High frequency post-disfluency word choices and task-dependent speech behavior characterize connected speech in individuals with mild cognitive impairment.

Background: Alzheimer's disease (AD) is characterized by progressive cognitive decline, including impairments in speech production and fluency. Mild cognitive impairment (MCI), a prodrome of AD, has also been linked with changes in speech behavior but to a more subtle degree. Objective: This study aimed to investigate whether speech behavior immediately following disfluencies (post-disfluency speech behavior) differs between individuals with MCI and healthy controls (HCs), and how these differences are influenced by the cognitive demands of various speech tasks. Methods: Transcribed speech samples were analyzed from both groups across different tasks, including immediate and delayed narrative recall, picture descriptions, and free responses. Key metrics including lexical and syntactic complexity, both overall and post-disfluency, were examined. Results: Significant differences were observed between the MCI and HC groups in terms of filled disfluencies, particularly "uh", with a higher incidence and longer latencies following these disfluencies in the MCI group. Word frequency following filled disfluencies was higher among MCI participants, with this effect varying based on the cognitive load of the tasks. Predictive analyses utilizing random forest classifiers demonstrated high specificity in using speech behavior metrics to differentiate between MCI and HCs. Conclusions: Speech behavior following disfluencies differs between MCI participants and healthy controls, with these differences being influenced by the cognitive demands of the speech tasks. Post-disfluency speech metrics can be easily integrated into existing speech analysis paradigms. This study contributes to the growing evidence on the significance of nuanced speech analysis in understanding and predicting cognitive decline in MCI.

Visual fixations during processing of time-compressed audiovisual presentations.

Time-compression is a technique that allows users to adjust the playback speed of audio recordings, but comprehension declines at higher speeds. Previous research has shown that under challenging auditory conditions people have a greater tendency to fixate regions closer to a speaker's mouth. In the current study, we investigated whether there is a similar tendency to fixate the mouth region for time-compressed stimuli. Participants were presented with a brief audiovisual lecture at different speeds, while eye fixations were recorded, and comprehension was tested. Results showed that the 50% compressed lecture group looked more at the nose compared to eye fixations for the normal lecture, and those in the 75% compressed group looked more towards the mouth. Greater compression decreased comprehension, but audiovisual information did not reduce this deficit. These results indicate that people seek out audiovisual information to overcome time-compression, demonstrating the flexibility of the multimodal attentional system.

The Healthy Brain Initiative (HBI): A prospective cohort study protocol.

BACKGROUND: The Health Brain Initiative (HBI), established by University of Miami's Comprehensive Center for Brain Health (CCBH), follows racially/ethnically diverse older adults without dementia living in South Florida. With dementia prevention and brain health promotion as an overarching goal, HBI will advance scientific knowledge by developing novel assessments and non-invasive biomarkers of Alzheimer's disease and related dementias (ADRD), examining additive effects of sociodemographic, lifestyle, neurological and biobehavioral measures, and employing innovative, methodologically advanced modeling methods to characterize ADRD risk and resilience factors and transition of brain aging. METHODS: HBI is a longitudinal, observational cohort study that will follow 500 deeply-phenotyped participants annually to collect, analyze, and store clinical, cognitive, behavioral, functional, genetic, and neuroimaging data and biospecimens. Participants are ≥50 years old; have no, subjective, or mild cognitive impairment; have a study partner; and are eligible to undergo magnetic resonance imaging (MRI). Recruitment is community-based including advertisements, word-of-mouth, community events, and physician referrals. At baseline, following informed consent, participants complete detailed web-based surveys (e.g., demographics, health history, risk and resilience factors), followed by two half-day visits which include neurological exams, cognitive and functional assessments, an overnight sleep study, and biospecimen collection. Structural and functional MRI is completed by all participants and a subset also consent to amyloid PET imaging. Annual follow-up visits repeat the same data and biospecimen collection as baseline, except that MRIs are conducted every other year after baseline. ETHICS AND EXPECTED IMPACT: HBI has been approved by the University of Miami Miller School of Medicine Institutional Review Board. Participants provide informed consent at baseline and are re-consented as needed with protocol changes. Data collected by HBI will lead to breakthroughs in developing new diagnostics and therapeutics, creating comprehensive diagnostic evaluations, and providing the evidence base for precision medicine approaches to dementia prevention with individualized treatment plans.

The Healthy Brain Initiative (HBI): A prospective cohort study protocol.

Background: The Health Brain Initiative (HBI), established by University of Miami's Comprehensive Center for Brain Health (CCBH), follows racially/ethnically diverse older adults without dementia living in South Florida. With dementia prevention and brain health promotion as an overarching goal, HBI will advance scientific knowledge by developing novel assessments and non-invasive biomarkers of Alzheimer's disease and related dementias (ADRD), examining additive effects of sociodemographic, lifestyle, neurological and biobehavioral measures, and employing innovative, methodologically advanced modeling methods to characterize ADRD risk and resilience factors and transition of brain aging. Methods: HBI is a longitudinal, observational cohort study that will follow 500 deeply-phenotyped participants annually to collect, analyze, and store clinical, cognitive, behavioral, functional, genetic, and neuroimaging data and biospecimens. Participants are ≥50 years old; have no, subjective, or mild cognitive impairment; have a study partner; and are eligible to undergo magnetic resonance imaging (MRI). Recruitment is community-based including advertisements, word-of-mouth, community events, and physician referrals. At baseline, following informed consent, participants complete detailed web-based surveys (e.g., demographics, health history, risk and resilience factors), followed by two half-day visits which include neurological exams, cognitive and functional assessments, an overnight sleep study, and biospecimen collection. Structural and functional MRI is completed by all participants and a subset also consent to amyloid PET imaging. Annual follow-up visits repeat the same data and biospecimen collection as baseline, except that MRIs are conducted every other year after baseline. Ethics and expected impact: HBI has been approved by the University of Miami Miller School of Medicine Institutional Review Board. Participants provide informed consent at baseline and are re-consented as needed with protocol changes. Data collected by HBI will lead to breakthroughs in developing new diagnostics and therapeutics, create comprehensive diagnostic evaluations, and provide the evidence base for precision medicine approaches to dementia prevention with individualized treatment plans.

Hierarchical Two-Stage Cost-Sensitive Clinical Decision Support System for Screening Prodromal Alzheimer's Disease and Related Dementias.

BACKGROUND: The detection of subtle cognitive impairment in a clinical setting is difficult. Because time is a key factor in small clinics and research sites, the brief cognitive assessments that are relied upon often misclassify patients with very mild impairment as normal. OBJECTIVE: In this study, we seek to identify a parsimonious screening tool in one stage, followed by additional assessments in an optional second stage if additional specificity is desired, tested using a machine learning algorithm capable of being integrated into a clinical decision support system. METHODS: The best primary stage incorporated measures of short-term memory, executive and visuospatial functioning, and self-reported memory and daily living questions, with a total time of 5 minutes. The best secondary stage incorporated a measure of neurobiology as well as additional cognitive assessment and brief informant report questionnaires, totaling 30 minutes including delayed recall. Combined performance was evaluated using 25 sets of models, trained on 1,181 ADNI participants and tested on 127 patients from a memory clinic. RESULTS: The 5-minute primary stage was highly sensitive (96.5%) but lacked specificity (34.1%), with an AUC of 87.5% and diagnostic odds ratio of 14.3. The optional secondary stage increased specificity to 58.6%, resulting in an overall AUC of 89.7% using the best model combination of logistic regression and gradient-boosted machine. CONCLUSION: The primary stage is brief and effective at screening, with the optional two-stage technique further increasing specificity. The hierarchical two-stage technique exhibited similar accuracy but with reduced costs compared to the more common single-stage paradigm.

Exploring Reasons for Differential Vulnerability and Alzheimer's Disease Risk in Racial and Ethnic Minorities.

BACKGROUND: African American and Hispanic older adults are reported to have up to a 2-fold higher risk of Alzheimer's disease and related disorders (ADRD), but the reasons for this increased vulnerability have not been fully explored. The Vulnerability Index (VI) was designed to identify individuals who are at risk of developing cognitive impairment in the future, capturing 12 sociodemographic variables and modifiable medical comorbidities associated with higher ADRD risk. However, a prior limitation of the VI was that the original study cohort had limited diversity. We examined the association of the VI within and between non-Hispanic White, African American, and Hispanic older adults with and without cognitive impairment and different socioeconomic strata enrolled in a community-based dementia screening study. OBJECTIVE: To explore reasons for reported higher ADRD vulnerability in African Americans and Hispanics. METHODS: In a cross-sectional study of 300 non-Hispanic White, African American, and Hispanic older adults with and without cognitive impairment, we studied the association between cognitive status, the VI, and socioeconomic status (SES). RESULTS: When considering race/ethnicity, the presence of more vascular comorbidities drove greater vulnerability. When considering SES, vascular comorbidities played a less prominent role suggesting resources and access to care drives risk. The VI had differential effects on cognitive performance with the greatest effect in the earlier stages of impairment. CONCLUSION: Findings from this study provide a deeper understanding of the differential risk of ADRD in multicultural older adults captured by the VI and how barriers to healthcare access may increase vulnerability in racial/ethnic minorities.

The Brain Health Platform: Combining Resilience, Vulnerability, and Performance to Assess Brain Health and Risk of Alzheimer's Disease and Related Disorders.

BACKGROUND: It is difficult to assess brain health status and risk of cognitive impairment, particularly at the initial evaluation. To address this, we developed the Brain Health Platform to quantify brain health and identify Alzheimer's disease and related disorders (ADRD) risk factors by combining a measure of brain health: the Resilience Index (RI), a measure of risk of ADRD; the Vulnerability Index (VI); and the Number-Symbol Coding Task (NSCT), a measure of brain performance. OBJECTIVE: The Brain Health Platform is intended to be easily and quickly administered, providing an overview of a patient's risk of developing future impairment based on modifiable and non-modifiable factors as well as current cognitive performance. METHODS: This cross-sectional study comprehensively evaluated 230 participants (71 controls, 71 mild cognitive impairment, 88 ADRD). VI and RI scores were derived from physical assessments, lifestyle questionnaires, demographics, medical history, and neuropsychological examination including the NSCT. RESULTS: Individuals with abnormal scores were 95.7% likely to be impaired, with a misclassification rate of 9.7%. The combined model had excellent discrimination (AUC:0.923±0.053; p < 0.001), performing better than the Montreal Cognitive Assessment. CONCLUSION: The Brain Health Platform combines measures of resilience, vulnerability, and performance to provide a cross-sectional snapshot of overall brain health. The Brain Health Platform can effectively and accurately identify even the very mildest impairments due to ADRD, leveraging brief yet powerful and actionable indices of brain health and risk that could be used to develop personalized, precision medicine-like interventions.

Digital detection of dementia (D3): a study protocol for a pragmatic cluster-randomized trial examining the application of patient-reported outcomes and passive clinical decision support systems.

BACKGROUND: Early detection of Alzheimer's disease and related dementias (ADRD) in a primary care setting is challenging due to time constraints and stigma. The implementation of scalable, sustainable, and patient-driven processes may improve early detection of ADRD; however, there are competing approaches; information may be obtained either directly from a patient (e.g., through a questionnaire) or passively using electronic health record (EHR) data. In this study, we aim to identify the benefit of a combined approach using a pragmatic cluster-randomized clinical trial. METHODS: We have developed a Passive Digital Marker (PDM), based on machine learning algorithms applied to EHR data, and paired it with a patient-reported outcome (the Quick Dementia Rating Scale or QDRS) to rapidly share an identified risk of impairment to a patient's physician. Clinics in both south Florida and Indiana will be randomly assigned to one of three study arms: 1200 patients in each of the two populations will be administered either the PDM, the PDM with the QDRS, or neither, for a total of 7200 patients across all clinics and populations. Both incidence of ADRD diagnosis and acceptance into ADRD diagnostic work-up regimens is hypothesized to increase when patients are administered both the PDM and QDRS. Physicians performing the work-up regimens will be blind to the study arm of the patient. DISCUSSION: This study aims to test the accuracy and effectiveness of the two scalable approaches (PDM and QDRS) for the early detection of ADRD among older adults attending primary care practices. The data obtained in this study may lead to national early detection and management program for ADRD as an efficient and beneficial method of reducing the current and future burden of ADRD, as well as improving the annual rate of newly documented ADRD in primary care practices. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT05231954 . Registered February 9, 2022.

The Vulnerability Index: A weighted measure of dementia and cognitive impairment risk.

INTRODUCTION: A brief, easily calculated and interpretable index to assess vulnerability to developing cognitive impairment is needed in clinical practice and research. To address this, we developed the Vulnerability Index (VI) with the goal of identifying individuals possessing a high risk for cognitive impairment. METHODS: Twelve easily obtained sociodemographic, medical, and functional factors were used to develop the VI, with each selectively weighted based on factor analysis and predictive modeling. This cross-sectional study examined 387 subject-partner dyads. RESULTS: The VI was found to accurately discriminate between cognitively normal controls and participants with cognitive impairment (area under the curve [AUC]: 0.844; 95% confidence interval [CI]: 0.776-0.913) and individuals scoring high on the VI (≥8) had worse health, functional, behavioral, cognitive, and quality of life ratings than those with lower scores. DISCUSSION: The VI could be used in screening asymptomatic individuals for risk of cognitive impairment and guiding the development of primary and secondary prevention plans.

The Resilience Index: A Quantifiable Measure of Brain Health and Risk of Cognitive Impairment and Dementia.

BACKGROUND: There is increasing interest in lifestyle modification and integrative medicine approaches to treat and/or prevent mild cognitive impairment (MCI) and Alzheimer's disease and related dementias (ADRD). OBJECTIVE: To address the need for a quantifiable measure of brain health, we created the Resilience Index (RI). METHODS: This cross-sectional study analyzed 241 participants undergoing a comprehensive evaluation including the Clinical Dementia Rating and neuropsychological testing. Six lifestyle factors including physical activity, cognitive activity, social engagements, dietary patterns, mindfulness, and cognitive reserve were combined to derive the RI (possible range of scores: 1-378). Psychometric properties were determined. RESULTS: The participants (39 controls, 75 MCI, 127 ADRD) had a mean age of 74.6±9.5 years and a mean education of 15.8±2.6 years. The mean RI score was 138.2±35.6. The RI provided estimates of resilience across participant characteristics, cognitive staging, and ADRD etiologies. The RI showed moderate-to-strong correlations with clinical and cognitive measures and very good discrimination (AUC: 0.836; 95% CI: 0.774-0.897) between individuals with and without cognitive impairment (diagnostic odds ratio = 8.9). Individuals with high RI scores (> 143) had better cognitive, functional, and behavioral ratings than individuals with low RI scores. Within group analyses supported that controls, MCI, and mild ADRD cases with high RI had better cognitive, functional, and global outcomes than those with low RI. CONCLUSION: The RI is a brief, easy to administer, score and interpret assessment of brain health that incorporates six modifiable protective factors. Results from the RI could provide clinicians and researchers with a guide to develop personalized prevention plans to support brain health.

Using Optical Coherence Tomography to Screen for Cognitive Impairment and Dementia.

BACKGROUND: Screening for Alzheimer's disease and related disorders (ADRD) and mild cognitive impairment (MCI) could increase case identification, enhance clinical trial enrollment, and enable early intervention. MCI and ADRD screening would be most beneficial if detection measures reflect neurodegenerative changes. Optical coherence tomography (OCT) could be a marker of neurodegeneration (part of the amyloid-tau-neurodegeneration (ATN) framework). OBJECTIVE: To determine whether OCT measurements can be used as a screening measure to detect individuals with MCI and ADRD. METHODS: A retrospective cross-sectional study was performed on 136 participants with comprehensive clinical, cognitive, functional, and behavioral evaluations including OCT with a subset (n = 76) completing volumetric MRI. Pearson correlation coefficients tested strength of association between OCT and outcome measures. Receiver operator characteristic curves assessed the ability of OCT, patient-reported outcomes, and cognitive performance measures to discriminate between individuals with and without cognitive impairment. RESULTS: After controlling for age, of the 6 OCT measurements collected, granular cell layer-inner plexiform layer (GCL + IPL) thickness best correlated with memory, global cognitive performance, Clinical Dementia Rating, and hippocampal atrophy. GCL + IPL thickness provided good discrimination in cognitive status with a cut-off score of 75µm. Combining GCL + IPL thickness as a proxy marker for hippocampal atrophy with a brief patient-reported outcome and performance measure correctly classified 87%of MCI and ADRD participants. CONCLUSION: Multimodal approaches may improve recognition of MCI and ADRD. OCT has the potential to be a practical, non-invasive biomarker for ADRD providing a screening platform to quickly identify at-risk individuals for further clinical evaluation or research enrollment.

Characterization of dementia with Lewy bodies (DLB) and mild cognitive impairment using the Lewy body dementia module (LBD-MOD).

INTRODUCTION: The National Institute on Aging Alzheimer's Disease Research Center program added the Lewy body dementia module (LBD-MOD) to the Uniform Data Set to facilitate LBD characterization and distinguish dementia with Lewy bodies (DLB) from Alzheimer's disease (AD). We tested the performance of the LBD-MOD. METHODS: The LBD-MOD was completed in a single-site study in 342 participants: 53 controls, 78 AD, and 110 DLB; 79 mild cognitive impairment due to AD (MCI-AD); and 22 MCI-DLB. RESULTS: DLB differed from AD in extrapyramidal symptoms, hallucinations, apathy, autonomic features, REM sleep behaviors, daytime sleepiness, cognitive fluctuations, timed attention tasks, and visual perception. MCI-DLB differed from MCI-AD in extrapyramidal features, mood, autonomic features, fluctuations, timed attention tasks, and visual perception. Descriptive data on LBD-MOD measures are provided for reference. DISCUSSION: The LBD-MOD provided excellent characterization of core and supportive features to differentiate DLB from AD and healthy controls while also characterizing features of MCI-DLB.

Screening for Early-Stage Alzheimer's Disease Using Optimized Feature Sets and Machine Learning.

BACKGROUND: Detecting early-stage Alzheimer's disease in clinical practice is difficult due to a lack of efficient and easily administered cognitive assessments that are sensitive to very mild impairment, a likely contributor to the high rate of undetected dementia. OBJECTIVE: We aim to identify groups of cognitive assessment features optimized for detecting mild impairment that may be used to improve routine screening. We also compare the efficacy of classifying impairment using either a two-class (impaired versus non-impaired) or three-class using the Clinical Dementia Rating (CDR 0 versus CDR 0.5 versus CDR 1) approach. METHODS: Supervised feature selection methods generated groups of cognitive measurements targeting impairment defined at CDR 0.5 and above. Random forest classifiers then generated predictions of impairment for each group using highly stochastic cross-validation, with group outputs examined using general linear models. RESULTS: The strategy of combining impairment levels for two-class classification resulted in significantly higher sensitivities and negative predictive values, two metrics useful in clinical screening, compared to the three-class approach. Four features (delayed WAIS Logical Memory, trail-making, patient and informant memory questions), totaling about 15 minutes of testing time (∼30 minutes with delay), enabled classification sensitivity of 94.53% (88.43% positive predictive value, PPV). The addition of four more features significantly increased sensitivity to 95.18% (88.77% PPV) when added to the model as a second classifier. CONCLUSION: The high detection rate paired with the minimal assessment time of the four identified features may act as an effective starting point for developing screening protocols targeting cognitive impairment defined at CDR 0.5 and above.

Perception of being observed by a speaker alters gaze behavior.

Previous research has shown that gaze behavior of a speaker's face during speech encoding is influenced by an array of factors relating to the quality of the speech signal and the encoding task. In these studies, participants were aware they were viewing pre-recorded stimuli of a speaker that is not representative of natural social interactions in which an interlocutor can observe one's gaze direction, potentially affecting fixation behavior due to communicative and social considerations. To assess the potential role of these factors during speech encoding, we compared fixation behavior during a speech-encoding task under two conditions: in the "real-time" condition, we used deception to convince participants that they were interacting with a live person who was able to see and hear them through online remote video communication. In the "pre-recorded" condition, participants were correctly informed they were watching a previously recorded video. We found that participants fixated the interlocutor's face significantly less in the real-time condition than the pre-recorded condition. When participants did look at the face, they fixated the mouth at a higher proportion of the time in the pre-recorded condition versus the real-time condition. These findings suggest that people engage in avoidance of potentially useful speech-directed fixations when they believe their fixations are being observed and demonstrate that social factors play a significant role in fixation behavior during speech encoding.