Back

Approbation of the Keen Eye Computer-Based Method for Diagnosing Visual Neglect

Vasyura, E. V.; Kovyazina, M. S.; Stepanov, G. K.; Russkikh, O. A.; Terentiy, D. D.; Propustina, V. A.; Skvortsov, A. A.; Varako, N. A.; Vasilyeva, S. A.; Daminov, V. D.; Zinchenko, Y. P.

2025-04-23 neurology
10.1101/2025.04.23.25326114 medRxiv
Show abstract

This study focuses on the approbation of the Keen Eye method for diagnosing visual neglect. A total of 102 patients with right hemisphere damage participated in the study, 38 of whom were diagnosed with neglect. The primary goal was to assess the effectiveness of Keen Eye in comparison with traditional paper-based tests. Keen Eye is based on a dual-task paradigm, integrating target identification and visual stimulus localization tasks, with stimuli presented in different areas of the screen. The results demonstrated the high diagnostic accuracy of the method, enabling the detection of covert forms of neglect. The study showed that the method allows for the assessment of both horizontal and vertical neglect severity and the identification of patients with neglect combined with non-lateralized attention deficits. The method exhibited high criterion and construct convergent validity and holds significant potential for clinical application.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.