眼动追踪在神经精神疾病中的跨疾病整合与个性化诊疗研究进展

Research Advances in Eye Movement Tracking for Cross-Disorder Integration and Personalized Diagnosis and Treatment in Neuropsychiatric Disorders

摘要: 背景：神经精神疾病是一类涉及神经系统结构和功能障碍的复杂疾病，其发病机制和临床表现具有多样性。目前，该疾病缺乏精准的诊断手段，临床诊断及预后评估很大程度上依赖于医生的临床主观判断。眼动追踪是一种新兴的技术，为神经精神疾病的诊断提供了客观、可量化且无创的评估方法，同时在探索疾病生物标志物方面展现出独特的价值与潜力。目标：本综述旨在探讨眼动追踪技术作为探索神经精神疾病生物学标志的潜力，并结合技术设备的发展历程，展望其在临床个性化诊疗中的应用。方法：全面的文献检索工作着眼于眼动追踪在神经精神疾病领域的研究与应用。通过PubMed、CNKI、Web of Science确定了相关出版物，使用关键术语，例如“神经退行性疾病中的眼球运动”、“眼动的生物标志物”等。还纳入了微型化硬件和基于AI的智能化干预措施的研究。结果：现有研究利用眼动追踪技术发现扫视速度与注视分散度可作为判断神经精神疾病的潜在标志物。此外，眼动追踪技术中微型化硬件的应用以及AI智能化解析的融入，为该疾病的诊断与治疗提供了广阔的应用前景。沉浸式VR技术与机器学习在此技术中的不断发展有助于推动临床个性化诊疗。结论：眼动追踪技术以可量化、无创式的个性化诊疗为切入角度，未来可在眼动生物学标志的挖掘以及AI模型在多模式治疗策略中的应用进展方面开展深入研究。

Abstract: Background: Neuropsychiatric disorders represent a spectrum of complex conditions involving structural and functional impairments of the neural system, characterized by heterogeneous pathogenetic mechanisms and clinical manifestations. Current diagnostic approaches lack precision, with clinical diagnosis and prognostic evaluation predominantly reliant on subjective physician assessment. Eye movement tracking (EMT) emerges as a novel technology providing objective, quantifiable, and non-invasive evaluation for neuropsychiatric disorders, demonstrating unique value and potential in discovering disease biomarkers. Objective: This review aims to explore EMT’s capability in identifying biological biomarkers for neuropsychiatric disorders and project its clinical application toward personalized diagnosis and treatment through technological evolution. Methods: A comprehensive literature search focused on the research and application of EMT in the field of neuropsychiatric disorders. Relevant publications were identified through PubMed, CNKI, and Web of Science using key terms such as “eye movements in neurodegenerative diseases”, “eye movement biomarkers”, etc. Studies on miniaturized hardware and AI-based intelligent intervention measures were also included. Results: Existing studies utilized EMT technology to identify saccadic velocity and fixation dispersion as potential biomarkers for neuropsychiatric conditions. Furthermore, the application of miniaturized EMT hardware and the integration of AI-powered analytics in EMT technology offer broad prospects for the diagnosis and treatment of these disorders. The ongoing development of immersive VR technology and machine learning within this field is expected to further advance personalized clinical diagnosis and treatment. Conclusion: EMT, characterized by its quantifiable and non-invasive approach to personalized diagnosis and treatment, holds promise for future in-depth research focusing on the discovery of eye movement biomarkers and the application of AI models in multimodal treatment strategies.