Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

How do network structures of depressive symptoms differ between asian patients with bipolar depression and those with unipolar depression?

Asian journal of psychiatry·2026

Same author

Is Richard Baxter's Melancholia Still Relevant Today?: Comparative Network Structures of Depressive Symptoms in Asian Individuals With Guilt-Rich and Guilt-Free Depression.

Psychiatry investigation·2026

Same author

Does tibial sclerosis severity influence bone resorption risk following total knee arthroplasty? : finite element analysis considering implant design and surgical technique.

Bone & joint research·2026

Same author

EEG-based biomarker for the identification of mild cognitive impairment via coherency analysis and iterative dynamic time warping.

Scientific reports·2026

Same author

Comparative Network Structures of Hikikomori (Social Withdrawal) Symptoms in Korean and Japanese Psychiatric Patients Prescribed Antidepressants: Findings From the Research on Asian Psychotropic Patterns for Antidepressants, Phase 3.

Journal of Korean medical science·2026

Same author

Combining EEG, event-related potentials, and MRI biomarkers for detection of mild cognitive impairment: A machine learning approach.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2026

Search research articles

相关实验视频

Updated: Jul 17, 2025

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

Published on: May 3, 2012

使用基于深度学习的方法自动化Rey复杂数字测试得分:一种潜在的大规模查工具,用于认知衰退.

Jun Young Park^1,2,3, Eun Hyun Seo^1,4, Hyung-Jun Yoon⁵

¹Gwangju Alzheimer's & Related Dementia Cohort Research Center, Chosun University, Gwangju, 61452, South Korea.

Alzheimer's research & therapy

|August 30, 2023

概括

一个人工智能 (AI) 评分系统的雷复杂图形测试 (RCFT) 使用深度学习开发. 这种人工智能系统表现出与经验丰富的心理学家可比的高准确性,为神经认知障碍提供了更快,更具成本效益的查工具.

关键词:

阿尔茨海默氏症是阿尔茨海默氏症的一种疾病.人工智能的人工智能是人工智能.卷积神经网络是一种卷积神经网络.深度学习是一种深度学习.雷伊复杂图形测试试验获得分数的得分.

更多相关视频

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage

Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage

Published on: August 4, 2018

相关实验视频

Last Updated: Jul 17, 2025

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

Published on: May 3, 2012

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage

Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage

Published on: August 4, 2018

科学领域:

神经科学是一个神经科学.
人工智能的人工智能
医学成像分析医学成像分析

背景情况:

雷伊复杂图形测试 (RCFT) 对于评估不同年龄组和临床人群的神经认知功能至关重要.
目前的RCFT评分是复杂的,可能导致评级者之间的变化.
现有的数字RCFT格式缺乏与专家心理学家可比的直接自动评分.

研究的目的:

开发和验证人工智能 (AI) 评分系统,用于Rey复杂图形测试 (RCFT).
使用深度学习 (DL) 算法进行自动化RCFT评分.
确保AI评分系统的有效性和可比性与经验丰富的心理学家的评估.

主要方法:

在6,680个受试者的20,040个RCFT图像上训练了一个深度学习模型 (DenseNet架构).
通过对初始结果差的图像进行重新检查和重新训练来提高模型性能.
验证了人工智能评分系统,使用150个独立的测试图像,由五位专家心理学家评分.

主要成果:

最终的AI模型在交叉验证中实现了0.95分的平均绝对误差 (MAE) 和0.986的R平方值.
人工智能预测的得分在正常认知,轻度认知障碍和痴呆症之间有显著差异.
外部验证显示AI和专家人类得分之间的MAE为0.64分,R平方为0.994.

结论:

与经验丰富的心理学家相比,RCFT的AI评分系统在准确度上没有根本的差异.
开发的AI系统可以促进更快,更具成本效益的早期阿尔茨海默病病理学查.
潜在的应用包括医疗检查中心和大型社区研究机构.