Citations

Background: Physical inactivity is highly prevalent among individuals with spinal cord injury (SCI), contributing to secondary health conditions and reduced quality of life (QOL). Objectives: To examine the independent associations between adherence to SCI cardiorespiratory fitness guidelines and health and psychosocial outcomes, while controlling for relevant covariates. Method: We conducted a multisite, cross-sectional study of adults with traumatic SCI stratified by self-reported leisure-time physical activity: no activity (28%), some activity (41%), and met guidelines (26%). Multivariable regression models analyzed associations between physical activity (PA) group and outcomes of hospitalization, self-perceived health, resilience (SCI-QOL Resilience), pain, depression (PHQ-8), QOL (SWLS), and social integration (CHART-SF). Results: The study included 361 participants (no activity, 28%; some activity, 41%; met guidelines, 26%). Meeting PA guidelines was associated with better self-perceived health (odds ratio [OR] 2.79, P < .001) and higher resilience (β = 1.78, P = .04) compared to the No Activity group. However, hospitalization risk was unexpectedly higher for both the Some Activity (risk ratio [RR] 1.93, P = .005) and Met Guidelines (RR 1.75, P = .03) groups. After adjusting for covariates, PA was not significantly associated with pain, depression, QOL, or social integration; instead, higher income was consistently associated with better outcomes in these domains. Conclusion: Adherence to SCI exercise guidelines is associated with enhanced self-perceived health and resilience. However, PA alone was not associated with broader psychosocial outcomes in this model, where socioeconomic factors such as income appeared to play a significant explanatory role.

Abstract INTRODUCTION Repetitive head impacts (RHI) from contact sports may cause a unique pattern of white matter hyperintensities (WMH) on T2‐weighted fluid‐attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI), termed RHI‐associated WMH (RHI‐WMH). These lesions are punctate, circular, and located at the gray–white matter boundary, an area vulnerable to trauma‐related damage. METHODS We investigated the association of RHI with these lesions in two aging cohorts: (1) former American football players versus asymptomatic unexposed men and (2) individuals with RHI from various contact sports versus non‐RHI participants. RHI‐WMH were assessed using visual ratings and a novel automated quantification pipeline. RESULTS Individuals with RHI had greater RHI‐WMH by both detection methods in both cohorts. RHI‐WMH were associated with plasma neurofilament light and p‐tau231, and flortaucipir positron emission tomography (PET) uptake. DISCUSSION RHI‐WMH may represent a new supportive biomarker for the detection of RHI‐related neuropathologies later in life.

Abstract Background: Accurate staging is essential for treatment selection, prognosis assessment, and trial eligibility. While prior studies attempted automating pathological (p) staging, few address clinical (c) staging and no studies have compared LLM-derived staging with clinician staging during clinical visit and retrospective cancer registry staging. Methods: We developed a multi-agent framework using Gemini-2.0-Flash-001 and GPT-5 to (1) identify reports (2) extract key data, and (3) apply AJCC 8th edition staging criteria. LLM staging was compared with clinician documentation and registry staging in breast cancer patients. Clinician-registry agreement served as the reference standard. Two independent breast oncologists reviewed discordant cases. Results: We analyzed 122 randomly selected breast cancer patients across all three Mayo Clinic sites from 2018 - 2023. LLM performance matched or exceeded human inter-rater agreement for pathological staging (95-99.2% vs. 95-98.4%). Clinical staging was more challenging, with LLM concordance of 73-77.9% for cT and 87-89.3% for cN versus 87.8% and 91.0% clinician-registry agreement. Among 89 patients with clinician-registry concordance, LLM concordance was 98.9% for pT/pN, 79.8% for cT, and 91.0% for cN. Experts favored LLM staging in 27.8% (5/18) of cT and 25.0% (2/8) of cN discordances. Error analysis revealed LLM challenges in handling non-mass enhancements (6 cases), selecting radiologic measurements (2 cases), identifying discrete masses (2 cases), and miscellaneous (3 cases). Conclusion: LLMs achieved human-level performance for pathological staging (98%), supporting human-in-the-loop deployment. For clinical staging (79.8% cT, 91.0% cN), future work must enhance multimodal reasoning and integrate physical examination data. Prospective validation is needed to assess real-world impact. With targeted refinements and oversight, automated staging can transform registry workflows while augmenting clinical decision-making. Citation Format: Arshad Mohammed, Umair Ayub, Pooja Advani, Shakeela W. Bahadur, Amye J. Tevaarwerk, Tufia C. Haddad, Elisabeth I. Heath, Brenda J. Ernst, Ben Zhou, Cui Tao, Sara J. Holton, Karthik V. Giridhar, Irbaz B. Riaz. Automating clinical and pathological staging for breast cancer patients [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 2744.

Abstract Objective Evaluate how RAG architecture, including corpus structure, retrieval strategy, and pipeline complexity, affects LLM-based medical problem solving and knowledge retrieval in sleep medicine. Materials and Methods We benchmarked four open-source LLMs (Llama-3-8B, Llama -3 -70B, Qwen 2.5-14B, and Qwen 2.5-235B) using a knowledge base of five sleep medicine textbooks. We compared performance across three dimensions: corpus structure (raw text vs table-of-contents aligned.), retrieval strategy (dense embedding vs hybrid sparse-dense), and pipeline complexity (baseline vs augmented). Evaluation metrics included board-style multiple choice question (MCQ) accuracy and clinical case vignette diagnostic ranking. Results RAG improved MCQ accuracy for all models. Llama-8B saw the largest gain of 10.6% (61.8% to 72.4%), while Qwen-235B reached 87.3%. In clinical cases, Llama-8B accuracy dropped by 7.1% when using raw text and dense retrieval due to context noise. This was corrected by using structured hybrid configurations. Hybrid retrieval consistently outperformed dense-only methods. Overall, structured corpora improved primary diagnosis accuracy by 6.1% on average, with Qwen-235B reaching a peak 10.2% increase. Discussion RAG effectiveness depends on the balance between model size and data structure. Large models handle uncurated text well, but smaller models are easily distracted by irrelevant data. Hybrid retrieval is necessary to maintain precision with specialized medical terms. A structured corpus paired with a baseline hybrid pipeline offers the best stability and speed for clinical use. Conclusion Rigorous data curation and hybrid retrieval are as essential as model scale for deploying safe, guideline-compliant AI in sleep medicine.

ABSTRACT Behavioral and social factors (BSFs) substantially influence the risk, onset, and progression of Alzheimer’s disease and related dementias (ADRD), yet BSF-related knowledge remains scattered across heterogeneous sources, posing critical challenges for data harmonization and evidence synthesis. To address this gap, we present the B ehavioral S ocial Data and Knowledge O ntology for AD RD (BSO-AD), a FAIR-compliant semantic resource for representing and harmonizing BSFs and ADRD-related knowledge. BSO-AD was developed following established ontology design principles with reuse of existing ontologies and controlled terminologies, including the Social Determinants of Health Ontology, Drug Repurposing-Oriented Alzheimer’s Disease Ontology, AD-Onto, ICD-9-CM, and ICD-10-CM. Relationships between BSFs and ADRD were derived through literature mining. BSO-AD contains 1,690 classes, 152 object properties, 49 data properties, and 40 annotation properties. Ontology evaluation through Hootation-based domain expert review and a scalable LLM-assisted ontology assessment framework demonstrated high domain coverage and strong semantic coherence. BSO-AD provides a semantic foundation for data harmonization and knowledge integration in BSF-related ADRD research, while the LLM-assisted evaluation framework supports scalable and automated ontology assessment.

Abstract Models that estimate the probability of an adverse clinical outcome require an operational cutoff to translate continuous estimated probabilities into discrete labels that can trigger clinical action. Although statistical methods identify ‘optimal’ cut-offs, threshold selection ultimately reflects value judgments regarding harm tolerance, resource allocation, and workflow feasibility. We describe a governance-informed approach to selecting a deployment threshold for an asthma exacerbation (AE) prediction model integrated into clinical workflows. Using prevalence-adjusted performance metrics and real-world provider capacity modeling, we evaluated multiple candidate thresholds and quantified downstream workload and missed-event trade-offs. We demonstrate that statistically optimal thresholds may produce operationally infeasible alert volumes or unacceptable miss rates. We propose a structured threshold governance framework integrating statistical performance, clinical utility, stakeholder input, and human oversight safeguards. This case illustrates how threshold decisions should be treated as organizational governance processes rather than purely technical optimizations.

Abstract AI-powered pathology foundation models provide general-purpose representations of histopathological images by encoding image tiles into numerical embeddings. However, these embeddings are not directly interpretable in biological or clinical terms and must be translated into biologically meaningful features, such as cell-type composition or gene expression, to enable downstream clinical applications. To bridge this gap, we developed STpath, a framework that integrates histopathology image embeddings derived from existing pathology foundation models with matched, spatially resolved transcriptomics data. STpath consists of cancer-specific XGBoost models trained to infer cell-type compositions and gene expression from histopathology image tiles. We evaluated STpath in colorectal and breast cancer datasets and showed that it provides accurate estimates of the composition of major cell types and the expression of a subset of genes, with further performance gains achieved by combining embeddings from multiple foundation models. Finally, we demonstrated that STpath inferred features that can be used in downstream studies to evaluate their associations with clinical outcomes.

Abstract Hypertensive disorders of pregnancy (HDP) are a leading cause of maternal and perinatal morbidity, yet modifiable environmental risk factors remain poorly characterized. Prior studies typically have only examined a limited number of exposures and have rarely distinguished HDP subtypes (ie, gestational hypertension, preeclampsia, eclampsia, and chronic hypertension with or without superimposed preeclampsia) or accounted for residential mobility during pregnancy. To address these gaps, we conducted a spatial and contextual exposome study of HDP using linked electronic health records (EHR) and vital statistics data in Florida. We analyzed 686 412 singleton pregnancies conceived between 2013 and 2018, using computable phenotyping to distinguish HDP subtypes. A total of 245 spatial and contextual exposome measures spanning natural, built, and social environments were linked to residential histories from conception through gestational week 19. Using a two-phase double machine learning (DML) framework with exposure-specific, directed acyclic graph-guided confounder adjustment, we conducted discovery and replication analyses, followed by multi-treatment DML to estimate effect sizes. In Phase 1, 26 exposome measures replicated for gestational hypertension and 34 for overall HDP. In Phase 2, 12 measures remained associated with gestational hypertension and 11 with overall HDP, including air toxicants, meteorological factors, ultraviolet radiation, neighborhood crime indicators, environmental noise, and proximity to coastline. No exposures passed multiple-comparison thresholds for preeclampsia or eclampsia. These findings demonstrate that the spatial and contextual exposome contributes to HDP in a subtype-specific manner. Integrating EHR-linked phenotyping, residential mobility, and causal machine-learning methods offers a scalable framework for identifying environmental factors relevant to HDP prevention.

Abstract Polycomb group (PcG) proteins form the Polycomb Repressive Complexes 1 and 2 (PRC1/2), which regulate gene expression through histone modifications. Their dysregulation is implicated in cancer. Genomic analysis of prostate cancer datasets revealed a striking divergence: PRC1 genes are frequently amplified in metastatic disease (SU2C), correlating with poor survival, higher tumor mutational burden (TMB), and enhanced androgen receptor (AR) signaling. In contrast, primary prostate cancer (PRAD) is characterized by recurrent deletion of the 3p13 locus, which harbors the gene for the non-canonical PRC1 subunit RYBP. Transcriptomic analysis indicated that RYBP loss derepresses gene expression, consistent with its role in transcriptional repression. Functionally, RYBP expression positively correlates with AR activity and negatively associates with neuroendocrine (NEPC) differentiation. Spatial and single-cell transcriptomics further show that RYBP is enriched in normal epithelial cells but downregulated in tumor cells. Besides, tumors with lower RYBP expression exhibit an immunosuppressive microenvironment, characterized by increased regulatory T cells. Collectively, these findings position RYBP deletion not only as a novel DNA-based biomarker for primary prostate cancer but also as a pivotal epigenetic deregulation event that coordinates oncogenic signaling and lineage plasticity.