Citations

866 Background: Emerging data suggests that Language Models (LLMs) provide an unprecedented opportunity to extract critical data from the unstructured pathology reports. However, the performance of state of art (SOTA) models on clinically meaningful tasks such as assessment of pathologic responses in patients receiving neoadjuvant chemotherapy (NAC) in muscle invasive bladder cancer(MIBC) is not well known. Methods: This retrospective cohort included patients with pathologically confirmed Muscle-Invasive Bladder Cancer from the year 2018 to 2024. Selected patients included those who underwent Neoadjuvant chemotherapy followed by definitive cystectomy at Mayo Clinic. Gold standard labels were manually curated by trained clinicians. The state of the art (SOTA) LLM – GPT4 – was utilized using a structured zero-shot prompt to extract relevant phenotypic variables such as tumor site, tumor histology and additional histological variants if any, presence of in-situ / invasive carcinoma, presence of lamina propria / muscularis propria / lympho-vascular / perineural invasion, and T-stage from unstructured pathology reports. Structured prompts were iteratively developed for each data variable and validated using ~5% of the total dataset. The extracted variables were manually compared and labelled as True positive / True negative / False positive / False negative. Final performance was assessed against a held-out expert annotated test dataset using evaluation metric (accuracy). Results: A total of 200 reports from 99 patients were extracted by the LLM. Of the 200 reports, 41 duplicate / other pathology reports (e.g. – autopsy, cholecystectomy, etc.) were removed during final assessment. Significant characteristics such as tumor site, histology, and additional histology variant had an accuracy of 89%, 87%, and 91% respectively. Notably, accuracy of detection of in-situ versus invasive carcinoma was 70% versus 91%. Specific variables such as lamina propria / muscularis propria invasion / T-stage / lympho-vascular invasion / perineural invasion were answered with the accuracy of 75%, 75%, 67%, 90%, and 94% respectively. Conclusions: LLMs have the potential to extract critical data from unstructured pathology reports and automate assessment of pathologic responses in MIBC patients receiving NAC. Iterative improvements in performance can be achieved by improving prompt design using expert clinical input. This process can be potentially scaled to automate cancer registries.

831 Background: Long non-coding RNA (lncRNA)-based genomic profiling has suggested utility to identify a distinct tumor subgroup corresponding to a favorable prognosis in patients with bladder cancer. Here, we further evaluate a genomic classifier in a cohort of patients undergoing radical cystectomy (RC). Methods: Transcriptome-wide expression profiling using Decipher Bladder was performed on TURBT samples from a cohort of patients with high grade, clinically organ confined (cTa-T2N0M0) UC who subsequently underwent RC without any neoadjuvant therapy (n=226). LncRNA-based luminal favorable status was determined using a previously developed genomic classifier. The primary endpoint was overall survival (OS) following surgery. Secondary endpoints included cancer-specific mortality and upstaging at RC. Results: In the study, 134 patients were clinical NMIBC (cTa/Tis/T1) and 92 patients were cT2. We identified 60 patients with luminal favorable subtype, all of which showed robust gene expression patterns associated with less aggressive bladder cancer biology. On MVA, patients with the luminal favorable subtype (vs. without) were significantly associated with lower odds of upstaging to pT3+ disease (OR [95% CI] 0.32 [0.12-0.82], p = 0.02), any upstaging (OR [95% CI] 0.41 [0.20-0.83], p = 0.01), and any upstaging and/or pN+ (OR [95% CI] 0.50 [0.25-1.00], p = 0.05). Luminal favorable bladder cancer was significantly associated with better OS (HR 0.33 [95% CI 0.15-0.74], p=0.007). Conclusions: This study validates the performance of the genomic classifier for identifying urothelial carcinomas with a luminal favorable subtype, harboring less aggressive tumor biology.

428 Background: Prostate cancer management presents a significant healthcare burden, with the need to efficiently triage patients for treatment. Our objective is to leverage large language models to predict physician-recommended treatment plans from unstructured clinical notes. By accurately predicting treatment plans, we aim to risk stratify and triage patients effectively, thereby optimizing the allocation of physician resources. Methods: 448 unstructured initial urology consultation patient notes following first positive prostate cancer biopsy were identified. The recommended and final treatments received were manually annotated to establish ground truth labels (Table 1). The dataset was split 80:20 for training and testing, preprocessed to remove plan sections and formatted into question-answer (QA) format. A domain-specific large language model (LLM) inspired by GPT and a specialized tokenizer (PCa- LLM) for prostate cancer terminology were developed. QA models were built using the PCa-LLM and compared with those using GPT-2 as the backbone to predict recommended and final treatments. Results: For the physician-recommended treatment plans, our LLM (PCa-LLM) showed superior performance with higher AUROC scores for curative vs. non-curative treatments (0.78 vs. 0.65), chemo-hormonal vs. other non-curative treatments (0.89 vs. 0.65), and surveillance vs. all other treatments (0.72 vs. 0.70), while both models achieved the same high AUROC of 0.99 for chemo-hormonal vs. all other treatments. For final treatments, PCa-LLM demonstrated better AUROC for curative vs. non-curative treatments (0.77 vs. 0.74) and chemo-hormonal vs. other non-curative treatments (0.71 vs. 0.66), while GPT2 outperformed PCa-LLM for surveillance vs. all other treatments (0.78 vs. 0.70). Both models achieved an AUROC of 0.99 for chemo-hormonal vs. all other treatments. Conclusions: PCa-LLM accurately predicted most treatment categories better than GPT2, with higher AUROC scores, and can be utilized to triage prostate cancer patients using initial consultation notes. Task Physician -Recommended Treatment Plan Final Treatment Received Curative Prostatectomy/Radiation 228 230 Non-Curative Focal Therapy 22 15 Active Surveillance 40 45 Chemo-hormonal 30 30 Model Predictions (AUROC) GPT2 PCa-LLM GPT2 PCa-LLM Curative vs. non-curative 0.65 0.78 0.74 0.77 Chemohormonal vs. other non-curative 0.65 0.89 0.66 0.71 Chemohormonal vs. all other 0.99 0.99 0.99 0.99 Surveillance vs. other non-curative 0.64 0.60 0.67 0.59 Surveillance vs. all other 0.70 0.72 0.78 0.70

425 Background: Prostate cancer (PC) ranks among the most prevalent cancers in men, with incidence rising due to factors like aging populations and enhanced screening techniques. Effective data extraction from clinical records is crucial for advancing research and improving patient care; however, traditional manual methods can be time-consuming and susceptible to mistakes. This study seeks to evaluate RadOnc-GPT against human annotation for extracting essential clinical information from prostate cancer clinical records. Methods: RadOnc-GPT is a retrieval augmented generation (RAG)-based chatbot with access to a variety of patient data including treatment details, radiology reports, and clinical notes. RadOnc-GPT uses Open AI’s gpt-4o model. Patients who received curative intent radiotherapy as initial treatment for PC in our institution between 2014 and 2023 were randomly selected for evaluation. Relevant Clinical factors were extracted by a human expert annotator on our on-site RedCap database. The extraction of the same variables was performed using RadOnc-GPT. A comparison between the ground truth (human annotation) and RadOnc-GPT, to evaluate the performance of the AI system, was carried out including accuracy, recall and F1 score. Results: A total of 382 PC patients were included in the cohort for data extraction. The clinical variables extracted were the treatment intent, NCCN risk category, T and N stage, Gleason score, radiation volume, and Androgen Deprivation therapy (ADT) use. The overall performance of RadOnc-GPT was excellent, with the highest accuracy achieved for treatment intent (99.7%), Gleason score (98.4%), and Treatment Volume (90.1-99.5%). Conclusions: RadOnc-GPT performed excellent at extracting relevant clinical details from the electronic medical record and radiation oncology information systems with dramatic reduction in time and cost compared with manual review. LLMs could be highly useful for large-scale data extraction in PC research, offering a promising solution for automating the accurate data extraction process. Correct (n) Total (n) Accuracy Recall F1 score RT with curative intent 381 382 99.7 99.9 99.9 Prostate Cancer Risk Category 345 382 90.3 90.4 95.1 Primary tumor staging (T) at diagnosis 368 382 96.3 96.3 97.9 Regional nodal status (N) at diagnosis 352 382 92.1 92.2 95.9 Gleason Score Primary Secondary Total 376372376 382382382 98.497.498.4 98.597.498.5 99.298.799.2 Treated Areas Prostate Pelvic Nodes Para-Aortic Nodes Distant Site 380344378372 382382382382 99.590.19997.4 99.490.199.197.4 99.79599.598.7 ADT Use with RT 365 382 95.5 95.7 97.8

424 Background: Advances in prostate cancer (PC) care have led to a 98% 10-year survival rate. Prostate Specific Antigen (PSA) is the primary method of follow-up after definitive radiotherapy (RT), with benign PSA ‘bounce’ occurring in up to 30% of patients, causing uncertainty and anxiety. Distinguishing between PSA bounce and biochemical recurrence (BCR) remains challenging. The Phoenix Criteria is the standard definition of BCR since 2006, defined as PSA nadir + 2 ng/dl, but does not consider patient specific information. Our study aims to explore factors associated with bounce and BCR and develop a predictive tool to differentiate between these two events. Methods: PC patients who received RT at our institution between 2006 and 2022 were identified, including only patients with a PSA increase during follow-up. Exclusion criteria included palliative RT, prostatectomy, or insufficient follow-up information. Patients’ clinical data was collected, and PSA increase was classified as bounce or BCR. Variables were compared using Kruskal Wallis or Chi-square. Multivariate logistic regression was performed in the subset of patients with absolute PSA value >2 (n= 581). Results: Of 1783 patients reviewed due to PSA rise after treatment, 694 met the inclusion criteria. There were 213 (30.7%) with PSA bounce and 481 (69.3%) with recurrence. Prior to meeting the Phoenix Criteria, 20 (4.2%) had biopsy-proven recurrence and 18 (3.7%) imaging-proven recurrence. The median delta PSA was 0.8 ng/mL for bounce vs 5 ng/mL for recurrence (p<0.001). The median time from treatment to event was 14.4 months for bounce vs 45.3 months for BCR (p<0.001). Recurrence was significantly associated (p<0.001) with older age at diagnosis, N1 stage, higher risk category, Gleason score, and higher baseline PSA. In the subgroup of patients without ADT, recurrence was associated with a lower median first PSA post-RT (1.9 vs. 2.4, p=0.046) and a lower median nadir before event (0.6 vs. 1.8, p<0.001). Multivariate logistic regression achieved an accuracy of 0.94, with a sensitivity of 0.83, specificity of 0.98, and an area under the curve (AUC) of 0.97. Conclusions: Our results highlight significant differences in clinical factors between bounce and recurrence in post-RT patients. The multivariate logistic regression differentiated the events with 94% accuracy for patients with a rising PSA value >2 subgroup. We highlight the possible improvement that could be accomplished by personalizing a PSA threshold for recurrence versus the Phoenix definition. This tool offers patients and providers a highly specific tool to differentiate between PSA recurrence and bounce, and may reduce stress and unnecessary testing, or help diagnosis recurrence faster. Next steps include prospective validation of the model to assess the impact on clinical practice costs, patient experience, and cancer outcomes.

Key Points Patient-centered care in an interdisciplinary CKD clinic addresses complex needs and supports comprehensive CKD management. Implementation of an interdisciplinary CKD clinic reduced hospital admissions by 26%, emergency department visits by 30%, and increased nephrology consultations. Comprehensive care models with integrated registries enhance tailored interventions, leading to improved CKD management outcomes. Background CKD is a significant public health issue globally. Its progressive nature calls for innovative care models to mitigate disease progression and enhance patient outcomes. An interdisciplinary clinic model may offer comprehensive care tailored to the needs of patients with CKD. The aim of this study was to evaluate the effect of an interdisciplinary CKD clinic on disease progression, health care utilization, and social determinants of health (SDOH). Methods We conducted a retrospective cohort study at the Mayo Clinic in Rochester, Minnesota. The study included 534 patients enrolled in the CKD clinic between March 5, 2021, and May 31, 2022, excluding those who opted out of research. The intervention involved a clinical registry and an interdisciplinary team delivering evidence-based care pathways, patient education, shared decision making, and care coordination. The primary outcomes assessed were CKD progression and health care utilization, while secondary outcomes examined the effect of SDOH. Results At entry, the median age was 73 (interquartile range, 64–79) years, with 60% at stage 4 or lower. Clinic implementation correlated with a 26% decrease in hospital admissions (incidence rate ratio [IRR], 0.74; 95% confidence interval [CI], 0.60 to 0.91; P = 0.004) and a 30% reduction in emergency visits (IRR, 0.70; 95% CI, 0.57 to 0.87; P = 0.001). Nephrology consultations increased by 46% (IRR, 1.46; 95% CI, 1.34 to 1.60; P < 0.001), reflecting enhanced specialized care. Lower exercise frequency and unemployment were linked to increased CKD progression and health care usage. Conclusions An interdisciplinary CKD clinic supported by a registry can potentially reduce health care utilization among patients with CKD, with SDOH playing a critical role in disease management.

Abstract Purpose: Tumor-infiltrating lymphocytes are associated with a decreased risk of recurrence in human papillomavirus–associated oropharyngeal squamous cell carcinoma. The composition and spatial distribution of tumor-infiltrating lymphocytes and tumor-infiltrating immune cells are not well characterized. Experimental Design: Formalin-fixed, paraffin-embedded primary and lymph node (LN) tumor tissues from 10 progressors (cases) and 10 matched nonprogressors (controls) were interrogated by imaging mass cytometry. Immune, stromal, and tumor cells were quantified from selected regions of interest using machine learning. Nearest neighbors, cell–cell interactions, and niche analyses were performed. Results: In primary regions of interest, immune cell, lymphocyte, T cell, CD8+ T cell, and innate cell prevalence was significantly greater in controls. High prevalence of immune cells, lymphocytes, innate cells, and CD4+ T cells in primary tissues was significantly associated with increased time to event (TTE). Although primary and LN prevalence of T cells, CD4+ T cells, CD8+ T cells, macrophages, and tumor cells were significantly correlated, differences in LNs were neither significant nor associated with TTE. Average distances between T cells and the nearest B cells and between lymphocytes and the nearest tumor cells were decreased in control primary tissues. Interactions between B and T cells were less organized in primary tissues from cases. A niche predominantly comprising lymphocytes was associated with longer TTE. Conclusions: In human papillomavirus–associated oropharyngeal squamous cell carcinoma, immune cell subset prevalence in primary tumors differs with outcome and is associated with TTE. Interactions between B cells and both T-cell subsets are associated with longer TTE, underscoring the importance of active intratumoral immune responses in outcomes.