Publication date: Available online 2 July 2019
Source: Journal of Surgical Education
Author(s): Marc Levin, Tyler McKechnie, Shuja Khalid, Teodor P. Grantcharov, Mitchell Goldenberg
Objective
The goal of the current study is to systematically review the literature addressing the use of automated methods to evaluate technical skills in surgery.
Background
The classic apprenticeship model of surgical training includes subjective assessments of technical skill. However, automated methods to evaluate surgical technical skill have been recently studied. These automated methods are a more objective, versatile, and analytical way to evaluate a surgical trainee's technical skill.
Study Design
A literature search of the Ovid Medline, Web of Science, and EMBASE Classic databases was performed. Articles evaluating automated methods for surgical technical skill assessment were abstracted. The quality of all included studies was assessed using the Medical Education Research Study Quality Instrument.
Results
A total of 1715 articles were identified, 76 of which were selected for final analysis. An automated methods pathway was defined that included kinetics and computer vision data extraction methods. Automated methods included tool motion tracking, hand motion tracking, eye motion tracking, and muscle contraction analysis. Finally, machine learning, deep learning, and performance classification were used to analyse these methods. These methods of surgical skill assessment were used in the operating room and simulated environments. The average Medical Education Research Study Quality Instrument score across all studies was 10.86 (maximum score of 18).
Conclusions
Automated methods for technical skill assessment is a growing field in surgical education. We found quality studies evaluating these techniques across many environments and surgeries. More research must be done to ensure these techniques are further verified and implemented in surgical curricula.
Δεν υπάρχουν σχόλια:
Δημοσίευση σχολίου