Deshmukh, Sameer

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)

e24201 Background: Anthracyclines remain curative in many pediatric and adolescent/young adult (AYA) cancers but confer dose-dependent cardiotoxicity. Dexrazoxane reduces cardiac injury; however, concerns persist regarding potential impact on oncologic outcomes. Methods: We conducted a PRISMA-compliant systematic review and meta-analysis of studies comparing anthracycline therapy with versus without dexrazoxane in pediatric/AYA populations. Databases included MEDLINE, Embase, and CENTRAL. Outcomes included cardiac function (LVEF decline, clinical heart failure), event-free survival (EFS), overall survival (OS), relapse, and second malignant neoplasms (SMN). Random-effects meta-analysis pooled hazard ratios (HRs) for time-to-event outcomes and risk ratios (RRs) for binary endpoints. Results: Twelve studies with 1,384 patients were included. Dexrazoxane significantly reduced risk of clinical heart failure (RR 0.34, 95% CI 0.21–0.55) and preserved LVEF compared with controls. No significant differences were observed in EFS (HR 0.97, 95% CI 0.84–1.12), OS (HR 0.95, 95% CI 0.81–1.11), relapse (RR 1.02, 95% CI 0.87–1.19), or SMN incidence (RR 1.05, 95% CI 0.78–1.41). Benefits were consistent across cancer types, cumulative anthracycline doses, and follow-up durations. Conclusions: Dexrazoxane provides substantial cardio protection in pediatric and AYA patients receiving anthracyclines without compromising oncologic outcomes or increasing risk of SMNs. Clinical Takeaway: Routine incorporation of dexrazoxane in high-risk anthracycline regimens can prevent cardiotoxicity while maintaining curative potential.

e24198 Background: Even when radiotherapy is delivered outpatient, treatment-related nausea, vomiting, and dehydration can precipitate hospitalization, driving cost and morbidity. National estimates of this burden are limited. Methods: We analyzed the HCUP National Inpatient Sample (NIS) for 2016–2022 to identify hospitalizations with radiotherapy encounters (Z51.0) and concurrent diagnoses of nausea, vomiting, or dehydration using ICD-10 codes. Outcomes included length of stay (LOS), total charges, ICU use proxies, in-hospital mortality, and non-home discharge. Survey-weighted national estimates were calculated, and multivariable regression assessed predictors including cancer site proxies, age, comorbidity burden, insurance status, income quartile, and hospital characteristics. Results: Across 7,842 weighted admissions, mean LOS was 4.6 days (SD 2.1), mean total charges $23,400 (SD $8,700), and ICU-level care proxies were required in 12% of admissions. In-hospital mortality was 0.9%, and 21% of patients required non-home discharge. Older age, higher comorbidity burden, lower income quartile, and rural hospital location were independently associated with longer LOS, higher charges, and greater risk of non-home discharge (p < 0.01). Admissions for gastrointestinal or head/neck malignancies had the highest rates of RINV-related hospitalization. Temporal trends showed stable rates over the 7-year period. Conclusions: Hospitalizations for RINV and dehydration during radiotherapy represent a measurable national burden with disparities by socioeconomic status, tumor site, and hospital location. Clinical Takeaway: Targeted outpatient supportive interventions, particularly for high-risk patients, may reduce hospitalization, costs, and morbidity during radiotherapy.

e22007 Background: Long-term neurocognitive impairment is a major source of disability in survivors of pediatric CNS tumors. Proton radiotherapy may reduce dose to developing brain structures, potentially preserving cognition compared with conventional photon therapy. Methods: We performed a systematic review and meta-analysis of MEDLINE, Embase, PsycINFO, and CENTRAL. Eligible studies included pediatric CNS tumor patients treated with proton or photon radiotherapy reporting neurocognitive outcomes (full-scale IQ, attention, processing speed, executive function) over time. Standardized mean differences (SMD) were pooled using random-effects models, and slope analyses assessed longitudinal IQ change. Subgroups included age at radiotherapy, craniospinal vs focal fields, tumor type, chemotherapy exposure, and follow-up duration. Certainty of evidence was graded using GRADE. Results: Eleven studies encompassing 624 patients were included. Proton therapy was associated with significantly less decline in full-scale IQ compared with photon therapy (SMD 0.43, 95% CI 0.21–0.65, p < 0.001). Domain-specific analyses showed preservation of attention (SMD 0.36, 95% CI 0.10–0.61) and processing speed (SMD 0.41, 95% CI 0.18–0.64). Longitudinal slope analysis indicated an average IQ decline of 0.7 points/year after proton therapy versus 2.4 points/year after photon therapy. Benefits were greatest in younger children (<8 years) and those receiving craniospinal irradiation. Attrition and missing data were similar across groups. Conclusions: Proton radiotherapy in pediatric CNS tumors is associated with clinically meaningful preservation of neurocognitive function compared with photon therapy, particularly in younger patients and those receiving extensive fields. Clinical Takeaway: When available, proton therapy should be considered for children at high risk of cognitive decline to optimize long-term functional outcomes.

e20511 Background: Trop-2 ADCs have emerged as a novel therapeutic approach in NSCLC that is refractory to chemotherapy and immune checkpoint inhibitors. Comparative interpretation of the efficacy of multiple Trop-2 ADCs, including Sacituzumab tirumotecan (Sac-TMT), Datopotamab deruxtecan (Dato-DXd), and Sacituzumab govitecan (SG), is limited. We therefore conducted a systematic review, IPD survival analysis, and meta-analysis to evaluate the efficacy and PROs of Trop-2 ADCs compared with chemotherapy in NSCLC. Methods: A systematic search was conducted from inception to October 31, 2025, across PubMed, Scopus, Cochrane, and CT.gov. Clinical trials evaluating Overall Survival (OS) and Progression-free survival (PFS) in patients treated with Trop-2 ADC alone or compared with Chemotherapy were included. IPD were extracted from the Kaplan-Meier curves of clinical trials for reconstruction using the KMfromIPD website by MD Anderson, which stratified the data by treatment group. Outcomes included OS, PFS, and time to deterioration (TTD). The cumulative data were analyzed using R 4.5.1 and RStudio. RevMan version 5.4.1 was used for the meta-analysis of subgroups. Heterogeneity was assessed using the I 2 statistic. Results: Of 513 articles, 7 phase 1/2 single-arm and 4 randomized control trials were included, comprising 2,619 patients.Trop-2 ADCs were associated with improved OS (Median 15.6 vs 12.5 months; HR 0.78, 95% CI 0.69-0.88; p < 0.0001) and PFS (Median 5.5 vs 4.1 months; HR 0.66, 95% CI 0.59-0.74; p < 0.0001). Sac-TMT demonstrated the greatest OS benefit (OS 23.3 months; HR 0.40). Further drug classes are depicted in Table 1. PROs assessment showed TROP-2 ADCs were associated with longer time to deterioration in global quality of life and dyspnea-free survival compared to chemotherapy (HR 0.8 and 0.69), (p = 0.04 and p < 0.0001, respectively). Exploratory subgroup analysis showed improved OS among patients with actionable gene alteration (AGA) treated with Trop-2 ADCs (HR 0.58, p < 0.00001). However, no significant difference was observed in either treatment arm among patients without AGA (HR 0.89, p = 0.15). Conclusions: Trop-2 ADCs were associated with improved survival and PROs compared with chemotherapy in NSCLC, with variability across agents. Sac-TMT has shown higher OS and PFS. Dato Dxd had a favorable PFS; however, the OS was not superior to chemo. Furthermore, SG showed no favorable clinical outcomes compared with the chemo group. These findings support the continued development of Trop-2-directed therapies and highlight the need for prospective comparative trials and biomarker-driven patient selection. Drug N mOS (months) HR p- value mPFS (months) HR p- value Sac-TMT 386 23.32 0.4 <0.000001 7.5 0.5 <0.000001 Dato-DXd 486 13.2 0.95 0.55 5.02 0.71 <0.000001 SG 347 12.61 1.02 0.82 4.18 0.87 0.05

e14098 Background: For IDH-mutant WHO grade 2 gliomas, extent of resection (EOR) is thought to improve long-term outcomes, but optimal thresholds and survival benefit remain uncertain. Quantifying the impact of EOR can guide surgical planning and patient counseling. Methods: We performed a systematic review and meta-analysis of MEDLINE, Embase, CENTRAL, and Web of Science. Eligible studies reported EOR (continuous or categorical) and outcomes including overall survival (OS), progression-free survival (PFS), malignant transformation, seizure control, and treatment-related morbidity. Random-effects models pooled hazard ratios (HRs) for survival outcomes, and meta-regression assessed relationships between EOR, histologic subtype (astrocytoma vs oligodendroglioma), measurement method (MRI volumetrics vs surgeon estimate), and adjuvant therapy. Results: Twelve studies including 1,052 patients were analyzed. Higher EOR was associated with improved survival: pooled HR for OS per 10% incremental resection was 0.88 (95% CI 0.83–0.93), and for PFS 0.85 (95% CI 0.79–0.91). Patients achieving ≥90% resection had the greatest benefit, with 10-year OS of 88% versus 62% for <90% resection (p < 0.001). Higher EOR also reduced risk of malignant transformation (HR 0.67, 95% CI 0.53–0.85) and improved seizure control in 68% of evaluable patients. Results were consistent across histologic subtypes and measurement methods, with minimal heterogeneity (I² < 35%). Conclusions: Greater EOR in IDH-mutant grade 2 gliomas is strongly associated with improved survival, lower malignant transformation risk, and better seizure control, supporting maximal safe resection as the standard of care. Clinical takeaway: Surgical planning aiming for ≥90% resection can optimize long-term outcomes and quality of life in patients with IDH-mutant grade 2 gliomas.

Abstract Background: B-cell acute lymphoblastic leukemia (B-ALL) accounts for 0.3% of all new cancer cases and 0.2% of cancer-related deaths in the United States. While survival outcomes have improved over the years, further intensifying chemotherapy has offered diminishing returns. Blinatumomab, a bispecific T-cell engager targeting CD3 and CD19, has shown clinical benefit in minimal residual disease (MRD)-positive and relapsed/refractory settings. Its recent FDA approval for use in the consolidation phase of newly diagnosed Philadelphia chromosome–negative, CD19-positive B-ALL followed the landmark E1910 trial, which demonstrated a survival advantage when added to standard chemotherapy. We conducted a systematic review and meta-analysis to evaluate the efficacy and safety of blinatumomab in the consolidation phase across clinical trials and real-world studies. Methods: A comprehensive review was carried out on PubMed, Clinicaltrials.gov and Cochrane library from inception up to July 2025 using the terms “Blinatumomab” and “ALL”. Studies that evaluated response: overall response rate (ORR) and complete response (CR) and adverse events between Blinatumomab and control groups were included. Out of the 19 studies that met the inclusion criteria, 12 were clinical trials and 7 were observational studies. Open meta-analyst software was used to analyze the data. For single arm study, PLO (logit-transformed proportion) was used as a metric. Der Simonian-Laird random effects model was used to generate forest plots of pooled response rate estimates and 95% CI along with p-values and I2 statistics for heterogeneity. Results: A total of 824 patients were included (54.4% male, 45.6% female), with a median age of 48 years. The median follow-up across studies was 18.2 months (range, 3.4 to 92.8 months). Pooled ORR was 96.4% (95% CI, 93–98; p=0.955), and pooled CR was 92.7% (95% CI, 87–95; p&lt;0.001). TRAEs leading to treatment discontinuation occurred in 6.8% (95% CI, 2.5–11.2; p=0.004), dose reductions in 2.9% (95% CI, 0.2–5.6; p=0.069), and treatment-related mortality in 1.4% (95% CI, 0.4–2.3; p=0.256). There was moderate heterogeneity across studies for toxicity outcomes. Conclusion: Consolidation-phase blinatumomab is associated with high response rates and a favorable safety profile, reinforcing the survival gains observed in E1910 (3-year OS: 83% vs 65%). With low rates of treatment-limiting toxicity and mortality, our findings support the incorporation of blinatumomab into standard adult B-ALL consolidation regimens. These data suggest that this immunotherapeutic approach may help narrow the outcome gap between adult and pediatric ALL.