Jingmei Yang, Samad Amini, Boran Hao, Seho Park, Cody Karjadi, Lance San Souci, Vijaya B Kolachalama, Stephanie Cosentino, Stacy L Andersen, Rhoda Au, Ioannis Ch Paschalidis
{"title":"开发一种可访问的痴呆症评估工具:利用残差网络、跟踪测试和人口统计数据。","authors":"Jingmei Yang, Samad Amini, Boran Hao, Seho Park, Cody Karjadi, Lance San Souci, Vijaya B Kolachalama, Stephanie Cosentino, Stacy L Andersen, Rhoda Au, Ioannis Ch Paschalidis","doi":"10.1177/13872877251359889","DOIUrl":null,"url":null,"abstract":"<p><p>BackgroundThe global burden of Alzheimer's disease and related dementias is rapidly increasing, particularly in low- and middle-income countries where access to specialized healthcare is limited. Neuropsychological tests are essential diagnostic tools, but their administration requires trained professionals, creating screening barriers. Automated computational assessment presents a cost-effective solution for global dementia screening.ObjectiveTo develop and validate an artificial intelligence-based screening tool using the Trail Making Test (TMT), demographic information, completion times, and drawing analysis for enhanced dementia detection.MethodsWe developed: (1) non-image models using demographics and TMT completion times, (2) image-only models, and (3) fusion models. Models were trained and validated on data from the Framingham Heart Study (FHS) (<i>N</i> = 1252), the Long Life Family Study (LLFS) (<i>N</i> = 1613), and the combined cohort (<i>N</i> = 2865).ResultsOur models, integrating TMT drawings, demographics, and completion times, excelled in distinguishing dementia from normal cognition. In the LLFS cohort, we achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 98<i>.</i>62%, with sensitivity/specificity of 87<i>.</i>69%/98<i>.</i>26%. In the FHS cohort, we obtained an AUC of 96<i>.</i>51%, with sensitivity/specificity of 85<i>.</i>00%/96<i>.</i>75%.ConclusionsOur method demonstrated superior performance compared to traditional approaches using age and TMT completion time. Adding images captures subtler nuances from the TMT drawing that traditional methods miss. Integrating the TMT drawing into cognitive assessments enables effective dementia screening. Future studies could aim to expand data collection to include more diverse cohorts, particularly from less-resourced regions.</p>","PeriodicalId":14929,"journal":{"name":"Journal of Alzheimer's Disease","volume":" ","pages":"13872877251359889"},"PeriodicalIF":3.1000,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Developing an accessible dementia assessment tool: Leveraging a residual network, the trail making test, and demographic data.\",\"authors\":\"Jingmei Yang, Samad Amini, Boran Hao, Seho Park, Cody Karjadi, Lance San Souci, Vijaya B Kolachalama, Stephanie Cosentino, Stacy L Andersen, Rhoda Au, Ioannis Ch Paschalidis\",\"doi\":\"10.1177/13872877251359889\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>BackgroundThe global burden of Alzheimer's disease and related dementias is rapidly increasing, particularly in low- and middle-income countries where access to specialized healthcare is limited. Neuropsychological tests are essential diagnostic tools, but their administration requires trained professionals, creating screening barriers. Automated computational assessment presents a cost-effective solution for global dementia screening.ObjectiveTo develop and validate an artificial intelligence-based screening tool using the Trail Making Test (TMT), demographic information, completion times, and drawing analysis for enhanced dementia detection.MethodsWe developed: (1) non-image models using demographics and TMT completion times, (2) image-only models, and (3) fusion models. Models were trained and validated on data from the Framingham Heart Study (FHS) (<i>N</i> = 1252), the Long Life Family Study (LLFS) (<i>N</i> = 1613), and the combined cohort (<i>N</i> = 2865).ResultsOur models, integrating TMT drawings, demographics, and completion times, excelled in distinguishing dementia from normal cognition. In the LLFS cohort, we achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 98<i>.</i>62%, with sensitivity/specificity of 87<i>.</i>69%/98<i>.</i>26%. In the FHS cohort, we obtained an AUC of 96<i>.</i>51%, with sensitivity/specificity of 85<i>.</i>00%/96<i>.</i>75%.ConclusionsOur method demonstrated superior performance compared to traditional approaches using age and TMT completion time. Adding images captures subtler nuances from the TMT drawing that traditional methods miss. Integrating the TMT drawing into cognitive assessments enables effective dementia screening. Future studies could aim to expand data collection to include more diverse cohorts, particularly from less-resourced regions.</p>\",\"PeriodicalId\":14929,\"journal\":{\"name\":\"Journal of Alzheimer's Disease\",\"volume\":\" \",\"pages\":\"13872877251359889\"},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2025-07-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Alzheimer's Disease\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1177/13872877251359889\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"NEUROSCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Alzheimer's Disease","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/13872877251359889","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
引用次数: 0
摘要
阿尔茨海默病和相关痴呆症的全球负担正在迅速增加,特别是在获得专业医疗保健有限的低收入和中等收入国家。神经心理学测试是必不可少的诊断工具,但它们的管理需要训练有素的专业人员,这就造成了筛查障碍。自动计算评估为全球痴呆症筛查提供了一种具有成本效益的解决方案。目的利用Trail Making Test (TMT)、人口统计信息、完成时间和绘图分析,开发并验证一种基于人工智能的筛查工具,以增强对痴呆症的检测。方法:(1)基于人口统计学和TMT完成时间的非图像模型;(2)纯图像模型;(3)融合模型。模型的训练和验证数据来自弗雷明汉心脏研究(FHS) (N = 1252)、长寿命家庭研究(LLFS) (N = 1613)和联合队列(N = 2865)。结果我们的模型整合了TMT图、人口统计学和完成时间,在区分痴呆和正常认知方面表现出色。在LLFS队列中,我们获得了98.62%的受试者工作特征曲线下面积(Area Under Receiver Operating Characteristic Curve, AUC),敏感性/特异性为87.69%/98.26%。在FHS队列中,我们获得的AUC为96.51%,敏感性/特异性为85.00%/96.75%。结论在年龄和TMT完成时间方面,sour方法优于传统方法。添加图像可以捕捉到传统方法无法捕捉到的TMT图中更细微的差别,将TMT图整合到认知评估中可以有效地筛查痴呆症。未来的研究可能旨在扩大数据收集,包括更多样化的人群,特别是来自资源匮乏地区的人群。
Developing an accessible dementia assessment tool: Leveraging a residual network, the trail making test, and demographic data.
BackgroundThe global burden of Alzheimer's disease and related dementias is rapidly increasing, particularly in low- and middle-income countries where access to specialized healthcare is limited. Neuropsychological tests are essential diagnostic tools, but their administration requires trained professionals, creating screening barriers. Automated computational assessment presents a cost-effective solution for global dementia screening.ObjectiveTo develop and validate an artificial intelligence-based screening tool using the Trail Making Test (TMT), demographic information, completion times, and drawing analysis for enhanced dementia detection.MethodsWe developed: (1) non-image models using demographics and TMT completion times, (2) image-only models, and (3) fusion models. Models were trained and validated on data from the Framingham Heart Study (FHS) (N = 1252), the Long Life Family Study (LLFS) (N = 1613), and the combined cohort (N = 2865).ResultsOur models, integrating TMT drawings, demographics, and completion times, excelled in distinguishing dementia from normal cognition. In the LLFS cohort, we achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 98.62%, with sensitivity/specificity of 87.69%/98.26%. In the FHS cohort, we obtained an AUC of 96.51%, with sensitivity/specificity of 85.00%/96.75%.ConclusionsOur method demonstrated superior performance compared to traditional approaches using age and TMT completion time. Adding images captures subtler nuances from the TMT drawing that traditional methods miss. Integrating the TMT drawing into cognitive assessments enables effective dementia screening. Future studies could aim to expand data collection to include more diverse cohorts, particularly from less-resourced regions.
期刊介绍:
The Journal of Alzheimer''s Disease (JAD) is an international multidisciplinary journal to facilitate progress in understanding the etiology, pathogenesis, epidemiology, genetics, behavior, treatment and psychology of Alzheimer''s disease. The journal publishes research reports, reviews, short communications, hypotheses, ethics reviews, book reviews, and letters-to-the-editor. The journal is dedicated to providing an open forum for original research that will expedite our fundamental understanding of Alzheimer''s disease.