Training Simulators for Gastrointestinal Endoscopy: Current and Future Perspectives

Development of a laparoscopic sigmoidectomy simulator: Sigmaster

The sigmoid colon simulator was designed to accurately reproduce the anatomical layer structure and the arrangement of characteristic organs in each layer, and to have conductivity so that energy devices can be used. Dry polyester fibers were used to reproduce the layered structures, which included characteristic blood vessels, nerve sheaths, and intestinal tracts. The adhesive strength of the layers was controlled to allow realistic peeling techniques. The features of the Sigmaster are illustrated through a comparison of simulated sigmoidectomy using Sigmaster and actual surgery. We developed a laparoscopic sigmoidectomy simulator called Sigmaster. Sigmaster is a training device that closely reproduces the membrane structures of the human body and allows surgeons to experience the entire laparoscopic sigmoidectomy process.

Validation and efficacy of the Varix Trainer model as a Training device for esophagogastroduodenoscopy

Background and study aims The Varix Trainer model 1 (VTM1) was created for trainees to safely practice basic endoscope manipulation skills. The VTM1 was tested to see if it could distinguish levels of endoscope manipulation skills (construct validity) and whether training with it could improve these skills faster (content validity). Patients and methods We enrolled 23 novice endoscopists, 18 second-year trainees, and 13 expert endoscopists. They were asked to point with the endoscope tip to 20 numbers in the model as quickly as possible using torque, single-hand small/large wheel manipulation (SHSW), and retroflexion techniques. Their mean times (t20) were compared to determine if the model could distinguish different levels of expertise. Subsequently, 14 novices trained for eight short sessions, and the pre-training and post-training t20 were compared. Nine novice endoscopists received no training and were retested after 4 to 6 weeks (controls). Results Experts had faster t20 than second-year trainees, who were faster than novices, for all three techniques ( P < 0.001). After eight sessions, the mean t20 for novices improved from 112 to 66 seconds for torque, 144 to 72 seconds for SHSW, and 108 to 63 seconds for retroflexion, (all P < 0.001). Their t20 were equivalent to second-year trainees. Improvement in t20 was also seen with the control group, but total reduction was less than for the training group. Conclusions The VTM1 distinguished varying levels of expertise for all techniques, suggesting that it is a valid tool for assessing endoscope manipulation skill. A short curriculum improved novices' manipulation skills faster than traditional practice.

Training and quality indicators in interventional endoscopic ultrasound

Endoscopic ultrasound (EUS) has transformed the landscape of minimally invasive gastrointestinal procedures, necessitating specialized training for proficiency in interventional EUS (iEUS). This study evaluates the effectiveness of iEUS training, focusing on learning curves, success rates, and the associated risks in various procedures, aiming to recommend practices for standardizing training and ensuring competency. Key metrics such as procedure type, learning curve for proficiency, success rates, and risk of adverse events were analyzed to establish benchmarks for training programs. Proficiency in pancreatic fluid collection drainage was achieved after 20-30 procedures, with a 100% success rate and a complication rate ranging from 1.5 to 80%. Gallbladder drainage required 19 cases to reach an 86% success rate, with adverse events reported in 19% of cases. Choledocoduodenostomy mastery was observed after approximately 100 cases, with postintervention pancreatitis affecting 5.3-6.6% of all cases. Hepaticogastrostomy showed a 93% success rate after 33 cases, with a 24.8% adverse event rate. Hepaticoenterostomy reached 100% success beyond the 40th patient, with a 20% rate of postsurgical strictures. Pancreatic duct drainage achieved 89% technical and 87% clinical success after 27 cases, with 12-15% adverse events. Gastro-enteric anastomosis required 25 cases for proficiency and approximately 40 cases for mastery, with 5.5% immediate and 1% late adverse events. iEUS training outcomes vary significantly across different procedures, highlighting the importance of structured, procedure-specific training programs to achieve proficiency. These findings provide a foundation for developing universal competency benchmarks in iEUS, facilitating consistent and effective training worldwide.

Systematic review of subjective validation methods for computerized colonoscopy simulators

Introduction: In recent years, different approaches have been used to conduct a subjective assessment of colonoscopy simulators. The purpose of this paper is to review these different approaches, specifically the ones used for computerized simulators, as the first step for the design of a standard validation procedure for this type of simulators. Methods: A systematic review was conducted by searching papers after 2010 in PubMed, Google Scholar, ScienceDirect, and IEEE Xplore databases. Papers were screened and reviewed for procedures regarding the subjective validation of computerized simulators for traditional colonoscopy with an endoscope. Results: An initial search in the databases identified 2094 papers, of which 7 remained after exhaustive review and application of exclusion criteria. All studies used questionnaires for subjective validation, with "face" being the most common validity type tested, while "content" validity and "usability" were less prominent. Conclusions: A classification of subscales for testing face validity was derived from the studies. The Colonoscopy Simulator Realism Questionnaire (CSRQ) was selected as the guide to follow for the development of future questionnaires related to subjective validation. Mislabeling of the validity tested in the studies due to ambiguous interpretations of the validity types was a common occurrence observed in the reviewed studies.

Canine Upper Digestive Tract 3D Model: Assessing Its Utility for Anatomy and Upper Endoscopy Learning

A teaching strategy using 3D-printed models of the canine upper digestive tract (UDT) for anatomy demonstration and upper endoscopy instruction was evaluated. The canine UDT (esophagus-stomach-duodenum) was scanned and 3D-printed molds were manufactured using silicone casting. First-year students were introduced to these 3D models in practical sessions alongside real specimens. Simultaneously, fifth-year students were trained in endoscope handling and anatomical recognition using 3D specimens. Both groups completed an anonymous survey. Results showed that overall, first-year (n = 93) and fifth-year (n = 45) students agreed or strongly agreed that the 3D-printed model was effective for learning purposes. In summary, first-year students highlighted an improved understanding of size, volume, topography, and easier manipulation of the 3D model compared to fresh specimens. Fifth-year students were more enthusiastic, finding the 3D model valuable for spatial vision and clinical training. While both groups were against completely replacing the natural UDT with the 3D model, first-year students were more hesitant. These findings suggest that the 3D model of the canine UDT is an effective tool for hands-on training in clinical endoscopy and a valuable, albeit complementary, resource for teaching anatomy and topography.

[Role of Virtual Reality in Gastrointestinal Endoscopy Training and Teaching]

Gastrointestinal (GI) endoscope is one of the instruments used extensively in the diagnosis and treatment of digestive tract disorders. China is confronted with a great demand for endoscopists working in grassroots healthcare facilities. Furthermore, endoscopic retrograde cholangiopancreatography (ERCP), endoscopic ultrasonography (EUS), and endoscopic submucosal dissection (ESD) are becoming the prevailing methods of endoscopic treatment of digestive diseases. Therefore, there is a growing demand for senior endoscopists. Currently, an important focus of GI endoscopy training is the acceleration of standardized training for endoscopists working in grassroots health facilities and advanced training for senior endoscopists. Simulation devices based on virtual reality technology exhibit strengths in objectivity, authenticity, and an immersive experience. These devices show advantages in the training method, the number of participants, and assessment over traditional training programs for GI endoscopy. Their application provides a new approach to the training and teaching of GI endoscopy. Herein, we summarized the explorations and practices of using virtual reality technology in the training and teaching of GI endoscopy, analyzed its application status in China, and discussed its prospects for future application.

Interactive training with a novel simulation model for upper gastrointestinal endoscopic hemostasis improves trainee technique and confidence

Background and study aims Endoscopic hemostasis is a life-saving procedure for gastrointestinal bleeding; however, training for it is often performed on real patients and during urgent situations that put patients at risk. Reports of simulation-based training models for endoscopic hemostasis are scarce. Herein, we developed a novel simulator called "Medical Rising STAR-Ulcer type" to practice endoscopic hemostasis with hemoclips and coagulation graspers. This study aimed to evaluate the reproducibility of the clinical difficulty of this model and the effectiveness of simulation-based training for clipping hemostasis. Patients and methods This was a prospective educational study. Fifty gastroenterology residents from Japan and Canada were recruited to participate in a simulation-based training program. The primary outcome was the success rate for clipping hemostasis. We measured differences in trainee subjective assessment scores and evaluated the co-occurrence network based on comments after training. Results The hemostasis success rate of the trainees significantly increased after instruction (64% vs. 86%, P < 0.05). The success rate for ulcers in the upper body of the stomach (59%), a high-difficulty site, was significantly lower than that for ulcers in the antrum, even after feedback and instruction. Trainee self-perceived proficiency and confidence significantly improved after simulation-based training ( P < 0.05). Co-occurrence network analysis showed that trainees valued a structured learning approach, acknowledged simulator limitations, and recognized the need for continuous skill refinement. Conclusions Our study demonstrates the potential of our simulation-based training model as a valuable tool for improving technical skills and confidence in trainees learning to perform endoscopic hemostasis.

A Framework for the Evaluation of Human Machine Interfaces of Robot-Assisted Colonoscopy

The Human Machine Interface (HMI) of intraluminal robots has a crucial impact on the clinician's performance. It increases or decreases the difficulty of the tasks, and is connected to the users' physical and mental stress.

OBJECTIVE

This article presents a framework to compare and evaluate different HMIs for robotic colonoscopy, with the objective of identifying the optimal HMI that minimises the clinician's effort and maximises the clinical outcomes.

METHODS

The framework comprises a 1) a virtual simulator (clinically validated), 2) wearable sensors measuring the cognitive load, 3) a data collection unit of metrics correlated to the clinical performance, and 4) questionnaires exploring the users' impressions and perceived stress. The framework was tested with 42 clinicians investigating the optimal device for tele-operated control of robotic colonoscopes. Two control devices were selected and compared: a haptic serial-kinematic device and a standard videogame joypad.

RESULTS

The haptic device was preferred by the endoscopists, but the joypad enabled better clinical performance and reduced cognitive and physical load.

CONCLUSION

The framework can be used to evaluate different aspects of a HMI, both hardware and software, and determine the optimal HMI that can reduce the burden on clinicians while improving the clinical outcome.

SIGNIFICANCE

The findings of this study, and of future studies performed with this framework, can inform the design and development of HMIs for intraluminal robots, leading to improved clinical performance, reduced physical and mental stress for clinicians, and ultimately better patient outcomes.

Development of convolutional neural network models that recognize normal anatomic structures during real-time radial-array and linear-array EUS (with videos)

BACKGROUND AND AIMS

EUS is a high-skill technique that requires numerous procedures to achieve competence. However, training facilities are limited worldwide. Convolutional neural network (CNN) models have been previously implemented for object detection. We developed 2 EUS-based CNN models for normal anatomic structure recognition during real-time linear- and radial-array EUS evaluations.

METHODS

The study was performed from February 2020 to June 2022. Consecutive patient videos of linear- and radial-array EUS videos were recorded. Expert endosonographers identified and labeled 20 normal anatomic structures within the videos for training and validation of the CNN models. Initial CNN models (CNNv1) were developed from 45 videos and the improved models (CNNv2) from an additional 102 videos. CNN model performance was compared with that of 2 expert endosonographers.

RESULTS

CNNv1 used 45,034 linear-array EUS frames and 21,063 radial-array EUS frames. CNNv2 used 148,980 linear-array EUS frames and 128,871 radial-array EUS frames. Linear-array CNNv1 and radial-array CNNv1 achieved a 75.65% and 71.36% mean average precision (mAP) with a total loss of .19 and .18, respectively. Linear-array CNNv2 obtained an 88.7% mAP with a .06 total loss, whereas radial-array CNNv2 achieved an 83.5% mAP with a .07 total loss. CNNv2 accurately detected all studied normal anatomic structures with a >98% observed agreement during clinical validation.

CONCLUSIONS

The proposed CNN models accurately recognize the normal anatomic structures in prerecorded videos and real-time EUS. Prospective trials are needed to evaluate the impact of these models on the learning curves of EUS trainees.

Exploring Endoscopic Competence in Gastroenterology Training: A Simulation-Based Comparative Analysis of GAGES, DOPS, and ACE Assessment Tools

Purpose

Accurate and convenient evaluation tools are essential to document endoscopic competence in Gastroenterology training programs. The Direct Observation of Procedural Skills (DOPS), Global Assessment of Gastrointestinal Endoscopic Skills (GAGES), and Assessment of Endoscopic Competency (ACE) are widely used validated competency assessment tools for gastrointestinal endoscopy. However, studies comparing these 3 tools are lacking, leading to lack of standardization in this assessment. Through simulation, this study seeks to determine the most reliable, comprehensive, and user-friendly tool for standardizing endoscopy competency assessment.

Methods

A mixed-methods quantitative-qualitative approach was utilized with sequential deductive design. All nine trainees in a gastroenterology training program were assessed on endoscopic procedural competence using the Simbionix Gi-bronch-mentor high-fidelity simulator, with 2 faculty raters independently completing the 3 assessment forms of DOPS, GAGES, and ACE. Psychometric analysis was used to evaluate the tools' reliability. Additionally, faculty trainers participated in a focused group discussion (FGD) to investigate their experience in using the tools.

Results

For upper GI endoscopy, Cronbach's alpha values for internal consistency were 0.53, 0.8, and 0.87 for ACE, DOPS, and GAGES, respectively. Inter-rater reliability (IRR) scores were 0.79 (0.43-0.92) for ACE, 0.75 (-0.13-0.82) for DOPS, and 0.59 (-0.90-0.84) for GAGES. For colonoscopy, Cronbach's alpha values for internal consistency were 0.53, 0.82, and 0.85 for ACE, DOPS, and GAGES, respectively. IRR scores were 0.72 (0.39-0.96) for ACE, 0.78 (-0.12-0.86) for DOPS, and 0.53 (-0.91-0.78) for GAGES. The FGD yielded three key themes: the ideal tool should be scientifically sound, comprehensive, and user-friendly.

Conclusion

The DOPS tool performed favourably in both the qualitative assessment and psychometric evaluation to be considered the most balanced amongst the three assessment tools. We propose that the DOPS tool be used for endoscopic skill assessment in gastroenterology training programs. However, gastroenterology training programs need to match their learning outcomes with the available assessment tools to determine the most appropriate one in their context.

A convenient machine learning model to predict full stomach and evaluate the safety and comfort improvements of preoperative oral carbohydrate in patients undergoing elective painless gastrointestinal endoscopy

BACKGROUND AND AIMS

Assessment of the patient's gastric contents is the key to avoiding aspiration incidents, however, there is no effective method to determine whether elective painless gastrointestinal endoscopy (GIE) patients have a full stomach or an empty stomach. And previous studies have shown that preoperative oral carbohydrates (POCs) can improve the discomfort induced by fasting, but there are different perspectives on their safety. This study aimed to develop a convenient, accurate machine learning (ML) model to predict full stomach. And based on the model outcomes, evaluate the safety and comfort improvements of POCs in empty- and full stomach groups.

METHODS

We enrolled 1386 painless GIE patients between October 2022 and January 2023 in Nanjing First Hospital, and 1090 patients without POCs were used to construct five different ML models to identify full stomach. The metrics of discrimination and calibration validated the robustness of the models. For the best-performance model, we further interpreted it through SHapley Additive exPlanations (SHAP) and constructed a web calculator to facilitate clinical use. We evaluated the safety and comfort improvements of POCs by propensity score matching (PSM) in the two groups, respectively.

RESULTS

Random Forest (RF) model showed the greatest discrimination with the area under the receiver operating characteristic curve (AUROC) 0.837 [95% confidence interval (CI): 79.1-88.2], F1 71.5%, and best calibration with a Brier score of 15.2%. The web calculator can be visited at https://medication.shinyapps.io/RF_model/. PSM results demonstrated that POCs significantly reduced the full stomach incident in empty stomach group (p < 0.05), but no differences in full stomach group (p > 0.05). Comfort improved in both groups and was more significant in empty stomach group.

CONCLUSIONS

The developed convenient RF model predicted full stomach with high accuracy and interpretability. POCs were safe and comfortably improved in both groups, with more benefit in empty stomach group. These findings may guide the patients' gastrointestinal preparation.

Smart Endoscopy Is Greener Endoscopy: Leveraging Artificial Intelligence and Blockchain Technologies to Drive Sustainability in Digestive Health Care

The surge in the implementation of artificial intelligence (AI) in recent years has permeated many aspects of our life, and health care is no exception. Whereas this technology can offer clear benefits, some of the problems associated with its use have also been recognised and brought into question, for example, its environmental impact. In a similar fashion, health care also has a significant environmental impact, and it requires a considerable source of greenhouse gases. Whereas efforts are being made to reduce the footprint of AI tools, here, we were specifically interested in how employing AI tools in gastroenterology departments, and in particular in conjunction with capsule endoscopy, can reduce the carbon footprint associated with digestive health care while offering improvements, particularly in terms of diagnostic accuracy. We address the different ways that leveraging AI applications can reduce the carbon footprint associated with all types of capsule endoscopy examinations. Moreover, we contemplate how the incorporation of other technologies, such as blockchain technology, into digestive health care can help ensure the sustainability of this clinical speciality and by extension, health care in general.

How to make cost-effective polyp simulators for high-fidelity simulation-based training in postpolypectomy bleeding management and EMR

Video 1Demonstration of manufacturing instructions and features of the postpolypectomy bleeding and conventional and underwater EMR simulators.

Burnout in healthcare - the Emperor's New Clothes

Burnout is common among physicians; it severely alters their health and has a negative impact on functioning of healthcare systems. Hypertension, increased cortisol levels, maladaptive behaviors with negative social consequences, and suboptimal quality of care have been associated with healthcare providers' burnout. As the number of patients with cancers, psychiatric and neurodegenerative disorders will rise, we need new solutions to maintain physicians' health and, therefore, quality of care. Coping strategies before the COVID-19 pandemic seem ineffective in scaling all the deficits of the global healthcare systems. Examples of new initiatives include new collaborative projects, such as COH-FIT (The Collaborative Outcomes study on Health and Functioning during Infection Times - https://www.coh-fit.com), which aims to collect global data and understand the impact of the COVID-19 pandemic on physical and mental health in order to identify various coping strategies for patients and healthcare workers during infection times, or MEMO (Minimizing Error, Maximizing Outcome), funded by the Agency of Healthcare Research and Quality (AHRQ). Others: i) Rome Foundation GastroPsych undertake efforts dedicated to the science and practice of psychogastroenterology, a burgeoning field with roots in behavioral intervention, cognitive science and experimental psychology focused on fostering the professional growth and collaboration of those engaged in medical practices, or ii) World Gastroenterology Organisation (WGO), Train The Trainers (TTT) program including a new topic of the impact of burnout on career longevity in order to foster strategies for staying healthy and increasing career satisfaction. There is a need for continuous development of digital technologies (e.g. training simulators, telemedicine, robots and artificial intelligence). Their implementation into medical practice is inevitable. Now more than ever, there is a need for a new spirit in healthcare. Together with others in the field, we believe this article is a desperate call for maximizing the use of novel technologies supported by collaborative interactions among healthcare providers and medical professionals of diverse medical fields.

Hybrid Models for Endoscopy Image Analysis for Early Detection of Gastrointestinal Diseases Based on Fused Features

The gastrointestinal system contains the upper and lower gastrointestinal tracts. The main tasks of the gastrointestinal system are to break down food and convert it into essential elements that the body can benefit from and expel waste in the form of feces. If any organ is affected, it does not work well, which affects the body. Many gastrointestinal diseases, such as infections, ulcers, and benign and malignant tumors, threaten human life. Endoscopy techniques are the gold standard for detecting infected parts within the organs of the gastrointestinal tract. Endoscopy techniques produce videos that are converted into thousands of frames that show the disease's characteristics in only some frames. Therefore, this represents a challenge for doctors because it is a tedious task that requires time, effort, and experience. Computer-assisted automated diagnostic techniques help achieve effective diagnosis to help doctors identify the disease and give the patient the appropriate treatment. In this study, many efficient methodologies for analyzing endoscopy images for diagnosing gastrointestinal diseases were developed for the Kvasir dataset. The Kvasir dataset was classified by three pre-trained models: GoogLeNet, MobileNet, and DenseNet121. The images were optimized, and the gradient vector flow (GVF) algorithm was applied to segment the regions of interest (ROIs), isolating them from healthy regions and saving the endoscopy images as Kvasir-ROI. The Kvasir-ROI dataset was classified by the three pre-trained GoogLeNet, MobileNet, and DenseNet121 models. Hybrid methodologies (CNN-FFNN and CNN-XGBoost) were developed based on the GVF algorithm and achieved promising results for diagnosing disease based on endoscopy images of gastroenterology. The last methodology is based on fused CNN models and their classification by FFNN and XGBoost networks. The hybrid methodology based on the fused CNN features, called GoogLeNet-MobileNet-DenseNet121-XGBoost, achieved an AUC of 97.54%, accuracy of 97.25%, sensitivity of 96.86%, precision of 97.25%, and specificity of 99.48%.

Simulator-based training method in gastrointestinal endoscopy training and currently available simulators

The apprenticeship-based training method (ABTM) is highly effective for gastrointestinal (GI) endoscopic training. However, the conventional ABTM has significant issues. Although many supplementary training methods (TMs) have been developed and utilized, they cannot entirely replace the ABTM, which remains the major TM strategy. Currently, new TM construction is crucial and necessary due to financial constraints, difficulty of obtaining sufficient training time due to patient safety-related regulations, and catastrophic damage caused by disasters such as the coronavirus disease 2019 pandemic. The simulator-based TM (SBTM) is widely accepted as an alternative to the ABTM, owing to the SBTM's advantages. Since the 1960s, many GI endoscopy training simulators have been developed and numerous studies have been published on their effectiveness. While previous studies have focused on the simulator's validity, this review focused on the accessibility of simulators that were introduced by the end of 2021. Although the current SBTM is effective in GI endoscopic education, extensive improvements are needed to replace the ABTM. Incorporating simulator-incorporated TMs into an improved ABTM is an attempt to overcome the incompleteness of the current SBTM. Until a new simulator is developed to replace the ABTM, it is desirable to operate a simulator-integrated and well-coordinated TM that is suitable for each country and institution.

Reperfused human cadaver as a new simulation model for colonoscopy: a pilot study

BACKGROUND

The reperfused human cadaver is a validated simulator for surgery. We aimed to use it as a colonoscopy simulator.

METHODS

Novices, intermediates and skilled participants in gastrointestinal endoscopy were included. They performed one colonoscopy on a reperfused human cadaver and reaching rates, time, and length needed to reach anatomical landmarks were reported for construct validity analysis. We also assessed our model realism (SRS survey), educational content (CVS survey) and task load (NASA-TLX index). Score items were collected and defined as "favorable" when items were rated ≥ 5/7 with an inter-quartile range (IQR) overlapping four, and "very favorable" when rated ≥ 5/7 with an IQR excluding four (neutral). Primary endpoints were the rectosigmoid junction (RSJ) reaching rate and the descending colon (DC) reaching time. Secondary objectives were SRS, CVS and NASA-TLX questionnaire results.

RESULTS

A total of 11 skilled participants, 5 intermediates and 8 novices were included. Skilled participants reached RSJ more often than novice and intermediary groups, respectively, 100%, 80% and 75% without differing significantly. They reached DC more frequently (100% for skilled, 80% for intermediates and 50% for novices, p = 0.018). The median time to reach RSJ (59, 272 and 686 s for skilled, intermediates and novices group, respectively) and DC (90, 534 and 1360 s for skilled, intermediates and novices) was significantly shorter for skilled participants (both p < .01). Nineteen out of the 22 items composing the realism survey obtained "very favorable" and "favorable" scores. Educational content was designated as "very favorable". Mental, physical, and technical demands were gradually higher the lower the initial level of experience.

CONCLUSIONS

Reperfused human cadaver model has the potential to be valid simulation tool for diagnostic colonoscopy training.

Endoscopic Features of Gastric Epithelial Neoplasm of Fundic Gland Mucosa Lineage

The endoscopic features of gastric epithelial neoplasms of fundic gland mucosa lineage (GEN-FGML) have not been well investigated. We aimed to clarify the endoscopic features of GEN-FGML and differences between gastric adenocarcinoma of the fundic gland type (GA-FG) and fundic gland mucosa type (GA-FGM). A total of 62 GEN-FGML lesions, including 52 GA-FG and 10 GA-FGM, were retrospectively analyzed using endoscopic and clinicopathological findings to provide information of diagnostic value using white light imaging (WLI) and magnifying endoscopy with narrow-band imaging (M-NBI). GA-FG frequently presented with a whitish, submucosal tumor (SMT) shape with dilated vessels with branching architecture and background mucosa without atrophic change in WLI, an indistinct demarcation line (DL), dilatation of the crypt opening and intervening part (IP), and microvessels without distinct irregularity in M-NBI. GA-FGM frequently presented as a reddish, elevated lesion in WLI, with a distinct DL, dilatation of the IP, and an irregular microvascular pattern in M-NBI. As for an M-NBI diagnosis, five GA-FGM lesions met the diagnostic criteria for cancer, whereas none of the GA-FG lesions met the same criteria. We highlight the endoscopic features of GEN-FGML, and the differentiation between GA-FG and GA-FGM might be possible by combination of lesion color and morphology in WLI and M-NBI diagnoses.

Evaluating the effect of an artificial intelligence system on the anesthesia quality control during gastrointestinal endoscopy with sedation: a randomized controlled trial

Background

Sedative gastrointestinal endoscopy is extensively used worldwide. An appropriate degree of sedation leads to more acceptability and satisfaction. Artificial intelligence has rapidly developed in the field of digestive endoscopy in recent years and we have constructed a mature computer-aided diagnosis (CAD) system. This system can identify the remaining parts to be examined in real-time endoscopic procedures, which may help anesthetists use anesthetics properly to keep patients in an appropriate degree of sedation.

Aims

This study aimed to evaluate the effects of the CAD system on anesthesia quality control during gastrointestinal endoscopy.

Methods

We recruited 154 consecutive patients at Renmin Hospital of Wuhan University, including 76 patients in the CAD group and 78 in the control group. Anesthetists in the CAD group were able to see the CAD system’s indications, while anesthetists in the control group could not. The primary outcomes included emergence time (from examination completion to spontaneous eye opening when doctors called the patients’ names), recovery time (from examination completion to achievement of the primary recovery endpoints) and patient satisfaction scores. The secondary outcomes included anesthesia induction time (from sedative administration to successful sedation), procedure time (from scope insertion to scope withdrawal), total dose of propofol, vital signs, etc. This trial was registered in the Primary Registries of the WHO Registry Network, with registration number ChiCTR2100042621.

Results

Emergence time in the CAD group was significantly shorter than that in the control group (p < 0.01). The recovery time was also significantly shorter in the CAD group (p < 0.01). Patients in the CAD group were significantly more satisfied with their sedation than those in control group (p < 0.01). Vital signs were stable during the examinations in both groups. Propofol doses during the examinations were comparable between the two groups.

Conclusion

This CAD system possesses great potential for anesthesia quality control. It can improve patient satisfaction during endoscopic examinations with sedation.

Trial registration

ChiCTR2100042621.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12871-022-01796-1.

Simulation-based mastery learning in gastrointestinal endoscopy training

Simulation-based mastery learning (SBML) is an emerging form of competency-based training that has been proposed as the next standard method for procedural task training, including that in gastrointestinal endoscopy. Current basic gastrointestinal endoscopy training relies on the number of procedures performed, and it has been criticized for its lack of objective standards that result in variable skills among trainees and its association with patient safety risk. Thus, incorporating simulators into a competency-based curriculum seems ideal for gastrointestinal endoscopy training. The curriculum for SBML in gastrointestinal endoscopy is currently being developed and has promising potential to translate into the clinical performance. Unlike the present apprenticeship model of “see one, do one, teach one,” SBML integrates a competency-based curriculum with specific learning objectives alongside simulation-based training. This allows trainees to practice essential skills repeatedly, receive feedback from experts, and gradually develop their abilities to achieve mastery. Moreover, trainees and trainers need to understand the learning targets of the program so that trainees can focus their learning on the necessary skills and trainers can provide structured feedback based on the expected outcomes. In addition to learning targets, an assessment plan is essential to provide trainees with future directions for their improvement and ensure patient safety by issuing a passing standard. Finally, the SBML program should be planned and managed by a specific team and conducted within a developed and tested curriculum. This review discusses the current state of gastrointestinal endoscopy training and the role of SBML in that field.

A Simulation Study to Investigate the Usefulness of a Novel Stricture Tool for Training Wire Guided Balloon Dilation

Background and Aims The training in esophageal stricture dilation is difficult to obtain and have few simulation models. The aim of the study was to evaluate a novel stricture simulation for training a wire-guided, controlled radial expansile (CRE) balloon dilation.

Methods The study was a pretest–posttest design without a control group involving a novel simulation device for esophageal stricture. The training session involved 12 final year gastroenterology fellows from five different centers. The trainees received 2 hours of education sessions featuring didactic content, a live demonstration of step-by-step demonstration of wire-guided CRE balloon dilation and a study material on the procedure. The simulation device used was a single-use hose pipe along with a red color nonhardening modeling clay with a 5.0-to-8.0-mm hole in the center.

Results All the trainees and instructor uniformly rated the model as excellent or good with simulation device being mild stiffer in haptics than of the real tissue. The mean (%) pretest scores of 39 (21.6%) improved significantly to 160 (88.8%) in mean (%) posttest questionnaire (p < 0.05). There was a significant improvement in the questionnaire of the dilation procedure after the simulation training episode.

Conclusion The novel stricture simulation model had good performance evaluation and can be used to train CRE balloon dilation procedure.

A Hybrid Surgical Simulator for Interactive Endoscopic Training

Endoscopy serves as an indispensable minimally-invasive surgical procedure. Due to the limited view and non-intuitive operation of the instrument, the mastery of endoscopic manipulation requires deep medical knowledge as well as complex perception and motor skills of the surgeon. Intensive surgical training is required, and simulation-based training is of more and more importance over traditional animal- or cadaver-based approaches. Here, we developed a hybrid surgical simulator that consists of a realistic physical organ model and an artificial intelligence (AI)-driven cyber model. We built a physical model of the full urinary tract with soft materials and detailed blood vessel structures. Endourological procedures were performed to localize and treat renal calculi by a flexible endoscope. An AI algorithm detects the lesions automatically with high accuracy and provides quantitative feedback about an operator's endoscopic skills. The hybrid simulator system shows great potential as an interactive and personalized learning environment for endoscopic skills. Clinical Relevance- This work establishes a preliminary approach for realistic endoscopic training. The developed hybrid surgical simulator - with high-fidelity physical organ models and quantitative feedback - can deliver effective hands-on learning to surgeons to improve their endoscopic skills.