NAR Genomics and Bioinformatics

Background: The development of personalised mRNA cancer vaccines holds considerable promise for oncology, yet a significant translational gap persists between neoantigen identification and the selection of therapeutically impactful targets. Current approaches predominantly prioritise human leukocyte antigen (HLA) binding affinity and immunogenicity, often overlooking the systems-level biological context of the target. This can inadvertently favour immunogenic but biologically peripheral peptides that exert limited influence on tumour signalling networks, thereby constraining vaccine efficacy. Furthermore, mRNA therapeutics must satisfy additional design requirements, including favourable codon usage and favourable secondary-structure stability, which directly affect in vivo translation and half-life. A unified computational framework that integrates neoantigen discovery with network biology is therefore critically needed. Results: Here, we present PimRNA, a Priority index (Pi)-centric computational medicine framework that bridges this gap by unifying neoantigen identification, mRNA sequence optimisation, and gene interaction network analysis. First, high-confidence tumour-specific HLA class I and II neoantigenic peptides are identified from paired tumour-normal genomic and tumour transcriptomic data using NeoDisc. Second, the coding sequences of these peptides are optimised for stability and translational efficiency with LinearDesign, yielding a core set of neoantigen-encoding mRNAs. Third, a random walk with restart algorithm is applied to a knowledgebase of gene interactions to identify peripheral genes exhibiting significant network connectivity to core genes, generating a gene-predictor matrix in which each gene is assigned an affinity score reflecting its network proximity to immunogenic neoantigens. These scores are consolidated into a single, unified priority rating (0-5) for each gene, followed by subnetwork analysis that reveals therapeutically relevant gene modules. Application of PimRNA to breast cancer and melanoma datasets demonstrates that it successfully selects high-confidence immunogenic neoantigen candidates embedded within biologically meaningful tumour-specific networks. Conclusion: PimRNA provides a systems biology foundation for mRNA vaccine design, moving beyond isolated immunogenicity to prioritise targets that are both highly presented and central to tumour-relevant biological networks. This framework offers a generalisable strategy for the rational discovery and prioritisation of mRNA therapeutics, significantly advancing the field of computational medicine towards personalised cancer vaccines.

Objective. Biomedical knowledge graphs (KGs) such as PrimeKG, Hetionet, UMLS, and PharmGKB are increasingly used as the substrate for downstream machine-learning, retrieval-augmented generation, drug-repurposing, and electronic health record (EHR) augmentation pipelines. The dominant assumption in published work is that integrating two or more such KGs is a tractable engineering step solved by identifier (ID) matching. This paper interrogates that assumption empirically. We quantify how much concept overlap survives realistic alignment, and we characterize the new failure modes introduced by the methods that practitioners reach for when ID matching is insufficient. Materials and Methods. We compared four widely used biomedical KGs (PrimeKG, Hetionet v1.0, the full UMLS Metathesaurus, and PharmGKB) across eleven node types using a tiered alignment pipeline: (1) direct ID matching for nodes sharing a primary vocabulary; (2) cross-ontology bridging using standard mappings (e.g., MONDO-DOID, HPO-UMLS, HPO-UMLS-MeSH for side effects, NCBI Gene-HGNC-UMLS, UBERON-FMA/SNOMEDCT_US/NCI/MeSH for anatomy); (3) ClinicalBERT cosine-similarity grouping at threshold >= 0.98 for over-segmented disease nodes, with a deterministic suffix-stripping canonicalizer; (4) exact name matching for ontology-poor types (anatomy, REACTOME pathways); and (5) embedding-based fuzzy matching with UMLS lookup (SapBERT and ClinicalBERT) for free-text microbiome concepts. We applied the pipeline to a 698-concept gut-microbiome benchmark spanning taxa, pathways, and disease labels, validated grouping decisions against the curated SSSOM mappings released by the MONDO project, and audited the ClinicalBERT consolidation against five clinical-genetics case studies drawn from the literature. Results. Per-type pairwise coverage was strikingly asymmetric. Genes/proteins and the three Gene Ontology categories aligned cleanly across PrimeKG and Hetionet (mutual coverage 94-99%), but disease overlap was sparse: only 0.7% of PrimeKG individual disease nodes mapped to Hetionet, rising to 2.0% after MONDO grouping (versus 78.7% and 18.4% from the Hetionet side). PrimeKG-to-UMLS coverage spanned 100% (effect/phenotype via HPO) down to 20.8% (REACTOME pathways), with drugs at 73.7% and anatomy at 58.8%. PrimeKG-to-PharmGKB drug coverage required up to two bridging hops (DrugBank -> UMLS -> RxNorm/ATC/MeSH). Bigger was not uniformly more complete: on a 698-concept microbiome drug benchmark, Hetionet missed 0 concepts while PrimeKG missed 16. ClinicalBERT-based grouping consolidated 22,205 raw MONDO disease nodes into 17,080 groups but introduced three reproducible failure modes documented in case studies: (i) peer over-merging: for example, all 22 osteogenesis imperfecta subtypes collapsed into a single node despite distinct severity classes; (ii) parent-child collapse: e.g. acute myeloid leukemia merged with myeloid leukemia, erasing the acute/chronic distinction that drives clinical management; and (iii) lexical false positives: neurofibromatosis and schwannomatosis grouped together despite cellular-pathology differences. Discussion. Identifier matching alone is a weak baseline for biomedical KG integration. Cross-ontology bridges and embedding-based consolidation expand coverage but do so at the cost of clinically meaningful resolution, and the resulting failures are systematic rather than random. Reporting only aggregate coverage statistics obscures these losses, which propagate silently into downstream tasks. Conclusion. We provide reusable per-type coverage tables, a taxonomy of three integration failure modes, and concrete recommendations for downstream studies that depend on a unified biomedical KG. We argue that future KG integration work should report per-type coverage and per-cluster confidence rather than aggregate match rates.

Andes orthohantavirus (ANDV), the primary etiological agent of hantavirus pulmonary syndrome (HPS) in South America, is uniquely capable of limited human-to-human transmission, posing a significant challenge for outbreak control. Recent events, including the 2018-2019 Epuyen outbreak and the 2026 MV Hondius incident, underscore the need for rapid, lineage-specific molecular diagnostics. In this study, we present an artificial intelligence (AI)-driven framework for the design of diagnostic primers targeting the S genomic segment of the Epuyen lineage. Using an evolutionary algorithm integrated with thermodynamic evaluation via Primer3Plus, candidate primers were optimized to maximize classification accuracy while satisfying stringent biochemical constraints. The resulting primer set enables amplification of lineage-specific regions suitable for molecular characterization and surveillance. In silico validation demonstrates that the proposed primers achieve perfect discrimination between 2026 outbreak sequences and other ANDV variants. Furthermore, in silico comparison with standard protocol-based primers reveals substantially reduced sensitivity and specificity in the latter, highlighting the limitations of static diagnostic designs when applied to evolving viral populations. Overall, this work demonstrates that AI-assisted primer design provides a robust and adaptable strategy to improve viral detection, enhance outbreak tracking, and support timely public health interventions. Integrating computational optimization into diagnostic development is essential for strengthening preparedness against emerging zoonotic threats.

Precision medicine aims to advance our ability from a "one-size-fits-all" approach to personalized and predictive healthcare across diverse populations. It promotes integration of multi-omics and phenotypic data to understand disease mechanisms and discover novel biomarkers and risk factors, which could be used to predict and prevent critical diseases in individual patients across diverse populations. The potential implications of precision medicine approach can accelerate our ability to classify patients at higher risk of developing critical diseases, improve diagnostic capabilities, develop deeper understanding of individual risk, investigate racial differences and demographic characteristics, and find relationships between genetic variants, expressions, and diseases. This study focuses on implementing an innovative and data driven framework of translational bioinformatics and Machine Learning (ML) techniques to analyze multi-omics, including RNA-seq and Whole-Genome Sequencing (WGS) data, generated using blood samples of randomly consented patients. First, we utilized bioinformatics pipelines to identify differentially expressed genes and their pathogenic and likely pathogenic variants for the downstream data analysis, annotation, and visualization. Then, applied a nexus of ML models for multi-omics biomarker discovery, disease prediction, density-based clustering, single-patient profiling, and pathogenicity classification. WGS data analysis supported the exploration of genetic variation and diversity among patients to identify known and novel biomarkers, whereas RNA-seq data analysis improved our understanding of functional and biological pathways that underlying disease states. We classified and clustered pathogenic variants and expressions across various genes and discovered numerous diseases leading risk factors. Our results include gene-disease associations and captured common pathways across the broader population, demonstrating a level of sensitivity and accuracy that has broad clinical implications. We validated our results through clinical records, and state of the science literature. This study delves into the strengths of multi-omics data integration and capabilities of ML application in genetically diverse and complex patient cohorts. Our approach has the potential to elucidate complex gene-disease interactions for genetically diverse populations, which can support earlier diagnoses for patients in many disease realms.

Pathway-specific polygenic risk scores (pathway-PRS) measure aggregate genetic risk across single nucleotide variants (SNVs) annotated to genes in a pathway of interest. In most applications, SNV-to-gene annotation is based on SNV position with respect to gene boundaries. This approach is ill-suited for incorporating non-coding SNVs, which can regulate gene expression over long distances and represent a large proportion of risk variants for Alzheimer's disease (AD). Here, we compare the performance of AD pathway-PRS across SNV-to-gene annotation strategies that integrate varying levels of functional genomic data, including adult brain chromatin interaction and expression quantitative trait loci (eQTL) data. In the UK Biobank (n=328,526), including AD cases defined by ICD-9/10 codes (n=3,043) and by family history of AD/dementia (n=38,589), we show that the annotation strategy integrating chromatin interaction and eQTL data consistently improves pathway-PRS performance. We replicate this finding in independent data from the Alzheimer's Disease Genetics Consortium (n=3,370). We further find that pathway-PRS associations with AD vary by annotation strategy and that power to detect sex-dependent and age-at-onset associations is increased with integrative annotation. Together, these findings support the use of functionally informed SNV-to-gene annotation for pathway-PRS construction and highlight the importance of applying multiple annotation strategies for robust inference.

Joint modelling of longitudinal data using non-linear mixed effects models and time-to-event outcomes provides a suitable framework to account for informative censoring when estimating biomarker dynamics and quantifying event risk using covariates and longitudinal trajectories. Their usefulness in clinical research depends on data collection design, particularly to precisely estimate the association (link) parameter between longitudinal and survival processes. However, optimal design strategies have so far been addressed separately for longitudinal and survival endpoints and remain unexplored for joint models. We propose two Fisher Information Matrix (FIM) computation methods for joint models, relying on Monte-Carlo integration over observations combined with either Markov Chains Monte-Carlo or Adaptive Gaussian Quadrature to integrate random effects. Their accuracy is assessed against clinical trial simulations in an oncological example based on the HORIZON III study with a tumour-growth-survival model including discrete and continuous covariates. We apply these methods to quantify the impact of follow-up duration, sampling richness, sample size, and covariate distribution on parameter uncertainty and test power. In our example, longitudinal-parameter uncertainty is barely affected by follow-up duration or sampling richness, whereas survival-parameter uncertainty decreases substantially from 1-year to 2-year follow-up. The number of subjects needed (NSN) to achieve <15\% uncertainty on the link parameter is comparable for a 2-year rich design and a 3-year sparse design. Optimal covariate distributions are stable across designs and systematically improve test power, outperforming longer and richer but non-optimised designs. These FIM-based methods accurately predict uncertainty and test powers, enabling design evaluation and NSN computation for joint-model-based clinical studies.

Most routine clinical markers are interpreted using population-based reference intervals, despite being regulated around patient-specific homeostatic setpoints. This mismatch obscures physiologic shifts, inhibiting detection of early disease signatures. Here, we develop a novel Bayesian inference method that adaptively constructs personalized reference intervals using each patients existing health records. In analysis of >100 million lab tests in >800,000 patients, these personalized intervals can be accurately constructed with only minimal prior data, meaning this method can be applied near universally. We show that across 43 common lab markers, patient setpoints are strongly associated with future morbidity, with signal strength increasing as more test data is collected. Deviation from personalized reference intervals provides strong and novel risk signatures across diverse disease states, including hypothyroidism, hematologic cancers, kidney disease, and pregnancy complications. Importantly, personalized reference intervals capture a different risk signature to existing population-based approaches, with the highest risk patients being those who deviate from both intervals simultaneously. In a targeted clinical use case study of iron infusion, use of personalized reference intervals greatly improved prediction of treatment efficacy and allowed precise tracking of treatment responses. Our results illustrate how existing health records can be used to construct personalized benchmarks for nearly all common clinical tests, driving a new paradigm for precision laboratory medicine.

Background: The All of Us Research Program represents a rich resource for cancer epidemiology research, with over 400,000 participants with whole genome sequences linked to electronic health records (EHR). Large cancer datasets often focus exclusively on cases without controls and neglect pre-diagnosis healthcare occurrences. Here, we perform a phenome-wide association study (PheWAS) of EHR data at least 1 year pre-diagnosis between cancer cases and matched controls, revealing co-occurring and mutually exclusive phenotypes. Methods: We identified 55,000+ cancer cases across 21 cancer types in All of Us version 8. To eliminate age-related confounding, we implemented a two-stage matching and censoring strategy: loose matching on demographics to establish index dates and cohort comparability, followed by right-censoring of EHR data (excluding 1 year pre-diagnosis/index), then 1:2 matching to address residual demographic imbalance. We tested associations between 23,193 cancer cases, 46,386 matched controls and approximately 1,600 clinical phenotypes using logistic regression adjusted for sex at birth, self-reported race, age at diagnosis/index date, and two censored EHR metrics: observation window and unique condition count, with Bonferroni correction for multiple testing. Results: Our analysis identified 232 significantly associated phenotypes, confirming established cancer risk factors including elevated prostate specific antigen (OR = 2.92, 95% CI: 2.65-3.23; p-value=1.8x10-101) and multinodular goiter (OR = 1.73, 95% CI: 1.56-1.91; p-value=6.7x10-27). Further investigation into the relationship between several phenotypes with seeming inverse effects is warranted. Conclusions: This PheWAS of EHR data at least 1 year pre-diagnosis leveraged the diversity of All of Us to examine how clinical phenotypes prior to cancer diagnosis vary across cancer types and racial groups. Our findings validate All of Us as a robust platform for cancer epidemiology research, confirming established risk factors at scale across diverse populations. This work provides methodological insights for EHR-based susceptibility analyses and demonstrates the value of agnostic phenome-wide approaches for generating hypotheses in precision medicine.

Objective: To systematically evaluate pathway-informed polygenic risk score (PRS) strategies and determine which approaches most effectively leverage biological annotations for risk prediction, using brain amyloid-beta positivity as a case study. Methods: We systematically benchmarked approaches for integrating pathway information into PRS construction to predict brain A{beta} positivity. Using two cohorts, the Alzheimer's Disease Neuroimaging Initiative (ADNI, n = 969) and Australian Imaging, Biomarkers and Lifestyle (AIBL, n = 251), we compared Apolipoprotein E (APOE) genetic risk score (GRS), clumping and thresholding (C+T) PRS, pathway-guided single nucleotide polymorphism (SNP) selection PRS, and pathway-specific PRSs ensembled via machine learning. Pathways were derived from manually curated literature or from pathway databases via Functional Mapping and Annotation (FUMA). Results: In cross-validation on the ADNI cohort, pathway-informed PRS using a narrow-set of pathways to guide SNP selection (PathPRS-SNPLit without APOE locus) significantly outperformed the standard PRS model (median AUC = 0.742, p = 0.006) and the APOE locus model (median AUC = 0.736, p = 5.1 x 10-5) based on the Mann-Whitney U test, achieving a median AUC of 0.763. This model showed enhanced ability to identify subgroups within the 10% lowest- and highest-risk groups compared to the current standard of APOE locus alone (odds ratio = 0.67, 95% CI: 0.56-0.81; and OR = 13.23, 95% CI: 10.23-17.11), highlighting its clinical potential. Using a focused set of literature-curated pathways outperformed using a broader set of database-derived pathways across configurations. When contrasting strategies for aggregating information across pathways, we observed that using pathways to guide selection of SNPs and then building a single PRS performed comparably to building PRS for each pathway and using machine learning (ML) to aggregate these, though the latter enabled pathway-level interpretability. Similar trends were observed in the external AIBL validation dataset. Interpretation: Pathway-informed PRS can meaningfully improve genetic risk enrichment for A{beta} positivity beyond APOE and standard C+T approaches, provided pathway definitions are carefully curated. The choice of pathway source has the strongest impact on predictive performance, with aggregation strategies or ML model choice having far less impact. Our findings highlight the utility of literature-curated, pathway-informed PRSs for A{beta} prediction and offer practical guidance for pathway-informed PRS construction in other polygenic traits.

Vocal biomarkers, encompassing voice and speech, have largely been developed for individual conditions in isolation, limiting their generalizability across diseases and recording settings. To address this, we introduce VoiceFM, a contrastive model that learns general-purpose clinical voice representations by aligning audio embeddings with rich clinical metadata. Using the Bridge2AI-Voice dataset (984 primarily English-speaking adult participants, 846 used for training and 138 held out as a temporally separated validation cohort, 40,056 recordings totaling 176 hours across 5 academic medical centers), VoiceFM pairs a fine-tuned Whisper large-v2 encoder with a tabular transformer over 44 clinical features via symmetric InfoNCE loss. Linear probes on frozen VoiceFM embeddings achieve mean AUROC 0.952 +/- 0.005 across five evaluation tasks (control vs disease screening plus four disease categories), significantly outperforming Frozen Whisper (0.926 +/- 0.013, p = 0.013), Frozen HuBERT (0.885 +/- 0.017, p = 0.0009), and the contrastively trained VoiceFM-HuBERT (0.938 +/- 0.006, p = 0.012). On the 138-participant held-out cohort, VoiceFM-Whisper achieves AUROCs of 0.99 for Alzheimer's/dementia/MCI and 0.89 for airway stenosis, demonstrating that the learned representations generalize to participants the model has never seen. VoiceFM representations transfer to three external datasets without retraining and improve few-shot classification. Recording task attribution identifies a small set of speech tasks that match or exceed the full battery's performance, suggesting shorter screening protocols are feasible. Trained predominantly on English audio, VoiceFM transfers without fine-tuning to Spanish-language Parkinson's disease (PD) detection (NeuroVoz, 107 participants, AUROC 0.93 +/- 0.02), with the signal dominated by articulatory rather than phonatory features. A fine-tuned classifier achieves participant-level AUROC 0.87 (sustained 0.85, countdown 0.80) on the mPower smartphone study (585 held-out participants). Together, these results show that contrastive alignment between voice and rich clinical metadata can serve as the basis for a clinical voice foundation model, producing a single set of transferable representations that generalize across diseases, languages, recording conditions, and patients enrolled after model freeze.

Subjective auditory-perceptual evaluation and uninterpretable deep learning models limit the clinical assessment of voice disorders. This study proposes a two-phase zero-shot framework to evaluate voice pathology. First, an Audio Spectrogram Transformer is fine-tuned on the Perceptual Voice Quality Database to generate an acoustic latent space. Second, Orthogonal Procrustes analysis maps these acoustic embeddings directly onto the semantic space of a pre-trained Sentence Transformer. The geometric alignment produced continuous semantic axes that outperformed a supervised machine learning baseline in regressing clinician-rated GRBAS (Grade, Roughness, Breathiness, Asthenia, and Strain) severity scales. Furthermore, these axes correlate with traditional acoustic measures, including Harmonics-to-Noise Ratio and local jitter, while remaining robust when applied to aperiodic signals by not requiring fundamental frequency extraction. Most importantly, the model achieved zero-shot semantic expansion, successfully evaluating voices using an untrained, natural clinical vocabulary beyond the GRBAS scale. External validation on the Voice ICarus Database confirmed cross-corpus stability and demonstrated the capacity for zero-shot differential phenotyping of specific etiologies, such as hypokinetic dysphonia and reflux laryngitis. By bridging acoustic and semantic latent spaces, this framework offers an objective, continuous, and transparent metric for evaluating voice quality using voice descriptive vocabulary.

Background: Biallelic variants in GFM2, encoding mitochondrial elongation factor G2 (mtEFG2), a GTPase involved in the termination stage of mitochondrial translation, cause autosomal recessive combined oxidative phosphorylation deficiency. Noncoding structural variants may be missed by exome sequencing but can disrupt splicing and provide opportunities for variant-specific therapeutic rescue. We investigated the molecular mechanism underlying suspected Leigh syndrome in an infant with mitochondrial disease and evaluated whether splice-switching oligonucleotide (SSO) treatment could correct the pathogenic splicing defect. Methods: The proband underwent exome sequencing followed by short-read and long-read whole genome sequencing. RNA sequencing, reverse-transcription PCR, quantitative PCR, and cycloheximide treatment were used to characterize the effect of the identified intronic duplication on GFM2 splicing and transcript stability. Patient-derived fibroblasts were treated with SSOs targeting the aberrant splice junction. Rescue was assessed by RNA studies, western blotting, and spectrophotometric measurement of cytochrome c oxidase (COX). Results: Whole genome sequencing identified a paternally-inherited GFM2 missense variant, NM_032380.5:c.2195C>T p.(Pro732Leu), in trans to a maternally-inherited 221-nucleotide intronic duplication, NM_032380.5:c.2029-741_2029-521dup. RNA studies revealed a 87-nucleotide pseudoexon, generated by activation of a cryptic acceptor splice site within the duplicated sequence. The resulting transcript harbored a premature termination codon (PTC) and underwent nonsense-mediated decay, as confirmed by cycloheximide rescue. Together with reduced mtEFG2 protein levels on western blot, the findings supported a loss-of-function mechanism. Enzymatic analysis of affected fibroblasts showed reduced activity of the mtDNA-dependent complex IV subunit COX, with preservation of the nuclear-encoded complex II enzyme succinate dehydrogenase and the control enzyme citrate synthase, consistent with impaired mitochondrial translation. A SSO targeting the aberrant intron-pseudoexon junction nearly abolished pseudoexon inclusion, restored correctly spliced GFM2 transcript from the duplication-containing allele, increased mtEFG2 protein levels, and significantly improved COX activity. Conclusions: This study identifies a pathogenic intronic GFM2 duplication that causes mitochondrial disease through pseudoexon activation and nonsense-mediated decay. The findings demonstrate the value of integrated genome and transcriptome analysis for exome-negative mitochondrial disease and provide in-vitro proof of concept that SSOs can restore transcript processing, protein expression, and mitochondrial respiratory-chain function in patient-derived cells.

Quantifying uncertainty in polygenic score (PGS)-based phenotype prediction is crucial for the integration of genomic data into precision medicine. While the PGS provides a fundamental pivot for point estimation, clinical decision-making necessitates the construction of well-calibrated prediction intervals that reliably encompass the true phenotypic values. However, phenotypic residuals are frequently characterized by complex heteroscedasticity and stratified variance structures across diverse demographic contexts. Existing approaches often rely on global calibration mechanisms, which fail to account for such localized variance structures and lead to systematic miscalibration within specific subpopulations. To bridge this gap, we propose Clustering-based Split Conformal Prediction with Normalized Residuals (C-SCNR), a versatile framework based on Split Conformal Prediction. By adopting residual normalization and incorporating a repetitive `split-and-cluster` mechanism, C-SCNR dynamically identifies latent error strata and applies fine-grained adjustments to the resulting intervals. Our framework requires no distributional assumptions regarding the phenotype, is compatible with any PGS method, and flexibly accommodates biologically-informed grouping. Simulation studies demonstrate that our framework consistently outperforms existing methods across diverse error distributions. In real-data applications analyzing Body mass index (BMI), Low-density lipoprotein (LDL) cholesterol, and High-density lipoprotein (HDL) cholesterol in the UK Biobank, C-SCNR effectively resolves the coverage deficiencies of existing methods in specific subgroups and consistently yields superior localized calibration. Overall, C-SCNR represents a flexible and powerful framework for constructing high-resolution context-specific prediction intervals, thereby facilitating more reliable clinical interpretations of polygenic risk.

Background and Objective: Access to real-world electronic health records (EHRs) remains limited by privacy, governance and annotation constraints, hindering the development of clinical natural language processing models. Realistic synthetic progress notes may provide EHR-like corpora that preserve clinically rigorous information on diagnoses, treatments, symptoms, imaging, laboratory findings and therapeutic trajectories without relying directly on sensitive patient records. This study evaluates whether large language models (LLMs) can generate realistic Spanish prostate cancer progress notes from published case reports, preserving clinical content, temporality and hospital-style conventions.

Background: Adverse drug events (ADEs) are a critical indicator of patient safety but are often documented only in free-text clinical notes. The potential of recent advances in natural language processing (NLP), particularly generative large language models (LLMs), to identify ADEs remains understudied. This study aimed to compare the performance of multiple LLMs in identifying ADE-Drug relationships in inpatient and ambulatory clinical notes. Methods: We used clinical notes from the 2018 National NLP Clinical Challenge (n2c2) ADE dataset (inpatient; n=505) and from outpatient encounters (n=2,555) between October 1, 2018, and December 31, 2019, at a large academic medical center based in New England. Notes were pre-processed into snippets for model input. Evaluated Models included: GPT-4o, GPT-4o-mini, LLAMA 3.3-70B and their instruction fine-tuned variants (including low-rank adapters for LLAMA). Performance was assessed using both strict and relaxed evaluations (precision, recall, and F1) for all models, followed by manual evaluation (exact semantic match, partial match, missing ADE, drug mention only, not a drug, or wrong) of the two best-performing models. Results: GPT-4o and GPT-4o-mini were the top-performing models among those evaluated. GPT-4o consistently outperformed GPT-4o-mini in ADE extraction across both datasets, with higher F1-scores (0.524 vs. 0.381) and a more balanced precision-recall profile. Both models captured ADEs effectively in explicit and complex clinical contexts, although limitations included misclassification of pre-existing allergies and occasional conflation of therapeutic indications with adverse effects. GPT-4o achieved higher exact match coverage and fewer errors across clinical notes, indicating more reliable performance in both inpatient and ambulatory settings. Conclusion: This work establishes a foundation for integrating LLM methods into real-world drug safety surveillance, with direct implications for improving patient safety.

Background: Severe cytokine release syndrome (CRS) and immune effector cell-associated neurotoxicity syndrome (ICANS) are major dose-limiting toxicities of chimeric antigen receptor (CAR) T-cell therapy. Existing pre-infusion biomarkers offer modest discrimination, motivating non-invasive alternatives. Methods: We prospectively enrolled 26 patients with relapsed/refractory large B-cell lymphoma receiving axicabtagene ciloleucel. Pre-infusion (day -1) exhaled breath samples were analyzed by gas chromatography-mass spectrometry for 40 volatile organic compounds (VOCs). Candidates with univariate AUC > 0.65 for severe (grade >=2) CRS or ICANS were carried forward to sensitivity-maximization-at-given-specificity with LASSO regularization (SMAGS-LASSO), which selected separate panels for each outcome. Model performance was assessed by leave-one-out cross-validation with permutation p-values and Harrell bootstrap optimism correction. Results: The 4-VOC CRS panel (heptanal, benzaldehyde, 2-butanone, ethylbenzene) achieved LOOCV AUC 82.5% (80% sensitivity at 88% specificity) and the 3-VOC ICANS panel (nonanal, allyl methyl sulfide, levomenthol) achieved AUC 86.3% (67% sensitivity at 86% specificity). By tertile, severe CRS occurred in 8/9 (89%) high-risk versus 2/9 (22%) low-risk patients (Cox HR 6.82, 95% CI 1.41-32.9, p=0.017) and severe ICANS occurred in 8/9 (89%) versus 2/9 (22%) (HR 8.28, 95% CI 1.73-39.6, p=0.008). Each 1-SD score increase corresponded to a 3.80-fold higher hazard of severe CRS (p<0.001) and 4.36-fold higher hazard of severe ICANS (p<0.001). In head-to-head comparison, the 3-VOC ICANS panel outperformed the modified Endothelial Activation and Stress Index (mEASIX) (delta-AUC +0.36, DeLong 1-sided p=0.008). The 4-VOC CRS panel had numerically higher AUC than mEASIX (delta-AUC +0.19, p=0.150). Conclusions: Pre-infusion exhaled breath VOC panels stratify CAR T-cell recipients by severity and timing of severe CRS and ICANS, providing a non-invasive complement to existing serum biomarkers. Multi-institutional validation is warranted.

Patients with primary immunodeficiency (PID) often face prolonged diagnostic delays and may increasingly turn to large language models (LLMs) to interpret their symptoms during this period. We evaluated whether an LLM could recognize PID from symptom descriptions derived from interviews with 21 PID patients. In a prior study, we showed that GPT-4o identified PID in 96% of cases when prompted with physician-written patient histories (Rider et al., JACI, 2024). Here, when prompted with symptom descriptions in patients' own words, GPT-5 identified PID in only 7 cases (33%), although it more broadly suggested immune system issues in 18 cases (81%). The gap between these findings indicates that LLMs are sensitive to the language and framing of symptom descriptions, performing substantially worse when patients describe their own symptoms in everyday language than when clinicians summarize patient histories in structured medical terms. This study underscores the need to carefully evaluate how LLMs are used in patient-facing applications.

Obstructive sleep apnea (OSA) is associated with a wide range of comorbidities, but the extent to which these follow predictable, age-dependent patterns is not well understood. Identifying such patterns could provide insight into OSA heterogeneity and its links to physiological measures of OSA. We trained age-dependent topic models (ATM) on longitudinal electronic health records from 36,426 patients with OSA in the Mass General Brigham Biobank. ATM organizes incident diagnoses into distinct comorbidity "topics," whose age-specific disease loadings represent predictive patterns linking related diagnoses across the life course. We applied the trained model to compute individual-level topic scores in independent data: a cohort of 11,689 OSA cases and 22,695 matched controls, and a cohort of 6,220 patients with polysomnography (PSG)-derived physiological measures. We identified 19 distinct age-dependent comorbidity profiles, all significantly associated with OSA case status (FDR-adjusted p<0.05). Topics reflected recognizable clusters including metabolic, neuropsychiatric, and immune-mediated conditions, and several were distinguished by age-of-onset of key comorbidities, such as early- vs late-onset asthma. Seventeen of the 19 topics were significantly associated with at least one of 13 PSG-derived physiological measures, including associations between cardiometabolic topics and the apnea-hypopnea index, sleep apnea specific hypoxic burden, and respiratory event-specific heart rate burden. These findings indicate that age-dependent comorbidity patterns distinguish meaningful OSA subtypes with differing prognoses and endophenotype associations. ATM offers insight into complex OSA comorbidity and suggests that age-informed, topic-based stratification may improve individualized risk assessment, interpretation of PSG findings, and targeting of clinical interventions.

Background: Preparing tumor board patient summaries is time intensive. Large-language-model based systems may automate summarization but require real-world evaluation prior to clinical use. We performed an exploratory retrospective evaluation of the Microsoft Healthcare Agent Orchestrator (HAO), deployed in a Mayo Clinic controlled staged environment, to generate tumor board-style patient summaries from retrospective Electronic Health Record (EHR) notes. Methods: HAO generated summaries for breast, hepatobiliary, and neuro-oncology tumor board cases using up to the most recent 1,000 clinical notes. Clinician reviewers evaluated outputs via REDCap surveys across perceived factuality, completeness, clarity/conciseness, temporal cohesion, comparative performance, safety, and clinical utility (0-4 Likert scale). Reviewers were permitted to query the HAO chat interface to address missing details. Automated factuality was assessed using TBFact (bidirectional entailment), reporting precision and recall against available reference summaries. Results: Among 57 survey responses from 5 different physicians, mean scores exceeded 2.8 across domains, with medians of 3 for most axes. In an exploratory comparison, oncology fellows required less time to review HAO-generated summaries than to manually generate patient summaries (mean difference 13.57 minutes per patient, p<0.001), although this difference may be influenced by prior familiarity with the same cases; 96% of survey responses indicated that HAO would save time. TBFact evaluations showed higher recall than precision across domains, consistent with broad capture of reference content alongside additional content that was not present in gold-standard summaries. Attribution was viewed favorably but showed issues with primary-source specificity and link reliability. Conclusions: In a controlled Mayo environment, HAO demonstrated moderate performance and was associated with reduced review time for tumor board preparation. These findings are promising but preliminary and do not establish clinical safety, noninferiority to manual review, or readiness for routine clinical use. Limitations, including verbosity, specialty-specific content gaps, and inconsistent attribution, highlight the need for iterative refinement and further evaluation.

Curative-intent immunochemotherapy fails in ~30% of patients with large B-cell lymphoma (LBCL), yet no validated molecular tool enables early identification of high-risk individuals to guide treatment intensification. Using shallow whole genome sequencing (sWGS) of plasma cell-free DNA from 190 LBCL patients, we developed and validated the ACT score (Aberrations, fragment Composition, Terminal motifs), a composite classifier integrating genomic and fragmentomic features from a single post-cycle-1 sample. ACT-positive patients had worse 2-year outcomes versus ACT-negative patients: time-to-progression 29% vs. 83% (HR 4.4, 95% CI 1.9 - 10.0; P = 1.5 x 10 - 4) and overall survival 47% vs. 93% (HR 8.7, 95% CI 3.0 - 25.4; P = 1.8 x 10-6). ACT score was independently prognostic of the International Prognostic Index, and their combination identified the highest-risk patients. Unlike mutation-based approaches, this assay requires neither tumor tissue, germline control nor a baseline plasma sample. Built on open-source tools and sWGS, the ACT score offers a feasible scalable strategy for early risk stratification in aggressive LBCL.