多模态测量方法识别轻度认知障碍个体：一项横断面研究的研究方案。
Multimodal measurement approach to identify individuals with mild cognitive impairment: study protocol for a cross-sectional trial.
机构信息
Institute of Sport Science, Faculty of Humanities, Otto von Guericke University Magdeburg, Magdeburg, Germany
Department of Neuroprotection, German Centre for Neurodegenerative Diseases Site Magdeburg, Magdeburg, Germany.
出版信息
BMJ Open. 2021 May 25;11(5):e046879. doi: 10.1136/bmjopen-2020-046879.
INTRODUCTION
The diagnosis of mild cognitive impairment (MCI), that is, the transitory phase between normal age-related cognitive decline and dementia, remains a challenging task. It was observed that a multimodal approach (simultaneous analysis of several complementary modalities) can improve the classification accuracy. We will combine three noninvasive measurement modalities: functional near-infrared spectroscopy (fNIRS), electroencephalography and heart rate variability via ECG. Our aim is to explore neurophysiological correlates of cognitive performance and whether our multimodal approach can aid in early identification of individuals with MCI.
METHODS AND ANALYSIS
This study will be a cross-sectional with patients with MCI and healthy controls (HC). The neurophysiological signals will be measured during rest and while performing cognitive tasks: (1) Stroop, (2) N-back and (3) verbal fluency test (VFT). Main aims of statistical analysis are to (1) determine the differences in neurophysiological responses of HC and MCI, (2) investigate relationships between measures of cognitive performance and neurophysiological responses and (3) investigate whether the classification accuracy can be improved by using our multimodal approach. To meet these targets, statistical analysis will include machine learning approaches.This is, to the best of our knowledge, the first study that applies simultaneously these three modalities in MCI and HC. We hypothesise that the multimodal approach improves the classification accuracy between HC and MCI as compared with a unimodal approach. If our hypothesis is verified, this study paves the way for additional research on multimodal approaches for dementia research and fosters the exploration of new biomarkers for an early detection of nonphysiological age-related cognitive decline.
ETHICS AND DISSEMINATION
Ethics approval was obtained from the local Ethics Committee (reference: 83/19). Data will be shared with the scientific community no more than 1 year following completion of study and data assembly.
TRIAL REGISTRATION NUMBER
ClinicalTrials.gov, NCT04427436, registered on 10 June 2020, https://clinicaltrials.gov/ct2/show/study/NCT04427436.
介绍
轻度认知障碍（MCI）的诊断，即正常年龄相关认知衰退与痴呆之间的过渡阶段，仍然是一项具有挑战性的任务。人们观察到，多模态方法（同时分析几种互补的模式）可以提高分类准确性。我们将结合三种非侵入性测量模式：功能近红外光谱（fNIRS）、脑电图和心电图的心率变异性。我们的目的是探索认知表现的神经生理相关性，以及我们的多模态方法是否有助于早期识别 MCI 个体。
方法和分析
这是一项横断面研究，纳入 MCI 患者和健康对照组（HC）。在休息和执行认知任务期间（1）Stroop、（2）N-back 和（3）言语流畅性测试（VFT）时，将测量神经生理信号。统计分析的主要目的是：（1）确定 HC 和 MCI 之间神经生理反应的差异；（2）研究认知表现和神经生理反应之间的关系；（3）研究我们的多模态方法是否可以提高分类准确性。为了达到这些目标，统计分析将包括机器学习方法。据我们所知，这是第一项同时在 MCI 和 HC 中应用这三种模式的研究。我们假设，与单模态方法相比，多模态方法可以提高 HC 和 MCI 之间的分类准确性。如果我们的假设得到验证，这项研究为痴呆症研究中的多模态方法研究铺平了道路，并促进了对非生理性年龄相关认知衰退早期检测的新生物标志物的探索。
伦理和传播
当地伦理委员会已批准该研究（参考编号：83/19）。在研究和数据汇编完成后不超过 1 年，将与科学界共享数据。
临床试验注册
ClinicalTrials.gov，NCT04427436，于 2020 年 6 月 10 日注册，https://clinicaltrials.gov/ct2/show/study/NCT04427436。
Zotero 插件