Jones, Jeremy C

The recent approval of encorafenib, cetuximab, and FOLFOX based on the phase III BREAKWATER trial has introduced a new standard of care for the first-line treatment of BRAF V600E–mutated metastatic colorectal cancer (mCRC). However, its safety and efficacy in patients with significant liver dysfunction remains unclear and, as such, patients are often excluded from pivotal clinical trials. This report presents a case of BRAF V600E–mutated mCRC presenting with extensive hepatic involvement and liver dysfunction. Despite the absence of guidelines, the patient was initiated on full-dose encorafenib, cetuximab, and FOLFOX. He experienced a rapid clinical and biochemical response, with near-normalization of liver enzymes after cycle 1, and complete functional recovery by cycle 3. Treatment was well tolerated, with no significant adverse events throughout 9 cycles. He subsequently transitioned to maintenance 5-FU, cetuximab, and encorafenib. Posttreatment blood-based next-generation sequencing revealed no residual actionable mutations. The patient then successfully underwent complete surgical resection of his primary tumor and metastatic disease with negative margins. This case highlights the importance of considering encorafenib-based therapy in select patients with BRAF V600E–mutated mCRC in the setting of compromised liver function.

Background/Objectives: Locoregional anal squamous cell carcinoma (ASCC) is usually cured with chemoradiotherapy; however, some patients relapse, require salvage abdominoperineal resection or develop metastatic disease. Approximately 90% of cases are driven by high-risk human papillomavirus, most commonly HPV16. Conventional surveillance using clinical examination and imaging may have limited sensitivity and specificity and is not individualized by recurrence risk. Circulating biomarkers (CBs), particularly circulating tumor DNA (ctDNA), have emerged as promising methods for real-time disease monitoring. We systematically reviewed available evidence evaluating CBs across treatment timepoints in localized ASCC. Methods: A PROSPERO-registered review (ID: 1133987) was conducted according to PRISMA guidelines. PubMed, EMBASE, Cochrane CENTRAL, Web of Science, and major conference proceedings (ASCO, ESMO, ASTRO) were searched on 30 November 2025. We included prospective or retrospective studies (≥10 patients) with stage I–III disease treated with curative-intent chemoradiotherapy that reported CBs, assay characteristics, and at least one clinical outcome. Studies with predominantly localized cohorts were included even if small proportions of metastatic patients were present, provided results relevant to curative-intent populations could be interpreted. Data were synthesized narratively by timepoint (baseline, mid-treatment, end of treatment, post-treatment/surveillance) and assay type given methodological heterogeneity. Results: Fifteen studies were included. CB assays comprised four categories: viral HPV ctDNA assays, tumor-informed ctDNA assays, non-specific total cell-free DNA (cfDNA) quantification, and circulating tumor cell (CTC)-based assays. Baseline detection rates varied by assay type. Viral HPV ctDNA assays demonstrated detection rates of 59–100%, while tumor-informed ctDNA assays showed rates of 79–89%. Across studies, higher CB detection rates and levels were generally associated with greater tumor burden, including more advanced T and N stage disease. Mid-treatment ctDNA clearance identified patients with excellent locoregional control and progression-free survival, whereas persistent ctDNA was associated with treatment failure. End-of-treatment and surveillance ctDNA positivity predicted recurrence within individual cohorts, with reported sensitivities of 80–90%, specificities of 95–99%, and molecular lead times preceding clinical or radiographic detection. In contrast, non-tumor-specific cfDNA dynamics showed more variable prognostic associations and were less consistently linked to tumor burden. Conclusions: Across heterogeneous assays, CB dynamics provide clinically meaningful prognostic information in localized ASCC, particularly when measured during treatment and early surveillance. Viral HPV and tumor-informed ctDNA may have the potential to guide follow-up intensity and inform future escalation or de-escalation strategies; however, prospective, standardized trials are needed to define actionable thresholds and test ctDNA-guided management.

PURPOSE Artificial intelligence (AI) has been rapidly evolving in medicine. While there are existing data about the perceptions and concerns of health care workers regarding AI, those of the hematology and oncology (HemOnc) workforce remain unknown. We assessed opinions of physicians (faculty and fellows), advanced practice providers (APPs), and nurses in HemOnc on integrating AI in medical education (MedEd) and clinical practice (CP). METHODS Group-specific electronic surveys were developed. The HemOnc workforce from the three Mayo Clinic sites was invited to participate. Participation was anonymous, with data collection between November 7, 2024, and January 20, 2025. Results were reported as proportions, with 95% binomial CI when appropriate. RESULTS A total of 344 participants responded, 118 physicians (77 faculty, 41 fellows), 49 APPs, and 177 nurses. Most had used AI although less than half felt very or moderately knowledgeable about it. A total of 95% of fellows, 97% of faculty physicians, 96% of APP, and 92% of nurses believe that AI will be integrated in MedEd. A total of 94% of physicians and 88% of nonphysicians believe that this integration would be beneficial. In CP, 98% of fellows, 96% of faculty physicians, 100% of APPs, and 92% of nurses believe in AI's integration. However, 51% of physicians and 68% of nonphysicians had some concerns, including technology time, medical costs, and burnout. Nonetheless, 85% of fellows, 94% of faculty physicians, 98% of APPs, and 86% of nurses would embrace AI. CONCLUSION The majority of this single health system HemOnc's workforce endorsed AI integration into MedEd and CP but highlighted relevant concerns. Proper education, effective partnership among all stakeholders, and well-organized integration are essential for optimizing AI's incorporation into HemOnc's MedEd and CP and ensuring that it fully supports the mission of providing high-quality patient care.

PURPOSE Gastroesophageal carcinoma (GEC) is increasingly managed using biomarker-guided therapies. Although both tissue DNA (tDNA) and circulating tumor DNA (ctDNA) testing are used clinically, the concordance of genomic alterations between primary tumors, metastatic sites, and liquid biopsy remains incompletely understood. METHODS We retrospectively analyzed 345 patients with GEC who underwent ctDNA testing at Mayo Clinic. tDNA next-generation sequencing and immunohistochemistry (IHC) for human epidermal growth factor receptor 2 (HER2)/erb-b2 receptor tyrosine kinase 2 ( ERBB2 ) and mismatch repair (MMR) were collected. Concordance was evaluated between ctDNA and tDNA, ctDNA and IHC, and across all three modalities, using 60-day and 30-day intervals. RESULTS Among 345 patients with ctDNA testing, 186 had tDNA testing, and 310 underwent IHC. ctDNA testing showed a shorter turnaround time than tDNA (median 6 v 13 days). The most frequent alteration in ctDNA, primary tDNA, and metastatic tDNA was TP53. Concordance between ctDNA and primary tDNA was ≥78.8% for key genes; between ctDNA and metastatic tDNA, it was ≥84.8%. IHC-ctDNA concordance was higher in metastatic tumors, with 91.1% for HER2/ ERBB2 and 97.7% for mismatch repair (MMR)/microsatellite instability (MSI) compared with 81.1% and 95.8%, respectively, in primary tumors. Triplet concordance for MSI/MMR was 97.6% in primary tumors and 100% in metastatic tumors, while ERBB2 /HER2 showed 84.4% and 93.9% concordance, respectively. ctDNA temporal heterogeneity analysis revealed 14 patients with fluctuating ERBB2 status and 3 with fluctuating MSI-H status. CONCLUSION ctDNA testing demonstrates high concordance with tDNA and IHC and offers faster turnaround. Given its minimally invasive nature and strong concordance with tissue-based testing, ctDNA is a reliable tool for genomic profiling and longitudinal monitoring in GEC.

Liver transplantation has emerged as a curative treatment option for selected patients with unresectable hepatic malignancies beyond hepatocellular carcinoma, marking a paradigm shift in transplant oncology. For colorectal cancer liver metastases (CRLM), prospective trials have demonstrated that highly selected patients achieve 5-year OS rates of 60–83%, with the Oslo score identifying optimal candidates for transplantation. Perihilar cholangiocarcinoma (pCCA) has been successfully treated using strict patient selection criteria combined with neoadjuvant therapy, achieving 5-year OS rates of 50–68%, though emerging data suggests chemotherapy-based approaches may be preferable to radiation in selected cases. Intrahepatic cholangiocarcinoma (iCCA), previously considered a contraindication to transplantation, can now achieve excellent long-term outcomes (79.5% 5-year OS) in patients demonstrating sustained response to neoadjuvant chemotherapy and radioembolization, with metabolic tumor volume < 70 cm3 serving as an objective prognostic marker. Across these three emerging indications, successful outcomes depend on strict patient selection based on tumor biology, intensive multimodal neoadjuvant therapy, multidisciplinary evaluation in high-volume centers, and careful observation during treatment to exclude patients with aggressive disease. This evolution in transplant practice offers curative intent therapy to patients that previously only had palliative therapeutic options, fundamentally transforming hepatobiliary and oncologic surgery.

830 Background: Immune checkpoint inhibitors (ICIs) are standard therapy for MSI-H GI cancers. Lynch syndrome, caused by germline mutations in mismatch repair (MMR) genes, leads to MSI-H tumors and robust ICI responses, but its effect on irAEs remains poorly defined. Clarifying this risk may inform treatment selection and toxicity monitoring. Methods: We retrospectively reviewed MSI-H or MMR-deficient (dMMR) GI cancer patients (pts) treated with ICIs across Mayo Clinic (AZ, MN, FL) from January 2017 to June 2025. Eligible pts were identified using Mayo Data Explorer. Demographics, treatment, and irAEs (graded per CTCAE v5.0) were collected. Lynch status was determined by germline testing when available. Logistic regression estimated odds ratios (ORs) for any grade and grade ≥3 irAEs, adjusting for age, cancer type, prior chemotherapy, and treatment regimen. Results: A total of 209 pts with dMMR/MSI-H GI cancer were included: 61 with Lynch syndrome and 148 without. Lynch pts were younger (median 58 vs 76 years, p < 0.001) and more likely to have received prior chemotherapy (62% vs 43%, p = 0.009). Colorectal cancer was the predominant cancer type (74%), but Lynch pts had proportionally more non-colorectal GI cancers (15% vs 2.7%, p = 0.007). Overall, 29% of pts experienced an irAE, with rates significantly higher in Lynch vs non-Lynch pts (43% vs 24%, p = 0.005). The most frequent irAEs were gastrointestinal, endocrine, and dermatologic, followed by hepatic and pulmonary events. Grade ≥3 irAEs occurred in 16% overall, with no significant difference between groups (p = 0.124). In adjusted models, Lynch syndrome was independently associated with a higher risk of any grade irAE (OR 2.14, 95% CI 1.09 - 4.19, p = 0.026), while risk of severe irAEs was not increased (OR 1.55, 95% CI 0.64 - 3.59, p = 0.316). Lynch syndrome pts were more likely to have combination therapy (17% vs 6.8%, p = 0.029). However, there were no differences observed in any grade irAE between monotherapy and combination immunotherapy (OR 1.36, 95% CI 0.49 - 3.54, p = 0.535). Conclusions: Lynch syndrome is associated with a higher prevalence of any-grade irAEs among dMMR/MSI-H GI cancer pts treated with ICIs, though severe events were not increased. Incorporating Lynch status into immunotherapy planning may improve risk stratification and guide regimen selection.

817 Background: Universal germline sequencing is increasingly utilized in practice, but existing evidence and guidelines are based on studies in predominantly white populations. This study aims to compare the prevalence of genetic alterations in white vs underrepresented minority (URM) populations and assess incremental findings discovered with universal testing beyond current guidelines. Methods: This prospective, multicenter study analyzed genetic alterations in white and URM cohorts with primary GI malignancies receiving care at Mayo Clinic cancer centers between April 2018 and April 2025. Patients underwent germline sequencing using a next-generation sequencing (NGS) platform targeting over 80 genes. We compared the distribution of results between white and URM populations. Concordance with NCCN testing guidelines and incremental findings were assessed. Results: A total of 1128 patients were studied, of which 758 were white and 370 were URM, (47.6% Hispanic, 22.7% Black, 13.8% Asian, 10.5% American Indian, 0.8% Pacific Islander, and 6.8% other). Pathogenic variants (PGV) were more common in the white population (16.1% vs 9.2% P < 0.001). Variants of uncertain significance (VUS) were more common in the URM population (53.2 vs 43.5%, P<0.001). A total of 156 patients were found to have a PGV. PGVs outside primary cancer genes were more common in white patients (57.4% vs. 32.4%; p=0.0241). Incremental findings from universal testing were higher in white patients (66.4% vs 35.3%; p=0.0011). Conclusions: This study reveals a significant difference in the prevalence of PGV and VUS between white and URM patients with primary GI malignancies. The higher rate of PGVs in white patients and VUS in URM patients highlights potential inequities in both detection and interpretation of genetic results. These findings emphasize the need for broader representation in genetic databases to ensure equitable access to precision oncology. Screening guidelines met by patients with PGV. White (N=122) URM (N=34) Total (N=156) p value Did they meet NCCN testing guidelines for their primary cancer? 0.0991 Yes 87 (71.3%) 29 (85.3%) 116 (74.4%) No 35 (28.7%) 5 (14.7%) 40 (25.6%) Was the PGV outside of the primary genes recommended for their primary cancer? 0.0241 Yes 70 (57.4%) 11 (32.4%) 81 (51.9%) No 47 (38.5%) 22 (64.7%) 69 (44.2%) Incremental Finding 0.0011 Yes 81 (66.4%) 12 (35.3%) 93 (59.6%) No 41 (33.6%) 22 (64.7%) 63 (40.4%)

679 Background: DNA-damaging agents improve outcomes in metastatic pancreatic cancer (mPC) with homologous recombination repair (HRR) deficiency, albeit use is limited to 6-9% of patients (pts) with BRCA1/2 or PALB2 mutations. We hypothesized that BRCA/PALB2 wildtype mPC may exhibit platinum sensitivity driven by altered HRR gene expression. We correlated HRR gene RNA profiles with real-world overall survival (rwOS) following first-line (1L) platinum therapy (PT). Methods: Tempus Lens, a platform used to query multimodal data from millions of de-identified patient records in the Tempus Database was used to identify mPC pts with wildtype somatic BRCA1/2 and PALB2 who had Tempus xT DNA and xR RNA testing. RNA-seq data were normalized to correct for assay/batch effects, quantified as transcripts per million (TPM) and reported as log2(TPM+1) for 17 HRR genes and GATA6 . Pts were classified as high and low expressors based on the top and bottom quartile gene expression. Pts were grouped as PT-treated (received 1L PT) or PT-naïve (never received PT). Real world overall survival (rwOS) was calculated from 1L start to death or loss to follow up. Risk set adjustment was applied to mitigate immortal time bias. Median rwOS was estimated using Kaplan-Meier and univariate Cox models. A multivariate Cox Proportional (CoxPh) model included PT use, RAS status, and expression of genes (as continuous variables). Results: Among 1,068 pts, the median age was 66 years and 609 (57%) received 1L PT. In low RAD51 expressors, PT-treated pts (n=136) had significantly longer rwOS than PT-naïve (n=112): 11.4 months (95% CI, 7.8–13.8) vs 8 months (95% CI, 5.5–9.0); p=0.028. In contrast, in high RAD51 expressors, rwOS was similar between PT-treated (n=150) and PT-naïve (n=97): 7.9 vs 6.9 months (p=0.236). High GATA6 expression was also associated with improved rwOS in PT-treated pts vs PT-naïve: 13.5 vs. 9.3 months; p=0.011. In multivariate analysis, increased GATA6 expression remained a positive predictor of rwOS (HR 0.82; 95% CI, 0.76–0.88; p<0.001), and high RAD51 expression was associated with shorter rwOS with PT (HR 1.18; 95% CI, 1.01–1.39; p=0.043). Conclusions: In BRCA/PALB2 wt mPC, transcriptomic profiling identified low RAD51 and high GATA6 expression as predictors for improved rwOS when treated with PT. Integrating these biomarkers may improve development of DNA-damaging therapies beyond canonically defined HRD. Hazard ratios of mPC mortality by selected HRR genes estimated by multivariate CoxPh models. HR 95% CI p value 1L PT (vs PT-naïve) 0.87 0.75, 1.00 0.054 BRCA1 1.15 0.98, 1.35 0.079 BRCA2 0.89 0.77, 1.04 0.14 GATA6 0.82 0.76, 0.88 <0.001 NBN 0.97 0.81, 1.15 0.7 RAD51 1.18 1.01, 1.39 0.043 RECQL4 0.94 0.84, 1.04 0.2 Any RAS mutation 1.43 1.14, 1.81 0.002

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%