Untutored training pathway to achieve competence in esophagogastric endoscopic submucosal dissection in a Western center

BACKGROUND AND AIMS

Endoscopic submucosal dissection (ESD) has a long learning curve. The aim of this study was to assess the efficacy of an ESD unsupervised training model for experienced endoscopists.

METHODS

Stepwise training included a visit to a high-volume center, unsupervised training on an ex vivo porcine model, and in vivo human upper GI cases with anatomic progression. Performance measures included en bloc resection, R0 resection, adverse event rates, and operating time.

RESULTS

After observation of 30 esophagogastric ESDs and 15 untutored ex vivo ESDs, 5 human cases of distal gastric ESDs were performed, followed by 55 unselected esophagogastric cases. En bloc and R0 resection rates were 93.0% and 80.7%, respectively. Operating time was 14.0 min/cm2 in the stomach and 25.1 min/cm2 in the esophagus, with evidence of a learning curve for esophageal ESDs (first block 30.26 min/cm2 vs second block 14.81 min/cm2, P = .01).

CONCLUSIONS

Untutored training for esophagogastric ESD is feasible and allows endoscopists, experienced in therapeutic endoscopy, to achieve the required standards toward competency.

Intelligent surgical workflow recognition for endoscopic submucosal dissection with real-time animal study

Recent advancements in artificial intelligence have witnessed human-level performance; however, AI-enabled cognitive assistance for therapeutic procedures has not been fully explored nor pre-clinically validated. Here we propose AI-Endo, an intelligent surgical workflow recognition suit, for endoscopic submucosal dissection (ESD). Our AI-Endo is trained on high-quality ESD cases from an expert endoscopist, covering a decade time expansion and consisting of 201,026 labeled frames. The learned model demonstrates outstanding performance on validation data, including cases from relatively junior endoscopists with various skill levels, procedures conducted with different endoscopy systems and therapeutic skills, and cohorts from international multi-centers. Furthermore, we integrate our AI-Endo with the Olympus endoscopic system and validate the AI-enabled cognitive assistance system with animal studies in live ESD training sessions. Dedicated data analysis from surgical phase recognition results is summarized in an automatically generated report for skill assessment.

Current status and trend in training for endoscopic submucosal dissection: A nationwide survey in Korea

BACKGROUND

Although endoscopic submucosal dissection (ESD) is widely used, the current status and trend in its training have yet to be fully evaluated. We aimed to investigate how ESD endoscopists have been trained in actual clinical practice.

METHODS

Endoscopists aged <45 years who have completed a gastroenterology fellowship or were currently in a fellowship for ≥2 years were included. We conducted a nationwide survey on the ESD training experiences of these endoscopists.

RESULTS

Among 79 young Korean endoscopists invited to participate in the survey, 68 (86.1%) trained in 24 major hospitals responded to the questionnaire. Twenty, 25, and 23 participants belonged to the second-year fellow, <5 years after training, and ≥5 years after training groups, respectively. Sixty-nine percent of the participants observed ≥50 ESD cases before starting ESD under supervision by an expert endoscopist. Additionally, 22% experienced ≥20 supervised ESDs during the training period. The proportion of the participants who underwent a hands-on course differed among the groups (≥5 years after training, 13.0%; <5 years after training, 40.0%; and second-year fellow, 50.0%; P = 0.027). ESD under supervision, observation, and hands-on course were the preferred methods for learning ESD (91.1%, 80.9%, and 35.3%, respectively). Overall, 42.6% of the participants were satisfied with their training program. More experience in supervised ESD (≥20 cases) was associated with an increased satisfaction (odds ratio, 6.65; 95% confidence interval, 1.62-36.31).

CONCLUSIONS

Observation and performance of ESD under the supervision of an expert endoscopist are the primary methods for learning ESD. Hands-on course program has been used more frequently in recent years.

A task and performance analysis of endoscopic submucosal dissection (ESD) surgery

BACKGROUND

ESD is an endoscopic technique for en bloc resection of gastrointestinal lesions. ESD is a widely-used in Japan and throughout Asia, but not as prevalent in Europe or the US. The procedure is technically challenging and has higher adverse events (bleeding, perforation) compared to endoscopic mucosal resection. Inadequate training platforms and lack of established training curricula have restricted its wide acceptance in the US. Thus, we aim to develop a Virtual Endoluminal Surgery Simulator (VESS) for objective ESD training and assessment. In this work, we performed task and performance analysis of ESD surgeries.

METHODS

We performed a detailed colorectal ESD task analysis and identified the critical ESD steps for lesion identification, marking, injection, circumferential cutting, dissection, intraprocedural complication management, and post-procedure examination. We constructed a hierarchical task tree that elaborates the order of tasks in these steps. Furthermore, we developed quantitative ESD performance metrics. We measured task times and scores of 16 ESD surgeries performed by four different endoscopic surgeons.

RESULTS

The average time of the marking, injection, and circumferential cutting phases are 203.4 (σ: 205.46), 83.5 (σ: 49.92), 908.4 s. (σ: 584.53), respectively. Cutting the submucosal layer takes most of the time of overall ESD procedure time with an average of 1394.7 s (σ: 908.43). We also performed correlation analysis (Pearson's test) among the performance scores of the tasks. There is a moderate positive correlation (R = 0.528, p = 0.0355) between marking scores and total scores, a strong positive correlation (R = 0.7879, p = 0.0003) between circumferential cutting and submucosal dissection and total scores. Similarly, we noted a strong positive correlation (R = 0.7095, p = 0.0021) between circumferential cutting and submucosal dissection and marking scores.

CONCLUSIONS

We elaborated ESD tasks and developed quantitative performance metrics used in analysis of actual surgery performance. These ESD metrics will be used in future validation studies of our VESS simulator.

Learning colorectal endoscopic submucosal dissection: a prospective learning curve study using a novel ex vivo simulator

BACKGROUND

Endoscopic submucosal dissection (ESD) is increasingly being used in Asia as a minimally invasive therapy to eradicate large laterally spreading superficial tumors in the colon. To date, the learning curve and effectiveness of ex vivo simulators in colonic ESD training remain unclear. The aim of the study is to determine the learning curve of colonic ESD in an ex vivo simulator.

METHODS

We conducted a prospective study of colon ESD in ex vivo porcine colons in a prototype simulator. Three endoscopists with prior experience in gastric ESD but with no experience in colonic ESD each performed 30 ESD resections on standardized lesions in the rectosigmoid and left colon of the porcine simulator. Procedure time, en bloc resection status, and perforation were recorded.

RESULTS

All 90 lesions were resected using the ESD technique. The mean time of procedure was 49.6 min (standard deviation 29.6 min). The aggregate rate of perforation was 14.4% and the aggregate rate of non-en bloc resection was 5.6%. Using a composite quality score integrating complications and procedural time, it was found that there was a significant difference between two local polynomial regression lines when using a cut-point at the 9th procedure (p = 0.04), reflecting the point at which most of the learning curve is traversed.

CONCLUSIONS

In this study, there were significant improvements realized in colonic ESD performance after 9 colon ESD procedures in ex vivo specimens. Although training will depend on endoscopist skill and expertise, we suggest at least 9 ex vivo procedures prior to moving to live animal or proctored training in colonic ESD.