Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2025.01.10.632396

Machine learning identifies routine blood tests as accurate predictive measures of pollution-dependent poor cognitive function

Johnson, H.·Longden, J.·Cameron, G.·Waiter, G. D.·Waldron, F. M.·Gregory, J. M.·Spence, H.
View original source ↗Export metadata ↓

Abstract

BackgroundSeveral modifiable risk factors for dementia and related neurodegenerative diseases have been identified including education level, socio-economic status, and environmental exposures - however, how these population-level risks relate to individual risk remains elusive. To address this, we assess over 450 potential risk factors in one deeply clinically and demographically phenotyped cohort using random forest classifiers to determine predictive markers of poor cognitive function. This study aims to understand early risk factors for dementia by identifying predictors of poor cognitive performance amongst a comprehensive battery of imaging, blood, atmospheric pollutant and socio-economic measures. MethodsRandom forest modelling was used to determine significant predictors of poor cognitive performance in a cohort of 324 individuals (age 61.6 {+/-} 4.8 years; 150 males, 174 females) without extant neurological disease. 457 features were assessed including brain imaging measures of volume and iron deposition, blood measures of anaemia, inflammation, and heavy metal levels, social deprivation indicators and atmospheric pollution exposure. ResultsRoutinely assessed markers of anaemia including mean corpuscular haemoglobin concentration were identified as robust predictors of poor general cognition, where both extremes (low and high) were associated with poor cognitive performance. The strongest, most consistent predictors of poor cognitive performance were environmental measures of atmospheric pollution, in particular, lead, carbon monoxide, and particulate matter. Feature analysis demonstrated a significant negative relationship between low mean corpuscular haemoglobin concentration and high levels of atmospheric pollutants highlighting the potential of routinely assessed blood tests as a predictive measure of pollution-dependent cognitive functioning, at an individual level. ConclusionsTaken together, these data demonstrate how routine, inexpensive medical testing and local authority initiatives could help to identify and protect at-risk individuals. These findings highlight the potential to identify individuals for targeted, cost effective medical and social interventions to improve population cognitive health. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=66 SRC="FIGDIR/small/632396v1_ufig1.gif" ALT="Figure 1"> View larger version (34K): org.highwire.dtl.DTLVardef@1cda09org.highwire.dtl.DTLVardef@2e9243org.highwire.dtl.DTLVardef@1849bfcorg.highwire.dtl.DTLVardef@11cf9aa_HPS_FORMAT_FIGEXP M_FIG C_FIG

Source connections

Explore related subjects

neurosciencePreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Johnson, H., Longden, J., Cameron, G., Waiter, G. D., Waldron, F. M., Gregory, J. M., Spence, H.. 2025-01-13. Machine learning identifies routine blood tests as accurate predictive measures of pollution-dependent poor cognitive function. https://doi.org/10.1101/2025.01.10.632396

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↗