Page 47 - Read Online

Page 451 Goyal et al. Art Int Surg. 2025;5:450-64 https://dx.doi.org/10.20517/ais.2024.108

of surgical phases, anatomical structures, and instruments, particularly in transabdominal preperitoneal (TAPP),
total extraperitoneal (TEP), and robotic inguinal hernia repair (RIHR). This systematic review evaluates the
accuracy, applicability, and clinical impact of AI-based systems in real-time surgical phase recognition during IHR.

Methods: Following PRISMA 2020 guidelines and PROSPERO registration (CRD42024621178), a systematic
search of PubMed, Scopus, Web of Science, Embase, Cochrane Library, and ScienceDirect was conducted on
November 12, 2024. Studies utilizing AI models for real-time video-based surgical phase recognition in minimally
invasive IHR (TAPP, TEP, and RIHR) were included. The screening process, data extraction task, and quality
assessment using NOS (Newcastle-Ottawa Scale) were performed by three independent reviewers. Primary
outcomes were AI performance metrics (accuracy, F1-score, precision, recall, and latency), and secondary
outcomes included clinical phase recognition performance.

Results: Out of 903 records, six studies (2022-2024) were included, involving laparoscopic (n = 4) and robotic-
assisted (n = 2) IHR from the United States (n = 2), France (n = 2), and Greece (n = 1). A total of 774 videos (25-
619 per study) underwent pre-processing (frame extraction or down-sampling). Annotation tools included CVAT,
SuperAnnotate, and manual labeling. AI models (VTN, DETR, ResNet-50, YOLOv8) demonstrated accuracy
between 74% and > 87%, with YOLOv8 achieving the highest F1-score (82%). Risk of bias was moderate to high,
with Fleiss’ kappa for inter-rater agreement at 0.82 (selection) and 0.49 (comparability).

Conclusion: AI and ML models demonstrate significant potential in achieving real-time surgical phase recognition
during minimally invasive IHR. Despite promising accuracies, challenges such as heterogeneity in model
performance, reliance on annotated datasets, and the need for real-time validation persist. Standardized
benchmarks, multicenter studies, and hardware advancements will be essential to fully integrate AI into surgical
workflows, improving surgical training, technical performance, and patient outcomes.
Keywords: Artificial intelligence, inguinal hernia repair, real-time surgical phase recognition, minimally invasive
surgery, AI performance metrics

INTRODUCTION
The revolutionary adoption of artificial intelligence (AI) in surgical applications has grown significantly in
recent years, offering transformative potential across a variety of procedures. The use of AI in medicine
dates back to the 1970s, with early systems assisting in bacterial detection, decision making, and imaging
[1,2]
analysis . As AI models and programming advanced, their application in surgical practice became
increasingly feasible. In recent literature, the use of AI has been appraised to be valuable in areas such as
[3,4]
colorectal surgery, laparoscopic cholecystectomy, and cardiac surgery . However, most of these
procedures utilize AI in specific aspects of their interventions, with notable effectiveness in assessing
[3-5]
complication risks, avoiding intraoperative errors, and predicting mortality outcomes .
An emerging field that has recently seen an increase in the incorporation of AI technologies is inguinal
[6]
hernia repair (IHR), the most prevalent groin repair procedure . By training AI models using compiled
videos and imaging data to identify specific steps, anatomical structures, and instruments during
procedures , medical teams can leverage real-time assistance to enhance decision making, improve surgical
[7]
[8,9]
efficiency, and support education and workflow optimization . This advantage is novel and has recently
been explored in studies across different AI systems.
Current research presents this variety of AI models developed to monitor and assist in different bilateral
and unilateral [8,10] IHR techniques, including transabdominal preperitoneal (TAPP), total extraperitoneal
(TEP), and robotic inguinal hernia repairs (RIHR) [8-10] . These AI applications optimize procedural efficiency