Differentiating Surgeons' Expertise solely by Eye Movement Features

Benedikt Hosp, Myat Su Yin, Peter Haddawy, Ratthapoom Watcharopas, Paphon Sa-Ngasoongsong, Enkelejda Kasneci

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

Medical schools are increasingly seeking to use objective measures to assess surgical skills. This extends even to perceptual skills, which are particularly important in minimally invasive surgery. Eye tracking provides a promising approach to obtaining such objective metrics of visual perception. In this work, we report on results of a cadaveric study of visual perception during shoulder arthroscopy. We present a model for classifying surgeons into three levels of expertise using only eye movements. The model achieves a classification accuracy of 84.44% using only a small set of selected features. We also examine and characterize the changes in visual perception metrics between the different levels of expertise, forming a basis for development of a system for objective assessment.

Original languageEnglish
Title of host publicationICMI 2021 Companion - Companion Publication of the 2021 International Conference on Multimodal Interaction
PublisherAssociation for Computing Machinery, Inc
Pages371-375
Number of pages5
ISBN (Electronic)9781450384711
DOIs
StatePublished - 18 Oct 2021
Externally publishedYes
Event23rd ACM International Conference on Multimodal Interaction, ICMI 2021 - Virtual, Online, Canada
Duration: 18 Oct 202122 Oct 2021

Publication series

NameICMI 2021 Companion - Companion Publication of the 2021 International Conference on Multimodal Interaction

Conference

Conference23rd ACM International Conference on Multimodal Interaction, ICMI 2021
Country/TerritoryCanada
CityVirtual, Online
Period18/10/2122/10/21

Keywords

  • diagnostic
  • eye
  • machine learning
  • model
  • surgeon
  • tracking

Fingerprint

Dive into the research topics of 'Differentiating Surgeons' Expertise solely by Eye Movement Features'. Together they form a unique fingerprint.

Cite this