skills (z = -0.37, P = 0.712), Strasberg (z = -1.84, P = 0.066), and Competency Assessment Tool (z = -0.73, P = 0.465). Surgeons in the coaching group overestimated their performance on each scale as well: Operative Performance Rating System (z = -0.67, P = 0.500), Global Operative Assessment of Laparoscopic Skills (z = -1.48, P = 0.138), Strasberg (z = -1.07, P = 0.285), and Competency Assessment Tool (z = -1.21, P = 0.225).

Our study confirms that an adequate CVS is infrequently obtained during LC in a small but national sample of general surgeons. It further adds to the existing body of literature that suggests that SA alone may be inadequate for performance improvement. Effective teaching methods such as expert or artificial intelligence coaching are needed to improve the use of appropriate CVS by surgeons that may help decrease bile duct injury risk.

Introduction and aim Laparoscopic surgery has revolutionized the field of surgery over the past few decades. The learning curve in laparoscopy is known to be slow, flat, and complex. This study aims to conduct a comparative analysis of laparoscopic skills, specifically focusing on suturing, knot tying, and needle handling, between novices and experts. The purpose is to objectively quantify the disparities in skill proficiency, identify specific areas needing improvement in training curricula, and contribute to the development of more effective training methodologies for emerging laparoscopic surgeons. Methods Residents from different specialties and institutions had their laparoscopic training and evaluation sessions recorded during their curriculum and compared with the performance of experienced surgeons from the Hôtel-Dieu de France University Hospital (Beirut, LBN) during live surgeries. This comparative study was based on the universally recognized Global Operative Assessment of Laparoscopic Skills (GOALS) score and an assessment of a detailed set of laparoscopic skills and techniques used during needle handling and knot tying. Results Twenty-one tasks performed by novices and 11 tasks performed by experts were considered. A significant difference was found in the GOALS score between the two groups (experts: 23.4/25; novices: 15.9/25). Moreover, a statistically significant difference was found to be present in favor of the experts in the following skills/techniques: using thread handling and forceps rotation for needle manipulation, laying the needle on a fixed driver arm before grasping it, using needle curvature for knot tying, using upward-facing forceps convexity when tying, using an open thread loop before tying, thread handling capacity, knot tying capacity, and number of needle skills performed per task. Conclusion This study demonstrates that many micro-steps in laparoscopic suturing are more prevalent among expert surgeons than among trainees. Incorporating these micro-steps into training could significantly accelerate learning curves, enabling trainees to refine their skills more efficiently and keep pace with the latest surgical advancements in their specialties.

Rigid surgical instruments limit movement whereas articulated instruments offer better control in small spaces and allow for intuitive and ergonomic movements. However, the effectiveness of the use of articulated instruments in improving colorectal laparoscopic outcomes remains unclear. The aim of this work was to determine whether colorectal laparoscopic surgical proficiency improved when multijoint instruments were used instead of conventional ones.

We enrolled 70 consecutive patients (n = 20 for conventional instruments) aged 19-80 years who underwent elective laparoscopic surgery for colorectal diseases. Unedited surgery videos were validated using the modified Global Operative Assessment of Laparoscopic Skills (mGOALS) scale. Learning curves were analysed using a cumulative sum control chart for mGOALS grades.

The surgery type, length of hospital stay and 30-day postoperative complication rates were comparable between the groups, and the surgeon's mGOALS grades were similar (p = 0.190). However, in the articulated group, the scores were significantly higher for depth perception (p = 0.012) and tissue-handling domains (p = 0.046), while surgical duration was significantly shorter and intraoperative blood loss was significantly lower (p = 0.022), compared with those in the conventional (p = 0.002) group. Learning curve findings indicated that the first 10 and subsequent 40 surgeries in the articulated group were within the inexperienced and experienced phases, respectively. The mGOALS score in the experienced phase improved in the articulated group compared with that in the conventional group (p = 0.036).

The use of articulated instruments in laparoscopic colorectal surgery showed potential benefits. Further studies are needed to confirm these findings.

Intraoperative hemorrhage during laparoscopic hepatectomy (LH) is a risk factor for negative postoperative outcomes. Ensuring appropriate hemostasis enhances the safety of surgical procedures. An automatic bleeding recognition system based on deep learning can lead to safer surgeries; however, deep learning models that are useful for detecting and stopping bleeding in LH have not yet been reported. In this study, we aimed to develop a deep learning model to automatically recognize bleeding regions during liver transection in LH.

In this retrospective feasibility study, bleeding scenes were randomly selected from LH videos, and the videos were divided into frames at 30 frames per second. Bleeding regions within the images were annotated by pixels, and subsequently, all images were assigned to the training, validation, and test datasets to develop the deep learning model. A convolutional neural network algorithm was used to perform semantic segmentation. After training and validation, the model was evaluated using images from the test dataset. Precision, recall, and Dice coefficients served as the evaluation metrics for the model.

In total, 2203 annotated images from 44 LH videos were utilized and divided into 1500, 400, and 303 frames for the training, validation, and test datasets, respectively. The precision, recall, and Dice coefficient values of the model were 0.76, 0.79, and 0.77, respectively.

We developed an automatic bleeding recognition model based on semantic segmentation and verified its performance. The proposed model is potentially useful for intraoperative alerting or evaluating surgical skills in the future.

Assessment of retroperitoneal nodes is an important part of the surgical staging of gynecologic cancers. Although pelvic and paraaortic lymphadenectomy have been widely described by different authors, there is little consensus on the description of the different surgical steps for each procedure. An Intergroup Committee on Onco-Gyn Minimally Invasive Surgery has been established with members of the European Society for Gynecological Endoscopy (ESGE), European Society of Gynaecological Oncology (ESGO) and the Society of European Robotic Gynaecological Surgery (SERGS). The Intergroup Committee has various objectives: writing down a surgical description of the technique, which will be assessed by a group of experts following a formal consensus method and developing a specific Objective Structured Assessment of Technical Skills (OSATS) scale for each procedure.

A hierarchical task analysis was conducted by a working group of eight experts from the three societies in order to identify the surgical steps of transperitoneal and extraperitoneal approach in paraaortic lymphadenectomy. The selection of the definitive surgical steps was confirmed by a group of 19 experts from the different societies, following a formal consensus method. Two rounds of Delphi panel rating were considered necessary for achieving an agreement. The consensus agreement identified 29 surgical steps in transperitoneal and 17 surgical steps in extraperitoneal approach to complete a paraaortic lymphadenectomy. Once the description of the procedure and the consensus were established, an Objective specific Scale for the Assessment of Technical Skills for Paraaortic lymphadenectomy (PA-OSATS) in the transperitoneal and extraperitoneal approach was developed.

In the first round of rating we found that 28 steps out of 29 in the transperitoneal approach and 13 out of 17 in the extraperitoneal approach did not reach a strong degree of agreement. They were reformulated based on comments made by the experts, and submitted to a second round of rating and this finally achieved an agreement.

We defined a list of surgical steps in transperitoneal and extraperitoneal approach in paraaortic lymphadenectomy and a specific PA-OSATS scale for these procedures. This tool will be useful for teaching, assessing and standardizing this surgical procedure.

There is an increasing demand for automated surgical skill assessment to solve issues such as subjectivity and bias that accompany manual assessments. This study aimed to verify the feasibility of assessing surgical skills using a surgical phase recognition model.

A deep learning-based model that recognizes five surgical phases of laparoscopic sigmoidectomy was constructed, and its ability to distinguish between three skill-level groups-the expert group, with a high Endoscopic Surgical Skill Qualification System (ESSQS) score (26 videos); the intermediate group, with a low ESSQS score (32 videos); and the novice group, with an experience of < 5 colorectal surgeries (27 videos)-was assessed. Furthermore, 1 272 videos were divided into three groups according to the ESSQS score: ESSQS-high, ESSQS-middle, and ESSQS-low groups, and whether they could be distinguished by the score calculated by multiple regression analysis of the parameters from the model was also evaluated.

The time for mobilization of the colon, time for dissection of the mesorectum plus transection of the rectum plus anastomosis, and phase transition counts were significantly shorter or less in the expert group than in the intermediate (p = 0.0094, 0.0028, and < 0.001, respectively) and novice groups (all p < 0.001). Mesorectal excision time was significantly shorter in the expert group than in the novice group (p = 0.0037). The group with higher ESSQS scores also had higher AI scores.

This model has the potential to be applied to automated skill assessments.

To develop a laparoscopic training course that combines a smartphone application (APP) and virtual reality (VR), and initially evaluate the feasibility and effectiveness of its implementation.

The Exploring Laparoscopy (Ex-Lap) app was developed to meet training demands. The course was designed by integrating the app with a VR simulator (LapSim®) and animal organ perfusion simulators. From January 2021 to December 2023, 91 participants were enrolled in the study and then divided into 5 separate batches to undergo the first stage of the course. The performance of the participants was evaluated by rating scale, the overall Training and Assessment of Basic Laparoscopic Techniques (TABLT) scores, and pass rates. Statistical analyses were conducted using SPSS 26.0, employing Kruskal-Wallis tests, Chi-squared analysis, and Fisher's exact test, depending on the data type.

The Staged Training and Assessment of Laparoscopic Skills (STALS) course was developed, consisting of three stages. The overall pass rates for the first stage across the five batches ranged from 85 to 100%, with no significant difference (P = 0.387). No significant differences were found in the scale scores or TABLT scores for the training tasks among students from different batches (all P > 0.05).

The STALS course is applicable in residency training, demonstrating satisfactory teaching effectiveness and replicability.

Laparoscopic surgery is associated with a prolonged learning curve for emerging surgeons, and simulation-based training (SBT) has become increasingly prominent in this context due to stringent working time regulations and heightened concerns regarding patient safety. While SBT offers a safe and ethical learning environment, the accuracy of simulators in the context of evaluating surgical skills remains uncertain. This study aims to assess the precision of a laparoscopic simulator with regard to evaluating surgical performance and to identify the instructor's role in SBT.

This retrospective study focused on surgical residents in their 1st through 5th years at the Department of Surgery of Linkou Chang Gung Memorial Hospital. The residents participated in a specially designed SBT program using the LapSim laparoscopic simulator. Following the training session, each resident was required to perform a laparoscopic procedure and received individualized feedback from an instructor. Both simulator and instructor evaluated trainees' performance on the LapSim, focusing on identifying correlations between the simulator's metrics and traditional assessments.

Senior residents (n = 15), who employed more complex laparoscopic procedures, exhibited more significant improvements after receiving instructor feedback than did junior residents (n = 17). Notably, a stronger correlation between the simulator and instructor assessments was observed in the junior group (junior Global Operative Assessment of Laparoscopic Skills (GOALS) adjusted R2 = 0.285, p = 0.016), while no such correlations were observed among the senior group.

A well-designed, step-by-step SBT can be a valuable tool in laparoscopic surgical training. LapSim simulator has demonstrated its potential in assessing surgical performances during the early stages of surgical training. However, instructors must provide intuitive feedback to ensure appropriate learning in later stages.

This study aimed to design a low-cost, simulation training platform for the ligation of deep dorsal vein (DVC) complex in radical prostatectomy and validate its training effectiveness.

A simplified prostate urethra model was produced by 0-degree silica gel and pulse pressure banding. This model was placed on a slope of about 30 degrees using cardboard to thus creating a narrow environment of the pelvis. The DVC ligation was performed by a 2D laparoscopy simulator. A total of 27 participants completed the study include 13 novices, 10 surgical residents and 4 urology experts. The novices were trained five trails with 24 hours interval, the residents and experts completed the DVC ligation once. The construct validity of this simulation training platform was performed by completing time, the GOALS (Global Operative Assessment of Laparoscopic Skills) and TSA (i.e. Task Specific Assessments) score. The face validity and content validity were performed by a specific closed-ended questionnaire.

There was no significant difference among three groups in demographic or psychometric variables (p > 0.05). Compared to the novices, the residents spend a shorter time to complete the DVC ligation (p < 0.05) and had higher GOALS scores (p < 0.05), but had no significant difference in TSA scores (p > 0.05). Additionally, the experts groups had a better performance compared to residents group in the completing time (p < 0.05), GOALS score (p < 0.05) and TSA score (p < 0.05). The learning curve of novices significantly promoted along with the increased times of training. Almost 90 percent of subjects considered that this simulator had a good performance in the realism and practicability.

We developed a novel low-cost a simulation training platform for the ligation of deep dorsal vein complex in radical prostatectomy, and this simulator had a good performance in the construct validity, face validity and content validity.

Our aim was to develop practical training for laparoscopic surgery using Thielembalmed cadavers. Furthermore, in order to verbalize experts' motion characteristics and provide objective feedback to trainees, we initiated motion capture analyses of multiple surgical instruments simultaneously during the cadaveric trainings. In the present study, we report our preliminary results.

Participants voluntarily joined the present cadaveric simulation trainings, and performed laparoscopic radical nephrectomy. After the trainings, scores for tissue similarity (face validity) and impression of educational merit (content validity) were collected from participants based on a 5-point Likert scale (tissue similarity: 5: very similar, 3: average, 1: very different; educational merit: 5: very high, 3: average, 1: very low). In addition, after the additional IRB approval, we started motion capture (Mocap) analyses of 6 surgical instruments (scissors, vessel sealing system, grasping forceps, clip applier, right-angled forceps, and suction), using an infrared trinocular camera (120-Hz location record). Mocap-metrics were compared according to the previous surgical experiences (experts: ≧50 laparoscopic surgeries, intermediates: 10-49, novices: 0-9), using the Kruskal-Wallis test.

A total of 9 experts, 19 intermediates, and 15 novices participated in the present study. In terms of face validity, the mean scores were higher than 3, other than for the Vena cava(mean score of 2.89). Participants agreed with the training value (usefulness for future skill improvement: mean score of 4.57). In terms of Mocap analysis, faster speed-related metrics (e.g., velocity, the distribution of tip velocity, acceleration, and jerk) in the scissors and vessel sealing system, a shorter path length of grasping forceps, and fewer dimensionless squared jerks, which indicated more purposeful motion of 4 surgical instruments (vessel sealing system, grasping forceps, clip applier and suction), were observed in the more experienced group.

The Thiel-embalmed cadaver provides an excellent training opportunity for complex laparoscopic procedures with participants' high level of satisfaction, and may become a promising tool for a better objective understanding of surgical dexterity. In order to enrich formative feedback to trainees, we are now proceeding with Mocap analysis.

To determine the ability of surgical trainees and faculty to correctly interpret entrustability of a resident learner in a modeled patient care scenario.

Prospective study utilizing a web-based survey including 4 previously-recorded short videos of resident learners targeted to specific levels of the American Board of Surgery's (ABS) Entrustment Scale. Respondents were asked to choose the entrustment level that best corresponded to their observations of the learner in the video. Responses were subcategorized by low and high entrustment.

Online, utilizing the Qualtrics survey platform.

Survey targeting US surgical trainees and surgical faculty via email and social media. We received 31 complete responses and 2 responses which completed > 1 video assessment question without demographic information (n = 33). Respondents included 10 trainees (32%) and 21 attending surgeons (68%).

Neither faculty nor trainees readily identified the targeted entrustment level for Question 1 (preoperative care of a patient with acute appendicitis with high entrustment, 36% correct), though evaluations of the remaining questions (2 through 4) demonstrated more accuracy (70, 84, and 75% correct, respectively). Faculty were more readily able than trainees to identify low entrustment (level Limited Participation) in intraoperative inguinal hernia repair (95% vs 60%, p = 0.03). After subcategorization to high and low entrustment, both residents and faculty were able to accurately identify entrustment 95% overall.

Both trainees and attending surgeons were able to identify high- and low-performing residents on short video demonstrations using the ABS EPA entrustment scale. This provides additional evidence in support of the need for frequent observations of EPAs to account for the variability in raters' perceptions in addition to complexity of clinical scenarios. Frame-of-reference training via a video-based platform may also be beneficial for both residents and faculty as an ongoing EPA implementation strategy.

The purpose of our narrative review is to summarize the utilization of social media (SoMe) platforms for research communication within the field of surgery. We searched the PubMed database for articles in the last decade that discuss the utilization of SoMe in surgery and then categorized the diverse purposes of SoMe. SoMe proved to be a powerful tool for disseminating articles. Employing strategic methods like visual abstracts enhances article citation rates, the impact factor, h-index, and Altmetric score (an emerging alternative metric that comprehensively and instantly quantifies the social impact of scientific papers). SoMe also proved valuable for surgical education, with online videos shared widely for surgical training. However, it is essential to acknowledge the associated risk of inconsistency in quality. Moreover, SoMe facilitates discussion on specific topics through hashtags or closed groups and is instrumental in recruiting surgeons, with over half of general surgery residency programs in the US efficiently leveraging these platforms to attract the attention of potential candidates. Thus, there is a wealth of evidence supporting the effective use of SoMe for surgeons. In the contemporary era where SoMe is widely utilized, surgeons should be well-versed in this evidence.

Bleeding during laparoscopic surgery is stressful and requires immediate efficient management. Skills for complication management are rarely trained. This study aims to investigate the impact of video-assisted coaching on laparoscopic skills acquisition and performance in emergency bleeding situations.

Participants faced simulated emergency scenarios during laparoscopy involving bleeding management in porcine aorta/kidney specimens. Four sequences were conducted over two days, with a structured video-assisted coaching provided between sequences. Performance was assessed using the Global Operative Assessment of Laparoscopic Skills (GOALS) score. The study involved 27 participants attending the advanced colorectal surgery module at the 40th Annual Davos Course in 2023.

54 video sequences were analyzed. Structured video-assisted coaching improved the GOALS sum score by 0.36 (95%CI: 0.21-0.50, P < 0.001) in contrast to simple repetition (0.05 with 95%CI: -0.43 to 0.53, P = 0.826). This association was observed for depth of perception (P < 0.001), bimanual dexterity (P < 0.001), tissue handling (P < 0.001), overall performance (P < 0.001), and efficiency (P < 0.001). Autonomy did not significantly improve (P = 0.55). Findings were consistent regardless of age, gender, and overall laparoscopic experience of the participants. However, a weaker effect of structured video-assisted coaching was observed in participants with experience in laparoscopic surgery.

Structured video-assisted coaching improved performance in laparoscopic skills in complex and stress-inducing bleeding scenarios. The findings of this study support the incorporation of video-assisted coaching and complication management exercises into surgical training curricula.

To characterize laparoscopy teaching in Medical Residency Programs in Gynecology and Obstetrics in Brazil, and to evaluate preceptors' characteristics in laparoscopy programs and map laparoscopic training practice scenarios.

This descriptive cross-sectional study evaluated questionnaire responses from coordinators of the Medical Residency Programs in Gynecology and Obstetrics from 2019 to 2021.

The questionnaire was sent to 175 programs, and 90 responses were received (51.4%). From the 85 valid responses, it was noted that 67 programs had laparoscopic training. Of the 64 responses received regarding location, 32 replies (50%) indicated the Southeast of Brazil, particularly some country's capitals. In 37.3% (n=25) of the cases, the program coordinator performed laparoscopy. The chief of the laparoscopy sector has advanced experience in most 52.5% (n=10) medical residency services; the preceptors also had advanced experience in 89.4% (n=59) of the services. Residents received laboratory training in 39.4% (n=26) of the services. In most cases, training was performed using a physical simulator. Of the 26 medical residency services with laparoscopy training outside the operating room, 80.8% (n=21) performed them as part of the curriculum, 61.5% (n=16) had a schedule for the same, and only 3.9% (n=1) were objectively evaluated.

Laparoscopy teaching in Brazil is heterogeneous, with only a few programs offering any training in laparoscopy. The preceptors had advanced experience and participated in laboratory and operating room training. Only a few programs have their own laboratories or training centers, and most teaching programs do not plan to set up training centers.

Tissue handling is one of the pivotal parts of surgical procedures. We aimed to elucidate the characteristics of experts' left-hand during laparoscopic tissue dissection.

Participants performed tissue dissection around the porcine aorta. The grasping force/point of the grasping forceps were measured using custom-made sensor forceps, and the forceps location was also recorded by motion capture system (Mocap). According to the global operative assessment of laparoscopic skills (GOALS), two experts scored the recorded movies, and based on the mean scores, participants were divided into three groups: novice (<10), intermediate (10≤ to <20), and expert (≤20). Force-based metrics were compared among the three groups using the Kruskal-Wallis test. Principal component analysis (PCA) using significant metrics was also performed.

A total of 42 trainings were successfully recorded. The statistical test revealed that novices frequently regrasped a tissue (median total number of grasps, novices: 268.0 times, intermediates: 89.5, experts: 52.0, p < 0.0001), the traction angle became stable against the aorta (median weighted standard deviation of traction angle, novices: 30.74°, intermediates: 26.80, experts: 23.75, p = 0.0285), and the grasping point moved away from the aorta according to skill competency [median percentage of grasping force applied in close zone (0 to 2.0 cm from aorta), novices: 34.96 %, intermediates: 21.61 %, experts: 10.91 %, p = 0.0032]. PCA showed that the efficiency-related (total number of grasps) and effective tissue traction-related (weighted average grasping position in Y-axis and distribution of grasping area) metrics mainly contributed to the skill difference (proportion of variance of first principal component: 60.83 %).

The present results revealed experts' left-hand characteristics, including correct tissue grasping, sufficient tissue traction from the aorta, and stable traction angle. Our next challenge is the provision of immediate and visual feedback onsite after the present wet-lab training, and shortening the learning curve of trainees.

To evaluate the effect of video-based coaching on the gynecology resident performance of laparoscopic salpingectomy.

PGY-1 and PGY-2 residents were randomized before their gynecology rotations to standard gynecology curriculum (control group) or standard curriculum plus two video-coaching sessions by a fellowship-trained minimally invasive gynecologic surgeon (VBC group). Residents were video recorded intraoperatively performing three unilateral laparoscopic salpingectomies. Participants in the VBC group were coached between the procedures. The primary outcome was the improvement in modified GOALS (Global Operative Assessment of Laparoscopic Skills) and OSA-LS (Objective Structured Assessment of Laparoscopic Salpingectomy) scores, compared with baseline, in the VBC and control groups, with videos independently graded by three blinded minimally invasive gynecologic surgeons. A minimum sample size of 18 participants (nine per group) was needed to achieve 90% power to detect a difference of 5.0 points.

From October 2021 to December 2022, 28 PGY-1 and PGY-2 residents completed the study with 14 participants per group. Baseline characteristics were similar between groups. In the VBC group, modified GOALS scores significantly improved by 3.0 points from video 1 to video 2 ( P =.04) and by 3.2 points from video 1 to video 3 ( P =.02). Modified OSA-LS scores also increased significantly in the VBC group, by 6.1 points from video 1 to video 3 ( P =.02). In the control group, modified GOALS and OSA-LS scores improved from baseline but were not significant ( P =.2, P =.5). Video-based coaching also enhanced resident comfort and confidence in performing laparoscopic surgery.

Video-based coaching improves resident performance of laparoscopic salpingectomy and can be used as an adjunct to resident surgical training.

ClinicalTrials.gov , NCT05103449.

Introduction: Ensuring patient safety in minimally invasive surgery (MIS) within the field of pediatric surgery requires systematic and extensive practice. Many groups have proposed mastery learning programs encompassing a range of training methods. However, short courses often have a narrow focus on specific objectives, limiting opportunities for sustained training. Our aim was to analyze our results with an online long-term competency-based and supervised training. Methods: This is a retrospective cohort study with prospective data collection of scores and performance of trainees during online courses from October 2020 to April 2023. Results: All participants (n = 76) were able to set up their personal training gym and complete the intensive stage of the course. The total score evolved from 2.60 ± 0.56 at the first meeting to 3.67 ± 0.61 at the fourth meeting, exhibiting a significant difference (P < .013). A considerable drop out was observed in the follow-up stage, with only 53.8% of the participants completing the course. When compared with the first meeting, they also showed a significant improvement with a mean general score of 3.85 ± 0.25 (P < .013) Conclusion: We have presented a novel online training program, based on continuous training that demonstrated that the unlimited access to a personal training gym allows surgeons to improve and maintain MIS skills.

This work presents FASTRL, a benchmark set of instrument manipulation tasks adapted to the domain of reinforcement learning and used in simulated surgical training. This benchmark enables and supports the design and training of human-centric reinforcement learning agents which assist and evaluate human trainees in surgical practice.

Simulation tasks from the Fundamentals of Arthroscopic Surgery Training (FAST) program are adapted to the reinforcement learning setting for the purpose of training virtual agents that are capable of providing assistance and scoring to the surgical trainees. A skill performance assessment protocol is presented based on the trained virtual agents.

The proposed benchmark suite presents an API for training reinforcement learning agents in the context of arthroscopic skill training. The evaluation scheme based on both heuristic and learned reward functions robustly recovers the ground truth ranking on a diverse test set of human trajectories.

The presented benchmark enables the exploration of a novel reinforcement learning-based approach to skill performance assessment and in-procedure assistance for simulated surgical training scenarios. The evaluation protocol based on the learned reward model demonstrates potential for evaluating the performance of surgical trainees in simulation.

The purpose of this study is to assess whether the Dunning-Kruger effect occurs in surgical residents when performing laparoscopic cholecystectomy in a porcine model.

Prospective blinded study, which counted with forty PGY-1 general surgery residents who agreed to participate in the study were blindly recruited to perform a laparoscopic cholecystectomy in a porcine model. At the end of the procedure, the participants assigned a score of 0-10 for their own performance and the video of the operation was independently assessed by 2 experienced laparoscopic surgeons using a validated tool.

Participants were divided into groups of 10 individuals according to objective performance and compared. The group with the worst objective result was inferior to the group with the best objective result (3.77 ± 0.44 vs. 8.1 ± 0.44, p < 0.001), but they were similar in self-perception of performance (5.11 ± 1.69 vs. 6.1 ± 1.79, p = 0.999).

In the studied sample, it was possible to demonstrate the presence of the Dunning-Kruger effect.

The learning curve in minimally invasive surgery (MIS) is lengthened compared to open surgery. It has been reported that structured feedback and training in teams of two trainees improves MIS training and MIS performance. Annotation of surgical images and videos may prove beneficial for surgical training. This study investigated whether structured feedback and video debriefing, including annotation of critical view of safety (CVS), have beneficial learning effects in a predefined, multi-modal MIS training curriculum in teams of two trainees.

This randomized-controlled single-center study included medical students without MIS experience (n = 80). The participants first completed a standardized and structured multi-modal MIS training curriculum. They were then randomly divided into two groups (n = 40 each), and four laparoscopic cholecystectomies (LCs) were performed on ex-vivo porcine livers each. Students in the intervention group received structured feedback after each LC, consisting of LC performance evaluations through tutor-trainee joint video debriefing and CVS video annotation. Performance was evaluated using global and LC-specific Objective Structured Assessments of Technical Skills (OSATS) and Global Operative Assessment of Laparoscopic Skills (GOALS) scores.

The participants in the intervention group had higher global and LC-specific OSATS as well as global and LC-specific GOALS scores than the participants in the control group (25.5 ± 7.3 vs. 23.4 ± 5.1, p = 0.003; 47.6 ± 12.9 vs. 36 ± 12.8, p < 0.001; 17.5 ± 4.4 vs. 16 ± 3.8, p < 0.001; 6.6 ± 2.3 vs. 5.9 ± 2.1, p = 0.005). The intervention group achieved CVS more often than the control group (1. LC: 20 vs. 10 participants, p = 0.037, 2. LC: 24 vs. 8, p = 0.001, 3. LC: 31 vs. 8, p < 0.001, 4. LC: 31 vs. 10, p < 0.001).

Structured feedback and video debriefing with CVS annotation improves CVS achievement and ex-vivo porcine LC training performance based on OSATS and GOALS scores.

Most intraoperative adverse events (iAEs) result from surgeons' errors, and bleeding is the majority of iAEs. Recognizing active bleeding timely is important to ensure safe surgery, and artificial intelligence (AI) has great potential for detecting active bleeding and providing real-time surgical support. This study aimed to develop a real-time AI model to detect active intraoperative bleeding.

We extracted 27 surgical videos from a nationwide multi-institutional surgical video database in Japan and divided them at the patient level into three sets: training (n = 21), validation (n = 3), and testing (n = 3). We subsequently extracted the bleeding scenes and labeled distinctively active bleeding and blood pooling frame by frame. We used pre-trained YOLOv7_6w and developed a model to learn both active bleeding and blood pooling. The Average Precision at an Intersection over Union threshold of 0.5 (AP.50) for active bleeding and frames per second (FPS) were quantified. In addition, we conducted two 5-point Likert scales (5 = Excellent, 4 = Good, 3 = Fair, 2 = Poor, and 1 = Fail) questionnaires about sensitivity (the sensitivity score) and number of overdetection areas (the overdetection score) to investigate the surgeons' assessment.

We annotated 34,117 images of 254 bleeding events. The AP.50 for active bleeding in the developed model was 0.574 and the FPS was 48.5. Twenty surgeons answered two questionnaires, indicating a sensitivity score of 4.92 and an overdetection score of 4.62 for the model.

We developed an AI model to detect active bleeding, achieving real-time processing speed. Our AI model can be used to provide real-time surgical support.

The advent of Artificial Intelligence (AI)-based object detection technology has made identification of position coordinates of surgical instruments from videos possible. This study aimed to find kinematic differences by surgical skill level. An AI algorithm was developed to identify X and Y coordinates of surgical instrument tips accurately from video. Kinematic analysis including fluctuation analysis was performed on 18 laparoscopic distal gastrectomy videos from three expert and three novice surgeons (3 videos/surgeon, 11.6 h, 1,254,010 frames). Analysis showed the expert surgeon cohort moved more efficiently and regularly, with significantly less operation time and total travel distance. Instrument tip movement did not differ in velocity, acceleration, or jerk between skill levels. The evaluation index of fluctuation β was significantly higher in experts. ROC curve cutoff value at 1.4 determined sensitivity and specificity of 77.8% for experts and novices. Despite the small sample, this study suggests AI-based object detection with fluctuation analysis is promising because skill evaluation can be calculated in real time with potential for peri-operational evaluation.