Subjective Cognitive Decline Plus and Longitudinal Assessment and Risk for Cognitive Impairment.

Importance: Subjective cognitive decline (SCD) is recognized to be in the Alzheimer disease (AD) cognitive continuum. The SCD Initiative International Working Group recently proposed SCD-plus (SCD+) features that increase risk for future objective cognitive decline but that have not been assessed in a large community-based setting. Objective: To assess SCD risk for mild cognitive impairment (MCI), AD, and all-cause dementia, using SCD+ criteria among cognitively normal adults. Design, Setting, and Participants: The Framingham Heart Study, a community-based prospective cohort study, assessed SCD between 2005 and 2019, with up to 12 years of follow-up. Participants 60 years and older with normal cognition at analytic baseline were included. Cox proportional hazards (CPH) models were adjusted for baseline age, sex, education, APOE ε4 status, and tertiles of AD polygenic risk score (PRS), excluding the APOE region. Data were analyzed from May 2021 to November 2023. Exposure: SCD was assessed longitudinally using a single question and considered present if endorsed at the last cognitively normal visit. It was treated as a time-varying variable, beginning at the first of consecutive, cognitively normal visits, including the last, at which it was endorsed. Main Outcomes and Measures: Consensus-diagnosed MCI, AD, and all-cause dementia. Results: This study included 3585 participants (mean [SD] baseline age, 68.0 [7.7] years; 1975 female [55.1%]). A total of 1596 participants (44.5%) had SCD, and 770 (21.5%) were carriers of APOE ε4. APOE ε4 and tertiles of AD PRS status did not significantly differ between the SCD and non-SCD groups. MCI, AD, and all-cause dementia were diagnosed in 236 participants (6.6%), 73 participants (2.0%), and 89 participants (2.5%), respectively, during follow-up. On average, SCD preceded MCI by 4.4 years, AD by 6.8 years, and all-cause dementia by 6.9 years. SCD was significantly associated with survival time to MCI (hazard ratio [HR], 1.57; 95% CI, 1.22-2.03; P <.001), AD (HR, 2.98; 95% CI, 1.89-4.70; P <.001), and all-cause dementia (HR, 2.14; 95% CI, 1.44-3.18; P <.001). After adjustment for APOE and AD PRS, the hazards of SCD were largely unchanged. Conclusions and Relevance: Results of this cohort study suggest that in a community setting, SCD reflecting SCD+ features was associated with an increased risk of future MCI, AD, and all-cause dementia with similar hazards estimated in clinic-based settings. SCD may be an independent risk factor for AD and other dementias beyond the risk incurred by APOE ε4 and AD PRS.

Corrigendum: Digital neuropsychological measures by defense automated neurocognitive assessment: reference values and clinical correlates.

[This corrects the article DOI: 10.3389/fneur.2024.1340710.].

Disease-driven domain generalization for neuroimaging-based assessment of Alzheimer's disease.

Development of deep learning models to evaluate structural brain changes caused by cognitive impairment in MRI scans holds significant translational value. The efficacy of these models often encounters challenges due to variabilities arising from different data generation protocols, imaging equipment, radiological artifacts, and shifts in demographic distributions. Domain generalization (DG) techniques show promise in addressing these challenges by enabling the model to learn from one or more source domains and apply this knowledge to new, unseen target domains. Here we present a framework that utilizes model interpretability to enhance the generalizability of classification models across various cohorts. We used MRI scans and clinical diagnoses from four independent cohorts: Alzheimer's Disease Neuroimaging Initiative (ADNI, n = 1821), the Framingham Heart Study (FHS, n = 304), the Australian Imaging Biomarkers & Lifestyle Study of Ageing (AIBL, n = 661), and the National Alzheimer's Coordinating Center (NACC, n = 4647). With this data, we trained a deep neural network to focus on areas of the brain identified as relevant to the disease for model training. Our approach involved training a classifier to differentiate between structural neurodegeneration in individuals with normal cognition (NC), mild cognitive impairment (MCI), and dementia due to Alzheimer's disease (AD). This was achieved by aligning class-wise attention with a unified visual saliency prior, which was computed offline for each class using all the training data. Our method not only competes with state-of-the-art approaches but also shows improved correlation with postmortem histology. This alignment with the gold standard evidence is a significant step towards validating the effectiveness of DG frameworks, paving the way for their broader application in the field.

Digital neuropsychological measures by defense automated neurocognitive assessment: reference values and clinical correlates.

Introduction: Although the growth of digital tools for cognitive health assessment, there's a lack of known reference values and clinical implications for these digital methods. This study aims to establish reference values for digital neuropsychological measures obtained through the smartphone-based cognitive assessment application, Defense Automated Neurocognitive Assessment (DANA), and to identify clinical risk factors associated with these measures. Methods: The sample included 932 cognitively intact participants from the Framingham Heart Study, who completed at least one DANA task. Participants were stratified into subgroups based on sex and three age groups. Reference values were established for digital cognitive assessments within each age group, divided by sex, at the 2.5th, 25th, 50th, 75th, and 97.5th percentile thresholds. To validate these values, 57 cognitively intact participants from Boston University Alzheimer's Disease Research Center were included. Associations between 19 clinical risk factors and these digital neuropsychological measures were examined by a backward elimination strategy. Results: Age- and sex-specific reference values were generated for three DANA tasks. Participants below 60 had median response times for the Go-No-Go task of 796 ms (men) and 823 ms (women), with age-related increases in both sexes. Validation cohort results mostly aligned with these references. Different tasks showed unique clinical correlations. For instance, response time in the Code Substitution task correlated positively with total cholesterol and diabetes, but negatively with high-density lipoprotein and low-density lipoprotein cholesterol levels, and triglycerides. Discussion: This study established and validated reference values for digital neuropsychological measures of DANA in cognitively intact white participants, potentially improving their use in future clinical studies and practice.

Design and Feasibility Analysis of a Smartphone-Based Digital Cognitive Assessment Study in the Framingham Heart Study.

BACKGROUND: Smartphone-based digital technology is increasingly being recognized as a cost-effective, scalable, and noninvasive method of collecting longitudinal cognitive and behavioral data. Accordingly, a state-of-the-art 3-year longitudinal project focused on collecting multimodal digital data for early detection of cognitive impairment was developed. METHODS AND RESULTS: A smartphone application collected 2 modalities of cognitive data, digital voice and screen-based behaviors, from the FHS (Framingham Heart Study) multigenerational Generation 2 (Gen 2) and Generation 3 (Gen 3) cohorts. To understand the feasibility of conducting a smartphone-based study, participants completed a series of questions about their smartphone and app use, as well as sensory and environmental factors that they encountered while completing the tasks on the app. Baseline data collected to date were from 537 participants (mean age=66.6 years, SD=7.0; 58.47% female). Across the younger participants from the Gen 3 cohort (n=455; mean age=60.8 years, SD=8.2; 59.12% female) and older participants from the Gen 2 cohort (n=82; mean age=74.2 years, SD=5.8; 54.88% female), an average of 76% participants agreed or strongly agreed that they felt confident about using the app, 77% on average agreed or strongly agreed that they were able to use the app on their own, and 81% on average rated the app as easy to use. CONCLUSIONS: Based on participant ratings, the study findings are promising. At baseline, the majority of participants are able to complete the app-related tasks, follow the instructions, and encounter minimal barriers to completing the tasks independently. These data provide evidence that designing and collecting smartphone application data in an unsupervised, remote, and naturalistic setting in a large, community-based population is feasible.

Comparing Cognitive Tests and Smartphone-Based Assessment in 2 US Community-Based Cohorts.

BACKGROUND: Smartphone-based cognitive assessments have emerged as promising tools, bridging gaps in accessibility and reducing bias in Alzheimer disease and related dementia research. However, their congruence with traditional neuropsychological tests and usefulness in diverse cohorts remain underexplored. METHODS AND RESULTS: A total of 406 FHS (Framingham Heart Study) and 59 BHS (Bogalusa Heart Study) participants with traditional neuropsychological tests and digital assessments using the Defense Automated Neurocognitive Assessment (DANA) smartphone protocol were included. Regression models investigated associations between DANA task digital measures and a neuropsychological global cognitive Z score (Global Cognitive Score [GCS]), and neuropsychological domain-specific Z scores. FHS participants' mean age was 57 (SD, 9.75) years, and 44% (179) were men. BHS participants' mean age was 49 (4.4) years, and 28% (16) were men. Participants in both cohorts with the lowest neuropsychological performance (lowest quartile, GCS1) demonstrated lower DANA digital scores. In the FHS, GCS1 participants had slower average response times and decreased cognitive efficiency scores in all DANA tasks (P<0.05). In BHS, participants in GCS1 had slower average response times and decreased cognitive efficiency scores for DANA Code Substitution and Go/No-Go tasks, although this was not statistically significant. In both cohorts, GCS was significantly associated with DANA tasks, such that higher GCS correlated with faster average response times (P<0.05) and increased cognitive efficiency (all P<0.05) in the DANA Code Substitution task. CONCLUSIONS: Our findings demonstrate that smartphone-based cognitive assessments exhibit concurrent validity with a composite measure of traditional neuropsychological tests. This supports the potential of using smartphone-based assessments in cognitive screening across diverse populations and the scalability of digital assessments to community-dwelling individuals.

Disease-driven domain generalization for neuroimaging-based assessment of Alzheimer's disease.

Development of deep learning models to assess the degree of cognitive impairment on magnetic resonance imaging (MRI) scans has high translational significance. Performance of such models is often affected by potential variabilities stemming from independent protocols for data generation, imaging equipment, radiology artifacts, and demographic distributional shifts. Domain generalization (DG) frameworks have the potential to overcome these issues by learning signal from one or more source domains that can be transferable to unseen target domains. We developed an approach that leverages model interpretability as a means to improve generalizability of classification models across multiple cohorts. Using MRI scans and clinical diagnosis obtained from four independent cohorts (Alzheimer's Disease Neuroimaging Initiative (ADNI, n = 1,821), the Framingham Heart Study (FHS, n = 304), the Australian Imaging Biomarkers and Lifestyle Study of Ageing (AIBL, n = 661), and the National Alzheimer's Coordinating Center (NACC, n = 4,647)), we trained a deep neural network that used model-identified regions of disease relevance to inform model training. We trained a classifier to distinguish persons with normal cognition (NC) from those with mild cognitive impairment (MCI) and Alzheimer's disease (AD) by aligning class-wise attention with a unified visual saliency prior computed offline per class over all training data. Our proposed method competes with state-of-the-art methods with improved correlation with postmortem histology, thus grounding our findings with gold standard evidence and paving a way towards validating DG frameworks.

Fusion of Low-Level Descriptors of Digital Voice Recordings for Dementia Assessment.

Digital voice recordings can offer affordable, accessible ways to evaluate behavior and function. We assessed how combining different low-level voice descriptors can evaluate cognitive status. Using voice recordings from neuropsychological exams at the Framingham Heart Study, we developed a machine learning framework fusing spectral, prosodic, and sound quality measures early in the training cycle. The model's area under the receiver operating characteristic curve was 0.832 (±0.034) in differentiating persons with dementia from those who had normal cognition. This offers a data-driven framework for analyzing minimally processed voice recordings for cognitive assessment, highlighting the value of digital technologies in disease detection and intervention.

Multimodal deep learning for Alzheimer's disease dementia assessment.

Worldwide, there are nearly 10 million new cases of dementia annually, of which Alzheimer's disease (AD) is the most common. New measures are needed to improve the diagnosis of individuals with cognitive impairment due to various etiologies. Here, we report a deep learning framework that accomplishes multiple diagnostic steps in successive fashion to identify persons with normal cognition (NC), mild cognitive impairment (MCI), AD, and non-AD dementias (nADD). We demonstrate a range of models capable of accepting flexible combinations of routinely collected clinical information, including demographics, medical history, neuropsychological testing, neuroimaging, and functional assessments. We then show that these frameworks compare favorably with the diagnostic accuracy of practicing neurologists and neuroradiologists. Lastly, we apply interpretability methods in computer vision to show that disease-specific patterns detected by our models track distinct patterns of degenerative changes throughout the brain and correspond closely with the presence of neuropathological lesions on autopsy. Our work demonstrates methodologies for validating computational predictions with established standards of medical diagnosis.

The Boston Process Approach and Digital Neuropsychological Assessment: Past Research and Future Directions.

Neuropsychological assessment using the Boston Process Approach (BPA) suggests that an analysis of the strategy or the process by which tasks and neuropsychological tests are completed, and the errors made during test completion convey much information regarding underlying brain and cognition and are as important as overall summary scores. Research over the last several decades employing an analysis of process and errors has been able to dissociate between dementia patients diagnosed with Alzheimer's disease, vascular dementia associated with MRI-determined white matter alterations, and Parkinson's disease; and between mild cognitive impairment subtypes. Nonetheless, BPA methods can be labor intensive to deploy. However, the recent availability of digital platforms for neuropsychological test administration and scoring now enables reliable, rapid, and objective data collection. Further, digital technology can quantify highly nuanced data previously unobtainable to define neurocognitive constructs with high accuracy. In this paper, a brief review of the BPA is provided. Studies that demonstrate how digital technology translates BPA into specific neurocognitive constructs using the Clock Drawing Test, Backward Digit Span Test, and a Digital Pointing Span Test are described. Implications for using data driven artificial intelligence-supported analytic approaches enabling the creation of more sensitive and specific detection/diagnostic algorithms for putative neurodegenerative illness are also discussed.

Digital Neuropsychological Assessment: New Technology for Measuring Subtle Neuropsychological Behavior.

Technology has transformed the science and practice of medicine. In this special mini-forum, data using digital neuropsychological technology are reported. All of these papers demonstrate how coupling digital technology with standard paper and pencil neuropsychological tests are able to extract behavior not otherwise obtainable. As digital assessment methods mature, early identification of persons with emergent neurodegenerative and other neurological illness may be possible.

Advantages of Continuous-Valued Risk Scores for Predicting Long-Term Costs: The Framingham Coronary Heart Disease 10-Year Risk Score.

BACKGROUND: The few studies that have examined the relationship between midlife cardiovascular disease risk and longer-term costs have differentiated risk using a small number of risk categories. In this paper, we illustrate the advantages of a continuous-valued score to examine the relationship between risk and longer-term costs: the Framingham 10-year coronary heart disease risk score. METHODS: Our study cohort consisted of 1333 Second Generation Framingham Heart Study participants enrolled in fee-for-service Medicare for at least 8 quarters and who had a risk score assessment between age 40 and 50 years. We used generalized linear models to examine the relationships between quarterly Medicare costs and risk scores. RESULTS: Using risk categories defined by the Framingham score, the cost differences between a low and high risk group were 40% to over 200% greater than differences in comparable studies using a small number of risk categories. A continuous-valued score facilitates comparison of the cost consequences of impacting risk score changes. For example, an intervention that is able to reduce a person's score change between midlife and later-life from the 75th percentile to the 25th percentile would result in almost a 20% reduction in longer-term costs. In contrast, an intervention that is able to reduce a person's midlife score from the 75th percentile to the 25th percentile would result in a 38% reduction in costs. CONCLUSIONS: A continuous-valued risk score has advantages compared to defining risk based on a small number of risk categories.

Aging Well: Using Precision to Drive Down Costs and Increase Health Quality.

Efforts to provide patients with individualized treatments have led to tremendous breakthroughs in healthcare. However, a precision medicine approach alone will not offset the rapid increase in prevalence and burden of chronic non-communicable illnesses that is continuing to pervade the world's aging population. With rapid advances in technology, it is now possible to collect digital metrics to assess, monitor and detect chronic disease indicators, much earlier in the disease course, potentially redefining what was previously considered asymptomatic to pre-symptomatic. Data science and artificial intelligence can drive the discovery of digital biomarkers before the emergence of overt clinical symptoms, thereby transforming the current healthcare approach from one centered on precision medicine to a more comprehensive focus on precision health, and by doing so enable the possibility of preventing disease altogether. Presented herein are the challenges to the current healthcare model and the proposition of first steps for reversing the prevailing intractable trend of rising healthcare costs and poorer health quality.

Assessment of the Mid-Life Demographic and Lifestyle Risk Factors of Dementia Using Data from the Framingham Heart Study Offspring Cohort.

BACKGROUND: Dementia is the leading cause of dependence and disability in the elderly population worldwide. However, currently there is no effective medication for dementia treatment. Therefore, identifying lifestyle-related risk factors including some that are modifiable may provide important strategies for reducing risk of dementia. OBJECTIVE: This study aims to highlight associations between easily obtainable lifestyle risk factors in mid-life and dementia in later adulthood. METHODS: Using data from the Framingham Heart Study Offspring cohort, we leveraged well-known classification models (decision tree classifier and random forests) to associate demographic and lifestyle behavioral data with dementia status. We then evaluated model performance by computing area under receiver operating characteristic (ROC) curve. RESULTS: As expected, age was strongly associated with dementia. The analysis also identified 'widowed' marital status, lower BMI, and less sleep at mid-life as risk factors of dementia. The areas under the ROC curves were 0.79 for the decision tree, and 0.89 for the random forest model. CONCLUSION: Demographic and lifestyle factors that are non-invasive and inexpensive to implement can be assessed in midlife and used to potentially modify the risk of dementia in late adulthood. Classification models can help identify associations between dementia and midlife lifestyle risk factors. These findings inform further research, in order to help public health officials develop targeted programs for dementia prevention.

Evidence on the Validity of a Comprehensive Health Risk Index and Implications for Ambulatory Care and Population Health Management.

A novel, comprehensive health risk index for adults has been validated and is now ready for use to improve the health of individuals and populations. This health risk index provides an estimate of the avoidable risk of death for adults 30 years or older. It includes 12 evidence-based clinical and behavioral risk factors and was validated on discrimination and calibration using the NHANES (National Health and Nutrition Examination Survey) and Framingham Heart Study cohorts. The results from both cohorts were consistent and similar. Discrimination was good, and calibration was acceptable but tended to overpredict mortality risk for females in the higher-risk deciles.

How technology is reshaping cognitive assessment: Lessons from the Framingham Heart Study.

OBJECTIVE: This article elucidates how the Boston process approach (BPA) can amplify the role of neuropsychology in the study of preclinical and clinical dementia, particularly Alzheimer's disease (AD), and how advancements in technology expand BPA capacity objectively and exponentially. METHOD: The BPA is based on a conceptualization of cognition as being comprised of multiple processes, the nature of which could not possibly be captured by a single score on a test or battery of tests. Identification of these processes is only possible with careful observation of an individual during the entire testing process to determine how, when, and why a person fails, which helps to reveal the integrity of the cognitive processes underlying the behavior. RESULTS: BPA use within the Framingham Heart Study is described, including how digital technology has been incorporated to enhance the sensitivity of BPA to detect insidious onset changes even earlier than had been previously possible. The digital technology movement will dramatically alter the means by which cognitive function is assessed going forward. CONCLUSIONS: Technological advances will catalyze groundbreaking discoveries for effective treatments of neurodegenerative cognitive disorders, such as AD, and inform novel strategies for dementia prevention and sustained lifelong cognitive health. (PsycINFO Database Record

Long-term exposure to fine particulate matter, residential proximity to major roads and measures of brain structure.

BACKGROUND AND PURPOSE: Long-term exposure to ambient air pollution is associated with cerebrovascular disease and cognitive impairment, but whether it is related to structural changes in the brain is not clear. We examined the associations between residential long-term exposure to ambient air pollution and markers of brain aging using magnetic resonance imaging. METHODS: Framingham Offspring Study participants who attended the seventh examination were at least 60 years old and free of dementia and stroke were included. We evaluated associations between exposures (fine particulate matter [PM2.5] and residential proximity to major roadways) and measures of total cerebral brain volume, hippocampal volume, white matter hyperintensity volume (log-transformed and extensive white matter hyperintensity volume for age), and covert brain infarcts. Models were adjusted for age, clinical covariates, indicators of socioeconomic position, and temporal trends. RESULTS: A 2-µg/m(3) increase in PM2.5 was associated with -0.32% (95% confidence interval, -0.59 to -0.05) smaller total cerebral brain volume and 1.46 (95% confidence interval, 1.10 to 1.94) higher odds of covert brain infarcts. Living further away from a major roadway was associated with 0.10 (95% confidence interval, 0.01 to 0.19) greater log-transformed white matter hyperintensity volume for an interquartile range difference in distance, but no clear pattern of association was observed for extensive white matter. CONCLUSIONS: Exposure to elevated levels of PM2.5 was associated with smaller total cerebral brain volume, a marker of age-associated brain atrophy, and with higher odds of covert brain infarcts. These findings suggest that air pollution is associated with insidious effects on structural brain aging even in dementia- and stroke-free persons.

Cardiac index is associated with brain aging: the Framingham Heart Study.

BACKGROUND: Cardiac dysfunction is associated with neuroanatomic and neuropsychological changes in aging adults with prevalent cardiovascular disease, theoretically because systemic hypoperfusion disrupts cerebral perfusion, contributing to subclinical brain injury. We hypothesized that cardiac function, as measured by cardiac index, would be associated with preclinical brain magnetic resonance imaging (MRI) and neuropsychological markers of ischemia and Alzheimer disease in the community. METHODS AND RESULTS: Brain MRI, cardiac MRI, neuropsychological, and laboratory data were collected on 1504 Framingham Offspring Cohort participants free of clinical stroke, transient ischemic attack, or dementia (age, 61+/-9 years; 54% women). Neuropsychological and brain MRI variables were related to cardiac MRI-assessed cardiac index (cardiac output/body surface area). In multivariable-adjusted models, cardiac index was positively related to total brain volume (P=0.03) and information processing speed (P=0.02) and inversely related to lateral ventricular volume (P=0.048). When participants with clinically prevalent cardiovascular disease were excluded, the relation between cardiac index and total brain volume remained (P=0.02). Post hoc comparisons revealed that participants in the bottom cardiac index tertile (values <2.54) and middle cardiac index tertile (values between 2.54 and 2.92) had significantly lower brain volumes (P=0.04) than participants in the top cardiac index tertile (values >2.92). CONCLUSIONS: Although observational data cannot establish causality, our findings are consistent with the hypothesis that decreasing cardiac function, even at normal cardiac index levels, is associated with accelerated brain aging.