Explore the vast range of titles available.

Biomedical research requires large, diverse samples to produce unbiased results. Retrospective data harmonization is often used to integrate existing datasets to create these samples, but the process is labor-intensive. Automated methods for matching variables across datasets can accelerate this process, particularly when harmonizing datasets with numerous variables and varied naming conventions. Research in this area has been limited, primarily focusing on lexical matching and ontology-based semantic matching. We aimed to develop new methods, leveraging large language models (LLMs) and ensemble learning, to automate variable matching. This study utilized data from two GERAS cohort studies (European [EU] and Japan [JP]) obtained through the Alzheimer's Disease (AD) Data Initiative's AD workbench. We first manually created a dataset by matching 347 EU variables with 1322 candidate JP variables and treated matched variable pairs as positive instances and unmatched pairs as negative instances. We then developed four natural language processing (NLP) methods using state-of-the-art LLMs (E5, MPNet, MiniLM, and BioLORD-2023) to estimate variable similarity based on variable labels and derivation rules. A lexical matching method using fuzzy matching was included as a baseline model. In addition, we developed an ensemble-learning method, using the Random Forest (RF) model, to integrate individual NLP methods. RF was trained and evaluated on 50 trials. Each trial had a random split (4:1) of training and test sets, with the model's hyperparameters optimized through cross-validation on the training set. For each EU variable, 1322 candidate JP variables were ranked based on NLP-derived similarity scores or RF's probability scores, denoting their likelihood to match the EU variable. Ranking performance was measured by top-n hit ratio (HR-n) and mean reciprocal rank (MRR). E5 performed best among individual methods, achieving 0.898 HR-30 and 0.700 MRR. RF performed better than E5 on all metrics over 50 trials (P < 0.001) and achieved an average HR-30 of 0.986 and MRR of 0.744. LLM-derived features contributed most to RF's performance. One major cause of errors in automatic variable matching was ambiguous variable definitions. NLP techniques (especially LLMs), combined with ensemble learning, hold great potential in automating variable matching and accelerating biomedical data harmonization.

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an artificial intelligence (AI) model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a microaveraged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the microaveraged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in clinical settings and drug trials. Further prospective studies are needed to confirm its ability to improve patient care. Drawing on 51,269 participants across 9 independent, geographically diverse datasets, an AI model identifies the etiologies contributing to dementia in individuals, harnessing a broad array of data, including demographics, medical history, medication use, neuropsychological assessments, functional evaluations, and multimodal neuroimaging.

The association between peripheral inflammatory biomarkers and Alzheimer disease (AD) is not consistent in the literature. It is possible that chronic inflammation, rather than 1 episode of inflammation, interacts with genetic vulnerability to increase the risk for AD. To study the interaction between the apolipoprotein E (ApoE) genotype and chronic low-grade inflammation and its association with the incidence of AD. In this cohort study, data from 2656 members of the Framingham Heart Study offspring cohort (Generation 2; August 13, 1971-November 27, 2017) were evaluated, including longitudinal measures of serum C-reactive protein (CRP), diagnoses of incident dementia including AD, and brain volume. Chronic low-grade inflammation was defined as having CRP at a high cutoff level at a minimum of 2 time points. Statistical analysis was performed from December 1, 1979, to December 31, 2015. Development of AD and brain volumes. Of the 3130 eligible participants, 2656 (84.9%; 1227 men and 1429 women; mean [SD] age at last CRP measurement, 61.6 [9.5] years) with both ApoE status and longitudinal CRP measurements were included in this study analysis. Median (interquartile range) CRP levels increased with mean (SD) age (43.3 [9.6] years, 0.95 mg/L [0.40-2.35 mg/L] vs 59.1 [9.6] years, 2.04 mg/L [0.93-4.75 mg/L] vs 61.6 [9.5] years, 2.21 mg/L [1.05-5.12 mg/L]; P < .001), but less so among those with ApoE4 alleles, followed by ApoE3 then ApoE2 genotypes. During the 17 years of follow-up, 194 individuals (7.3%) developed dementia, 152 (78.4%) of whom had AD. ApoE4 coupled with chronic low-grade inflammation, defined as a CRP level of 8 mg/L or higher, was associated with an increased risk of AD, especially in the absence of cardiovascular diseases (hazard ratio, 6.63; 95% CI, 1.80-24.50; P = .005), as well as an increased risk of earlier disease onset compared with ApoE4 carriers without chronic inflammation (hazard ratio, 3.52; 95% CI, 1.27-9.75; P = .009). This phenomenon was not observed among ApoE3 and ApoE2 carriers with chronic low-grade inflammation. Finally, a subset of 1761 individuals (66.3%) underwent brain magnetic resonance imaging, and the interaction between ApoE4 and chronic low-grade inflammation was associated with brain atrophy in the temporal lobe (β = -0.88, SE = 0.22; P < .001) and hippocampus (β = -0.04, SE = 0.01; P = .005), after adjusting for confounders. In this study, peripheral chronic low-grade inflammation in participants with ApoE4 was associated with shortened latency for onset of AD. Rigorously treating chronic systemic inflammation based on genetic risk could be effective for the prevention and intervention of AD.

The digital Clock Drawing Test (dCDT) has been recently used as a more objective tool to assess cognition. However, the association between digitally obtained clock drawing features and structural neuroimaging measures has not been assessed in large population-based studies. We aimed to investigate the association between dCDT features and brain volume. This study included participants from the Framingham Heart Study who had both a dCDT and magnetic resonance imaging (MRI) scan, and were free of dementia or stroke. Linear regression models were used to assess the association between 18 dCDT composite scores (derived from 105 dCDT raw features) and brain MRI measures, including total cerebral brain volume (TCBV), cerebral white matter volume, cerebral gray matter volume, hippocampal volume, and white matter hyperintensity (WMH) volume. Classification models were also built from clinical risk factors, dCDT composite scores, and MRI measures to distinguish people with mild cognitive impairment (MCI) from those whose cognition was intact. A total of 1656 participants were included in this study (mean age 61 years, SD 13 years; 50.9% women), with 23 participants diagnosed with MCI. All dCDT composite scores were associated with TCBV after adjusting for multiple testing (P value <.05/18). Eleven dCDT composite scores were associated with cerebral white matter volume, but only 1 dCDT composite score was associated with cerebral gray matter volume. None of the dCDT composite scores was associated with hippocampal volume or WMH volume. The classification model for differentiating MCI and normal cognition participants, which incorporated age, sex, education, MRI measures, and dCDT composite scores, showed an area under the curve of 0.897. dCDT composite scores were significantly associated with multiple brain MRI measures in a large community-based cohort. The dCDT has the potential to be used as a cognitive assessment tool in the clinical diagnosis of MCI.

Subtle cognitive alterations that precede clinical evidence of cognitive impairment may help predict the progression to Alzheimer’s disease (AD). Neuropsychological (NP) testing is an attractive modality for screening early evidence of AD. Longitudinal NP and demographic data from the Framingham Heart Study (FHS; N = 1696) and the National Alzheimer's Coordinating Center (NACC; N = 689) were analyzed using an unsupervised machine learning framework. Features, including age, logical memory-immediate and delayed recall, visual reproduction-immediate and delayed recall, the Boston naming tests, and Trails B, were identified using feature selection, and processed further to predict the risk of development of AD. Our model yielded 83.07 ± 3.52% accuracy in FHS and 87.57 ± 1.19% accuracy in NACC, 80.52 ± 3.93%, 86.74 ± 1.63% sensitivity in FHS and NACC respectively, and 85.63 ± 4.71%, 88.41 ± 1.38% specificity in FHS and NACC, respectively. Our results suggest that a subset of NP tests, when analyzed using unsupervised machine learning, may help distinguish between high- and low-risk individuals in the context of subsequent development of AD within 5 years. This approach could be a viable option for early AD screening in clinical practice and clinical trials.

Background Informal caregiving is a major driver of the societal impact of Alzheimer’s disease (AD) and has important implications for caregiver health, workforce participation, and gender equity. While prior research indicates that female informal caregivers of people living with AD experience greater physical and psychological burden than their male counterparts, most studies are limited to single-country contexts, and little is known about gender differences in nonmedical societal costs. To address these gaps, we examined caregiver-gender differences in informal care costs and caregiver burden associated with AD across seven countries. Methods We conducted a cross-sectional analysis of harmonized baseline data from community-dwelling individuals with clinically diagnosed AD and their informal caregivers in four cohort studies: GERAS-EU (France, Germany, United Kingdom), GERAS-II (Italy, Spain), GERAS-JP (Japan), and GERAS-US (United States), accessed via the AD Data Initiative’s AD Workbench. Monthly informal care costs (e.g., costs of caregiver time and missing work) were derived using the Resource Utilization in Dementia Questionnaire and quantified in US dollars. Caregiver burden was assessed using the Zarit Burden Interview (ZBI) questionnaire (total score: 0–88). We estimated caregiver-gender differences in informal care costs using two-part models (logistic regression followed by gamma regression) and differences in ZBI using linear regression. All models were adjusted for care recipient and caregiver characteristics and country. Secondary analyses stratified the models by disease severity, caregiver employment status, and country. Results Among 3,318 caregivers (66.2% women; mean age 63.1 ± 13.8 years), female caregivers had higher monthly informal care costs than male caregivers (adjusted mean difference: 191.8 USD; 95% CI: 27.4 to 356.1; P =.02) and greater burden (adjusted mean difference in ZBI: 4.0 points; 95% CI: 2.6 to 5.3; P <.001). Gender-disparity patterns were significant or directionally consistent in most stratified analyses and were also consistently observed in sensitivity analyses using an imputed dataset. Conclusions Across seven countries, women providing informal care for people living with AD experienced higher costs and greater burden than men, highlighting gender-disparity in unpaid care. These findings support public health and policy efforts to strengthen caregiver supports (e.g., workplace accommodations and tailored caregiver support programs) to reduce burden and productivity loss, particularly for women.

Human voice has increasingly been recognized as an effective indicator for the detection of cognitive disorders. However, the association of acoustic features with specific cognitive functions and mild cognitive impairment (MCI) has yet to be evaluated in a large community-based population. This study aimed to investigate the association between acoustic features and neuropsychological (NP) tests across multiple cognitive domains and evaluate the added predictive power of acoustic composite scores for the classification of MCI. This study included participants without dementia from the Framingham Heart Study, a large community-based cohort with longitudinal surveillance for incident dementia. For each participant, 65 low-level acoustic descriptors were derived from voice recordings of NP test administration. The associations between individual acoustic descriptors and 18 NP tests were assessed with linear mixed-effect models adjusted for age, sex, and education. Acoustic composite scores were then built by combining acoustic features significantly associated with NP tests. The added prediction power of acoustic composite scores for prevalent and incident MCI was also evaluated. The study included 7874 voice recordings from 4950 participants (age: mean 62, SD 14 years; 4336/7874, 55.07% women), of whom 453 were diagnosed with MCI. In all, 8 NP tests were associated with more than 15 acoustic features after adjusting for multiple testing. Additionally, 4 of the acoustic composite scores were significantly associated with prevalent MCI and 7 were associated with incident MCI. The acoustic composite scores can increase the area under the curve of the baseline model for MCI prediction from 0.712 to 0.755. Multiple acoustic features are significantly associated with NP test performance and MCI, which can potentially be used as digital biomarkers for early cognitive impairment monitoring.

Cerebral microbleeds (CMB) increase the risk for Alzheimer disease. Current neuroimaging methods that are used to detect CMB are costly and not always accessible. This study aimed to explore whether the digital clock-drawing test (DCT) may provide a behavioral indicator of CMB. In this study, we analyzed data from participants in the Framingham Heart Study offspring cohort who underwent both brain magnetic resonance imaging scans (Siemens 1.5T, Siemens Healthcare Private Limited; T2*-GRE weighted sequences) for CMB diagnosis and the DCT as a predictor. Additionally, paper-based clock-drawing tests were also collected during the DCT. Individuals with a history of dementia or stroke were excluded. Robust multivariable linear regression models were used to examine the association between DCT facet scores with CMB prevalence, adjusting for relevant covariates. Receiver operating characteristic (ROC) curve analyses were used to evaluate DCT facet scores as predictors of CMB prevalence. Sensitivity analyses were conducted by further including participants with stroke and dementia. The study sample consisted of 1020 (n=585, 57.35% female) individuals aged 45 years and older (mean 72, SD 7.9 years). Among them, 64 (6.27%) participants exhibited CMB, comprising 46 with lobar-only, 11 with deep-only, and 7 with mixed (lobar+deep) CMB. Individuals with CMB tended to be older and had a higher prevalence of mild cognitive impairment and higher white matter hyperintensities compared to those without CMB (P<.05). While CMB were not associated with the paper-based clock-drawing test, participants with CMB had a lower overall DCT score (CMB: mean 68, SD 23 vs non-CMB: mean 76, SD 20; P=.009) in the univariate comparison. In the robust multiple regression model adjusted for covariates, deep CMB were significantly associated with lower scores on the drawing efficiency (β=-0.65, 95% CI -1.15 to -0.15; P=.01) and simple motor (β=-0.86, 95% CI -1.43 to -0.30; P=.003) domains of the command DCT. In the ROC curve analysis, DCT facets discriminated between no CMB and the CMB subtypes. The area under the ROC curve was 0.76 (95% CI 0.69-0.83) for lobar CMB, 0.88 (95% CI 0.78-0.98) for deep CMB, and 0.98 (95% CI 0.96-1.00) for mixed CMB, where the area under the ROC curve value nearing 1 indicated an accurate model. The study indicates a significant association between CMB, especially deep and mixed types, and reduced performance in drawing efficiency and motor skills as assessed by the DCT. This highlights the potential of the DCT for early detection of CMB and their subtypes, providing a reliable alternative for cognitive assessment and making it a valuable tool for primary care screening before neuroimaging referral.

Apolipoprotein ε4 ( APOE ε4) is the most significant genetic risk factor for late-onset Alzheimer’s disease (AD). Elevated blood C-reactive protein (CRP) further increases the risk of AD for people carrying the APOE ε4 allele. We hypothesized that CRP, as a key inflammatory element, could modulate the impact of other genetic variants on AD risk. We selected ten single nucleotide polymorphisms (SNPs) in reported AD risk loci encoding proteins related to inflammation. We then tested the interaction effects between these SNPs and blood CRP levels on AD incidence using the Cox proportional hazards model in UK Biobank ( n  = 279,176 white participants with 803 incident AD cases). The five top SNPs were tested for their interaction with different CRP cutoffs for AD incidence in the Framingham Heart Study (FHS) Generation 2 cohort ( n  = 3009, incident AD = 156). We found that for higher concentrations of serum CRP, the AD risk increased for SNP genotypes in 3 AD-associated genes ( SPI1 , CD33 , and CLU ). Using the Cox model in stratified genotype analysis, the hazard ratios (HRs) for the association between a higher CRP level (≥10 vs. <10 mg/L) and the risk of incident AD were 1.94 (95% CI: 1.33–2.84, p  < 0.001) for the SPI1 rs1057233-AA genotype, 1.75 (95% CI: 1.20–2.55, p  = 0.004) for the CD33 rs3865444-CC genotype, and 1.76 (95% CI: 1.25–2.48, p  = 0.001) for the CLU rs9331896-C genotype. In contrast, these associations were not observed in the other genotypes of these genes. Finally, two SNPs were validated in 321 Alzheimer’s Disease Neuroimaging (ADNI) Mild Cognitive Impairment (MCI) patients. We observed that the SPI1 and CD33 genotype effects were enhanced by elevated CRP levels for the risk of MCI to AD conversion. Furthermore, the SPI1 genotype was associated with CSF AD biomarkers, including t-Tau and p-Tau, in the ADNI cohort when the blood CRP level was increased ( p  < 0.01). Our findings suggest that elevated blood CRP, as a peripheral inflammatory biomarker, is an important moderator of the genetic effects of SPI1 and CD33 in addition to APOE ε4 on AD risk. Monitoring peripheral CRP levels may be helpful for precise intervention and prevention of AD for these genotype carriers.

Monocyte chemoattractant protein-1 (MCP-1), a cytokine involved in peripheral inflammation, has been shown to modulate established Alzheimer’s disease (AD) loci. In this study, we hypothesized that blood MCP-1 levels may impact the associations of other genetic variants with AD risk beyond the well-established AD loci. We performed a genome-wide association study (GWAS) using logistic regression with the generalized estimating equation (GEE) and Cox proportional hazards models to examine the combined effects of single nucleotide polymorphisms (SNPs) and blood MCP-1 levels on AD. Three datasets were used: the Framingham Heart Study (FHS), Religious Orders Study/Memory and Aging Project (ROSMAP), and Alzheimer’s Disease Neuroimaging Initiative (ADNI). We identified SNPs in two genes in the meta-analysis, namely, neuron navigator 3 ( NAV3 , also named unc-53 homolog 3, rs696468) (p < 7.55 × 10 −9 ) and the homolog unc-5 netrin receptor c ( UNC5C rs72659964) (p < 1.07 × 10 −8 ), which are modified by blood MCP-1 concentration for AD risk. Elevated blood MCP-1 concentrations increased AD risk and brain AD pathology in individuals with NAV3 (rs696468-CC) and UNC5C (rs72659964-AT + TT) genotypes. Given that NAV3 and UNC5C are involved in regulating neurite outgrowth and guidance, increased MCP-1 levels may disturb the functions of vulnerable gene carriers to increase AD risk.