Detecting early cognitive decline from saccades in natural ball game viewing

Abstract

Cognitive decline (CD) is a hallmark symptom of many neurodegenerative diseases, and in severe cases, it progresses to cognitive dysfunction and a loss of independent daily functioning. Eye movement interaction (EMI) has shown promise in detecting early signs of CD, but its applications remain largely confined to clinical settings, limiting integration into everyday life. In response, this paper proposes a novel method based on naturalistic EMI for the prediagnosis of CD, leveraging sports streaming to induce saccades and using ball movements as dynamic stimuli to uncover early neural dysfunction. Through a pilot and empirical study, we demonstrate that ball games can effectively elicit saccades, and our algorithm can accurately extract batting saccades to distinguish between the healthy control group (HCG) and the cognitive decline group (CDG). In this study with 60 participants, the accuracy of recognizing CDG in natural, unmarked game viewing was 0.7333 at best, and reached 0.8833 when semi-natural random flashing cues were introduced on balls. These findings illustrate the potential for seamlessly integrating naturalistic EMI-based prediagnosis into everyday interactions.