Citations

Abstract Rationale In fungal endemic regions, differentiating benign from malignant pulmonary nodules on CT scans remains a major diagnostic challenge. Coccidioides nodules frequently resemble malignant lesions on CT and PET imaging, presenting significant challenges for differentiation, even among radiologists. Consequently, the benign biopsy and resection rate, especially in the Southwestern US, remains high. We previously developed [DOI:10.1371/journal.pone.0196910] and externally validated [DOI:10.1183/13993003.02485-2020] the Benign versus aggRessive nODule Evaluation using Radiomic Stratification (BRODERS) machine learning (ML) classifier to non-invasively distinguish between benign and malignant pulmonary nodules with an AUC of 0.87. However, its performance in certain benign nodules with malignant surface and texture characteristics like in coccidioidomycosis had a suboptimal AUC of 0.65. In this study, we redesigned our radiomics model by including numerous clinical features. Methods In this retrospective study, 113 pulmonary nodules (66 Coccidioides and 47 adenocarcinoma spectrum) detected on CTs with ground truth pathology diagnosis were identified by screening for key terms like “nodule”, “cocci”, and “adenocarcinoma” from both CT and pathology reports using a large language model trained on clinical textual data (Illuminate®). Clinical features such as demographics, smoking history, and laboratory studies were extracted by trained clinicians from the electronic medical record. All nodules were segmented and radiomic features extracted using a semi-automated seed growing algorithm previously described [DOI: 10.1097/JTO.0b013e3182843721]. The database was randomly split into an 80%-20% development and hold-out set prior to ML modeling. Feature selection for variables was conducted utilizing Elastic Net Regression, which provides a balanced approach between Lasso and Ridge regression. A logistic regression model was developed using the selected features and ground truth information of the training cohort. The true performance of the model was tested on the hold-out set. Results 160 radiomics and 22 clinical features were extracted. Elastic Net regression identified 44 features that contributed the most. Some of these clinical features include presence of satellite lesions, smoking history, and presence of positive IgG coccidiomycosis serology. The AUC of the ROC curve for the hold-out test set was 0.86. Conclusions The clinical features of significance that emerged during multimodal modeling are explainable. Designing explainable ML models is important, especially in the Southwestern US where Coccidioides nodules can appear to be malignant to both human experts and ML models. Although coccidioidomycosis serologies alone lack sensitivity and specificity to diagnose Coccidioides nodules, integrating them with a multimodal ML model can improve differentiation between benign Coccidioides and malignant adenocarcinoma nodules. This abstract is funded by: None

Abstract Rationale Advances in bronchoscopic technology, including robotic-assisted bronchoscopy (RaB) and cone-beam CT (CBCT), have enabled biopsy of multiple nodules in a single procedure. Here we present the procedural characteristics, safety, diagnostic yield, and use of linear endobronchial ultrasound (EBUS) staging in patients with multifocal pulmonary nodules biopsied under a single anesthesia event. Methods This multi-center, retrospective observational study included adults undergoing RaB biopsy of multifocal peripheral pulmonary lesions and lymph node assessment under a single anesthesia event at six U.S. centers from 11/2019 - 8/2025. Procedures utilized either the Ion (Intuitive) or Monarch (Ethicon) systems under general anesthesia. De-identified demographic, radiologic, procedural, pathologic, and safety data were collected in a secure centralized database. Safety outcomes included pneumothorax and its sequelae, hypoxia, and infectious complications. Diagnostic yield was determined using the 2024 ATS/ACCP consensus statement. NGS adequacy was reported from two health systems with well-defined criteria for sufficiency and standard institutional practices for sending NGS testing on both nodules. Statistical analyses utilized included descriptive statistics, t-tests, chi-squared/Fisher’s tests where appropriate, and logistic regression. Results Among 191 patients, 177 underwent biopsy of two and 14 of three nodules. Lymph nodes were sampled in 167 (87.4%), with 18 (10.8%) positive for malignancy; notably, 17 of 18 (94%) patients with nodal metastases had at least one fully solid nodule. Complications occurred in 20 patients (10.5%), including pneumothorax in 14 (7.3%), with 4 (2.1%) requiring tube thoracostomy. There were no cases of bilateral pneumothorax. Transient hypoxia occurred in 3 patients (1.6%) and 3 developed outpatient-managed bronchitis. Seven patients (3.7%) required unplanned admission. Overall diagnostic yield was 72.2%, with 122 (63.9%) patients having two diagnostic nodules and 33 (17.4%) having two non-diagnostic nodules. Bronchus sign (OR 2.9, p = 0.003), radial EBUS use (OR 2.6, p = 0.025), and CBCT use (OR 2.4, p = 0.021) were associated with procedures having two diagnostic nodules. At sites with standardized NGS adequacy reporting, 74 of 81 malignant nodules (91%) provided sufficient tissue for NGS. Conclusions •Single-procedure biopsy of multifocal pulmonary nodules is feasible, safe, and achieves industry-standard strict diagnostic yield. •Complications are slightly higher than single-nodule procedures. Serious events were rare. •17 of 18 patients with malignant nodal disease had at least one fully solid nodule; no patients with two pure ground glass nodules had nodal metastasis. •NGS testing was feasible and adequate on the majority of samples, aiding clinicians in staging multifocal nodules. This abstract is funded by: None

Abstract Introduction Large Language Models (LLMs) have proven effective at analyzing unstructured and structured data from electronic health records (EHR). Their reliance on static EHR data means they miss the dynamic, high-resolution physiological signals that are the first indicators of patient decline, creating a fundamental data lag as clinical documentation of an event may occur hours after its onset. This represents a critical gap in the ability to develop truly effective triage tools. Furthermore, while LLMs can synthesize multi-source data for acuity assessment, they exhibit known limitations, including hallucinations that constrain autonomous use in safety-critical settings. In contrast, a Vision-Language Model (VLM) with strong image-grounded clinical reasoning can interpret vital sign trend images, surpassing the limitations of current EHR-based models. This approach provides immediate triage evaluations that lead to earlier detection of patient deterioration. Methods This mixed-methods study deployed a VLM (Gemini 2.5) integrated within the eICU dashboard. We used near-real-time two-hour trends in heart rate, blood pressure, respiratory rate, and oxygen saturation from consecutive patient cases during alerts in hospital floor units monitored by eICU that admit acute medical and surgical patients. To increase the diversity of the sample, we sought routine cases from patients without alerts and emergent cases from patients admitted to the medical, surgical, trauma, and mixed ICUs. A structured context prompt was used to generate a standardized summary including clinical interpretation, data quality and artifact assessment, triage recommendation, and the model’s chain-of-thought reasoning. Results We included patients from Mayo Clinic Rochester, MN, using an 800-patient cohort for prompt development and a 100-patient cohort for validation against clinically adjudicated results. In the validation cohort the VLM achieved 80% accuracy (80/100). An analysis of the 20 incorrect predictions revealed a clear pattern of conservative over-triage: 80% (16/20) of errors were clinically acceptable adjacent-class discrepancies (routine↔urgent or urgent↔emergent). Only 4/20 discrepancies represented a substantive misclassification. Most errors therefore reflected conservative prioritization rather than incorrect assessment. The model demonstrated a perfect safety profile, underestimating patient acuity in 0% of cases, and thus avoiding the most clinically dangerous error. These results confirm the feasibility of VLM-based approach and provide a strong foundation for the proposed work. Conclusion This VLM performs cross-modal reasoning by fusing deep visual perception with broad clinical context. The result is a fully contextualized and explainable triage prioritization, which provides direct decision support and integrates into the clinical workflow, allowing for faster and more confident acute care assessments. This abstract is funded by: none

Abstract Rationale Interstitial lung disease (ILD) affects ∼50% of patients with systemic sclerosis (SSc) and is a leading cause of mortality. Visual assessment of ILD extent and morphologies, including ground-glass opacities (GGO) and reticular densities (RD), suffers from poor interobserver agreement, limiting prognostic consistency. CALIPER Quantitative CT (QCT) provides reproducible volumetric measures of parenchymal and vascular features. This study evaluated baseline QCT-derived lung features for association with transplant/mortality risk in SSc-ILD. Methods A retrospective cohort of SSc patients (≥18 years) seen at an academic center from 2007-2018 was identified using ICD codes, with ACR/EULAR 2013 SSc criteria confirmed by chart review. Inclusion required ILD on high-resolution CT (HRCT) ±2 years of SSc diagnosis, and PFTs ±6 months of HRCT. CALIPER quantified volumes of normal lung, GGO, RD, hyperlucency, honeycombing (HC), and pulmonary vascular-related structures (PVRS), which are expressed as percentages of total lung volume. Right heart catheterization confirmed pulmonary hypertension (PH) defined by 2022 ESC/ERS criteria (Eur Heart J, 2022). Cox hazards models assessed associations with combined mortality/transplant outcome, a priori adjusted for age, sex, diffuse SSc subtype, ILD duration, and PH (Column B), and further adjusted for baseline percent predicted FVC (ppFVC) and ppDLCO (Column C)(Table 1). Results Of 132 SSc-ILD patients, median SSc and ILD disease durations at HRCT were 1.4 (0.6, 2.4) and 0.0 (0.0, 0.5) years. Median feature percentages: total ILD 13.0% (IQR: 6.4, 21.0), GGO 10.2% (4.6, 16.9), RD 1.9% (0.8, 3.7), HC 0.03% (0.00, 0.09), PVRS 3.2% (2.3, 4.1). Median ppFVC was 81.1% (69.4, 92.6), and ppDLCO 60.0% (46.0, 75.7); 21 patients had PH. There were 2 transplants and 45 deaths. Every 5% increase in baseline total ILD and GGO associated with 22% (HR 1.22; 95% CI 1.12-1.33) and 24% (1.24; 1.12-1.36) higher risk of transplant/mortality on unadjusted models (Column A), respectively, remaining significant after a priori (CB) and full adjustment (CC)(Table 1). Every 1% increase in RD and PVRS conferred 19% (1.19; 1.08-1.31) and 33% (1.33; 1.08-1.63) higher risk of transplant/mortality in unadjusted models (CA); RD retained significance after a priori adjustment (1.17; 1.03-1.33), while PVRS trended non-significant in adjusted models. Conclusions In early SSc-ILD, QCT-derived GGO, RD, and PVRS provide robust prognostic value for mortality/transplant risk assessment, with small increases in baseline severity—at or below visual detection thresholds—associating with clinically meaningful risk increases. These findings support integrating baseline QCT biomarkers into risk stratification beyond clinical and PFT measures. This abstract is funded by: Rheumatology Research Foundation

Abstract Background Meningiomas exhibit clinical heterogeneity. Radiotherapy (RT) remains the only adjuvant therapy, but tumor-control is variable, and biomarkers are limited. NRG/RTOG-0539 is the first prospective phase 2 trial to stratify meningioma patients for adjuvant RT based on clinical risk. Here, we apply modern molecular tools to this cohort and identify correlates of RT response. Methods Tumor tissue from 100 RTOG-0539 patients was profiled using DNA methylation arrays, RNA sequencing, and whole-exome sequencing. Recurrence scores, Molecular Groups, gene expression, and copy number alterations were compared across clinical groups and between RT responders and non-responders; non-response was defined as progression or death within 3 years. Results Modern grading criteria, including brain invasion, TERT mutation, CDKN2A/B deletion, and 1p/1q status, would reclassify 10% of tumors and alter treatment group assignment in 7%. Non-responders to RT exhibited more frequent 1p and 14q loss, and more copy number alterations. Transcriptomic and epigenetic profiling revealed immune-related signatures in responders and cell cycle–related pathways in non-responders, several of which overlapped with targets of vorinostat, a histone deacetylase inhibitor previously validated in aggressive meningioma models. The Proliferative Molecular Group was an independent predictor of post-RT recurrence in multivariable analysis, outperforming WHO grade. Conclusion Multi-omic analysis of the NRG/RTOG-0539 cohort shows that updated WHO grading criteria, incorporating molecular and cytogenetic features, improve risk stratification. However, molecular classification, particularly the Proliferative group, remains an independent and stronger predictor of RT response. These findings support integrating molecular biomarkers alongside modern grading frameworks to guide treatment and trial design in meningioma. Clinical Trial Information NCT00895622.

The NCCN Guidelines for Prostate Cancer include recommendations for staging and risk assessment after a prostate cancer diagnosis and for the care of patients with localized, regional, recurrent, and metastatic disease. These NCCN Guidelines Insights summarize the panel’s discussions on select 2026 updates to the guidelines regarding nonmetastatic disease: the elimination of the very-low-risk group, updates to the Principles of Active Surveillance, and caution in the use of focal therapy in newly diagnosed patients.

Abstract Rationale Dyspnea is a prominent symptom of fibrotic hypersensitivity pneumonitis (fHP), limiting patients’ activity and impairing their quality of life. The University of California San Diego Shortness of Breath questionnaire (UCSD-SOBQ) is a 24-item instrument used to assess dyspnea severity in patients with various respiratory conditions. Objectives This study aimed to examine the reliability and responsiveness of the UCSD-SOBQ score, its validity as a measure of dyspnea severity, and its prognostic value in a prospective cohort with fHP. Methods We conducted psychometric analyses on UCSD-SOBQ response data and assessed the association between score changes and survival in patients with fHP who completed the UCSD-SOBQ and other HP severity metrics at baseline, 6 and 12 months. We introduce the reliable change index (RCI) and the likely change index (LCI) to assess the statistical significance of within-individual change in UCSD scores. Results At baseline, internal consistency was high (Cronbach’s alpha = 0.97). Significant moderately strong correlations were observed between UCSD-SOBQ scores and percent predicted forced vital capacity (FVC%), r = -0.46, percent predicted diffusing capacity of the lung for carbon monoxide (DLCO%), r = -0.32, and Borg dyspnea scores r = 0.56. UCSD-SOBQ scores were significantly different between the lowest and highest strata of FVC% (64.9 ± 18.9 vs. 36.2 ± 22.9), DLCO% and Borg scores. The threshold for worsening within-individual change in the UCSD-SOBQ score at 95% confidence was 12 points. A 1-point higher baseline UCSD-SOBQ score was associated with a 2% increase in the risk of death or transplant (HR 1.02, 95% CI 1.00, 1.04). Conclusions In fHP, the UCSD-SOBQ score is a reliable and valid measure of dyspnea severity, is responsive to change, discriminates patients with differing severities, and is associated with transplant free survival. Additional qualitative data and psychometric analyses could tailor the UCSD-SOBQ to fHP and may further improve its measurement properties.

Abstract Rationale Quantitative CT using multiple instance learning (MIL)-usual interstitial pneumonia (UIP) classifier and data-driven textural analysis (DTA) provides objective and reproducible measurements of disease pattern and extent, respectively. However, the understanding of their individual or combined relationships with outcomes in fibrotic hypersensitivity pneumonitis (fHP) remains limited. Objectives To determine whether visual CT patterns of fHP or UIP, a MIL-UIP classifier, baseline and changes in DTA over 12-months and DTA at 12 months are associated with progression-free survival (PFS) in fHP. Methods The primary cohort included 134 participants with fHP. Associations between CT variables and subsequent lung function change, and PFS were assessed using linear mixed models and Cox hazards models. Results were validated in a combined dataset from three independent populations (N = 216). Results Visual patterns of fHP or UIP were not associated with PFS. A baseline MIL-UIP classification and DTA were significantly associated with 24-month PFS. However, the MIL-UIP did not predict PFS after adjusting for DTA fibrosis extent. Over 12 months, a 1-point increase in DTA across and within patients resulted in a significant decline in FVC% and DLCO%. A 12-month change in DTA (HR = 1.07, 95%CI 1.01-1.13) and DTA at 12-months (HR = 1.03, 95%CI 1.01-1.05) were associated with subsequent 12-month PFS. Similar estimates were observed in the validation cohort. Conclusions In fHP, the objectively measured extent of lung fibrosis is more prognostic than either a UIP classifier or visual CT patterns of fHP or UIP. Baseline DTA, DTA at 12 months, and its change over 12-months are associated with PFS.

Introduction: Inflammatory bowel disease is characterized by remitting and relapsing bouts of intestinal inflammation accompanied by sensory and motor dysfunction that persists beyond the active periods of inflammation. Evidence suggests that neural pathways of the Gut-Brain Axis, particularly the sensory and sympathetic nervous system, are involved in pathophysiology, but until recently technical restrictions have limited our understanding of the underlying neural circuit mechanisms. In this study, we examined how sensory-sympathetic circuits are modified by colitis and how these alterations contribute to dysfunction during both active inflammation and post-inflammatory recovery. Methods: E2a-GCaMP mice were treated with vehicle or 3% dextran sodium sulfate (DSS) for 5 days to induce experimental colitis and switched to normal drinking water. Mice were assessed at two time points: Day 7 (two days after ending DSS treatment), representing active inflammation, and Day 21 to represent recovery. Inflammation and mucosal damage were evaluated using disease activity index scores and hematoxylin and eosin (H&E) staining. Colon motility was assessed in vivo via colonic bead expulsion and ex vivo using whole-colon preparations. We performed Ca 2+ imaging of sympathetic motor neurons in prevertebral ganglia (PVG) and sensory neurons in dorsal root ganglia (DRG) neurons in ex vivo preparations that preserve extrinsic neural circuitry with the colon (intestinofugal-sympathetic and spinal cord-sympathetic pathways). Results: Histological analysis confirmed hallmark features of colitis, including colon shortening, immune infiltration, and mucosal damage at 7 days post-DSS (p< 0.05, n=3–4), which resolved after recovery. During active inflammation, in vivo colon transit time was significantly faster, and this persisted after recovery (p< 0.05, n=7-9). Ex vivo motility assays in isolated colons also revealed DSS-induced dysmotility during active inflammation, but the irregular colon motor complexes became normal after recovery (p< 0.05, n=7-9), suggesting that extrinsic neural pathways contribute to prolonged dysmotility. In preparations without the spinal cord, PVG neurons exhibited increased activity and increased responses to distension during active inflammation but returned to baseline after recovery (p< 0.05, n=3-4), suggesting alternative sensory-PVG pathways contribute to persistent dysmotility. In preparations with spinal circuits intact, thoracolumbar (TL), but not lumbosacral (LS), DRG sensory neurons were hypersensitive to colonic distension during inflammation (p< 0.05, n=8-9). Furthermore, TL spinal stimulation evoked more responses in PVG neurons during active inflammation, but this was associated with decreased inhibition of ENS motor circuits (p< 0.05, n=6-7) and increased Ca 2+ signaling in the epithelium (p< 0.05, n=5), suggesting shifts in TL spinal-sympathetic motor output. Preliminary studies show an increase in spontaneous activity of TL DRG neurons in recovery that does not occur at LS levels (p< 0.05, n=3-6), which suggests that thoracolumbar spinal pathways remain hyperexcitable after recovery.Conclusions: Our findings indicate that TL spinal pathways associated with sympathetic motor outflow contribute to pain and dysmotility during active inflammation and may contribute to the post-inflammatory recovery processes that seem to go awry in IBD patients with relapsing inflammation. This abstract was presented at the American Physiology Summit 2026 and is only available in HTML format. There is no downloadable file or PDF version. The Physiology editorial board was not involved in the peer review process.

ABSTRACT Background Interpretation of urodynamic studies (UDS) is central to diagnosing lower urinary tract dysfunction, but it is often complex, time‐consuming, and subject to interobserver variability. Recent advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), have enabled automated analysis of multichannel pressure–flow data and may improve objectivity and efficiency in UDS interpretation. Objective To critically review current applications of ML and DL for interpretation of multichannel UDS data and to evaluate their performance, clinical targets, and limitations. Methods A literature search of PubMed, Scopus, and Web of Science was performed through September 2, 2025, without language or date restrictions. A narrative review was conducted of peer‐reviewed studies applying ML or DL techniques to invasive UDS signals, including vesical, abdominal, and detrusor pressures as well as urinary flow. Studies limited to uroflowmetry or non‐UDS inputs were excluded. Model design, input features, validation strategies, and clinical outcomes were systematically assessed. Results A total of 12 studies met inclusion criteria. AI models were applied to a range of UDS tasks, including detection of detrusor overactivity, classification of bladder outlet obstruction and detrusor underactivity, multi‐feature UDS pattern recognition, severity grading, and real‐time event detection. Reported diagnostic performance was generally high, with many models achieving accuracies or AUCs between 80% and 95% for primary outcomes. However, study designs were heterogeneous, most datasets were retrospective and single‐center, and external validation was limited. Conclusions ML and DL approaches can extract clinically meaningful information from multichannel UDS recordings and demonstrate strong technical performance across several diagnostic tasks. However, variability in methodology, limited generalizability, and lack of prospective validation currently limit clinical adoption. AI‐based UDS interpretation remains an emerging research area requiring standardized data, robust validation, and integration with clinical workflows.