ABSTRACT
Conducting external post-mortem examinations is an essential skill required of physicians in various countries, regardless of their specialization. However, the quality of these examinations has been a subject of continuous debates, and notable errors were reviled. In response to these shortcomings, a virtual reality (VR) application was developed at Halle's medical department in Germany, focusing on the scene of discovery and the completion of death certificates. The initial trial of this VR application in 2020 involved 39 students and 15 early-career professionals. Based on the feedback, the application underwent improvements and was subsequently introduced to the medical department in Dresden, Germany, in 2022. Its primary objective was to showcase the VR training's adaptability and scalability across various educational structures and levels of medical expertise. Out of 73 students who participated, 63 completed the evaluation process. 93.1% (n = 58) of the evaluators reported increased confidence in conducting external post-mortem examinations, and 96.8% (n = 61) felt more assured in filling out death certificates, crediting this progress to the VR training. Additionally, 98.4% (n = 62) believed that repeating forensic medical aspects in their coursework was crucial, and 96.8% (n = 61) viewed the VR examination as a valuable addition to their academic program. Despite these positive responses, 91.6% (n = 55) of participants maintained that training with real corpses remains irreplaceable due to the insufficiency of haptic feedback in VR. Nevertheless, the potential for enhancing the VR content and expanding the training to additional locations or related disciplines warrants further exploration.
ABSTRACT
PURPOSE: Efficient and precise surgical skills are essential in ensuring positive patient outcomes. By continuously providing real-time, data driven, and objective evaluation of surgical performance, automated skill assessment has the potential to greatly improve surgical skill training. Whereas machine learning-based surgical skill assessment is gaining traction for minimally invasive techniques, this cannot be said for open surgery skills. Open surgery generally has more degrees of freedom when compared to minimally invasive surgery, making it more difficult to interpret. In this paper, we present novel approaches for skill assessment for open surgery skills. METHODS: We analyzed a novel video dataset for open suturing training. We provide a detailed analysis of the dataset and define evaluation guidelines, using state of the art deep learning models. Furthermore, we present novel benchmarking results for surgical skill assessment in open suturing. The models are trained to classify a video into three skill levels based on the global rating score. To obtain initial results for video-based surgical skill classification, we benchmarked a temporal segment network with both an I3D and a Video Swin backbone on this dataset. RESULTS: The dataset is composed of 314 videos of approximately five minutes each. Model benchmarking results are an accuracy and F1 score of up to 75 and 72%, respectively. This is similar to the performance achieved by the individual raters, regarding inter-rater agreement and rater variability. We present the first end-to-end trained approach for skill assessment for open surgery training. CONCLUSION: We provide a thorough analysis of a new dataset as well as novel benchmarking results for surgical skill assessment. This opens the doors to new advances in skill assessment by enabling video-based skill assessment for classic surgical techniques with the potential to improve the surgical outcome of patients.
ABSTRACT
Objective: Drastic restrictions were imposed due to the COVID-19 pandemic, especially relating to the practical training part of the undergraduate human and dental medical training. During emergency mode teaching in the summer semester of 2020, a pilot project on practical classroom teaching under COVID-19 conditions was undertaken the Skills Lab Dresden, the Interprofessional Medical Training Centre (MITZ). Students were able to continue learning basic communication and manual skills. This project report presents the adaptations needed for this teaching concept and discusses their feasibility as well as selected evaluation results of the trial run. Description of the project: In normal teaching, students rotate to complete training sessions in small groups. Teaching is provided in a peer-teaching format. An Inverted Classroom Model was implemented as a teaching concept during emergency operation with preparation through digital learning and classroom teaching. Organisational and teaching adjustments were carried out for the concept and to comply with containment regulations. The concept was evaluated by the students using a standardised online questionnaire. Results: 1012 students completed their training during emergency operation at the university. The containment regulations meant that there were a higher number of training sessions and a higher workload. Only one of the alternative dates provided had to be used for COVID-19-related reasons. Infection chains could be tracked. The majority of students found the communication of information via Moodle to be sufficient and did not experience any technical problems. An analysis of the students' evaluation revealed a high level of overall satisfaction with the adapted teaching concept. Conclusion: The MITZ will once again use the concept in a modified form should there be renewed or continued emergency operation. The Inverted Classroom Model will also be established as an integral part of regular teaching. The findings may be of interest to other Skills Labs to develop concepts for emergency operation teaching to efficiently utilise site-specific resources.
