Grewal, Udhayvir Singh

e13656 Background: Effective multidisciplinary cancer care is bottlenecked by the cognitive burden of synthesizing fragmented electronic health records across different specialties. Current AI tools often function as isolated chatbots rather than integrated workflow assistants. We developed and validated "OncoSphere AI," an Agentic AI multidisciplinary clinical workflow support tool designed to autonomously orchestrate the multidisciplinary review process by deconstructing complex cases into domain-specific insights. Methods: OncoSphere AI is a novel, multi-agent large language model–driven platform that simulates a multidisciplinary tumor board for cancer care. The architecture uses a parallel reasoning framework in which eight virtual specialty agents—Medical Oncology, Radiation Oncology, Surgical Oncology, Pathology, Radiology, Pharmacy, Clinical Research, and Nurse Navigation—independently analyze structured and unstructured patient data against specialty specific guidelines and contemporary peer-reviewed literature. System performance was assessed via built-in telemetry (task completion, latency, inter-agent agreement) and blinded review by eight expert oncologists using a structured survey to rate data extraction fidelity, guideline concordance, safety, and clinical utility compared with standard manual review. Results: The study cohort (n=20, median age 59.5 years; 55% female) had a median of 2.5 (range 0-7) prior lines of therapy and multiorgan metastatic disease (median: 2, range 1–4), including lung, breast, gastrointestinal (CRC, pancreatic, hepatobiliary), and genitourinary (prostate, renal) malignancies. OncoSphere AI demonstrated high workflow utility (mean rating: 4/5) and strong extraction fidelity, with more than 90% of biomarker extractions rated as a “perfect match” by expert reviewers. Operational efficiency gains were substantial with AI processing averaged 4.7 minutes per case versus 29.3 minutes for manual review, corresponding to an 84% reduction in time (p<0.001). System telemetry revealed adaptive compute behavior, with the platform autonomously allocating 1.73-fold more reasoning tokens to complex, refractory cases than to standard scenarios. Safety review identified only one critical contraindication issue in a heavily pretreated, multi-line setting. Conclusions: OncoSphere AI effectively automates the clinical “perception layer,” consistently transforming heterogeneous longitudinal data into decision-grade insights with high fidelity and marked time savings. By operating as a coordinated ensemble of domain-specialized AI agents rather than a single generic model, it offers a scalable approach to reduce physician cognitive burden and to standardize guideline-concordant care planning in diverse, heavily pretreated oncology populations.

Abstract Background Neuroendocrine tumors (NETs) are rare, heterogeneous neoplasms associated with prolonged survival and substantial symptom burden. However, patient-reported outcomes across NET subtypes remain poorly characterized, particularly in real-world settings. This study describes baseline health-related quality of life (HRQoL) and care experiences among patients with gastroenteropancreatic and lung NETs, examining differences by tumor site and time since diagnosis. Methods The Neuroendocrine Tumors–Patient Reported Outcomes study is a prospective, multi-institutional US cohort of adults (aged 18 years and older) with incident small intestinal, pancreatic, gastroenteropancreatic, or lung NETs diagnosed from January 2018 through September 2024, identified via a validated electronic medical record–based computable phenotype. Baseline surveys assessed HRQoL, symptoms, care experiences, and clinical characteristics using validated instruments. Descriptive statistics and standardized mean differences compared responses by NET site and time since diagnosis. Results Among 2367 participants (mean age = 57.8 years; 57.3% female), 1974 had gastroenteropancreatic NETs (659 small intestinal NET, 555 pancreatic NET) and 393 had lung NETs. Fatigue (mean = 33.0), insomnia (mean = 32.5), and diarrhea (mean = 25.7) were the most burdensome symptoms. Lung NET patients reported worse dyspnea (standardized mean difference = 0.58, P &lt; .001) and lower physical, role, and global QoL scores than those with gastroenteropancreatic NETs, while pancreatic NET patients reported better functioning. Diarrhea worsened over time, especially in small intestinal NETs. Most rated care highly (75.3%) but cited concerns about treatment side effects (80.4%), costs (60.7%), and travel burden (58.8%). Conclusions This large US cohort reveals persistent symptom burden and HRQoL variation by tumor site and disease duration, underscoring the need for longitudinal HRQoL assessment in NET care.

Abstract Introduction: Recruitment for rare disease studies is challenging due to small eligible populations. Traditional clinical research management systems often lack tools to track recruitment contacts prior to enrollment. The NET-PRO study, focused on neuroendocrine tumors (NETs), implemented a participation monitoring system to enhance recruitment efficiency and representativeness. Methods: NET-PRO is a multicenter cohort study of 2538 adults diagnosed with gastroenteropancreatic (GEP) or lung NETs between January 2018 and September 2024. Recruitment occurred from January 2022 to February 2025 across 14 U.S. medical centers. Sites used flexible recruitment methods (email, mail, phone, in-clinic) and tracked contacts using REDCap-based tools. Participant characteristics were analyzed by enrollment mode (online or mail) and recruitment difficulty (number of contacts required prior to enrollment) using standardized mean differences, chi-square tests, and ANOVA. Results: Of 9279 contacted patients, 2675 consented (28.8%) and 2538 enrolled (27.4%). Most enrolled online (83.2%), while 16.8% enrolled by mail. Mail respondents were older, had lower education and income, and more comorbidities. Among those enrolled, recruitment difficulty was associated with older age, lower education and income, but not comorbidity. Over half of the most difficult-to-recruit participants enrolled online. Contact methods varied by attempt, with email dominating early contacts and phone/mail used more in later attempts. Conclusions: A participation monitoring tool supported flexible, multimodal recruitment and improved sample representativeness in a rare cancer study. Tracking recruitment contacts enabled adaptive strategies and may reduce bias in observational research by enabling better outreach to harder-to-reach populations.

PURPOSE We conducted a systematic review to evaluate the outcome of patients with early-stage (stages I-III) mismatch repair deficient (dMMR) colorectal cancer (CRC) receiving neoadjuvant immunotherapy (NIT) with immune checkpoint inhibitor (ICI)–based regimens. METHODS MEDLINE, Scopus, Embase, Web of Science, and Cochrane Central Register of Controlled Trials were searched for publications reporting the outcome of patients with early-stage dMMR CRC receiving NIT. The primary outcome measures were the complete response (CR) rate (clinical CR [cCR] or pathologic CR [pCR]) and the incidence of grade 3 or higher toxicities. RESULTS The search identified 37 publications that included 423 patients with colon (n = 326, 77%) and rectal (n = 97,23%) cancers aged 19-82 years; most patients had stage III CRC (88%). Approximately 67% of patients received monotherapy with anti–PD-1 agents; the rest received dual ICIs (ipilimumab plus nivolumab). The CR rate (pCR + cCR) in the overall population was 72% (305 of 423). The R0 resection and pCR rates were 99.3% and 70% among the patients undergoing surgery, respectively. Only four (0.9%) patients had primary resistance to NIT. After median follow-up periods ranging from 4 to 27 months, 3 (0.7%) patients progressed after an initial response. Grade 3 or higher toxicities were uncommon (6.3%), rarely delaying planned surgery. CONCLUSION NIT in patients with early-stage dMMR CRC is associated with a high response rate, low primary resistance to immunotherapy and cancer recurrence rate, and an excellent safety profile. The findings of the present systematic review support further investigation of NIT in patients with early-stage dMMR CRC, with a particular emphasis on the organ-preserving potential of this strategy.

Abstract Introduction: Colorectal cancer (CRC) is the second leading cause of cancer death in the United States (US). Primary care physicians (PCP) are critical towards a successful CRC screening program. However, the impact of availability of PCP on CRC-related mortality is not well studied. Materials and Methods: We extracted data on crude incidence and mortality rates of CRC among all 50 states and District of Columbia (D.C.) from the Center for Disease Control (CDC) WONDER database for the year 2019. Data on number of actively practicing PCPs in all 50 states and D.C. for the year 2020 were obtained from Association of American Medical Colleges (AAMC) State Physician Workforce Data Report. The correlation between the ratio of number of PCPs per CRC case with age-adjusted mortality rate (AAMR) for CRC was studied by state and within White and African American (AA) populations from 2017-2019. Pearson’s co-efficient was used to study correlations and T-test was used for comparing independent samples. Statistical analysis was performed using VassarStats. Results: The median AAMR for CRC from 2017-2019 in the US was 13.2 (IQR 11,15.4) per 100,000 population. AAMR for CRC was significantly higher among AA versus White populations (t=5.79, p&lt;0.001). The national median PCP per CRC case ratio was 2.14 (IQR 1.46, 2.82). Higher state-wide PCP per CRC case ratio correlated with lower state CRC-related mortality (r=-0.36, p=0.011). PCP per CRC case ratio was significantly lower among AA as compared to White populations (t=-15.95, p&lt;0.0001). Higher PCP per CRC case ratio correlated with lower CRC-related mortality among both White (r=-0.64, p&lt;0.0001) and AA (r=-0.57, p=0.0002) populations. Using Fisher r-to-z transformation, we found no significant difference between the correlation of PCP per CRC case ratio with CRC-related mortality in White versus AA populations (z=-0.51, p=0.61). Conclusion: Results of this study suggest that greater availability of primary care physicians correlates with lower CRC-related mortality. AA have a significantly higher AAMR for CRC with a lower PCP per CRC case ratio. This may indicate a lower access to primary care among AA populations with CRC. Our results underscore the need to expand access to primary care among AA populations with the goal of minimizing disparities in CRC-related mortality. Citation Format: Udhayvir S. Grewal, Shiva J. Gaddam, Manik Aggarwal, Subhash C. Garikipati, Prabhat Kumar, Naomi Fei. Correlation of availability of primary care physicians and colorectal cancer-related mortality in the United States: Do racial disparities exist. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 6488.

80 Background: Incidence of colorectal cancer (CRC) among adolescents and young adults (AYA) is increasing. A significant proportion of adolescents and young adults (AYA) with colorectal cancer (CRC) lack traceable genetic risk factors. We sought to study the impact of lifestyle-related risk factors on the incidence and mortality of CRC in these patients. Methods: We extracted data on crude incidence and mortality rates of CRC (reported per 100,000 population) for ages 15-39 years in all 50 U.S. states and District of Columbia from the Center for Disease Control (CDC) WONDER database (1999-2018). Data on risk factors such as obesity, physical activity, alcohol and tobacco abuse and nutrition were obtained from the Behavioral Risk Factor Surveillance System (BRFSS, 2020). Correlations were analyzed using Pearson’s co-efficient. p < 0.05 was considered statistically significant. Statistical analysis was performed using VassarStats. Results: Median crude incidence and mortality rates of CRC in AYA in the US from 1999-2018 were 3.8 (IQR 3.2, 4.4) and 0.7 (IQR 0.5,0.9) per 100,000 population respectively. States with higher age-adjusted prevalence of obesity per 100,000 had higher incidence (r = 0.36, p = 0.01) and mortality rates (r = 0.49, p = 0.0002) of CRC in AYA population. States with a higher age-adjusted prevalence of adherence to recommended weekly aerobic activity had lower incidence (r = -0.4515, p = 0.001) and mortality (r = -0.569, p < 0.0001) rates. While states with higher age-adjusted prevalence of tobacco abuse had higher incidence rate of CRC (r = 0.33, p = 0.02), there was no correlation with mortality rates (r = 0.24, p = 0.09). Higher prevalence of alcohol consumption was associated with decreased mortality rate (r = -0.44, p = 0.001), with no impact on incidence rate (r = -0.16, p = 0.26). States with lower daily consumption of fruits had higher incidence (r = 0.37, p = 0.01) and mortality rates (r = 0.59, p < 0.0001). No correlation of daily consumption of vegetables with incidence (r = -0.1516, p = 0.29) and mortality (r = 0.18, p = 0.22) rates was noted. Conclusions: In the current analysis, higher prevalence of obesity, lower rates of aerobic activity and lower daily consumption of fruits were strongly associated with increased incidence and mortality rates. The impact of tobacco abuse and alcohol consumption was more variable. Apart from improving access to genetic testing and counseling, efforts aimed at mitigating the rise of CRC incidence among AYA should also focus on traditional lifestyle-related risk factors.