Citations

373 Background: Recent studies have demonstrated encouraging outcomes with neoadjuvant ICIs in pts with localized deficient mismatch repair (dMMR) and/or microsatellite instability-high (MSI-H) GEC, prompting discussions around the feasibility of nonoperative management (NOM). However, current evidence is largely from phase 1 and 2 clinical trials with limited sample sizes. Thus, the efficacy and safety of neoadjuvant ICI in this pt population remain subject to ongoing debate. Methods: We conducted a systematic review and meta-analysis of prospective and retrospective studies evaluating neoadjuvant ICIs in pts with localized dMMR/MSI-H GEC according to the PRISMA guidelines. The primary outcomes were pathological complete response (pCR) and complete clinical response (cCR) rates. cCR was defined as no evidence of residual disease on tumor-specific imaging and on endoscopy with biopsy. Secondary outcomes included major pathologic response (MPR) rates and the incidence of grade 3–4 immune-related adverse events (irAEs). Proportions with 95% confidence intervals (CI) were used to pool event rates for occurrence of cCR, pCR, MPR and grade 3-4 irAEs. The DerSimonian and Laird random-effects model was used. NOM was assessed as part of the qualitative analysis. Results: 20 studies comprising 396 pts treated with neoadjuvant ICIs were included. Three studies utilized double ICI blockade (PD-1/ PD-L1 inhibitor plus CTLA-4 inhibitor), while the remaining studies primarily utilized monotherapy with a PD-1 inhibitor, with or without chemotherapy. Overall, 320 (81.0%) underwent surgical resection. The pooled pCR rate was 41.6% (95% CI, 33.1%–50.8%), cCR 63.8% (95% CI, 45.6%–78.8%), and MPR 64.2% (95% CI, 49.1%–76.9%). The pooled incidence of grade 3–4 irAEs was 5.1% (95% CI, 0.6%–12.2%). Subgroup analysis showed higher pCR with ≥3 months versus <3 months of ICI (50.2% [95% CI 42.2–58.3] vs 28.4% [18.9–40.2]; χ²=8.69, p=0.003). Forty-four pts were managed with NOM, two experienced early local regrowth over median follow-up ranging from 11.5 to 28 months. Conclusions: Neoadjuvant ICI therapy appears to be a safe and effective therapeutic strategy for pts with localized dMMR/MSI-H GEC. Neoadjuvant ICI exposure for ≥3 months seems to yield higher pCR rates than <3 months. The high and prolonged cCR rates support the nonoperative strategy in selected patients with dMMR/MSI-H GEC.

103 Background: Clinicians spend significant time extracting and synthesizing information to risk-stratify and make adjuvant chemotherapy (AC) recommendations for CRC. By automating parts of this process, LLMs could help reduce documentation burden and variability in decision-making. Methods: We selected 144 stage III, pMMR CRC patients treated at Mayo Clinic (2017–2021). HIPAA-compliant Gemini-2.0-Flash-001 and GPT-4o extracted clinical variables (age, neuropathy grade, pathological stage) from EHRs and generated AC recommendations. Two approaches were compared: (1) a rule-based algorithm with nested if/else statements translating variables into NCCN-based recommendations, and (2) a dynamic LLM agent generating recommendations using a structured prompt informed by NCCN guidelines. Concordance with treating physicians was assessed, with disagreements reviewed by a blinded GI oncologist. Results: The dataset included 144 patients with median age 67 (IQR 66–68), 48.6% female. The LLM pipeline extracted neuropathy grade with 100% accuracy and pathological T/N stages with 99.3% accuracy. Concordance with physician recommendations was 93.1% for the rule-based algorithm and 62.5% for the LLM agent. In discordant cases, blinded adjudication by a GI oncologist favored the algorithm and LLM agent over physicians in most cases (Table 1). Conclusions: This exploratory work shows LLM agents can reliably extract variables and generate evidence-based treatment recommendations for stage III CRC. The high rate of expert preference for LLM recommendations in discordant cases is intriguing but limited by small sample size and possible adjudicator bias. Discordant physician recommendations reflect the complexity of decision-making, including patient preferences, performance status, comorbidities, and subtle findings not fully captured in EHRs. Rather than replacing judgment, we envision LLMs as decision support tools—analogous to an advanced trainee reviewing charts and presenting evidence-based recommendations to the attending physician with ultimate authority. Larger multi-institutional studies with multiple adjudicators are needed to validate these findings and clarify AI’s role in oncology. Patient characteristics, LLM extraction accuracy, and concordance with physician recommendations. Metric Result Total patients 144 Median age (IQR) 67 (66-68) Female (%) 48.6% LLM extraction accuracy – Neuropathy grade 100% LLM extraction accuracy – Pathological T and N stages 99.3% Primary Concordance – Rule-based algorithm vs. physician 93.1% Adjudicator preference of rule-based algorithm over treating physician for discordant cases 100% Concordance – LLM agent vs. physician 62.5% Adjudicator preference of LLM agent over treating physician for discordant cases 82.0%

Abstract Background The increasing reliance on accelerated approvals and surrogate endpoints for Food and Drug Administration (FDA) approvals of gastrointestinal (GI) cancer therapies raises concerns about their clinical benefit and long-term patient outcomes. The shift toward single-arm trials in regulatory decisions further complicates treatment evaluation. Material and Methods This retrospective observational study evaluated all FDA approvals for GI cancer therapies from January 2006 through January 2025. Data were extracted from FDA archives, ClinicalTrials.gov, and PubMed. Approvals were categorized by regulatory pathway (accelerated vs regular), trial design (single-arm vs randomized), and primary endpoint (surrogate vs overall survival [OS]). Clinical benefit was assessed based on OS improvement and the European Society for Medical Oncology Magnitude of Clinical Benefit Scale (ESMO-MCBS). The primary outcome was the proportion of approvals based on surrogate versus OS endpoints. Secondary outcomes included use of single-arm designs, frequency of accelerated approvals, OS gain, and the proportion meeting ESMO-MCBS substantial benefit (score ≥ 4). Results The FDA granted 60 GI cancer drug approvals from 67 trials. Approvals rose from 15 (25%) in 2006-2014 to 45 (75%) in 2015-2025. Single-arm trials increased to 24%, and surrogate endpoints were used in 41.8% (ORR 20.9%, PFS 19.4%). Median OS improvement was 2.1 months (IQR: 1.6-2.65). Only 24.3% of trials met ESMO-MCBS substantial benefit. Of 15 accelerated approvals, 66.7% remained pending, 13.3% received full approval, and 20% were withdrawn. Conclusion Expedited approvals have improved drug access in GI oncology, but modest benefits highlight the need to balance speed with outcomes that truly matter to patients.

Abstract Introduction: Lutetium-177 DOTATATE peptide receptor radionuclide therapy (PRRT) is an effective treatment for gastroenteropancreatic neuroendocrine tumors (GEP-NETs). While generally well tolerated, PRRT can result in hematologic toxicity ranging from mild cytopenias to therapy-related myeloid neoplasms (t-MNs). Understanding the incidence, severity, and clinical consequences of hematologic toxicity is essential for optimizing treatment decisions and establishing effective monitoring strategies. This study aimed to characterize hematologic toxicity patterns, severity, and recovery profiles in GEP-NET patients treated with Lutetium-177 DOTATATE PRRT and to determine the frequency of cytopenia-related treatment discontinuation. Methods: We conducted a retrospective analysis of 160 consecutive GEP-NET patients who underwent PRRT. Hematologic parameters (hemoglobin, white blood cell count, absolute neutrophil count, platelet count, and lymphocyte count) were assessed at baseline, mid-treatment (post-cycle 2), and post-treatment (post-cycle 4). Cytopenias were graded using Common Terminology Criteria for Adverse Events version 4.03 and categorized as never (grade &lt;2 throughout), transient (grade ≥2 mid-treatment, resolving post-treatment), persistent (grade ≥2 at both timepoints), or late-onset (grade &lt;2 mid-treatment, grade ≥2 post-treatment). Treatment completion rates and discontinuation reasons were documented. Results: Overall, 73% of patients (117/160) completed all planned PRRT cycles. Among the 43 patients who discontinued treatment early, only 4 (2.5% of total cohort) discontinued specifically due to cytopenia, while the remainder discontinued for other reasons. Post-treatment grade ≥2 cytopenias were uncommon: lymphocytes (4.4%), hemoglobin (2.5%), neutrophils (1.9%), white blood cells (1.3%), and platelets (1.3%). The majority of patients (≥85%) never experienced grade ≥2 cytopenia throughout treatment. When cytopenias occurred, they were predominantly transient (8-10% of patients) with complete recovery by treatment completion. Persistent cytopenias were rare (&lt;5% across all cell lines), while late-onset cytopenia occurred most frequently with neutrophils (14%). Conclusion: Lutetium-177 DOTATATE PRRT demonstrates an excellent hematologic safety profile in GEP-NET patients. Severe cytopenias are uncommon, predominantly transient, and rarely necessitate treatment discontinuation. These findings support the continued use of PRRT in appropriate candidates, with cytopenia-related discontinuation occurring in fewer than 3% of cases. Long-term follow-up remains essential to monitor delayed hematologic effects, including t-MNs. Future research should evaluate baseline predictors such as prior chemotherapy, renal function, and marrow reserve to identify patients at higher risk who may benefit from closer hematologic surveillance.

Abstract Background This phase 1 study aimed to determine the maximum tolerated dose (MTD) and evaluate the safety and preliminary efficacy of rucaparib (RUB), a poly(adenosine diphosphate ribose) polymerase (PARP) inhibitor, combined with liposomal irinotecan (nal‐IRI) and 5‐fluorouracil (5‐FU) in metastatic gastrointestinal (GI) cancers. RUB targets DNA repair pathways, showing efficacy in tumors with homologous recombination deficiency, such as BRCA mutations. Preclinical data suggest synergy with irinotecan, but overlapping toxicities pose challenges. Methods Eighteen patients with metastatic GI cancers, who previously progressed on at least one systemic therapy, were enrolled. A novel sequential dosing regimen, informed by nal‐IRI pharmacokinetic analysis, was used. Twelve patients were evaluable for dose‐limiting toxicity (DLT) and 12 for response per Response Evaluation Criteria in Solid Tumors v1.1 criteria. Results The MTD was established as RUB 600 mg twice daily, nal‐IRI 50 mg/m 2 , and 5‐FU 2400 mg/m 2 over 46 hours. The objective response rate (ORR) was 33% (4 of 12), and the disease control rate (DCR) was 75% (9 of 12). Common grade 3 adverse events included diarrhea (33%) and neutropenia (25%), with no grade 4/5 events. Responses were notable in patients with somatic ATM and BRCA mutations, especially those with prior platinum exposure. No DLTs occurred at the recommended phase 2 dose. Conclusions This optimized dosing schedule successfully established the MTD for RUB with nal‐IRI and 5‐FU, overcoming prior challenges with PARP inhibitor and irinotecan combinations. The promising ORR and DCR support further evaluation of this regimen in advanced GI malignancies.

PURPOSE Neoadjuvant immune checkpoint inhibitors (nICIs) have demonstrated high response rates in deficient mismatch repair/microsatellite instability–high (dMMR/MSI-H) gastroesophageal adenocarcinoma (GEA). The NEONIPIGA and INFINITY trials demonstrated high rates of pathologic complete response (pCR) in this patient population. Furthermore, the INFINITY trial explored the feasibility of managing these patients nonoperatively, demonstrating promising results. This study aimed to evaluate clinical outcomes of nICIs in resectable dMMR/MSI-H GEA, with a focus on the feasibility of nonoperative management (NOM). MATERIALS AND METHODS This retrospective cohort study included patients with resectable dMMR/MSI-H GEA and treated with nICIs ± surgery at the Mayo Clinic. Patients were identified from institutional records, and clinical data were retrospectively reviewed. Primary outcomes were clinical complete response (cCR) and pCR. Secondary outcomes included event-free survival (EFS), radiologic complete response (rCR), and immune-related adverse events (irAEs). RESULTS A total of 26 patients treated between April 1, 2017, and July 30, 2025, were identified. Nine patients (34.6%) underwent surgery, of whom six (66.7%) achieved pCR. Seventeen patients (65.4%) pursued NOM, with 10 (71.4%) of 14 evaluable patients achieving cCR and 14 (82.4%) of 17 evaluable achieving rCR. One patient who initially achieved cCR had a local recurrence on surveillance endoscopy and underwent salvage endoscopic resection. At a median follow-up of 19.3 months, 15 (88.2%) of 17 patients in the NOM cohort were alive and metastasis-free, with EFS rates of 87.3% at 12 and 24 months for all patients. irAEs occurred in nine patients (34.6%), with no grade ≥3 toxicities. CONCLUSION In this retrospective cohort study, nICIs led to high cCR and pCR rates in resectable dMMR/MSI-H GEA, supporting the use of immune checkpoint inhibitors in this setting and the feasibility of NOM in select patients.

The role of circulating tumor DNA (ctDNA) in gastroesophageal adenocarcinoma (GEA) has expanded in recent years. In resectable disease, postoperative ctDNA is able to detect patients at highest risk of recurrence months before scans. Tumor-informed assays provide the best sensitivity and emerging methylation assays are useful when tissue is scarce. In metastatic GEA, baseline ctDNA burden correlates with prognosis, and a decrease in ctDNA level after treatment initiation reflects therapeutic response. It can also uncover actionable targets, including ERBB2, FGFR2, and MSI-H, and detect resistance that can arise after starting treatment. Limitations include variable assay performance, low shedding in some tumors, clonal hematopoiesis confounding, and a lack of randomized data showing that ctDNA-guided changes improve outcomes. Ongoing trials are testing MRD-guided escalation/de-escalation and ctDNA-directed biomarker therapy. In this review, we evaluate the role of ctDNA in GEA cancers over recent years.

Intracardiac metastases from gastroenteropancreatic neuroendocrine tumors (NETs) are rare and challenging to diagnose. Lutetium (Lu)-177 DOTATATE therapy has demonstrated significant benefit in patients with metastatic NET; however, there are limited data regarding the direct impact on cardiac metastases. Patients with intracardiac metastasis from NET were evaluated. Patients were stratified by treatment with Lu-177 DOTATATE. Quantitative assessments of the progression of cardiac metastatic size (maximal diameter) and metabolic activity, as measured by maximal standardized uptake value (SUV max ), were performed on serial 68 Ga-DOTATATE PET imaging. In a cohort of 23 patients, 11 patients (47.8%) received Lu-177 DOTATATE therapy. Through a median of 2.2 years of follow-up, these patients showed some reduction in metastatic burden with a median reduction in maximal diameter of 1.0 mm (IQR: 0.0–3.0) and a median change in SUV max of −1.6 (IQR: −4.4 to 1.5). In contrast, patients who did not receive Lu-177 DOTATATE had some increase in maximal diameter of 0.5 mm (−2.0 to 2.0) and an increase in SUV max of 1.4 (−6.2 to 2.3). Overall, Lu-177 DOTATATE therapy may result in modest regression of intracardiac metastases as assessed by molecular imaging, whereas patients with cardiac metastases who did not receive therapy appeared to show progression.

Abstract Molecular profiling reveals that up to 40% of advanced biliary tract cancers (BTCs) harbor actionable genomic alterations amenable to matched targeted therapies. However, conventional trial designs typically evaluate these agents in pretreated populations, resulting in approvals for later-line use. Notably, 25–44% of patients with advanced BTC may become ineligible for treatment after first-line therapy due to disease progression or functional decline, thus the real-world survival outcomes with matched therapies remains poorly characterized. This international collaborative study includes data from Mayo Clinic, Duke Cancer Institute, and National Cancer Center East (Japan), as well as a combined dataset from the SCRUM-Japan GOZILA, MONSTAR-SCREEN-1, and MONSTAR-SCREEN-2 projects. We assessed overall survival (OS) of patients based on the presence of actionable alterations and the receipt of matched therapy. To adjust for confounding, we applied propensity score weighting with inverse probability of treatment and multivariate Cox regression modeling, controlling for age, sex, tumor location, prior resection, and mutational subgroup. Among 1,049 patients that were analyzed, 358 (34.1%) harbored actionable alterations, with 160 (44.7%) receiving matched targeted therapy. The matched group (patients with actionable tumors who received a matched therapy) were significantly associated with longer median OS (23.3 months; 95% CI: 19.5–30.4) compared to the unmatched group (14.7 months; 95% CI: 12.8–17.9) and those with non-actionable tumors (17.1 months; 95% CI: 15.5–18.7; HR 0.57, 95% CI: 0.46–0.71; p < 0.0001). The unmatched group also was associated with the lowest three-year OS rate (13% vs. 35% in matched and 19% in actionable groups, respectively; p<0.0001). On multivariable analysis with patients who received ≥2 lines of therapy, receipt of matched therapy remained an independent predictor of improved OS (HR 0.62; 95% CI 0.43–0.90). These findings support the early integration of targeted therapies in BTC management and underscore the need to overcome systemic barriers to treatment access.