Journal article
Prediction of radiological decision errors from longitudinal analysis of gaze and image features
Artificial intelligence in medicine, Vol.160, 103051
12/12/2024
DOI: 10.1016/j.artmed.2024.103051
PMID: 39708677
Abstract
Medical imaging, particularly radiography, is an indispensable part of diagnosing many chest diseases. Final diagnoses are made by radiologists based on images, but the decision-making process is always associated with a risk of incorrect interpretation. Incorrectly interpreted data can lead to delays in treatment, a prescription of inappropriate therapy, or even a completely missed diagnosis. In this context, our study aims to determine whether it is possible to predict diagnostic errors made by radiologists using eye-tracking technology. For this purpose, we asked 4 radiologists with different levels of experience to analyze 1,000 images covering a wide range of chest diseases. Using eye-tracking data, we calculated the radiologists’ gaze fixation points and generated feature vectors based on this data to describe the radiologists’ gaze behavior during image analysis. Additionally, we emulated the process of revealing the read images following radiologists’ gaze data to create a more comprehensive picture of their analysis. Then we applied a recurrent neural network to predict diagnostic errors. Our results showed a 0.7755 ROC AUC score, demonstrating a significant potential for this approach in enhancing the accuracy of diagnostic error recognition.
•Investigated the novel field of radiologists’ decision error detection for longitudinal eye movements.•Proposed an AI framework that mimics human image reading by employing gaze features, longitudinally-revealed images, GRU and CNNs.•Validated the proposed framework on 4000 X-ray readings performed by four radiologists.•Used AI to pinpoint image reading patterns associated with radiologist reading errors.
Details
- Title: Subtitle
- Prediction of radiological decision errors from longitudinal analysis of gaze and image features
- Creators
- Anna Anikina - University of CopenhagenDiliara Ibragimova - Kazan Federal UniversityTamerlan Mustafaev - University of PittsburghClaudia Mello-Thoms - University of IowaBulat Ibragimov - Kazan State Medical University
- Resource Type
- Journal article
- Publication Details
- Artificial intelligence in medicine, Vol.160, 103051
- Publisher
- Elsevier B.V
- DOI
- 10.1016/j.artmed.2024.103051
- PMID
- 39708677
- ISSN
- 0933-3657
- eISSN
- 1873-2860
- Grant note
- NFF20OC0062056 / Novo Nordisk Foundation 1R01CA259048 / National Institue of Health
- Language
- English
- Date published
- 12/12/2024
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology
- Record Identifier
- 9984758187902771
Metrics
5 Record Views