Citations

OBJECTIVE Ruptured, large pediatric arteriovenous malformations (AVMs) pose a significant management challenge due to high rerupture risk and the morbidity of conventional treatments. Volume-staged stereotactic radiosurgery (VS-SRS) has emerged as an alternative; however, evidence for its use in this specific population is limited. This study aimed to evaluate the long-term efficacy and safety of VS-SRS for ruptured, large AVMs in a dedicated pediatric cohort. METHODS This international, multicenter, retrospective cohort study from 21 centers analyzed outcomes for 42 pediatric patients (age < 18 years) with previously ruptured, large AVMs treated with VS-SRS. The primary outcome was complete AVM obliteration, and secondary outcomes included post-SRS hemorrhage, radiation-induced changes (RICs), and favorable outcome. Favorable outcome in this study was defined as obliteration without post-SRS hemorrhage or permanent RIC. RESULTS At the initial SRS, the median patient age was 14.5 years, and the median AVM volume was 15.0 cm 3 ; most AVMs were high grade (Spetzler-Martin grades IV and V). With a median follow-up of 41.5 months, complete AVM obliteration was achieved in 21 patients (50.0%). The cumulative obliteration rate was 37% at 5 years and 56% at 10 years. Patients with a nidus volume of ≤ 10 cm 3 had significantly higher cumulative obliteration rates than those with a nidus volume > 10 cm 3 (log-rank test, p = 0.021). Similarly, patients treated with a prescription dose > 17 Gy showed significantly higher cumulative obliteration rates compared to those treated with a dose ≤ 17 Gy (log-rank test, p = 0.012). The cumulative 5-year incidences of hemorrhage and RICs following VS-SRS were 19% and 7%, respectively. In multivariable analysis, only larger total AVM volume was an independent predictor of a lower likelihood of favorable outcome (hazard ratio 0.89, 95% CI 0.80–0.99; p = 0.036). CONCLUSIONS In this multicenter pediatric cohort, VS-SRS for ruptured, large AVMs provides a reasonable chance of long-term obliteration, but generally acceptable risks of post-SRS hemorrhage and RICs exist. VS-SRS should be considered as an option for pediatric patients with large, ruptured AVMs.

As machine learning (ML)-based decision support tools proliferate in clinical practice, understanding how clinicians integrate personalized ML predictions alongside randomized controlled trial (RCT) evidence is critical. We designed a web-based clinical decision support system (CDSS) presenting survival and adverse event data from a simulated RCT and ML model across 12 synthetic multiple myeloma scenarios. In a within-subjects study with 32 physicians, we evaluated how clinicians synthesize competing evidence sources to make treatment decisions. When ML and RCT outputs were concordant, physicians reported greater confidence than with RCT data alone. When results were discordant, most physicians shifted toward the ML-supported treatment, often before reviewing any information about model training or validation, suggesting a tendency toward automation bias rather than algorithm avoidance. Despite reporting higher perceived reliability after viewing model quality disclosures, physicians were largely unable to describe the validation procedures they had reviewed. Taken together, these findings reveal that clinicians may over-rely on ML recommendations even when equipped with tools designed to support critical appraisal. We discuss implications for CDSS design, clinician training, and the institutional safeguards needed before ML-based systems are deployed in high-stakes oncology settings.

ABSTRACT Background : Tirofiban is a GP IIb/IIIa inhibitor, an anti‐platelet drug that is used in ischemic stroke or acute coronary syndromes. The goal of this study is to assess the safety and efficacy of the drug in patients who have suffered an acute ischemic stroke. Methods : A comprehensive search of PubMed, Embase, the Cochrane Library, and ClinicalTrials.gov from inception to December 2025 yielded randomized controlled trials (RCTs) comparing Tirofiban and conventional management in patients with acute ischemic stroke. We assessed the risk of bias using the revised Cochrane “Risk of bias” tool for randomized trials (RoB 2.0). We analyzed the outcomes using RevMan 5.4, with risk ratio (RR) as the effect measure. Results : A total of 9 RCTs with 4210 patients were included in our meta‐analysis. According to our meta‐analysis, the tirofiban group was associated with a statistically significant increase in the patients showing functional independence at 90 days, measured by patients with Modified Rankin Score (mRS) of 0–2 (RR 1.13; CI = 1.06–1.20) and excellent outcome (mRS score 0–1) at 90 days (RR 1.17; CI = 1.05–1.29). We found no statistically significant difference between the two groups regarding mortality (RR 0.94; CI = 0.63–1.40). The tirofiban group had an increased incidence of intracranial hemorrhage (ICH) (RR 1.25; CI = 1.06–1.47) but had a similar incidence of symptomatic ICH as compared to the control group (RR 1.48; CI = 0.98–2.24). Conclusion : This meta‐analysis suggests that tirofiban may improve favorable functional outcomes (mRS 0–2) in acute ischemic stroke, although the certainty of evidence was moderate. While no significant increase in sICH was observed, some analyses showed a higher rate of overall intracranial hemorrhage. These findings should therefore be interpreted cautiously, and further high‐quality randomized trials are needed to confirm the efficacy and safety of tirofiban before routine guideline use.

e20139 Background: Extensive-stage small cell lung cancer (ES-SCLC) frequently presents with brain metastases, affecting approximately 20% of the patients at diagnosis. The prognostic impact of baseline brain metastases on survival outcomes in patients treated with contemporary chemo-immunotherapy remains unclear, creating uncertainty in first-line treatment selection for this high-risk population. We conducted a systematic review and meta-analysis to evaluate the impact of baseline brain metastases on treatment outcomes in ES-SCLC. Methods: This PRISMA-compliant systematic review and meta-analysis was prospectively registered in PROSPERO. PubMed, Embase, Cochrane CENTRAL, and ClinicalTrials.gov were systematically searched from database inception through January 2026 to identify randomized controlled trials evaluating PD-1/PD-L1-based chemo-immunotherapy versus platinum-etoposide chemotherapy in adults with ES-SCLC. Two reviewers independently screened studies and extracted data, with discrepancies resolved by consensus. Hazard ratios (HRs) for overall survival (OS) and progression-free survival (PFS) were pooled separately for patients with baseline brain metastases (BM+) and without brain metastases (BM−) using random-effects models with Hartung–Knapp adjustment. Analyses were performed using R. Prespecified subgroup analyses were conducted based on follow-up duration and immunotherapy regimen. Results: Twelve randomized controlled trials were included. Among patients with baseline brain metastases (BM+), pooled OS from seven studies did not show a significant survival benefit (HR 0.84, 95% CI 0.66–1.08, I² = 0.0%, P = 0.145), nor did pooled PFS from five studies (HR 1.03, 95% CI 0.60–1.79, I² = 0.0%). Subgroup analyses revealed no significant heterogeneity. In contrast, among patients without baseline brain metastases (BM−), pooled OS from nine studies demonstrated a significant survival benefit (HR 0.72, 95% CI 0.69–0.76, I² = 0.0%, P < 0.001), with corresponding improvement in PFS (HR 0.70, 95% CI 0.60–0.82, I² = 0.0%). These findings indicate a differential treatment effect according to baseline brain metastasis status. Conclusions: First-line chemo-immunotherapy does not apprear to confer a significant survival benefit in ES-SCLC patients with baseline brain metastases, reflecting a differential treatment effect by brain metastasis status. These findings suggest that baseline brain metastases should be considered in treatment selection and future clinical trial design and highlight the need for optimized systemic strategies for this high-risk population.

e18607 Background: Progression to myelofibrosis (MF) is associated with worse survival and influences treatment decisions, yet predictors of fibrotic progression in polycythemia vera (PV) and essential thrombocythemia (ET) remain poorly characterized. Methods: Patients with pathologically confirmed PV or ET were identified from a retrospective chart review. Demographics (age, sex, race, ethnicity), clinical features (thrombosis and bleeding history, performance status, symptom burden, organomegaly), bone marrow pathology (cellularity, trilineage hematopoiesis, megakaryocyte proliferation and atypia, fibrosis grade), molecular markers ( JAK2 , CALR , MPL , ASXL1 , EZH2 , TET2 , SRSF2 , IDH1/2 , SF3B1 , TP53 ), cytogenetics, laboratory values, and treatment history (phlebotomy, hydroxyurea, interferon, ruxolitinib) at first bone marrow biopsy were recorded. MF progression was defined as hematologist-confirmed transformation to MF. Kaplan-Meier analyses estimated median MF-free survival (MFS), defined as time to MF progression or death. Univariable followed by multivariable Cox proportional regression were performed to identify candidate MFS predictors. The proportional hazards assumption was assessed using Schoenfeld residuals. Hazard ratios (HR) with 95% confidence intervals (CI) were computed, with p<0.05 indicating statistical significance. Results: A total of 505 PV and 198 ET patients were identified. The majority were White (PV: 92%; ET: 86%). PV patients were predominantly male (54%) whereas ET patients were predominantly female (66%). MF progression occurred in 160 (32%) PV and 32 (16%) ET patients. Death was observed in 139 (28%) PV and 10 (5%) ET patients. Median MFS was 158.5 months (95% CI: 143.0-183.0) for PV and 308.0 months (95% CI: 175.0-NR) for ET. In PV, older age at diagnosis (HR 1.04; 95% CI: 1.02-1.07; p<0.001) and shorter time since PV or ET diagnosis to biopsy (HR 0.995; 95% CI: 0.990-0.999; p=0.048) independently predicted worse MFS. In ET, bone marrow hypercellularity (HR 5.67, 95% CI: 1.40-23.0, p=0.015) independently predicted worse MFS. Conclusions: PV patients demonstrated shorter MFS compared to ET. Older age at diagnosis in PV, whereas bone marrow hypercellularity in ET was significantly associated with fibrotic progression or death. Active surveillance of at-risk patients may facilitate early detection and timely treatment initiation. Disease Variable HR (95%CI) P-value PV Age at diagnosis 1.04 (1.02-1.07) <0.001 Time since PV or ET diagnosis to biopsy 0.995 (0.990-0.999) 0.048 ET Bone marrow hypercellularity 5.67 (1.40-23.0) 0.015

e18574 Background: ND has historically been recommended to reduce infectious complications in cancer patients (pts). While the adoption of ND has declined over the last decade, recent studies - particularly in pts undergoing hematopoietic stem cell transplantation (HSCT) - have raised uncertainty regarding the safety of LD. Herein, we performed a meta-analysis of studies directly comparing ND with LD in pts with cancer. Methods: We conducted a systematic search of MEDLINE, Embase, and Cochrane databases from inception through January 2026. Comparative retrospective and prospective studies were included if they were comparing ND with LD in adults or children with cancer. Primary outcomes were major infections and bacteremia/fungemia. Secondary outcomes were pneumonia, diarrhea, and all-cause mortality. Random-effects meta-analyses were performed to calculate pooled risk ratios (RR) with 95% confidence intervals (CI). The review followed PRISMA 2020 guidelines. Results: Fifteen studies enrolling 4,320 patients were included in the primary analysis. Six studies enrolled only adult patients, three were restricted to pediatric populations, and six included mixed adult and pediatric cohorts. Across these studies, ND was not associated with a significant reduction in major infections (RR 1.02, 95% CI 0.88–1.18; p=0.795), bacteremia/fungemia (RR 0.97, 95% CI 0.78–1.22; p=0.805), pneumonia (RR 0.98, 95% CI 0.59–1.63; p=0.933), diarrhea (RR 1.12, 95% CI 0.96–1.31; p=0.159), or all-cause mortality (RR 0.94, 95% CI 0.77–1.15; p=0.632). Sensitivity analyses restricted to RCTs showed consistent results. Subgroup analysis of hematological/HSCT studies (9 studies; 1,769 pts) also showed no differences across outcome. Analysis restricted to RCTs in hematologic/HSCT pts (6 studies; 855 pts) showed no differences in major infections, pneumonia, diarrhea, or mortality; however, ND was associated with a lower risk of bacteremia/fungemia (RR 0.67, 95% CI 0.47–0.95; p=0.023). Heterogeneity across studies was low to moderate. Conclusions: ND was not associated with reductions in major infections, pneumonia, diarrhea, or mortality compared with LD. A reduction in bacteremia/fungemia was observed in RCTs of hematologic malignancy and HSCT pts. Overall, these findings suggest that routine ND implementation is unnecessary for most cancer pts, although cautious dietary practices may remain reasonable in selected high-risk hematologic malignancy/HSCT populations.

e17005 Background: We previously developed a hybrid framework combining LLMs and rule-based algorithms (RBA) for automated risk stratification in localized prostate cancer (locPCa), achieving 89% accuracy. However, clinical T-stage (cTS) inference from narrative MRI reports remained the primary source of errors. Herein, we evaluated whether ensemble approaches using multiple state-of-the-art LLMs could improve cTS inference and overall NCCN risk stratification accuracy. Methods: This study included patients with locPCa presenting with at least one positive prostate biopsy and MRI report available. Building on our previously validated hybrid framework that extracts structured phenotypic variables (PSA, prostate volume, cTS, Gleason patterns, grade group, positive and examined cores) from unstructured reports using LLMs and applies NCCN-concordant RBA for risk stratification, we focused on improving cTS inference. Four HIPAA-compliant LLMs (GPT-4.1, GPT-5.1, Gemini-2.5-Pro, Gemini-2.5-Flash) were evaluated using structured zero-shot prompts iteratively refined through oncologist feedback. Majority voting was employed to generate consensus cTS predictions. Performance was evaluated using weighted accuracy. Results: A total of 358 patients were included. The median age at diagnosis was 65 years (IQR: 60-69); the majority were White (92%) and non-Hispanic (94%). cTS distribution was T2a (51%), T2c (20%), T3a (16%), T3b (7%), T2b (4%), and T4 (2%). The most prevalent risk category was unfavorable intermediate (38%) followed by favorable intermediate (20%), high risk (19%), very high risk (16%), low (5%), and very low (1%). Individual LLM accuracy for cTS inference ranged from 85-90%, with Gemini-2.5-Pro achieving highest accuracy (90%), followed by GPT-4.1 (88%), GPT-5.1 (87%), and Gemini-2.5-Flash (85%). The four-model ensemble reached consensus in 92% of cases, achieving 93% cTS inference accuracy. When integrated into NCCN risk stratification schema, single-model approaches achieved 89-92% accuracy, while ensemble consensus cases achieved 95% accuracy. Conclusions: The ensemble framework using multiple LLMs significantly improves cTS inference and achieves 95% NCCN risk stratification accuracy in consensus cases (92% of patients), representing a 6-percentage-point improvement over our previous single-model framework (89%). This strategy demonstrates that ensemble methods can overcome individual model limitations for complex clinical tasks and holds promise for reliable AI-assisted risk stratification.

e17004 Background: Living clinical practice guidelines offer the opportunity to keep recommendations aligned with the latest evidence, but they also present a fundamental challenge: as evidence accumulates, panelists cannot sustainably query and synthesize a growing body of literature. In developing ASCO's living metastatic castration-resistant prostate cancer (mCRPC) guideline, we encountered this challenge firsthand. To address it, we developed and evaluated an interactive agentic framework that enables guideline panelists to query evidence in natural language and retrieve structured facts, tables, and figures—with the goal of extending this tool as a clinician-facing companion to enhance guideline accessibility. Methods: The mCRPC systematic review dataset supporting ASCO's clinical practice guideline was used, comprising 212 structured columns capturing trial characteristics, patient populations, and outcomes extracted from 188 references across 88 clinical trials. A large language model (LLM)-based agentic framework was developed employing a coding agent that translates natural language queries into executable scripts for structured evidence retrieval. Claude (Haiku 4.5, Sonnet 4.5, and Opus 4.5) served as the core LLM agents. We constructed a benchmark of 50 fact-based queries with gold-standard answers targeting trial identification, treatment modalities, and endpoint characteristics (e.g., "Which trials evaluated systemic monotherapy?"). Performance was evaluated using exact-match accuracy for final answers, and precision, recall, and F1 score for trial-level retrieval. Results: Across 50 queries, exact-match accuracy ranged from 82% to 86%. Haiku 4.5 and Sonnet 4.5 each achieved 82% (42/50), while Opus 4.5 achieved 86% (43/50). Precision ranged from 0.93–0.97, recall from 0.94–0.96, and F1 scores from 0.91–0.94. Conclusions: This agentic framework enables scalable, auditable, natural language interrogation of guideline evidence, addressing a critical bottleneck in living guideline maintenance. For panelists, it supports rapid, reproducible evidence surveillance during recommendation development. For clinicians, it offers a foundation for an interactive companion tool that transforms static guidelines into queryable resources—enabling personalized evidence retrieval at the point of care. LLM EM Precision Recall F1 claude-haiku-4-5 0.82(42/50) 0.95 0.94 0.91 claude-sonnet-4-5 0.82(42/50) 0.97 0.96 0.93 claude-opus-4-5 0.86(43/50) 0.93 0.96 0.94

e17003 Background: Accurate ascertainment of prostate cancer (PCa) disease states—biochemical recurrence (BCR), castration-sensitive prostate cancer (CSPC), and castration-resistant prostate cancer (CRPC)—is critical for automated clinical trial enrollment, quality improvement initiatives, and real-world evidence generation. Essential information for disease state ascertainment resides in unstructured EHR data, requiring labor-intensive manual abstraction that is inconsistent and not scalable. We developed an automated hybrid AI framework using large language models to identify PCa disease states from real-world EHR data. Methods: This retrospective study included patients with histopathologically confirmed PCa (2017-2022) and ≥3 years follow-up. Sequential EHR data—including PSA and testosterone levels, clinical notes, pathology and radiology reports—were retrieved across temporal points. BCR was identified using rule-based algorithms (post-radical prostatectomy [RP]: PSA ≥0.2 ng/mL ×2; post-radiation therapy [RT]: nadir + 2 ng/mL ×2). CRPC was determined using androgen deprivation therapy (ADT) timing, PSA kinetics, testosterone < 50 ng/dL, and radiographic progression per PCWG/EAU-ASCO criteria. GPT-4o with structured parametrized prompts extracted metastatic status and radiographic progression. Independent clinicians performed manual annotation for validation. The framework was developed on 10% of data with evaluation on 90%. External validation used a held-out cohort of clinical trial patients. Results: Among 200 PCa patients (median age 66 years [IQR 60-71]; 91% White, 93% non-Hispanic), the framework demonstrated high accuracy: PCa diagnosis (92%), RP dates (94%), RT dates (93%), and ADT initiation (92%). For disease state identification, BCR detection achieved 90% accuracy, castration status 93%, and metastatic state (M0/M1) 87%. External validation on trial-enrolled patients confirmed robust performance: 26/31 (84%) CRPC trial patients and 26/27 (96%) CSPC trial patients were correctly classified, validating the framework’s reliability for clinical trial matching. Conclusions: This hybrid LLM-based framework accurately identifies PCa disease states using real-world EHR data with minimal manual intervention. The system offers a scalable, reproducible approach for automated disease state identification, enabling streamlined clinical trial matching and enhanced real-world data curation in oncology.

e16502 Background: Accurate postoperative risk stratification in localized clear-cell renal cell carcinoma (ccRCC) informs prognosis, surveillance intensity, and eligibility for adjuvant systemic therapy. Although validated prognostic models (Leibovich 2018, SSIGN, and UISS) exist, they are inconsistently applied in routine practice due to workflow and documentation barriers. Using AI assisted tools within the electronic medical record (EMR) may enable rapid, standardized risk assessment and improve clinical use. Methods: We retrospectively analyzed 92 patients with localized ccRCC undergoing radical nephrectomy and postoperative oncology evaluation (December 2021–September 2025) across three Mayo Clinic sites. Pathology reports and oncology notes were extracted via structured SQL queries. Clinical and pathologic variables were parsed using a zero-shot GPT-4o pipeline. Gold-standard prognostic risk classification and adjuvant therapy eligibility were established by an expert oncology clinician using validated prognostic calculators and KEYNOTE-564 eligibility criteria. AI-generated outputs and novice manual abstraction by two first-year fellows were compared against expert assessment using accuracy, precision, recall, and F1 score. Leibovich and SSIGN were evaluated as three-class models (low/intermediate/high), and UISS as binary risk stratification (high vs non-high). Results: Among 92 patients with localized ccRCC (median age 64 years [range 41–78]), AI-generated outputs demonstrated near-perfect agreement with expert assessment for KEYNOTE-564 adjuvant immunotherapy eligibility (accuracy 97%, precision 100%, recall 97%, F1 score 98%). For three-class prognostic stratification, AI achieved perfect agreement for Leibovich disease-free survival risk (accuracy, precision, recall, and F1 all 100%), outperforming novice abstraction. For SSIGN, AI demonstrated strong multi-class performance (accuracy 91%, precision 91%, recall 93%, F1 score 92%), compared with novice abstraction (accuracy 92%, F1 score 90%). For binary UISS risk stratification, AI achieved 81% accuracy, precision 74%, recall 100%, and F1 score 85% showing a tendency towards false positives. Conclusions: This study demonstrates AI can use existing prognostic and systemic therapy eligibility to accurately risk stratify and identify patients eligible for adjuvant systemic immunotherapy post nephrectomy. For our next steps, we plan to develop a multimodal AI platform integrating pathologic, radiologic, and clinical data to improve prognostication for outcomes and predictive capabilities for patients who would benefit from adjuvant systemic therapy for more personalized medicine.