Citations

e19554 Background: Adding daratumumab to standard multiple myeloma (MM) regimens improves response rates and clinical outcomes. Systematic reviews (meta-analyses) allow further evaluation of its effectiveness in MM patients with high-risk cytogenetic factors but are limited by model assumptions. his study addresses these limitations using a novel synthetic individual patient data (SynIPD) generation algorithm to enable a more robust analysis. Methods: Advances in AI have enabled the creation of synthetic data that mimics the statistical properties of real patient data, empowering aggregated analyses of clinical trials. This study focuses on newly diagnosed MM (NDMM) and relapsed/refractory MM (RRMM) patients with high-risk cytogenetic profiles. Six studies were included: ALCYONE, CASSIOPEIA, and MAIA for NDMM, and CANDOR, CASTOR, and POLLUX for RRMM. Large language models extracted clinical evidence, and SynIPD was generated, incorporating cytogenetic profiles. Random-effects meta-analyses were conducted, and results were compared with pooled analyses using synthetic data. Results: Synthetic data were generated for three studies for NDMM (ALCYONE, CASSIOPEIA, MAIA) and three studies for RRMM (CANDOR, CASTOR, POLLUX). The generated hazard ratios (HRs) for each study closely aligned with reported HRs for high-risk patients, with a maximum relative error of less than 2%. By pooling these datasets, we obtained synthetic datasets for NDMM and RRMM patients. Stratified Cox regression analyses yielded HRs (95% confidence interval) of 0.764 (0.529-1.104) for NDMM and 0.431 (0.294-0.613) for RRMM. Random-effects meta-analyses showed HRs (95% confidence interval) of 0.764 (0.529-1.104) for NDMM and 0.425 (0.287-0.621) for RRMM. Compared with traditional meta-analysis techniques, the synthetic data approach provides additional clinical insights that were not available in the original publications. For instance, the clinical results for the three NDMM studies are summarized as KM curves in Figure 1, which were not reported in the original studies. Conclusions: Our results suggest that the addition of daratumumab to standard regimens improves PFS for RRMM patients with high-risk cytogenetic factors, although its benefit for NDMM patients is not statistically significant. Pooling synthetic data enhances the robustness of conventional meta-analysis outcomes. The identification of HRs and corresponding confidence intervals through SynIPD improves the credibility of our proposed method, offering a reliable approach to evaluating the efficacy of daratumumab in high-risk patients. Since SynIPD includes individual covariate information, it provides deep clinical insights beyond merely enhancing meta-analysis. In other words, any statistical results derived from the original IPD can be effectively approximated using SynIPD.

3520 Background: Recent analyses highlight nonhierarchical outcomes using the 8 th Edition AJCC staging system for CC. For instance, the 5-year survival rate for stages I and IIIa patients (pts) closely align. Additionally, tumor deposits (TDs) have been established as significant prognostic indicators. The AJCCCCEP commissioned this study to develop an updated pathological staging system for CC focused specifically on pts without distant metastasis (M0), while retaining the existing stage IV classification. Methods: Individual patient data (IPD) from pts diagnosed with cc (2010- 2017) in the NCDB were divided into training (70%) and internal validation (30%) datasets. External validation used IPD from clinical trials. The primary endpoint was overall survival (OS). Risk classification development for M0 pts incorporated ungrouped data on pathologic T categories, the number of involved regional lymph nodes (LN+), and TD counts. Recursive partitioning and regression tree analyses were applied to construct hierarchical staging levels. Pre-specified criteria required survival probabilities to be consecutive and show clear separations using Kaplan-Meier (KM) estimates with pairwise log-rank test P of < 0.005 for the training and < 0.05 for validation analyses. Results: Data from 281,997 pts (median age 67 years, 50% male, 81% white, 55% T3, 19% T4, 44% N+, 26% M+, and 11% with ≥1 TD) were analyzed, with a median follow-up of 7.3 years. The updated staging system (Table) met pre-specified criteria, with all observed pairwise P < 0.0001 in the development and internal validation sets. KM OS curves displayed a hierarchical separation across all sub-levels after the 1 st year of diagnosis. Consistent results were seen in pts treated with adjuvant chemotherapy in 4 trials (all pair-wise P < 0.0001). Conclusions: The proposed pathological staging system for M0 pts fulfills pre-specified criteria for hierarchical risk stratification, validated both internally and externally, and provides an evidence-based update. Pending review process, the AJCCCCEP will recommend that these changes be made to the Version 9 staging protocol for colon cancer to improve prognostication for CC pts. Stage T, # of LN+, # of TD M % of pts 1y OS (CI), % 3y OS (CI), % 5y OS (CI), % I T1, 0, 0 0 5 96 (95-97) 91 (90-92) 84 (83-86) IIa T2, 0, 0 0 10 95 (94-95) 88 (88-89) 80 (79-81) IIb T1, 0, 1+T1, 1+, 0T2, 0, 1+T2, 1-4, 0T3, 0, 0 0 27 93 (92-93) 84 (84-85) 75 (75-76) IIIa T1, 1+, 1+T2, 1-4, 1+T2, 5+, 0T3, 0, 1+T3, 1-4, 0 0 14 92 (91-92) 80 (80-81) 71 (70-72) IIIb T2, 5+, 1+T3, 1-4, 1+T3, 5+, 0T4a, 0-4, 0T4b, 0-2, 0 0 13 86 (86-87) 69 (68-70) 58 (57-59) IIIc T3, 5+, 1+T4a, 0-4, 1+T4a, 5+, anyT4b, 0-2, 1+T4b, 3+, any 0 5 78 (77-80) 53 (51-54) 40 (38-41) IVa Any 1a 19 59 (58-60) 28 (28-29) 17 (16-18) IVb Any 1b 7 43 (42-44) 14 (13-14) 6 (6-7) CI: 95% confidence internal; Peritoneum involvement data were not available before 2018 in NCDB. Thus, IVa/b were based on 7 th Edition.

3504 Background: Among patients with resected node-positive colon cancer, nearly 30% will relapse despite standard adjuvant chemotherapy. Analysis of molecular residual disease (MRD) using circulating tumor DNA (ctDNA) may enable risk stratification for tumor recurrence and inform adjuvant treatment decisions. Methods: Postsurgical ctDNA was analyzed in patients with stage III colon carcinoma who participated in a phase 3 trial of adjuvant FOLFOX alone or combined with cetuximab (n = 3084) [NCCTG N0147]. We utilized a tissue-free epigenomic assay for ctDNA detection (Guardant Reveal) with sampling prior to start of adjuvant therapy. Among ctDNA positives, epigenomic tumor fraction (TF) was estimated and ctDNA genotyping was done with Guardant360 (panel of 739 genes). Median follow-up was 6.1 years (yr). Study endpoints included time-to-recurrence (TTR), disease-free survival (DFS) and overall survival (OS) analyzed by Kaplan–Meier method. Multivariable Cox proportional hazards models were used to assess prognostic utility of ctDNA status adjusting for confounders. Interaction between ctDNA and clinicopathological features were assessed. Results: Among 2260 patients with evaluable ctDNA data, 461 (20.4%) were ctDNA positive.Tumors were significantly associated with higher T, N stage, BRAF V600E , high grade, obstruction/perforation, and worse performance status. Positive vs negative ctDNA was significantly associated with shorter TTR (hazard ratio [HR] 4.33, 95% confidence interval [CI] 3.65-5.13, P < 0.0001), poorer DFS (HR 3.74, CI 3.18-4.39, P < 0.0001] and OS (HR 3.17, CI 2.63-3.83, P < 0.0001), adjusting for covariates and tissue MMR, KRAS and BRAF V600E . ctDNA positive vs negative patients had 3y DFS of 36.4% (95%CI 32.2-41.2%) vs 82.5% (95% CI 80.0-84.4%), respectively. Adverse prognosis was consistent across subgroups (all P < 0.05), with stronger detrimental effects for positive ctDNA in N1 (vs. N2), T1/2 (vs T3 or 4), and mismatch repair deficient tumors [interaction P = 0.0002 to 0.041). Among patients with positive ctDNA, TF in those who recurred/died within 3 yr was double of those who remained recurrence-free ( P = 0.0001). High vs. low ctDNA TF ( > vs ≤ median) further stratified TTR (HR 1.48, CI 1.17-1.88, P = 0.0011), DFS (HR 1.52, CI 1.21-1.92, P = 0.0004) and OS (HR 1.58, CI 1.21-2.07, P = 0.0009), adjusting for confounders. ctDNA positive cases, . Analyses of ctDNA detection by site of recurrence, ctDNA clearance, and genomic variant detection are ongoing. Conclusions: In the largest study evaluating tissue-free epigenomic-based MRD detection, we demonstrate a robust prognostic utility of postsurgical ctDNA. Tumor fraction provided further patient stratification and analysis is ongoing to identify a subgroup based on TF that may be unlikely to clear ctDNA despite adjuvant chemotherapy.

TPS3634 Background: For patients with oligometastatic colorectal cancer (CRC), aggressive local therapy of isolated metastases, particularly in the liver, has been associated with long-term progression-free and overall survival (OS) primarily based on retrospective evidence. However, in patients with limited metastatic CRC that is deemed inoperable or those with additional disease outside of the liver or lungs, the role of local ablative therapies, including microwave ablation (MWA) and stereotactic body radiation therapy (SBRT), to render patients disease free is less clear. Despite the long history of treating oligometastatic CRC with local therapy, which is largely provider biased, questions remain regarding the benefit of extending the paradigm of metastatic directed therapy to patients with more extensive disease. This trial seeks to use a pragmatic multimodality approach that mirrors the current clinical dilemma. This study is designed to evaluate the safety and efficacy of adding total ablative therapy (TAT) of all sites of disease to standard of care systemic treatment in those with limited metastatic CRC. Methods: A022101/NRG-GI009 is a National Clinical Trials Network randomized phase III study planned to enroll 364 patients with newly diagnosed metastatic CRC (BRAF wild-type, microsatellite stable) without peritoneal metastasis or liver-only disease on baseline imaging. Patients receive first-line systemic therapy for 12-39 weeks. Patients with ≤4 sites of metastatic disease following initial systemic therapy that are amenable to any combination of surgical resection, MWA, and/or SBRT are then randomized 1:1, stratified by number of metastatic organ sites (1-2 vs. 3-4), timing of metastatic disease diagnosis (de novo vs. secondary), and presence of metastatic disease outside the liver/lungs in at least 1 site. Patients in Arm 1 will receive TAT consisting of treatment of all metastatic sites with SBRT, MWA, and/or surgical resection followed by standard of care systemic therapy. Patients in Arm 2 will continue with standard of care systemic therapy alone. The primary endpoint is OS. Secondary endpoints include event-free survival, treatment-related toxicities, and local recurrence with exploratory biomarker analyses. The study needs 346 evaluable patients combined in the 2 arms to demonstrate an improvement in OS with a hazard ratio of 0.7 to provide 80% power with a one-sided alpha of 5%. The trial utilizes a group sequential design with two interim analyses (25% and 50% of events) for futility. The trial activated in January 2023 and recruitment is ongoing. Support: U10CA180821, U10CA180882; https://acknowledgments.alliancefound.org. U10CA180820 (ECOG-ACRIN); U10CA180868 (NRG); U10CA180888 (SWOG); Clinical trial information: NCT05673148 .

TPS3650 Background: A total neoadjuvant therapy (TNT) approach improves compliance with chemotherapy and increases rates of tumor response compared to neoadjuvant chemoradiation (CRT) alone in those with locally advanced rectal cancer. Recent data indicate that optimal sequencing of TNT involves consolidation (rather than induction) chemotherapy to improve complete response rates. The use of FOLFIRINOX has shown to improve response and outcomes compared to CRT and surgery alone. Data have also shown that patients with clinical complete response (cCR) after TNT may be managed with a watch and wait approach (WW) instead of preemptive total mesorectal resection (TME). However, the optimal consolidation chemotherapy regimen to improve cCR rates has not been established, and a randomized clinical trial has not robustly evaluated cCR as a primary endpoint. We designed this NCI-sponsored study of chemotherapy intensification to address this and to increase cCR rates, provide opportunity for organ preservation, and survival outcomes. Methods: In this multigroup randomized, seamless phase II/III trial (1:1), up to 760 patients with LARC, T4N0, any T with node positive disease (any T, N+) or T3N0 requiring abdominoperineal resection or coloanal anastomosis and distal margin within 12 cm of anal verge will be enrolled. Stratification factors include tumor stage (T4 vs T1-3), nodal stage (N+ vs N0) and distance from anal verge (0–4; 4–8; 8–12 cm). Patients will be randomized to receive neoadjuvant long-course chemoradiation (LCRT) followed by consolidation doublet (mFOLFOX6 or CAPOX (control arm)) or triplet chemotherapy (FOLFIRINOX (experimental arm)) for 3–4 months. LCRT in both arms involve 4500 cGy in 25 fractions over 5 weeks +900 cGy boost in 5 fractions with a fluoropyrimidine. Patients will undergo assessment 8–12 (±4) weeks post-TNT completion. The primary endpoint for the phase II portion will compare cCR between treatment arms. A total number of 312 patients (156 per arm) will provide statistical power of 90.5% to detect a 17% increase in cCR rate, at a one-sided alpha = 0.048. The primary endpoint for the phase III portion will compare disease-free survival (DFS) between arms. A total of 285 DFS events will provide 85% power to detect an effect size of hazard ratio 0.70 at a one-sided alpha of 0.025, requiring enrollment of 760 patients (380 per arm). Secondary objectives include overall survival, organ preservation time, time to distant metastasis, and adverse event rates. This study has accrued 587 patients as of January 2025, and is investigating exploratory correlatives (e.g., ctDNA). Support: U10CA180821, U10CA180882, U24 CA196171. https://acknowledgments.alliancefound.org. Clinicaltrials.gov ID: NCT05610163. Clinical trial information: NCT05610163 .

3624 Background: Increasing chemotherapy completion and reducing chemotherapy adverse events (AE) are critical to improve survival after colon cancer diagnosis. Sex, as a biological variable, may impact chemotherapy treatment differently, and thus further investigation is needed to examine sex differences in chemotherapy completion and adverse events among patients with colon cancer. Methods: Among an NCI-sponsored trial conducted among patients with stage III colon cancer (CALGB/SWOG 80702), all patients received standard adjuvant chemotherapy FOLFOX (fluorouracil, leucovorin, and oxaliplatin). To signal chemotherapy completion, we utilized relative dose intensity (RDI) calculated as the ratio of the delivered dose intensity to planned dose intensity; and reduced RDI (RDI <85%) was considered as a clinically significant deviation from standard FOLFOX. From clinicians’ records of NCI’s Common Terminology Criteria for Adverse Events (CTCAE), we primarily focused on clinically significant AE such as neutrophils decrease, nausea, platelets decrease, hypertension, peripheral neuropathy, diarrhea, fatigue, gastritis, creatinine increase, gastric ulcer, myocardial ischemia, and cerebral ischemia; and severe AE was defined as the occurrence of any above AE with CTCAE grade ≥3. Using multivariable logistic regression that adjusted for body surface area (BSA) and other clinicopathological confounders, we estimated adjusted odds ratios (OR) for the associations of sex with reduced RDI and severe AE. Results: Of 2201 patients, mean (standard deviation [SD]) age was 60.9 (10.9) years, 1019 (46.3%) were female, 1750 (79.5%) were White, 172 (7.8%) were Hispanic, 964 (43.8%) experienced reduced RDI, and 1156 (52.5%) had severe adverse events. Compared to males, females were at significantly higher risks of experiencing reduced RDI (OR [95% CI]: 1.57 [1.27-1.93], P <0.001) and severe AE (OR [95% CI]: 1.73 [1.41-2.12], P <0.001). Conclusions: Our findings suggested females are more likely than men to experience reduced RDI and severe AE during colon cancer chemotherapy. Clinical Impact: In the era of precision medicine, sex (as a biological variable) should be considered in optimizing colon cancer chemotherapy to improve completion and reduce toxicities. Clinical trial information: NCT01150045 .

e14626 Background: Despite advancements in neoadjuvant therapy and surgical techniques, patients with pancreatic ductal adenocarcinoma (PDAC) often experience high recurrence rates after total neoadjuvant therapy (TNT) and resection. Existing tumor response scoring systems, such as the College of American Pathologists (CAP) guidelines, fail to stratify recurrence risk effectively, emphasizing the need for novel, objective approaches. Methods: This study evaluated spatial characteristics of residual cancer and stroma in a multi-site cohort of 203 patients with resected PDAC following TNT, not having achieved a major pathologic response (CAP 2 or 3). Whole slide images (WSI) of hematoxylin and eosin-stained sections were digitized and analyzed using artificial intelligence to perform tissue segmentation. Metrics quantifying spatial morphology and configuration, inspired by principles of landscape ecology, were computed to explore spatial features of the tumor microenvironment (TME). Statistical models (recursive partitioning and regression tree [RPRT] model and Cox model with backwards eliminations) incorporating these features were developed to stratify recurrence risk. Results: Five metrics were used for risk classification model build. Three models successfully classified patients into high- and low-risk groups based on spatial metrics. Models demonstrated moderate discriminatory power (C-statistics: 0.560–0.566) and showed that increased tumor fragmentation, like stromal patch density and cancer patch shape index, were strongly associated with improved outcomes. Conclusions: Integrating spatial metrics of cancer-stroma configuration enhances risk stratification beyond conventional scoring systems. Given increased tumor fragmentation is associated with improved outcomes, these data indirectly suggest ecological mechanisms of treatment resistance. This approach offers a pathway toward personalized post-operative management strategies to improve outcomes in PDAC. Risk classification models. Model Description Event/n Median DFS (95% CI) HR(95% CI) p-value C-statistics 1(RPRT) High risk: log standard deviation of the stroma shape index > 0.651 87 / 101 8.22(5.72 – 10.1) 1.64(1.20 – 2.25) 0.002 0.562 Low risk: log standard deviation of the stroma shape index ≤ 0.651 71 / 102 11.90(9.24 – 25.1) Ref 2(RPRT) High risk: log standard deviation of the stroma shape index > 0.651 & mean cancer shape index ≤ 1.775 58 / 63 7.23(5.19 – 9.63) 1.82(1.31 – 2.52) 0.0003 0.560 Low risk: (log standard deviation of the stroma shape index > 0.651 & mean cancer shape index > 1.775) or log standard deviation of the stroma shape index ≤ 0.651 100 / 140 11.57(9.24 – 17.92) Ref 3(Backwards elimination) High risk: PI * > median 86 / 101 8.02(6.08 – 9.86) 1.73(1.26 – 2.37) 0.0007 0.566 Low risk:PI * ≤ median 72 / 102 15.72(9.97 – 25.05) Ref *PI: (0.2701 * log mean stroma area) + (0.3905 * log edge density).

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.

7547 Background: Minimal residual disease (MRD) has been recently accepted by the Food and Drug Administration (FDA) as an endpoint for accelerated approval in Multiple Myeloma. However, emerging data from recent trials were not included in previous analyses. While literature-based meta-analyses on the correlation between MRD and approved clinical outcomes typically require extensive manual review, leveraging AI with expert-in-the-loop validation can efficiently generate reliable evidence from comprehensive clinical studies with up-to-date outcomes. Methods: An AI-assisted framework was developed to identify relevant studies and extract critical information via two independent objectives. The first objective examined trial-level associations, modeling treatment effects on MRD and clinical endpoints across patient populations using weighted least squares, with association strength measured by coefficients of determination (R²) and 95% confidence intervals (CIs). The second objective analyzed individual-level associations using synthetic individual patient data (SynthIPD) generated from the published Kaplan-Meier plots and summary statistics of patient subgroups. Results: AI-assisted screening identified eligible studies (>50 patients per treatment arm) reporting progression-free survival (PFS), overall survival (OS), and MRD-negative complete response rates (MRD-CR rate) using multi-parameter next-generation flow cytometry or sequencing methods (sensitivity threshold ≥10⁻⁵), expanding previous analyses from 15 to 20 two-arm studies. Trial-level analysis demonstrated an R² of 0.69 (95% CI 0.50–0.89) for PFS log hazard ratio versus MRD-CR rate log odds ratio. Analysis of synthetic individual data from Kaplan-Meier curves using a novel digitization method yielded a global odds ratio of 7.28 (95% CI 5.60–8.95) for individual-level correlation between MRD-CR rates and PFS outcomes. Conclusions: This study validates MRD-CR rate as an endpoint for accelerated approval in MM through rapid AI-assisted literature review and synthetic individual patient data. The findings demonstrate moderate correlation between MRD-CR rate and median PFS at both trial and individual levels, consistent with previous literature but incorporating additional eligible studies. The novel SynthIPD approach presents an efficient alternative to traditional data-sharing methods while maintaining analytical robustness. These results align with current Oncologic Drugs Advisory Committee (ODAC) surrogacy analysis methods and support the utility of MRD assessment in MM clinical trials.

PURPOSE Several lines of treatment can be used sequentially in patients with metastatic colorectal cancer. We investigated the evolution of patient/tumor characteristics and their prognostic impact across treatment lines to develop an overall prognostic score (OPS). PATIENTS AND METHODS Individual patient data from 48 randomized trials were analyzed. The end point was overall survival (from random assignment to death). Missing data were imputed. The complete data set was then separated into construction (80%) and validation sets (20%). The Cox's model was used to define risk groups for survival using the OPS. The discrimination capability was assessed in each treatment-line via bootstrapping to obtain optimism-corrected calibration and discrimination C-indices. Internal validation was done in the validation set. RESULTS A total of 37,560 patients (26,974 in first-line [1L], 7,693 in second-line [2L], and 2,893 in third-line [3L]) were analyzed. Some clinical, biological, and molecular characteristics of patients/tumors included in therapeutic trials evolve over the lines. Seven independent prognostic variables were retained in the final multivariate model common to all lines: Eastern Cooperative Oncology Group performance status, hemoglobin, platelet count, WBC/absolute neutrophil count ratio, lactate dehydrogenase, alkaline phosphatase, and the number of metastatic sites. The OPS was used to define four patient subgroups with significantly different prognoses in 1L, 2L, and 3L, separately, with adequate C-indices: 0.65, 0.66, and 0.69 in the construction set and 0.65, 0.66, and 0.68 in the validation set, respectively. The OPS was not predictive, with 3L drugs ( v placebo) or subsequent line (2L/1L or 3L/2L) extending survival in all prognostic groups. CONCLUSION The same prognostic model using practical variables can be used before all treatment lines. The OPS could better stratify patients in future clinical trials and help to therapeutic decision in routine practice.