Hou, Alicia

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.

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.

1615 Background: Immune checkpoint inhibitors (ICIs) have revolutionized lung cancer treatment but cause adverse events, including immune-related colitis (ir-colitis). Accurate identification of ir-colitis is critical for improving patient outcomes and clinical research. However, current methods relying on ICD codes have substantial limitations: non-specific categories that fail to capture the cases or distinguish cases from infectious or ischemic etiologies, as well as incomplete coding that leads to missed cases. Large language models (LLMs), with advanced natural language understanding capabilities, offer a scalable approach for automated phenotyping using unstructured clinical notes. We aimed to develop and evaluate an LLM-based approach for identifying ir-colitis in patients with lung cancer receiving ICIs and compare it with ICD code based method. Methods: We identified 5,278 lung cancer patients with ICI administration at Mayo Clinic (2012-2025). To investigate ir-colitis occurrence within two years after ICI initiation, patients were stratified into three ICD-based cohorts: (1) IR-Colitis, with clinician-assigned ir-colitis-specific diagnosis codes; (2) Non-IR Colitis, with colitis diagnosis codes excluding ir-colitis; and (3) No-Colitis, absent of any colitis-related codes. We used three open-source LLMs to process clinical notes : Llama4, MedGemma, and Qwen. Prompts were designed to extract both gold standard evidence (explicit ir-colitis terminology, such as "immune-mediated colitis" and "checkpoint inhibitor colitis") and supportive evidence (such as pathology and lab results). Results: Llama4 demonstrated superior accuracy among three LLMs in manual evaluation and was thus selected for all cohort analyses. Among ICD-based IR-Colitis patients (n = 339), 82.0% had confirmatory evidence while 18% lacked evidence, suggesting potential false-positive coding. In the Non-IR Colitis cohort (n = 297), LLM-based extraction identified 43.8% patients in fact had ir-colitis, demonstrating substantial misclassification. In the No-colitis cohort (n = 4,642, random sample of 996 for analysis), the LLM identified 10.7% with documented ir-colitis, revealing substantial missing by administrative coding. Conclusions: LLM-based phenotyping demonstrates superior sensitivity for identifying ir-colitis compared to ICD codes alone, successfully uncovering cases missed by administrative coding. This scalable approach enables more comprehensive case identification for immunotherapy safety research and clinical surveillance. ICD-Based Cohorts LLM-Identified ir-Colitis Gold Standard Evidence Supportive Evidence Any Evidence ir-Colitis (n = 339) 277/339 (81.7%) 275/339 (81.1%) 278/339 (82.0%) Non-ir-Colitis (n = 297) 129/297 (43.4%) 126/297 (42.4%) 130/297 (43.8%) No Colitis (n = 996) 106/996 (10.6%) 104/996 (10.4%) 107/996 (10.7%)