Recent advances (2022-2024) in eye-tracking for Parkinson's disease: a promising tool for diagnosing and monitoring symptoms.

Introduction: Parkinson's disease (PD) is one of the most prevalent neurodegenerative disorders, characterized by both motor and non-motor symptoms, including impaired oculomotor functions. Eye-tracking technology, a precise and non-invasive method for measuring eye movements, has emerged as a promising tool for diagnosing and monitoring PD progression. This systematic review evaluates the effectiveness of eye-tracking in assessing motor and cognitive alterations associated with PD. Methods: A systematic review of the literature was conducted using PubMed, Web of Science, Embase, Scopus and Cochrane Library databases to identify studies applying eye-tracking to assess oculomotor functions in PD patients. Only articles published from 2022 to 2024 were considered. Results: A total of 10809 studies were identified. 18 met the inclusion criteria and were included. Findings indicate that eye-tracking may offer valuable insights into both oculomotor and cognitive dysfunctions. Specific metrics such as saccade velocity, fixation duration, and pupil size have been correlated with disease severity. Recent technological advancements, including the integration of machine learning (ML) and virtual reality (VR), have further enhanced the diagnostic accuracy and scalability of eye-tracking methods. Conclusion: In the past 3 years, eye-tracking has rapidly advanced, particularly through its integration with ML and VR. These innovations have enhanced precision, accessibility, and clinical relevance. Emerging evidence also supports its potential to detect eye movement biomarkers associated with disease stage, motor subtypes, and cognitive decline. This review synthesizes the latest findings, underscoring the role of eye-tracking as a scalable and personalized tool for PD assessment. However, further efforts are needed to address challenges such as protocol standardization and device variability. Systematic review registration: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42024602802, identifier CRD42024602802.