Assessing the Performance of a Novel Bayesian Algorithm at Point of Care for Red Eye Complaints

Abstract

The current diagnostic aids for red eye are static flowcharts that do not provide dynamic, stepwise workups. The diagnostic accuracy of a novel dynamic Bayesian algorithm for red eye was tested. Fifty-seven patients with red eye were evaluated by an emergency medicine physician who completed a questionnaire about symptoms/findings (without requiring extensive slit lamp findings). An ophthalmologist then attributed an independent “gold-standard diagnosis”. The algorithm used questionnaire data to suggest a differential diagnosis. The referrer’s diagnostic accuracy was 70.2%, while the algorithm’s accuracy was 68.4%, increasing to 75.4% with the algorithm’s top two diagnoses included and 80.7% with the top three included. In urgent cases of red eye (n = 26), the referrer diagnostic accuracy was 76.9%, while the algorithm’s top diagnosis was 73.1% accurate, increasing to 84.6% (top two included) and 88.5% (top three included). The algorithm’s sensitivity for urgent cases was 76.9% (95% CI: 56–91%) using its top diagnosis, with a specificity of 93.6% (95% CI: 79–99%). This novel algorithm provides dynamic workups using clinical symptoms, and may be used as an adjunct to clinical judgement for triaging the urgency of ocular causes of red eye.