Sridhar, Arthi

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 Pulmonary large cell neuroendocrine carcinoma (LCNEC) is a rare, aggressive lung tumor marked by significant molecular heterogeneity. In a study of 590 patients across two independent cohorts, we observed comparable overall survival across treatment regimens (chemotherapy, chemoimmunotherapy, immunotherapy) without unexpected adverse events. Genomic analysis identified distinct NSCLC-like (KEAP1, KRAS, STK11 mutations) and SCLC-like (RB1, TP53 mutations) LCNEC subtypes, with 80% aligning with SCLC transcriptional profiles. Serial sampling revealed stable mutational but shifting transcriptomic landscapes over time. NSCLC-like LCNECs showed elevated FGL-1 (a LAG-3 ligand) and SPINK1 expression, while SCLC-like subtypes expressed higher levels of DLL3. Immunofluorescence confirmed FGL-1 in NSCLC-like LCNECs, and H&E slide analyses indicated fewer tumor-infiltrating lymphocytes in LCNECs versus other lung cancers. These findings highlight LCNEC’s distinct immunogenomic profile, supporting future investigations into LAG-3, SPINK1, and DLL3-targeted therapies.

PURPOSE Although international medical graduates (IMGs) and Puerto Rican Medical Graduates (PRMGs) comprise an integral part of the health care workforce, these individuals, particularly women, frequently face numerous types of discrimination throughout medical training and independent practice. To our knowledge, we conducted the first cross-sectional study to understand the journeys and consequences of migration faced by IMGs and PRMGs in the US oncology workforce. METHODS We developed a cross-sectional, online survey consisting of 51 multiple choice and open-ended questions that captured demographic information, professional status, period of migration to the United States, location within the United States that participants migrated to, reasons for migration, cultural adaptation, experiences of discrimination during training, and overall professional experiences in the United States. RESULTS The majority of participants cited better education, professional gains, and a lack of opportunities in participants' home country as primary reasons for migration to the United States. However, most participants, particularly women, experienced staunch assimilation to fit the mold of professional American standards; women were also particularly likely to report experiences of racial/ethnic, language, and gender discrimination during oncology training in the United States, which only marginally improved during independent practice. Despite such discrimination, most participants reported excellent professional satisfaction during training and independent practice, although only moderate personal satisfaction. Most participants decided to stay in the United States, citing reasons pertaining to enhanced professional opportunities, whereas those that returned home valued reasons relating to family and quality of life. CONCLUSION Our sobering findings underscore the need for institutional enforcement of an inclusive environment encompassing cultural humility, enactment of programs addressing barriers to socialization, immigration laws, and financial support, creation of IMG-specific support networks, and the sponsorship and promoting of minority women physicians.

8106 Background: Due to lack of prospective data, the optimal first line treatment approach for patients (pts) with pure LCNEC histology remains uncertain. Methods: Across 17 centers, we conducted a retrospective analysis of metastatic pure LCNEC (diagnosed at local institutions) who received 1st-line systemic therapy between 2015-2023. Pts were either treated with chemotherapy (chemo), immunotherapy (IO), or a combination (chemoIO). Clinical outcomes were progression-free survival (PFS), overall survival (OS), objective response rates (ORR), and treatment-related adverse events (trAE) as defined using CTCAE 5.0. Survival analysis by genomic alteration status ( TP53, RB1, STK11, KEAP1, KRAS) and PD-L1 status were performed. Results: We identified 161 pts with median age of 67 years (IQR: 58-83) at 1st line systemic therapy; 54% (n = 87) were males. Median follow-up was 55 months (mo), 62 mo, and 29 mo for the chemo, IO, and chemoIO groups, respectively. 79% (n = 127) were former or current smokers. 1st-line treatments were chemo (n = 94), IO (n = 11), or chemoIO (n = 56). Of 85 pts with PD-L1 status, 58 (68%) were 0% and 27 (32%) were ≥1%. The most common chemo regimen was platinum-etoposide (n = 72, 78%). ChemoIO regimens included carboplatin/etoposide/atezolizumab (n = 23, 43%) and carboplatin/pemetrexed/pembrolizumab (n = 17, 31%). In the IO group, 1 patient received dual IO. Lung (n = 74, 46%) and liver (n = 71, 41%) were the most common sites of metastasisThere was no significant difference in PFS across the groups (median PFS [mPFS] chemoIO: 5.7 mo, 95% CI: 5.0-6.3, chemo: 5.1 mo, 95% CI: 3.1-5.9; IO: 3.6 mo, 95% CI: 1.7-6.5) on multivariable analysis adjusting for ECOG and “M” stage (p = 0.2 and 0.24 for chemoIO-chemo and chemoIO-IO comparisons, respectively). There was no difference in OS (mOS chemo: 11 mo, 95% CI: 7.6-17.4; IO: 13.6 mo, 95% CI: 5.9-not reached; chemoIO: 12.2 mo, 95% CI: 7.4-20.6, p = 0.5 and 0.8 for chemoIO-chemo and chemoIO-IO comparisons, respectively). ORR was 35.2% (31/88) in chemo, 25% (2/8) in IO, and 35.7% (20/56) in chemoIO ( p= 0.46). There were no significant differences in PFS and OS outcomes by treatment group when divided by genetic profile (n = 79, methods), or by PD-L1 status (0% vs ≥1%). Any grade trAE occurred in 48 (51%), 5 (45%), and 28 (50%) pts treated with chemo, IO, and chemoIO, respectively. Grade ≥3 toxicity profiles are shown (table). Conclusions: For 1st-line treatment of LCNEC, similar PFS, OS, and ORR were seen for chemo, IO, and chemoIO. This questions the added benefit of chemoIO compared to chemo alone, and warrants future clinical trials to discern the optimal 1st line treatment. [Table: see text]

9011 Background: 'Gender disparities' is a familiar term in medicine. Only 35.2% of oncologists in the U.S. self-identified as women in 2021. Women in medicine are undercompensated and underpromoted. Little is known of the experiences of non-U.S. female physicians in the U.S. We created the first cross-sectional study to assess gender disparities in IMGs and Puerto Rican medical graduates (PRMGs) in oncology in the U.S. Methods: An anonymous online survey was created and distributed via Survey Monkey. Eligible participants were non-U.S. IMGs and PRMGs who trained and/or practiced independently in the U.S. Participants were recruited through email and social media from Sept-Dec 2023. Bivariate association analyses were performed using the two-sample Wilcoxon test for ordered categorical variables and Fisher’s exact test for nominal categorical variables. Results: 97 IMGs and PRMGs in oncology completed the survey. As shown in the table, women were more likely to move to the U.S. for family (22.4% vs 6.2%, p=0.040), whereas men did more for financial gains (20.8% vs 6.1%, p=0.040). culture, particularly to the traditions (65.3% vs 43.8%;p=0.042) and dress code (44.9% vs 20.8%, p=0.017). Women experienced higher rates of gender discrimination during training (53.2% vs 4.5%, p <0.001) and independent practice (57.6% vs 3.6%, p<0.001) than men. Women were also more likely than men to face ethnic/racial discrimination during training (69.6% vs 38.1%; p=0.005). Despite lack of statistical significance, higher trends of ethnic/racial discrimination during independent practice were reported by women (table). More women reported no plans on returning home (68.8% vs 38.3%), whereas more men planned to return home at some point (38.3% vs 16.7%). 18.8% of men vs 0% of women elected leadership opportunities as the reason for returning to their home country (p=0.001). Conclusions: Our study reveals the unfortunate reality that many IMG and PRMG women face in oncology in the U.S. Despite national efforts to reduce the gap in gender disparities, minority women continue to experience racial/ethnic and gender discrimination at higher rates than men. To overcome inequities and achieve gender equity pay transparency, diversity in selection committees is necessary. Further, efforts should be across all settings, academia, private practice, and industry. The time for gender equity in oncology is now. [Table: see text]

9001 Background: With an increasingly diverse patient population in the U.S., the need for a diverse clinician workforce has been exemplified. In 2021, 28% of the practicing physicians in the U.S. were born/trained outside of the continental U.S. Though strides in promoting diversity among oncologists have been made, continuous longitudinal assessments and improvements are important to ensure goals are met. We conducted the first cross-sectional study to understand the challenges and experiences of IMGs and Puerto Rican (PR) medical graduates in oncology in the U.S. Methods: An anonymous online questionnaire via Survey Monkey was developed. Non-U.S. IMGs and PRMGs who trained and/or practicing independently in the U.S. were eligible to participate. The study launched on Twitter with promotional materials, inviting participants to complete the survey. A list of IMGs and PR medical graduates was also compiled and an email invitation with the survey link was sent to. The enrollment period was from Sept-Dec 2023. Data was analyzed using descriptive statistics. Results: 97 participants from oncology-related fields completed the survey. Most were attendings (62.9%), and women (50.5%). 95.9% were IMGs and 5.2% PRMGs. 79.4% participants migrated after medical school and 90.7% were still living In the U.S. The main reasons for migrating were looking for better training (63.9%), seeking professional gains (57.7%), and lack of opportunities in their home country (49.5%). Most had to adapt to new cuisine (51.5%), community (53.6%), traditions (54.6%), and celebrations (58.8%). Participants expressed the need to change their dress code (33%), tone of voice (39.2%), the way they spoke (51.5%), and conducted themselves (49.5%). Participants faced racial/ethnic (54.5%), gender (29.7%), and language (41.9%) discrimination during training in the U.S. Similarly, they experienced racial/ethnic (46.8%), gender (32.8%), and language (24.6%) discrimination during independent practice in U.S. Most participants reported moderate personal (57%), yet extreme professional (57.4%) satisfaction in the U.S. 10.5% of participants had returned to their home country, 27.4% planned to, and 53.7% did not plan to return. The main reasons for going back home were family (67%), quality of life (28.9%), and feelings of isolation/lack of community (22.7%). Conclusions: Our study reveals that the main reasons physicians migrate to the U.S. is for education and professional opportunities. Yet these could come at a high cost, leading foreign-born physicians to compromise their true identities. Despite increasing representation of IMGs and PRMGs in the medical field in the U.S., they remain victims of discrimination at frequent rates. It is imperative to implement changes beyond diversifying the work field and strive for equity to create a more conducive environment for minority physicians.

8602 Background: LCNECs are a rare subtype of lung cancer, with limited clinical trial data and an unclear consensus on first-line treatment. Even less is known about the optimal treatment approach for pts with mixed LCNECs, a pathologic subtype where tumors contain both LCNEC histology as well as features of adenocarcinoma, squamous cell, or small cell lung cancer. Methods: We conducted an international multi-institutional retrospective analysis (n=13 institutions) of pts with advanced or metastatic mixed LCNECs who received 1st-line systemic therapy with either chemotherapy alone (chemo) or chemo-immunotherapy (chemoIO) between 2010-2023. Clinical outcomes included progression-free survival (PFS), overall survival (OS), objective response rate (ORR), and treatment-related adverse events (trAEs). Survival comparisons were made via the log-rank test. Results: Seventy-three pts with mixed LCNECs received either chemo (n=42, 57.5%) or chemoIO (n=31, 42.5%). The most common chemo regimens were carboplatin/etoposide (n=27) and cisplatin/etoposide (n=8), while the most common chemoIO was carboplatin/etoposide/atezolizumab (n=19). Median age at 1st-line therapy initiation was 65 (IQR: 60-72). 64% of pts were male (n=47). The majority were former smokers (n=41, 56.2%), with 22 current smokers (30.1%), and 10 non-smokers (13.7%). Mixed histologies included LCNEC/NSCLC (n=45, 56.2%), LCNEC/SCLC (n=17), LCNEC/carcinoid (n=1), and unspecified mixed LCNEC (n=10). Median PFS for chemo was 5 months (95% CI 2.7-9.2) vs. 6 months (95% CI 4.4-8.3) for chemoIO ( p=0.86). Median OS for chemo was 14.2 months (95% CI 10.4-22.5) vs. 17.2 months (95% CI 9.4-27.2) for chemoIO ( p=0.66). The ORR did not differ between chemo (n=18, 45%) and chemoIO (n=15, 48.4%) ( p=0.81). In the chemo group, 60% (n=25) experienced trAEs of any grade, with 23.8% (n=10) experiencing grade 3+ events and four requiring hospitalizations. For chemoIO pts, 61% (n=19) experienced trAEs, with 25.8% (n=8) experiencing grade 3+ events and six requiring hospitalizations. Neutropenia was the most common grade 3+ trAE for both chemo (n=5) and chemoIO (n=4). Overall, there were no significant differences between chemo or chemoIO groups for ORR ( p=0.81), all-grade trAEs ( p=0.88), grade 3+ trAEs ( p=0.84), PFS ( p=0.86), or median OS ( p=0.66). There were no significant differences in median PFS ( p=0.46) or OS ( p=0.99) for pts with mixed LCNEC/NSCLC vs. LCNEC/SCLC. Conclusions: For mixed LCNECs, there was no significant difference in PFS or OS between first-line treatment with chemo vs. chemoIO, suggesting limited benefit from immunotherapy for these pts. Additionally, survival outcomes did not differ between mixed LCNEC/NSCLC and LCNEC/SCLC, suggesting a biology primarily driven by their neuroendocrine component.

8071 Background: Data from the PACIFIC study demonstrated a 5-yr median progression free survival (PFS) and overall survival (OS) of 16.9 and 47.5 months respectively for patients with stage 3A and stage 3B NSCLC demonstrating a high risk of relapse. The 8th ed. of the IASLC staging project reports that the 60-month OS for stage 3A, B and C disease is 41%, 24% and 12% respectively, indicating that improved treatment options are needed for this patient population. Induction chemo-IO (ID chemo-IO) followed by concurrent chemo-radiation (CRT) has not been fully investigated due to concerns regarding the toxicity profile, but this may representant an important unexplored avenue for research. We aim to describe the outcomes of patients who received ID chemo-IO followed by CRT with or without maintenance IO. Methods: We conducted a retrospective study across all Mayo Clinic sites. Patients were included if they were diagnosed with Stage 3 NSCLC deemed ineligible for resection and/or requiring raditation over a large-field ] by a multidisciplinary team with plans for ID chemo-IO prior to CRT and maintenance IO. A total of 927 cases of stage 3 NSCLC patients were screened and those receiving ID chemo-IO followed by CRT were extracted (n = 36). Clinical endpoints are PFS, OS, overall response rate (ORR) and treatment related adverse events (TrAE) defined using CTCAE 5.0. Results: The median age was 67 years, 52.8% were female, all patients were past smokers and 97.2% identified as white. The tumor histologies were adenocarcinoma (66.67%), squamous (27.8%), mucinous adenocarcinoma (2.8%) and sarcomatoid (2.8%). Majority were Stage 3B (47.2%) followed by 3C (38.9%) and 3A (13.9%). N2 and N3 disease was noted in 36.1% and 55.6% of patients respectively. PD-L1 by IHC was > 1-49% (47.2%), > 50% (22.2%) and < 1% (19.4%). Patients received ID chemo-IO with pembrolizumab (83.3%), nivolumab (11.1%) and atezolizumab (2.78%). Average number of ID chemo-IO cycles were 3.67 cycles. The ORR to ID chemo-IO was 86.11%. The median PFS was 23.67 mths and the median OS was 32.07 months. About 94% of patients received CRT afterwards and 66.67% received maintenance IO with pembrolizumab (53.17%) or durvalumab (45.83%). Any grade TrAE occured in 58.33% of patients. Pneumonitis was the most common event (38.9%). Grade 3 -4 pneumonitis was noted in 28.5% (4/11) patients. Other toxicities included hepatitis (8.3%), colitis (11.1%) and myasthenia gravis (2.8%) and 22% of these TrAE’s were grade 3 or 4. Conclusions: Our results indicate that ID chemo-IO shows promise as a therapeutic approach for patients with unresectable stage III NSCLC, especially for patients deemed ineligible or high risk for upfront radiation. Further investigation is needed through a randomized clinical trial to systematically explore and validate the safety and efficacy of ID chemo-IO.

The therapeutic landscape of the management of stage III non-small cell lung cancer (NSCLC) has drastically evolved with the incorporation of immunotherapy and targeted therapy. Stage III NSCLC accounts for one-third of the cases and the treatment strategy of these locally advanced presentations are diverse, ranging from surgical to non-surgical options; with the incorporation of chemo-immunotherapy, radiation, and targeted therapies wherever applicable. The staging of this disease has also changed, and it is essential to have a strong multidisciplinary approach to do justice to patient care. In this article, we aim to navigate the nuanced approaches in the diagnosis and treatment of stage III NSCLC and expand on the evolution of the management of this disease.

Precision immuno-oncology involves the development of personalized cancer treatments that are influenced by the unique nature of an individual’s DNA, immune cells, and their tumor’s molecular characterization. Biological sex influences immunity; females typically mount stronger innate and adaptive immune responses than males. Though more research is warranted, we continue to observe an enhanced benefit for females with lung cancer when treated with combination chemoimmunotherapy in contrast to the preferred approach of utilizing immunotherapy alone in men. Despite the observed sex differences in response to treatments, women remain underrepresented in oncology clinical trials, largely as a result of gender-biased misconceptions. Such exclusion has resulted in the development of less efficacious treatment guidelines and clinical recommendations and has created a knowledge gap in regard to immunotherapy-related survivorship issues such as fertility. To develop a more precise approach to care and overcome the exclusion of women from clinical trials, flexible trial schedules, multilingual communication strategies, financial, and transportation assistance for participants should be adopted. The impact of intersectionality and other determinants of health that affect the diagnosis, treatment, and outcomes in women must also be considered in order to develop a comprehensive understanding of the unique impact of immunotherapy in all women with lung cancer.