Citations

4584 Background: EVP is the preferred frontline regimen in pts with aUC. Despite initial response to treatment, many pts treated with EVP ultimately have progression. We hypothesized that recurrence patterns would differ between pts with and without baseline liver metastases. Methods: UNITE is a multi-institutional retrospective database capturing clinical and treatment characteristics of pts with aUC receiving systemic therapies. We queried this database to identify pts who achieved an observed response (OR) to EVP. Pts were grouped by initial metastatic sites using a non-mutually exclusive approach. Descriptive statistics were used to summarize observed response rates (ORR) and recurrence patterns at time of progression. Progression-free survival (PFS) from start of EVP was estimated using the Kaplan-Meier method. The effect of liver metastases on PFS was assessed via multivariable Cox regression. Median-follow up time was estimated using the reverse Kaplan-Meier method. Statistical analyses were conducted in RStudio. Results: We identified 464 pts treated with EVP (median age 72; 74% male, 80% White). Best ORR in pts with baseline liver metastases (n=77) were complete response 9%, partial response 35%, stable disease 18%, and progressive disease 21%, compared with 18%, 37%, 27%, and 18%, respectively, in pts without baseline liver metastases (n=325). The estimated median follow-up time was 52 weeks (95% CI 48-62). Among pts with initial OR to EVP, those with baseline liver metastases showed a non-significant trend toward shorter PFS (HR 1.35; 95% CI 0.67–2.75; p=0.40) versus those without baseline liver metastases. Among pts with initial OR to EVP and subsequent progression the distribution of sites of recurrences at progression for those with (n = 10) and without (n = 40) baseline liver metastases were: liver (50% vs. 10%), lymph nodes (60% vs. 55%), lungs (50% vs. 38%), bone (20% vs 20%), and primary tumor (20% vs 25%). EVP responders with baseline liver metastases had a numerically higher rate of site-specific metastasis resolution at progression versus those with lymph node or lung metastases (Table). Conclusions: Our analysis suggests that liver metastases may be associated with shorter PFS among EVP responders, though these pts frequently do not retain liver metastases at time of progression. Study limitations include retrospective analysis, investigator-assessed response, small sample size, selection and confounding biases. Patterns of recurrence following EVP merits further evaluation. Metastatic Site Pts with Site-Specific Baseline Metastases (n) Pts with Resolution of Site-Specific Metastases at Progression, n (%) Pts without Baseline Metastases at Site (n) Pts who Remained Free of Site-Specific Metastases at Progression, n (%) Liver 10 5 (50%) 40 36 (90%) Lymph Nodes 37 12 (32%) 13 10 (77%) Lungs 26 8 (31%) 24 22 (92%)

4565 Background: EVP is the preferred 1 st -line regimen for patients (pts) with aUC. EV-related toxicities are often managed with dose adjustments, such as reductions and holds. Analysis of EV monotherapy trials showed consistent survival outcomes despite dose adjustments. We hypothesized that on-treatment EV dose adjustments would not impact survival in these pts. Methods: Pts with aUC treated with EVP in the multisite UNITE study were analyzed. Early dose reductions (DR) and holds were defined as occurring < 9 weeks from EVP start, with the remainder classified as late. Pts with DR at treatment start were excluded. Survival endpoints were progression-free survival (PFS) and overall survival (OS) from EVP start, assessed by Kaplan-Meier analysis and Cox models. Multivariable Cox analysis (MVA) included age (≥ 75 vs < 75), ECOG performance status (0-1 vs 2-3), Hgb level (< 10 vs ≥ 10) and liver metastases (present vs not). A time-dependent covariate was used to reduce immortal time bias. Complementary MVA landmark analyses were performed, aligned to the total number of treatment cycles received, with six analyses from cycles 2 to 7. Results: 360 pts from 17 sites were included (median age 70; 78% Caucasian; 76% male; 27% upper tract primary; 35% histology subtype component; 17% with liver metastasis; 78% frontline); median follow-up was 11.7 months (95% CI [10.79, 13.08]). Median number of cycles was 6 in pts with DR and 3 with no DR. Early DRs (100 pts [28%]) and holds (18 pts [5%]) were most commonly due to rash (28% of all early DRs and holds). Late DR (75 pts [21%]) and holds (50 pts [14%]) were most commonly due to neuropathy (52% of all late DRs and holds). Pts with early or late DR had longer PFS and OS vs those who did not (Table); however, there was no significant PFS or OS difference with dose hold vs no hold (PFS HR 0.65, 95%CI (0.40, 1.05), p = 0.08; OS HR 0.70, 95%CI (0.39, 1.27), p=0.24). In landmark analyses, about 50% of pts had DR; no significant difference in PFS or OS was observed at most landmarks, except for longer OS in the DR cohort at cycle 4 (HR 0.53, 95% CI (0.29, 0.98), p = 0.042) and cycle 5 (HR 0.43, 95% CI (0.19, 0.99), p = 0.048). Conclusions: In this real-world retrospective analysis, EVP efficacy was maintained despite DR and dose holds. Survival difference noted in the time-dependent analyses were not consistently reproduced in landmark analyses, suggesting exposure-related selection bias rather than causal effect. Prospective studies are warranted to validate these hypothesis-generating findings. Association of EV DR with PFS/OS (time-dependent analyses). Early DR Late DR DR vs no DR outcomes UVAHR (95% CI), p MVAHR (95% CI), p UVAHR (95% CI), p MVAHR (95% CI), p PFS 0.50 (0.35, 0.72), <.001 0.56 (0.38, 0.84), 0.005 0.32 (0.21, 0.49), <.001 0.36 (0.23, 0.57), <.001 OS 0.51 (0.32, 0.79), 0.003 0.57 (0.35, 0.92), 0.022 0.26 (0.15, 0.45), <.001 0.31 (0.17, 0.55), <.001

TPS913 Background: A subset of patients with MIBC who receive neoadjuvant therapy (NAT) prior to radical cystectomy (RC) have a pathologic complete response (pCR) at the time of RC. With pCR rates of 22-42% in patients with MIBC following NAT (+/- ICI), whether a subset of patients with good clinical response to NAT can avoid RC is an important unanswered question, especially with the development of more active systemic therapies. HCRN 16-257 evaluated maintenance nivolumab in lieu of cystectomy in patients with MIBC who experienced clinical complete response (cCR) following neoadjuvant GC and nivolumab. The cCR rate was 48%, but 8/33 (24%) patients who elected bladder preservation subsequently underwent cystectomy for local disease recurrence. The RETAIN trial also evaluated omission of local therapy following neoadjuvant therapy with a 2-year bladder preservation rate in patients with ≤T1 disease following NAC of 54% (22/41). Of the 9/25 (36%) patients on that trial developed metastatic disease, 8/9 developed localized disease before metastasizing. These data illustrate the critical role that local therapy plays in patients with MIBC. For this reason, we believe that radiotherapy to the bladder combined with ICI will improve bladder intact event-free survival (BI-EFS). This trial also allows for patients to opt for bladder preservation based on a good clinical response to NAT. Methods: This is a single arm, phase 2 trial (NCT07061964) evaluating risk-adapted bladder preservation therapy for patients with MIBC following NAT. NAT consists of any NCCN guideline concordant therapy for MIBC. Patients with cT2-T4aN0M0 MIBC who complete NAT will be eligible if they have ≤T1 disease on post-NAT TURBT, confirmed by biopsies of prior tumor sites and systematic sampling (left/right lateral walls, dome, posterior wall, trigone). Patients will receive 55 Gray (Gy) in 20 fractions of radiotherapy (RT) to the bladder with 1 year of pembrolizumab. The primary objective is to evaluate whether 3-year BI-EFS is at least 70% in participants with < = T1 (without multifocal CIS) following NAT and RT with 1 year of pembrolizumab. Secondary objectives include local muscle invasive recurrence-free survival, metastasis-free survival (MFS), overall survival (OS), the rate of salvage cystectomy, and evaluation of the frequency and severity of toxicities in participants who receive RT and pembrolizumab. Plasma and urine will be banked for future correlative studies. S2427 was activated in September 2025 with an accrual goal of 111 patients. Clinical trial information: NCT07061964 .

794 Background: HER2 protein, encoded by ERBB2 gene, is the target of emerging therapies for patients (pts) with advanced urothelial carcinoma (aUC). High HER2 IHC expression (IHC 3+) is present in ~15% of pts with aUC, while >50% of pts have HER2 IHC 1+/2+/3+ expression. EVP is the preferred 1 st line regimen for pts with aUC, but the impact of HER2 status on EVP outcomes is unclear. Methods: We identified pts from the UNITE study with tumor samples tested for HER2 by IHC and another cohort with next-generation sequencing (NGS) data available. Outcomes were compared by HER2 IHC status (HER2 IHC 0/1+ vs 2+/3+) and separately based on ERBB2 status (alteration vs wild-type). X 2 test was used to compare observed response rate (ORR) and logistic regression was used to compare disease control rate (DCR). Duration of response (DOR), progression-free survival (PFS) and overall survival (OS) from EVP start were evaluated using log-rank test and Cox proportional hazards models. Multivariate analysis (MVA) included age, sex, race, ECOG PS, neutrophil:lymphocyte ratio, albumin, hemoglobin, primary tumor site, tumor histology, prior lines of treatment, and metastatic sites as covariates. Results: Among 521 pts treated with EVP from 16 sites, 112 had HER2 IHC data and 313 had NGS. Median age was 71, 74% were men, 84% Caucasian, 82% had ECOG PS 0-1, 65% pure urothelial histology, and 73% received frontline EVP. HER2 IHC distribution (n=112) was 27%/21%/37%/15% for 0/1+/2+/3+, respectively. ERBB2 alterations were present in 14% (44/313). Baseline characteristics were similar in HER2 0/1+ and 2+/3+ pts, except more primary bladder tumors in 2+/3+ pts (83% vs 63%, p=0.01). For the overall cohort (n=521), with a median follow up of 7.3 mos from EVP start, ORR was 54%, DCR 81%, median DOR (mDOR) 8.5 mos, median PFS (mPFS) 8.5 mos, and median OS (mOS) 19.8 mos. Pt outcomes by HER2 IHC status are shown (Table). In univariate analysis (UVA), pts with HER2 IHC 0/1+ had longer mOS compared to HER2 IHC 2+/3+, but this was not significant in MVA (HR: 0.5; CI: 0.2–1.3, p=0.17). No significant differences were observed in other outcomes. Evaluating clinical outcomes by ERRB2 status, no significant differences were seen for ERBB2 -altered vs wild-type pts. Conclusions: In this retrospective study, no significant differences were seen in EVP treatment outcomes based on HER2 IHC status or ERBB2 status. These findings are hypothesis-generating and require validation in larger and prospective cohorts. HER2 0/1+ (n=54)* HER2 2+/3+ (n=58) OR (95%CI, p) HR UVA (95%CI, p) HR MVA (95%CI, p) ORR 49% (23/47) 55% (27/49) 1.3 (0.6-2.9, p=0.5) - - DCR 79% (37/47) 88% (43/49) 1.9 (0.7-6.2, p=0.2) - - mDOR 11.7 mos 10.4 mos - 1.3 (0.7-2.4, p=0.4) 1.2 (0.4-3.3, p=0.8) mPFS 5.9 mos 7.1 mos - 0.8 (0.5-1.4, p=0.5) 1.1 (0.5-2.5, p=0.9) mOS 42.4 mos 18.7 mos - 2.3 (1.1-4.5, p=0.02) 2.0 (0.8-5.4, p=0.2) *HER2 0/1+ used as reference.

696 Background: EVP is the preferred 1st-line therapy for patients (pts) with aUC. Upfront EV dose reductions may be utilized to enhance tolerance and minimize treatment-related toxicities when intolerance is anticipated. Prior studies of EV monotherapy suggest that starting dose 1.25 mg/kg resulted in exposure that maximized chance of response. We hypothesize that upfront EV dose reductions would not compromise EVP efficacy. Methods: Pts with aUC treated with EVP in the multi-site UNITE database were analyzed. Upfront dose reduction was defined as starting dose < 1.25 mg/kg. Correlation between clinical features and EV dose reduction were assessed using Fisher’s Exact test. Endpoints include progression-free survival (PFS) and overall survival (OS) from EVP initiation, assessed by Kaplan-Meier analysis and Cox models. Multivariable Cox analysis (MVA) included age (< 75 vs ≥ 75), ECOG performance status (PS) (0-1 vs 2-3), hemoglobin level (< 10 vs ≥ 10), and liver metastases (present vs absent), chosen in accordance with Bellmunt criteria. Correlation with investigator-assessed observed response rate (ORR) was determined using logistic regressions. All tests were 2-sided with p < 0.05 considered significant. Results: A total of 456 pts across 17 sites were included (median age 72; 77% Caucasian; 75% male; 26% upper tract primary; 66% pure UC; 77% ECOG PS 0-1; 17% with liver metastasis; 89% 1 st line EVP). Upfront dose reduction occurred in 96 pts (21%); 76 pts (79%) started at 1.0 mg/kg and 20 pts (21%) at 0.75 mg/kg. Upfront dose reduction was significantly associated with age ≥ 75 (p = 0.002), ECOG PS 2/3 (p = 0.04), and hemoglobin < 10 (p = 0.01) but not with liver metastasis (p = 0.9). Lower starting EV dose correlated with shorter median PFS (5 vs 6 months) and OS (9 vs 10 months), and lower ORR (28% vs. 60%) when compared to full dose (Table). In MVA adjusting for prognostic factors for PFS and OS, these associations were no longer statistically significant. Conclusions: In this real-world analysis, upfront EV dose reductions were most frequently used in pts with factors associated with frailty and poor prognosis, e.g. older age and ECOG PS 2/3, and were associated with lower ORR. When adjusted for these factors, upfront EV dose reductions were not associated with shorter PFS/OS though a trend towards inferior outcomes persisted. These differences in outcomes may reflect baseline risk factors rather than dose intensity; however, prospective investigation is required to validate our hypothesis-generating results. Association of upfront EV dose reduction with outcomes. Outcome (Upfront dose reduction vs no upfront dose reduction) Univariable analysis Multivariable analysis PFS: HR (95% CI), p 1.50 (1.11 – 2.02), 0.008 1.33 (0.95-1.86), 0.09 OS: HR (95% CI), p 1.56 (1.11-2.20), 0.01 1.41 (0.96-2.06), 0.08 ORR: OR (95% CI), p 0.35 (0.21-0.60), 0.0001 0.38 (0.21-0.67), 0.0009

PURPOSE Previous studies suggest that SPOP mutations result in increased sensitivity to androgen receptor pathway inhibitors (ARPIs) but are limited by lack of granular data. We hypothesize that SPOP mutations are associated with improved outcomes across the spectrum of advanced prostate cancer (PC). METHODS Using the real-world clinicogenomic Prostate Cancer Precision Medicine Multi-Institutional Collaborative Effort database, we analyzed outcomes based on SPOP mutation status. The primary end point was overall survival (OS) from the diagnosis of metastatic disease. Secondary end points included real-world progression-free survival (PFS) and PSA90 response. RESULTS Among 2,097 patients with metastatic PC, 5.5% (N = 115) had SPOP -mutated tumors. Compared with SPOP wild-type, patients with SPOP mutations were older at diagnosis (median 65 v 63 years; P = .001) and had higher (≥8) Gleason sum (68% v 54%; P = .02), higher incidence of lung metastasis (17% v 6%; P = .001), and increased frequency of intraductal features (13% v 5%; P < .001). SPOP mutations were associated with improved PSA90 response with first ARPI exposure in the castrate-resistant setting (60% v 40.6%; OR, 2.20 [95% CI, 1.15 to 4.19]; P = .02) but not in the castrate-sensitive setting (78.9% v 71.5%; OR, 1.49 [95% CI, 0.66 to 3.37]; P = .43). Median PFS with first ARPI did not differ in SPOP- mutated versus wild-type group in both the castrate-sensitive (24.2 v 19.2 months; hazard ratio [HR], 0.80 [95% CI, 0.49 to 1.32]; P = .39) and castrate-resistant settings (15.0 v 12.4 months; HR, 0.81 [95% CI, 0.58 to 1.12]; P = .20). In multivariable analysis, SPOP mutations were associated with improved OS (HR, 0.65, P = .02). CONCLUSION SPOP mutations were associated with longer OS despite the presence of aggressive clinical features. The distinct clinical and molecular features of SPOP -mutated PC support its consideration as a unique molecular subtype with prognostic implications.

5108 Background: We previously proposed a hybrid framework combining LLMs and rule based algorithm (RBA) for automating risk stratification in locPCa. Herein, we aim to validate the risk stratification agent (RSA) in a prospective cohort, develop & evaluate the treatment recommendation agent (TRA) based on NCCN guidelines, and develop an interactive interface to facilitate clinicians for accurate risk stratification and treatment recommendations at the point of care. Methods: This study included pts with locPCa (2004-2024) presenting at Mayo Clinic with at least 1 positive prostate biopsy and MRI report available. For RSA prospective validation, GPT4 extracted key phenotypic variables (PSA, T stage, prostate volume, number of cores, Gleason patterns, grade group) from unstructured MRI and biopsy reports using a zeroshot prompt. An RBA then classified pts into NCCN risk groups. The agent performance was compared with the treating clinician's documentation and evaluated against gold-standard labels manually annotated by two independent clinicians. For development of TRA, two experiments were performed using GPT4 with and without retrieval-augmented generation (RAG) to generate treatment plans. Generated treatment plans were evaluated using NCCN guideline-informed treatment decision tree based algorithm (DTA). Evaluation metrics, weighted – accuracy (acc) and F1, were computed. A clinician facing interface (lisr.org/risk) was developed to provide accurate risk stratification and treatment plans. Results: A total of 858 pts were included (500 for prospective validation, 358 for treatment recommendations). Prospective validation for RSA demonstrated a higher F1 score of 0.89 compared to the treating clinician (F1: 0.58). Treatment recommendation experiments showed that GPT4 with RAG achieved higher acc (64% full – all correct treatment options and 36% partial – at least 1 correct treatment option) compared to GPT4 alone (35% and 65%, respectively). Sensitivity analysis using DTA-informed GPT4 note generation achieved 94% full acc and 6% partial acc. GPT4 alone generated hallucinated treatment options in 71% of cases, while GPT4 with RAG reduced this to 32%. Conclusions: The multi-agent framework based on LLM and RBA achieves high accuracy in risk stratification and treatment recommendation for locPCa. A multi-agent framework with an interactive interface holds high promise to enable efficient, accurate decision-making, and improve locPCa management at the point of care Performance evaluation. RSA(acc; F1) % TRA(full acc; partial acc) % Clinician RSA* GPT4 RAG+GPT4 DTA+GPT4 Overall 60; 58 89; 89 29; 71 64; 36 94; 6 V. High 94; 33 96; 96 55; 45 69; 31 93; 7 High 46; 52 92; 89 - - - Int. Unf 80; 61 91; 90 5; 95 38; 62 93; 7 Int. Fav 57; 64 84; 87 0; 100 98; 2 100; 0 Low 57; 65 87; 80 100; 0 95; 5 90; 10 V. Low 8; 13 50; 67^ - - - *Statistical significance (p<0.01) except for ^V. Low.

4516 Background: Ipilimumab/nivolumab (ipi/nivo) is a standard of care first-line treatment (tx) for patients (pts) with mccRCC; however, ideal timing of subsequent immunotherapy txs are not well defined. We performed an analysis of patients initially treated with ipi/nivo and subsequent cohort assignments on PDIGREE (A031704). Methods: The PDIGREE trial treated pts with IMDC intermediate/poor risk mccRCC with first-line ipi/nivo (Step 1) at NCTN sites (categorized as academic (A), academic regional (R), and community (C)). Subsequent management was based on iRECIST responses at 12 weeks: pts with complete response (CR) received 1-year nivo maintenance; pts with progressive disease (PD) received cabozantinib (cabo) monotherapy, pts with non-CR/non-PD were randomized to nivo with or without cabo (for primary endpoint of overall survival [OS], target sample size was 1175). Enrollment was held when the randomized sample target was reached. Pts with unresolved toxicity at week 22 were managed off protocol. Step 1 pt demographics, assignments into Step 2, and adverse event (AE) data are presented. Descriptive statistics were used, and cohorts were compared using a chi-square test. These data were released with DSMB approval and do not inform the primary OS endpoint (1EP). Results: From May 2019 to May 2024, 1111 pts were enrolled and treated with ipi/nivo. Pt characteristics included median age 64.0 years (range 29.0-86.0); 819 (73.7%) males; White (85.1%), Hispanic (10.4%), Black (4.2%), and American Indian/Native Hawaiian (1.3%); 849 (76.8%) intermediate risk/257 (23.2%) poor risk; 458 (41.2%) at Academic, 113 (10.2%) at Regional, and 540 (48.6%) at Community centers; and 603 (54.3%) with de novo metastases. 364 pts (33%) stopped tx in Step 1: 160 (44%) for AEs, 46 (13%) for PD/clinical PD/suspected PD, 42 (12%) withdrawals, 39 (11%) alternative txs, 37 (10%) deaths on the study, 12 (3%) other complicating disease, 8 (2%) MD decision and 19 (5%) other reasons. Of the 37 deaths, 15 (1.4%) grade 5 SAEs were reported, 6 of which were due to PD. Of 747 (67%) pts registered to Step 2 at 3 months, 9 (1.2%) achieved CR, and 141 (18.9%) pts were assigned to the PD cohort. 597 pts (80%) were randomized for the 1EP, notable with fewer pts with poor risk [(21 vs 27%, p = 0.01] and bone metastases [24.5% vs 34.2%, p = 0.0007] compared to Step 1 pts who discontinued tx. Gr 3/4 tx-related AEs in 314/1093 (29%) evaluable pts included diarrhea/colitis (8%), transaminase elevation (3%), rash (2%), adrenal insufficiency (2%), fatigue (2%), and hypophysitis (1%). Conclusions: The PDIGREE trial enrolled a representative US-based population with mccRCC. Step 1 pt characteristics and associated outcomes with induction ipi/nivo reveal new insights into the tolerability and tx response of 1L ipi/nivo. Clinical trial information: NCT03793166 .

4545 Background: The treatment landscape of front-line nccRCC has evolved with recent trials demonstrating the efficacy of combination systemic therapy. However, the efficacy of treatment after combination therapy is unknown. This study evaluates the efficacy of VEGF-based regimens in nccRCC patients (pts) previously treated with combination regimens. Methods: ORACLE is a real-world, multi-center, retrospective database that includes nccRCC patients that received combination systemic therapies (IO+IO, IO+VEGF and VEGF+ mTOR) in any line. Subsequent treatments were categorized as VEGF only regimens (cabozantinib vs other VEGF), IO+ VEGF and VEGF+ mTOR. The primary endpoint was objective response rate (ORR) assessed by investigator review using RECIST 1.1. Secondary endpoints included disease control rate (DCR), defined as the proportion of patients achieving complete or partial responses or stable disease, time to treatment progression (TTP), calculated from the date of VEGF-based initiation to progression or last follow-up using the Kaplan-Meier method. Differences between groups were estimated with the log-rank test, and categorical outcomes were compared with the chi-square test. Results: 105 pts who received VEGF – based regimens after combination therapy were included in the analysis. Baseline characteristics: median age: 59years, 71 % male, 58% white, 25% black, 87% ECOG 0-2. IMDC-risk categories included:21% favorable, 59% intermediate and 20% poor risk. Histology included papillary (40%), unclassified (32%), chromophobe (16%) and other rare subtypes (12%). Prior combination therapies included IO+IO: 62%, IO+ VEGF: 34% and VEGF+ mTORi:4%. 70% pts received combination therapy in the first line setting while the remainder received combination therapy in a second or later line. Outcomes with subsequent treatments are described in Table1. IMDC risk score correlated with TTP. Conclusions: Modest antitumor activity was observed with VEGF- based approaches in combination therapy refractory nccRCC. Optimal management of nccRCC remains an unmet need. Outcomes of nccRCC patients by treatment and histologic type. Outcomes per Treatment n ORR (%) DCR (%) mTTP (mo.) Cabozantinib 56 18 47 3.6 VEGF/mTOR 19 16 42 9.3 IO+VEGF 17 29 47 5.6 Other VEGF 13 15 46 5.5 Outcomes per Histology Papillary 42 19 43 6.5 Unclassified 33 21 42 6.1 Chromophobe 17 29 59 8.9 Other * 13 0 46 NR

341 Background: Specialist clinicians (oncologists, urologists, radiation oncologists) read through free text reports of prostate MRI and biopsy reports to risk stratify patients during initial consultation of localized PCa. This laborious and time-consuming process is repeated for each day during the clinic. Herein, we propose a hybrid stratification framework utilizing a combination of large language model (LLM) and rule-based programming to automate this process. Methods: This retrospective study included patients with localized PCa (2004-2024) presenting to care at Mayo Clinic with at least one positive prostate biopsy and MRI report available. The state-of-the-art LLM – GPT4 – was utilized using a structured zeroshot prompt to extract relevant phenotypic variables (clinical T stage, Gleason patterns, grade group, extent of specimen/cores involved, prostate size/volume) from unstructured MRI and biopsy reports. Using a rule-based algorithm, the extracted variables and PSA at PCa diagnosis were used to categorize each patient into one of the six NCCN risk categories (very low [VL], low [L], favorable intermediate [FInt], unfavorable intermediate [UFInt], high risk (HR), very high risk [VHR]). Prompts were iteratively developed using ~5% of the total dataset and validated on ~10% of the dataset. Final performance was assessed against a held-out expert annotated test dataset using evaluation metrics (accuracy, F1-score, precision, recall). Additionally, manual annotation was conducted by two independent novice reviewers to compare machine annotated and novice-human annotated risk categorization. Results: A total of 397 patients were included in the evaluation. The median age at diagnosis was 64.8 (IQR: 59.7-68.5); majority of the men were White (n: 366; 92%) and non-Hispanic (n: 371; 94%). The most prevalent risk category was UFint (n: 151; 38%) followed by FInt (n: 80; 20.2%), HR (n: 76; 19.1%), VHR (n: 64; 16.1%), L (21: 5.3%), and VL (n: 5; 1.3%). Novice reviewers achieved an accuracy of 79%, precision of 80%, recall of 82% and a F1-score of 0.81. The hybrid stratification framework using GPT4 achieved an accuracy of 89%, precision of 89%, recall of 88% and a F1-score of 0.88. Among 43 errors by GPT4 risk stratification, majority of the errors were due to miscategorization of clinical T-stage (n: 21; 49%) followed by erroneous number of positive cores (n: 13; 30%). However, additional evaluation showed that GPT4 achieved numerically higher performance (accuracy: 90%; precision: 91%; recall: 90%; F1: 0.90) compared to novice reviewers (accuracy: 77%; precision: 89%; recall: 77%; F1: 0.82) for ascertaining clinical T-stage. Conclusions: Large language models exhibited superior performance than novice clinicians for risk stratification in patients with localized PCa. As the next step, we intend to validate our framework for automated risk classification in a prospective manner.