e-Posters
AW Khalid, D Rawaf, M ElBahnasawi, C Ludick, M Harris, M Sheikh, T Luqman, G Beghal, J Toms, DSSR Palagani, K Pouris, O Musbahi, M Nurek, M Vella-Baldachino, O Kostopoulou, C Hing, A Bottle, J Cobb, G Jones, K Pouris, O Musbahi, S Hadjixenophontos, D Leon, I Soteriou, G Jones

TL;DR
This paper evaluates the use of augmented reality (AR) in surgical training and explores the capabilities of AI tools like ChatGPT in medical decision-making and literature reviews.
Contribution
The study introduces a novel AR-based surgical simulator evaluated across Kirkpatrick's pyramid levels and assesses ChatGPT's potential in medical literature reviews and surgical decision-making.
Findings
AR-based surgical training significantly improved trainees' performance metrics like completion time and distance travelled.
ChatGPT demonstrated high PPV in deciding between UKR and TKR, showing substantial agreement with surgeons.
AI models like ChatGPT can generate readable clinic letters but have limitations in providing accurate references for literature reviews.
Abstract
Novel augmented-reality (AR)-based surgical simulator offers promise in training, yet its comprehensive evaluation across Kirkpatrick's pyramid levels is pivotal. Kirkpatrick's pyramid, a four-level framework, assesses training effectiveness. A holistic assessment of AR-based surgical simulators across Kirkpatrick's levels was executed through multiple studies encompassing four main modalities. A pilot study (n=11) and a multi-centre study (n=6) scrutinised junior trainees' performance in appendectomies and vaginal cuff closures, emphasising completion time and distance travelled metrics (Level 2). A concurrent study evaluated self-confidence scores pre- and post-AR training, showcasing a mean improvement of 3.82 (Likert, p=0.018), indicating enhanced morale and skill translatability (Level 1 and 3). Health economics review exhibited potential cost savings (Level 4). An independent…
Genes, proteins, chemicals, diseases, species, mutations and cell lines named across the full text — each resolved to its canonical identifier and authoritative record.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
