BMC Bioinformatics

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.

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.

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.

Background: Recent food-based recommendations for flavan-3-ols highlight a growing need to understand the breadth of our dietary polyphenol exposure. However, estimation of dietary polyphenol intake remains challenging, requiring custom computational tools that are often difficult to implement or not fully reproducible. Objective: We aimed to an automated, user-friendly tool to estimate polyphenol intake from diet recalls and records. Methods: We developed Polyphenol Estimator, a tool that processes dietary data from the Automated Self-Administered 24-Hour (ASA24) Dietary Assessment Tool or the Automated Multiple-Pass Method from the National Health and Examination Survey (NHANES). Polyphenol Estimator disaggregates foods using the FDA Food Disaggregation Database into ingredients, matches these ingredients to FooDB, and estimates polyphenol intake at the total, class, and compound level. Optionally, these polyphenol estimates can be used to calculate the Dietary Inflammatory Index (DII). Polyphenol Estimator is freely available online (https://swi1.github.io/polyphenol_estimator) with a tutorial for users with limited programming experience. Results: To illustrate Polyphenol Estimator, we applied it to two days of diet recalls from adults ([≥] 20 years) in NHANES 2021-2023 (n = 2778). For 97.7% of participants, less than 2.5% of reported foods went unmapped, with 75.7% of participants having complete mappings. Total polyphenol intake was 517 +/- 439 (mean +/- SD) mg/1000 kcal, largely from green tea, coffee, black tea, apples, wine, oranges, and blueberries. At the class level, polyphenols classified as organooxygen compounds, flavonoids, and cinnamic acids and derivatives were top intake contributors. At the compound level, cyptochlorogenic acid, neocholorogenic acid, and caffeic acid were top contributors. Lastly, the DII was 1.4 +/- 1.9, indicating the average diet had proinflammatory potential. Conclusions: Polyphenol Estimator offers an automated method to obtain total, class, and compound-level polyphenol estimates from dietary data to aid future efforts to understand polyphenol intake exposures and their biological impact on health.

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.

Importance Prognostic tools beyond staging are needed to guide treatment and counseling in head and neck squamous cell carcinoma (HNSCC). Objective To develop and externally validate a machine learning model predicting survival in advanced HNSCC using routinely collected clinical and biomarker data. Design, Setting, and Participants Retrospective, multi-institutional cohort study including 2,385 patients with stage III-IV HNSCC diagnosed from 2012-2022 in the University of California Health Data Warehouse (UCHDW). Patients were randomly split into training (n = 1,908) and test (n = 477) sets. Partial external validation used 7,749 patients from the Surveillance, Epidemiology, and End Results (SEER) registry (2010-2020). Exposures Demographic, tumor, treatment, comorbidity, and biomarker variables recorded at or before diagnosis. Main Outcomes and Measures The primary outcome was all-cause mortality within 70 months. Cox proportional hazards models included all predictors. Discrimination was assessed with Harrell's concordance index (C-index), calibration with predicted vs observed survival, and stratification with Kaplan-Meier curves. A Random Survival Forest (RSF) was trained for benchmarking and interpretability using Shapley Additive exPlanations (SHAP). Results Among 2,385 patients in UCHDW (median age, 63 years; 29.0% mortality), the Cox model achieved a C-index of 0.735 in the internal test set. Risk quartiles showed clear separation on Kaplan-Meier curves (log-rank p < 0.0001). In the SEER cohort (n = 7,749), where only demographic, staging, subsite, and treatment variables were available, the reduced Cox model achieved a C-index of 0.688, with calibration showing modest underestimation of survival in high-risk groups. Age, T stage, Charlson Comorbidity Index, neutrophil-to-lymphocyte ratio, and platelet count were among the strongest predictors, while surgery was associated with improved survival. The RSF achieved a C-index of 0.758 internally, with SHAP highlighting nonlinear effects of albumin, BMI, and inflammatory markers. Conclusions and Relevance A machine learning model using routine clinical and biomarker data demonstrated good prognostic performance in advanced HNSCC, with partial external validation. Such approaches may support individualized survival estimates, risk stratification, and treatment discussions, but broader validation is required before clinical adoption.

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: Generative AI tools can support data-intensive research by writing code, drafting prose, searching analytical possibilities, and stress-testing claims. They can also produce false citations, drift between statistical specifications, and lose continuity across long investigations. This paper describes a practical workflow for using AI systems in empirical research while keeping discovery, verification, and accountability inspectable. Methods: We developed and applied a three-phase human-AI workflow to a case study of 14 elite Ethiopian distance runners. The dataset contained 22,605 GPS-segments collected across 97 consecutive days in late 2025, supplemented by venue and athlete metadata collected in the field. Phase 1 used an autonomous data-exploration tool to pre-filter the hypothesis space across five seeded research questions. Phase 2 used an AI system under direct human guidance to construct candidate findings into numerical claims, verification scripts, and draft text. Phase 3 used an independent AI system in an adversarial role to stress-test methods, statistics, prose, figures, and citations. The workflow was informed by Pearl's distinction between association, intervention, and counterfactual reasoning, with human judgement retained for research direction, interpretation, and final claims. Results: The workflow produced three empirical analyses and a documented correction process. The analyses estimated an altitude-to-sea-level pace correction of +0.10 min/km per 1,000 m at matched heart rate, showed why pooled altitude-surface regression was not identifiable within this venue system, documented method-dependence in heart-rate-based intensity classification, characterised within-venue route variation as a 64/36 path-fixed-to-trail-variable split with the Sululta label resolving into two functionally distinct sub-venues, and reframed the cohort's training through a 3x3x3 prescription lattice grounded in Ethiopian coaching practice. The adversarial phase identified several hallucinated citations, a terminology error between HC1 and cluster-robust standard errors, and several inconsistencies between prose, figures, and computed results. Verification scripts re-derived nearly all numerical claims from the cleaned lap-level data. Conclusions: The case study shows how researchers can organise AI-assisted empirical work so that candidate discovery, claim construction, independent stress-testing, and final accountability remain separated. The workflow did not remove the need for domain expertise or human judgement. Its value was in making the route from candidate finding to manuscript claim explicit, reproducible, and open to challenge. Trial registration: Not applicable.

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.

This work focuses on the global and partial identification problem for fractional differential equations. We provide a general numerical procedure based on global and local optimization algorithms with two refinements for biological systems that ensure solution positivity and homogeneous parameter units. The method is applied to a new fractional model of Dengue outbreak called the Fractional Homogeneous Nishiura (FHN) model, calibrated using data of newly infected people in Cape Verde. We show that our identification method yields a better fit between data and model solutions than previous approaches and that our FHN model captures the dynamics of Dengue more closely than existing systems.

Objectives: The aim of mammographic screening is the early detection of invasive cancers. In the era of artificial intelligence (AI), this tool may improve diagnosis of earlier stages. The purpose of this study was to assess the impact on selected quality indicators retrospectively. Method: The data source was the Breast Cancer Screening Registry using data from one Screening Unit that currently uses AI routinely. The indicators of the cancer detection rate (CDR), further assessment rate (FAR), and recall rate (RR) in the year 2023, when AI was used, and the year 2022, without AI, in women aged 45-69 were compared. The statistical evaluation used the chi-square test and logistic regression adjusting for the effects of age, a woman's risk level, and the screening round at a 5% significance level. Results: In 2022, without AI, 4,034 women aged 45-69 were included, compared with 4,049 women in 2023 when AI was used. This study showed a non-significant increase in CDR from 5.0 breast cancers detected per 1,000 women (non-AI assessment) to 5.2 (AI-assisted assessment), p = 0.919; OR (95% CI): 1.034 (0.542-1.974), a significant decrease in the FAR from 5.2% to 3.9%, p < 0.001; OR (95% CI): 0.665 (0.529-0.836), and a decrease in RR from 2.4% to 1.9%, p = 0.083; OR (95% CI): 0.754 (0.548-1.037). Conclusion: AI has the potential to be a useful tool in the early detection of breast cancer by improving quality through a decrease in FAR and RR, while probably maintaining CDR.

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.

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.

Currently, the genetic architecture of Middle Eastern populations is underrepresented in global genomic databases. This gap increases the rate of Variants of Uncertain Significance (VUSs) and clinical misinterpretations of genomic data especially in Middle Eastern populations. Whole exome sequencing was conducted on 90 healthy individuals from Jordan and the data were analysed using Principal Component Analysis (PCA) and multi-computational filtering. PCA revealed a double ancestry (EUR-AFR) admixture rather than a triple admixture (EUR-AFR-AMR). More than 3,500 populations-specific variants (PSVs) were identified, of which 72% were singletons. Additionally, 19 variants were significantly enriched compared to the maximum allele frequencies in public global databases (Fisher's exact test with Benjamini-Hochberg false discovery rate correction, p-value < 0.05). Consequently, the results suggest the reclassification of variants of Uncertain Significance (VUS) which reside in the ECE2 gene to likely benign and the variants of Conflicting Classification of Pathogenicity in the genes IL1RN and THPO to benign based on the significant allele frequency (AF=0.0389, p-value < 0.05). Furthermore, a pathogenic ClinVar variant was identified in a healthy individual, warranting careful interpretation. The findings underscore the importance of identifying PSVs in order to minimize or even prevent clinical misdiagnosis and highlight the unique genetic signature in Jordan. The study serves as a foundational resource for precision medicine in the region.

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.

Background: Traditional diagnostic models lack explainability, while multimodal language models prone to hallucination remain unsafe for medical education. An interactive, risk-free artificial intelligence framework is required to serve as a reliable clinical mentor for radiology trainees. Methods: We propose a multi-agent architecture decoupling deterministic image analysis from generative consultation. Specialized computer vision models perform anatomical localization and pathological segmentation. These quantitative outputs are synthesized into a structured payload, which grounds a locally hosted large language model (LLaVA 7B) using strict prompt guardrails and prerequisite protocols. Results: The system effectively eliminates visual hallucinations by intercepting unanchored queries. The artificial intelligence tutor successfully contextualizes spatial anomalies and baseline metrics, generating accurate conversational explanations and formally structured radiology reports while strictly enforcing medical safety disclaimers. Discussion and Conclusion: By anchoring language generation exclusively to verified algorithmic realities, this framework transforms opaque diagnostic models into safe, interactive educational simulators. This establishes a highly reliable paradigm for integrating explainable artificial intelligence into medical training.

Background. Cross-validation (CV) is widely used to estimate predictive performance, but can overestimate performance when applied at the observation level to repeated-measures data. When continuous predictor variables are measured repeatedly within subjects and the binary outcome is defined at the subject level, naive observation-level CV introduces data leakage through within-subject dependence, producing optimistically biased estimates of the area under the receiver operating characteristic curve (AUROC). The magnitude of this bias and the performance of alternative partitioning strategies have not been formally characterized for this data structure. Methods. Three CV strategies were compared for estimating subject-level AUROC in ridge logistic regression models: naive observation-level 10-fold CV, subject-level 10-fold CV, and leave-one-cluster-out (LOCO) CV. The framework was applied to a motivating clinical dataset of daily oxygenation measures and retinopathy of prematurity outcomes among 101 extremely low birth weight infants. A factorial simulation study was conducted across 162 parameter combinations varying cluster count (20-150), intraclass correlation (0.1-0.5), within-cluster autocorrelation (0.2-0.8), and outcome prevalence (10-35%), with 500 simulated datasets per condition (76,389 valid datasets total). Results. In the motivating dataset, naive CV produced optimism of +0.078 AUROC units for severe ROP prediction (15 events, 101 subjects) and +0.031 for any ROP prediction (48 events). Subject-level 10-fold CV closely approximated LOCO (deviation [&le;] 0.015). In the simulation, naive CV optimism ranged from +0.039 to +0.204 across all conditions, increasing monotonically with higher ICC, higher autocorrelation, fewer clusters, and lower event rates. Subject-level 10-fold CV was essentially unbiased relative to LOCO across all 162 conditions (mean absolute deviation = 0.002). Conclusions. Naive observation-level CV meaningfully overestimates discriminative performance in the repeated-measures binary outcome setting and should not be used. Subject-level CV partitioning effectively eliminates this bias. Accordingly, subject-level partitioning should be considered essential, not optional, when validating prediction models using repeated-measures data with subject-level outcomes.

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.

Objective To examine the effects of combined oral contraceptive (OC) use on clinical markers of ovarian reserve by comparing Anti-Muellerian Hormone (AMH), antral follicle count (AFC), and ovarian volume (OV) before and after starting or stopping OC. Methods This analysis is based on data from a prospective cohort study conducted at the University Hospital Tubingen, Germany, as part of the IRTG-2804 project. A total of 54 healthy women were included and categorized into three groups based on their OC use status: OC starters (n = 12), stoppers (n = 16), and long-term OC-users (n = 26). Each participant underwent a transvaginal ultrasound (including AFC and OV) and serum sampling (including AMH) at two time points (S1 and S2), three to six months apart. OC starters were assessed first during the early follicular phase (day 1-7) and then during active OC intake (day 8-21), while stoppers were assessed in the reverse order. Long-term users were assessed twice during active OC intake. Results OC stoppers showed significant within-group increases in all ovarian reserve markers, including AMH ({Delta} = 2.57 ng/mL, p < .001), AFC ({Delta} = 3.88, p = .004), and OV, which almost doubled (1.94-fold increase; 95% CI [1.35, 2.80], p < .001). In contrast, OC starters exhibited a significant decline in AMH ({Delta} = -1.25 ng/mL, p = .013), but no changes in AFC or OV. No significant longitudinal changes were observed among long-term OC users. Conclusion AMH levels decrease after starting OC use whereas AFC and OV are not affected. In contrast, AMH, AFC, and OV recover within three to six months after stopping OC, suggesting a reversible suppression of ovarian reserve markers during OC use. These findings are clinically relevant for fertility counseling and for the interpretation of ovarian reserve markers in women using hormonal contraception.

Introduction: The use of artificial intelligence (AI) by clinicians has increased rapidly in recent years, with large language models (LLMs) emerging as tools that can equal clinician diagnostic performance in simulated settings. However, limited data exist regarding physicians use of LLMs in real-world clinical practice. This study aimed to evaluate the frequency of LLM use among practicing hospitalists, identify which LLMs are most commonly utilized, and assess hospitalists' perceptions of the benefits and limitations of LLM use in clinical care. Methods: We conducted a cross-sectional survey study of academic hospital medicine faculty across 8 institutions within the Hospital Medicine Reengineering Network (HOMERuN), a collaborative research consortium. Eligible participants included hospitalists practicing within participating HOMERuN sites during the study period. The survey assessed the frequency of LLM use, types of LLMs used, clinical applications, and physician perceptions regarding usefulness, efficiency, and concerns associated with LLM adoption. Results: 170 respondents (67.1%) reported ever using an LLM in clinical practice. Among LLM users, OpenEvidence was the most used tool (88.9%), followed by ChatGPT (58.5%), Google Gemini (26.9%), and Microsoft Copilot (20.5%). Only a minority of hospitalists reported using LLMs daily while seeing patients. The most common use cases of LLMs were answering diagnostic (77.1%) and management (77.6%) questions. A majority also reported using LLMs to identify or summarize primary literature (60.0%). Lack of trust in outputs (49.8%), uncertainty around institutional policies (48.6%), and lack of access to secure applications (43.1%) were cited as the most frequent barriers to using LLMs in practice. Discussion: The use of LLMs in clinical practice is already widespread, though regular or daily use is not yet typical. Concerns regarding reliability, patient privacy, and safe integration into clinical workflows remain significant barriers to broader adoption. The responsible implementation of LLMs in hospital medicine will require addressing these barriers.