Dataset Information

Continuous monitoring of surgical bimanual expertise using deep neural networks in virtual reality simulation.

ABSTRACT: In procedural-based medicine, the technical ability can be a critical determinant of patient outcomes. Psychomotor performance occurs in real-time, hence a continuous assessment is necessary to provide action-oriented feedback and error avoidance guidance. We outline a deep learning application, the Intelligent Continuous Expertise Monitoring System (ICEMS), to assess surgical bimanual performance at 0.2-s intervals. A long-short term memory network was built using neurosurgeon and student performance in 156 virtually simulated tumor resection tasks. Algorithm predictive ability was tested separately on 144 procedures by scoring the performance of neurosurgical trainees who are at different training stages. The ICEMS successfully differentiated between neurosurgeons, senior trainees, junior trainees, and students. Trainee average performance score correlated with the year of training in neurosurgery. Furthermore, coaching and risk assessment for critical metrics were demonstrated. This work presents a comprehensive technical skill monitoring system with predictive validation throughout surgical residency training, with the ability to detect errors.

SUBMITTER: Yilmaz R

PROVIDER: S-EPMC9042967 | biostudies-literature | 2022 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Continuous monitoring of surgical bimanual expertise using deep neural networks in virtual reality simulation.

Yilmaz Recai R Winkler-Schwartz Alexander A Mirchi Nykan N Reich Aiden A Christie Sommer S Tran Dan Huy DH Ledwos Nicole N Fazlollahi Ali M AM Santaguida Carlo C Sabbagh Abdulrahman J AJ Bajunaid Khalid K Del Maestro Rolando R

NPJ digital medicine 20220426 1

In procedural-based medicine, the technical ability can be a critical determinant of patient outcomes. Psychomotor performance occurs in real-time, hence a continuous assessment is necessary to provide action-oriented feedback and error avoidance guidance. We outline a deep learning application, the Intelligent Continuous Expertise Monitoring System (ICEMS), to assess surgical bimanual performance at 0.2-s intervals. A long-short term memory network was built using neurosurgeon and student perfo ...[more]

PMID: 35473961

Similar Datasets

Project description:Background and aimsTraditional apprenticeship-based surgical training presents with challenges, especially in acute scenarios. Simulation provides the current standard of facilitating surgical training in a low-risk environment but is restricted by limited accessibility and high costs. Virtual reality (VR) offers immersive three-dimensional computer-generated training scenarios and can connect users from various locations. We aimed to compare the performance of junior doctors to manage an acute surgical scenario using VR and mannequin-based simulation. We hypothesised that VR would be as effective as mannequin-based simulation in performance outcomes.MethodsThis multicentre, randomised controlled pilot study was conducted with eighteen junior doctor volunteers (Foundation and Core Trainee Year 1). Ten were randomly allocated to VR and eight to mannequin-based simulation. Participants completed questionnaires and a 15-min pneumothorax scenario. Quantitative metrics included overall score, time-to-critical decisions, and academic buoyancy scores (ABS). Qualitative metrics included participants' likes and dislikes of their allocated simulation modality.ResultsVR participants scored significantly higher than mannequin-based simulation participants in overall scores (74.30% (SD ± 5.08%) vs. 59.75% (SD ± 10.14) (p = 0.04)), and technical skills aspects (77.20% (SD ± 8.01%) vs. 65.00% (SD ± 8.21%) (p = 0.01)). Mannequin-based simulation participants initiated critical decisions faster and demonstrated a trend towards a faster mean time-to-completion (p = 0.06). ABS scores increased for both study groups, though was only significant for VR participants (p ≤ 0.01). VR participants liked how VR fostered independent learning but disliked the formulaic content and impaired communication-learning compared to mannequin-based simulation.ConclusionBoth VR and mannequin-based simulation training are effective in training junior doctors in acute surgical scenarios but present different educational benefits. Future research should recruit a larger sample size for a full comparative randomised controlled trial.

Dataset Information

Continuous monitoring of surgical bimanual expertise using deep neural networks in virtual reality simulation.

Publications

Continuous monitoring of surgical bimanual expertise using deep neural networks in virtual reality simulation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets