Frontiers in Neuroinformatics

Dynamic positron emission tomography (PET) with long axial field-of-view (LAFOV) scanners enables multi-organ imaging and kinetic quantification beyond static (late-phase) imaging; however, the long times typically required for dynamic acquisitions remain clinically impractical. This study evaluates a deep learning (DL) framework to enable abbreviated dynamic PET acquisitions, comparing single-time-window (STW, early dynamic data only) and dual-time-window (DTW, early dynamic data plus a late 5-min static frame) protocols with early dynamic scan durations of 5-30 min and dose levels ranging from 360 MBq to 18 MBq. Seventeen 60-min dynamic [18F]FDG datasets were first motion-corrected using a staggered FALCON pipeline and then used to train and test a spatiotemporal DL model for autoregressive frame prediction. Performance was assessed across the full quantitative workflow, from DL-predicted frames and time-activity curves to organ-based kinetic modeling and voxel-wise parametric imaging in multiple tissues and two patient cohorts. DTW protocols consistently outperformed STW, better preserving late-phase kinetics. For a 15-min early dynamic scan, adding a late 5-min scan reduced mean absolute Ki difference from 23% (STW) to 17% (DTW) in the liver and from 26% to 15% in the thalamus. DTW + DL further reduced errors to [≤]10% in the liver, thalamus, and breast lesion, and 16% in muscle. Our recommended protocol, 15-min early dynamic scan plus a 5-min late scan with DL, remained robust to up to a 5-fold dose reduction (~74 MBq). Overall, these findings support DL-enabled abbreviated, low-dose dynamic LAFOV PET as a clinically feasible approach for accurate kinetic quantification

Automated lesion segmentation is increasingly central to PSMA PET/CT interpretation, supporting staging, treatment planning, and response assessment at a scale that outpaces available nuclear-medicine expertise. However, automated PSMA-PET/CT whole-body lesion segmentation models are trained on images alone, with no knowledge of where in the body prostate metastases actually tend to occur. Radiologists use clinical domain knowledge of metastatic spread, but its absence in machine learning models produces false positives in anatomically implausible locations and missed lesions in high-risk sites such as the liver. In this work, we explore whether population-level spatial knowledge of metastatic spread can be used to augment deep learning segmentation predictions, and how such a prior should be fused with a network's output, without additional training. We build a data-driven metastasis atlas from 375 expert-annotated whole-body PSMA PET/CT scans and investigate its fusion with a trained segmentation network under a Bayesian framework, in which prediction probabilities from an nnU-Net-based lesion segmentation model serve as the likelihood and the data-driven atlas as the prior. Because metastases occupy only a small fraction of whole-body voxels, the atlas's peak probability is too low, and standard power-scaled or naive Bayesian pooling references lack the tools to deal with this shortcoming. This causes these standard fusion strategies to fail and, in the naive Bayesian case, to sharply degrade performance. We instead derive a calibrated, background-referenced log-odds fusion, one of many possible approaches to combine a population atlas with a deep learning model's predictions, distinct from classical multi-atlas label fusion in that it fuses a single population prior with a trained network's softmax rather than combining several registered atlases. Furthermore, this approach is neutral outside atlas support by construction, reduces exactly to the baseline network when unweighted, and requires no retraining. This atlas fusion significantly improved mean Dice over the baseline nnU-Net on a disjoint internal test set ($+0.011$, Holm-adjusted $p=0.021$) and on an independent external cohort ($+0.0129$, Holm-adjusted $p=3.8\times10^{-16}$), with lesion sensitivity improving from 0.849 to 0.861 internally and Dice improving over baseline in every stratified anatomic region, including the rare, high-risk sites motivating this work, while naive Bayesian pooling degrades performance sharply and power-scaled pooling underperforms it throughout. Our findings suggest that population-level spatial priors can meaningfully augment deep learning predictions in whole-body oncologic segmentation, provided the fusion rule is calibrated to where the prior actually carries signal.

Conventional sleep electroencephalography (EEG) measures often rely on predefined bands, thresholds, and averages that incompletely capture transient oscillatory dynamics across an entire night. Here, we introduce the Dynamic Oscillation (DYNAM-O) Toolbox, an open-source, cross-platform (MATLAB, Python, and Rust) software package for data-driven characterization of individualized neural dynamics in sleep EEG. DYNAM-O identifies transient oscillations as time-frequency peaks on multitaper spectrograms using a novel multi-resolution procedure, computes intrinsic and sleep-state-dependent extrinsic features for each event, and represents the overnight distributions of tens of thousands of TF-peaks as feature histograms spanning oscillation frequency, slow oscillation power, and slow oscillation phase. This distributional representation preserves continuous brain-state variation that could be obscured by averaging within conventional sleep stages. The toolbox further provides Gaussian and spline basis-based dimensionality reduction, visualization, and whole-histogram statistical testing tools to support both exploratory and hypothesis-driven analyses. To demonstrate its use for group-level inference, we analyzed overnight C3-channel EEG from 133 adults (71 females, 72 males; ages 20-35 years) in the Cleveland Family Study. Whole-histogram and parameterized-mode analyses reproduced the established higher center frequency of fast-spindle activity in females and additionally revealed greater low-alpha transient oscillatory activity in females, a pattern outside the conventional sleep spindle range. By completing the analysis cycle from TF-peak extraction to statistical inference, DYNAM-O provides an accessible and interpretable framework for studying individualized sleep physiology and identifying subtle, reproducible electrophysiological patterns.

Genome-wide coexpression analysis of intact tissue samples is a powerful approach for identifying reproducible signatures of cell types and states, since it can survey vast numbers of individuals, cells, and transcripts. However, it can be difficult to optimize gene coexpression network construction and compare results from independent analyses. To address these challenges, we developed OMICON (theomicon.ucsf.edu) for research on human brain gene coexpression networks. OMICON contains gene expression data from >17K normal and neoplastic human brain samples with standardized metadata. Systematic analysis of independent datasets identified >250K gene coexpression modules, which were characterized and compared via enrichment analysis with >40K gene sets. All modules are discoverable via an advanced search engine that can filter by genes, metadata, and enrichment results. Analyses can also be browsed with an interactive workflow visualization tool, and users can communicate within OMICON using @mention functionality to support communal research on human brain gene coexpression networks.

Background. Accurate delineation of the gross tumour volume (GTV) - primary tumour (GTVp) and nodal disease (GTVn) - on FDG-PET/CT is a critical step of head and neck radiotherapy planning. Comparisons between lightweight custom networks and the auto-configured nnU-Net v2 are usually reported as end-to-end pipelines, conflating the contribution of the network with that of the inference-time post-processing applied on top of it. We separated the two. Methods. MiniUNet3D (custom 3D U-Net, 18.3 M parameters) and nnU-Net v2 (3d_fullres, 88.2 M parameters) were trained on the same 578 FDG-PET/CT cases (85/15 author-defined split of the HECKTOR 2025 Task 1 set, 8 centres) and evaluated on the same internal cohort. Three arms were compared pairwise: MiniUNet3D raw output at a fixed 0.5 threshold, MiniUNet3D with a locked adaptive post-processing pipeline, and nnU-Net v2. Comparisons used paired Wilcoxon tests with bootstrap confidence intervals, Bonferroni and Benjamini-Hochberg correction, and Cohen's d; catastrophic failure (Dice < 0.01) was compared with an exact McNemar test. Cases with an empty reference for a given target were excluded from that target's analysis (n = 98 GTVp, n = 93 GTVn). Results. With post-processing matched off, nnU-Net v2 was superior: median GTVp Dice 0.799 versus 0.592 (mean difference -0.244, 95 % CI -0.300 to -0.191; d = -0.88) and GTVn 0.774 versus 0.598 (d = -0.82). Post-processing raised MiniUNet3D to 0.800 (GTVp) and 0.738 (GTVn), recovering 79 % of that difference. Post-processed, MiniUNet3D matched nnU-Net v2 on GTVp Dice (p = 0.113) but remained inferior on nodal disease after Bonferroni correction (Dice p = 0.041; surface Dice p = 0.049). Catastrophic GTVp failures were 25/98 raw, 8/98 post-processed and 1/98 for nnU-Net v2 (McNemar p = 0.016). Inference took 34 s versus 78 s per case on the same GPU. Conclusions. Post-processing recovered most, but not all, of the difference between the two models, and it did not confer robustness: an eight-fold higher rate of empty contours on small primaries persisted, which is the more consequential difference for planning safety. Pipeline comparisons reported without a post-processing ablation risk attributing to a network what post-processing supplied.

Three-dimensional (3D) mural cell morphology is heterogeneous and coupled to vessel geometry, however, measurements from two-dimensional (2D) maximum intensity projections (MIP) obscure overlapping processes and cell-vessel contacts. Accordingly, we developed Mural-VISTA, a semi-automated Python workflow for mural cell-vessel interaction and single-cell topo-morphology analysis of reconstructed surface meshes. This workflow integrates mesh pretreatment, interactive centerline extraction, hierarchical segmentation of cell soma, main axis and secondary processes (branches), and extraction of 36 multiscale (cell process segment level, process level, and whole cell level) topo-morphological and vessel-referenced metrics. Mural-VISTA identified morphological changes in pericytes and vascular smooth muscle cells (vSMCs) with altered RhoA activity. Constitutive active RhoA (RhoA CA) over-expression reduced branch complexity and increased process alignment in both cell types, while increased whole-cell and branch solidity only in vSMCs. Dominant negative RhoA (RhoA DN) over-expression increased branch abundance and reduced branch solidity in pericytes but not vSMCs, suggesting cell-type specific effect of reduced RhoA activity. In conclusion, Mural-VISTA enables quantitative 3D profiling of mural cell architecture and its spatial relationship with the vessel.

Objective: Published P300-speller fusion schemes fix prior trust regardless of trial reliability; we tested whether a reliability estimate improves on it. Methods: We reanalyzed 3,373 archived P300-speller selections from 47 people with ALS (BigP3BCI). A fair, matched-search-space comparison, tuning both a fixed weight and an adaptive policy out-of-fold, was evaluated across 22 evaluable language-model priors up to 46.7B parameters. Two representative priors, GPT-2 and a classical 5-gram, additionally received detailed naive and mechanistic analyses. Results: No prior's 95% CI favored adaptive fusion under the fair comparison, despite unexploited oracle headroom at every scale. Under GPT-2, the naive comparison was significantly worse for adaptive fusion; both anchors converged to a degenerate or near-degenerate fair-comparison solution. For the representative anchors, three further controllers failed to convert that headroom into benefit; the fixed-fused posterior's output probability outperformed the best controller for flagging errors (2.8- to 3.8-fold enrichment). Conclusion: A tuned fixed weight is a difficult-to-beat default across the tested scale range; reliability estimation gave no deployable adaptive advantage. Significance: Adaptive weighting should be validated against a fairly tuned baseline across model families and scales; in this dataset, the fused output's confidence identified high-risk selections better than the tested purpose-built ranker.

Background: Hippocampal sclerosis (HS) is a common cause of drug-resistant focal epilepsy (DRFE) and amenable to neurosurgical treatment. Detection relies on MRI but can be challenging. 7 Tesla (T) ultra-high field MRI and automated MRI post-processing tools have independently been shown to improve radiological diagnosis of HS. However, combining these approaches remains underexplored. This study evaluated whether AID-HS, a tool for HS detection developed using 3T MRI, generalises to 7T MRI data. Methods: We collated a dataset of paired 3T and 7T T1-weighted MRI from four epilepsy centres, including 23 patients with HS, 39 healthy controls, and 23 individuals with focal cortical dysplasia as disease controls. Histopathology served as the gold standard for defining HS where available (n=7), otherwise radiological findings (n=16). AID-HS was applied to images acquired at both field strengths, and sensitivity and specificity for detection and lateralisation of HS were compared. Additionally, agreement of hippocampal features across 3T and 7T was evaluated. Results: We found no evidence of a difference in performance of AID-HS between 3T and 7T. Sensitivity for detection of unilateral HS was 63% (12/19) at 3T and 68% (13/19) at 7T (McNemar's exact test p=1.0). Specificity in controls was 97% (60/62) at 3T and 100% (62/62) at 7T (p=0.5). Bilateral HS was correctly flagged in 3 of 4 cases using feature-based criteria, with high specificity in controls. Quantitative hippocampal features showed moderate to good agreement across field strengths (ICC 0.70 to 0.98), with small differences observed for volume and thickness estimates. Conclusion: AID-HS provides robust detection and lateralisation of HS across multiple 7T MRI centres, highlighting its potential to enhance lesion detection. Future work is needed to investigate whether models trained on 7T data can leverage the improved image quality for further gains in HS detection performance.

Diffusion models achieve high reconstruction quality in low-dose computed tomography (LDCT), but their iterative sampling trajectories impose substantial computational costs. Unlike unconditional generation, paired LDCT reconstruction starts from an image that already contains the anatomy and spatial structure of the standard-dose CT (SDCT) target; reconstruction primarily requires correcting dose-related noise and artifacts. We therefore introduce Residual Endpoint Flow Matching (REFM), an LDCT reconstruction method that learns to transport an LDCT image directly toward its paired SDCT endpoint rather than defining a noise-to-image trajectory. REFM predicts the residual velocity along linear interpolations between both images and supports single-step and multi-step reconstruction using the same trained network. We evaluate five model capacities using 1 to 50 Euler steps against deterministic U-Net and diffusion-based baselines. Across all REFM variants, one-step inference consistently provides the highest reconstruction quality. On the TCIA validation set, REFM Base achieves 50.98 dB PSNR and 0.9865 SSIM at 94.54 fps, compared with 50.92 dB, 0.9847, and 9.26 fps for DDPM-10. REFM Small retains 50.71 dB while increasing throughput to 198.56 fps. Without fine-tuning, REFM Base also matches the 25-step DDPM baseline on the external Mayo Clinic dataset, although DDPM remains stronger on synthetically degraded CRLM images. Thus, our results show that exploiting paired anatomical correspondence enables diffusion-level LDCT reconstruction with a single step reconstruction.

A new electrical stimulation focused computational model of the visual cortex had been created to aid in the development of cortical visual prosthesis. The model consists of 10,666 biophysical neurons representing 0.13mm3 of a layer 2/3 of the primary visual cortex and was calibrated to match the baseline activity of rat brain recordings. A novel model of electrical stimulation was developed to allow for selective activation of specific neuron types, and matched the single cell stimulation response generated by known stimulation models. The electrode was tuned to match recorded population level change in activity across distances and currents recorded in the rats brain. The model is now ready to explore electrical stimulation effects on the visual cortex for examination of neuron specific stimulation to assist in the development of cortical visual prosthesis.

Stroke remains a leading cause of mortality and long-term disability worldwide, yet rapid diagnosis is often limited by the shortage of trained radiologists, particularly in resource-constrained settings. Automated analysis of CT imaging offers a potential solution, but existing methods often struggle to achieve clinically generalisable performance while jointly addressing multiple diagnostic tasks. Here we present the Intelligent Integrated Stroke Diagnosis System IISDS, an end-to-end deep learning framework built upon StrokeGNN, a graph-based architecture that integrates 3D contextual feature extraction with U-Net-based 2D lesion segmentation to enable comprehensive stroke analysis from non-contrast CT scans. IISDS performs stroke subtype classification, lesion segmentation and lesion volume estimation within a unified pipeline. To develop and validate the system, we collected and curated BGD-ISD through a collaboration between AI researchers, neurologists, radiologists and clinicians, resulting in a large multi-centre dataset comprising 1,507 CT scans from 597 stroke cases acquired across six hospitals and medical centres in Bangladesh. Across BGD-ISD and multiple publicly available datasets, IISDS achieves state-of-the-art performance on all tasks, improving segmentation accuracy by [&ge;]0.011 Dice score, reducing lesion volume estimation error by [&ge;]0.3 average symmetric surface distance (ASSD), and increasing classification performance by [&ge;]0.018 area under the receiver operating characteristic curve (AUC) compared with existing approaches. These results demonstrate the potential of graph-based deep learning to enable clinically generalisable, automated and scalable stroke diagnosis from CT imaging, supporting rapid clinical decision-making, particularly in healthcare environments with limited access to expert radiological interpretation.

Background: Reproducible taxonomic collapsing and geological-timescale annotation of time-calibrated phylogenetic trees in R often require coordination among several packages and repeated code for label parsing, clade validation, plotting, and export. Workflow-managed analyses additionally benefit from non-interactive configuration, predictable diagnostics, and machine-readable exit status. Results: We present Rclade, an R package that consolidates the multi-package coordination required for taxonomic collapsing into a streamlined, single-function interface. Rclade provides (1) custom ggproto objects (GeomPolygonStraight/GeomSegmentStraight) that bypass coord_munch() interpolation to achieve straight-edge rendering of collapsed triangles in circular layouts; (2) automatic detection and parsing of four taxonomic-label formats (GTDB, Silva, NCBI, embedded) plus user-supplied custom regex, with explicit input-validation contracts and parsing-accuracy evaluation on real and derived test sets; and (3) workflow embeddability through YAML configuration, library-mode APIs, and standard Unix exit codes. Benchmarks on synthetic and real datasets (200-10,000 synthetic tips and real reference trees up to 10,122 tips; 5 replicates at every scale under a unified fully rendered measurement protocol) show that the full-pipeline overhead is modest for interactive use (median {approx}0.87 s in-session rendering and {approx}8.4 s process-level wall-clock at 10,000 tips). Conclusions: Rclade is a convenience layer over the ggtree/deeptime ecosystem that reduces boilerplate while adding targeted technical improvements for circular-layout rendering and format heterogeneity management.

Purpose: The primary objective of the Stanford Knee Osteoarthritis PET/MRI Evaluation (SKOPE) study is to develop and evaluate a multimodal, dynamic [18F]NaF PET-MRI framework for characterizing whole-joint physiology and its relationship to osteoarthritis (OA) risk, pain, and disease progression. Specifically, we aim to integrate dynamic PET with quantitative and anatomical MRI, to characterize structural, compositional, and metabolic features across the knee and surrounding musculoskeletal system, evaluate acute tissue responses to exercise, and identify imaging biomarkers associated with OA risk, pain, and disease progression. Methods: The SKOPE study includes multimodal PET-MRI of the knee and surrounding musculoskeletal tissues, with imaging of the knee, tibia, ankle, thigh, hip, pelvis, and lumbosacral spine. Dynamic [18F]NaF PET is combined with conventional anatomical MRI and quantitative MRI techniques, including quantitative double-echo steady-state (qDESS) T2 mapping of cartilage, Dixon fat-fraction imaging, ultrashort echo time (UTE) T2* mapping of short-T2 tissues, UTE imaging of tibial bone, and zero echo time (ZTE) imaging for bone morphology and pseudo-CT generation. Additional MRI sequences characterize muscle composition, bone and joint anatomy, intervertebral discs, and regional vascular anatomy. Selected scans are acquired before and after a standardized exercise protocol to assess the acute physiological response of the joint. Automated segmentation is used to generate subject-specific masks of muscles, bones, vertebrae, and intervertebral discs. A subset of the MRI protocol is repeated at 1- and 2-year follow-up to assess longitudinal changes. Expected Impact: By combining dynamic bone metabolic imaging with quantitative measures of cartilage, menisci, muscle, bone, fat, vascular structures, and the spine and hip, the SKOPE protocol provides a whole-joint and multijoint framework for studying the structural, metabolic, and physiological processes associated with OA and pain. Exercise and longitudinal imaging further enable assessment of acute tissue responses and changes over time, supporting the development of quantitative imaging biomarkers for OA risk, pain, and disease progression.

We describe LRSPAT (low-rank spatial toolkit), a fast and memory-efficient framework for approximating measures of spatial association for high-dimensional data. While LRSPAT can be applied to any multivariate spatial dataset, development was motivated by the computational challenge of identifying spatially variable genes in high-resolution spatial transcriptomics (ST) data generated by technologies such as 10x Visium HD, Xenium and Atera. LRSPAT leverages a truncated SVD of the expression data and a thresholded spatial weights matrix to perform reduced-rank reconstruction of spatial statistics in the quadratic form family, including global and local versions of Moran's I, Geary's C, and Getis-Ord G. A regularization approach is leveraged to account for the inflated null distribution of spatial statistics computed on latent variables. By performing key operations on the low-dimensional embeddings, LRSPAT is orders of magnitude faster than standard implementations with significantly lower memory requirements. Because the low-rank approach denoises and desparsifies ST data, LRSPAT is also more accurate than standard techniques at identifying genes with true spatial expression patterns. The dramatic improvements in execution time and memory consumption enable the genome-wide analysis of spatially variable genes (SVGs) and exploration of the full range of hyperparameters including spatial scale, distance metric, and embedding rank. This preprint outlines the background and mathematical details of the approach with limited preliminary results and a short conclusion.

Objectives To validate two computational fluid dynamics (CFD) models derived from computed tomography angiography (CTA) for estimating trans-stenotic pressure gradients, using invasive intra-arterial pressure measurements as the reference standard in patients with renal artery stenosis (RAS). Background We assessed whether non-invasive assessment of the pressure gradient using CFD could be a reliable alternative to intra-arterial measurements for identifying hemodynamically significant RAS. Methods We performed intra-arterial measurements at rest and during dopamine-induced hyperemia to assess the trans-stenotic pressure gradient in 28 patients with RAS. A pre-intervention CTA scan was used to simulate the pressure gradient with a CFD model using a strategy based on Murray's law (CFD-Mu) and cortical volume (CFD-C). The agreement between the simulated and measured pressure gradients was assessed using intraclass correlation coefficients (ICC), Bland-Altman analysis and diagnostic agreement on the presence of a hemodynamically significant stenosis. Results In 20 patients, successful measurements and simulations were obtained. The ICC between measured pressure gradient and the CFD pressure gradient was 0.78 and 0.94 during baseline and 0.86 and 0.72 during hyperemia, for CFD-Mu and CFD-C, respectively. The sensitivity of CFD-Mu and CFD-C was 70% for both models at rest and 100% compared to the hyperemic measurements, whereas the specificity was 90% and 70% at rest and 79% and 72% during hyperemia, respectively. Conclusions The results support the use of individualized CFD simulations for hemodynamic assessment of RAS using CTA as input. The CFD models demonstrated high accuracy for the identification of a hemodynamically significant stenosis.

Background: The Centiloid (CL) scale standardizes global amyloid PET quantification and is widely used to define amyloid positivity. As a global summary measure, however, CL may not fully reflect the regional distribution of amyloid deposition, which can carry additional prognostic information about the rate of cognitive decline. Objective: To develop and externally validate a fixed, regional amyloid PET composite score that complements CL for predicting cognitive decline in Alzheimer's disease. Methods: The Regional Amyloid PET Score (RAPS) was derived from 82 FreeSurfer regions using machine learning with bootstrap stability selection to predict the rate of change in CDR-Sum of Boxes (CDR-SB) in 433 amyloid-positive ADNI [18F]florbetapir participants. The fixed nine-region weights were applied without retraining in a cross-tracer ADNI [18F]florbetaben subset (N = 71; largely overlapping the discovery participants) and two external validation cohorts, NACC SCAN (N = 1531; four tracers) and OASIS-3 (N = 428). Results: RAPS comprised nine regions. In ADNI, RAPS correlated more strongly with CDR-SB slope than CL and showed higher discrimination of rapid decliners (AUC 0.813 vs 0.713). Performance was directionally consistent across validation cohorts; in NACC SCAN, RAPS and CL independently predicted clinical progression. Cross-cohort meta-analysis of the three independent cohorts supported incremental discrimination beyond CL (pooled {Delta}AUC +0.066; I2 = 0%). Conclusions: RAPS, a fixed regional amyloid PET-derived score, may complement CL for prognostic stratification in Alzheimer's disease research.

Background Understanding the mechanisms underlying brain aging and age-related pathological changes is essential for advancing brain health research. Our group previously developed a mechanistic mathematical model of healthy brain, Chamberland et al. (2024) that integrates key biological processes involved in normal aging, from which Alzheimer's disease (AD) related changes may emerge naturally. Objectives To characterize and validate this brain model by evaluating its sensitivity, calibrating its parameters, and assessing generalizability in independent populations. Methods The model represents the evolution of key biological processes associated with brain aging, including amyloid beta (A{beta}), tau pathologies, neuroinflammation, and neuronal death. After identifying the 30 most influential parameters, we calibrated the model using cognitively normal (CN) participants from the AD Neuroimaging Initiative (ADNI) database (n = 211) by minimizing a loss function composed of three outcomes (AB) plaques, tau tangles, and neuronal density). The calibrated model was then applied to the UK Biobank cohort (n = 35,899) of normal controls (aged 44-82 years). The effects of sex and APOE were evaluated using stratified simulations. Results Parameter calibration significantly reduced the prediction errors for A{beta} and tau. Neuronal density predictions showed strong agreement in the UK Biobank cohort. The variance decomposition identified APOE status as a major contributor to variability in A{beta}. Conclusion Our validated brain health model links mechanistic pathways with population data and reproduces neuronal density patterns in an independent cohort. These findings support its use as a framework for studying brain aging and investigating how Alzheimer's disease related pathological changes may emerge with aging.

Molecular staging of Alzheimer's disease (AD) increasingly defines transition boundaries along single-cell pseudo-progression trajectories, yet whether such boundaries reproduce across brain regions, cohorts and molecular modalities is rarely tested. We present a permutation-controlled audit that combines nine boundary-detection algorithms with a fixed marker panel and four orthogonal reproducibility axes-algorithmic consensus, region, cohort and modality. On synthetic data with planted ground-truth boundaries the audit reaches 100% sensitivity and 94% specificity, rejecting four distinct artefact classes each by a different axis. Applied to the Seattle Alzheimer's Disease Brain Cell Atlas middle temporal gyrus, it localizes a transition that is robust across algorithms and recovered in most cell types but does not generalize: its leading marker is attenuated or absent in prefrontal cortex, entorhinal cortex and cerebrospinal fluid, and an apparent cross-region conservation of glial metabolic genes proves to be a global-expression offset rather than a shared program. The same audit nonetheless certifies an externally validated marker (astrocytic PTGDS) as reproducible across regions and modalities, showing that it separates generalizable anchors from dataset-specific ones rather than rejecting all signals. We provide this four-axis audit as a transferable, code-available standard to apply before a trajectory boundary is read as a biological stage, in AD and other progressive proteinopathies.

Background: A dose finding trial evaluated safety and adherence for pre-cardiac surgery administration of sodium valproate. Integrated multi-omics analyses of myocardium were used to characterise mechanisms underlying the treatment effects. Methods: Adults undergoing cardiac surgery were randomised 1:1:1:1 with concealed allocation to no treatment (Controls), sodium valproate 15mg/kg/day for 1-2 weeks, 15mg/kg/day for 4-6 weeks, or 25mg/kg/day for 4-6 weeks pre-surgery. The primary analysis evaluated adherence and toxicity. Myocardial injury was defined by high sensitivity serum troponin at 24 hours post-surgery. Single-nucleus Assay for Transposase-Accessible Chromatin with sequencing (snATACseq) and single nuclei RNA sequencing (snRNAseq) of myocardial biopsies collected at surgery assessed treatment effects on chromatin accessibility and gene expression. Candidate mechanisms were validated in in vitro. Results: The analysis cohort included 42 participants enrolled between January 2020 and August 2024. Non-compliance (38%) was highest with longer and higher dosing. Sodium valproate 15mg/kg/day for 1-2 weeks had the highest levels of complete treatment adherence (70%), with 20% experiencing moderate/severe drug related adverse effects. An as-treated analyses demonstrated reductions in troponin release in participants receiving Valproate[&le;]14 days. Myocardial biopsies from trial participants demonstrated activation of hormetic p53 and Akt-GSK-3{beta} ferroptosis protection pathways. Treatment effects were not attributable to chromatin accessibility. Treatment >14 days resulted in a heart failure phenotype with suppression of ferroptosis protection pathways, endothelial mesenchymal transition, and increased myocardial injury. Conclusions: Sodium valproate 15mg/kg/day for [&le;]14 days pre-surgery is well tolerated in adults awaiting cardiac surgery. This treatment was associated with upregulation of ferroptosis protection pathways and reductions in myocardial injury.

Background: Consumer use of AI chatbots for health advice is rising, yet triage safety relative to established services remains unclear. Australia's Healthdirect, a government-backed symptom checker with 2.4 million uses in FY2024-25, remains unevaluated against frontier large language models (LLMs), and whether premium subscriptions improve triage safety remains unexplored. This study compared the triage accuracy and safety of Healthdirect against six LLM configurations across ChatGPT, Claude, and Gemini, assessed whether paid subscriptions improve triage safety, and characterised each system's error patterns. Methods: Forty-five clinical vignettes from the Semigran et al. benchmark spanning emergency, non-emergent, and self-care categories (15 each) were evaluated across seven systems. Healthdirect was tested following a seven-rule interaction protocol. LLMs were evaluated using first-person patient-language prompts under free-tier and paid-tier conditions. Outcomes were triage accuracy, emergency sensitivity, under-triage, and critical misses, analysed using Cochran's Q, Bonferroni-corrected McNemar tests, Cohen's kappa, and Wilson intervals. Findings: Triage accuracy differed significantly (Cochran's Q = 36.79, p < 0.001). Healthdirect achieved 48.9% accuracy (95% CI 35.0% to 63.0%; kappa = 0.233) versus 73.3% to 86.7% for LLMs (kappa = 0.600 to 0.800). Healthdirect operated under conservative interactive defaults while LLMs received complete information in a single prompt, which may have disadvantaged Healthdirect. Emergency sensitivity was 46.7% versus 80.0% to 86.7% for LLMs. Healthdirect produced two critical misses; no LLM produced any across 270 evaluations (95% CI 0% to 1.4%). When LLMs undertriaged, they recommended GP care rather than self-care. No tier differences were significant (all p > 0.05), and most systems over-triaged self-care cases. Interpretation: Frontier LLMs demonstrated higher triage accuracy and safer error profiles than Healthdirect. All LLMs avoided critical misses; Healthdirect did not. Premium subscriptions did not significantly improve triage safety. These findings support clinical governance decisions about whether LLMs warrant formal evaluation alongside government-backed symptom checkers.