Adeoye, Oluwatayo

21 Background: Large language models (LLMs) are becoming an increasing source of medical information for both patients and providers. Clinical decision making is occasionally complex and may use factors outside of traditional guidelines. We conducted a comparative performance evaluation of frontier models on standardized genitourinary (GU) oncology knowledge assessments derived from the American Society of Clinical Oncology Self-Evaluation Program 2025 (ASCO SEP 2025) in addition to challenging questions developed by GU oncology experts. Methods: Three frontier LLMs were selected: ChatGPT-5.2 (OpenAI, San Francisco, CA, USA), Claude Opus 4.6 (Anthropic, San Francisco, CA, USA), and Gemini 3 Pro (Google DeepMind, Mountain View, CA, USA). Model selection was based on publicly reported performance on “Humanity’s Last Exam,” a benchmark of advanced scientific reasoning (Scale AI leaderboard Jan-Feb 2026). The OpenEvidence (OpenEvidence Inc., MA, USA) search engine was also selected for evaluation. All models were asked 145 ASCO SEP 2025 GU oncology questions and 12 real world challenging scenarios using an uniform prompt. Subject matter experts peer reviewed LLM generated responses to challenging questions and credit was given only for correct rationale and option selection. Results: All models demonstrated high and comparable accuracy on Standardized knowledge assessment, with Gemini 3 Pro leading numerically at 97.24% (95% CI, 93.1% – 99.0%), OpenEvidence followed with an accuracy of 94.48% (95% CI, 89.5% – 97.3%), while Chat GPT -5.2 and Claude OPUS 4.6 scored 92.41% (95%, CI 86.9% – 95.7%) and 79.31% (95% CI, 71.9% – 85.1%) respectively. On challenging real world scenarios, ChatGPT-5.2 demonstrated the highest numerical accuracy at 100% (95% CI, 75.8% – 100%), Gemini 3 Pro and Open Evidence scored 75.0% (95% CI, 46.8%–91.1%) each, followed by Claude Opus 4.6 at 66.7% (39.1–86.3). Conclusions: All current frontier AI models appear to provide accurate medical information and rationale on a large majority of guideline based medical knowledge assessments for GU oncology. Frontier AI models also appear to have emerging competence in highly challenging real-world scenarios. AI based tools may become a valuable and reliable tool for patients and providers. Comparative LLM performance. Model ASCO SEP 2025 % (95% CI) Real World Scenarios % (95% CI) Gemini 3 Pro 97.24% (93.1–99.0) 75.0% (46.8–91.1) OpenEvidence 94.48% (89.5–97.3) 75.0% (46.8–91.1) ChatGPT-5.2 92.41% (86.9–95.7) 100% (75.8–100) Claude Opus 4.6 79.31% (71.9–85.1) 66.67% (39.1–86.3)

e20595 Background: Circadian regulation of immune function has been proposed as a modifier of immune checkpoint inhibitor (ICI) efficacy, with retrospective studies suggesting improved outcomes with earlier infusion timing. Whether these findings translate to routine oncology practice, where ICIs are administered across multiple lines, frequently combined with chemotherapy, and subject to treatment interruptions, remains uncertain. We evaluated the association between ICI infusion timing and overall survival (OS) in a real-world cohort of patients with non-small cell lung cancer (NSCLC). Methods: A retrospective cohort study included adults with NSCLC who received at least one line of ICI therapy at a community oncology center between January 2018 and December 2024. Infusion timing was defined at the patient level as morning-only ( < 1300 hours), evening-only (≥1300 hours), or mixed timing, reflecting receipt of infusions exclusively in different time-of-day categories across treatment lines. OS was measured from diagnosis to death or last follow-up. Kaplan-Meier and Cox proportional hazards models were used. Multivariable analyses adjusted for stage, ECOG performance status, body mass index, and premature ICI discontinuation. Line of therapy was excluded due to collinearity with mixed-timing classification and risk of immortal time bias. Results: A total of 127 patients were included (morning-only n = 77; mixed timing n = 36; evening-only n = 14). Staging data were available for 99.2%, and 94 deaths occurred. Median OS was 495 days for morning-only, 850 days for mixed timing, and 388 days for evening-only patients. Kaplan-Meier analysis showed no statistically significant OS differences across groups. In sensitivity analysis excluding patients with mixed infusion timing, morning-only and evening-only groups demonstrated overlapping survival curves, with no evidence of a time-of-day–specific survival advantage. In univariate analysis, mixed timing was associated with a borderline reduction in mortality compared with morning-only infusions (HR 0.63, 95% CI 0.39-1.00), while evening-only timing was not (HR 1.63, 95% CI 0.85-3.16). In multivariate analysis restricted to stage III-IV disease, infusion timing was not independently associated with OS. ECOG performance status, premature ICI discontinuation and advanced staging were the strongest predictors of mortality. Conclusions: In this real-world NSCLC cohort, ICI infusion timing was not independently associated with overall survival after adjustment for patient fitness and treatment continuity. These findings suggest that in pragmatic settings, clinical factors may outweigh subtle chronotherapy effects reported in more selected populations.

e17027 Background: Guidelines recommend active surveillance for low-risk prostate cancer and definitive therapy for high-risk disease. We evaluated national patterns of risk-misaligned care and the survival consequences of undertreatment. Methods: National Cancer Database prostate cancer cases diagnosed from 2010–2022 were analyzed. Low-risk disease was defined as clinical T1–T2, Grade Group 1, and PSA < 10; overtreatment was definitive treatment vs active surveillance or no treatment. High-risk disease was defined as Grade Group ≥4, PSA ≥20, or clinical T3–T4; undertreatment was no definitive local therapy or incomplete definitive therapy. Multivariable logistic regression evaluated factors associated with misalignment. Overall survival (OS) among high-risk patients was assessed using multivariable Cox regression. Results: Among low-risk patients (N = 124,562), overtreatment occurred in 40% of cases. Overtreatment was more common among young men (adjusted odds ratio [aOR] 0.982; p < 0.001) and less common at academic centers (aOR 0.414; p = 0.015). Compared with White men, odds of overtreatment were lower among Black men (aOR 0.946; p = 0.002) and Asian men (aOR 0.827; p < 0.001), with additional variation by education and region (all p < 0.001). Among high-risk patients (N = 318,532), undertreatment affected 27.3% of patients and was more common among older men (aOR 1.061; p < 0.001). Compared with White men, undertreatment was higher among Black men (aOR 1.479; p < 0.001) and lower among Asian patients (aOR 0.863; p < 0.001) (overall race p < 0.001). Compared with private insurance, undertreatment was higher in Medicaid (aOR 2.038; p < 0.001) and uninsured patients (aOR 2.649; p < 0.001), and slightly lower with Medicare (aOR 0.931; p < 0.001) (overall insurance p < 0.001). Multiple comorbidities were associated with higher undertreatment (≥2 vs 0: aOR 1.252; p < 0.001). Facility type was not independently associated (p = 0.490), while region remained significant (overall p < 0.001). In the survival cohort (high risk) (N = 338,919), undertreatment was associated with substantially worse OS (HR 2.745, 95% CI 2.706–2.784; p < 0.001), adjusted for age (HR 1.056; p < 0.001), race (p = 0.001), insurance (p < 0.001), comorbidity (p < 0.001), income (overall p < 0.001), education (overall p < 0.001), and facility region (overall p < 0.001). Conclusions: Low-risk overtreatment remains common nationwide and varies across patient and health-system factors. In high-risk disease, undertreatment affects over one-quarter of patients and disproportionately impacts Black men and those with Medicaid or no insurance. Undertreatment confers a nearly threefold mortality hazard (adjusted HR 2.75; p < 0.001), highlighting a major national quality gap and the urgent need for system-level interventions to ensure equitable, guideline-concordant delivery of definitive therapy.

e16488 Background: Small bowel adenocarcinoma (SBA) and ampullary adenocarcinoma (ampullary AC) are rare gastrointestinal (GI) malignancies. Treatment strategies are largely extrapolated from colorectal cancer, where oxaliplatin-based regimens are the most common first-line therapy in advanced disease. Although bevacizumab is considered safe in metastatic SBA, its efficacy remains unproven, and evidence is limited to small retrospective studies. We assessed the association of adding bevacizumab to FOLFOX with survival and toxicity in a large real-world cohort. Methods: We conducted a retrospective cohort study using the TriNetX Global Collaborative Network (January 2000-December 2025), including data from 105 healthcare organizations. Adults (≥18 years) with SBA or ampullary AC treated with FOLFOX with or without bevacizumab were identified. Cohorts were propensity score-matched on age, sex, race, comorbidities, and metastatic sites. Outcomes included overall mortality, GI perforation, bleeding, venous thromboembolism (VTE), hospital admission, and emergency department (ED) visits. Kaplan-Meier and Cox proportional hazards models were used for time-to-event analyses. Results: After matching, 818 patients were included in each cohort. In the FOLFOX + bevacizumab cohort, mean age was 66.1 ± 12.0 years and 53.8% were male; 63.7% were White, 13.8% Black, 5.6% Asian, 12.0% Unknown/Other, and 4.4% Hispanic/Latino. Over a median follow-up of 13 months, FOLFOX + bevacizumab was associated with higher overall mortality compared with FOLFOX alone (55.3% vs 45.2%; HR 1.24 [95% CI 1.1-1.4]; p = 0.002) and shorter median OS (15.1 vs 19.5 months). Rates of GI perforation (15.5% vs 16.7%; HR 0.90 [95% CI 0.71-1.15]; p = 0.39), GI bleeding (13.1% vs 13.6%; HR 0.96 [95% CI 0.73-1.25]; p = 0.74), and VTE (19.1% vs 21.4%; HR 0.88 [95% CI 0.71-1.09]; p = 0.23) were similar between groups. Hospital admissions were higher in the FOLFOX + bevacizumab cohort (2.8% vs 1.3%; HR 2.1 [95% CI 1.0-4.3]; p = 0.04). Findings were consistent at 5-year follow-up. Conclusions: In this real-world cohort, the addition of bevacizumab to FOLFOX was not associated with improved survival and was associated with higher healthcare utilization. Prospective, disease-specific studies are needed to define its role in this population. Outcomes at median 13-month follow-up after propensity matching (FOLFOX + bevacizumab vs FOLFOX). Outcome % vs % HR p Overall mortality 55.3 vs 45.2 1.24 0.002 Hospital admission 2.8 vs 1.3 2.1 0.04 ED visit 45.2 vs 42.4 1.02 0.75 GI perforation 15.5 vs 16.7 0.90 0.39 GI bleeding 13.1 vs 13.6 0.96 0.74 VTE 19.1 vs 21.4 0.88 0.23

e16435 Background: Peritoneal metastasis in pancreatic ductal adenocarcinoma (PDAC) is historically associated with a dismal prognosis and limited response to systemic therapy alone. The role of locoregional therapy remains controversial. This study evaluated the survival impact and safety of HIPEC, with or without cytoreductive surgery (CRS), compared to standard-of-care systemic therapy in patients with peritoneal metastatic PDAC. Methods: We conducted a comparative analysis of 130 patients with peritoneal metastatic PDAC, comprising a study cohort treated with HIPEC (n = 33) and a control group treated with systemic chemotherapy alone (Non-HIPEC, n = 97). HIPEC patients received induction chemotherapy (predominantly FOLFIRINOX) followed by HIPEC ± CRS. Co-primary endpoints included 12 months survival, and 6 months progression free survival (PFS). Secondary endpoints evaluated Overall Survival (OS ), safety of CRS, and impact of germline mutation status on survival. Study was approved under IRB protocol 25-008762. Results: The 12-month OS rate was significantly higher in the HIPEC group compared to the chemotherapy-only control group (100% vs. 52.6%, P < 0.001). The 6-month PFS rate in the HIPEC group was 63.0% vs. 47.94 in-only control group (P < 0.001). For secondary endpoints, the HIPEC group demonstrated a significantly longer median OS of 33.0 months vs. 17.0 months for controls (P < 0.001). Within the HIPEC cohort, the addition of CRS (n = 25) significantly improved outcomes compared to HIPEC alone (n = 8): median OS improved from 21.5 to 36.0 months (P = 0.03). Germline testing was performed in 61% of HIPEC patients and 48% of controls, identifying pathogenic mutations in 25% and 17%, respectively. Identified pathogenic mutations in both groups included ATM (n = 4), MUTYH (n = 2), BRCA2 (n = 1), CHEK2 (n = 1), PALB2 (n = 1), and KIT (n = 1). In the control group, specific mutations drove divergent outcomes; ATM median OS: 23.5 months vs. MUTYH : 8.0 months (P = 0.04). Conversely, in the HIPEC+CRS cohort, survival was excellent regardless of genetic profile: mutation carriers achieved a median OS of 33.0 months compared to 31.0 months in wild-type patients (P = 0.85). Despite a 34.8% postoperative complication rate in the HIPEC group, there was no perioperative mortality. Conclusions: In selected patients with peritoneal metastatic PDAC, HIPEC provides a substantial survival advantage over systemic therapy alone, achieving a 100% 12-month survival rate and more than doubling the median overall survival. Importantly, germline mutation status did not preclude survival benefit, with mutation carriers deriving equal efficacy from the multimodal approach. These findings support HIPEC+CRS as a highly effective strategy that may overcome adverse biologic drivers.

e16018 Background: Intrahepatic cholangiocarcinoma (iCCA) exhibits marked heterogeneity in outcomes that is incompletely explained by stage or treatment timing. Although treatment delay is frequently cited as a modifiable risk factor, its prognostic significance in real-world practice remains unclear. We applied machine learning (ML) to model iCCA as a dynamic disease process and to evaluate whether longitudinal disease trajectories better explain outcomes than treatment timing alone. Methods: We conducted a population-based retrospective analysis of adults diagnosed with iCCA using the Surveillance, Epidemiology, and End Results (SEER) database (2000–2022). Time from diagnosis to first cancer-directed therapy was categorized as ≤30 days, 31–60 days, or > 60 days. Associations between treatment delay, disease characteristics, and overall survival (OS) were assessed using multivariable logistic and Cox regression models. To capture real-world disease evolution, each patient’s clinical course was encoded as an ordered longitudinal sequence of diagnosis, treatment states (surgery, chemotherapy, radiation), and outcome. Unsupervised ML was used to identify latent disease-course trajectories. A supervised ML model using variables available at diagnosis was developed to predict membership in high-risk trajectories. Results: The cohort included 18,312 patients with iCCA. Treatment initiation beyond 30 days occurred in more than half of patients and was more common in localized than advanced disease. In adjusted survival analyses, shorter time to treatment was paradoxically associated with worse OS, consistent with confounding by disease severity rather than a protective effect of delay. Unsupervised ML identified four distinct and reproducible disease trajectories with markedly different outcomes. Median OS ranged from approximately 2 months in early-failure trajectories to approximately 15 months in favorable multimodality trajectories. Trajectory membership was not fully explained by stage or treatment timing. A supervised ML model predicted high-risk trajectory membership with good discrimination (AUC 0.82). Key predictors included tumor grade, age, tumor burden, and incomplete staging, whereas treatment timing had minimal influence. Conclusions: In iCCA, treatment delay reflects underlying disease biology and care prioritization rather than independently determining survival. ML-based trajectory modeling reveals clinically meaningful disease courses that better explain outcome heterogeneity than treatment timing or stage alone and enables early identification of patients at highest risk for unfavorable real-world outcomes.

e15501 Background: CP is the backbone of first-line therapy for recurrent or metastatic ASCC. In practice, Q3-week CP has been explored as a potential alternative to the standard (d1,8,15 Q28-day cycle) dosing, though its efficacy is not known. This study evaluated CP scheduling and clinical survival associations in metastatic ASCC. Methods: This multicenter retrospective cohort study included patients with metastatic ASCC treated with first-line CP, identified using the Mayo Data Explorer database. Electronic health records were reviewed to collect baseline clinical characteristics, treatment regimens, responses, progression-free survival (PFS), and overall survival (OS). Descriptive statistics were used to summarize patient demographics. Survival was estimated using Kaplan–Meier methods. Multivariable Cox proportional hazards models were used to compare survival by dosing schedule, adjusting for age, ECOG performance status, HPV (p16) status, liver metastasis, and prior chemoradiation. Results: 54 patients treated between 2020-2025 with first-line CP for metastatic ASCC were included. Baseline patient demographics were balanced between dosing groups (Table 1). Median follow-up time was 26.2 months. For Q3-week CP (n = 21), median PFS and OS were 9.8 (95% CI 8.1, NR) and 27.0 (95% CI 15.7, NR) months, respectively, while median PFS was 6.5 (95% CI 4.5,15.3) months with standard CP (n = 33) and median OS was not reached (95% CI 11.2, NR). Response rate was 76% with Q3-week and 60.6% with standard CP (p = 0.23) dosing. Survival outcomes were similar when comparing Q3-week CP relative to standard CP dosing using multivariable analysis (PFS HR 0.68, 95% CI 0.33–1.41; OS HR 1.67, 95% CI 0.67–4.14). Higher ECOG and liver metastasis were independently associated with inferior outcomes, while HPV was associated with improved survival. Subsequent therapy patterns were similar between CP schedule groups. Ten patients (16.9%) received local therapy, and 24 of 28 patients with progression received further systemic therapy, including 21 (87.5%) treated with immunotherapy. Conclusions: Survival outcomes were similar across dosing schedules, suggesting Q3-week CP may be a reasonable alternative to standard CP, with potential to reduce treatment-related burden in metastatic ASCC. Future analysis will compare toxicity profiles between CP dosing schedules, including in combination with PD1 inhibitors given the results of the POD1UM-303 trial. Patient demographics (n=54). Variable Q3-week CP (n=21) Standard CP (n=33) p-value Sex Female 16 (76.2%) 24 (72.7%) 0.77 Male 5 (23.8%) 9 (27.3%) Age Median (Q1, Q3) 62 (50.5, 69) 64 (55.5, 70) 0.57 BMI Median (Q1, Q3) 27.1 (21.9, 34.4) 27.4 (22.5, 31.7) 0.72 ECOG 0 9 (42.9%) 11 (34.4%) 0.53 ≥ 1 12 (57.1%) 21 (65.6%) Confirmed HPV (p16) Positive 16 (76.2%) 24 (72.7%) 0.77 Prior chemoradiation Yes 17 (81.0%) 21 (63.6%) 0.17

9558 Background: Ipilimumab 3 mg/kg plus nivolumab 1 mg/kg (Ipi3+Nivo1) is the standard immunotherapy regimen for metastatic melanoma with brain metastases (MBM) but is associated with significant immune-related toxicity, particularly neurologic toxicity. Ipilimumab 1 mg/kg plus nivolumab 3 mg/kg (Ipi1+Nivo3) has demonstrated improved tolerability in extracranial melanoma, though comparative data in MBM are limited. We compared efficacy and toxicity of these dosing strategies in a multisite real-world cohort. Methods: We retrospectively identified patients with MBM treated with ipilimumab plus nivolumab across three Mayo Clinic sites between 2016 and 2024. Patients were classified by induction dosing as Ipi1+Nivo3 or Ipi3+Nivo1. Overall survival (OS) and progression-free survival (PFS) were estimated using the Kaplan–Meier method and compared using log-rank tests. Best overall response (BOR) and toxicity outcomes were summarized descriptively. Results: Among 147 patients (Ipi1+Nivo3 n=32; Ipi3+Nivo1 n=115), 144 were evaluable for survival. Median age was higher in the Ipi1+Nivo3 group (69.5 vs 66.0 years); males predominated in both groups (71.9% vs 61.7%), and the cohort was predominantly White (>96%). Most patients had ECOG 0–1 in both groups (84.4% in Ipi1+ Nivo3 and 90.4% in Ipi3+Nivo1). BRAF mutation status was balanced between regimens, with approximately half of patients harboring BRAF-mutant disease (51.6% vs 53.2%). Median OS was 18.5 months (95% CI, 5.7–54.7) with Ipi1+Nivo3 versus 10.6 months (95% CI, 6.5–19.1) with Ipi3+Nivo1 (log-rank p=0.25). Two-year OS was 45.9% and 35.0%, and five-year OS was 24.5% and 19.2%, respectively. Median PFS was 7.3 months (95% CI, 1.8–10.9) versus 2.8 months (95% CI, 2.1–4.4) (log-rank p=0.16). BOR was available for 138 patients; objective response rates were 35.5% and 31.8%, respectively. 3–5 adverse events occurred in 24.1% of Ipi1+Nivo3 versus 30.5% of Ipi3+Nivo1 patients. Hospitalizations were less frequent (16.7% vs 36.1%), and neurologic adverse events occurred only with Ipi3+Nivo1 (11.9% vs 0%). Conclusions: In this multisite real-world MBM cohort, Ipi1+Nivo3 demonstrated comparable efficacy, numerically longer survival, and a more favorable toxicity profile compared with standard Ipi3+Nivo1. Notably, no neurologic toxicity was observed with the Ipi1+Nivo3 regimen. These findings support further prospective evaluation of lower dose ipilimumab strategies. Response and survival outcomes. Outcome Ipi1 + Nivo3 Ipi3 + Nivo1 Complete response (CR) 2 / 31 (6.5%) 8 / 107 (7.5%) Partial response (PR) 9 / 31 (29.0%) 26 / 107 (24.3%) Objective response rate (ORR = CR+PR) 11 / 31 (35.5%) 34 / 107 (31.8%) Disease control rate (DCR = CR+PR+SD) 18 / 31 (58.1%) 51 / 107 (47.7%) Median PFS, months (95% CI) 7.3 (1.8–10.9) 2.8 (2.1–4.4) 2-year PFS 27.6% 22.3% Median OS, months (95% CI) 18.5 (5.7–54.7) 10.6 (6.5–19.1) 2-year OS 45.9% 35.0% 5-year OS 24.5% 19.2%

9021 Background: An escape room is a team-based activity in which participants collaborate to solve puzzles within a fixed time limit and escape. Prior studies demonstrate high learner satisfaction and improved teamwork and communication with medical education escape rooms. To date, no published reports describe an escape room designed specifically for hematology/oncology (hem/onc) fellows. As part of Hem/Onc Curriculum, we designed and implemented a hem/onc-focused escape room and evaluated learner satisfaction and perceived learning impact. Methods: The escape room was designed using evidence-based learning science principles (Table 1). Teams worked to solve sequential puzzles, centered on a patient case, addressing key hem/onc concepts, including transfusion medicine, peripheral blood smears, lymphoma classification, and coagulation disorders. Each solved puzzle revealed additional patient laboratory and pathology data. Successful completion required teams to diagnose the patient and select appropriate treatment. Following the activity, teams participated in a facilitator-led debrief focused on team dynamics, communication, and problem solving. Teams observed each other and shared feedback. A larger group debrief co-led by chief fellows and faculty reviewed learning objectives and key takeaways. Learner outcomes were assessed using a post-activity survey evaluating satisfaction, engagement, and impact on learning. Results: Eighteen learners participated, including 14 hem/onc fellows, 1 APP hem/onc fellow, and 3 internal medicine residents. Three of four teams escaped within 1 hour (mean completion time, 52 minutes). All participants provided positive verbal feedback. Fifteen learners completed the post-activity survey, and all respondents reported satisfaction with the activity and would recommend it for future fellows. One-word descriptors included “engaging,” “fun,” and “challenging.” Most respondents (93.3%) agreed that the activity reinforced key hem/onc concepts and improved confidence in clinical problem-solving. All learners felt the activity supported learning, and 93.3% reported that collaboration enhanced the learning experience. Participants identified team-based problem solving, clinical application, and interactive puzzles as the most effective components. Conclusions: A hem/onc escape room resulted in high learner satisfaction and reinforced hem/onc knowledge and clinical problem-solving. This feasible, fun, and innovative activity complements traditional fellowship education by leveraging adult learning principles through gamified, team-based learning and should be incorporated into training programs’ curriculum. Learning science principles applied in a hem/onc escape room. Active Learning Belonging Contrasting Cases Debriefing Deliberate Practice Elaboration Generation Listening and Sharing Reward Worked Examples