Biology subjects

Mormino, E.

Publications and source records attributed to Mormino, E..

6 recordsLinked to original sources

bioRxiv2026

Predicting Autopsy-Confirmed Neuropathology across Clinical, Neuroimaging, and CSF Biomarkers using Machine Learning

Accurate in vivo prediction of neuropathology is critical for advancing diagnosis and treatment of Alzheimers disease and related dementias (ADRDs). As many individuals with ADRDs have mixed pathologies ({beta}-amyloid, pathologic tau, cerebrovascular disease, vascular brain injury, pathologic TDP-43, hippocampal sclerosis, Lewy bodies), there is interest in determining how accurately we can infer these pathologic changes from clinical data, biofluid assays (e.g., CSF), and neuroimaging. Here we evaluated automated machine learning models trained on data curated by the AD Sequencing Project Phenotype Harmonization Consortium (N=7,894 individuals), to predict 26 autopsy-confirmed neuropathological outcomes. Predictors included in vivo clinical and cognitive composite scores, brain measures from 3D structural MRI and diffusion tensor imaging, image-derived measures of white matter hyperintensities (WMH), and CSF biomarkers. Predictive models were trained using ensemble learning with stratified cross-validation. We assessed performance using Spearmans rank correlation and Matthews correlation coefficient, to accommodate co-occurring pathologic changes. The added value of neuroimaging and CSF versus clinical features alone was quantified. Braak stage was among the most consistently predicted outcomes. CSF biomarkers best predicted {beta}-amyloid and tau pathology, but diffusion MRI metrics best captured vascular brain injury and white matter injury, and outperformed clinical and cognitive measures and anatomical MRI in predicting Lewy body disease. Anatomical measures from structural MRI outperformed standard clinical assessments in assessing neurodegeneration and hippocampal sclerosis, and WMH complemented cognitive measures in predicting TDP-43 pathology. These results establish a baseline for comparing modalities for inferring neuropathology.

neuroscience↗

bioRxiv2026

Latent brain state dynamics predict early amyloid accumulation and cognitive impairment

Amyloid-{beta} (A{beta}) accumulation is a continuous process central to pathological aging that begins decades before cognitive impairment emerges. While subthreshold A{beta} levels have been linked to future decline in cognitive control, the neural mechanisms connecting this early accumulation to its neurocognitive impact are poorly understood. Brain circuit dynamics, which are essential for cognitive function, may offer a sensitive lens into these initial pathological changes. Here, we tested whether brain state dynamics could serve as sensitive markers for cognitive impairment at an early stage of A{beta} burden. Using the Bayesian Switching Dynamic System (BSDS) model, we identified 4 distinct latent brain states from high-temporal-resolution (800 ms) fMRI data acquired from 116 older adults, including 72 cognitively normal (CN) individuals and 44 with mild cognitive impairment (MCI), during an N-back working-memory task. Adopting a dimensional approach, we examined how latent brain state dynamics relate to early amyloid burden, cognitive performance, and clinical symptoms. While A{beta} levels failed to differentiate clinical groups or predict clinical symptoms and task performance, the dynamics of latent brain states proved highly sensitive to both early A{beta} accumulation and cognition. Canonical correlation analysis revealed a significant relationship between brain state dynamics and early A{beta} burden. Furthermore, the temporal properties of brain states were significantly predictive of working memory performance in CN individuals, a relationship that was selectively disrupted in the MCI group. The features of brain dynamics can also successfully predict cognitive impairment. Our findings establish brain state dynamics as sensitive neural markers of initial A{beta} accumulation and early cognitive impairment, offering a new framework for developing predictive models to identify individuals at risk for future cognitive decline.

neuroscience↗

bioRxiv2025

Denoising 7T Structural MRI with Conditional Generative Diffusion Models

Purpose7T MRI offers ultra-high resolution and improved sensitivity for iron deposition in neurodegenerative disorders, but commonly used acquisitions are long and hence challenging, especially for elderly subjects. Efficiently denoising a short acquisition to achieve the image quality of a longer acquisition would be of translational benefit. Materials and MethodsWe introduce a conditional diffusion model derived from generative AI (a 7T Conditional Diffusion Model, 7TCDM) that was trained on native single-acquisition 2D reconstructions and referenced multi-repetition images to guide the denoising process and improve SNR and contrast. 7TCDM model was tested on 2D T2-weighted gradient-echo imaging from 19 participants, including healthy controls and individuals with mild cognitive impairment or Alzheimers disease (AD). 7TCDMs performance was assessed using Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and comprehensive reader studies. ResultsReferencing the multi-repetition ground truth, 7TCDM improved the single-acquisition original image by 29.1% in MSE, 5.8% in PSNR, and 9.4% in SSIM, and outperformed convolutional neural network-based models in all metrics. Expert rater evaluations confirmed superior image quality, with significantly enhanced detail and contrast preservation in regions such as the hippocampi, white matter lesions, and small cortical veins. The model also demonstrated robust performance in both the concurrently acquired and publicly available 3D multi-echo gradient echo acquisitions, which the model was not trained on. ConclusionsThe 7T Conditional Diffusion Model provides high-quality denoised images from shorter scans, increasing the feasibility of scanning patients in shorter times while preserving essential anatomical and pathological details.

neuroscience↗

bioRxiv2024

Top-down attention and Alzheimer's pathology impact cortical selectivity during learning,influencing episodic memory in older adults

Human aging affects the ability to remember new experiences, in part, because of altered neural function during memory formation. One potential contributor to age-related memory decline is diminished neural selectivity -- i.e., a decline in the differential response of cortical regions to preferred vs. non-preferred stimuli during event perception -- yet the factors driving variability in neural selectivity with age remain unclear. We examined the impact of top-down attention and preclinical Alzheimers disease (AD) pathology on neural selectivity during memory encoding in 156 cognitively unimpaired older participants who underwent fMRI while performing a word-face and word-scene associative memory task. Neural selectivity in face- and place-selective cortical regions was greater during events that were later remembered compared to forgotten. Critically, neural selectivity during learning positively scaled with memory-related variability in top-down attention, whereas selectivity negatively related to early AD pathology, evidenced by elevated plasma pTau181. Path analysis revealed that neural selectivity at encoding mediated the effects of age, top-down attention, and pTau181 on associative memory. Collectively, these data reveal multiple pathways that contribute to memory differences among older adults -- AD-independent reductions in top-down attention and AD-related pathology alter the precision of cortical representations of events during experience, with consequences for remembering.

neuroscience↗

bioRxiv2024

Synapse protein signatures in cerebrospinal fluid and plasma predict cognitive maintenance versus decline in Alzheimers disease

Rates of cognitive decline in Alzheimers disease (AD) are extremely heterogeneous, with ages of symptom onset ranging from age 40-100 years and conversion from mild cognitive impairment to AD dementia taking 2-20 years. Development of biomarkers for amyloid-beta (A{beta}) and tau protein aggregates, the hallmark pathologies of AD, have improved patient monitoring/stratification and drug development, but they still only explain 20-40% of the variance in cognitive impairment (CI) in AD. To discover additional molecular drivers and biomarkers of AD dementia, we perform cerebrospinal fluid (CSF) proteomics on 3,416 individuals from six deeply phenotyped prospective AD case-control cohorts. We identify synapse proteins as the strongest correlates of CI, independent of A{beta} and tau. Using machine learning we derive the CSF YWHAG:NPTX2 synapse protein ratio, a robust correlate of CI, which explains 27% of the variance in CI beyond CSF PTau181:A{beta}42, 10% beyond tau PET, and 50% beyond CSF NfL in A{beta} positive individuals. We find YWHAG:NPTX2 also increases with normal aging as early as age 20 and increases at a faster rate in APOE4 carriers and autosomal dominant-AD mutation carriers. Most notably, YWHAG:NPTX2+ individuals (top 25th percentile) are 15-times (HR=15.4 [10.6-22.2]) more likely to experience cognitive decline over 15 years compared to YWHAG:NPTX2- individuals (bottom 25th percentile), and this rises to 19-times (HR=18.9 [10.83-32.9]) with additional stratification by A{beta} and phosphorylated tau status. Lastly, we perform plasma proteomics on 4,245 individuals to develop a plasma-based signature of CI which partly recapitulates CSF YWHAG:NPTX2. Overall, our findings underscore CSF YWHAG:NPTX2 and the corresponding plasma signature as robust prognostic biomarkers for AD onset and progression beyond gold-standard biomarkers of A{beta}, tau, and neurodegeneration and implicate synapse dysfunction as a core driver of AD dementia.

neuroscience↗

bioRxiv2018

Lipid associated polygenic enrichment in Alzheimer’s disease

Cardiovascular (CV) and lifestyle associated risk factors (RFs) are increasingly recognized as important for Alzheimers disease (AD) pathogenesis. Beyond the [isin]4 allele of apolipoprotein E (APOE), comparatively little is known about whether CV associated genes also increase risk for AD (genetic pleiotropy). Using large genome-wide association studies (GWASs) (total n > 500,000 cases and controls) and validated tools to quantify genetic pleiotropy, we systematically identified single nucleotide polymorphisms (SNPs) jointly associated with AD and one or more CV RFs, namely body mass index (BMI), type 2 diabetes (T2D), coronary artery disease (CAD), waist hip ratio (WHR), total cholesterol (TC), low-density (LDL) and high-density lipoprotein (HDL). In fold enrichment plots, we observed robust genetic enrichment in AD as a function of plasma lipids (TC, LDL, and HDL); we found minimal AD genetic enrichment conditional on BMI, T2D, CAD, and WHR. Beyond APOE, at conjunction FDR < 0.05 we identified 57 SNPs on 19 different chromosomes that were jointly associated with AD and CV outcomes including APOA4, ABCA1, ABCG5, LIPG, and MTCH2/SPI1. We found that common genetic variants influencing AD are associated with multiple CV RFs, at times with a different directionality of effect. Expression of these AD/CV pleiotropic genes was enriched for lipid metabolism processes, over-represented within astrocytes and vascular structures, highly co-expressed, and differentially altered within AD brains. Beyond APOE, we show that the polygenic component of AD is enriched for lipid associated RFs. Rather than a single causal link between genetic loci, RF and the outcome, we found that common genetic variants influencing AD are associated with multiple CV RFs. Our collective findings suggest that a network of genes involved in lipid biology also influence Alzheimers risk.

genetics↗