Machine Learning Classification of Alzheimer's Disease Pathology Reveals Diffuse Amyloid as a Major Predictor of Cognitive Impairment in Human Hippocampal Subregions

Stephen, T.-L.; Korobkova, L.; Breningstall, B.; Nguyen, K.; Mehta, S.; Pachicano, M.; Jones, K.; Hawes, D.; Cabeen, R. P.; Bienkowski, M.

doi:10.1101/2023.05.31.543117

bioRxiv · 10.1101/2023.05.31.543117

Machine Learning Classification of Alzheimer's Disease Pathology Reveals Diffuse Amyloid as a Major Predictor of Cognitive Impairment in Human Hippocampal Subregions

Stephen, T.-L.·Korobkova, L.·Breningstall, B.·Nguyen, K.·Mehta, S.·Pachicano, M.·Jones, K.·Hawes, D.·Cabeen, R. P.·Bienkowski, M.

View original source ↗Export metadata ↓

Abstract

Analyzing Alzheimers disease (AD) pathology within anatomical subregions is a significant challenge, often carried out by pathologists using a standardized, semi-quantitative approach. To augment traditional methods, a high-throughput, high-resolution pipeline was created to classify the distribution of AD pathology within hippocampal subregions. USC ADRC post-mortem tissue sections from 51 patients were stained with 4G8 for amyloid, Gallyas for neurofibrillary tangles (NFTs) and Iba1 for microglia. Machine learning (ML) techniques were utilized to identify and classify amyloid pathology (dense, diffuse and APP (amyloid precursor protein)), NFTs, neuritic plaques and microglia. These classifications were overlaid within manually segmented regions (aligned with the Allen Human Brain Atlas) to create detailed pathology maps. Cases were separated into low, intermediate, or high AD stages. Further data extraction enabled quantification of plaque size and pathology density alongside ApoE genotype, sex, and cognitive status. Our findings revealed that the increase in pathology burden across AD stages was driven mainly by diffuse amyloid. The pre and para-subiculum had the highest levels of diffuse amyloid while NFTs were highest in the A36 region in high AD cases. Moreover, different pathology types had distinct trajectories across disease stages. In a subset of AD cases, microglia were elevated in intermediate and high compared to low AD. Microglia also correlated with amyloid pathology in the Dentate Gyrus. The size of dense plaques, which may represent microglial function, was lower in ApoE4 carriers. In addition, individuals with memory impairment had higher levels of both dense and diffuse amyloid. Taken together, our findings integrating ML classification approaches with anatomical segmentation maps provide new insights on the complexity of disease pathology in AD progression. Specifically, we identified diffuse amyloid pathology as being a major driver of AD in our cohort, regions of interest and microglial responses that might advance AD diagnosis and treatment.

Explore related subjects

neuroscience Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Stephen, T.-L., Korobkova, L., Breningstall, B., Nguyen, K., Mehta, S., Pachicano, M., Jones, K., Hawes, D., Cabeen, R. P., Bienkowski, M.. 2023-06-05. Machine Learning Classification of Alzheimer's Disease Pathology Reveals Diffuse Amyloid as a Major Predictor of Cognitive Impairment in Human Hippocampal Subregions. https://doi.org/10.1101/2023.05.31.543117

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

The Unreasonable Effectiveness of Cell Types in Describing Neuronal Physiological Features

Single-cell RNA sequencing (scRNA-seq) captures detailed gene expression profiles at scale, while patch-clamp recordings measure intrinsic neuronal electrophysiological properties. Modeling the relations between these two modalities remains a challenge. Here, we compare how well electrophysiological features can be predicted by traditional transcriptomic cell type classification, representations derived from a foundational model (scGPT) pretrained on large-scale scRNA-seq datasets, ion channel-coding genes, and highly variable genes. Using paired transcriptomic and electrophysiological patch-sequencing data from 495 human neurons from neurosurgical tissue, we find that cluster-level cell type representations consistently outperform highly variable gene selection, ion channel gene selection, and context-enriched scGPT embeddings. Notably, performance varies across model architectures and initializations, and the best results are obtained by combining the outputs of separate cell type and scGPT-based models. Together, these findings suggest that traditional discrete cellular classification is highly effective in predicting physiological features. For maximum performance it can be complemented by pretrained transformer models.

neuroscience↗

bioRxiv2026

A nonlinear inhibition pathway underlying cortical responses to tuned holographic optogenetic perturbations

Optogenetics enables causal manipulation of cortical activity. Perturbation responses can be counterintuitive due to network interactions, making theory essential for predicting them. Existing approaches often rely on linear approximations, which fail for many biologically relevant perturbations. Here we develop a nonlinear theory of responses to holographic perturbations in cell-type-specific recurrent networks with structured connectivity. We fit a nonlinear model to mouse V1 data, which shows cotuned-ensemble suppression: perturbing spatially clustered neurons with similar preferred orientations yields markedly stronger short-range suppression than perturbing untuned ensembles. We show that cotuned-ensemble suppression arises from a feature-tuned, nonlinear inhibition pathway implicating somatostatin-positive (SST) interneurons. The theory predicts that cotuned ensembles suppress parvalbumin-positive (PV) neurons but facilitate SST neurons, and links the degree of cotuned-ensemble suppression or facilitation to the variance of the SST response. This framework identifies mechanisms by which nonlinear inhibition sculpts cortical dynamics and establishes a predictive basis for targeted optogenetic interventions.

neuroscience↗

bioRxiv2026

Proteomic signatures of APOE ε4 across human tissues and cell types in Alzheimers disease

The apolipoprotein E {varepsilon}4 (APOE {varepsilon}4) allele is the strongest genetic risk factor for late-onset Alzheimers disease (AD). However, the underlying molecular mechanisms remain unclear. This study included 1691 participants from the Religious Orders Study and Rush Memory and Aging Project (ROSMAP), 1226 participants from the Accelerating Medicines Partnership - Alzheimers Disease (AMP-AD) Diverse Cohorts Study, and 735 participants from the Alzheimers Disease Neuroimaging Initiative (ADNI). To characterise APOE {varepsilon}4 molecular effects, we analysed proteomic data from plasma, cerebrospinal fluid (CSF), and induced pluripotent stem cell (iPSC)-derived astrocytes and neurons, as well as transcriptomic and proteomic data from multiple brain regions. The association of APOE {varepsilon}4 with AD neuropathology was also examined. APOE {varepsilon}4 carriers shared a plasma proteomic signature enriched for immune processes, irrespective of AD diagnosis. A machine learning classifier trained on this signature discriminated APOE {varepsilon}4 carriers from non-carriers in an independent cohort using CSF proteomics. APOE {varepsilon}4 carriage was associated with higher Braak stages and Consortium to Establish a Registry for Alzheimers Disease (CERAD) score. However, only limited APOE {varepsilon}4-associated transcriptomic and proteomic changes were observed in bulk brain tissue, with poor cross-layer concordance. Proteomic analyses of iPSC-derived astrocytes and neurons further revealed cell-type-specific APOE {varepsilon}4-associated changes. APOE {varepsilon}4 is associated with a consistent proteomic signature across plasma and CSF. Its molecular effects in the brain differ across cell types, brain regions and molecular layers. These findings support the need for cell-type-resolved multi-omic studies to elucidate how APOE {varepsilon}4 confers AD risk.

neuroscience↗