Using an Overlapping Time Interval Strategy to Study Diagnostic Instability in Mild Cognitive Impairment Subtypes

Examining the role of participant and study partner report in widely-used classification approaches of mild cognitive impairment in demographically-diverse community dwelling individuals: results from the Einstein aging study

Objective

The role of subjective cognitive concerns (SCC) as a diagnostic criterion for MCI remains uncertain and limits the development of a universally (or widely)-accepted MCI definition. The optimal MCI definition should define an at-risk state and accurately predict the development of incident dementia. Questions remain about operationalization of definitions of self- and informant-reported SCCs and their individual and joint associations with incident dementia.

Methods

The present study included Einstein Aging Study participants who were non-Hispanic White or Black, free of dementia at enrollment, had follow-up, and completed neuropsychological tests and self-reported SCC at enrollment to determine MCI status. Informant-reported SCC at baseline were assessed via the CERAD clinical history questionnaire. Self-reported SCC were measured using the CERAD, items from the EAS Health Self-Assessment, and the single memory item from the Geriatric Depression Scale. Cox proportional hazards models examined the association of different operationalizations of SCC with Petersen and Jak/Bondi MCI definitions on the risk of dementia, further controlling for age, sex, education, and race/ethnicity. Time-dependent sensitivity and specificity at specific time points for each definition, and Youden's index were calculated as an accuracy measure. Cox proportional hazards models were also used to evaluate the associations of combinations of self- and informant-reported SCC with the risk of incident dementia.

Results

91% of the sample endorsed at least one SCC. Youden's index showed that not including SCC in either Jak/Bondi or Petersen classifications had the best balance between sensitivity and specificity across follow-up. A subset of individuals with informants, on average, had a lower proportion of non-Hispanic Blacks and 94% endorsed at least one self-reported SCC. Both informant-reported and self-reported SCC were significantly associated with incident dementia.

Conclusion

Our findings suggest that the SCC criterion may not improve the predictive validity for dementia when included in widely-employed definitions of MCI. Consistent with some prior research, informant-reported SCC was more related to risk of incident dementia than self-reported SCC. Given that requiring informant report as a diagnostic criterion may unintentionally exclude health disparate groups, additional consideration is needed to determine how best to utilize informant-report in MCI diagnosis.

Relevance of Complaint Severity in Predicting the Progression of Subjective Cognitive Decline and Mild Cognitive Impairment: A Machine Learning Approach

BACKGROUND

The presence of subjective cognitive complaints (SCCs) is a core criterion for diagnosis of subjective cognitive decline (SCD); however, no standard procedure for distinguishing normative and non-normative SCCs has yet been established.

OBJECTIVE

To determine whether differentiation of participants with SCD according to SCC severity improves the validity of the prediction of progression in SCD and MCI and to explore validity metrics for two extreme thresholds of the distribution in scores in a questionnaire on SCCs.

METHODS

Two hundred and fifty-three older adults with SCCs participating in the Compostela Aging Study (CompAS) were classified as MCI or SCD at baseline. The participants underwent two follow-up assessments and were classified as cognitively stable or worsened. Severity of SCCs (low and high) in SCD was established by using two different percentiles of the questionnaire score distribution as cut-off points. The validity of these cut-off points for predicting progression using socio-demographic, health, and neuropsychological variables was tested by machine learning (ML) analysis.

RESULTS

Severity of SCCs in SCD established considering the 5th percentile as a cut-off point proved to be the best metric for predicting progression. The variables with the main role in conforming the predictive algorithm were those related to memory, cognitive reserve, general health, and the stability of diagnosis over time.

CONCLUSION

Moderate to high complainers showed an increased probability of progression in cognitive decline, suggesting the clinical relevance of standard procedures to determine SCC severity. Our findings highlight the important role of the multimodal ML approach in predicting progression.

Multi-View Based Multi-Model Learning for MCI Diagnosis

Mild cognitive impairment (MCI) is the early stage of Alzheimer’s disease (AD). Automatic diagnosis of MCI by magnetic resonance imaging (MRI) images has been the focus of research in recent years. Furthermore, deep learning models based on 2D view and 3D view have been widely used in the diagnosis of MCI. The deep learning architecture can capture anatomical changes in the brain from MRI scans to extract the underlying features of brain disease. In this paper, we propose a multi-view based multi-model (MVMM) learning framework, which effectively combines the local information of 2D images with the global information of 3D images. First, we select some 2D slices from MRI images and extract the features representing 2D local information. Then, we combine them with the features representing 3D global information learned from 3D images to train the MVMM learning framework. We evaluate our model on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our proposed model can effectively recognize MCI through MRI images (accuracy of 87.50% for MCI/HC and accuracy of 83.18% for MCI/AD).

Longitudinal Patterns of the Tip-of-the-Tongue Phenomenon in People With Subjective Cognitive Complaints and Mild Cognitive Impairment

Background

The Tip-of-the-Tongue (ToTs) state is considered a universal phenomenon and is a frequent cognitive complaint in old age. Previous cross-sectional studies have found that ToT measures successfully discriminate between cognitively unimpaired adults and adults with Mild Cognitive Impairment (MCI). The aim of this study was to identify longitudinal patterns of ToTs in individuals with subjective complaints and with MCI regarding progress of their cognitive status.

Method

The study included 193 participants with subjective cognitive complaints (SCC) and 56 participants with MCI who completed a baseline and two follow-up assessments, with an interval of about 18 months between each assessment. Participants were classified into three groups by considering cognitive stability or deterioration from the baseline diagnosis: SCC-stable, MCI-stable and MCI-worsened. Participants performed a ToT task involving recognition and naming of famous people depicted in 50 photographs. Generalized Linear Mixed Models (GLMM) were used to model longitudinal changes in familiarity, feeling of knowing, semantic access, phonological access and verbal fluency.

Results

Phonological access differentiated MCI patients, stable and worsened, from adults with SCCs at all evaluation times. Phonological access declined over time in the three groups, without significant interactions between groups and time.

Discussion

This study provides the first longitudinal evidence of differences in ToT measures for adults with MCI. The findings indicate that phonological access measures successfully differentiated between the diagnostic groups. However, slopes remain irrespective of the diagnostic group and progression toward more advance stages of cognitive impairment.