Dataset Information

Multimodal measurement approach to identify individuals with mild cognitive impairment: study protocol for a cross-sectional trial.

ABSTRACT:

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.

SUBMITTER: Grassler B

PROVIDER: S-EPMC8154928 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Effective and accurate diagnosis of Alzheimer's disease (AD), as well as its prodromal stage (i.e., mild cognitive impairment (MCI)), has attracted more and more attention recently. So far, multiple biomarkers have been shown to be sensitive to the diagnosis of AD and MCI, i.e., structural MR imaging (MRI) for brain atrophy measurement, functional imaging (e.g., FDG-PET) for hypometabolism quantification, and cerebrospinal fluid (CSF) for quantification of specific proteins. However, most existing research focuses on only a single modality of biomarkers for diagnosis of AD and MCI, although recent studies have shown that different biomarkers may provide complementary information for the diagnosis of AD and MCI. In this paper, we propose to combine three modalities of biomarkers, i.e., MRI, FDG-PET, and CSF biomarkers, to discriminate between AD (or MCI) and healthy controls, using a kernel combination method. Specifically, ADNI baseline MRI, FDG-PET, and CSF data from 51AD patients, 99 MCI patients (including 43 MCI converters who had converted to AD within 18 months and 56 MCI non-converters who had not converted to AD within 18 months), and 52 healthy controls are used for development and validation of our proposed multimodal classification method. In particular, for each MR or FDG-PET image, 93 volumetric features are extracted from the 93 regions of interest (ROIs), automatically labeled by an atlas warping algorithm. For CSF biomarkers, their original values are directly used as features. Then, a linear support vector machine (SVM) is adopted to evaluate the classification accuracy, using a 10-fold cross-validation. As a result, for classifying AD from healthy controls, we achieve a classification accuracy of 93.2% (with a sensitivity of 93% and a specificity of 93.3%) when combining all three modalities of biomarkers, and only 86.5% when using even the best individual modality of biomarkers. Similarly, for classifying MCI from healthy controls, we achieve a classification accuracy of 76.4% (with a sensitivity of 81.8% and a specificity of 66%) for our combined method, and only 72% even using the best individual modality of biomarkers. Further analysis on MCI sensitivity of our combined method indicates that 91.5% of MCI converters and 73.4% of MCI non-converters are correctly classified. Moreover, we also evaluate the classification performance when employing a feature selection method to select the most discriminative MR and FDG-PET features. Again, our combined method shows considerably better performance, compared to the case of using an individual modality of biomarkers.

Project description:Studies have suggested that insulin resistance plays a role in cognitive impairment in individuals with type 2 diabetes. We aimed to determine whether an improvement in insulin resistance could explain cognitive performance variations over 36 weeks in older individuals with mild cognitive impairment (MCI) and type 2 diabetes.A total of 97 older individuals (mean +/- SD age 76 +/- 6 years) who had recently (<2 months) started an antidiabetes treatment of metformin (500 mg twice a day) (n = 30) or metformin (500 mg/day)+rosiglitazone (4 mg/day) (n = 32) or diet (n = 35) volunteered. The neuropsychological test battery consisted of the Mini-Mental State Examination (MMSE), Rey Verbal Auditory Learning Test (RAVLT) total recall, and Trail Making Tests (TMT-A and TMT-B) performed at baseline and every 12 weeks for 36 weeks along with clinical testing.At baseline, no significant differences were found between groups in clinical or neuropsychological parameters. Mean +/- SD values in the entire population were as follows: A1C 7.5 +/- 0.5%, fasting plasma glucose (FPG) 8.6 +/- 1.3 mmol/l, fasting plasma insulin (FPI) 148 +/- 74 pmol/l, MMSE 24.9 +/- 2.4, TMT-A 61.6 +/- 42.0, TMT-B 162.8 +/- 78.7, the difference between TMT-B and TMT-A [DIFFBA] 101.2 +/- 58.1, and RAVLT 24.3 +/- 2.1. At follow-up, ANOVA models tested changes in metabolic control parameters (FPI, FPG, and A1C). Such parameters improved in the metformin and metformin/rosiglitazone groups (P(trend) < 0.05 in both groups). ANCOVA repeated models showed that results for the metformin/rosiglitazone group remained stable for all neuropsychological tests, and results for the diet group remained stable for the MMSE and TMT-A and declined for the TMT-B (P(trend) = 0.024), executive efficiency (DIFFBA) (P(trend) = 0.026), and RAVLT memory test (P(trend) = 0.011). Results for the metformin group remained stable for the MMSE and TMTs but declined for the RAVLT (P(trend) = 0.011). With use of linear mixed-effects models, the interaction term, FPI x time, correlated with cognitive stability on the RAVLT in the metformin/rosiglitazone group (beta = -1.899; P = 0.009).Rosiglitazone may protect against cognitive decline in older individuals with type 2 diabetes and MCI.