Citations

e16486 Background: Allele-specific KRAS G12C inhibitors have revolutionized lung and colorectal cancer treatment, yet the biology of G12C in other gastrointestinal (GI) malignancies remains undefined. We aimed to elucidate the clinicopathologic and genomic landscape of KRAS G12C-mutated tumors compared to other G12 variants in a large non-colorectal GI cohort. Methods: We queried cBioPortal for pancreatic, esophagogastric, hepatobiliary, ampullary, and appendiceal adenocarcinomas. Following data quality control, the final cohort (n = 6,352) was stratified into KRAS wild-type (n = 3,293), G12C (n = 63), and other G12 variants (n = 2,996). Clinicopathologic features, tumor mutational burden (TMB), microsatellite instability status, and co-alteration in 96 key genes across 11 signaling pathways were compared. Statistical significance was assessed using Fisher’s exact or Chi-square tests for categorical variables and Kruskal-Wallis tests for continuous variables. The Benjamini-Hochberg method was applied to correct for multiple hypothesis testing. Results: KRAS G12C prevalence was 1.0% overall, with significant heterogeneity across cancer subtypes (p < 0.001). Appendiceal adenocarcinoma demonstrated the highest G12C prevalence at 5.71% (10/175), followed by ampullary (1.44%, 2/139), pancreatic (1.17%, 34/2906), hepatobiliary (0.88%, 12/1360), and esophagogastric cancers (0.28%, 5/1772). G12C patients were significantly older than wild-type patients (64.8±11.2 vs 62.5±12.9 years, mean±SD, p < 0.001) but younger than other G12 variant carriers (65.8±10.4 years). G12C tumors demonstrated intermediate genomic instability, with a TMB of 4.82±6.17 compared to 4.98±10.55 in wild-type tumors and 3.67±10.12 in other G12 variants (p < 0.001). Notably, G12C tumors were universally microsatellite stable (0% MSI-H vs 4.0% wild-type vs 0.9% other G12, p < 0.001). Genomic analysis revealed that AKT1 mutations were significantly enriched in the G12C cohort (6.3% vs 0.4%; q = 0.025) as compared to other G12 variants. A trend of increased mutation frequency in HRAS was observed specifically in pancreatic cancers in G12C tumors as compared to other variants (8.8% vs 0.7%; q = 0.083). In pancreatic adenocarcinoma, G12C tumors were enriched for chromatin modifiers, notably ARID1A (17.6% vs 7.7%, p = 0.045) and SETD2 / SETD26 (8.8% vs 1.1%, p = 0.006), though these did not reach FDR significance. Notably, the immunotherapy-resistance drivers STK11 and KEAP1 were absent (0%) in the whole G12C cohort. Conclusions: KRAS G12C represents a biologically distinct subgroup of exon 2 KRAS mutations compared to other KRAS G12 pathogenic variants. The absence of resistance markers and enrichment of actionable AKT1 and chromatin-modifier mutations suggest distinct therapeutic vulnerabilities in non-colorectal KRAS G12C-mutated GI cancers.

Abstract Background Despite the reported benefits, lung cancer screening (LCS) uptake remains alarmingly low in comparison to other cancer screening programs. Objective To develop and evaluate an automated, electronic health record (EHR)-embedded LCS outreach program designed to increase screening uptake while minimizing workload for referring providers and schedulers. Methods We developed an automated outreach and referral program at two Mayo Clinic campuses (Rochester [RST] and northwest Wisconsin [NWW]) coupled with a streamlined virtual care delivery process. Eligible patients were identified based on the information in the EHR regarding US Preventive Services Task Force guidelines for screening and were contacted through either a patient portal message, letter, or both. Outreach included LCS educational materials and self-scheduling instructions for a telephone or video shared decision-making (SDM) visit. During the visit, a licensed care team member discussed the risks and benefits of a low dose computed tomography (LDCT) scan with patients who could choose to enroll in the Lung Cancer Screening Program or decline. Results During the study period, 8,845 eligible patients (RST: 2201, NWW: 6644) were contacted using automated portal messages, letters, or both. Among the RST cohort, 2,156 portal messages and 1,060 letters were distributed in comparison to 7,642 portal messages, 6,441 letters, and 618 text messages in the NWWI cohort. The study showed increase in shared decision-making visits completion and screenings for eligible patients across both groups. Portal engagement was higher among the RST group 75.4% than 55.8% in the NWWI group, as was digital brochure access (14.1% vs 6.5%). Scheduling for share-decision-making visits was noted to be higher among the RST group (22% vs 13.6%), though visit completion rates were similar across sites (12.6 vs 13.6%). A lower opt-out rate was noted among the RST group (12.6% vs. 14.3%). Collectively, both campuses demonstrated meaningful patient engagement. Conclusion The automated outreach program effectively increased lung cancer screening engagement and uptake for eligible patients without adding significant administrative burden on primary care providers and clinical staff. Observed differences in engagement between sites, as well as relatively low completion rates highlight the need for further investigation into contextual and operational factors influencing program performance. This abstract is funded by: none

Abstract Introduction Hypertrophic cardiomyopathy (HCM) is an autosomal dominant disorder with a pathogenic mutation identified in approximately 50% of cases. The MYH7 and MYBPC3 genes account for over half of these cases, while dozens of other genes can be pathogenic(1). Genetic test results are not independently used to determine which people with HCM benefit from implanted cardiac defibrillators (ICDs)(2, 3). Little is known about the additive role of genetic testing results to existing indications for ICD insertion. Purpose This study aims to examine the interaction between genetic testing results and existing ICD indications and imaging results on defibrillator discharge rates in HCM. Methods Patients who underwent an ICD for HCM, who underwent a cardiac magnetic resonance (CMR) study and who underwent genetic testing were included across 3 sites. The outcome was the incidence rate of appropriate ICD discharges, calculated using cox regression controlling for current age and primary vs secondary prevention. Interaction analysis between genetic risk factors and existing ICD indications, and with CMR quantification of LGE and septal thickness, was performed, and stratum specific estimates calculated using linear computation. Results 177 patients were included in the study, of whom 70 (39.55%) had a pathogenic mutation, 5 (2.82%) had a variant likely pathogenic (VLP), 44 (24.86%) had a variant of undetermined significance (VUS) and 58 (39.55%) had no identifiable mutation. The event rate was 3.32 {2.28 to 4.84) per 100 person years. There was no association between genetic variables and ICD discharge rate. There was an 80% reduction in ICD discharge rate in people who underwent ICD insertion exclusively for family history of sudden cardiac death or for syncope who had no pathogenic or likely pathogenic mutation, however this change was not statistically significant (table 2). Conclusion There is no strong association between genetic characteristics and ICD discharge rates among people with hypertrophic cardiomyopathy with an existing ICD indication. There is a nonsignificant trend towards fewer ICD discharges among people who underwent ICD insertion for family history alone or for a history of syncope and did not have a pathologic variant.Table 1 Table 2

Introduction: Hypertrophic cardiomyopathy (HCM) is the most common cardiomyopathy. People with HCM are at risk of cardiac arrest. ACC/AHA guideline-supported indications for ICD placement include cardiac arrest or VT, family history of sudden cardiac death in a close relative ≤50, massive septal hypertrophy (MSH - septal thickness ≥30mm), apical pouch, and non-sustained ventricular tachycardia (NSVT). Methods: People attending any Mayo Clinic site on > 1 occasion who underwent ICD placement for HCM who had documented cardiac magnetic resonance (CMR) results were included in the study from time of ICD placement to last device interrogation. Outcome was incidence rate of first appropriate shock. Multivariable cox regression was used to examine the association between septal thickness and shock rate, controlling for current age, sex and secondary vs primary prevention device. An interaction term for association between septal thickness and each ICD indication in turn was incorporated into regression, and stratum specific estimates produced using linear computation. Results: 326 people were included in the study, of whom 50 experienced at least one appropriate ICD shock over 1,487.95 person years (incidence rate 3.36 per 100 person years, NNT 29.76 per year). MSH was strongly associated with shock rate (HR 2.29 [1.19 to 4.40], p=0.013). In people without MSH, there was a 50% reduction in shocks where a subjective measure (syncope or family history of sudden cardiac death) was present (table 1). In this cohort, NSVT resulted in a threefold increase in incidence of shock (HR 3.15 [1.446 to 6.47], p=0.003). In the presence of MSH, there was a four-fold increase in shock rate in people who underwent ICD insertion for family history of sudden cardiac death or for syncope (table 2). There was no difference in shock rates in people with NSVT prior to ICD placement based on septal thickness (HR 0.76 [0.21 to 2.74], p=0.679). There was strong evidence of interaction between NSVT and MSH on shock rates (LR χ2 =6.94, p=0.008), such that presence of both risk factors did not increase shock rate. Concurrent presence of late gadolinium enhancement (LGE) >15% on CMR and MSH was associated with a significant increase in shock rate (3.58 [1.43 to 8.98], p=0.006). Conclusion: MSH is a helpful indicator of who will benefit from ICD placement among people with a pre-existing indication for a device, particularly among those with a more subjective indication for a device.

INTRODUCTION: Screening for Barrett's esophagus (BE) is suggested in those with risk factors, but remains underutilized. BE/esophageal adenocarcinoma (EAC) risk prediction tools integrating multiple risk factors have been described. However, accuracy remains modest (area under the receiver-operating curve [AUROC] ≤0.7), and clinical implementation has been challenging. We aimed to develop machine learning (ML) BE/EAC risk prediction models from an electronic health record (EHR) database. METHODS: The Clinical Data Analytics Platform, a deidentified EHR database of 6 million Mayo Clinic patients, was used to predict BE and EAC risk. BE and EAC cases and controls were identified using International Classification of Diseases codes and augmented curation (natural language processing) techniques applied to clinical, endoscopy, laboratory, and pathology notes. Cases were propensity score matched to 5 independent randomly selected control groups. An ensemble transformer-based ML model architecture was used to develop predictive models. RESULTS: We identified 8,476 BE cases, 1,539 EAC cases, and 252,276 controls. The BE ML transformer model had an overall sensitivity, specificity, and AUROC of 76%, 76%, and 0.84, respectively. The EAC ML transformer model had an overall sensitivity, specificity, and AUROC of 84%, 70%, and 0.84, respectively. Predictors of BE and EAC included conventional risk factors and additional novel factors, such as coronary artery disease, serum triglycerides, and electrolytes. DISCUSSION: ML models developed on an EHR database can predict incident BE and EAC risk with improved accuracy compared with conventional risk factor-based risk scores. Such a model may enable effective implementation of a minimally invasive screening technology.

Understanding temporal dynamics of COVID-19 symptoms could provide fine-grained resolution to guide clinical decision-making. Here, we use deep neural networks over an institution-wide platform for the augmented curation of clinical notes from 77,167 patients subjected to COVID-19 PCR testing. By contrasting Electronic Health Record (EHR)-derived symptoms of COVID-19-positive (COVID pos ; n = 2,317) versus COVID-19-negative (COVID neg ; n = 74,850) patients for the week preceding the PCR testing date, we identify anosmia/dysgeusia (27.1-fold), fever/chills (2.6-fold), respiratory difficulty (2.2-fold), cough (2.2-fold), myalgia/arthralgia (2-fold), and diarrhea (1.4-fold) as significantly amplified in COVID pos over COVID neg patients. The combination of cough and fever/chills has 4.2-fold amplification in COVID pos patients during the week prior to PCR testing, in addition to anosmia/dysgeusia, constitutes the earliest EHR-derived signature of COVID-19. This study introduces an Augmented Intelligence platform for the real-time synthesis of institutional biomedical knowledge. The platform holds tremendous potential for scaling up curation throughput, thus enabling EHR-powered early disease diagnosis.