Toward effective pediatric minimally invasive surgical simulation

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.

DEVELOPMENT AND VALIDATION OF A NEW LAPAROSCOPIC ENDOTRAINER FOR NEONATAL SURGERY AND REDUCED SPACES

BACKGROUND

Pediatric laparoscopy box with sliding tray. Pediatric procedures have the difficulty of being performed in reduced spaces. Training in reduced spaces has proven to be different in complexity compared to adult laparoscopic endotrainers.

AIM

To develop and validate a new neonatal/reduced-space endotrainer.

METHODS

The simulator was tested and assessed by users with different skill levels and experience in laparoscopic pediatric surgery through an 8-item questionnaire. Construct validity was determined by evaluating the performance of each subject on nine exercises.

RESULTS

A 10.5 x 10 x 18 cm acrylic simulator was created, with an internal working surface of 9 x 9 cm. An HD camera was incorporated, with a 0-180° range of movement. All exercises of a Basic Laparoscopic Training Program were adapted on a scale of 1:0.5 to fit in. From 49 participants, 42 (85.71%) answered the survey; 80.5% considered that the simulator reproduces similar conditions to procedures performed in children under one year of age; 61.1% thought that the simulator represents a difficulty identical to procedures performed in newborns; 73.7% considered that the neonatal simulator is more complicated than the adult simulator. Experts showed significantly better performance in all proposed exercises.

CONCLUSION

The simulator has a high-quality image and design that allows training with basic tasks. The endotrainer permitted to discriminate between these different skill levels and was well evaluated by users with diverse surgical experience.

Evaluation methods and impact of simulation-based training in pediatric surgery: a systematic review

PURPOSE

The aim of this study was to identify (1) the type of skill evaluation methods and (2) how the effect of training was evaluated in simulation-based training (SBT) in pediatric surgery.

METHODS

Databases of PubMed, Cochrane Library, and Web of Science were searched for articles published from January 2000 to January 2017. Search concepts of Medical Subject Heading terms were "surgery," "pediatrics," "simulation," and "training, evaluation."

RESULTS

Of 5858 publications identified, 43 were included. Twenty papers described simulators as assessment tools used to evaluate technical skills. Reviewers differentiated between experts and trainees using a scoring system (45%) and/or a checklist (25%). Simulators as training tools were described in 23 papers. While the training's effectiveness was measured using performance assessment scales (52%) and/or surveys (43%), no study investigated the improvement of the clinical outcomes after SBT.

CONCLUSION

Scoring, time, and motion analysis methods were used for the evaluation of basic techniques of laparoscopic skills. Only a few SBT in pediatric surgery have definite goals with clinical effect. Future research needs to demonstrate the educational effect of simulators as assessment or training tools on SBT in pediatric surgery.

Current status of simulation-based training in pediatric surgery: A systematic review

BACKGROUND

Simulation based training enables pediatric surgical trainees to attain proficiency in surgical skills. This study aims to identify the currently available simulators for pediatric surgery, assess their validation and strength of evidence supporting each model.

METHODS

Both Medline and EMBASE were searched for English language articles either describing or validating simulation models for pediatric surgery. A level of evidence (LoE) followed by a level of recommendation (LoR) was assigned to each validation study and simulator, based on a modified Oxford Centre for Evidence-Based Medicine classification for educational studies.

RESULTS

Forty-nine articles were identified describing 44 training models and courses. Of these articles, 44 were validation studies. Face validity was evaluated by 20 studies, 28 for content, 24 demonstrated construct validity and 1 showed predictive validity. Of the validated models, 3 were given an LoR of 2, 21 an LoR of 3 and 12 an LoR of 4. None reached the highest LoR.

CONCLUSIONS

There are a growing number of simulators specific to pediatric surgery. However, these simulators have limited LoE and LoR in current studies. The lack of NoTSS training is also apparent. We advocate more randomized trials to validate these models, and attempts to determine predictive validity.

TYPE OF STUDY

Original / systematic review.

LEVEL OF EVIDENCE

1.

The National Pediatric Surgery Simulation Program in France: A tool to develop resident training in pediatric surgery

BACKGROUND/PURPOSE

To implement resident curriculum in France based on theoretical teaching and bed side training, the national council known as the "Collège Hospitalier et Universitaire de Chirurgie Pédiatrique" examined the relevance and feasibility of systematically introducing simulation program in the pediatric surgery resident training.

MATERIAL AND METHODS

A national simulation training program was developed and took place in a 2-day session organized in 7 simulation centers in France. The program included technical (laparoscopic/suturing technique on low-fidelity models) and nontechnical (6 scenarios for standardized consultation, and a team work scenario based on errors prevention in the operative room) skills. Evaluation of the program (Likert scale from 1 (bad) to 5 (excellent) and notation on 20 points) concerned trainees and trainers.

RESULTS

40 residents (95% of all pediatric surgery French residents) attended with a ratio of trainees/trainer of ½. The training objectives earned a score of 4.46/5. The pedagogical value of the seminar scored 4.7/5, teaching quality 17.95/20, and the overall seminar score was 17.35/20.

CONCLUSION

This program, unique nationally, was assessed very favorably by the participating residents and by the involved trainers. To our knowledge, it represents the first mandatory national simulation training program included within a surgical training model.

LEVEL OF EVIDENCE

Level IV.

Video-based skill assessment of endoscopic suturing in a pediatric chest model and a box trainer

PURPOSE

Pediatric endoscopic surgery requires special surgical skills because of the small working space and tissue fragility. This article presents a video-based skill assessment method for endoscopic suturing using a pediatric chest model.

MATERIALS AND METHODS

A commercial suture pad was placed in a rapid-prototyped pediatric chest model of a 1-year-old patient to simulate the thoracoscopic repair of esophageal atresia type C. Twenty-eight pediatric surgeons (9 experts, 9 intermediates, and 10 trainees) performed an endoscopic intracorporeal suturing and knot-tying task both in the pediatric chest model and in a box trainer. The tasks were video-recorded and rated by two blinded observers using the 29-point checklist method and a suturing errors score sheet method. The task completion time and the number of needle manipulations were measured.

RESULTS

The expert group showed better performance than the intermediate and trainee groups in the pediatric chest model, and the differences were larger than those in the box trainer. Significant differences between the expert and the trainee groups were observed in the items related to safety such as the skills for keeping the needle in view at all times. Significant differences between the expert and intermediate groups were observed in the items related to task quality and efficiency such as the smoothness of knot tying and the number of needle manipulations.

CONCLUSIONS

Video-based skill assessment of endoscopic suturing using the pediatric chest model and a box trainer distinguished pediatric endoscopic surgeons according to their clinical experience, and pediatric-specific skills were identified.

Designing and conducting simulation-based research

As simulation is increasingly used to study questions pertaining to pediatrics, it is important that investigators use rigorous methods to conduct their research. In this article, we discuss several important aspects of conducting simulation-based research in pediatrics. First, we describe, from a pediatric perspective, the 2 main types of simulation-based research: (1) studies that assess the efficacy of simulation as a training methodology and (2) studies where simulation is used as an investigative methodology. We provide a framework to help structure research questions for each type of research and describe illustrative examples of published research in pediatrics using these 2 frameworks. Second, we highlight the benefits of simulation-based research and how these apply to pediatrics. Third, we describe simulation-specific confounding variables that serve as threats to the internal validity of simulation studies and offer strategies to mitigate these confounders. Finally, we discuss the various types of outcome measures available for simulation research and offer a list of validated pediatric assessment tools that can be used in future simulation-based studies.

Collaboration in simulation: the development and initial validation of a novel thoracoscopic neonatal simulator

PURPOSE

We sought to create and validate a high fidelity, anatomically correct real tissue simulation model for thoracoscopic esophageal atresia/tracheoesophageal fistula (EA/TEF) repair.

METHODS

A scale reproduction of a neonatal rib cage was created. Surgically modified (EA/TEF) fetal bovine tissue completed the simulator. Nine pediatric surgery fellows and two attending pediatric surgeons (n=11) performed the simulated thoracoscopic EA/TEF repair. Participants completed a self-report rating scale, ranging from 1 (Don't know) to 5 (Highly realistic). Construct validity relevant to test content was evaluated by examining the ratings using the many-Facet Rasch model.

RESULTS

Analyses indicated no differences when comparing faculty (Observed Average (OA)=4.5/5.0) to fellow (OA=3.3) ratings, p=.71. In descending order, observed averages of the domains were 4.7 (Relevance), 4.5 (Physical attributes), 4.5 (Realism of materials), 4.4 (Ability to perform task), and 4.2 (Value). The observed Global opinion rating indicated the simulator can be considered for teaching thoracoscopic EA/TEF repair but could be improved slightly.

CONCLUSIONS

Fellow and faculty ratings indicated the simulator was valuable as a learning tool with minor modifications. Comments were consistent with high physical attribute ratings.