The Digital Clock and Recall can predict functional impairment in individuals with and without cognitive impairment and triage those in need of further assessment

IF 13 1区 医学 Q1 CLINICAL NEUROLOGY
Marissa C Ciesla, Claudio Toro-Serey, Ali Jannati, Joyce Rios Gomes-Osman, Russel Banks, John Showalter, Sean Tobyne, Alvaro Pascual-Leone
{"title":"The Digital Clock and Recall can predict functional impairment in individuals with and without cognitive impairment and triage those in need of further assessment","authors":"Marissa C Ciesla,&nbsp;Claudio Toro-Serey,&nbsp;Ali Jannati,&nbsp;Joyce Rios Gomes-Osman,&nbsp;Russel Banks,&nbsp;John Showalter,&nbsp;Sean Tobyne,&nbsp;Alvaro Pascual-Leone","doi":"10.1002/alz.089288","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Introduction</h3>\n \n <p>Evaluation of functional dependence in activities of daily living (ADLs) and instrumental activities of daily living (iADLs) is necessary for dementia diagnosis. ADL and iADL questionnaires are typically employed, but with progressive cognitive impairment, a care partner must step in to assist with these tests, causing logistical burdens. Pre-screening tools that triage patients in need of formal functional assessment would optimize clinical workflows. Here we evaluated whether the Linus Health Digital Clock and Recall (DCRTM), a brief automatically-scored test of multiple cognitive domains, could concurrently predict functional impairment among individuals with and without cognitive impairment.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>We collected data from 922 participants in the Bio-Hermes-001 multi-site study (age mean±SD = 72±6.6; 57% female; years of education mean±SD = 15±2.71; primary language English), classified as cognitively unimpaired (n = 402), mild cognitively impaired (n = 298), or probable Alzheimer’s dementia (n = 242) based on clinical consensus and neuropsychological evaluation. We split participants, each including 2000 speech and drawing DCR metrics and age, into training (80%) and test (20%) sets, ensuring equal rates of functional impairment across sets (Functional Activities Questionnaire ≥ 6; 25% rate). We performed recursive feature elimination on 10-fold cross-validated random forests (5 repetitions) on the training set to identify the best model and feature set. Model performance was evaluated on the test set.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The optimal model (500 features) classified functional impairment with 0.77 sensitivity, 0.82 specificity, 0.90 negative predictive value (NPV), 0.61 positive predictive value (PPV), 0.86 area under the receiver operating characteristic curve (AUC), and 0.80 accuracy. The most predictive features were the duration of speech during recall and the placement of clock components.</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>The DCR, a brief digital cognitive assessment with automatic scoring that can be completed in primary-care settings, can also be used to identify individuals in need of further evaluation and engagement of care partners as informants. The high NPV can reassure healthcare professionals when no further assessment of ADLs and iADLs is indicated. These results also enable identifying care partners who are likely to benefit from receiving personalized recommendations or training to assist them in caregiving tasks and alleviate caregiver burden.</p>\n </section>\n </div>","PeriodicalId":7471,"journal":{"name":"Alzheimer's & Dementia","volume":"20 S5","pages":""},"PeriodicalIF":13.0000,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/alz.089288","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Alzheimer's & Dementia","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/alz.089288","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction

Evaluation of functional dependence in activities of daily living (ADLs) and instrumental activities of daily living (iADLs) is necessary for dementia diagnosis. ADL and iADL questionnaires are typically employed, but with progressive cognitive impairment, a care partner must step in to assist with these tests, causing logistical burdens. Pre-screening tools that triage patients in need of formal functional assessment would optimize clinical workflows. Here we evaluated whether the Linus Health Digital Clock and Recall (DCRTM), a brief automatically-scored test of multiple cognitive domains, could concurrently predict functional impairment among individuals with and without cognitive impairment.

Methods

We collected data from 922 participants in the Bio-Hermes-001 multi-site study (age mean±SD = 72±6.6; 57% female; years of education mean±SD = 15±2.71; primary language English), classified as cognitively unimpaired (n = 402), mild cognitively impaired (n = 298), or probable Alzheimer’s dementia (n = 242) based on clinical consensus and neuropsychological evaluation. We split participants, each including 2000 speech and drawing DCR metrics and age, into training (80%) and test (20%) sets, ensuring equal rates of functional impairment across sets (Functional Activities Questionnaire ≥ 6; 25% rate). We performed recursive feature elimination on 10-fold cross-validated random forests (5 repetitions) on the training set to identify the best model and feature set. Model performance was evaluated on the test set.

Results

The optimal model (500 features) classified functional impairment with 0.77 sensitivity, 0.82 specificity, 0.90 negative predictive value (NPV), 0.61 positive predictive value (PPV), 0.86 area under the receiver operating characteristic curve (AUC), and 0.80 accuracy. The most predictive features were the duration of speech during recall and the placement of clock components.

Conclusion

The DCR, a brief digital cognitive assessment with automatic scoring that can be completed in primary-care settings, can also be used to identify individuals in need of further evaluation and engagement of care partners as informants. The high NPV can reassure healthcare professionals when no further assessment of ADLs and iADLs is indicated. These results also enable identifying care partners who are likely to benefit from receiving personalized recommendations or training to assist them in caregiving tasks and alleviate caregiver burden.

数字时钟和回忆可以预测有或没有认知障碍的个体的功能损伤,并对那些需要进一步评估的人进行分类
日常生活活动(ADLs)和日常生活工具活动(iADLs)的功能依赖评估是痴呆诊断的必要条件。通常采用ADL和iADL问卷调查,但随着认知障碍的进展,护理伙伴必须介入协助进行这些测试,从而造成后勤负担。预筛选工具对需要正式功能评估的患者进行分类,将优化临床工作流程。在这里,我们评估了Linus健康数字时钟和回忆(DCRTM),一个简短的多个认知领域自动评分测试,是否可以同时预测有和没有认知障碍的个体的功能障碍。方法:我们收集了922名来自Bio - Hermes - 001多站点研究的参与者的数据(年龄平均±SD = 72±6.6;57%的女性;平均受教育年限±SD = 15±2.71;主要语言为英语),根据临床共识和神经心理学评估分为认知未受损(n = 402)、轻度认知受损(n = 298)或可能的阿尔茨海默氏痴呆症(n = 242)。我们将参与者分为训练组(80%)和测试组(20%),每个组包括2000个演讲和绘画DCR指标和年龄,以确保各组功能障碍的发生率相等(功能活动问卷≥6;率25%)。我们对训练集上的10倍交叉验证随机森林(5次重复)进行递归特征消除,以确定最佳模型和特征集。在测试集上评估模型的性能。结果最优模型(500个特征)对功能障碍的分类灵敏度为0.77,特异性为0.82,阴性预测值(NPV)为0.90,阳性预测值(PPV)为0.61,受试者工作特征曲线下面积(AUC)为0.86,准确率为0.80。最具预测性的特征是回忆时的语音持续时间和时钟组件的位置。结论DCR是一种简短的数字认知评估,具有自动评分功能,可在初级保健机构中完成,也可用于识别需要进一步评估的个体,以及护理伙伴作为信息提供者的参与。当不需要进一步评估adl和iadl时,高NPV可以让医疗保健专业人员放心。这些结果还有助于确定可能受益于个性化建议或培训的护理伙伴,以帮助他们完成护理任务并减轻护理人员的负担。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Alzheimer's & Dementia
Alzheimer's & Dementia 医学-临床神经学
CiteScore
14.50
自引率
5.00%
发文量
299
审稿时长
3 months
期刊介绍: Alzheimer's & Dementia is a peer-reviewed journal that aims to bridge knowledge gaps in dementia research by covering the entire spectrum, from basic science to clinical trials to social and behavioral investigations. It provides a platform for rapid communication of new findings and ideas, optimal translation of research into practical applications, increasing knowledge across diverse disciplines for early detection, diagnosis, and intervention, and identifying promising new research directions. In July 2008, Alzheimer's & Dementia was accepted for indexing by MEDLINE, recognizing its scientific merit and contribution to Alzheimer's research.
×
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