Mahdi Norouzi, Rahele Kafieh, Paul Chazot, Daniel T Smith, Zahra Amini
{"title":"Insights from the eyes: a systematic review and meta-analysis of the intersection between eye-tracking and artificial intelligence in dementia.","authors":"Mahdi Norouzi, Rahele Kafieh, Paul Chazot, Daniel T Smith, Zahra Amini","doi":"10.1080/13607863.2025.2464704","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>Dementia can change oculomotor behavior, which is detectable through eye-tracking. This study aims to systematically review and conduct a meta-analysis of current literature on the intersection between eye-tracking and artificial intelligence (AI) in detecting dementia.</p><p><strong>Method: </strong>PubMed, Embase, Scopus, Web of Science, Cochrane, and IEEE databases were searched up to July 2023. All types of studies that utilized eye-tracking and AI to detect dementia and reported the performance metrics, were included. Data on the dementia type, performance, artificial intelligence, and eye-tracking paradigms were extracted. The registered protocol is available online on PROSPERO (ID: CRD42023451996).</p><p><strong>Results: </strong>Nine studies were finally included with a sample size ranging from 57 to 583 participants. Alzheimer's disease (AD) was the most common dementia type. Six studies used a machine learning model while three used a deep learning model. Meta-analysis revealed the accuracy, sensitivity, and specificity of using eye-tracking and artificial intelligence in detecting dementia, 88% [95% CI (83%-92%)], 85% [95% CI (75%-93%)], and 86% [95% CI (79%-93%)], respectively.</p><p><strong>Conclusion: </strong>Eye-tracking coupled with AI revealed promising results in terms of dementia detection. Further studies must incorporate larger sample sizes, standardized guidelines, and include other dementia types.</p>","PeriodicalId":55546,"journal":{"name":"Aging & Mental Health","volume":" ","pages":"1-9"},"PeriodicalIF":2.8000,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Aging & Mental Health","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/13607863.2025.2464704","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"GERIATRICS & GERONTOLOGY","Score":null,"Total":0}
引用次数: 0
摘要
目的痴呆症会改变眼球运动行为，而眼球运动行为可以通过眼动追踪检测到。本研究旨在对眼动追踪和人工智能（AI）在检测痴呆症方面的交叉研究进行系统回顾和荟萃分析：方法：检索了截至 2023 年 7 月的 PubMed、Embase、Scopus、Web of Science、Cochrane 和 IEEE 数据库。纳入了利用眼动追踪和人工智能检测痴呆症并报告了性能指标的各类研究。提取了有关痴呆症类型、性能、人工智能和眼动追踪范例的数据。注册协议可在 PROSPERO（ID：CRD42023451996）上在线查阅：最终纳入了九项研究，样本量从 57 到 583 人不等。阿尔茨海默病（AD）是最常见的痴呆类型。六项研究使用了机器学习模型，三项使用了深度学习模型。元分析显示，使用眼动追踪和人工智能检测痴呆症的准确性、敏感性和特异性分别为88% [95% CI (83%-92%)]、85% [95% CI (75%-93%)]和86% [95% CI (79%-93%)]：眼动跟踪与人工智能相结合，在痴呆症检测方面取得了令人鼓舞的成果。进一步的研究必须纳入更大的样本量、标准化指南，并包括其他痴呆类型。
Insights from the eyes: a systematic review and meta-analysis of the intersection between eye-tracking and artificial intelligence in dementia.
Objectives: Dementia can change oculomotor behavior, which is detectable through eye-tracking. This study aims to systematically review and conduct a meta-analysis of current literature on the intersection between eye-tracking and artificial intelligence (AI) in detecting dementia.
Method: PubMed, Embase, Scopus, Web of Science, Cochrane, and IEEE databases were searched up to July 2023. All types of studies that utilized eye-tracking and AI to detect dementia and reported the performance metrics, were included. Data on the dementia type, performance, artificial intelligence, and eye-tracking paradigms were extracted. The registered protocol is available online on PROSPERO (ID: CRD42023451996).
Results: Nine studies were finally included with a sample size ranging from 57 to 583 participants. Alzheimer's disease (AD) was the most common dementia type. Six studies used a machine learning model while three used a deep learning model. Meta-analysis revealed the accuracy, sensitivity, and specificity of using eye-tracking and artificial intelligence in detecting dementia, 88% [95% CI (83%-92%)], 85% [95% CI (75%-93%)], and 86% [95% CI (79%-93%)], respectively.
Conclusion: Eye-tracking coupled with AI revealed promising results in terms of dementia detection. Further studies must incorporate larger sample sizes, standardized guidelines, and include other dementia types.
期刊介绍：
Aging & Mental Health provides a leading international forum for the rapidly expanding field which investigates the relationship between the aging process and mental health. The journal addresses the mental changes associated with normal and abnormal or pathological aging, as well as the psychological and psychiatric problems of the aging population. The journal also has a strong commitment to interdisciplinary and innovative approaches that explore new topics and methods.
Aging & Mental Health covers the biological, psychological and social aspects of aging as they relate to mental health. In particular it encourages an integrated approach for examining various biopsychosocial processes and etiological factors associated with psychological changes in the elderly. It also emphasizes the various strategies, therapies and services which may be directed at improving the mental health of the elderly and their families. In this way the journal promotes a strong alliance among the theoretical, experimental and applied sciences across a range of issues affecting mental health and aging. The emphasis of the journal is on rigorous quantitative, and qualitative, research and, high quality innovative studies on emerging topics.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
