The Journal of Prevention of Alzheimer's Disease

Background: International Classification of Diseases (ICD) codes are often used in epidemiological studies to track disease rates over time. Objective: This evaluation of ICD-code-based algorithms for electronic medical record (EMR) studies of Alzheimers disease (AD) and related dementias (ADRD) examines the impact of incorporating Centers for Medicare and Medicaid (CMS) data as an additional source of diagnostic and treatment information in Department of Veterans Affairs (VA) EMR studies. Methods: We performed a chart review of 100 VA Million Veteran Program (MVP) participants to evaluate algorithm performance. We also assessed genetic associations across algorithms in a large MVP cohort (n=396k). Results: Adding CMS data increased the number of detected cases, sensitivity, and positive predictive value, but decreased specificity and negative predictive value. Genetic analyses showed that broader (ADRD/dementia) algorithms with just VA data performed similarly to narrow (AD-focused) algorithms incorporating both VA and CMS ICD codes. Additionally, narrow AD algorithms based solely on VA data yielded the highest ORs, indicating the largest proportion of late-onset AD cases. Conclusions: We recommend using a broad (ADRD) algorithm without CMS or medication data, particularly for epidemiological studies or a strict AD algorithm including CMS and medication cases for genetic discovery of late-onset AD associations in VA EMR, and a strict AD algorithm without CMS data for applications focused solely on AD and sensitive to misspecification. Careful evaluation of algorithm performance is warranted in different EMR systems, as ICD coding practices vary by institution, as demonstrated by this comparison of VA EMR and CMS data.

Background: Electronic health record (EHR)-linked biorepositories provide opportunities to advance epidemiological research in Alzheimer's disease (AD) and related dementias. Objective: Evaluate the extraction, curation, and associative validity of Mini Mental State Examination (MMSE) scores from the VA EHR for participants in the VA Million Veteran Program (MVP). Methods: The sample (N = 49,555; 7.4% women) included a multiethnic cohort (European [68.3%], African [20.4%], Hispanic [9.0%]) with EHR-extracted MMSE scores; 30.7% were apolipoprotein E (APOE) {epsilon}4 carriers, and 25.8% had multiple scores. Linear regressions examined cross-sectional associations between {epsilon}4 dosage (0, 1, 2) and first and lowest MMSE scores. MMSE scores were also evaluated against MVP dementia diagnostic algorithms in participants aged [&ge;]65 years. Results: Among participants of European ancestry, there was a significant {epsilon}4 dose-response relationship (ps < .001) with MMSE scores. Homozygote carriers scored lower than heterozygote carriers (Mdiff: first = -0.5; lowest = -0.9), who scored lower than non-carriers (Mdiff: first = -0.4; lowest = -0.6). Among Veterans of African and Hispanic ancestry, no dose-response relationship was observed, although {epsilon}4 carriers had lower scores than non-carriers (ps [&le;] .04). MMSE scores corresponded strongly with dementia case/control status across phenotypes: mild impairment on the MMSE was strongly associated with AD (odds ratio [OR] = 11.48), with more severe MMSE impairment showing stronger associations (moderate OR = 17.95; severe OR = 27.83). Conclusion: This study demonstrated MMSE scores can be systematically extracted and curated from the VA EHR. Findings offer a scalable framework for future studies on risk stratification, highlighting the potential for harnessing MVP to explore genetic and clinical factors contributing to cognitive and dementia outcomes in diverse samples.

INTRODUCTION: The biomarker-based amyloid/ tau/ neurodegeneration (A/T/N) framework has become a popular staging method for Alzheimer's disease (AD) research. Previous studies use the framework either as a rule-based or data-driven approach but typically sacrifice either adaptivity or interpretability. METHODS: We present an interpretable, hybrid method, called Neurosymodal Data Fusion, for predicting incident AD in the ADNI dataset. Specifically, we encode the A/T/N framework as a logic program, where the input biomarker features are extracted by one or more neural networks. RESULTS: Our pipeline predicted four-year incident AD with a sensitivity of up to 0.84. Additionally, our models learned scores for each A/T/N profile, denoting relative importances to model predictions. These scores also indicated that empirically-derived cut-off values for the A and T criteria might be uninformative for the ADNI data. DISCUSSION: Our pipeline provides a novel way to use the A/T/N framework that could potentially improve early AD screening years before clinical manifestations.

Background: Plasma phosphorylated tau-217 (pTau-217) measurements for use in Alzheimer disease (AD) identification require thresholds to define positivity and there exist different approaches to operationally defining the boundary. We compared amyloid {beta} (AB) PET-anchored and distribution-based positivity cut-off values and explored how these mapped onto latent biomarker states. Methods: We analysed plasma pTau-217 measured in the Bio-Hermes-001 cohort (N = 990) using an immunoassay (Lilly) and mass spectrometry assay (University of Gothenburg). Gaussian mixture models were used to identify latent classes and thresholds were derived in two ways: achieving 90% specificity for AB PET positivity and exceeding the mean + 2SDs of the lowest latent class. We explore classes in reference to AB PET status and clinical diagnosis, as well as agreement between approaches using Cohen kappa for both assays. Results: In both assays, three latent biomarker classes were identified with monotonic increases in AD clinical diagnosis and AB PET positivity. PET-anchored thresholds showed lower specificity but higher sensitivity to amyloid positivity than distribution-based thresholds. Overall agreement between the approaches was acceptable (k = 0.678 for Lilly and 0.575 for University of Gothenburg), with disagreement concentrated in the intermediate latent class. Classes with the lowest and highest pTau-217 concentrations were classified consistently using both thresholds Discussion: The two thresholding approaches yielded similar classifications at both the negative and positive tail of the observed biomarker distribution, but classify intermediate concentrations differently. The boundary definition influenced pTau-217 positivity more than the analytical platform itself. Thresholding approaches may capture different pTau-217 biomarker states, therefore such methodological decisions should be grounded in the context of the intended application.

Background: Accelerated biological aging can be assessed with DNA methylation (DNAm)- based epigenetic clocks. Research suggests that greater DNAm is associated with faster cognitive decline and risk of Alzheimer disease (AD) and other dementias. However, most studies have relied on single-time-point measurements of clocks, rather than evaluating dynamic changes over time. We examined the association between 15-year epigenetic aging trajectories and brain health outcomes in midlife. Methods: We analyzed 2,833 middle-aged adults (mean baseline age 40 years, 59% female and 44% Black) with [&ge;]3 DunedinPACE (a recently developed epigenetic clock) measurements, collected over 15 years. Using mixed-effects modeling, we derived individual-specific slopes of epigenetic aging trajectories and categorized participants as Fast Agers (slopes > 1 SD above the mean), Slow Agers (slopes < 1 SD below the mean), or Typical Agers (within &plusmn1 SD of the mean). We examined associations between trajectory group and cognition on five cognitive domains as well as on plasma AD biomarkers (NfL, p-tau217, A{beta}42/A{beta}40), all assessed 15-20 years post-baseline. Models were adjusted for demographics, education, physical activity and APOE*{varepsilon}4 carrier status (with additional adjustments for eGFRcr for biomarker outcomes). Results: Epigenetic aging trajectories were associated with multiple domains of cognition and AD biomarkers (Figure 1). Compared to Typical Agers, Fast Agers showed worse processing speed, memory, executive function, and global cognition (all p<0.05), with no difference in verbal fluency. Slow Agers had better performance on memory and global cognition (both p < 0.05). Fast Agers also exhibited significantly lower A{beta}42/A{beta}40 levels (p = 0.011) compared to Typical agers; no significant associations with p-tau217 or NfL were observed in either group. Conclusion: Middle-aged adults with faster 15-year epigenetic aging trajectories demonstrated worse cognitive performance, whereas those with slower biological aging trajectories exhibited cognitive resilience and more favorable AD biomarker profiles. By examining long-term trajectories rather than single timepoints, these findings identify individuals at differential risk for brain health outcomes.

INTRODUCTION: Brain age gap (BAG) is the difference between a person's chronological age and the age predicted from the structural appearance of their brain on MRI. A higher BAG indicates an older-appearing brain and provides a global marker of structural brain aging across the Alzheimer's disease continuum. Prior studies suggest that females may show greater Alzheimer's disease-related pathology or faster late-stage neurodegeneration than males. We tested whether sex was associated with baseline BAG or longitudinal BAG change after accounting for APOE {epsilon}4 genetic risk, amyloid positivity, cognitive severity, and disease stage. METHODS: We developed a domain-adaptive deep learning model to estimate BAG from T1-weighted MRIs, training it on 26,512 neurologically healthy UK Biobank data and fine-tuning it on 2,974 amyloid-negative cognitively normal samples from Mayo Clinic Study of Aging and OASIS-3 cohorts. We applied the model to ADNI and used hierarchical mixed-effects models to test whether sex was associated with BAG trajectories after adjusting for Alzheimer's disease risk factors. RESULTS: After adjustment for Alzheimer's disease risk factors, there was no baseline sex differences in BAG. Longitudinally, females showed greater BAG acceleration than males, but this effect was moderated by APOE {epsilon}4 status. APOE {epsilon}4 accelerated brain aging in a dose-dependent manner, independent of amyloid burden. DISCUSSION: Sex differences in BAG across the AD continuum were largely explained by APOE {epsilon}4-related acceleration rather than by an independent effect of sex alone. These findings suggest that females may be more vulnerable to APOE {epsilon}4-associated structural brain aging over time.

Deep learning classifiers applied to structural MRI (sMRI) have achieved high performance in detecting Alzheimer's Disease (AD), yet systematic investigation of their failure modes remains limited. In this study, we trained two deep learning architectures to classify AD from cognitively normal (CN) participants using sMRI data from the ADNI dataset, and examined whether misclassifications persist across models and training configurations. We identified a subgroup of subjects who were persistently misclassified across 100 model instances, and found that these subjects exhibited a markedly different atrophy subtype distribution compared to correctly classified AD cases, with substantial enrichment of hippocampal-sparing and minimal atrophy subtypes. To disentangle whether persistent false negatives (FN) reflect earlier disease stage or atypically presenting disease, we analyzed longitudinal follow-up scans and tested whether model predictions changed as neurodegeneration progressed. A change in prediction (from FN to true positive (TP)) was observed in only a subgroup of subjects and required intervals of up to five years, suggesting that persistent misclassification may not always be explained by disease staging alone. Although the sample size is small, these findings underscore the importance of accounting for disease heterogeneity in the development and evaluation of clinical AI models for AD detection.

Magnetic Resonance Imaging (MRI) derived brain age varies substantially between individuals, but it remains unclear whether early deviations from normal brain ageing precede future cognitive decline and whether they provide predictive value beyond conventional MRI measures. Here, we investigated whether MRI-derived brain age gap estimation (BrainAGE) identifies early structural brain ageing differences among cognitively normal individuals who later develop mild cognitive impairment (MCI) or dementia. We analysed longitudinal structural MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and replicated the main findings in the population-based Kuopio Osteoporosis Risk Factor and Prevention Study (OSTPRE). Individuals who later converted to MCI or dementia had higher BrainAGE values several years before diagnosis and, in ADNI, showed steeper longitudinal increases than stable individuals. Elevated BrainAGE values were also associated with increased risk of future conversion to MCI in cognitively healthy individuals and faster subsequent memory decline. Cross-sectional differences and the association between BrainAGE and risk of future conversion were replicated in OSTPRE. Importantly, adding BrainAGE to models including demographic, APOE4, cognitive, and MRI-derived measures consistently improved prediction of future cognitive outcomes, with the greatest benefit observed for individuals who converted after longer follow-up. These findings show that structural brain ageing begins to diverge years before the onset of MCI. BrainAGE captures this early divergence, providing complementary information beyond conventional structural MRI measures that may improve the early identification of cognitively normal individuals at increased risk of future cognitive decline when integrated with other biomarkers.

People with Down syndrome have higher age-specific mortality rates compared to the general population as well as peers with other intellectual and developmental disabilities. While a large proportion of mortality is attributable to Alzheimers disease, many die prior to Alzheimers diagnosis and some live to old ages, dying without Alzheimers. Our objectives were to use 11 years of Medicaid and Medicare data to describe characteristics and factors related to death in adults with Down syndrome and use machine learning to identify which conditions most strongly predict death in the full population and stratified by age. We identified death using Center for Medicare and Medicaid Systems reported date of death health conditions using ICD 9 and 10 codes. We used a case-control design with risk set sampling to have that controls to mimic the distribution of times of incident Alzheimers disease. We trained gradient boosted trees to identify strongest predictors. Our cohort included 137,293 adults with Down syndrome. Among those, 30,894 (22.5%) died during the study period. Mean age at death among those who died was 55 years (SD=10). Mean age of death in those with Alzheimers disease was 59 (SD=7) and those without was 52 (SD=12). The most influential predictors of mortality were any claim for dementia, any claim for pneumonia, re-occurring claim for cardiovascular disease three years before index death, and any claim for heart failure and epilepsy. Our results align with previous clinical work and highlight intervenable areas to reduce mortality in the Down syndrome population.

INTRODUCTION: The Diabetes Prevention Program (DPP) was a randomized clinical trial designed to prevent type 2 diabetes (T2D) in adults with prediabetes. The DPP Outcomes Study (DPPOS) is the 30-year follow-up of this cohort, focusing on T2D, prediabetes, and related complications. Cognitive assessments began in 2009 and expanded in 2022 to examine cognitive impairment, including Alzheimer's disease (AD) and AD related dementias (ADRD), in the surviving cohort. To support these aims, the National Alzheimer's Coordinating Center Uniform Data Set version 3 (NACC-UDSv3), the standardized framework used by Alzheimer's Disease Research Centers, was implemented in DPPOS in 2022 to enable data sharing with NACC. These forms were complemented by cognitive tests administered in DPPOS. We aimed to integrate the NACC-UDSv3 into the existing longitudinal DPPOS framework while maintaining fidelity to its structure and developing automated reports to streamline cognitive outcomes adjudication. METHODS: Items from the 16 NACC-UDSv3 data forms were compared with those already collected within DPPOS to integrate overlapping similar items, add missing NACC-UDSv3 items, and create a dataset harmonized with NACC-UDSv3. Forms were adapted for electronic data capture (EDC) using the MIDAS (Multimodal Integrated Data Acquisition System, George Washington University). Automated reports integrated current and prior neuropsychological scores to support adjudications. In the first wave of the DPPOS-AD/ADRD study, 1561 cognitive adjudications were successfully completed using the harmonized DPPOS and NACC-UDSv3 data implemented into MIDAS. DISCUSSION: The DPPOS-AD/ADRD project demonstrated that NACC-UDSv3 can be successfully integrated into a long-standing longitudinal cohort not originally designed for AD/ADRD research. The harmonization, electronic capture, and automated adjudication processes may provide a practical framework for other cohorts seeking to incorporate NACC-UDSv3 to align with national AD/ADRD research standards.

Introduction: The Diabetes Prevention Program Outcomes Study (DPPOS) is an established cohort of aging persons with pre-diabetes and type 2 diabetes with 25 years of median follow-up. In 2022 DPPOS added Alzheimer's disease (AD), and AD related dementias (ADRD) phenotyping using the National Alzheimer's Coordinating Center (NACC) Uniform Data Set (UDSv3), which included a standardized neurological examination across 25 clinical sites, administered by clinical staff and interpreted centrally by clinicians. Methods: A DPPOS video-based asynchronous neurological examination (DPPOS-VANE) was developed iteratively through consensus from research clinicians and staff feedback to harmonize with UDSv3 to identify common neurological diagnoses aside from dementia including diabetic cranial neuropathies, stroke and parkinsonism. DPPOS-VANE was designed to be conducted without direct participant contact by the examiner, reproducible, and independent of clinical skills of PCs. An iPad camera recorded the video exam, comprised of assessments of extraocular and facial movements, visual fields, speech, gross motor strength, pronator drift, praxis and parkinsonism. A 10-minute training video demonstrated the examination step-by-step with scripts and instructions in English and Spanish. Site-specific performance review, feedback, and staff certification preceded central reading of video recordings by physicians. After two years of implementation, 1286 DPPOS-VANEs led to 1284 examination reviews. Of these, 1204 (93%) were completed by having the examiner follow the standard script. Overall, 1237 examinations (96%) were delivered as planned, 41 (3%) had minor errors but were still usable, and 6 (0.4%) had major deviations in exam technique; two additional recorded evaluations were not usable as recorded videos were inaccessible due to technical errors. Each examination was completed within 10-15 minutes. Each site on average completed 51.4 examinations (range 14-92). Discussion: Engaging 55 research staff across 25 sites and 3 physician-reviewers, this study is the first to demonstrate feasibility of a VANE as an efficient neurological examination model enabled by commonly used devices. Such a multisite standardized VANE represents a novel paradigm for large epidemiological studies.

We used the September 2013 age-based rollout of the live-attenuated shingles vaccine in England as a natural experiment to estimate the effect of vaccine eligibility on shingles and dementia diagnoses in linked hospital records. Individuals born just before and after the eligibility cutoff were compared using regression discontinuity methods, with follow-up for up to eight years after programme introduction. Eligibility was associated with a clear reduction in hospital-coded shingles diagnoses (RD estimate -0.12 percentage points, 95% CI -0.153 to -0.079; p = 5.9 x 10-10), but there was no evidence of a corresponding reduction in hospital-coded dementia diagnoses (RD estimate -0.06 percentage points, 95% CI -0.40 to 0.27; p = 0.72). Results were robust across denominator definitions, diagnostic-code specifications, estimator choice, placebo cutoffs, and negative-control analyses. The dementia estimate was also close to null in an independently conducted analysis using a separately held HES extract. Comparator analyses in Welsh data with linked primary care and death data did not suggest these results were driven by our reliance on hospital data. These findings do not support a detectable intention-to-treat effect of live-attenuated shingles vaccine eligibility on hospital-coded dementia in England.

Background Primary care in China lacks structured mental-health assessment, and the machine-learning models that could support such screening are typically developed on heavily selected samples. Cumulative inclusion and exclusion criteria, though usually treated as neutral data-cleaning steps, can create heterogeneity in predictive reliability among retained participants. Using the China Health and Retirement Longitudinal Study (CHARLS) 2011 baseline, we quantified how selection funnels distort epidemiological associations and inflate machine-learning metrics, and tested selective prediction as mitigation. Methods Using the CHARLS 2011 baseline with temporal external validation in CHARLS-2018, we built a four-level selection funnel (L0-L3), evaluated five classifiers with nested cross-validation and SMOTE, and compared model-embedded uncertainty with a decoupled predictor-selector framework; XGBoost cross-validation residuals drove risk stratification and classification and regression tree (CART) rules. Results Sample sizes fell from L0 n=17,705 to L3 n=4,256 (24.0%). The cancer-depression odds ratio attenuated from 1.78 (95% CI 1.32-2.41) to 1.39 (0.74-2.63), losing significance. AUC rose with selection but not after multiple-comparison correction, whereas calibration error increased for four of five models. Model-embedded uncertainty succeeded only for XGBoost; with the decoupled XGBoost residual selector, all five models achieved selective prediction at approximately 20% coverage (test AUC 0.90, 95% CI 0.85-0.95), abstaining on approximately 80% of cases for individual safety. Risk stratification was stable (residual Spearman correlations >0.95; multi-seed Jaccard 0.88), and CART rules used self-rated health, education, pain, and marital status. Conclusions The findings support a deployable primary-care triage pathway: a four-variable rule identifies patients suitable for algorithm-assisted scoring (approximately 20% coverage) and routes the remainder to human evaluation. Methodologically, cumulative selection bias produces a dual distortion: epidemiological associations are compressed and machine-learning metrics inflated. Selective prediction is limited mainly by uncertainty-indicator design. Performance metrics should be reported with selection level, coverage, and calibration trajectory. Decoupled selective prediction with CART rule extraction provides an actionable framework for quality-controlled, tiered-care deployment. Keywords: selective prediction, selection bias, CHARLS, depression, predictor-selector decoupling, uncertainty quantification, classification and regression tree, triage, clinical decision support, health management.

Cognitive impairment is a prevalent symptom extending from physiological ageing to disease. It commonly manifests itself in initial memory problems, progressing and co-occurring in more severe conditions such as Mild Cognitive Impairment, Alzheimer's Disease and Major Depressive Disorder. However, current non-invasive screening assessments either lack biological information or are invasive and restricted to specialized centers with complex and cost-intensive set-ups. Here, we conducted an initial validation of mobile pupillometry with Virtual Reality (VR) under experimental conditions as a digital biomarker for cognitive impairment by testing required biomarker-specific properties. For this purpose, we first assessed its construct validity by testing healthy participants (n=43) on an n-back task in VR while pupil size was measured. Mixed effects models revealed that similar to lab-based eye-tracking systems, pupil size increased in a sensible and distinguishable fashion as a function of working memory load. Second, to test the signal's reliability, the same participants were tested on the identical set-up two to three months after their first visit. We observed that the pupil response profile was highly stable over this period. Third, for its clinical validity, we examined patients (n=89) from three different cohorts with varying degrees of cognitive impairment and compared them to healthy control participants (n=81). Mixed-effects models indicated that pupil size was reduced as a function of cognitive impairment levels at higher cognitive load and that this effect was stronger pronounced with increasing age. In conclusion, we provide initial evidence for mobile pupillometry being a sensitive, reliable and clinically valid digital biomarker for cognitive functioning and impairment, which offers desirable properties due to its quick, automatized and location-independent set-up. Keywords: digital biomarker, mobile pupillometry, Virtual Reality, cognition, , Major Depressive Disorder, Mild Cognitive Impairment, Alzheimer's Disease

Automated interpretation of neuroimaging studies requires simultaneous assessment of multiple imaging evidence variables, each tied to distinct anatomical structures. Vision-language models (VLMs) offer a unified framework for multi-task analysis, but adapting pre-trained VLMs remains challenging. Full fine-tuning is computationally prohibitive, and joint multi-task training requires simultaneous access to all task data, which is often infeasible in clinical settings. Although model merging enables multi-task composition without joint re-training, existing methods focus on post-hoc algorithms with limited extension to VLMs and minimal application to neuroimaging. Here, we present GRadient-guided Adapter Merging (GRAM), a layer-selective low-rank adaptation (LoRA)-based fine-tuning and merging framework for multi-task neuroimaging visual question-answering (VQA). GRAM uses a gradient ratio that contrasts class-specific gradients to identify task-discriminative layers, and applies subspace-constrained projected gradient descent to restrict LoRA updates to directions consistent with the geometry of the pre-trained model. We leveraged a structured VQA benchmark, developed from the National Alzheimer's Coordinating Center (NACC) dataset, that pairs multi-sequence brain MRI studies with question-answer pairs across clinically relevant imaging evidence variables. Experiments on the VQA benchmark showed that GRAM outperformed or matched all-layer LoRA fine-tuning and a standard merging baseline while reducing inter-task interference during merging, and approached or surpassed the performance of joint multi-task training without joint re-training.

Objectives To identify stakeholder-perceived design tensions in a two-sided marketplace for reusable digital therapeutics (DTx) software components and to use these tensions to propose alternative marketplace concepts. Methods We conducted 24 semi-structured interviews with digital health researchers and professionals. Data were analysed using hybrid deductive-inductive codebook thematic analysis. The Magic Triangle provided the initial deductive structure. One researcher coded all transcripts; a second independently applied the developing codebook to five transcripts to refine definitions and consistency. Seventeen parent themes were synthesized into 12 design tensions, which informed three author-generated marketplace concepts. Results Participants described trade-offs concerning target users and host, component scope and customization, quality labels, verification, geographic scope, pricing, interoperability, platform launch, risks and market niche. The resulting concepts emphasized a regional startup ecosystem, a research-oriented hybrid marketplace or a global marketplace with stricter entry requirements. Discussion The concepts combine the tensions in different ways and highlight competing priorities in governance, openness, assurance, scalability and early platform growth. Conclusion Stakeholders identified recurring design choices for a DTx software-component marketplace. The concepts provide hypotheses for prototyping and evaluation; the study did not test technical feasibility, market demand, regulatory acceptability or effects on development cost or time.

Introduction Parkinson's disease (PD) is a multifactorial disorder, affecting multiple neurotransmitter systems, including the cholinergic system. Cholinergic denervation is heterogeneous across patients and difficult to predict based on clinical presentation. In this study, we assessed the sensitivity of structural MRI (sMRI) and functional MRI (fMRI) to cholinergic degeneration related to PD and to cognitive functioning in PD. We compared our results to results from previously reported [18F]Fluoroethoxybenzovesamicol ([18F]FEOBV) PET imaging, which is considered the gold standard for cholinergic imaging. Methods 34 PD patients and 10 healthy controls underwent structural T1-weighted MRI. A subset of 14 patients and 9 controls also underwent resting-state fMRI. We extracted the bilateral volumes of the nucleus basalis of Meynert (NBM) from the sMRI images. Functional connectivity (FC) from the NBM to the cortex (NBM-FC) was determined using fMRI data. Principal component analysis (PCA) was applied to reduce the dimensionality of the NBM-FC images. We assessed performances for NBM-FC in distinguishing patients from controls using stepwise logistic regression. Similarly, NBM volume was used using logistic regression. Furthermore, the relation between these measures and cognitive function in several domains was investigated with (stepwise) linear regression. Leave-one-out cross validation (LOOCV) and bootstrapping was performed to assess robustness of the results. Results NBM-FC was well able to discriminate patients from controls with an AUC of 0.84 (95% CI: 0.62-1). NBM volume showed lower performance, but was still better than chance: AUC: 0.75 (95% CI: 0.57-0.93). Significant correlations were found between 1) cognition in the attentional domain and NBM-FC (r=0.63; p=.015) and 2) global cognition and NBM volume (r=0.55, p=.001). These results were inferior to those previously reported using [18F]FEOBV tracer uptake (see Chapter 6). Bootstrapping revealed that NBM volume of only the left hemisphere was stably related to PD diagnosis and global cognition in PD patients. We found that a lower NBM-FC in specific brain areas, including the fusiform gyrus, supramarginal gyrus and dorsolateral prefrontal cortex, was related to PD diagnosis. Bootstrapping revealed no stable NBM-FC pattern related to attention. Conclusion Although MRI results were slightly inferior to [18F]FEOBV PET data, MRI may provide a cheaper and more widely available alternative for cholinergic imaging. We recommend testing the utility of MRI as predictor and monitor of cholinergic treatment effect in a longitudinal study.

Aphasia diagnosis in Indonesia remains challenging due to limited culturally and linguistically appropriate instruments. Widely used tools such as the Boston Diagnostic Aphasia Examination (BDAE) and Western Aphasia Battery (WAB) are not adapted to the Indonesian context, while Tes Afasia untuk Diagnosis, Informasi, dan Rehabilitasi (TADIR) provides screening but lacks diagnostic accuracy. To address this gap, we developed the Instrumen Diagnosis dan Evaluasi Afasia (IDEA) for native Indonesian speakers and evaluated its validity, reliability, and normative cutoff values in cognitively healthy Indonesian adults. Eighty-three cognitively normal adults (screened using MoCA-Ina) with no history of neurological disease were assessed using IDEA, which evaluates six language domains. Items were adapted from existing tools and reviewed by experts. Content validity, internal consistency (Cronbachs alpha), and construct validity (Exploratory Factor Analysis) were analyzed using SPSS v25. A total of 83 participants were included (median age = 55.81 years, 54% secondary education). IDEA demonstrated good feasibility, with an average completion time of 45-60 minutes depending on participant engagement. Content validity was established by unanimous expert consensus. Construct validity showed meritorious sampling adequacy (KMO = .872) and significant sphericity (Bartletts test {chi}^2 (15) = 278.523, p<.001), supporting factor analysis. Internal consistency showed good reliability across six domains (Cronbachs = 0.896). IDEA is a valid and reliable tool for assessing aphasia in Indonesian natives. It is a culturally appropriate assessment tool which offers structured, domain-based evaluation and supports differential diagnosis of both classical and progressive aphasia syndromes. Keywords: Aphasia, Language Assessment, Indonesian, IDEA, Validity

Whether diverse populations outside Western settings are behaviourally ready to integrate wearable-derived data into clinical care remains poorly understood. This study examines sociotechnical determinants of wearable adoption and digital health data-sharing readiness in a large, highly diverse multinational population in Qatar, a rapidly digitising health ecosystem with advanced eHealth infrastructure. We conducted a cross-sectional community-based survey of 3,004 adults across Qatar, assessing wearable device use, behavioural engagement, and willingness to integrate wearable-generated data into healthcare workflows. Multivariable logistic regression identified independent predictors of wearable adoption. Wearable device use prevalence was 34.1%. Behavioural factors were the strongest independent predictors of adoption: daily exercisers had more than four times the odds of wearable use compared with rarely active participants, and willingness to share data with healthcare providers was independently associated with adoption after full adjustment. Notably, education level was not independently associated with wearable use, suggesting that behavioural readiness outweighs traditional socioeconomic indicators as a determinant of digital health engagement. Older age ([&ge;]56 years) and African ethnicity were associated with lower adoption odds, highlighting persistent digital inequities. These findings challenge the assumption that digital health equity is primarily an education or access problem, repositioning it as a behavioural engagement challenge. Health systems scaling remote monitoring programmes should prioritise identifying behaviourally engaged subpopulations rather than relying solely on demographic targeting. Targeted digital engagement strategies addressing older adults and underrepresented ethnic groups are essential for equitable implementation of digital medicine.

Background: Post-stroke dysphagia (PSD) contributes to aspiration, pneumonia, malnutrition, prolonged hospitalization and mortality. We evaluated the discrimination, validity and readiness of machine learning and data-driven prediction models for PSD-related outcomes. Methods: Following a prospectively registered protocol (PROSPERO CRD420261419259), we searched PubMed/MEDLINE, Embase, Web of Science Core Collection, CINAHL and CENTRAL from inception through June 7, 2026. Eligible studies developed or validated multivariable prediction models for PSD-related outcomes in adults with stroke. We used PROBAST and PROBAST+AI to assess risk of bias and applicability and TRIPOD+AI to evaluate reporting. Area under the curve (AUC) estimates were pooled on the logit scale with random-effects models. Results: Twenty-four studies were included and ten contributed to meta-analysis. Four studies predicting early or incident PSD yielded a pooled AUC of 0.94 (95% CI 0.60-0.99; I2 = 95.6%). Pooled AUCs were 0.84 (95% CI 0.71-0.92) for aspiration or penetration-aspiration and 0.89 (95% CI 0.24-1.00) for severe dysphagia. The exploratory analysis of all ten risk-prediction models produced an AUC of 0.90 (95% CI 0.80-0.95), but heterogeneity was substantial (I2 = 90.3%) and the prediction interval was 0.51-0.99. Every study had high risk of bias because of analysis-domain concerns; calibration and external validation were uncommon. Conclusions: Reported discrimination was often high, but the evidence does not establish reliable performance in care. Independent validation, calibration, complete model reporting and clinical-impact studies are needed before these models guide post-stroke swallowing care. Keywords: Post-stroke dysphagia; Stroke; Deglutition disorders; Machine learning; Clinical prediction model; Area under the curve; Meta-analysis