An Eye-Tracking Based Machine Learning Model Towards the Prediction of Visual Expertise for Electrocardiogram Interpretation

Mohammed Tahri Sqalli*, Dena Al-Thani, Mohamed B. Elshazly, Mohammed Al-Hijji, Alaa Alahmadi, Yahya Sqalli Houssaini

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

The electrocardiogram, known as the ECG or EKG, is considered among the mostly used medical diagnostic tests worldwide. Despite the test’s prevalence in the healthcare sector, there still exist gaps into training medical practitioners become skilled and efficient ECG interpreters. Moreover, this also brings the challenge of assessing the expertise of those practitioners. This is primarily due to the difficulty of assessing visual expertise. Visual expertise is the skill of interpreting images relating to a certain technical field. Due to the limited quantitative research methodologies that could not capture this subtle skill during the previous two decades, a limited number of models are being conceptualized and assessed. In addition, automated ECG interpretation models based on artificial intelligence are still not accurate enough to be fully deployed in the medical field. This therefore leaves only one choice, which is to focus on improving on methodologies to train and assess medical practitioners’ visual expertise. This approach will contribute towards increasing the accuracy of ECG interpretations within medical institutions by forming competent medical staff. In this paper, we present a road map for the development of an eye-tracking based machine learning model that leads towards the prediction of visual expertise within medical practitioners. To develop the model, we built on top of our previously conducted research that aimed at understanding the differences in visual patterns within medical practitioners with different expertise levels. The developed model could predict the expertise level of the ECG interpreter with an accuracy of 94.08%. This is thanks to the eye movement patterns of the participant.

Original languageEnglish
Title of host publicationMedical Imaging and Computer-Aided Diagnosis - Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis MICAD 2022
EditorsRuidan Su, Yudong Zhang, Han Liu, Alejandro F Frangi
PublisherSpringer Science and Business Media Deutschland GmbH
Pages305-315
Number of pages11
ISBN (Print)9789811667749
DOIs
Publication statusPublished - 2023
EventInternational Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022 - Leicester, United Kingdom
Duration: 20 Nov 202221 Nov 2022

Publication series

NameLecture Notes in Electrical Engineering
Volume810 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceInternational Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2022
Country/TerritoryUnited Kingdom
CityLeicester
Period20/11/2221/11/22

Keywords

  • ECG
  • ECG interpretation
  • Electrocardiogram
  • Eye-tracking
  • Human-computer interaction

Fingerprint

Dive into the research topics of 'An Eye-Tracking Based Machine Learning Model Towards the Prediction of Visual Expertise for Electrocardiogram Interpretation'. Together they form a unique fingerprint.

Cite this