Evaluation of a Virtual Reality-Based Open Educational Resource Software.

OBJECTIVES: Virtual reality (VR) teaching methods have potential to support medical students acquire increasing amounts of knowledge. EVENT (Easy VR EducatioN Tool) is an open educational resource software for immersive VR environments, which is designed for use without programming skills. In this work, EVENT was used in a medical student VR course on pancreatic cancer. METHODS: Medical students were invited to participate in the course. Before and after VR simulation, participants completed a multiple-choice knowledge assessment, with a maximum score of 10, and a VR experience questionnaire. The primary endpoint compared pre- and post-VR simulation test scores. Secondary endpoints included usability and factors that could affect learning growth and test results. RESULTS: Data from 117 of the 135 participating students was available for analysis. Student test scores improved by an average of 3.4 points (95% CI 3.1-3.7, P < 0.001) after VR course. The secondary endpoints of gender, age, prior knowledge regarding the medical subject, professional training completed in the medical field, video game play, three-dimensional imagination skills, or cyber-sickness had no major impact on test scores or final ranking (top or bottom 25%). The 27 students whose post-VR simulation test scores ranked in the top 25% had no prior experience with VR. The average System Usability Scale score was 86.1, which corresponds to an excellent outcome for user-friendliness. Questionnaire responses post-VR simulation show students (81.2% [95/117]) interest in more VR options in medical school. CONCLUSIONS: We present a freely available software that allows for the development of VR teaching lessons without programming skills.

Frame-by-Frame Analysis of a Commercially Available Artificial Intelligence Polyp Detection System in Full-Length Colonoscopies.

INTRODUCTION: Computer-aided detection (CADe) helps increase colonoscopic polyp detection. However, little is known about other performance metrics like the number and duration of false-positive (FP) activations or how stable the detection of a polyp is. METHODS: 111 colonoscopy videos with total 1,793,371 frames were analyzed on a frame-by-frame basis using a commercially available CADe system (GI-Genius, Medtronic Inc.). Primary endpoint was the number and duration of FP activations per colonoscopy. Additionally, we analyzed other CADe performance parameters, including per-polyp sensitivity, per-frame sensitivity, and first detection time of a polyp. We additionally investigated whether a threshold for withholding CADe activations can be set to suppress short FP activations and how this threshold alters the CADe performance parameters. RESULTS: A mean of 101 ± 88 FPs per colonoscopy were found. Most of the FPs consisted of less than three frames with a maximal 66-ms duration. The CADe system detected all 118 polyps and achieved a mean per-frame sensitivity of 46.6 ± 26.6%, with the lowest value for flat polyps (37.6 ± 24.8%). Withholding CADe detections up to 6 frames length would reduce the number of FPs by 87.97% (p < 0.001) without a significant impact on CADe performance metrics. CONCLUSIONS: The CADe system works reliable but generates many FPs as a side effect. Since most FPs are very short, withholding short-term CADe activations could substantially reduce the number of FPs without impact on other performance metrics. Clinical practice would benefit from the implementation of customizable CADe thresholds.

Autonomous Nervous Response During Sedation in Colonoscopy and the Relationship With Clinician Satisfaction.

Background: Nurse assisted propofol sedation (NAPS) is a common method used for colonoscopies. It is safe and widely accepted by patients. Little is known, however, about the satisfaction of clinicians performing colonoscopies with NAPS and the factors that negatively influence this perception such as observer-reported pain events. In this study, we aimed to correlate observer-reported pain events with the clinicians' satisfaction with the procedure. Additionally, we aimed to identify patient biosignals from the autonomic nervous system (B-ANS) during an endoscopy that correlate with those pain events. Methods: Consecutive patients scheduled for a colonoscopy with NAPS were prospectively recruited. During the procedure, observer-reported pain events, which included movements and paralinguistic sounds, were simultaneously recorded with different B-ANS (facial electromyogram (EMG), skin conductance level, body temperature and electrocardiogram). After the procedure, the examiners filled out the Clinician Satisfaction with Sedation Instrument (CSSI). The primary endpoint was the correlation between CSSI and observer-reported pain events. The second primary endpoint was the identification of B-ANS that make it possible to predict those events. Secondary endpoints included the correlation between CSSI and sedation depth, the frequency and dose of sedative use, polyps resected, resection time, the duration of the procedure, the time it took to reach the coecum and the experience of the nurse performing the NAPS. ClinicalTrials.gov: NCT03860779. Results: 112 patients with 98 (88.5%) available B-ANS recordings were prospectively recruited. There was a significant correlation between an increased number of observer-reported pain events during an endoscopy with NAPS and a lower CSSI (r = -0.318, p = 0.001). Additionally, the EMG-signal from facial muscles correlated best with the event time points, and the signal significantly exceeded the baseline 30 s prior to the occurrence of paralinguistic sounds. The secondary endpoints showed that the propofol dose relative to the procedure time, the cecal intubation time, the time spent on polyp removal and the individual nurse performing the NAPS significantly correlated with CSSI. Conclusion: This study shows that movements and paralinguistic sounds during an endoscopy negatively correlate with the satisfaction of the examiner measured with the CSSI. Additionally, an EMG of the facial muscles makes it possible to identify such events and potentially predict their occurrence.