Pupil diameter changes reflect difficulty and diagnostic accuracy during medical image interpretation.

Tad T Brunyé,Joann G Elmore,Marianna D Eddy,Donald L Weaver,Ezgi Mercan,Kimberly H Allison

doi:10.1186/s12911-016-0322-3

Abstract

BackgroundNo automated methods exist to objectively monitor and evaluate the diagnostic process while physicians review computerized medical images. The present study tested whether using eye tracking to monitor tonic and phasic pupil dynamics may prove valuable in tracking interpretive difficulty and predicting diagnostic accuracy.MethodsPathologists interpreted digitized breast biopsies varying in diagnosis and rated difficulty, while pupil diameter was monitored. Tonic diameter was recorded during the entire duration of interpretation, and phasic diameter was examined when the eyes fixated on a pre-determined diagnostic region during inspection.ResultsTonic pupil diameter was higher with increasing rated difficulty levels of cases. Phasic diameter was interactively influenced by case difficulty and the eventual agreement with consensus diagnosis. More difficult cases produced increases in pupil diameter, but only when the pathologists’ diagnoses were ultimately correct. All results were robust after adjusting for the potential impact of screen brightness on pupil diameter.ConclusionsResults contribute new understandings of the diagnostic process, theoretical positions regarding locus coeruleus-norepinephrine system function, and suggest novel approaches to monitoring, evaluating, and guiding medical image interpretation.

Highlights

No automated methods exist to objectively monitor and evaluate the diagnostic process while physicians review computerized medical images
The present study extends this research to examine whether pupil dilation during visual image interpretation might reveal reliable differences based on case difficulty, diagnostic category of the biopsy findings, or the convergence with consensus reference diagnoses
We aim to test both of these hypotheses by using an eye tracking system to monitor pupil diameter while pathologists interpret and diagnose digitized breast biopsies

Summary

Introduction

No automated methods exist to objectively monitor and evaluate the diagnostic process while physicians review computerized medical images. Interpreting medical images involves dynamic interactions between the perception of visual features and the application of knowledge This visual interpretive process is fundamental to arriving at accurate diagnoses across several medical specialties including pathology, radiology, and dermatology. Research on whole slide images has demonstrated that novice and expert pathologists move their eyes differently, focus on different elements of the visual image, and often arrive at very different diagnostic decisions [1,2,3]. These new metrics make it possible to objectively assess student progress in innovative ways without directly probing subjective knowledge.

Objectives

Methods

Results

Conclusion