Afzal, M.

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.

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.

352 Background: Glucagon-like peptide 1 (GLP1) receptor expression in prostate cancer tissue has raised concerns that GLP1 receptor agonists (GLP1A) may influence tumor growth or progression. We compared prostate cancer severity at diagnosis among patients receiving GLP1A versus other glucose lowering therapies. Methods: A retrospective chart review identified patients who received GLP1A or alternative second-line glucose lowering agents (DPP4/SGLT2 inhibitors) and were subsequently diagnosed with prostate cancer. Patients receiving both drug classes were excluded. Baseline demographics (race, ethnicity, age), comorbidities (diabetes, myocardial infarction, peripheral vascular disease) concomitant medications (insulin, metformin, statins), appointments (within past year) and laboratory values (HbA1c, eGFR) at therapy initiation were recorded. Primary outcomes included Gleason grade group and metastatic presentation within three months of diagnosis. Propensity score matching balanced baseline characteristics between groups. Mann-Whitney U tests compared grade groups. Chi-square tests compared metastatic presentation, reporting odds ratios (OR) with 95% confidence intervals (CI). Multivariable logistic regression identified predictors of grade group (low-grade: 1-2; high-grade: ≥3) and metastatic presentation, reporting OR with 95% CI. A p value <0.05 indicated a significant association. Results: Of 260 propensity-matched patients (GLP1A: 130, comparison: 130), 87% were White and 95% were Non-Hispanic/Non-Latino in each group. Median HbA1c was 7% (IQR: 6.4-8) in GLP1A group versus 7.5% (6.2-8.5) in comparison group. Median eGFR was 75mL/min/1.73m 2 (IQR: 61.5-90.0) in GLP1A group versus 60.0 (52.0-80.5) in comparison group. High-grade disease occurred in 33 (25%) GLP1A patients and 37 (29%) comparison patients. Among patients with available imaging (GLP1A: 40; comparison: 32), metastatic presentation occurred in 7 (18%) GLP1A group and 7 (22%) comparison group patients. No significant differences were observed in grade group (GLP1A median: 2; IQR: 1-2 vs. comparison median: 2; 1-3; p=0.44) or metastatic presentation (OR: 1.32; 95%CI: 0.41-4.25; p=0.64) between groups. In multivariable analysis, higher HbA1c was associated with high-grade disease in GLP1A group (OR: 1.83; 95%CI: 1.07-3.35; p=0.03) while higher eGFR was associated with low-grade disease in the comparison group (0.97; 0.93-0.99; p=0.04). Conclusions: GLP1A use was not associated with prostate cancer grade or metastatic presentation at diagnosis compared to alternative glucose-lowering agents. However, the association between elevated HbA1c and high-grade disease in GLP1A patients suggests a potential impact of poor glycemic control on tumor biology. Prospective studies are needed to elucidate the relationship between metabolic dysregulation and prostate cancer severity.

129 Background: Androgen receptor pathway inhibitors (ARPIs) improve metastasis-free and overall survival in men with non-metastatic hormone-resistant prostate cancer (nmHRPC). Apalutamide and darolutamide were approved by the Federal Drug Administration in 2018 and 2019, respectively, based on pivotal clinical trials showing similar efficacy. However, no head-to-head comparisons exist in real-world settings. We compared prescription patterns and survival outcomes between apalutamide and darolutamide in men with nmHRPC using the Surveillance, Epidemiology and End Results (SEER)-Medicare data. Methods: We identified men aged ≥66 years with localized or locoregional prostate cancer between 2000 and 2021 using the SEER-Medicare linked database. Eligible patients initiated apalutamide or darolutamide between January 2019 and December 2021, defined by Medicare Part D claims. The index date was the first prescription of either agent. Men with distant metastases, prior malignancies and age ≤65 were excluded. Baseline demographics and clinical characteristics were compared using chi-square and Wilcoxon rank-sum tests. Survival was assessed using Kaplan-Meier analysis with log-rank tests. Cox proportional hazards regression was used to estimate adjusted hazard ratios (HRs) for mortality. Results: Among 582 men with nmHRPC, 435 (74.7%) received apalutamide and 147 (25.3%) received darolutamide. The mean age at diagnosis was 73.8 vs 74.1 years (p=0.95). Most patients were White (84.6% vs 81.0%, p=0.21) and resided in metropolitan areas (85.0% vs 88.4%, p=0.39). Darolutamide use was more frequent in the Northeast (42.9% vs 24.6%, p<0.001), while apalutamide was more common in the South (28.7% vs 15.6%, p<0.001). Patients receiving darolutamide had higher-grade tumors (68.0% grade III vs 51.3%, p=0.002) and a longer median time from diagnosis to prescription (93 vs 64 months, p<0.001). Kaplan-Meier curves and adjusted Cox models showed no significant difference in overall survival (HR 1.00; 95% CI 0.51–1.98; p=1.00). Age was independently associated with mortality (HR 1.05 per year; 95% CI 1.00–1.10; p=0.04). Conclusions: Apalutamide and darolutamide demonstrated comparable real-world survival outcomes in nmHRPC. Geographic and clinical factors influenced prescribing patterns, but survival did not differ between agents. Treatment choice may therefore be guided by patient comorbidities, tolerability, and clinician preference. Variable Comparison HR (95% CI) P-Value Treatment Darolutamide vs Apalutamide 1.00 (0.51,1.98) 1.00 Age at Diagnosis 1.05 (1.00, 1.10) 0.04* Race White vs Non-White 0.71 (0.28, 1.80) 0.47 Marital Status Married vs Unmarried 1.29 (0.60, 2.75) 0.51 Geographic Region -Midwest vs West 1.18 (0.34, 4.15) 0.79 -Northeast vs West 1.92 (0.92, 3.88) 0.07 -South vs West 1.01 (0.43, 2.36) 0.99

127 Background: Bone metastases affect up to 90 % of patients with metastatic hormone-resistant prostate cancer (mHRPC) and cause substantial morbidity from skeletal-related events (SREs) such as fracture, spinal-cord compression, and palliative interventions. Bone-modifying agents (BMAs) including bisphosphonates and denosumab reduce SRE risk and are NCCN-recommended, however, real-world use remains inconsistent. Methods: Patients with mHRPC treated from January 2017-September 2024 across Mayo Clinic sites were identified using SQL-based EHR queries confirmed by manual chart review. Bone Metastases were detected through keyword searchers of radiology reports and confirmed through manual chart review. SRE-prevention dosing was defined as zoledronic acid 4mg IV or denosumab 120mg SC; osteoporosis dosing was excluded. SREs were identified using diagnosis codes and text-pattern searches for radiotherapy, surgery, fracture, and spinal-cord compression. Descriptive statistics summarized BMA utilization and SRE incidence. Categorical variables were compared using Chi-square tests, and a risk ratio (RR) with 95% confidence intervals was calculated to evaluate association between early BMA initiation and SRE risk. Results: Among 778 patients with mHRPC, 685 (88 %) had bone metastases (mean age 70.5 years). Of these, 169 (24.7 %) had an SRE, and 261 (38.1 %) received BMAs at SRE-prevention doses (denosumab n = 157 [60 %]; zoledronic acid n = 104 [40 %]). Based on a chi-square test, combined SRE incidence did not differ significantly (No BMA 23 %, denosumab 23 %, zoledronic 33 %; p = 0.069). Bone pain at baseline was more common in patients who later received a BMA (136 [68 %]) than in those who did not (82 [41 %]; p < 0.001). Among 200 randomly sampled non-BMA patients, 83 had no recorded BMA discussion (66 also lacked bone pain), 38 lacked dental clearance, 32 had uncompleted plans and 18 declined therapy. Early BMA initiation (before first bone metastases) was associated with fewer SREs (16 % vs 29 %; RR 0.56, 95 % CI 0.33–0.96). Conclusions: Less than half of bone-metastatic mHRPC patients received BMAs. Non-initiation was often linked to modifiable factors such as delayed dental clearance or lack of treatment discussions, highlighting the need for system-level strategies to improve timely bone-directed care. SREs were common, affecting one quarter of patients. Small sample size precluded meaningful comparison of the impact of BMAs on SRE incidence however early BMA initiation may lower SREs. Incidence of SREs stratified by no BMA vs BMA treatment. SRE No BMA BMA Overall Pathological Fracture 6.4% (27/424) 4.9% (13/261) 5.8% (40/685) Radiotherapy to Bone 13.9% (59/424) 18.8% (49/261) 15.7% (108/685) Spinal Cord Compression 0.7% (3/424) 3.1% (8/261) 1.6% (11/685) Surgery to Bone 2.1% (9/424) 0.3% (1/261) 1.5% (10/685) Combined 23% (98/424) 27.2% (71/261) 24.7% (169/685)

e17155 Background: Localized PCa is classified into six NCCN risk categories, each with specific treatment recommendations. However, treatment concordance across these categories and its variation by race in clinical practice remain unexplored. Therefore, we aim to describe patterns of guideline-concordant treatment receipt for localized PCa across risk groups and race. Methods: Surveillance, Epidemiology, and End Results (SEER) database (2018–2020) was queried to identify patients with localized PCa from 17 registries. Data regarding clinical T stage, Gleason patterns, PSA level, biopsy cores and initial treatment received (radiation, radical prostatectomy, systemic therapy) was obtained. Each patient was then stratified into one of six NCCN-based risk categories using a rule-based algorithm. Using the stratified risk category of each patient, treatment recommendations were obtained from the NCCN guidelines. Concordance was assessed by comparing the received treatment and guideline-recommended treatment. A focused bi-variate logistic regression analysis was performed adjusting for risk groups, and race. Odds ratio (OR) with 95% confidence intervals (CI) were computed to quantify the magnitude of guideline-discordant treatment receipt. Results: This analysis included 69,584 patients with localized PCa (White: 53,875 [77.4%]; Black: 11,265 [16.2%]; Asian/Pacific Islander: 4,133 [5.9%]; American Indian/Alaska Native: 311 0.5%]). In terms of risk groups, patients in higher risk categories had increased odds of discordance compared to the lower risk groups (Table). In terms of race, Black men had significantly higher odds of receiving guideline-discordant therapy (OR:1.67, 95% CI:1.58–1.76), while no statistically significant difference was observed with American Indian/Alaska Native men (OR:1.21, 95% CI: 0.92–1.61) and Asian/Pacific Islander men (OR:1.05, 95% CI:0.97–1.14) compared to White men. Conclusions: Population level data, based on limited sample size in some groups, suggests that treatment concordance with NCCN guidelines varies by risk group and race in localized PCa. Black patients, and those with higher risk groups were more likely to receive guideline-discordant therapy. These findings highlight the need for strategies and prospective studies at individual patient level to evaluate and enhance guideline adherence to promote personalized care for these patients. Variable Discordant Treatment (%) OR (95% CI) White 22168 (41.1) REF Black 5653 (47.5) 1.67 (1.58-1.76) * Asian/Pacific Islander 1822 (44.1) 1.05 (0.97-1.14) American Indian/Alaska Native 191 (61.4) 1.22 (0.92- 1.61) Very Low Risk 770 (9) REF Low Risk 146 (2) 0.16 (0.13-0.19) * Favorable Risk 35 (0.4) 0.03 (0.02-0.04) * Unfavorable Risk 15125 (83.2) 36.30 (33.72-39.25) * High/Very High Risk 13441 (50) 7.32 (6.83-7.86) * * p <0.05.

132 Background: Distant metastasis at the time of prostate cancer (PCa) diagnosis is associated with increased morbidity and mortality. This study aimed to assess the impact of sociodemographic characteristics on distant metastasis at the time of PCa diagnosis. Methods: The Surveillance Epidemiology and End Results (SEER) database (2000-2021), including PCa patients from 17 registries, was queried. Patients with late-stage diagnosis (LSD) were defined as those who were initially diagnosed with stage IV disease, indicating distant metastasis. Sociodemographic predictors included race, ethnicity, age, marital status, residential status, and median household income. Multicollinearity was assessed using variance inflation factors (VIF). Univariable logistic regression was performed to identify significant predictors of LSD, which were further analyzed in multivariable logistic regression using a maximum likelihood estimation approach. Odds ratios with 95% confidence intervals (CI) were computed with a p-value of <0.05 indicating a statistically significant association. Results: Of the 1,089,736 PCa patients diagnosed, 64,983 (6%) had an LSD. The majority were white (80%), non-Hispanic/Latino (HL) (91%), aged ≥65 years (60%), married (75%), residents in metropolitan areas (88%), and had an annual house income of ≥$70,000 (70%). Multivariable logistic regression identified Black (OR: 1.24; 95%CI: 1.22-1.27), Asian or Pacific Islander (1.35; 1.30-1.40), and American Indian/Alaska Native (1.70; 1.53-1.89) to have higher odds of LSD compared to White patients (Table). In addition, HL ethnicity compared to non-HL (OR: 1.45; 95% CI: 1.42-1.49), age ≥65 compared to <65 (1.68; 1.65-1.71), unmarried status compared to married (1.88; 1.85-1.91), residency in non-metropolitan areas compared to metropolitan (1.10; 1.07-1.12), and household income <$70,000 compared to ≥$70,000 (1.03; 1.01-1.05) had a significant association with LSD. Conclusions: Older, non-White (Black, Asian/Pacific Islander, American Indian/Alaska Native), Hispanic/Latino, unmarried men, residents of non-metropolitan areas, or those with lower annual household incomes have higher odds of late-stage diagnosis. Interventions targeting early detection in these at-risk groups may improve prostate cancer outcomes in the US. Variable Odds Ratio (95% CI) p-value Race (Black vs White) 1.24 (1.22-1.27) <0.01 Race (Asian or Pacific Islander vs White) 1.35 (1.31-1.40) <0.01 Race (American Indian/Alaska Native vs White) 1.70 (1.53-1.89) <0.01 Ethnicity (Hispanic/Latino vs non-/Hispanic/Latino) 1.45 (1.42-1.49) <0.01 Age (≥65 vs <65) 1.68 (1.65-1.71) <0.01 Marital status (unmarried vs married) 1.88 (1.85-1.91) <0.01 Residence status (non-metropolitan vs metropolitan) 1.10 (1.07-1.12) <0.01 Household income (<$70,000 vs ≥$70,000) 1.03 (1.01-1.05) <0.01