Predicting risk of dementia in older adults: The late-life dementia risk index

Cross-cultural adaptation and validation of the Australian National University Alzheimer Disease Risk Index (ANU-ADRI) for Chinese community-dwelling residents: A cross-sectional Study

OBJECTIVE

To cross-culturally adapt the Australian National University Alzheimer Disease Risk Index (ANU-ADRI) and verify the reliability and validity of its cognitive activity domain.

METHODS

According to Beaton's guidelines, the ANU-ADRI was were translated into Chinese. The psychometric properties of ANU-ADRI its cognitive activity was conducted among community-dwelling residents (n = 442) in Changchun, Harbin and Hegang from December 2021 to July 2023.

RESULTS

The Chinese version of the ANU-ADRI had good content validity and face validity. Exploratory factor analysis of cognitive activity revealed a 3-factor structure, with a cumulative variance contribution rate of 64.124 %. Confirmatory factor analysis revealed a good model fit (x2/df = 1.664, RMSEA = 0.055, RMR = 0.090, GFI = 0.942, CFI = 0.919, IFI = 0.921, TLI = 0.902, and NFI = 0.824). The internal consistency (Cronbach's α = 0.807) and test-retest reliability (ICC = 0.787) were considered satisfactory.

CONCLUSION

The ANU-ADRI showed acceptable reliability and validity for assessing risk factors for Alzheimer's disease among middle-aged and elderly community-dwelling residents.

The Association Between Physical Activity and Cognition in a Racially/Ethnically Diverse Cohort of Older Adults: Results From the Kaiser Healthy Aging and Diverse Life Experiences Study

OBJECTIVE

Most prior research on physical activity (PA) and cognition is based on predominantly white cohorts and focused on associations of PA with mean (average) cognition versus the distribution of cognition. Quantile regression offers a novel way to quantify how PA affects cognition across the entire distribution.

METHODS

The Kaiser Healthy Aging and Diverse Life Experiences study includes 30% white, 19% black, 25% Asian, and 26% Latinx adults age 65+ living in Northern California (n = 1600). The frequency of light or heavy PA was summarized as 2 continuous variables. Outcomes were z-scored executive function, semantic memory, and verbal episodic memory. We tested associations of PA with mean cognition using linear regression and used quantile regression to estimate the association of PA with the 10th-90th percentiles of cognitive scores.

RESULTS

Higher levels of PA were associated with higher mean semantic memory (b = 0.10; 95% CI: 0.06, 0.14) and executive function (b = 0.05; 95% CI: 0.01, 0.09). Associations of PA across all 3 cognitive domains were stronger at low quantiles of cognition.

CONCLUSION

PA is associated with cognition in this racially/ethnically diverse sample and may have larger benefits for individuals with low cognitive scores, who are most vulnerable to dementia.

The predictive validity of a Brain Care Score for dementia and stroke: data from the UK Biobank cohort

Introduction

The 21-point Brain Care Score (BCS) was developed through a modified Delphi process in partnership with practitioners and patients to promote behavior changes and lifestyle choices in order to sustainably reduce the risk of dementia and stroke. We aimed to assess the associations of the BCS with risk of incident dementia and stroke.

Methods

The BCS was derived from the United Kingdom Biobank (UKB) baseline evaluation for participants aged 40-69 years, recruited between 2006-2010. Associations of BCS and risk of subsequent incident dementia and stroke were estimated using Cox proportional hazard regressions, adjusted for sex assigned at birth and stratified by age groups at baseline.

Results

The BCS (median: 12; IQR:11-14) was derived for 398,990 UKB participants (mean age: 57; females: 54%). There were 5,354 incident cases of dementia and 7,259 incident cases of stroke recorded during a median follow-up of 12.5 years. A five-point higher BCS at baseline was associated with a 59% (95%CI: 40-72%) lower risk of dementia among participants aged <50. Among those aged 50-59, the figure was 32% (95%CI: 20-42%) and 8% (95%CI: 2-14%) for those aged >59 years. A five-point higher BCS was associated with a 48% (95%CI: 39-56%) lower risk of stroke among participants aged <50, 52% (95%CI, 47-56%) among those aged 50-59, and 33% (95%CI, 29-37%) among those aged >59.

Discussion

The BCS has clinically relevant and statistically significant associations with risk of dementia and stroke in approximately 0.4 million UK people. Future research includes investigating the feasibility, adaptability and implementation of the BCS for patients and providers worldwide.

Logistic regression with sparse common and distinctive covariates

Having large sets of predictor variables from multiple sources concerning the same individuals is becoming increasingly common in behavioral research. On top of the variable selection problem, predicting a categorical outcome using such data gives rise to an additional challenge of identifying the processes at play underneath the predictors. These processes are of particular interest in the setting of multi-source data because they can either be associated individually with a single data source or jointly with multiple sources. Although many methods have addressed the classification problem in high dimensionality, the additional challenge of distinguishing such underlying predictor processes from multi-source data has not received sufficient attention. To this end, we propose the method of Sparse Common and Distinctive Covariates Logistic Regression (SCD-Cov-logR). The method is a multi-source extension of principal covariates regression that combines with generalized linear modeling framework to allow classification of a categorical outcome. In a simulation study, SCD-Cov-logR resulted in outperformance compared to related methods commonly used in behavioral sciences. We also demonstrate the practical usage of the method under an empirical dataset.

Development and validation of risk of CPS decline (RCD): a new prediction tool for worsening cognitive performance among home care clients in Canada

BACKGROUND

To develop and validate a prediction tool, or nomogram, for the risk of a decline in cognitive performance based on the interRAI Cognitive Performance Scale (CPS).

METHODS

Retrospective, population-based, cohort study using Canadian Resident Assessment Instrument for Home Care (RAI-HC) data, collected between 2010 and 2018. Eligible home care clients, aged 18+, with at least two assessments were selected randomly for model derivation (75%) and validation (25%). All clients had a CPS score of zero (intact) or one (borderline intact) on intake into the home care program, out of a possible score of six. All individuals had to remain as home care recipients for the six months observation window in order to be included in the analysis. The primary outcome was any degree of worsening (i.e., increase) on the CPS score within six months. Using the derivation cohort, we developed a multivariable logistic regression model to predict the risk of a deterioration in the CPS score. Model performance was assessed on the validation cohort using discrimination and calibration plots.

RESULTS

We identified 39,292 eligible home care clients, with a median age of 79.0 years, 62.3% were female, 38.8% were married and 38.6% lived alone. On average, 30.3% experienced a worsening on the CPS score within the six-month window (i.e., a change from 0 or 1 to 2, 3, 4, 5, or 6). The final model had good discrimination (c-statistic of 0.65), with excellent calibration.

CONCLUSIONS

The model accurately predicted the risk of deterioration on the CPS score over six months among home care clients. This type of predictive model may provide useful information to support decisions for home care clinicians who use interRAI data internationally.

HomeADScreen: Developing Alzheimer's disease and related dementia risk identification model in home healthcare

BACKGROUND

More than 50 % of patients with Alzheimer's disease and related dementia (ADRD) remain undiagnosed. This is specifically the case for home healthcare (HHC) patients.

OBJECTIVES

This study aimed at developing HomeADScreen, an ADRD risk screening model built on the combination of HHC patients' structured data and information extracted from HHC clinical notes.

METHODS

The study's sample included 15,973 HHC patients with no diagnosis of ADRD and 8,901 patients diagnosed with ADRD across four follow-up time windows. First, we applied two natural language processing methods, Word2Vec and topic modeling methods, to extract ADRD risk factors from clinical notes. Next, we built the risk identification model on the combination of the Outcome and Assessment Information Set (OASIS-structured data collected in the HHC setting) and clinical notes-risk factors across the four-time windows.

RESULTS

The top-performing machine learning algorithm attained an Area under the Curve = 0.76 for a four-year risk prediction time window. After optimizing the cut-off value for screening patients with ADRD (cut-off-value = 0.31), we achieved sensitivity = 0.75 and an F1-score = 0.63. For the first-year time window, adding clinical note-derived risk factors to OASIS data improved the overall performance of the risk identification model by 60 %. We observed a similar trend of increasing the model's overall performance across other time windows. Variables associated with increased risk of ADRD were "hearing impairment" and "impaired patient ability in the use of telephone." On the other hand, being "non-Hispanic White" and the "absence of impairment with prior daily functioning" were associated with a lower risk of ADRD.

CONCLUSION

HomeADScreen has a strong potential to be translated into clinical practice and assist HHC clinicians in assessing patients' cognitive function and referring them for further neurological assessment.

Using Hypothesis-Led Machine Learning and Hierarchical Cluster Analysis to Identify Disease Pathways Prior to Dementia: Longitudinal Cohort Study

BACKGROUND

Dementia development is a complex process in which the occurrence and sequential relationships of different diseases or conditions may construct specific patterns leading to incident dementia.

OBJECTIVE

This study aimed to identify patterns of disease or symptom clusters and their sequences prior to incident dementia using a novel approach incorporating machine learning methods.

METHODS

Using Taiwan's National Health Insurance Research Database, data from 15,700 older people with dementia and 15,700 nondementia controls matched on age, sex, and index year (n=10,466, 67% for the training data set and n=5234, 33% for the testing data set) were retrieved for analysis. Using machine learning methods to capture specific hierarchical disease triplet clusters prior to dementia, we designed a study algorithm with four steps: (1) data preprocessing, (2) disease or symptom pathway selection, (3) model construction and optimization, and (4) data visualization.

RESULTS

Among 15,700 identified older people with dementia, 10,466 and 5234 subjects were randomly assigned to the training and testing data sets, and 6215 hierarchical disease triplet clusters with positive correlations with dementia onset were identified. We subsequently generated 19,438 features to construct prediction models, and the model with the best performance was support vector machine (SVM) with the by-group LASSO (least absolute shrinkage and selection operator) regression method (total corresponding features=2513; accuracy=0.615; sensitivity=0.607; specificity=0.622; positive predictive value=0.612; negative predictive value=0.619; area under the curve=0.639). In total, this study captured 49 hierarchical disease triplet clusters related to dementia development, and the most characteristic patterns leading to incident dementia started with cardiovascular conditions (mainly hypertension), cerebrovascular disease, mobility disorders, or infections, followed by neuropsychiatric conditions.

CONCLUSIONS

Dementia development in the real world is an intricate process involving various diseases or conditions, their co-occurrence, and sequential relationships. Using a machine learning approach, we identified 49 hierarchical disease triplet clusters with leading roles (cardio- or cerebrovascular disease) and supporting roles (mental conditions, locomotion difficulties, infections, and nonspecific neurological conditions) in dementia development. Further studies using data from other countries are needed to validate the prediction algorithms for dementia development, allowing the development of comprehensive strategies to prevent or care for dementia in the real world.

Modifiable cardiovascular risk factors and genetics for targeted prevention of dementia

Dementia is a major global challenge for health and social care in the 21st century. A third of individuals >65 years of age die with dementia, and worldwide incidence numbers are projected to be higher than 150 million by 2050. Dementia is, however, not an inevitable consequence of old age; 40% of dementia may theoretically be preventable. Alzheimer's disease (AD) accounts for approximately two-thirds of dementia cases and the major pathological hallmark of AD is accumulation of amyloid-β. Nevertheless, the exact pathological mechanisms of AD remain unknown. Cardiovascular disease and dementia share several risk factors and dementia often coexists with cerebrovascular disease. In a public health perspective, prevention is crucial, and it is suggested that a 10% reduction in prevalence of cardiovascular risk factors could prevent more than nine million dementia cases worldwide by 2050. Yet this assumes causality between cardiovascular risk factors and dementia and adherence to the interventions over decades for a large number of individuals. Using genome-wide association studies, the entire genome can be scanned for disease/trait associated loci in a hypothesis-free manner, and the compiled genetic information is not only useful for pinpointing novel pathogenic pathways but also for risk assessments. This enables identification of individuals at high risk, who likely will benefit the most from a targeted intervention. Further optimization of the risk stratification can be done by adding cardiovascular risk factors. Additional studies are, however, highly needed to elucidate dementia pathogenesis and potential shared causal risk factors between cardiovascular disease and dementia.

A flexible modeling approach for biomarker-based computation of absolute risk of Alzheimer's disease dementia

INTRODUCTION

As Alzheimer's disease (AD) biomarkers rapidly develop, tools are needed that accurately and effectively communicate risk of AD dementia.

METHODS

We analyzed longitudinal data from >10,000 cognitively unimpaired older adults. Five-year risk of AD dementia was modeled using survival analysis.

RESULTS

A demographic model was developed and validated on independent data with area under the receiver operating characteristic curve (AUC) for 5-year prediction of AD dementia of 0.79. Clinical and cognitive variables (AUC = 0.79), and apolipoprotein E genotype (AUC = 0.76) were added to the demographic model. We then incorporated the risk computed from the demographic model with hazard ratios computed from independent data for amyloid positron emission tomography status and magnetic resonance imaging hippocampal volume (AUC = 0.84), and for plasma amyloid beta (Aβ)42/Aβ40 (AUC = 0.82).

DISCUSSION

An adaptive tool was developed and validated to compute absolute risks of AD dementia. This approach allows for improved accuracy and communication of AD risk among cognitively unimpaired older adults.

Screening for preclinical Alzheimer's disease: Deriving optimal policies using a partially observable Markov model

Alzheimer's Disease (AD) is believed to be the most common type of dementia. Even though screening for AD has been discussed widely, there is no screening program implemented as part of a policy in any country. Current medical research motivates focusing on the preclinical stages of the disease in a modeling initiative. We develop a partially observable Markov decision process model to determine optimal screening programs. The model contains disease free and preclinical AD partially observable states and the screening decision is taken while an individual is in one of those states. An observable diagnosed preclinical AD state is integrated along with observable mild cognitive impairment, AD and death states. Transition probabilities among states are estimated using data from Knight Alzheimer's Disease Research Center (KADRC) and relevant literature. With an objective of maximizing expected total quality-adjusted life years (QALYs), the output of the model is an optimal screening program that specifies at what points in time an individual over 50 years of age with a given risk of AD will be directed to undergo screening. The screening test used to diagnose preclinical AD has a positive disutility, is imperfect and its sensitivity and specificity are estimated using the KADRC data set. We study the impact of a potential intervention with a parameterized effectiveness and disutility on model outcomes for three different risk profiles (low, medium and high). When intervention effectiveness and disutility are at their best, the optimal screening policy is to screen every year between ages 50 and 95, with an overall QALY gain of 0.94, 1.9 and 2.9 for low, medium and high risk profiles, respectively. As intervention effectiveness diminishes and/or its disutility increases, the optimal policy changes to sporadic screening and then to never screening. Under several scenarios, some screening within the time horizon is optimal from a QALY perspective. Moreover, an in-depth analysis of costs reveals that implementing these policies are either cost-saving or cost-effective.

Modified dementia risk score as a tool for the prediction of dementia: a prospective cohort study of 239745 participants

Based on risk profiles, several approaches for predicting dementia risk have been developed. Predicting the risk of dementia with accuracy is a significant clinical challenge. The goal was to create a modified dementia risk score (MDRS) based on a big sample size. A total of 239,745 participants from UK Biobank were studied (mean follow-up of 8.7 years). The score value of each risk factor was estimated according to the β coefficient in the logistic regression model. The total dementia risk score was the sum of each risk score. Kaplan Meier survival curves and Cox proportional hazards analyses were used to assess the associations between total score and dementia. Among all participants included, 3531 incident cases of all-cause dementia (ACD), 1729 cases of Alzheimer's disease (AD), and 925 cases of vascular dementia (VD) were identified. Several vascular risk factors (physical activity, current smoking status, and glycemic status) and depressive symptoms were found to be significantly related to dementia risk. The modified dementia risk scores predicted dementia well (model 1, area under curve 0.810; model 2, area under curve 0.832). In model 1, the cut-off value for high risk (HR) was 81 or higher, and in model 2 (including the APOE4), it was 98 or higher. According to Kaplan-Meier survival analyses, patients in the HR group had faster clinical progression (p < 0.0001) in either model 1 or 2. Cox regression analyses for HR versus low risk (LR) revealed that the Hazard radio for ACD was 7.541 (6.941 to 8.193) in model 1 and 8.348 (7.727 to 9.019) in model 2. MDRS is appropriate for dementia primary prevention, and may help quickly identify individuals with elevated risk of dementia.

Development and validation of a risk model for cognitive impairment in the older Chinese inpatients: An analysis based on a 5-year database

Early diagnosis of cognitive impairment is important but difficult. Prediction models may work as an efficient way to identify high risk individuals for this disease. This study aimed to develop a simple and convenient model to identify high-risk individuals of cognitive impairment in the older Chinese inpatients. We enrolled 1300 inpatients aged 60 years or above from the department of geriatrics of the First Affiliated Hospital of Chongqing Medical University during 2013 to 2017. The model for cognitive impairment was established in the developing cohort of 1100 participants and tested in another validating cohort of 200 participants. Logistic regression analyses were used to identify the candidate variables of cognitive impairment. Receiver operating curve was adopted to validate the model. Logistic regression analyses showed that increasing age, diabetes, depression and low educational level were independently associated with cognitive impairment. The model was generated in the following way: P_model = e^y/(1 + e^y), where y = -6.874 + 0.088 * age + 0.317 * diabetes + 0.647 * depression + 0.345 * education level. The value of P_model indicates the probability of cognitive impairment for each patient. The present model proved to be a reliable marker for identifying people at high risk of cognitive impairment (area under curve = 0.790, 95% CI = 0.728-0.852, p < 0.001). It had a high sensitivity (86.2%) but a relatively low specificity (59.4%). It may be helpful to "recognize" those at high risk of cognitive impairment rather than "rule out" those at low risk of this disease.

Determining Vascular Risk Factors for Dementia and Dementia Risk Prediction Across Mid- to Later Life: The Framingham Heart Study

BACKGROUND AND OBJECTIVES

The association between vascular risk factors and dementia varies with age, making generalizability of dementia risk prediction rules to individuals of different ages challenging. We determined the most important vascular risk factors for inclusion in age-specific dementia risk scores.

METHODS

Framingham Heart Study Original and Offspring cohort participants with available data on the Framingham Stroke Risk Profile (FSRP) at midlife (age 55; n = 4,899, 57% women), late life (ages 65 or 70), or later life (ages 75 or 80 [n = 2,386, 62% women]) were followed for 10-year incident dementia risk from ages 65, 70, 75, and 80.

RESULTS

Age- and sex-adjusted midlife risk factors associated with 10-year risk of dementia from age 65 included FSRP (hazard ratio [HR] 1.16, 95% CI 1.06-1.26, per 1 SD increment in log-transformed score), diabetes mellitus (DM; HR 4.31, 95% CI 1.97-9.43), and systolic blood pressure (SBP; HR 1.12, 95% CI 1.02-1.24, per 10 mm Hg increment). Late-life risk factors associated with 10-year incident dementia from ages 65 or 70 included FSRP (age 65 only: HR 1.06, 95% CI 1.02-1.10), antihypertensive use (age 65 reported: HR 1.66, 95% CI 1.12-2.46), DM (age 65 reported: HR 1.96, 95% CI 1.09-3.52), atrial fibrillation (age 65 reported: HR 2.30, 95% CI 1.00-5.27), nonstroke cardiovascular disease (nsCVD; age 65 reported: HR 1.95, 95% CI 1.24-3.07), and stroke (age 70 only: HR 3.61, 95% CI 2.21-5.92). Later-life risk factors associated with 10-year incident dementia from ages 75 or 80 included antihypertensive use (age 80 only: HR 0.74, 95% CI 0.62-0.89), DM (age 80 reported: HR 1.40, 95% CI 1.04-1.89), atrial fibrillation (age 80 reported: HR 1.43, 95% CI 1.07-1.92), and stroke (age 80 reported: HR 1.63, 95% CI 1.13-2.35). In stepwise models, SBP and DM at age 55, nsCVD at age 65, DM and stroke at ages 70 and 75, and DM, stroke, and use of antihypertensives (protective) at age 80 were the most important vascular risk factors for dementia.

DISCUSSION

Our findings support the use of age-specific dementia risk scores, which should prioritize including, at age 55, SBP and DM; at age 65, nsCVD; at ages 70 and 75, DM and stroke; and at age 80, DM, stroke, and antihypertensive use.

Dementia Risk Scores and Their Role in the Implementation of Risk Reduction Guidelines

Dementia prevention is a global health priority. In 2019, the World Health Organisation published its first evidence-based guidelines on dementia risk reduction. We are now at the stage where we need effective tools and resources to assess dementia risk and implement these guidelines into policy and practice. In this paper we review dementia risk scores as a means to facilitate this process. Specifically, we (a) discuss the rationale for dementia risk assessment, (b) outline some conceptual and methodological issues to consider when reviewing risk scores, (c) evaluate some dementia risk scores that are currently in use, and (d) provide some comments about future directions. A dementia risk score is a weighted composite of risk factors that reflects the likelihood of an individual developing dementia. In general, dementia risks scores have a wide range of implementations and benefits including providing early identification of individuals at high risk, improving risk perception for patients and physicians, and helping health professionals recommend targeted interventions to improve lifestyle habits to decrease dementia risk. A number of risk scores for dementia have been published, and some are widely used in research and clinical trials e.g., CAIDE, ANU-ADRI, and LIBRA. However, there are some methodological concerns and limitations associated with the use of these risk scores and more research is needed to increase their effectiveness and applicability. Overall, we conclude that, while further refinement of risk scores is underway, there is adequate evidence to use these assessments to implement guidelines on dementia risk reduction.

The Association between Late-Life Alcohol Consumption and Incident Dementia among Mexican Americans Aged 75 and Older

Background: Evidence for late-life alcohol consumption being associated with reduced dementia risk is largely based on cohort studies of predominately non-Hispanic white older adults. Our objective was to investigate the relationship between late-life alcohol consumption and dementia risk among Mexican-America adults aged 75 and older. Methods: This study was a retrospective analysis of waves 5 (2004/05) to 8 (2012/13) of the Hispanic Established Populations for the Epidemiologic Study of the Elderly. The final sample included 1,255 participants. Late-life alcohol consumption status was classified as life-long abstainer, former drinker, and current drinker. Dementia was defined as a score of 18 points or lower on the Mini-Mental Status Examination or a proxy-reported diagnosis of dementia. Results: 41.8% of participants were life-long abstainers, 42.0% were former drinkers, and 16.3% were current drinkers. Current alcohol consumers had significantly lower dementia risk compared to life-long abstainers (HR=0.63, 95% CI = 0.44–0.89). Dementia risk for former alcohol consumers compared to life-long abstainers was not statistically significant (HR = 0.85, 95% CI = 0.67–1.09). Conclusions: Current alcohol consumption was associated with lower dementia risk for Mexican Americans aged 75 and older. Continued research is needed to identify pathways for the protective association between late life alcohol consumption and dementia risk.

Multi-domain interventions for the prevention of dementia and cognitive decline

BACKGROUND

Dementia is a worldwide concern. Its global prevalence is increasing. Currently, no effective medical treatment exists to cure or to delay the onset of cognitive decline or dementia. Up to 40% of dementia is attributable to potentially modifiable risk factors, which has led to the notion that targeting these risk factors might reduce the incidence of cognitive decline and dementia. Since sporadic dementia is a multifactorial condition, thought to derive from multiple causes and risk factors, multi-domain interventions may be more effective for the prevention of dementia than those targeting single risk factors.

OBJECTIVES

To assess the effects of multi-domain interventions for the prevention of cognitive decline and dementia in older adults, including both unselected populations and populations at increased risk of cognitive decline and dementia.

SEARCH METHODS

We searched ALOIS, the Cochrane Dementia and Cognitive Improvement Group's register, MEDLINE (Ovid SP), Embase (Ovid SP), PsycINFO (Ovid SP), CINAHL (EBSCOhost), Web of Science Core Collection (ISI Web of Science), LILACS (BIREME), and ClinicalTrials.gov on 28 April 2021. We also reviewed citations of reference lists of included studies, landmark papers, and review papers to identify additional studies and assessed their suitability for inclusion in the review.

SELECTION CRITERIA

We defined a multi-domain intervention as an intervention with more than one component, pharmacological or non-pharmacological, but not consisting only of two or more drugs with the same therapeutic target. We included randomised controlled trials (RCTs) evaluating the effect of such an intervention on cognitive functioning and/or incident dementia. We accepted as control conditions any sham intervention or usual care, but not single-domain interventions intended to reduce dementia risk. We required studies to have a minimum of 400 participants and an intervention and follow-up duration of at least 12 months.

DATA COLLECTION AND ANALYSIS

We initially screened search results using a 'crowdsourcing' method in which members of Cochrane's citizen science platform identify RCTs. We screened the identified citations against inclusion criteria by two review authors working independently. At least two review authors also independently extracted data, assessed the risk of bias and applied the GRADE approach to assess the certainty of evidence. We defined high-certainty reviews as trials with a low risk of bias across all domains other than blinding of participants and personnel involved in administering the intervention (because lifestyle interventions are difficult to blind). Critical outcomes were incident dementia, incident mild cognitive impairment (MCI), cognitive decline measured with any validated measure, and mortality. Important outcomes included adverse events (e.g. cardiovascular events), quality of life, and activities of daily living (ADL).  Where appropriate, we synthesised data in random-effects meta-analyses. We expressed treatment effects as risk ratios (RRs) and mean differences (MDs) with 95% confidence intervals (CIs).

MAIN RESULTS

We included nine RCTs (18.452 participants) in this review. Two studies reported incident dementia as an outcome; all nine studies reported a measure for cognitive functioning. Assessment of cognitive functioning was very heterogeneous across studies, ranging from complete neuropsychological assessments to short screening tests such as the mini-mental state examination (MMSE). The duration of the interventions varied from 12 months to 10 years. We compared multi-domain interventions against usual care or a sham intervention. Positive MDs and RRs <1 favour multi-domain interventions over control interventions. For incident dementia, there was no evidence of a difference between the multi-domain intervention group and the control group (RR 0.94, 95% CI 0.76 to 1.18; 2 studies; 7256 participants; high-certainty evidence). There was a small difference in composite Z-score for cognitive function measured with a neuropsychological test battery (NTB) (MD 0.03, 95% CI 0.01 to 0.06; 3 studies; 4617 participants; high-certainty evidence) and with the Montreal Cognitive Assessment (MoCA) scale (MD 0.76 point, 95% CI 0.05 to 1.46; 2 studies; 1554 participants), but the certainty of evidence for the MoCA was very low (due to serious risk of bias, inconsistency and indirectness) and there was no evidence of an effect on the MMSE (MD 0.02 point, 95% CI -0.06 to 0.09; 6 studies; 8697participants; moderate-certainty evidence). There was no evidence of an effect on mortality (RR 0.93, 95% CI 0.84 to 1.04; 4 studies; 11,487 participants; high-certainty evidence). There was high-certainty evidence for an interaction of the multi-domain intervention with ApoE4 status on the outcome of cognitive function measured with an NTB (carriers MD 0.14, 95% CI 0.04 to 0.25, noncarriers MD 0.04, 95% CI -0.02 to 0.10, P for interaction 0.09). There was no clear evidence for an interaction with baseline cognitive status (defined by MMSE-score) on cognitive function measured with an NTB (low baseline MMSE group MD 0.06, 95% CI 0.01 to 0.11, high baseline MMSE group MD 0.01, 95% CI -0.01 to 0.04, P for interaction 0.12), nor was there clear evidence for an effect in participants with a Cardiovascular Risk Factors, Aging, and Incidence of Dementia (CAIDE) score > 6 points (MD 0.07, 95%CI -0.00 to 0.15).

AUTHORS' CONCLUSIONS

We found no evidence that multi-domain interventions can prevent incident dementia based on two trials. There was a small improvement in cognitive function assessed by a NTB in the group of participants receiving a multi-domain intervention, although this effect was strongest in trials offering cognitive training within the multi-domain intervention, making it difficult to rule out a potential learning effect. Interventions were diverse in terms of their components and intensity.

Investigating Predictors of Preserved Cognitive Function in Older Women Using Machine Learning: Women's Health Initiative Memory Study

BACKGROUND

Identification of factors that may help to preserve cognitive function in late life could elucidate mechanisms and facilitate interventions to improve the lives of millions of people. However, the large number of potential factors associated with cognitive function poses an analytical challenge.

OBJECTIVE

We used data from the longitudinal Women's Health Initiative Memory Study (WHIMS) and machine learning to investigate 50 demographic, biomedical, behavioral, social, and psychological predictors of preserved cognitive function in later life.

METHODS

Participants in WHIMS and two consecutive follow up studies who were at least 80 years old and had at least one cognitive assessment following their 80th birthday were classified as cognitively preserved. Preserved cognitive function was defined as having a score ≥39 on the most recent administration of the modified Telephone Interview for Cognitive Status (TICSm) and a mean score across all assessments ≥39. Cognitively impaired participants were those adjudicated by experts to have probable dementia or at least two adjudications of mild cognitive impairment within the 14 years of follow-up and a last TICSm score <  31. Random Forests was used to rank the predictors of preserved cognitive function.

RESULTS

Discrimination between groups based on area under the curve was 0.80 (95%-CI-0.76-0.85). Women with preserved cognitive function were younger, better educated, and less forgetful, less depressed, and more optimistic at study enrollment. They also reported better physical function and less sleep disturbance, and had lower systolic blood pressure, hemoglobin, and blood glucose levels.

CONCLUSION

The predictors of preserved cognitive function include demographic, psychological, physical, metabolic, and vascular factors suggesting a complex mix of potential contributors.

Development and validation of the dialysis dementia risk score: A retrospective, population-based, nested case-control study

Background

Dementia is prevalent and underdiagnosed in the dialysis population. We aimed to develop and validate a simple dialysis dementia scoring system to facilitate identification of individuals who are at high risk for dementia.

Methods

We applied a retrospective, nested case‐control study design using a national dialysis cohort derived from the National Health Insurance Research Database in Taiwan. Patients aged between 40 and 80 years were included and 2940 patients with incident dementia were matched to 29,248 non‐dementia controls. All subjects were randomly divided into the derivation and validation sets with a ratio of 4:1. Conditional logistic regression models were used to identify factors contributing to the risk score. The cutoff value of the risk score was determined by Youden's J statistic and the graphic method.

Results

The dialysis dementia risk score (DDRS) finally included age and 10 comorbidities as risk predictors. The C‐statistic of the model was 0.71 (95% confidence interval [CI] 0.70–0.72). Calibration revealed a strong linear relationship between predicted and observed dementia risk (R² = 0.99). At a cutoff value of 50 points, the high‐risk patients had an approximately three‐fold increased risk of having dementia compared to those with low risk (odds ratio [OR] 3.03, 95% CI 2.78–3.31). The DDRS performance, including discrimination (C‐statistic 0.71, 95% CI 0.69–0.73) and calibration (p value of Hosmer−Lemeshow test for goodness of fit = 0.18), was acceptable during validation. The OR value (2.82, 95% CI 2.37–3.35) was similar to those in the derivation set.

Conclusion

The DDRS system has the potential to serve as an easily accessible screening tool to determine the high‐risk groups who deserve subsequent neurological evaluation in daily clinical practice.

Associations Between Cardiorespiratory Fitness, Cardiovascular Risk, and Cognition Are Mediated by Structural Brain Health in Midlife

Background

Evidence in older adults suggests that higher cardiorespiratory fitness and lower cardiovascular risk are associated with greater cognition. However, given that changes in the brain that lead to cognitive decline begin decades before the onset of symptoms, understanding the mechanisms by which modifiable cardiovascular factors are associated with brain health in midlife is critical and can lead to the development of strategies to promote and maintain brain health as we age.

Methods and Results

In 501 middle‐aged (aged 40–65 years) adult participants of the BBHI (Barcelona Brain Health Initiative), we found differential associations among cardiorespiratory fitness, cardiovascular risk, and cognition and cortical thickness. Higher cardiorespiratory fitness was significantly associated with better visuospatial abilities and frontal loading abstract problem solving (β=3.16, P=0.049) in the older middle‐aged group (aged 55–65 years). In contrast, cardiovascular risk was negatively associated with better visuospatial reasoning and problem‐solving abilities (β=−0.046, P=0.002), flexibility (β=−0.054, P<0.001), processing speed (β=−0.115, P<0.001), and memory (β=−0.120, P<0.001). Cortical thickness in frontal regions mediated the relationship between cardiorespiratory fitness and cognition, whereas cortical thickness in a disperse network spanning multiple cortical regions across both hemispheres mediated the relationship between cardiovascular risk and cognition.

Conclusions

The relationships between modifiable cardiovascular factors, cardiorespiratory fitness, and cardiovascular risk, and cognition are present in healthy middle‐aged adults. These relationships are also mediated by brain structure highlighting a potential mechanistic pathway through which higher cardiorespiratory fitness and lower cardiovascular risk can positively impact cognitive function in midlife.

A Modified CAIDE Risk Score as a Screening Tool for Cognitive Impairment in Older Adults

BACKGROUND

Although an efficacious dementia-risk score system, Cardiovascular Risk Factors, Aging, and Dementia (CAIDE) was derived using midlife risk factors in a population with low educational attainment that does not reflect today's US population, and requires laboratory biomarkers, which are not always available.

OBJECTIVE

Develop and validate a modified CAIDE (mCAIDE) system and test its ability to predict presence, severity, and etiology of cognitive impairment in older adults.

METHODS

Population consisted of 449 participants in dementia research (N = 230; community sample; 67.9±10.0 years old, 29.6%male, 13.7±4.1 years education) or receiving dementia clinical services (N = 219; clinical sample; 74.3±9.8 years old, 50.2%male, 15.5±2.6 years education). The mCAIDE, which includes self-reported and performance-based rather than blood-derived measures, was developed in the community sample and tested in the independent clinical sample. Validity against Framingham, Hachinski, and CAIDE risk scores was assessed.

RESULTS

Higher mCAIDE quartiles were associated with lower performance on global and domain-specific cognitive tests. Each one-point increase in mCAIDE increased the odds of mild cognitive impairment (MCI) by up to 65%, those of AD by 69%, and those for non-AD dementia by > 85%, with highest scores in cases with vascular etiologies. Being in the highest mCAIDE risk group improved ability to discriminate dementia from MCI and controls and MCI from controls, with a cut-off of ≥7 points offering the highest sensitivity, specificity, and positive and negative predictive values.

CONCLUSION

mCAIDE is a robust indicator of cognitive impairment in community-dwelling seniors, which can discriminate well between dementia severity including MCI versus controls. The mCAIDE may be a valuable tool for case ascertainment in research studies, helping flag primary care patients for cognitive testing, and identify those in need of lifestyle interventions for symptomatic control.

Efficient and Explainable Risk Assessments for Imminent Dementia in an Aging Cohort Study

As the aging US population grows, scalable approaches are needed to identify individuals at risk for dementia. Common prediction tools have limited predictive value, involve expensive neuroimaging, or require extensive and repeated cognitive testing. None of these approaches scale to the sizable aging population who do not receive routine clinical assessments. Our study seeks a tractable and widely administrable set of metrics that can accurately predict imminent (i.e., within three years) dementia onset. To this end, we develop and apply a machine learning (ML) model to an aging cohort study with an extensive set of longitudinal clinical variables to highlight at-risk individuals with better accuracy than standard rudimentary approaches. Next, we reduce the burden needed to achieve accurate risk assessments for those deemed at risk by (1) predicting when consecutive clinical visits may be unnecessary, and (2) selecting a subset of highly predictive cognitive tests. Finally, we demonstrate that our method successfully provides individualized prediction explanations that retain non-linear feature effects present in the data. Our final model, which uses only four cognitive tests (less than 20 minutes to administer) collected in a single visit, affords predictive performance comparable to a standard 100-minute neuropsychological battery and personalized risk explanations. Our approach shows the potential for an efficient tool for screening and explaining dementia risk in the general aging population.

Dementia risk in the general population: large-scale external validation of prediction models in the AGES-Reykjavik study

We aimed to evaluate the external performance of prediction models for all-cause dementia or AD in the general population, which can aid selection of high-risk individuals for clinical trials and prevention. We identified 17 out of 36 eligible published prognostic models for external validation in the population-based AGES-Reykjavik Study. Predictive performance was assessed with c statistics and calibration plots. All five models with a c statistic > .75 (.76-.81) contained cognitive testing as a predictor, while all models with lower c statistics (.67-.75) did not. Calibration ranged from good to poor across all models, including systematic risk overestimation or overestimation for particularly the highest risk group. Models that overestimate risk may be acceptable for exclusion purposes, but lack the ability to accurately identify individuals at higher dementia risk. Both updating existing models or developing new models aimed at identifying high-risk individuals, as well as more external validation studies of dementia prediction models are warranted.

Development and validation of a predictive algorithm for risk of dementia in the community setting

Background

Most dementia algorithms are unsuitable for population-level assessment and planning as they are designed for use in the clinical setting. A predictive risk algorithm to estimate 5-year dementia risk in the community setting was developed.

Methods

The Dementia Population Risk Tool (DemPoRT) was derived using Ontario respondents to the Canadian Community Health Survey (survey years 2001 to 2012). Five-year incidence of physician-diagnosed dementia was ascertained by individual linkage to administrative healthcare databases and using a validated case ascertainment definition with follow-up to March 2017. Sex-specific proportional hazards regression models considering competing risk of death were developed using self-reported risk factors including information on socio-demographic characteristics, general and chronic health conditions, health behaviours and physical function.

Results

Among 75 460 respondents included in the combined derivation and validation cohorts, there were 8448 cases of incident dementia in 348 677 person-years of follow-up (5-year cumulative incidence, men: 0.044, 95% CI: 0.042 to 0.047; women: 0.057, 95% CI: 0.055 to 0.060). The final full models each include 90 df (65 main effects and 25 interactions) and 28 predictors (8 continuous). The DemPoRT algorithm is discriminating (C-statistic in validation data: men 0.83 (95% CI: 0.81 to 0.85); women 0.83 (95% CI: 0.81 to 0.85)) and well-calibrated in a wide range of subgroups including behavioural risk exposure categories, socio-demographic groups and by diabetes and hypertension status.

Conclusions

This algorithm will support the development and evaluation of population-level dementia prevention strategies, support decision-making for population health and can be used by individuals or their clinicians for individual risk assessment.

Developing an Explainable Machine Learning-Based Personalised Dementia Risk Prediction Model: A Transfer Learning Approach With Ensemble Learning Algorithms

Alzheimer's disease (AD) has its onset many decades before dementia develops, and work is ongoing to characterise individuals at risk of decline on the basis of early detection through biomarker and cognitive testing as well as the presence/absence of identified risk factors. Risk prediction models for AD based on various computational approaches, including machine learning, are being developed with promising results. However, these approaches have been criticised as they are unable to generalise due to over-reliance on one data source, poor internal and external validations, and lack of understanding of prediction models, thereby limiting the clinical utility of these prediction models. We propose a framework that employs a transfer-learning paradigm with ensemble learning algorithms to develop explainable personalised risk prediction models for dementia. Our prediction models, known as source models, are initially trained and tested using a publicly available dataset (n = 84,856, mean age = 69 years) with 14 years of follow-up samples to predict the individual risk of developing dementia. The decision boundaries of the best source model are further updated by using an alternative dataset from a different and much younger population (n = 473, mean age = 52 years) to obtain an additional prediction model known as the target model. We further apply the SHapely Additive exPlanation (SHAP) algorithm to visualise the risk factors responsible for the prediction at both population and individual levels. The best source model achieves a geometric accuracy of 87%, specificity of 99%, and sensitivity of 76%. In comparison to a baseline model, our target model achieves better performance across several performance metrics, within an increase in geometric accuracy of 16.9%, specificity of 2.7%, and sensitivity of 19.1%, an area under the receiver operating curve (AUROC) of 11% and a transfer learning efficacy rate of 20.6%. The strength of our approach is the large sample size used in training the source model, transferring and applying the "knowledge" to another dataset from a different and undiagnosed population for the early detection and prediction of dementia risk, and the ability to visualise the interaction of the risk factors that drive the prediction. This approach has direct clinical utility.

Predicting Cognitive Impairment and Dementia: A Machine Learning Approach

BACKGROUND

Efforts to identify important risk factors for cognitive impairment and dementia have to date mostly relied on meta-analytic strategies. A comprehensive empirical evaluation of these risk factors within a single study is currently lacking.

OBJECTIVE

We used a combined methodology of machine learning and semi-parametric survival analysis to estimate the relative importance of 52 predictors in forecasting cognitive impairment and dementia in a large, population-representative sample of older adults.

METHODS

Participants from the Health and Retirement Study (N = 9,979; aged 50-98 years) were followed for up to 10 years (M = 6.85 for cognitive impairment; M = 7.67 for dementia). Using a split-sample methodology, we first estimated the relative importance of predictors using machine learning (random forest survival analysis), and we then used semi-parametric survival analysis (Cox proportional hazards) to estimate effect sizes for the most important variables.

RESULTS

African Americans and individuals who scored high on emotional distress were at relatively highest risk for developing cognitive impairment and dementia. Sociodemographic (lower education, Hispanic ethnicity) and health variables (worse subjective health, increasing BMI) were comparatively strong predictors for cognitive impairment. Cardiovascular factors (e.g., smoking, physical inactivity) and polygenic scores (with and without APOEɛ4) appeared less important than expected. Post-hoc sensitivity analyses underscored the robustness of these results.

CONCLUSIONS

Higher-order factors (e.g., emotional distress, subjective health), which reflect complex interactions between various aspects of an individual, were more important than narrowly defined factors (e.g., clinical and behavioral indicators) when evaluated concurrently to predict cognitive impairment and dementia.

Body weight changes and longitudinal associations with cognitive decline among community-dwelling older adults

INTRODUCTION

We aim to investigate the longitudinal associations between changes in body weight (BW) and declines in cognitive function and risk of mild cognitive impairment (MCI)/dementia among cognitively normal individuals 65 years or older.

METHODS

Data from the Age Gene/Environment Susceptibility-Reykjavik Study (AGES-Reykjavik Study) including 2620 participants, were examined using multiple logistic regression models. Cognitive function included speed of processing (SP), executive function (EF), and memory function (MF). Changes in BW were classified as; weight loss (WL), weight gain (WG), and stable weight (SW).

RESULTS

Mean follow-up time was 5.2 years and 61.3% were stable weight. Participants who experienced WL (13.4%) were significantly more likely to have declines in MF and SP compared to the SW group. Weight changes were not associated with EF. WL was associated with a higher risk of MCI, while WG (25.3%) was associated with a higher dementia risk, when compared to SW.

DISCUSSION

Significant BW changes in older adulthood may indicate impending changes in cognitive function.

A Novel Score for Predicting Alzheimer's Disease Risk from Late Life Psychopathological and Health Risk Factors

With the increasing size of the aging population, dementia risk reduction has become a main public health concern. Dementia risk models or indices may help to identify individuals in the community at high risk to develop dementia. We have aimed to develop a novel dementia risk index focused on the late-life (65 years or more) population, that addresses risk factors for Alzheimer's disease (AD) easily identifiable at primary care settings. These risk factors include some shown to be associated with the risk of AD but not featured in existing indices, such as hearing loss and anxiety. Our index is also the first to account for the competing risk of death. The Zaragoza Dementia and Depression Project (ZARADEMP) Alzheimer Dementia Risk Score predicts an individual´s risk of developing AD within 5 years. The probability of late onset AD significantly increases in those with risk scores between 21 and 28 and, furthermore, is almost 4-fold higher for those with risk scores of 29 or higher. Our index may provide a practical instrument to identify subjects at high risk of AD and to design preventive strategies targeting the contributing risk factors.

Are adverse childhood experiences associated with late-life cognitive performance across racial/ethnic groups: results from the Kaiser Healthy Aging and Diverse Life Experiences study baseline

OBJECTIVES

Evidence on adverse childhood experiences (ACEs) and late-life cognitive outcomes is inconsistent, with little research among diverse racial/ethnic groups. We investigated whether ACE exposures were associated with worse late-life cognition for all racial/ethnic groups and at different ages of exposure.

DESIGN

Covariate-adjusted mixed-effects linear regression models estimated associations of: (1) total number of ACEs experienced, (2) earliest age when ACE occurred and (3) type of ACE with overall cognition.

SETTING

Kaiser Permanente Northern California members aged 65 years and older, living in Northern California.

PARTICIPANTS

Kaiser Healthy Aging and Diverse Life Experiences study baseline participants, aged 65 years and older (n=1661; including 403 Asian-American, 338 Latino, 427 Black and 493 white participants).

RESULTS

Most respondents (69%) reported one or more ACE, most frequently family illness (36%), domestic violence (23%) and parental divorce (22%). ACE count was not adversely associated with cognition overall (β=0.01; 95% CI -0.01 to 0.03), in any racial/ethnic group or for any age category of exposure. Pooling across all race/ethnicities, parent's remarriage (β=-0.11; 95% CI -0.20 to -0.03), mother's death (β=-0.18; 95% CI -0.30 to -0.07) and father's death (β=-0.11; 95% CI -0.20 to -0.01) were associated with worse cognition.

CONCLUSION

Adverse childhood exposures overall were not associated with worse cognition in older adults in a diverse sample, although three ACEs were associated with worse cognitive outcomes.

Deep neural network models for identifying incident dementia using claims and EHR datasets

This study investigates the use of deep learning methods to improve the accuracy of a predictive model for dementia, and compares the performance to a traditional machine learning model. With sufficient accuracy the model can be deployed as a first round screening tool for clinical follow-up including neurological examination, neuropsychological testing, imaging and recruitment to clinical trials. Seven cohorts with two years of data, three to eight years prior to index date, and an incident cohort were created. Four trained models for each cohort, boosted trees, feed forward network, recurrent neural network and recurrent neural network with pre-trained weights, were constructed and their performance compared using validation and test data. The incident model had an AUC of 94.4% and F1 score of 54.1%. Eight years removed from index date the AUC and F1 scores were 80.7% and 25.6%, respectively. The results for the remaining cohorts were between these ranges. Deep learning models can result in significant improvement in performance but come at a cost in terms of run times and hardware requirements. The results of the model at index date indicate that this modeling can be effective at stratifying patients at risk of dementia. At this time, the inability to sustain this quality at longer lead times is more an issue of data availability and quality rather than one of algorithm choices.

Factors predicting episodic memory changes in older adults with subjective cognitive decline: A longitudinal observational study

Episodic memory is affected early in the neuropathological process of Alzheimer's dementia. This study was performed to identify longitudinal associations between baseline vascular/neuropsychiatric risk factors and episodic memory changes over 4.1 ± 2.4 years in 1,401 older adults with subjective cognitive decline (age 74.0 ± 8.2 years). Data were from the National Alzheimer's Coordinating Center-Uniform Data Set and linear mixed effects regression models were used. Reference was those without risk factors. Participants with hypercholesterolemia and with former cigarette smoking had higher episodic memory scores, but current smokers had fewer points than reference at their first and follow-up visits. Despite no difference at baseline, episodic memory scores decreased in those with depressive symptoms relative to reference over time. In older adults with subjective cognitive decline, interventions managing current smoking and depressive symptoms could preserve episodic memory, which may result in delaying the onset of Alzheimer's dementia. Further research is required for the role of cholesterol and smoking.

Apathy, but not depression, predicts all-cause dementia in cerebral small vessel disease

OBJECTIVE

To determine whether apathy or depression predicts all-cause dementia in small vessel disease (SVD) patients.

METHODS

Analyses used two prospective cohort studies of SVD: St. George's Cognition and Neuroimaging in Stroke (SCANS; n=121) and Radboud University Nijmegen Diffusion Tensor and Magnetic Resonance Cohort (RUN DMC; n=352). Multivariate Cox regressions were used to predict dementia using baseline apathy and depression scores in both datasets. Change in apathy and depression was used to predict dementia in a subset of 104 participants with longitudinal data from SCANS. All models were controlled for age, education and cognitive function.

RESULTS

Baseline apathy scores predicted dementia in SCANS (HR 1.49, 95% CI 1.05 to 2.11, p=0.024) and RUN DMC (HR 1.05, 95% CI 1.01 to 1.09, p=0.007). Increasing apathy was associated with dementia in SCANS (HR 1.53, 95% CI 1.08 to 2.17, p=0.017). In contrast, baseline depression and change in depression did not predict dementia in either dataset. Including apathy in predictive models of dementia improved model fit.

CONCLUSIONS

Apathy, but not depression, may be a prodromal symptom of dementia in SVD, and may be useful in identifying at-risk individuals.

Using Dual Neural Network Architecture to Detect the Risk of Dementia With Community Health Data: Algorithm Development and Validation Study

Background

Recent studies have revealed lifestyle behavioral risk factors that can be modified to reduce the risk of dementia. As modification of lifestyle takes time, early identification of people with high dementia risk is important for timely intervention and support. As cognitive impairment is a diagnostic criterion of dementia, cognitive assessment tools are used in primary care to screen for clinically unevaluated cases. Among them, Mini-Mental State Examination (MMSE) is a very common instrument. However, MMSE is a questionnaire that is administered when symptoms of memory decline have occurred. Early administration at the asymptomatic stage and repeated measurements would lead to a practice effect that degrades the effectiveness of MMSE when it is used at later stages.

Objective

The aim of this study was to exploit machine learning techniques to assist health care professionals in detecting high-risk individuals by predicting the results of MMSE using elderly health data collected from community-based primary care services.

Methods

A health data set of 2299 samples was adopted in the study. The input data were divided into two groups of different characteristics (ie, client profile data and health assessment data). The predictive output was the result of two-class classification of the normal and high-risk cases that were defined based on MMSE. A dual neural network (DNN) model was proposed to obtain the latent representations of the two groups of input data separately, which were then concatenated for the two-class classification. Mean and k-nearest neighbor were used separately to tackle missing data, whereas a cost-sensitive learning (CSL) algorithm was proposed to deal with class imbalance. The performance of the DNN was evaluated by comparing it with that of conventional machine learning methods.

Results

A total of 16 predictive models were built using the elderly health data set. Among them, the proposed DNN with CSL outperformed in the detection of high-risk cases. The area under the receiver operating characteristic curve, average precision, sensitivity, and specificity reached 0.84, 0.88, 0.73, and 0.80, respectively.

Conclusions

The proposed method has the potential to serve as a tool to screen for elderly people with cognitive impairment and predict high-risk cases of dementia at the asymptomatic stage, providing health care professionals with early signals that can prompt suggestions for a follow-up or a detailed diagnosis.

Loneliness is associated with risk of cognitive impairment in the Survey of Health, Ageing and Retirement in Europe

OBJECTIVES

To test whether loneliness is associated with the risk of cognitive impairment up to 11 years later in a European sample of middle-aged and older adults. The study examines whether this association is independent of measures of social isolation, depression, and other risk factors for cognitive impairment and dementia.

METHODS

Participants (N = 14 114) from the Survey of Health, Ageing and Retirement in Europe (SHARE) answered a single item on loneliness at baseline and were assessed for cognitive impairment every 2-to-3 years for 11 years. Participants who scored at least 1.5 standard deviations below the age-graded mean on both a memory recall task and verbal fluency task were classified as impaired. A three-item measure of loneliness was available for a sample of respondents followed up to 4 years.

RESULTS

Feeling lonely was associated with increased risk of incident cognitive impairment (HR = 1.31, 95%CI = 1.19-1.44), after accounting for age, sex, education, and SHARE country strata. The association was robust but reduced in magnitude when controlling for clinical and behavioral risk factors, health-related activity limitations, social isolation, social disengagement, and depressive symptoms. The association was not moderated by socio-demographic factors and was also apparent when using the three-item loneliness scale instead of the single-item measure.

CONCLUSIONS

These findings expand the extant literature on loneliness and the risk of cognitive impairment in older adulthood. Loneliness is one modifiable factor that can be intervened prior to the development of severe impairment or dementia.

Predicting Onset of Dementia Using Clinical Notes and Machine Learning: Case-Control Study

Background

Clinical trials need efficient tools to assist in recruiting patients at risk of Alzheimer disease and related dementias (ADRD). Early detection can also assist patients with financial planning for long-term care. Clinical notes are an important, underutilized source of information in machine learning models because of the cost of collection and complexity of analysis.

Objective

This study aimed to investigate the use of deidentified clinical notes from multiple hospital systems collected over 10 years to augment retrospective machine learning models of the risk of developing ADRD.

Methods

We used 2 years of data to predict the future outcome of ADRD onset. Clinical notes are provided in a deidentified format with specific terms and sentiments. Terms in clinical notes are embedded into a 100-dimensional vector space to identify clusters of related terms and abbreviations that differ across hospital systems and individual clinicians.

Results

When using clinical notes, the area under the curve (AUC) improved from 0.85 to 0.94, and positive predictive value (PPV) increased from 45.07% (25,245/56,018) to 68.32% (14,153/20,717) in the model at disease onset. Models with clinical notes improved in both AUC and PPV in years 3-6 when notes’ volume was largest; results are mixed in years 7 and 8 with the smallest cohorts.

Conclusions

Although clinical notes helped in the short term, the presence of ADRD symptomatic terms years earlier than onset adds evidence to other studies that clinicians undercode diagnoses of ADRD. De-identified clinical notes increase the accuracy of risk models. Clinical notes collected across multiple hospital systems via natural language processing can be merged using postprocessing techniques to aid model accuracy.

Protocol for an embedded pragmatic clinical trial to test the effectiveness of Aliviado Dementia Care in improving quality of life for persons living with dementia and their informal caregivers

INTRODUCTION

Persons living with Alzheimer's disease and related dementias (ADRD) frequently experience pain and behavioral and psychological symptoms of dementia (BPSD) which decrease quality of life (QOL) and influence caregiver burden. Home healthcare professionals however may underrecognize or lack the ability to manage BPSD.

INTERVENTION

This protocol describes an ADRD palliative quality assurance performance improvement program for home healthcare, Aliviado Dementia Care-Home Health Edition. It includes training, mentoring, and a toolbox containing intervention strategies.

METHODS

This embedded pragmatic clinical trial will utilize a multi-site, cluster randomized control design. Recruitment will occur from three home healthcare agencies located in New Jersey, Utah, and Florida. At each agency, care teams will be randomized as clusters and assigned to either the Aliviado Dementia Care program or usual care. We plan to enroll 345 persons living with ADRD and their informal caregiver dyads. The primary outcome will be to measure QOL in both the person living with ADRD and their informal caregiver, and emergency department visits and hospital admissions. Secondary outcomes in the person living with ADRD will include the examination of pain, BPSD, antipsychotic and analgesic use. Secondary outcomes in caregivers include burden, depressive symptoms, functional health and wellbeing, and healthcare utilization.

CONCLUSION

This study will be the first large-scale embedded pragmatic clinical trial in home healthcare focused on care quality and outcomes in addressing QOL in ADRD. If proven successful, the intervention can then be disseminated to agencies throughout the country to improve the quality of care for this vulnerable, underserved population.

TRIAL REGISTRATION

Clinical Trials.gov: NCT03255967.

Relationship between Surgery under General Anesthesia and the Development of Dementia: A Systematic Review and Meta-Analysis

Objective

To investigate the association between exposure to general anesthesia and the development of Alzheimer's disease (AD) and dementia by reviewing and integrating the evidence from epidemiological studies published to date.

Methods

We searched MEDLINE, EMBASE, and Google Scholar to identify all relevant articles up to April 2018 reporting the risk of AD/dementia following exposure to general anesthesia and finally updated in February 2020. We included patients older than 60 or 65 years who had not been diagnosed with dementia or AD before the study period. The overall pooled effect size (ES) was evaluated with a random-effect model. Subgroup analyses were conducted and possibility of publication bias was assessed.

Results

A total of 23 studies with 412253 patients were included in our analysis. A statistically significant positive association between exposure to general anesthesia and the occurrence of AD was detected in the overall analysis (pooled ES = 1.11, 95%confidence interval = 1.07–1.15), but with substantial heterogeneity (p_χ² < 0.001, I² = 79.4). Although the overall analysis revealed a significant association, the results of the subgroup analyses were inconsistent, and the possibility of publication bias was detected.

Conclusion

s. This meta-analysis demonstrated a significant positive association between general anesthesia and AD. However, considering other results, our meta-analysis must be interpreted with caution. Particularly, it should be considered that it was nearly impossible to discriminate the influence of general anesthesia from the effect of surgery itself on the development of AD. Further, large-scale studies devised to reduce the risk of bias are needed to elucidate the evidence of association between general anesthesia and AD. Trial registration. PROSPERO International prospective register of systematic reviews CRD42017073790.

Machine learning models to predict onset of dementia: A label learning approach

Introduction

The study objective was to build a machine learning model to predict incident mild cognitive impairment, Alzheimer's Disease, and related dementias from structured data using administrative and electronic health record sources.

Methods

A cohort of patients (n = 121,907) and controls (n = 5,307,045) was created for modeling using data within 2 years of patient's incident diagnosis date. Additional cohorts 3–8 years removed from index data are used for prediction. Training cohorts were matched on age, gender, index year, and utilization, and fit with a gradient boosting machine, lightGBM.

Results

Incident 2-year model quality on a held-out test set had a sensitivity of 47% and area-under-the-curve of 87%. In the 3-year model, the learned labels achieved 24% (71%), which dropped to 15% (72%) in year 8.

Discussion

The ability of the model to discriminate incident cases of dementia implies that it can be a worthwhile tool to screen patients for trial recruitment and patient management.

Cardiovascular risk factors and memory decline in middle-aged and older adults: the English Longitudinal Study of Ageing

Background

We investigated the association between trajectories of verbal episodic memory and burden of cardiovascular risk factors in middle-aged and older community-dwellers.

Methods

We analysed data from 4372 participants aged 50–64 and 3005 persons aged 65–79 years old from the English Longitudinal Study of Ageing who were repeatedly evaluated every 2 years and had six interviews of a 10-year follow-up. We measured the following baseline risk factors: diabetes, hypertension, smoking, physical inactivity and obesity to derive a cardiovascular risk factor score (CVRFs). Adjusted linear mixed effect regression models were estimated to determine the association between number of CVFRs and six repeated measurements of verbal memory scores, separately for middle-aged and older adults.

Results

CVRFs was not significantly associated with memory at baseline. CVFRs was significantly associated with memory decline in middle-aged (50-64y), but not in older (65-79y) participants. This association followed a dose-response pattern with increasing number of CVFRs being associated with greater cognitive decline. Comparisons between none versus some CVRFs yielded significant differences (p < 0.05).

Conclusions

Our findings confirm that the effect of cumulative CVRFs on subsequent cognitive deterioration is age-dependent. CVRFs are associated with cognitive decline in people aged 50–64 years, but not in those aged ≥65 years. Although modest, the memory decline associated with accumulation of cardiovascular risk factors in midlife may increase the risk of late-life dementia.

Predicting Dementia in Cerebral Small Vessel Disease Using an Automatic Diffusion Tensor Image Segmentation Technique

Supplemental Digital Content is available in the text.

Cerebral small vessel disease (SVD) is the most common cause of vascular cognitive impairment, with a significant proportion of cases going on to develop dementia. We explore the extent to which diffusion tensor image segmentation technique (DSEG; which characterizes microstructural damage across the cerebrum) predicts both degree of cognitive decline and conversion to dementia, and hence may provide a useful prognostic procedure.

Risk Factors and Neuropsychological Assessments of Subjective Cognitive Decline (plus) in Chinese Memory Clinic

Background

Since subjective cognitive decline (SCD) was standardized in 2014, many studies have investigated its features. However, the risk of SCD (plus) progressing to AD is much higher, and yet there have been few studies reporting the risk factors and neuropsychological assessment characteristics of SCD (plus).

Objective

To characterize SCD (plus) by comparing it with normal control (NC), amnesic mild cognitive impairment (aMCI), and Alzheimer Disease (AD) regarding their demographics, lifestyle, family history of dementia, multimorbidity and the neuropsychological assessments.

Methods

A total of 135 participants were recruited, including 23 NC, 30 SCD (plus), 45 aMCI and 37 AD. Descriptive statistics were provided. A logistic regression model was used to analyze the affecting factors of SCD (plus), and finally the Receiver Operating Characteristic (ROC) analysis was applied to distinguish between SCD (plus) and NC.

Results

(1) SCD (plus) group was younger than both the aMCI group and AD group. It consisted of more participants with mental work and higher body mass index (BMI) than the AD group. (2) Scores of Auditory Verbal Learning Test - Immediate recall (AVLT-IR) and AVLT-Long delayed recall (AVLT-LR) decreased in the following order: NC→SCD (plus)→aMCI→AD. (3) The Area Under Curve (AUC) for discriminating SCD (plus) and NC group was from 0.673 to 0.838.

Conclusion

Aging is an important risk factor of both NC progressing to SCD (plus), and SCD (plus) progressing to aMCI or AD. In addition to aging, lower education level and lower BMI were significantly associated with greater odds of SCD (plus) progressing to aMCI or AD patients, whereas mental work was a protective factor of SCD (plus) progressing to AD. Finally, AVLT is a sensitive indicator of the cognitive decline and impairment in SCD (plus) in relative to normal controls.

N-of-1 Clinical Trials in Nutritional Interventions Directed at Improving Cognitive Function

Longer life expectancy has led to an increase in the prevalence of age-related cognitive decline and dementia worldwide. Due to the current lack of effective treatment for these conditions, preventive strategies represent a research priority. A large body of evidence suggests that nutrition is involved in the pathogenesis of age-related cognitive decline, but also that it may play a critical role in slowing down its progression. At a population level, healthy dietary patterns interventions, such as the Mediterranean and the MIND diets, have been associated with improved cognitive performance and a decreased risk of neurodegenerative disease development. In the era of evidence-based medicine and patient-centered healthcare, personalized nutritional recommendations would offer a considerable opportunity in preventing cognitive decline progression. N-of-1 clinical trials have emerged as a fundamental design in evidence-based medicine. They consider each individual as the only unit of observation and intervention. The aggregation of series of N-of-1 clinical trials also enables population-level conclusions. This review provides a general view of the current scientific evidence regarding nutrition and cognitive decline, and critically states its limitations when translating results into the clinical practice. Furthermore, we suggest methodological strategies to develop N-of-1 clinical trials focused on nutrition and cognition in an older population. Finally, we evaluate the potential challenges that researchers may face when performing studies in precision nutrition and cognition.

Identifying incident dementia by applying machine learning to a very large administrative claims dataset

Alzheimer's disease and related dementias (ADRD) are highly prevalent conditions, and prior efforts to develop predictive models have relied on demographic and clinical risk factors using traditional logistical regression methods. We hypothesized that machine-learning algorithms using administrative claims data may represent a novel approach to predicting ADRD. Using a national de-identified dataset of more than 125 million patients including over 10,000 clinical, pharmaceutical, and demographic variables, we developed a cohort to train a machine learning model to predict ADRD 4-5 years in advance. The Lasso algorithm selected a 50-variable model with an area under the curve (AUC) of 0.693. Top diagnosis codes in the model were memory loss (780.93), Parkinson's disease (332.0), mild cognitive impairment (331.83) and bipolar disorder (296.80), and top pharmacy codes were psychoactive drugs. Machine learning algorithms can rapidly develop predictive models for ADRD with massive datasets, without requiring hypothesis-driven feature engineering.

A Population Perspective on Prevention of Dementia

The global number of people living with dementia is expected to increase to 130 million in 2050. Based on extensive evidence from observational studies, it is estimated that about 30% of dementia cases may be attributable to potentially modifiable risk factors. This suggests that interventions targeting these factors could perhaps delay or prevent the onset of dementia. Since the vast majority of people with dementia live in low- and middle-income countries, such interventions should preferably be easy and affordable to implement across a wide range of health care systems. However, to date, results from dementia prevention trials do not provide convincing evidence that treatment of these risk factors reduces the risk of dementia. The current paper aims to give an overview of available evidence for the potential for dementia prevention. In particular, we discuss methodological issues that might complicate the development of effective prevention interventions and explore the opportunities and challenges for future dementia prevention research. Currently, several ongoing and planned trials are testing the effect of multi-domain interventions on dementia risk in high-risk populations. It is desirable that future dementia strategies also target the wider population, through interventions on the individual, community, and population level, in order to constrain the growing prevalence of dementia worldwide.

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.

Alcohol consumption and incident dementia in older Japanese adults: The Okayama Study

AIM

To evaluate the association between the amount and frequency of alcohol consumption and incident dementia in older Japanese adults using large sample size data over a long follow-up period.

METHODS

This was a retrospective cohort study carried out in Japan. A total of 53 311 older adults were followed from 2008 to 2014. A health checkup questionnaire was used to assess the amount and frequency of alcohol consumption. The Dementia Scale of long-term care insurance was used as a measure of incident dementia. Cox proportional hazards models were used to calculate adjusted hazard ratios, with their 95% confidence intervals, for the incidence of dementia across the categories of alcohol consumption by sex.

RESULTS

During a 7-year follow-up period, 14 479 participants were regarded as having incident dementia. Compared with non-drinkers, the multivariate adjusted hazard ratios for participants with alcohol consumption ≤2 units per day, occasionally (0.88, 95% CI 0.81-0.96 in men and 0.84, 95% 0.79-0.90 in women) and daily (0.79, 95% 0.73-0.85 in men and 0.87, 95% 0.78-0.97 in women) were statistically significant, and the difference between occasional and daily consumption was only statistically significant in men; however, for participants with alcohol consumption >2 units per day, occasionally (0.91, 95% 0.71-1.16 in men and 1.09, 95% 0.72-1.67 in women) and daily (0.89, 95% 0.81-1.00 in men and 1.16, 95% 0.84-1.81 in women) were not significant.

CONCLUSIONS

Alcohol consumption of ≤2 units per day, occasionally or daily, could reduce the risk of incident dementia, with greater benefit for men with such daily consumption. Geriatr Gerontol Int 2019; 19: 740-746.

Precision Aging: Applying Precision Medicine to the Field of Cognitive Aging

The current "one size fits all" approach to our cognitive aging population is not adequate to close the gap between cognitive health span and lifespan. In this review article, we present a novel model for understanding, preventing, and treating age-related cognitive impairment (ARCI) based on concepts borrowed from precision medicine. We will discuss how multiple risk factors can be classified into risk categories because of their interrelatedness in real life, the genetic variants that increase sensitivity to, or ameliorate, risk for ARCI, and the brain drivers or common mechanisms mediating brain aging. Rather than providing a definitive model of risk for ARCI and cognitive decline, the Precision Aging model is meant as a starting point to guide future research. To that end, after briefly discussing key risk categories, genetic risks, and brain drivers, we conclude with a discussion of steps that must be taken to move the field forward.

Association of Brain Magnetic Resonance Imaging Signs With Cognitive Outcomes in Persons With Nonimpaired Cognition and Mild Cognitive Impairment

IMPORTANCE

Brain atrophy and vascular lesions contribute to dementia and mild cognitive impairment (MCI) in clinical referral populations. Prospective evidence in older general populations is limited.

OBJECTIVE

To evaluate which magnetic resonance imaging (MRI) signs are independent risk factors for dementia and MCI.

DESIGN, SETTING, AND PARTICIPANTS

This population-based cohort study included 1553 participants sampled from the Atherosclerosis Risk in Communities Study who had brain MRI scans and were dementia free during visit 5 (June 2011 to September 2013). Participants' cognitive status was evaluated through visit 6 (June 2016 to December 2017).

EXPOSURES

Brain regional volumes, microhemorrhages, white matter hyperintensity (WMH) volumes, and infarcts measured on 3-T MRI.

MAIN OUTCOMES AND MEASURES

Cognitive status (dementia, MCI, or nonimpaired cognition) was determined from in-person evaluations. Dementia among participants who missed visit 6 was identified via dementia surveillance and hospital discharge or death certificate codes. Cox proportional hazards models were used to evaluate the risk of dementia in 3 populations: dementia-free participants (N = 1553), participants with nonimpaired cognition (n = 1014), and participants with MCI (n = 539). Complementary log-log models were used for risk of MCI among participants with nonimpaired cognition who also attended visit 6 (n = 767). Models were adjusted for demographic variables, apolipoprotein E ε4 alleles, vascular risk factors, depressive symptoms, and heart failure.

RESULTS

Overall, 212 incident dementia cases were identified among 1553 participants (mean [SD] age at visit 5, 76 [5.2] years; 946 [60.9%] women; 436 [28.1%] African American) with a median (interquartile range) follow-up period of 4.9 (4.3-5.2) years. Significant risk factors of dementia included lower volumes in the Alzheimer disease (AD) signature region, including hippocampus, entorhinal cortex, and surrounding structures (hazard ratio [HR] per 1-SD decrease, 2.40; 95% CI, 1.89-3.04), lobar microhemorrhages (HR, 1.90; 95% CI, 1.30-2.77), higher volumes of WMH (HR per 1-SD increase, 1.44; 95% CI, 1.23-1.69), and lacunar infarcts (HR, 1.66; 95% CI, 1.20-2.31). The AD signature region volume was also consistently associated with both MCI and progression from MCI to dementia, while subcortical microhemorrhages and infarcts contributed less to the progression from MCI to dementia.

CONCLUSIONS AND RELEVANCE

In this study, lower AD signature region volumes, brain microhemorrhages, higher WMH volumes, and infarcts were risk factors associated with dementia in older community-based residents. Vascular changes were more important in the development of MCI than in its progression to dementia, while AD-related signs were important in both stages.

Population-based dementia prediction model using Korean public health examination data: A cohort study

The early identification and prevention of dementia is important for reducing its worldwide burden and increasing individuals’ quality of life. Although several dementia prediction models have been developed, there remains a need for a practical and precise model targeted to middle-aged and Asian populations. Here, we used national Korean health examination data from adults (331,126 individuals, 40–69 years of age, mean age: 52 years) from 2002–2003 to predict the incidence of dementia after 10 years. We divided the dataset into two cohorts to develop and validate of our prediction model. Cox proportional hazards models were used to construct dementia prediction models for the total group and sex-specific subgroups. Receiver operating characteristics curves, C-statistics, calibration plots, and cumulative hazards were used to validate model performance. Discriminative accuracy as measured by C-statistics was 0.81 in the total group (95% confidence interval (CI) = 0.81 to 0.82), 0.81 in the male subgroup (CI = 0.80 to 0.82), and 0.81 in the female subgroup (CI = 0.80 to 0.82). Significant risk factors for dementia in the total group were age; female sex; underweight; current hypertension; comorbid psychiatric or neurological disorder; past medical history of cardiovascular disease, diabetes mellitus, or hypertension; current smoking; and no exercise. All identified risk factors were statistically significant in the sex-specific subgroups except for low body weight and current hypertension in the female subgroup. These results suggest that public health examination data can be effectively used to predict dementia and facilitate the early identification of dementia within a middle-aged Asian population.