Roy, Arya Mariam

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.

PURPOSE Despite international medical graduates (IMGs) accounting for up to one third of all practicing oncologists in the United States, and nearly half of fellowship trainees, little is known about their contributions to presentations at international oncology meetings. Therefore, we investigated the representation of IMGs in invited faculty roles at the ASCO Annual Meeting as a representative example. METHODS Presentation data from ASCO 2022 and 2023 Annual Meetings were obtained from program guides. We collected presentation-level and speaker-level variables of invited faculty roles and original research. Speakers were categorized as American medical graduate (AMG), IMG, non–US-based, or non-MD (Doctor of Medicine). Univariable and multivariable analyses assessed factors influencing selection for invited faculty roles. RESULTS A total of 2,590 presentations by 2,109 unique speakers were reviewed, including primary research presenters and invited faculty. Among the 1,352 presentations by AMGs, 30% were primary research and 70% were invited faculty roles. For the 374 presentations by IMGs, 41% were primary research and 59% were invited faculty roles. Notably, first-author IMGs were significantly less likely to receive invited faculty roles relative to their primary research output compared with first-author AMGs (adjusted odds ratio, 0.69 [95% CI, 0.53 to 0.90]; P = .006), even when accounting for academic rank, presumed sex, and year. CONCLUSION Relative to IMGs' original research output, IMGs appear to receive fewer invitations for ASCO Annual Meeting invited faculty roles compared with AMGs. Our findings suggest potential underrepresentation and under-recognition of IMGs in these roles, despite their contributions to the oncology workforce in the United States.

9009 Background: International Medical Graduates (IMGs) are a vital component of the US oncology workforce, representing nearly half of practicing medical oncologists. However, systemic barriers may influence their career trajectories differently. Understanding these challenges is essential for addressing workforce disparities and optimizing cancer care delivery across diverse geographic regions. Methods: We conducted a cross-sectional study of 13,497 medical oncologists using the 2024 Dec CMS Provider Dataset linked with the 2023 Rural-Urban Continuum Codes (RUCC). Medical oncologists were identified by their self-reported primary specialties, including Hematology/Oncology, Medical Oncology, and Hematopoietic Cell Transplant. Physicians were categorized by graduation origin (based on their self-reported medical school), career stage (early: 0–10 years, mid: 11–30 years, late: >30 years post-medical school graduation). The primary outcomes included practice at Main Campus of NCI Designated Cancer Centers (as an indicator of academic practice) and the geographical location of their practice (Metro, Non-Metro, Mixed). We employed chi-squared tests for statistical comparisons and performed stratified analyses by career stage to evaluate transition patterns over time. Results: 6920 IMGs constituted 48.7% of the oncology workforce, with similar gender distributions between IMG and non-IMG oncologists (37.9% vs 36.5% female, p=0.068). Notably, early career oncologists were less likely to be IMGs (IMG vs non-IMGs: 8.2% vs 12.5%, p<0.001). Compared to Non-IMGs, IMG oncologists are less likely to practice at main campuses of NCI Center (19.9% vs. 27.7%, p<0.001), especially as their career advances (all p<0.01). (Table). IMGs had higher representation in non-metropolitan areas than non-IMGs (11.4% vs 9.1%, p<0.001), particularly in late-career stages (14.7% vs 12.3%, p=0.033), indicating their unique role in serving underserved regions. (Table). Conclusions: Our findings reveal that, IMGs are less likely to practice at main campuses of NCI-Cancer Center than their non-IMG colleagues. Meanwhile, IMG oncologists are disproportionately serving rural communities. Supporting IMG pathways in oncology is critical to ensure a balanced cancer care delivery across the United States. Practice setting distribution and academic affiliation among international medical graduates (IMGs) and US graduates (USGs) by career stage. IMG (N=6,577) Non-IMG (N=6,920) IMG (N=6,577) Non-IMG (N=6,920) NCI Center Other NCI Center Other Metro Non-Metro/Mixed Metro Non-Metro/Mixed Total 19.9% 80.1% 27.7% 72.3% 88.6% 11.4% 90.9% 9.1% Career Stage Early (0-10y) 29.1% 70.9% 36.1% 63.9% 91.1% 8.9% 95.4% 4.6% Mid (11-30y) 21.3% 78.7% 28.8% 71.2% 90.1% 9.9% 91.6% 8.4% Senior (30+y) 15.0% 85.0% 22.0% 78.0% 85.3% 14.7% 87.7% 12.3%

9000 Background: Despite IMGs accounting for up to one-third of all practicing oncologists in the United States, little is known about their contributions to presentations at international oncology meetings, such as the American Society of Clinical Oncology (ASCO). Therefore, we investigated the representation of IMGs in invited faculty roles at ASCO Annual Meetings. Methods: Speaker presentation details at ASCO 2022 and 2023 Annual Meetings were collected using publicly available program guides. We collected presentation-level variables of invited faculty roles (discussant, moderator, chairmanship, session topic presenter) and original research type (oral abstract, poster discussion, plenary session). Speaker-level variables comprised presumed gender, academic rank, and institution. Speakers were categorized into the following groups - American Medical Graduate (AMG): currently affiliated with a US institution, completed medical school in the US; IMG: affiliated with a US institution, completed medical school outside the US; non-US based speakers: affiliated with an institution outside the US; non-MD speakers. Univariable and multivariable analyses were employed to assess factors associated with the selection of presenters for invited faculty roles. Results: A total of 3337 presentations (1649 from 2022, 1688 from 2023) were included. 71.6% of the speakers were US-based, 56.6% were male and 40.5% were full professors. The highest proportion of podium presentations was by AMGs (48.5%), followed by non-US based (28.3%), IMGs (14.1%), and non-MD (9.1%) speakers. 57% of IMG presentations consisted of original research compared to 48.7% for AMGs (Table). Notably, compared to AMGs, IMGs were significantly less likely to be included in invited faculty roles (odds ratio [OR] 0.72 [95% CI 0.58 – 0.88], p <0.01), a finding that remained significant after accounting for gender and academic rank (adjusted OR 0.75 [0.61 – 0.94], p= 0.01). Conclusions: Relative to IMGs’ original research output, IMGs appear to receive less invitations for ASCO Annual Meeting invited faculty roles compared to AMGs. Our findings suggest potential under-representation and under-recognition of IMGs in these roles, despite their contributions to the oncology workforce in the US. [Table: see text]

e13683 Background: Access to specialized cancer care varies by place of residence, partly due to differences in geographic proximity to designated cancer centers. Telehealth services can help alleviate some of these geographic disparities. In response to the COVID-19 pandemic, Medicare telehealth services were expanded rapidly. In this study, we sought to describe the geographic variations in Medicare telehealth utilization and their relationship with locations of designated cancer centers in the United States. We hypothesized that differences in telehealth utilization might be reflective of barriers to telehealth access for Medicare beneficiaries in these regions. Methods: We used the Medicare Telehealth Trends data file and calculated the proportion of Medicare users who used a telehealth service (% Telehealth Users) across all quarters of 2021. To obtain % Telehealth Users in a state, the number of telehealth users were divided by the total number of telehealth-eligible users. Then, using % Telehealth Users as a metric of telehealth utilization, we ranked all US states by overall % Telehealth Users, and % Telehealth Users in rural and urban locations. Finally, we correlated these ranks with the presence of an NCI (National Cancer Institute) Designated Cancer Center within the states. Results: The % Telehealth Users ranged from 15%-53% overall, 16%-54% for rural locations, and 14%-54% for urban locations, across lowest ranked to highest ranked states. The 5 lowest ranking states and their respective % Telehealth Users overall were- Wyoming (20%), Montana (20%), Iowa (20%), South Dakota (18%), Nebraska (17%), and North Dakota (15%). The lowest ranking states in terms of rural % Telehealth Users were Montana, Kansas, Iowa, Tennessee, Wyoming (19% each), and South Dakota and Nebraska (16% each). The lowest ranking states in terms of urban % Telehealth Users were Montana (20%), Wyoming (20%), Nebraska (19%), South Dakota (16%), and North Dakota (14%). 4 out of 6 states overall, 3 out of 7 in the rural category, and 4 out of 5 states in the urban category that were ranked the lowest in telehealth utilization did not have an in-state NCI designated cancer center. Conclusions: Telehealth services can bridge gaps in access to specialty cancer care for patients that do not live in geographic proximity of cancer centers. However, regions lacking geographic proximity to cancer centers were also regions with poorest telehealth utilization. Advocacy and policy efforts directed towards increasing access to telehealth can ensure equitable and timely access to specialized cancer care in these regions of need.