利用卷积神经网络进行时钟绘制测试以判别轻度认知障碍

IF 2.5 4区 医学 Q2 PSYCHIATRY
Jin-Hyuck Park
{"title":"利用卷积神经网络进行时钟绘制测试以判别轻度认知障碍","authors":"Jin-Hyuck Park","doi":"10.1016/j.ejpsy.2024.100256","DOIUrl":null,"url":null,"abstract":"<div><h3>Background and objectives</h3><p>The Clock Drawing Test (CDT) is a tool to assess cognitive function. Despite its usefulness, its interpretation remains challenging, leading to a low reliability. The main objective of this study was to determine the feasibility of using the CDT with convolutional neural networks (CNNs) as a screening tool for amnestic type of mild cognitive impairment (a-MCI).</p></div><div><h3>Methods</h3><p>A total of 177 CDT images were obtained from 103 healthy controls (HCs) and 74 patients with a-MCI. CNNs were trained to classify MCI based on the CDT images. To evaluate the performance of the CDT with CNNs, accuracy, sensitivity, specificity, precision, and f1-score were calculated. To compare discriminant power, the area under the curve of the CDT with CNNs and the Korean version of the Montreal Cognitive Assessment (MoCA-K) was calculated by the receiving operating characteristic curve analysis.</p></div><div><h3>Results</h3><p>The CDT with CNNs was more accurate in discriminating a-MCI (CDT with CNNs = 88.7%, MoCA-<em>K</em> = 81.8%). Furthermore, the CDT with CNNs could better discriminate a-MCI than the MoCA-K (AUC: CDT with CNNs = 0.886, MoCA-<em>K</em> = 0.848).</p></div><div><h3>Conclusion</h3><p>These results demonstrate the superiority of the CDT with CNNs to the MoCA-K for distinguishing a-MCI from HCs. The CDT with CNNs could be a surrogate for a conventional screening tool for a-MCI.</p></div>","PeriodicalId":12045,"journal":{"name":"European Journal of Psychiatry","volume":null,"pages":null},"PeriodicalIF":2.5000,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Clock drawing test with convolutional neural networks to discriminate mild cognitive impairment\",\"authors\":\"Jin-Hyuck Park\",\"doi\":\"10.1016/j.ejpsy.2024.100256\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background and objectives</h3><p>The Clock Drawing Test (CDT) is a tool to assess cognitive function. Despite its usefulness, its interpretation remains challenging, leading to a low reliability. The main objective of this study was to determine the feasibility of using the CDT with convolutional neural networks (CNNs) as a screening tool for amnestic type of mild cognitive impairment (a-MCI).</p></div><div><h3>Methods</h3><p>A total of 177 CDT images were obtained from 103 healthy controls (HCs) and 74 patients with a-MCI. CNNs were trained to classify MCI based on the CDT images. To evaluate the performance of the CDT with CNNs, accuracy, sensitivity, specificity, precision, and f1-score were calculated. To compare discriminant power, the area under the curve of the CDT with CNNs and the Korean version of the Montreal Cognitive Assessment (MoCA-K) was calculated by the receiving operating characteristic curve analysis.</p></div><div><h3>Results</h3><p>The CDT with CNNs was more accurate in discriminating a-MCI (CDT with CNNs = 88.7%, MoCA-<em>K</em> = 81.8%). Furthermore, the CDT with CNNs could better discriminate a-MCI than the MoCA-K (AUC: CDT with CNNs = 0.886, MoCA-<em>K</em> = 0.848).</p></div><div><h3>Conclusion</h3><p>These results demonstrate the superiority of the CDT with CNNs to the MoCA-K for distinguishing a-MCI from HCs. The CDT with CNNs could be a surrogate for a conventional screening tool for a-MCI.</p></div>\",\"PeriodicalId\":12045,\"journal\":{\"name\":\"European Journal of Psychiatry\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2024-04-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Journal of Psychiatry\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0213616324000077\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"PSYCHIATRY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Psychiatry","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0213616324000077","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PSYCHIATRY","Score":null,"Total":0}
引用次数: 0

摘要

背景和目的计时绘图测试(CDT)是一种评估认知功能的工具。尽管 CDT 很有用,但其解释仍具有挑战性,导致其可靠性较低。本研究的主要目的是确定将 CDT 与卷积神经网络(CNNs)一起用作轻度认知障碍(a-MCI)的失忆型筛查工具的可行性。方法从 103 名健康对照组(HCs)和 74 名轻度认知障碍患者身上共获得 177 张 CDT 图像。根据 CDT 图像训练 CNN 对 MCI 进行分类。为了评估 CDT 与 CNN 的性能,计算了准确度、灵敏度、特异性、精确度和 f1 分数。为了比较判别能力,采用接收操作特征曲线分析法计算了带 CNN 的 CDT 和韩文版蒙特利尔认知评估(MoCA-K)的曲线下面积。结果 带 CNN 的 CDT 在判别 a-MCI 方面更准确(带 CNN 的 CDT = 88.7%,MoCA-K = 81.8%)。此外,带 CNN 的 CDT 比 MoCA-K 更能区分 a-MCI(AUC:带 CNN 的 CDT = 0.886,MoCA-K = 0.848)。带 CNN 的 CDT 可以替代 a-MCI 的传统筛查工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Clock drawing test with convolutional neural networks to discriminate mild cognitive impairment

Background and objectives

The Clock Drawing Test (CDT) is a tool to assess cognitive function. Despite its usefulness, its interpretation remains challenging, leading to a low reliability. The main objective of this study was to determine the feasibility of using the CDT with convolutional neural networks (CNNs) as a screening tool for amnestic type of mild cognitive impairment (a-MCI).

Methods

A total of 177 CDT images were obtained from 103 healthy controls (HCs) and 74 patients with a-MCI. CNNs were trained to classify MCI based on the CDT images. To evaluate the performance of the CDT with CNNs, accuracy, sensitivity, specificity, precision, and f1-score were calculated. To compare discriminant power, the area under the curve of the CDT with CNNs and the Korean version of the Montreal Cognitive Assessment (MoCA-K) was calculated by the receiving operating characteristic curve analysis.

Results

The CDT with CNNs was more accurate in discriminating a-MCI (CDT with CNNs = 88.7%, MoCA-K = 81.8%). Furthermore, the CDT with CNNs could better discriminate a-MCI than the MoCA-K (AUC: CDT with CNNs = 0.886, MoCA-K = 0.848).

Conclusion

These results demonstrate the superiority of the CDT with CNNs to the MoCA-K for distinguishing a-MCI from HCs. The CDT with CNNs could be a surrogate for a conventional screening tool for a-MCI.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
2.90
自引率
0.00%
发文量
40
审稿时长
43 days
期刊介绍: The European journal of psychiatry is a quarterly publication founded in 1986 and directed by Professor Seva until his death in 2004. It was originally intended to report “the scientific activity of European psychiatrists” and “to bring about a greater degree of communication” among them. However, “since scientific knowledge has no geographical or cultural boundaries, is open to contributions from all over the world”. These principles are maintained in the new stage of the journal, now expanded with the help of an American editor.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信