AI-based differential diagnosis of dementia etiologies on multimodal data.

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.

Impact of C-Reactive Protein on Cognition and Alzheimer Disease Biomarkers in Homozygous Apolipoprotein E ɛ4 Carriers.

OBJECTIVE: Previous research has shown that elevated blood C-reactive protein (CRP) is associated with increased Alzheimer's disease (AD) risk only in apoliprotein E4 genotype (APOE ε4) allele carriers. The objective of this study was to examine the interactive effects of plasma CRP and apoliprotein E (APOE) genotype on cognition and AD biomarkers. METHODS: Data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study was analyzed, including APOE genotype; plasma CRP concentrations; diagnostic status (i.e., MCI and dementia due to AD); Mini-Mental State Exam (MMSE) and Clinical Dementia Rating (CDR) Dementia Staging Instrument; cerebral spinal fluid (CSF) concentrations of amyloid-ß peptide (Aß42), total tau (t-Tau) and phosphorylated tau (p-Tau); and amyloid (AV45) PET imaging. Multivariable regression analyses tested the associations between plasma CRP and APOE on cognitive and biomarker outcomes. RESULTS: Among 566 ADNI participants, 274 (48.4%) had no, 222 (39.2%) had one, and 70 (12.4%) had two APOE ε4 alleles. Only among participants who had two APOE ε4 alleles, elevated CRP was associated with lower MMSE at baseline [ß (95%CI): -0.52 ( -1.01, -0.12)] and 12-month follow-up [ß (95%CI): -1.09 (-1.88, -0.17)] after adjusting for sex, age and education. The interaction of two APOE ε4 alleles and elevated plasma CRP was associated with increased CSF levels of t-Tau (ß = +11.21, SE = 3.37, p < 0.001) and p-Tau (ß = +2.74, SE = 1.14, p < 0.01). Among those who had no APOE ε4 allele, elevated CRP was associated with decreased CSF t-Tau and p-Tau. These effects were stronger at 12-month follow-up. CONCLUSIONS: CRP released during peripheral inflammation could be a mediator in APOE ε4 related AD neurodegeneration and serve as a drug target for AD.

Temporal association of neuropsychological test performance using unsupervised learning reveals a distinct signature of Alzheimer's disease status.

INTRODUCTION: 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. METHODS: 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. RESULTS: 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. DISCUSSION: 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.