Nature Computational Science

Biobank-scale genomic analyses remain computationally expensive, CPU-bound workflows, particularly when adjusting for confounding. Here, we present CuGen, a GPU-accelerated framework for large-scale genomics. CuGen uses UltraLasso, a novel hierarchical application of univariate-guided sparse regression (uniLasso), to select a compact, phenotype-informed active set of fewer than 30,000 variants. This achieves robust leave-one-chromosome-out (LOCO) confounding control, enabling both downstream GWAS and in-sample fine-mapping. Additionally, we introduce the .cugen file format, a genotype representation designed for memory-optimized, high-throughput streaming and random access on GPU hardware. Building on this substrate, we provide a general GPU-accelerated genomics toolkit handling polygenic prediction, data manipulation, quality control, analysis, and visualization. We demonstrate CuGen's efficacy in the UK Biobank with up to 408,624 individuals, where the full GWAS pipeline and fine-mapping against 6.8 million imputed variants completes in approximately 10 minutes on a single high-throughput GPU with 80 GB of memory. The pipeline scales efficiently to massive phenome-wide analyses with sublinear resource consumption.

Rising costs, slow accrual and molecular substratification of cancers necessitate novel clinical trial designs. We demonstrate that artificial intelligence-generated synthetic patients can replace real controls to reproduce results of the SORAML trial. Using external multimodal data from 1,377 acute myeloid leukemia (AML) patients from previous trials and a real-world registry, we fine-tuned a tabular foundation model to generate synthetic patients, reproducing clinical and genetic features and outcome associations. Synthetic patients were then matched to the original SORAML intervention group using Cox risk scores, replacing the original control and reproducing the original trial result with near-identical median event-free survival (EFS) and treatment effect (original hazard ratio [HR] 0.64, 95%-confidence interval [CI] 0.47-0.87, p=0.004; with synthetic control HR 0.66, 95%-CI 0.48-0.90, p=0.009). Our findings demonstrate that AI-generated synthetic patients can serve as statistically rigorous controls supporting novel trial designs.

The Cancer Genome Atlas (TCGA) holds clinical data for over 11,000 patients across 33 cancer types, but access is hard because of complex file structures, heterogeneous formats, and the need for programming. We present an agentic system for natural language querying and statistical analysis of TCGA clinical data. The system uses a large language model as an autonomous ReAct agent that selects from eight computational tools, including data extraction, descriptive statistics, Kaplan-Meier survival analysis with log-rank tests, hypothesis testing, and verification against the curated TCGA Pan-Cancer Clinical Data Resource (CDR). The agent reasons about intermediate results, adapts its approach, and returns clinically contextualized responses with source attribution and auditable traces. We introduce TCGA-Agent-Bench, 440 queries across five difficulty tiers with ground truth from the independently curated TCGA-CDR, evaluated with dual metrics of numerical accuracy and clinical completeness. The system achieves 93.4% overall accuracy (100% single-patient lookups, 99.1% cohort statistics, 92.8% comparative analyses), outperforming a fixed rule-based pipeline (87.1%), a single-pass LLM (81.8%), and retrieval-augmented generation (66.9% on a subset). Most of the benchmark is answerable from the CDR alone, so we locate the extraction layer's value in fields the CDR lacks (drug treatments, TNM components, biomarkers, biospecimen metadata): on 26 queries targeting these, the full system answers 100% versus 3.8% for CDR-only. Ablations show the reasoning loop is most impactful (+9.1% accuracy, +22.0 completeness points). A tool-based agentic architecture enables accurate, auditable analysis of clinical repositories, with value driven by tool design and recovered fields rather than model scale.

Causal effect estimates can often be biased in clinical and epidemiological studies as patient cohorts frequently exhibit substantial covariate imbalances between treated and control groups, often amplified in multicentre studies due to heterogeneous recruitment, clinical practice, and case mix. Covariate balancing methods are therefore essential for valid causal inference. However, their application becomes challenging when data are distributed across cohorts and cannot be pooled because of privacy, legal, or institutional constraints, leaving a gap in practical methods for causal effect estimation in federated and imbalanced clinical data settings. We develop a privacy-preserving framework for covariate balancing and causal effect estimation across distributed data providers, combining federated aggregation with differential privacy to enable propensity score subclassification and matching without sharing individual-level records. Matching relies on non-disclosive quantities and differentially private distance evaluation, and the resulting matched subsets remain local to each server. Balance can be assessed through federated diagnostics and privacy-preserving visualisations, and we provide secure estimators for average treatment effects with associated uncertainty quantification. We implement this framework in the DataSHIELD federated analysis platform via 2 R packages. In simulations, we demonstrate agreement between federated and centralised analyses in the absence of privacy noise and quantify the bias--variance trade-offs induced by differential privacy. We illustrate applicability in two multinational settings-a Long COVID cohort and very preterm birth cohorts-showing that the approach enables practical causal analyses under real-world data protection constraints. The DataSHIELD packages are available on Github. Additional methodological details are provided in the Supplementary Material.

Automated interpretation of neuroimaging studies requires simultaneous assessment of multiple imaging evidence variables, each tied to distinct anatomical structures. Vision-language models (VLMs) offer a unified framework for multi-task analysis, but adapting pre-trained VLMs remains challenging. Full fine-tuning is computationally prohibitive, and joint multi-task training requires simultaneous access to all task data, which is often infeasible in clinical settings. Although model merging enables multi-task composition without joint re-training, existing methods focus on post-hoc algorithms with limited extension to VLMs and minimal application to neuroimaging. Here, we present GRadient-guided Adapter Merging (GRAM), a layer-selective low-rank adaptation (LoRA)-based fine-tuning and merging framework for multi-task neuroimaging visual question-answering (VQA). GRAM uses a gradient ratio that contrasts class-specific gradients to identify task-discriminative layers, and applies subspace-constrained projected gradient descent to restrict LoRA updates to directions consistent with the geometry of the pre-trained model. We leveraged a structured VQA benchmark, developed from the National Alzheimer's Coordinating Center (NACC) dataset, that pairs multi-sequence brain MRI studies with question-answer pairs across clinically relevant imaging evidence variables. Experiments on the VQA benchmark showed that GRAM outperformed or matched all-layer LoRA fine-tuning and a standard merging baseline while reducing inter-task interference during merging, and approached or surpassed the performance of joint multi-task training without joint re-training.

Objectives. Radiomics pipelines extract hundreds of quantitative features that are widely known to be redundant, but the structure of this redundancy is usually treated as a per-dataset nuisance to be pruned away. We tested the alternative hypothesis that a substantial number of feature-feature correlations are universal: they persist across patients and across anatomically distinct structures because they reflect shared mathematical and image-statistical properties of how the image is summarised, rather than properties of the tissue being imaged. Materials and Methods. We re-analysed the publicly available Radiomics Atlas Dataset of normal Abdominal and Pelvic CT (RADAPT), restricting the analysis to the 526 non-contrast-enhanced examinations of the 531-subject atlas and to the 107 original (non-filtered) PyRadiomics features. The 53 segmented structures were grouped into four broad anatomical categories -- bones, muscles, vessels, and parenchymal organs. RADAPT is distributed as one Excel file per structure, with patients as rows and features as columns. Within each structure file we z-score-normalised every feature across patients, computed the absolute Spearman correlation matrix, and retained edges with |{rho}| [≥] {tau} for {tau} in {0.70, 0.80, 0.90}. We then intersected the edge sets across all structure files to obtain a "universal" correlation graph, in which an edge survives only if it exceeds the threshold in every structure (each estimated across the full patient sample). Stable feature communities were defined as the maximal cliques of this graph. Robustness to patient sampling was tested by repeating the entire pipeline on five independent random splits of each file into two patient halves (10 sub-cohorts per threshold), and the implementation was independently reproduced in R. Results. Despite the strictness of the global-intersection criterion, 34, 24, and 14 stable feature communities survived at {tau} = 0.70, 0.80, and 0.90 respectively, with the largest cliques containing six members at {tau} = 0.70 and {tau} = 0.80 and five members at {tau} = 0.90. The community structure was clearly interpretable: separate cliques captured (i) variance-like intensity dispersion, (ii) long-run / low-frequency (coarse) texture, (iii) high gray-level texture, (iv) low gray-level texture, (v) volume and surface shape, and (vi) local-homogeneity and energy/entropy duals. On random-half resampling the exact-match recovery rate of these communities was 81.5 %, 86.7 %, and 80.7 % across the three thresholds; departures from exact recovery were almost always a single boundary feature added or dropped, consistent with finite-sample fluctuation of near-threshold edges rather than structural instability. The R re-implementation reproduced the Python results exactly. Conclusion. A substantial portion of radiomics feature collinearity is universal across patients and tissues. We distinguish two layers within it: trivial near-algebraic duals that are universal by construction, and non-trivial cross-matrix-family communities that are the genuine empirical finding. Together they provide an interpretable, definition-grounded basis for aggressive dimensionality reduction, for retrospectively reconciling apparently different feature selections in the literature, and for moving radiomics pipelines toward organ-agnostic, more reproducible models. Clinical relevance statement. Selecting a single representative feature from each universal community shrinks the original-feature space by roughly an order of magnitude without sacrificing biologically distinct information. For example, the five variance-family members (first-order Variance, GLCM SumSquares, GLCM ClusterTendency, GLDM and GLRLM GrayLevelVariance) can be replaced by a single representative, removing redundant degrees of freedom that would otherwise inflate model variance; and labelling each retained feature by its community lets two studies that selected different variance-family names be recognised as having found the same signal, simplifying model development and improving cross-cohort generalisability in clinical CT workflows.

The aim of this work is to validate patient-specific EEG baseline establishment using the e-norms method as a screening and retrospective-review tool for seizure detection in pediatric epilepsy. The method was applied to 247 seizure-free EEG recordings (263.92 hours) from 10 patients in the CHB-MIT Scalp EEG Database (ages 3-18). A composite stability metric combining first-derivative dynamics, spectral entropy, variance, and line length was computed per 2-second epoch across 23 channels. Patient-specific detection thresholds were derived from each patient's seizure-free baseline using a weighted statistical procedure. Performance was validated against 72 expert-annotated seizures (2,705 epochs) across 62 seizure files, with durations spanning 6 to 264 seconds (44-fold range). The results show that detection achieved 94.4% event-level sensitivity (68 of 72 seizures; 95% CI 86.6-97.8%) and 81.5% epoch-level sensitivity (2,204 of 2,705 epochs; 95% CI 80.0-82.9%). Eight of ten patients achieved 100% event-level sensitivity with epoch-level sensitivity ranging from 58.7% to 100.0%. Two patients showed partial event-level failures (CHB-15: 17 of 20; CHB-18: 5 of 6), with the four missed events attributable to two characterizable failure modes. Patient-specific thresholds ranged from 4.06 to 4.81 (mean 4.51 +/- 0.25); threshold variation did not correlate reliably with age or sex, confirming that no universal threshold could achieve comparable performance. Detection margins ranged from 0.88 to 1.24 times. Patient-specific e-norms achieves 94.4% event-level sensitivity for pediatric EEG seizure detection without requiring labeled seizure training data, exceeding published human expert inter-rater agreement (50-76%) and recent automated approaches in adult cohorts using behind-the-ear EEG and wearable ECG. Two characterizable failure modes account for the four missed events and inform appropriate clinical use. As a high-sensitivity screening tool complementary to real-time alarm systems, the method is ready for adult validation, prospective deployment, and head-to-head benchmarking.

Summary It has become standard practice to visualize regional signals from genomewide association studies GWAS using LocusZoom plots Similarly GWAS signals are compared to regionally matched quantitative trait loci QTLs ie varianttogene regulation data using LocusCompare plots to aid assessment of candidate traitrelated genes Despite broad usage these tools annotate variants by linkage disequilibrium LD to a single lead or index variant This singleindex representation has limitations for visualizing complex loci that contain multiple independent signals We present LocusBlend an interactive web application for multiindex LDblended visualization of genomic loci LocusBlend supports one or two genomic association summarystatistic datasets and one to three index variants multiindex LocusZoom colorblended plots and matching LocusCompare visualizations Applications to Alzheimers disease GWAS and QTL signals illustrate LocusBlend enables visualization and separation of independent signals despite shared LD and high genomic complexity Overall LocusBlend is aimed at supporting researchers handle the continuously expanding complexity of human genomics findings Availability and Implementation LocusBlend is freely available at httpslocusblendwustledu Publication ready plots are generated in 1min Source code documentation example datasets input templates and reproducibility instructions are available at httpsgithubcomBelloyLabLocusBlend LocusBlend is implemented in Python using Streamlit Plotly and PLINK Supplementary Information Supplementary data are available online

Background: Increased public access to data from disparate sources provides opportunities to study and validate predictive and subphenotype models in heterogeneous disease conditions using aggregated individual patient data. Robust, explicit, and transparent harmonization of data elements is critical to ensure interpretability, reproducibility, and generalizability of secondary and retrospective analyses. Methods & Results: We designed and implemented ADAPT (Aggregating Data to Accelerate Personalized Therapy), a scalable framework using multiple software packages (R, SQL, BigQuery) that enables rapid, explicit harmonization of structured data elements from randomized trials and observational studies using a standard spreadsheet interface. User-specified criteria are applied to primary study data to produce harmonized longitudinal datasets comprised of demographics, medical history, quantitative observations, repeated measures, and clinical outcomes. We demonstrate this functionality using 26 clinical studies found in the National Heart, Lung, and Blood Institute BioLINCC resource. We illustrate the scalability of ADAPT to the order of billions of datapoints using administrative clinical data in a cloud-computing platform. We also present examples of collaborators using ADAPT for independent harmonization tasks for secondary analyses and democratization of publicly available data. Conclusion: ADAPT is a disease-agnostic, extensible, and scalable platform to support robust, transparent harmonization of structured research data using interfaces accessible to a variety of researchers regardless of programming ability. It extends FAIR principles beyond research data to also represent harmonization analyses by improving Findability of harmonization decisions, Accessibility of methods to other stakeholders, Interoperability with independent analyses and datasets, and Reusability through efficient implementation in a variety of analysis environments.

Motor speech disorders (MSDs) are early markers of neurological disease, but expert perceptual analysis is rarely available outside specialized centers. Automated speech analysis offers a scalable alternative, yet prior studies have not systematically compared modeling approaches or assessed clinically relevant metrics in independent datasets. This study compared static acoustic features, articulatory informed Phonet features, and self-supervised pretrained models for binary and multi label MSD classification. We trained and evaluated models on 583 speech samples using speaker level splits. Baseline models included logistic regression and Gated Recurrent Units (GRUs) trained on eGeMAPS and MFCCs. We extracted three types of Phonet derived features and evaluated pretrained HuBERT and SSAST models in frozen, partially fine-tuned, and fully fine-tuned configurations. Binary classification distinguished MSDs from controls, while multi label classification identified six MSD subtypes. Models were assessed using validation AUC, and cut points were tested on two independent datasets. Pretrained and Phonet based models substantially outperformed static acoustic features. In binary classification, HuBERT achieved the highest AUC (0.95), while compact Phonet derived GRUs achieved comparable performance (up to 0.94). These models generalized well to independent datasets, maintaining high sensitivity (0.94) and specificity (0.97). In multi label classification, Phonet models achieved the highest macro average AUC (0.86), but threshold-based subtype performance declined on unseen data. Automated MSD detection is feasible and clinically promising. Binary classification generalized well, whereas multi label classification showed limited threshold stability across datasets.

Comprehensive biomarkers of multiple sclerosis (MS) capable of simultaneously diagnosing the condition, capturing symptom severity and predicting treatment efficacy remain elusive. Although several studies have highlighted the pivotal role played by demyelinating lesions in determining MS structural pathology, their relationship with symptom severity is limited. Here, we combined personalized computational brain modeling with magnetoencephalography (MEG) recordings from 17 MS patients and 20 healthy controls (CTR) to derive personalized brain network excitability parameters, which we tested as MS biomarkers. Personalized parameters discriminated between CTR and MS participants with high accuracy, also classifying between progressing and remitting MS patients. Notably, they also predicted MS clinical scales across multiple domains. In all clinical tasks, personalized parameters consistently outperformed standard clinical measures and total lesion loads. Together, these results highlight the potential of personalized brain modelling in deriving integrative MS biomarkers, capable of simultaneously identifying the condition, classifying MS subtypes and predicting symptom severity. d brain modelling in deriving integrative MS biomarkers, capable of simultaneously identifying the condition, classifying between MS subtypes and predicting the severity of symptomatology.

Background. Early diagnosis and intervention are crucial in multiple sclerosis (MS), yet diagnostic delays are common. Large language models (LLMs) such as generative pre-trained transformers (GPTs) may help streamline diagnostic workflows by extracting MS diagnostic signals from clinical notes. Objective. To derive MS diagnosis status from the first neurology note using a computable algorithm based on the 2017 McDonald criteria and applying GPT-4 for node-level reasoning within a structured decision framework. Methods. We analyzed first neurology notes from 125 randomly selected patients (including those with MS, related disorders, and controls) enrolled in a clinic cohort between 2017 and 2023. We included the clinical history and diagnostic testing sections but redacted the assessment and plan. We converted the 2017 McDonald criteria into a decision tree and provided expert-curated clinical knowledge to guide GPT-4 reasoning at each decision node. GPT-4 generated binary decisions at each node to traverse the tree and classified MS diagnoses at terminal nodes. We evaluated performance against neurologist-assessed diagnoses and characterized hallucinations (non-factual, incongruent, irrelevant, over-reliant, and logical reasoning errors). Results. In this study cohort (mean age 40{+/-}13 years; 81% women) representative of the clinic population, GPT-4 performed well in predicting MS diagnosis (84% accuracy, 79% precision, 74% recall, 91% specificity) using first neurology notes. Hallucinations occurred in 32 cases (26%), most commonly incoherence (75%) and overreliance (47%). Conclusion. A structured, LLM-guided decision framework can flag MS diagnoses from early clinical documentation. Large-scale studies are needed to mitigate hallucinations, validate this approach, and test implementation in clinical settings.

The incidence rate ratio R is the standard measure for comparing event rates in clinical trials and epidemiology. In vaccine trials, the vaccine efficacy is VE = 1 - R. When events are rare, the two arm counts are Poisson. The estimator of R is heteroskedastic: its sampling variance changes with the data. So no fixed-width interval covers correctly everywhere. The usual log-Wald interval is undefined at zero events and covers poorly at small counts. Early vaccine and drug-safety readouts fall in exactly this regime. We show that a single reparameterization collapses this bivariate problem to an effective one-parameter family with a quadratic variance function, whose variance-stabilizing transformation is 2 arcsinh(sqrt(R)). The reduction yields a closed-form confidence interval for R. Its two leading errors, a curvature bias and the variability of the estimated scale, each admit a closed-form correction with no tuning constants. In a Monte Carlo study of our seven arcsinh variants and five competitors, the +Curve+Stu variant covers within 0.002 of the nominal 0.95 for about 50 control and 5 treatment events. Its width is on par with the best competitor. It avoids the conservatism and zero-count breakdown of log-Wald and MOVER. For moderate counts, we recommend this interval; for sparser data, our Bar-Lev and Enis count-shift variant is more robust. The result is a ready-to-use, closed-form interval for the low-count regime. We illustrate it on early Covid-19 vaccine-efficacy readouts and provide reference implementations in R and Python.

Asthma is a heritable complex disease that disproportionately burdens minority and admixed populations in the US. However, the causal genes and regulatory mechanisms governing inherited risk remain largely unresolved. We performed a European-ancestry meta-analysis of 141,894 cases and 1,361,846 controls drawn from the Trans-national Asthma Genetic Consortium (TAGC) and Global Biobank Meta-analysis Initiative (GBMI), yielding an estimated h2SNP of 0.056 (SE = 0.0038) and 275 independently associated loci. To enhance mechanistic inference beyond variant-level associations, we developed a multimodal framework to predict asthma risk integrating GWAS summary statistics, bulk tissue expression quantitative trait loci (eQTL) data from the Genotype-Tissue Expression (GTEx) project, and single-cell gene eQTL data from the OneK1K Project. We performed transcriptome-wide association studies (TWAS) and subsequently applied probabilistic fine-mapping with FOCUS to prioritize putative causal genes expressed in bulk tissues and higher resolution immune cell populations. Fine-mapping asthma-associated genes implicated barrier-immune and metabolic-endocrine tissues alongside adaptive T-cell subsets as the primary mediators of asthma genetic risk, resolving canonical CD4+ Th2 effector genes including IL1RL1, TSLP, STAT6, and GATA3. Using these prioritized genes, we constructed a polygenic transcriptome risk score (PTRS) using random forest to integrate gene-level effects across critical tissues and cell types. Evaluated in two ancestrally distinct pediatric asthma cohorts, the Childhood Asthma Management Program (CAMP) and the Genetics of Asthma in Costa Rica Study (GACRS), our PTRS demonstrated improved transferability over the standard variant-level and gene-level baseline models. While modest common variant heritability limits the discriminative power of our models, we estimated a theoretical maximum achievable area under the receiver operating characteristic (AUROC) curve of 0.64. Our integrative nonlinear model of PRS-CSx and cross-modal (bulk tissue and single cell) FOCUS PTRS resulted in the best cross-cohort performance (CAMP AUC = 0.632, sd = 0.04, 3.55 case/control odds ratio in top vs. bottom quartiles), representing an increase of +0.118 AUC over PRS-CSx, +0.067 AUC over tissue-specific TWAS pruning and thresholding, and +0.041 AUC over cell-type-specific FOCUS PTRS. Our results demonstrate that modeling nonlinear interactions between variant- and gene-level effects across both bulk tissue and single cell eQTL data improves our ability to determine high-risk individuals and to explain the likely mechanisms driving genetic susceptibility of childhood-onset asthma.

Offline reinforcement learning (RL) has emerged as a promising framework for clinical decision support in sepsis, yet most existing studies focus exclusively on adult populations, leaving pediatric care largely unexplored despite important physiological and treatment differences. In this work, we develop offline RL policies for pediatric sepsis management in the Pediatric Intensive Care Unit (PICU) using a retrospective cohort of 2,229 episodes from Great Ormond Street Hospital (GOSH), formalized as finite horizon Markov Decision Process (MDP) with joint intravenous fluid and vasopressor actions. To better capture pediatric organ dysfunction dynamics, we incorporate Phoenix 8, a recently proposed pediatric sepsis severity score, as an intermediate reward shaping signal in addition to terminal 90 day mortality. We systematically vary the time step size (4, 8, and 12 hours) and reward structure (terminal 90 day mortality, with and without Phoenix 8 based intermediate shaping), and compare Double Deep Q Networks (DDQN), Conservative Q Learning (CQL), and a behavior cloning (BC) model of clinician practice. CQL consistently exhibits stable learning dynamics and favorable Fitted Q Evaluation estimates, while DDQN is prone to overestimation and instability, particularly at finer temporal resolutions and with dense rewards. CQL policies achieve high action-level agreement with historical clinician decisions for both fluids and vasopressors and reproduce clinically plausible escalation patterns across sepsis severity strata, whereas DDQN policies diverge more frequently toward implausible dosing. Temporal aggregation emerges as a key regularizer: moving from 4 hour to 8 hour bins shortens horizons, smooths reward noise, and improves stability without erasing clinically meaningful dynamics, with 8 hour binning providing the best trade off between policy performance and granularity. Our findings highlight time step size as a core design choice in offline RL for healthcare and provide empirical evidence that alternatives beyond the conventional 4 hour setup can enhance stability and safety while preserving clinical interpretability.

Pneumonia is a leading cause of infectious disease mortality worldwide, accounting for approximately 2.5 million deaths annually and 15% of deaths in children under five. Chest X-ray imaging remains the primary diagnostic tool, but accurate interpretation requires radiological expertise that is disproportionately concentrated in high-income settings, creating a diagnostic gap where disease burden is highest. Automated deep learning offers a scalable complement to specialist-dependent diagnosis, yet clinical adoption requires both high accuracy and transparent, interpretable reasoning. Convolutional neural networks (CNNs) have shown strong potential for pneumonia detection from chest X-rays, but two barriers impede clinical translation: the interpretability of black-box models and the computational feasibility of large architectures in resource-constrained settings. Explainable AI (XAI) methods such as Grad-CAM, Grad-CAM++, and Score-CAM address the interpretability barrier, yet systematic quantitative comparisons across multiple CNN architectures remain scarce. Furthermore, CNN architectures widely used for medical image classification carry high parameter counts that limit feasibility in resource-constrained settings, motivating architectures that achieve competitive accuracy with substantially fewer parameters. Here we propose a parameter-efficient deep learning framework for pneumonia detection based on transfer learning, evaluated across three CNN architectures representing distinct architectural families: EfficientNet-B0 with fine-tuning (proposed method), ResNet50, and DenseNet121, trained under identical conditions on the Kaggle chest X-ray dataset (5,863 images). Our method achieved 90% classification accuracy, outperforming both baselines while requiring 4.8x fewer parameters than ResNet50. To evaluate explainability, Grad-CAM, Grad-CAM++, and Score-CAM were applied across all three architectures and compared quantitatively using Intersection over Union against manually annotated lung segmentation masks, Insertion score, and Deletion score, with pairwise statistical validation via Wilcoxon signed-rank tests and Bonferroni correction. Findings show that classification accuracy and XAI explanation quality must be evaluated independently, and that the proposed parameter-efficient architecture offers a favorable trade-off for resource-constrained clinical deployment.

Efficiently summarizing dietary records at scale remains a persistent bottleneck in nutritional epidemiology. We present FoodScribe, which translates free-text meal descriptions into quantitative nutrient profiles by combining ingredient parsing with nutrient retrieval by querying the USDA FoodData Central (FDC) database. Benchmarked using three LLM providers using Nutribench dataset, FoodScribe completed annotation of 3,807 meal descriptions in 2.5 hours, a task otherwise requiring substantial manual effort from trained nutritionists. FoodScribe achieved accuracy across macronutrient estimation (F1=0.79-0.89), with models performing better for protein than fat estimation. Application to a Mediterranean diet intervention cohort indicated dietary shifts consistent with the intervention pattern based on model-derived estimates. Integration with metabolomics data suggested that fiber and vegetable intake were positively associated with a fecal metabolite cluster.

Stochastic epidemic models are a cornerstone of infectious disease epidemiology and are often used to study intervention scenarios. However, large run-to-run variability can make intervention effects difficult to estimate precisely. We revisit the epidemic Sellke construction, which assigns each individual an infection threshold for the cumulative infection hazard such that, conditional on the thresholds, the epidemic trajectory becomes deterministic. This enables coupling of simulations with and without an intervention, yielding low-variance effect estimates even when outcomes such as final size or peak incidence vary widely between runs. We develop an exact, event-driven implementation that maintains infection and recovery events in priority queues. Cumulative infection-hazard updates require O(log N) time per event, yielding overall complexity O(Elog N) for E events in a population of size N. The implementation achieves computational performance comparable to the classical Gillespie algorithm while naturally accommodating non-Markovian infectious periods and complex infectiousness profiles. We illustrate the approach using distance-dependent spread of avian influenza between poultry farms in the Netherlands and a multilayer population with households, schools, and workplaces. In both examples, coupling enables efficient within-run comparisons of intervention scenarios across stochastic realisations.

Background with objective: Detecting EGFR mutations is critical for treating lung adenocarcinoma with highly effective targeted therapies. However, standard genetic testing is expensive, complex, and often unavailable in resource-limited settings like Bangladesh. Because elevated serum CEA has been linked to these genetic alterations, it could serve as an accessible screening tool. This study aims to evaluate the association between serum CEA levels and EGFR mutation status to determine if routine CEA testing can reliably predict these mutations and guide treatment. Methodology: In this cross-sectional analytical study, we recruited 58 patients with histologically confirmed treatment naive lung adenocarcinoma. The presence of EGFR mutations in the ctDNA was determined via ARMS (Amplification Refractory Mutation System) PCR. Patient data was statistically analyzed to assess the diagnostic correlation between serum CEA levels and the presence of EGFR mutations. Result: The overall EGFR mutation rate was 43.1% with exon 19 deletion (48%) and exon 21 mutations (44%) were the predominant types. Median serum CEA levels were significantly higher in patients with EGFR mutations compared to wild-type cases (14.6 ng/ml vs 2.8 ng/ml, p<0.001). A multivariate analysis revealed a 14% increased likelihood of an EGFR mutation for 1 ng/ml rise in serum CEA. Furthermore, serum CEA showed strong diagnostic accuracy for ctDNA samples at a 6.39 ng/ml cut-off (AUC 0.82, sensitivity 68.0%, specificity 84.8%). Conclusion: Serum CEA is a valuable, cost-effective, and non-invasive biomarker demonstrating significantly higher levels and strong diagnostic accuracy in EGFR-mutated lung adenocarcinoma compared to wild-type cases.

Background: Actigraphy-derived rest-activity rhythm (RAR) features are widely used to characterize clinical states in bipolar disorder (BD). Both mean levels and temporal variability of these features have been associated with mood episodes; however, variability measures are often statistically coupled with the mean, particularly in skewed distributions. This raises a question as to whether variability reflects a separate characteristic of the data or whether the observed association arises from statistical properties of the data. Objective: In this study, we aim to determine whether temporal variability of actigraphy-derived RAR features provides standalone information on mood episodes in BD beyond mean activity levels after accounting for mean-variance dependence. Methods: We analyzed actigraphy data from a subset of 72 participants with BD drawn from a larger longitudinal study, extracting 22 daily RAR features aggregated weekly as sample mean (MEAN) and within-week temporal variability computed as sample standard deviation (VAR). Variance-stabilizing transformations (Box-Cox or Yeo-Johnson) were applied to the entire study cohort to reduce mean-variance dependence. Associations with mood episodes and remission (mania: n=34; depression: n=58 annotated participants) were evaluated using generalized linear mixed-effects models with a logistic link function, including univariate (MEAN or VAR) and multivariate (MEAN+VAR) specifications, assessed by likelihood-based metrics and the area under the receiver operating characteristic curve (AUC). Results: Transformations reduced mean-absolute correlations from 0.43 to below 0.06. Temporal variability remained significantly associated with clinical state for 11/22 RAR features in mania and 16/22 features in depression, with all significant associations remaining after false discovery rate correction (p<0.05). Joint models showed modest incremental gains (AUC 3%-4% overall; up to 12% in mania, 7% in depression), with absolute performance remaining limited (AUC 0.50-0.66). In both mania and depression, nearly all significant variability-based regressors contributed incremental information beyond mean-based models. Only sleep duration and activity changes around wake time (+-1 hour), did not improve discrimination between mania and remission. Conclusions: Temporal variability in RAR features can be considered a standalone state marker of mood episodes not captured by mean activity. We found it to be more consistently associated with depression than mania. Its incremental discriminative contribution is modest, suggesting greater utility within multivariate or multimodal frameworks.