JMIR Publications

ABSTRACT

Background:

Artificial intelligence (AI) has introduced novel opportunities for assessment and evaluation in surgical training, offering potential improvements that could surpass traditional educational methods.

Objective:

This scoping review explores the integration of AI in surgical training, assessment, and evaluation with the objective of determining how AI technologies can enhance trainees’ learning paths and performance by incorporating data-driven insights and predictive analytics. In addition, this review examines the current state and applications of AI algorithms in this field, identifying potential areas for future research.

Methods:

Following the Systematic Reviews and Meta-Analyses extension for scoping reviews (PRISMA-ScR) guidelines, PubMed, Scopus, and Web of Science were searched for studies published between 2020 and March 18, 2024. Eligibility criteria included full-text articles in English that investigated the application of AI in surgical training, assessment, or evaluation; non-English texts, reviews, preprints, and studies not addressing AI in surgical education were excluded. After duplicate removal and screening, 56 studies were included. Data were structured by categorizing studies according to surgical procedure, AI technique, and training setup. Results were synthesized narratively and summarized in frequency tables.

Results:

From 1,400 initial records, 56 studies met the inclusion criteria. Most were journal articles (84% - 47 out of 56), with the remainder conference papers (16% - 9 out of 56). AI was most frequently applied in minimally invasive surgery (27% - 15 out of 56), neurosurgery (20% - 11 out of 56), and laparoscopy (16% - 9 out of 56). Common techniques included machine learning (20% - 11 out of 56), clustering (14% - 8 out of 56), deep learning (11% - 6 out of 56), convolutional neural networks (11% - 6 out of 56), and support vector machines (11% - 6 out of 56). Training setups were dominated by simulation platforms (33% - 19 out of 56) and box-trainers (24% - 13 out of 56), followed by surgical video analysis (16% - 9 out f 56) and robotic systems such as the da Vinci platform (13% - 7 out of 56). Across studies, AI-enhanced training environments provided automated skill assessment, personalized feedback, and adaptive learning trajectories, with several reporting improvements in trainees’ learning curves and technical proficiency. However, heterogeneity in study design and outcome measures limited comparability, and algorithmic transparency was often lacking.

Conclusions:

The use of AI in surgical training demonstrates the potential to enhance skill acquisition and support more efficient, personalized, and adaptive learning pathways. Despite encouraging findings, limitations of the current evidence include small sample sizes, lack of standardized evaluation metrics, and insufficient external validation of AI models. Future studies should focus on clarifying AI methodologies, improving reproducibility, and developing scalable, simulation-based solutions aligned with global education goals.