Citations

Background: Large language models (LLMs) are increasingly used in patient-facing clinical applications, creating a need for scalable methods to evaluate the accuracy, safety, and appropriateness of their responses. Although physician review remains the reference standard, it is resource-intensive and difficult to scale. Objective: To develop and clinically validate an LLM-as-a-judge framework for evaluating responses to patients’ periprocedural questions. Methods: We retrospectively evaluated 1285 patient–AIVA interactions from 112 patients across two Mayo Clinic sites and multiple surgical specialties. Physician reviewers classified interactions using a predefined true-positive (TP), false-negative (FN), true-negative (TN), and false-positive (FP) framework. The finalized LLM judge independently evaluated the same interactions. Agreement was assessed using four-class and category-specific agreement, Cohen’s kappa, and a secondary binary analysis of response correctness. Results: Overall, four-class agreement was 93.1% (95% CI, 91.7–94.5%), with Cohen’s κ = 0.852 (95% CI, 0.823–0.882). Category-specific agreement was 94.1% for TP, 90.7% for FN, 95.5% for TN, and 84.9% for FP classifications. In the binary correctness analysis, accuracy was 93.4% (95% CI, 92.0–94.7%), sensitivity 94.6%, specificity 90.2%, precision 96.2%, and F1-score 0.954. McNemar’s test demonstrated no significant asymmetry between paired classifications (p = 0.11). Conclusions: A clinically grounded LLM judge closely approximated physician evaluation of patient-facing AI responses. These findings support its potential as a scalable assistive monitoring tool while preserving physician oversight for uncertain or safety-sensitive interactions.

BACKGROUND Acral lentiginous melanoma (ALM) is a biologically distinct, inherently aggressive, and understudied melanoma subtype without a unified surgical approach. OBJECTIVE To provide an updated review of ALM and offer practical, surgeon-focused guidance on diagnosis, biopsy, margin-controlled excision, and Mohs micrographic surgery (MMS)-based management of ALM. METHODS & MATERIALS A PubMed/MEDLINE search of ALM, with an emphasis on articles published after 2015. RESULTS ALM demonstrates inherent biological aggressiveness characterized by extensive subclinical spread, delayed diagnosis, and higher stage-adjusted recurrence compared with nonacral cutaneous melanomas. Anatomic constraints additionally necessitate specialized surgical approaches, although current management is extrapolated from nonacral melanoma data. Retrospective data support MMS and margin-controlled excision and tissue preservation in ALM, with the benefit of digit-sparing surgery and functional preservation. No randomized trials have included ALM, highlighting a key evidence gap. CONCLUSION Margin-controlled approaches such as MMS may improve local control and tissue preservation in select ALM patients. Prospective ALM-specific research and standardized diagnostic and surgical protocols are strongly needed.

Objective To evaluate the efficacy of cytokine‐directed therapies in VEXAS (vacuoles, E1 enzyme, X‐linked, autoinflammatory somatic) syndrome using previously proposed treatment response criteria. Methods All patients with genetically confirmed VEXAS syndrome who received targeted therapies with JAK inhibitors (JAKi), tumor necrosis factor α inhibitors (TNFαi), or interleukin‐1 (IL‐1) or IL‐6 inhibitors were identified. Clinical and biochemical data were recorded for patients at time of targeted therapy initiation, and at 3‐, 6‐, and 12‐month follow‐up time points. Treatment response was labeled as complete response (CR; normalization of C‐reactive protein [CRP], prednisone <10 mg/day, and resolution of disease activity), partial response (PR; >50% improvement in CRP, >50% prednisone dose reduction, improvement or resolution of disease features), treatment failure (TF; worsening CRP, increasing prednisone, worsening of disease features), or no response (not meeting criteria for CR, PR, or TF). Results Overall, 52 patients received an IL‐1i, IL‐6i, or JAKi therapy. At six‐month follow‐up, 3 of 19 IL‐6i patients experienced CR, 4 of 19 experienced PR, and 7 of 19 experienced TF. 2 of 17 patients receiving JAKi experienced CR, 3 of 17 experienced PR, and 6 of 17 experienced TF. No patients receiving IL‐1i or TNFαi experienced CR, and only 1 of 5 IL‐1i patients experienced PR. Among those still receiving biologic therapy at 12 months, only 1 of 11 receiving IL‐6i and 0 of 7 receiving JAKi experienced CR. Conclusion IL‐6i and JAKi therapies demonstrated limited, unsustained efficacy for management of VEXAS syndrome. IL‐1i and TNFαi therapies were not efficacious. Useful application of previously reported treatment response criteria was demonstrated, but future incorporation of hematologic parameters may be beneficial.

Antisense oligonucleotides (ASOs) represent a promising therapeutic modality for RNA-based disease mechanisms, but identifying high-efficacy candidates from large sequence spaces remains a major bottleneck in drug development. Here, we present ASOFormer, a novel Transformer-based neural network that predicts the inhibition efficiency of RNase H-mediated ASOs from sequence, predicted secondary structure, and chemical modification features. ASOFormer was trained on a knockdown efficacy dataset spanning over 170,000 ASO-target pairs compiled largely from published patents. Ablation analysis confirmed that the addition of chemical modification features to the primary sequence drove the largest performance gains, with predicted secondary structure providing complementary benefit when combined with modification information. Further analysis highlighted the importance of the wings of gapmer ASOs and other features. As independent validation, ASOFormer was applied to ASOs targeting seven genes that were not in the training dataset gene list. For four out of the seven genes, the ground truth ASO inhibition efficiency was obtained from a public dataset, whereas the others were measured in-house via qPCR. Compared to two published state-of-the-art methods, ASOFormer achieved the best overall accuracy and prioritized the strongest inhibitors. Crucially, only ASOFormer consistently exceeded random expectation for top-candidate recovery across all seven test genes.

Abstract Introduction Quantitative interpretation of pediatric brain [ 18 F]-FDG PET is limited by the lack of age-matched normative reference databases, despite substantial developmental variation in cerebral glucose metabolism. This study aimed to construct a large-scale normative pediatric [ 18 F]-FDG PET database and develop an age-specific z-score mapping framework for quantitative evaluation of pediatric epilepsy. Method Pediatric brain PET data were retrospectively derived from clinically acquired whole-body or dedicated [ 18 F]-FDG PET examinations in participants 0–19 years of age without neurologic disease or visible brain abnormalities. A total of 417 PET scans from 341 participants were stratified into five developmental age groups: infancy, early childhood, middle childhood/school age, adolescence, and late adolescence. SUVR maps were generated using whole-brain atlas and brainstem reference regions. Voxel-wise t-test analyses were performed to characterize age- and sex-related metabolic differences. Age-specific voxel-wise mean and standard deviation maps were generated from the normative cohort and used to calculate age-matched hypometabolic z-score maps in 14 pediatric patients with epilepsy. The resulting abnormalities were qualitatively evaluated for concordance with epileptogenic findings identified on clinical MRI and/or PET by expert image review. Results Voxel-wise analyses demonstrated prominent age-dependent SUVR differences, particularly between infancy and older age groups. With whole-brain atlas normalization, older children showed progressively higher relative SUVR in cortical and cerebellar gray matter regions, whereas infancy showed relatively higher SUVR in the occipital cortex, white matter, thalamus, and brainstem. Brainstem normalization produced distinct developmental patterns, emphasizing higher white matter SUVR in infancy and broader gray matter differences in older groups. Sex-related differences were limited and regionally specific. Whole-brain atlas normalization showed lower variability than brainstem normalization and was selected for z-score mapping. In representative epilepsy cases, age-matched z-score maps identified focal or regional hypometabolism corresponding to malformations of cortical development, focal cortical dysplasia, mesial temporal sclerosis, nonlesional MRI cases, remote insult, tumor-related abnormalities, and Sturge-Weber syndrome. Discussion A large-scale normative pediatric [18F]-FDG PET database can support developmentally appropriate quantitative interpretation of pediatric brain PET. Age-matched z-score mapping may complement visual assessment by highlighting abnormal cerebral glucose metabolism in pediatric epilepsy, although findings should be interpreted with MRI, EEG, seizure semiology, and other presurgical data.

ABSTRACT Extracellular vesicles (EVs) are membrane‐enclosed nanoparticles that mediate intercellular communication by transferring proteins, nucleic acids, and lipids. Within the hematopoietic system, EVs orchestrate critical signaling between bone marrow (BM) niche cells and hematopoietic stem and progenitor cells (HSPCs) to regulate quiescence, proliferation, and lineage commitment. During aging, senescence and telomere attrition drive a profound remodeling of EV biogenesis and cargo. Aged EVs, particularly those released from senescent mesenchymal stromal cells (MSCs) and osteoblasts, exhibit altered microRNA profiles and reduced protective antioxidants. These changes perpetuate niche dysfunction, induce senescence in recipient cells, and promote myeloid‐biased hematopoiesis. Importantly, this communication is a selective process governed by vesicle‐intrinsic surface signatures, such as tetraspanins and integrins, which interact with specific receptors on distinct hematopoietic subsets to regulate signaling fidelity. Conversely, EVs from young or pluripotent stem cells deliver rejuvenating signals that can restore aged HSPC function and attenuate inflammaging. Elucidating these mechanisms of selective targeting and stress‐responsive cargo remodeling provides vital insights for developing EV‐based diagnostic tools and rejuvenation strategies to prevent age‐related immune imbalances and hematologic malignancies.

Advanced-stage high grade serous ovarian cancer (HGSC) initially responds to platinum-based chemotherapy; however, most HGSC tumors recur and develop chemotherapy-resistance, making recurrent ovarian cancer (OC) a fatal disease. Ovarian cancer stem cells (OCSCs), a subpopulation of cells capable of surviving treatment and repopulating tumors, contribute to disease relapse, and understanding the mechanisms(s) responsible for OCSC survival is critical for developing strategies to overcome acquired resistance and prevent tumor recurrence. However, whether platinum-induced OCSC enrichment results from the selection of pre-existing OCSCs or chemotherapy-induced cellular plasticity, and the molecular mechanisms underlying these processes, remain poorly understood. Here, we demonstrated that cisplatin treatment not only enriched for OCSCs but promoted the conversion of ALDH- cells to ALDH+ cells, revealing chemotherapy-induced plasticity as a potential mechanism for OCSC expansion. This conversion was associated with nuclear receptor signaling pathways, vitamin D receptor signaling (VDR/RXR) and retinoic acid receptor signaling (RAR/RXR). Importantly, activation of VDR/RXR signaling with vitamin D reduced stemness phenotypes and the cisplatin induced conversion to ALDH+ cells. In addition, vitamin D combined with cisplatin decreased tumor volume in vivo compared to either treatment alone. In contrast, cisplatin treatment increased RAR/RXR signaling, supporting an associative role for ligand-dependent nuclear receptor signaling in OCSC plasticity. Together, these findings reveal that platinum chemotherapy can actively promote the acquisition of stem-like properties and identifies VDR/RXR signaling as a potential regulatory mechanism of OCSC plasticity. Targeting this pathway with vitamin D may provide a therapeutic strategy to target OCSCs and improve responses to platinum-based chemotherapy.

Abstract Post-traumatic headache (PTH) is the most common consequence of mild traumatic brain injury (mTBI) and often resembles migraine. In 20% to 30% of migraine patients, headaches are preceded by aura, transient visual or sensory disturbances, which are caused by cortical spreading depression (CSD) that can induce headache pain. However, whether mTBI promotes the development of aura and CSD and their possible contributions to PTH remains unclear. We examined the incidence of new-onset aura in individuals with PTH who had no history of aura. Thirty-two percent (35/108) developed new aura symptoms within 60 days of injury, suggesting that mTBI can sensitize the cortex to the induction of CSD. To test this, we combined electrophysiology, neuroimaging, and behavioral assays in a mouse model of mTBI-induced PTH. After closed-head mTBI, injured mice exhibited a 160% increase in CSD induction probability (ie, lowered threshold) and became sensitized to CSD induction by brief exposure to stress, a common headache trigger. When evoked optogenetically, CSD produced prolonged periorbital and hind paw allodynia, consistent with headache-like pain. Subcutaneous onabotulinumtoxinA administered to the scalp after mTBI did not alter CSD susceptibility but completely abolished optogenetic CSD-induced allodynia. These findings suggest that mTBI elicits sensitization to CSD induction and promotes the emergence of aura in humans, likely contributing to PTH. It is important that, even after mTBI-induced sensitization, onabotulinumtoxinA decoupled CSD from pain behaviors, suggesting efficacy in treating PTH associated with aura.