Bringing prevost's sign into the third dimension: Artificial intelligence estimation of conjugate gaze adjusted length (CGAL) and correlation with acute ischemic stroke

Hillel S. Maresky*, Joseph M. Rootman, Miriam M. Klar, Max Levitt, Alexander P. Kossar, David Zucker, Michael Glazier, Shani Kalmanovich-Avnery, Richard Aviv, Birgit Ertl-Wagner, Sigal Tal

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Conjugate gaze deviation is associated with acute ischemic stroke (AIS), although previously only measured on a 2D plane. The current study evaluates 3D imaging efficacy to assess conjugate gaze deviation and correlate direction and strength of deviation to neuro-clinical findings.A retrospective analysis of 519 patients who had CT scans for suspected AIS at our institution. Direction and angle of eye deviation were calculated based on 2D axial images. Volumetric reconstruction of CT scans allowed for calculation of 3D conjugate gaze adjusted length (CGAL). Angle, direction, and vector strength of both 2D and 3D scans were calculated by an artificial intelligence algorithm and tested for agreement with hemispheric ischemia location. CGAL measurements were correlated to NIHSS scores. Follow up MRI data was used to evaluate the sensitivity and specificity of CGAL in the identification of AIS.The final analysis included 122 patients. A strong agreement was found between 3D gaze direction and hemispheric ischemia location. CGAL measurements were highly correlated with NIHSS score (r=.72, P=.01). A CGAL >0.25, >0.28, and >0.35 exhibited a sensitivity of 91%, 86%, and 82% and specificity of 66%, 89%, and 89%, respectively, in AIS identification. A CGAL >0.28 has the best sensitivity-specificity balance in the identification of AIS. A CGAL >0.25 has the highest sensitivity.Given CED's correlation with NIHSS score a 1/4 deviation in the ipsilateral direction is a sensitive ancillary radiographic sign to assist radiologists in making a correct diagnosis even when not presented with full clinical data.

Original languageEnglish
Pages (from-to)E23330
JournalMedicine (United States)
Volume99
Issue number49
DOIs
StatePublished - 4 Dec 2020

Keywords

  • acute ischemic stroke
  • artificial intelligence
  • conjugate eye deviation
  • conjugate gaze adjusted length (CGAL)
  • prevost sign

Fingerprint

Dive into the research topics of 'Bringing prevost's sign into the third dimension: Artificial intelligence estimation of conjugate gaze adjusted length (CGAL) and correlation with acute ischemic stroke'. Together they form a unique fingerprint.

Cite this