Citations

e17168 Background: Prostate cancer is the most prevalent cancer and the second leading cancer related death in men in the USA. Radical prostatectomy represents the mainstay treatment for patients with localized prostate cancer. Management of metastatic disease requires multidisciplinary practice and innovative approach for individualized favorable outcomes. Treatment sequencing in patients with advanced prostate cancer has been reported to impact patient’s response to subsequent treatment as well as overall survival outcomes. Here in, we thought to investigate the impact of prior chemotherapy treatment on PSA response rates to 177Lut PSMA. Methods: We conduct a single center retrospective study including 164 patients diagnosed with advanced prostate cancer and treated with 177Lut PSMA for metastatic hormone resistant prostate cancer. 92 patients received 177Lut PSMA as a salvage treatment late after chemotherapy (group A), and we compared them with 70 patients received 177Lut PSMA early in an adjuvant fashion within 3 months after chemotherapy (group B). Favorable PSA response was defined by 50% or more reduction in PSA value after complete treatment with 177Lut PSMA. Results: Approximately 43 % of patients in (group B) received their 177Lut PSMA within six months. The average number of chemo cycles received by patients of (group B) is between 3 to 6 cycles. Median patients’ age (IQR) 63 years (57.75 - 68), median (IQR) number of cycles of 177Lut PSMA 5 (5 - 6). Statistical analyses were performed to determine any differences in post lut PSA response in both groups of patients. Approximately 49 % of patients in (group A) had favorable PSA response versus 44 % of patients in (group B) (p-value 0.3853). Conclusions: The use of 177Lut-PSMA in the post-chemotherapy setting demonstrated similar outcomes whether administered early or late. These findings suggest that the timing of treatment may not significantly impact its effectiveness, but further research is needed to confirm these results and explore potential optimizations for patient care.

e17159 Background: Socioeconomic inequality (SI) is a recognized risk factor for negative outcomes in prostate cancer (PCa), influenced by biology, healthcare access, and lifestyle. This study aims to explore the molecular impact of SI on PCa, focusing on targetable and prognostic biomarkers. Methods: We conducted a retrospective analysis of 100 metastatic hormone-sensitive PCa patients (2016-2023), with 97 undergoing next-generation sequencing (NGS). We examined only pathogenic variants alongside clinical variables. The Area Deprivation Index (ADI) assessed neighborhood SI, with higher scores indicating greater disadvantage. Patients were divided into tertiles. Chi-square and Fisher’s exact tests evaluated the relationships between tertiles and genomic alterations, while ordinal logistic regression analyzed outcomes by various stratifications. Results: Of the 97 patients, 29 were in tertile 1, 34 in tertile 2, and 35 in tertile 3. Tertile 1 had a significantly higher percentage of non-Hispanic patients (90%) compared to tertile 2 (62%) and tertile 3 (37%), p=0.0001. Other demographic factors, such as age, comorbidities, and cancer history, showed no significant differences by tertile. Median PSA levels increased from tertile 1 (22 ng/mL) to tertile 3 (95 ng/mL), although this was not statistically significant (p=0.14). Tumor volume and visceral metastasis were notably higher in tertile 3 (p=0.029 and p=0.02). BRCA1/2 mutations were more prevalent in tertile 3 (11%, p=0.03) via liquid biopsy compared to tertiles 1 and 2 (0%). TMPRSS2-ERG fusion mutations were significantly more common in tertile 3 (66.6%) compared to tertile 2 (19.1%) and tertile 1 (14.2%), p=0.009. The association between ADI tertile and TMPRSS2 approached significance when controlled for ethnicity (p=0.061), with Hispanic ethnicity having 3.5 times the odds of the fusion compared to non-Hispanics (p=0.02). Tertile 1 patients were more associated with receiving progressive therapy lines (2L p=0.01, 3L p=0.03, 4L p=0.04), but median time to subsequent treatment at 5 years was similar across tertiles (p=0.84). Conclusions: Higher SI was linked to increased PSA, tumor volume, visceral metastasis risk, and higher prevalence of BRCA1/2 and TMPRSS2-ERG mutations. This study highlights the need for further research on the molecular impacts of SI on adverse PCa outcomes, particularly among Hispanic populations.

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.

1593 Background: “Financial toxicity” refers to the financial burden imposed by treatment costs on individuals with cancer, constituting a major barrier to achieving equitable cancer outcomes. Recent literature increasingly demonstrates the detrimental impacts of financial toxicity on quality of life (QOL) among individuals with cancer, including individuals who have undergone hematopoietic stem cell transplantation (HSCT). This study evaluates associations among treatment cost burden and various aspects of QOL following HSCT. Methods: Seven hundred one HSCT recipients completed a survey examining their biopsychosocial health one year following transplant. The survey included the Functional Assessment of Cancer Therapy – Bone Marrow Transplantation (FACT-BMT), a multifactorial measure of QOL specific to this population. Treatment cost burden endorsement was measured on a 5-item Likert scale. Hierarchical regression models were developed to assess the incremental effects of demographic characteristics (i.e., Block 1), clinical predictors (Block 2), and cost burden (Block 3) on physical, emotional, social, functional, BMT-specific, general, and composite QOL outcomes. Results: Significant model improvement was observed with the addition of clinical factors ( ΔF(2,650) = 20.28, p < .001), and subsequently, treatment cost burden ( ΔF(1,649) = 110.29, p < .001). In the final model, higher cost burden was associated with poorer physical (β = -0.323, p < .001), emotional (β = -0.301, p < .001), social (β = -0.250, p < .001), functional (β = -0.317, p < .001), BMT-specific (β = -0.341, p < .001), general (β = -0.377, p < .001), and composite QOL (β = -0.381, p < .001). Poorer performance score was associated with each QOL indicator ( p < .001), with allogeneic transplant type associated with poorer functional (β = -0.001, p = .002), but higher emotional (β = 0.118, p = .002), wellbeing. Older age (β = 0.113, p = .003) and female sex predicted higher (β = 0.183, p < .001), while Hispanic ethnicity predicted poorer (β = -0.095, p = .010), social wellbeing. Female sex was associated with poorer QOL specific to BMT concerns (β = -0.118, p = .001). Conclusions: Higher treatment cost burden is associated with poorer overall QOL and its physical, emotional, social, functional, and BMT-specific components one year following HSCT, after controlling for demographic and clinical characteristics. This reflects a critical barrier to equitable cancer care, suggesting that financial toxicity may perpetuate preexisting inequities in QOL, treatment, disease, and survival outcomes that disproportionately impact the underserved. Future research should prioritize 1) better understanding relationships among complex indicators of financial toxicity, QOL, and their underpinning mechanisms and 2) developing solutions to mitigate financial toxicity of HSCT and overall cancer care.

1586 Background: Black and Hispanic breast cancer (BC) survivors have a higher prevalence of obesity and experience less success with weight loss interventions (WLI) than White BC survivors. The BWEL trial (Alliance A011401; NCT02750826) is a phase III randomized trial evaluating the impact of a 2-year telephone-based WLI on invasive disease-free survival in participants (pts) with stage II-III HER2-negative BC and a BMI ≥ 27 kg/m 2 . At 12-months, the WLI induced significant weight loss across demographic factors, including race and ethnicity. However, Black and Hispanic pts lost less weight and completed fewer calls than White pts. Here, we evaluate intervention adherence, engagement and tool utilization in BWEL pts by race and ethnicity. Methods: BWEL randomized pts to a WLI plus health education (HE) or HE alone. WLI pts received semi-structured telephone-based health coaching, delivered in English or Spanish, and received an activity monitor and wireless scale. Pts self-reported race and ethnicity. Mean values for call duration, call density (time to complete the initial 12-week intensive intervention phase), intervention attrition, and frequency of Fitbit use and weight tracking over 12-months were compared by race and ethnicity, comparing least squares means with Tukey-Kramer adjustment for multiple comparisons with adjusted p-values. Results: Of 3181 pts randomized to the study between 08/2016 and 02/2021, 1591 pts were allocated to the WLI arm. 80.5% of pts were White, 12.8% Black, and 7.1% Hispanic. Average BMI was 34.5 (±5.7) kg/m2. Compared to White pts, Black pts had fewer days of Fitbit usage (113.6 vs. 159.8, p<0.0001) and weight tracking (77.9 vs. 135.6 days, p< 0.0001). Hispanic pts had fewer days of Fitbit usage (108.8 vs. 154.9, p= 0.001) and weight tracking (87 vs. 129.5 days, p=0.0002) compared to non-Hispanic pts. There were no differences in attrition rate, average call duration, or call density by race or ethnicity. Conclusions: In a phase III WLI trial, engagement with tools designed to support weight loss was significantly lower in Black and Hispanic pts. Future work is needed to explore ways to enhance engagement and improve weight loss outcomes for racial and ethnic minority pts. Support: U10CA180821, U10CA180882, UG1CA189823; https://acknowledgments.alliancefound.org . Clinical trial information: NCT02750826 . Measure of engagement Race Ethnicity WhiteN=1281 BlackN=204 p-value Non-HispanicN=1459 HispanicN=113 p-value Withdrew from intervention n (%) 58 (4.5%) 13 (6.4%) 0.56 70 (4.8%) 6 (5.3%) 0.51 Call Duration (min)Mean (SD) 34.5 (7.6) 34.6 (9.1) 0.99 34.6 (7.8) 33.3 (7.9) 0.25 Call density(weeks)Mean (SD) 14.2 (7.2) 14.2 (8.8) 0.99 14.2 (7.3) 14.2 (9.7) 0.99 Days of Fitbit UseMean (SD) 159.8 (132.2) 113.6 (124.7) < 0.0001 154.9 (131.8) 108.8 (125.7) 0.001 Days of weight trackingMean (SD) 135.6 (109.5) 77.9 (87.5) < 0.0001 129.5 (108.8) 87 (96.5) 0.0002

e13661 Background: MM survival has improved significantly, resulting in increased survivorship and caregiver burden and is crucial to understand the real-world impact of MM. We analyzed results from a large, prospective MM patient survey using ML models to identify key predictive factors for survivorship and caregiver burden. Methods: A 45-item questionnaire spanning sociodemographics, treatment preferences, symptom burden and caregiver impact was distributed to MM patients at Mayo Clinic and International Myeloma Foundation support groups. Questions about quality of life (QOL) and treatment satisfaction (TS) represented survivorship outcomes while caregiver workday loss (WL) and job loss (JL) were surrogates for caregiver burden. 6 ML models (multinomial, random forest (RF), XGB (XGBoost), k-NN, GBM, Naïve Bayes) with a training: testing cohort of 80:20 were used to predict each of the 4 outcomes independently, considering model accuracy, C-index, precision, recall, and F1 score (Table), and using R studio (V4.4.1) and Bluesky Statistics (V10.3.4). Results: 2,239 participants (54% male, 89% Whites) with median age 68 yrs completed the survey. 71% respondents had a college degree, 44% resided in Midwest states, 62% reported household income >$75,000, and 67% had Medicare/Medicaid. Median age at MM diagnosis was 67 yrs with 58% diagnosed within the past 5 yrs and 73% currently receiving MM treatment. 72% reported their spouse as the primary caregiver. XGB was the best predictive model for QOL with gender, household income, stem cell transplant, CAR-T therapy, support from medical staff, and symptom burden (pain, neuropathy, mental well-being) as significant predictors. The RF model was the best for TS with pain and neuropathy levels as the most impactful predictors. For caregiver burden, XGB was the best model for WL with gender, household income, CAR-T therapy, financial strain, lack of support from medical staff, self-workdays missed, self-job loss, and pain and neuropathy levels as significant predictors. For JL, RF was the best model with significant variables being workdays missed by self, increased healthcare needs, symptom burden (pain, neuropathy, and mental well-being), and restricted physical activity. Conclusions: Our study shows the significant impact of MM survivorship and efficiently identifies predictive factors associated with survivorship and caregiver burden from a large prospective dataset using validated ML models. These findings highlight the complex challenges from MM and provide contemporary ML methods to better understand their interplay such that a framework of real-world interventions can be developed. Outcome Best ML Model Accuracy C-Index Precision Recall F1 score QOL XG 0.996 0.996 0.996 0.997 0.996 TS RF 0.984 0.900 0.937 0.948 0.937 WL XGB 0.984 1.000 0.944 0.947 0.945 JL RF 0.989 0.800 0.829 0.848 0.835

e13656 Background: Evidence-based medicine is crucial for clinical decision-making, yet studies suggest that a significant proportion of treatment decisions do not fully incorporate the latest evidence. Large Language Models (LLMs) show promise in bridging this gap, but their reliability for medical recommendations remains uncertain. Methods: We conducted an evaluation study comparing five LLMs’ recommendations across 50 clinical scenarios related to multiple myeloma diagnosis, staging, treatment, and management. The evaluation included three general-purpose LLMs (OpenAI o1-preview, Claude 3.5 Sonnet, Gemini 1.5 Pro), one retrieval-augmented generation (RAG) system (Myelo), and one agentic workflow-based system (HopeAI). General-purpose LLMs generated responses based solely on their internal knowledge, while the RAG system enhanced these capabilities by incorporating external knowledge retrieval. The agentic workflow system extended the RAG approach by implementing multi-step reasoning and coordinating with multiple tools and external systems for complex task execution. Three independent hematologist-oncologists evaluated the LLM-generated responses using standardized scoring criteria developed specifically for this study. Performance assessment encompassed five dimensions: accuracy, relevance, comprehensiveness, hallucination rate, and clinical use readiness. Results: HopeAI demonstrated superior performance across accuracy (82.0%), relevance (85.3%), and comprehensiveness (74.0%), compared to OpenAI o1-preview (64.7%, 57.3%, 36.0%), Claude 3.5 Sonnet (50.0%, 51.3%, 29.3%), Gemini 1.5 Pro (48.0%, 46.0%, 30.0%), and Myelo (58.7%, 56%, 32.7%). Hallucination rates were consistently low across all systems: HopeAI (5.3%), OpenAI o1-preview (3.3%), Claude 3.5 Sonnet (10.0%), Gemini 1.5 Pro (8.0%), and Myelo (5.3%). Clinical use readiness scores were relatively low for all systems: HopeAI (25.3%), OpenAI o1-preview (6.0%), Claude 3.5 Sonnet (2.7%), Gemini 1.5 Pro (4.0%), and Myelo (4.0%). Conclusions: This study demonstrates that while current LLMs show promise in medical decision support, their recommendations require careful clinical supervision to ensure patient safety and optimal care. Further research is needed to improve their clinical use readiness before integration into oncology workflows. These findings provide valuable insights into the capabilities and limitations of LLMs in oncology, guiding future research and development efforts toward integrating AI into clinical workflows.

e13637 Background: Large language models (LLMs) like GPT-4 (OpenAI) and Claude Opus (Anthropic) showed high accuracy in medical multiple-choice exams, but data on their oncology-specific clinical reasoning and performance is limited. This study evaluates their accuracy and clinical reasoning on breast oncology multiple-choice questions (MCQs) from the American Society of Clinical Oncology (ASCO) question bank. Methods: Using OpenAI and Anthropic Application Programming Interface (APIs), questions were tested without additional prompts under consistent settings (GPT-4 and Claude Opus; Temperature = 0, Tokens = Max). Each question was tested three times to assess precision. Then, Chain-of-thought (COT) prompting was applied to promote LLMs stepwise reasoning to increase their accuracy. Accuracy before and after COT prompting was compared. Incorrect responses were reviewed by board-certified medical oncologists speclized in breast cancer, who scored reasoning clarity, bias, and clinical relevance. Qualitative feedback was descriptively analyzed. Results: A total of 273 breast oncology MCQs were evaluated across the two LLMs. GPT-4 achieved an initial accuracy of 81.3% (222/273; 95% CI: 76.3%-85.5%), compared to Claude Opus, which achieved an accuracy of 79.5% (217/273; 95% CI: 74.3%-83.9%). The Chi-squared test for difference between the models before chain-of-thought (COT) prompting yielded a p-value of 0.59, indicating no statistically significant difference in accuracy between GPT-4 and Claude Opus prior to COT prompting. After COT prompting, the performance of the two models diverged significantly. GPT-4 saw a net decline in accuracy, decreasing by a net of 1 correct answer, resulting in an overall accuracy of 80.95% (221/273). In contrast, Claude Opus experienced a notable improvement, with a net of 19 additional correct answers, leading to an accuracy of 86.4% (236/273). A statistical analysis using a Chi-squared test revealed a difference in accuracy between the two models of 5.5% (p = 0.08), demonstrating that the improvement in accuracy for Claude Opus after COT prompting was borderline statistically significant compared to GPT-4. Thematic analysis of oncologists' feedback revealed that the most common reasons for incorrect answers were reliance on outdated guidelines, misinterpretation of clinical trial data, and failure to consider multidisciplinary or patient-specific approaches in clinical decision-making. Conclusions: Although AI models can achieve high scores on multiple-choice exams, they still require human supervision. These models rely on potentially outdated training data and lack the ability to individualize patient care or apply data from clinical trials. especially in unique or unconventional/non textbook scenarios.

e13622 Background: Chimeric antigen receptor T-cell (CAR-T) therapy has revolutionized treatment of hematologic malignancies; however, severe toxicities like cytokine release syndrome (CRS) remain a limitation to broader utilization. Using a large dataset of patients treated with CAR-T, we developed a machine learning (ML) model leveraging multi-model patient characteristics to predict the risk of CRS onset with clinically meaningful lead times. Methods: A prospectively maintained dataset of CAR-T patients treated at Mayo Clinic was used. Baseline disease/patients characteristics, labs, ECG, echocardiogram, and vital signs (including data from remote patient monitoring program) were collected. A 24-hour rolling window was used to generate daily averages, maximum, minimum, and deltas for each parameter. ECG and echocardiogram data were forward-imputed; vital signs and labs were not imputed. Each day-post-infusion served as a potential event (CRS onset vs. no CRS). A gradient boosting classifier was trained and tested on a subset of patients (n = 351) using 1,000 bootstrap iterations, evaluating 24-, 48-, and 72-hour lead times. Shapley-based feature importance guided simplification to an 11-feature model, externally validated on an independent cohort (n = 51). Models’ performance assessed using the area under the receiver operating characteristic curve (AUC). Results: A total of 402 patients treated with CAR-T were examined. Median age was 64 years and 36% were female. Primary diagnosis was B-cell lymphoma (n = 240) or multiple myeloma (n = 162). A total of 226,332 vital sign measurements and 372,871 lab values, as well as ECG and echocardiogram data, were collected for 30 days post-infusion. Overall, 79.8% of patients experienced CRS within 30 days. The full ML model demonstrated AUCs of 0.90 (95% CI 0.86–0.93), 0.83 (95% CI 0.77–0.88), and 0.82 (95% CI 0.77–0.87) for 24-, 48-, and 72-hour predictions of CRS, respectively. Including “day of CRS onset post CAR-T” as a feature improved the 72-hour AUC to 0.87 (95% CI 0.83–0.90). A model restricted to vital signs alone showed AUCs of 0.88, 0.75, and 0.71 for 24-, 48-, and 72-hour horizons. An 11-feature model—focusing on temperature, blood pressure, fibrinogen, CRP, serum sodium level, QRS interval, and lymphocyte counts—maintained high accuracy at 24 hours (AUC 0.90, 95% CI 0.86–0.93) and was validated externally using an independent dataset with an AUC of 0.92. Conclusions: Our ML model provides a reliable approach for predicting if/when CRS will occur, with up to three days of lead time before clinical manifestation, offering an opportunity for proactive management. The robust performance of a parsimonious 11-feature model supports practical adoption across clinical settings and real-time risk stratification to enhance patient safety. Prospective validation and integration into clinical workflows will be critical to translating these findings into practice.

e13551 Background: The landscape of cancer care is evolving rapidly. In 2023, there were 83 new FDA oncology approvals, and 145 interventional treatment (tx) studies opened across Mayo Clinic. We are exploring novel precision outreach approaches utilizing an LLM-integrated chatbot application to “ping” patients (pts) with specific clinical or genomic characteristics about newly available drugs or clinical trials. As novel outreach methods are considered, we surveyed a patient (pt) support group to understand communication preferences and awareness of adjuvant CDK4/6 inhibitors in tx of breast cancer (BC). Methods: On October 7, 2024, we administered a cross-sectional survey to 41 members of the Breast Cancer Support Network (BCSN) in Rochester, MN as a part of an IRB exempt quality improvement project. Leaders of the BCSN shared information to all participants, noting that the survey’s intent was to represent the pt voice and participation was voluntary. Anonymous survey data were collected with descriptive results reported. Results: 34/41 participants in the BCSN shared demographic information. The majority (83%) were > 50 years of age. 47% reported stage I BC, 12% stage II, 6% stage III, and 35% were unsure of their stage. Most participants (26/34, 76%) reported that their BC was hormone receptor positive (HR+), 2 HER-2 positive, and 6 unsure of their BC receptor status. 24/26 (92%) of pts with HR+ BC were taking or planning to start adjuvant endocrine therapy. 10/34 (29%) were aware that adjuvant CDK 4/6 inhibitors were approved. Of these 10 participants, 2 learned of it from online health resources, 6 from their clinician, 1 from social media, and 1 from a support group. The majority (66%) were unsure if they qualified for these drugs. Regarding receipt of information on new drug approvals/tx options, the highest ranked communication preference was to receive this information in person at an upcoming visit (ranked 1st by 50% of participants), followed by EHR-based message (28%), email (10%), phone call (6%), letter (4%), or an interactive chatbot (0%). Most respondents noted that communication from their healthcare provider was very important (30/37, 81%), with others stating that this was somewhat important (5/37, 14%) or neutral (2/37, 5%). Most noted that receiving information about tx options via video or visual aid before a visit would be very helpful (33/41, 80%). When asked about follow up after learning of a new drug approval, 17/32 (53%) of pts preferred an appointment, 9/32 (28%) a phone call, 3/32 (9%) a decision aid tool, and 3/32 (9%) a questionnaire to assess their understanding. Conclusions: Providing personalized, timely communication about new FDA approved tx options is important for BC survivors and critical for improving care delivery. While technological solutions could broaden awareness, this requires balancing pt preferences for direct communication with clinicians.