Central retinal artery occlusion - detection score

Abstract

Purpose: To investigate the sensitivity and specificity of central retinal artery occlusion (CRAO)-Detection Score in diagnosing CRAO via questionnaire and without fundoscopy.

Methods: This prospective study enrolled 176 emergency patients suffering from acute visual loss, of whom 38 were suffering from CRAO. Before conducting any examination, we administered our questionnaire containing six questions, followed by a thorough ophthalmologic examination to make the diagnosis. Statistical analysis involved a LASSO penalised multivariate logistic regression model.

Results: Our receiver operating characteristic (ROC) analysis based on a LASSO penalised multivariate logistic regression model showed an area under the curve (AUC) of 0.9 - three out of six questions were selected by LASSO. Interestingly, the unweighted ROC analysis of only two questions (Short CRAO-Detection Score) yielded similar results with an AUC of 0.88. The short CRAO-Detection Score of 2 yielded 14% (4/28) false positive patients.

Conclusion: This prospective study demonstrates that a high percentage of CRAO patients are detectable with a questionnaire. The CRAO-Detection Score might be used to triage patients suffering acute visual loss, which is important as intravenous fibrinolysis seem to be time-dependent to be effective.

Keywords: CRAO; central retinal artery occlusion; questionnaire; stroke; triage.

Figure 1

ROC curve for questions one, two, three, four, five, and six. AUC-area under the curve.

Figure 2

ROC curve for the LASSO regression score. AUC–area under the curve.

Figure 3

ROC curve for questions one and four. AUC-area under the curve.