Giridhar, Karthik V.

PURPOSE Incorporation of structured data elements within the electronic health record generates real-time data for many potential uses. However, this requires a change in documentation practices, which may increase documentation effort. The best strategies to support structured documentation interventions have not been thoroughly investigated. Herein, we report the results of extending a data capture tool across multiple disease sites and practice locations. METHODS A note-based data capture tool was developed to collect five data elements using minimum common oncology data elements language. Soft-stop close visit validation (CVV), offloading of data entry tasks to allied health staff, group education, individualized e-mails, and one-on-one assistance were used to support utilization. Baseline and follow-up surveys were collected. For each provider, we compared data capture in the 6 months before and after their CVV go-live. RESULTS Forty-five providers participated (31 physicians, 14 nurse pracationers and physician assistants [NPPAs]), resulting in 23,274 encounters pre-CVV go-live and 23,146 post-CVV go-live visits. Median percentage of all data elements captured increased from 69.5% to 82.6% across all providers. The effect of CVV was immediate and sustained. When surveyed, most respondents agreed with the value propositions of understanding practice population, outcomes, selecting trials to open, and identifying patients for trial enrollment. Most respondents (15/20, 75%) felt the soft stop was a helpful reminder. CONCLUSION Structured data can be successfully collected in provider notes with >80% data capture. Personalized assistance incorporating the structured data elements into users' preexisting templates and soft-stop CVV, along with monitoring the results of implementation and personalized follow-up, was used to support the structured data capture intervention.

Abstract Background: Accurate staging is essential for treatment selection, prognosis assessment, and trial eligibility. While prior studies attempted automating pathological (p) staging, few address clinical (c) staging and no studies have compared LLM-derived staging with clinician staging during clinical visit and retrospective cancer registry staging. Methods: We developed a multi-agent framework using Gemini-2.0-Flash-001 and GPT-5 to (1) identify reports (2) extract key data, and (3) apply AJCC 8th edition staging criteria. LLM staging was compared with clinician documentation and registry staging in breast cancer patients. Clinician-registry agreement served as the reference standard. Two independent breast oncologists reviewed discordant cases. Results: We analyzed 122 randomly selected breast cancer patients across all three Mayo Clinic sites from 2018 - 2023. LLM performance matched or exceeded human inter-rater agreement for pathological staging (95-99.2% vs. 95-98.4%). Clinical staging was more challenging, with LLM concordance of 73-77.9% for cT and 87-89.3% for cN versus 87.8% and 91.0% clinician-registry agreement. Among 89 patients with clinician-registry concordance, LLM concordance was 98.9% for pT/pN, 79.8% for cT, and 91.0% for cN. Experts favored LLM staging in 27.8% (5/18) of cT and 25.0% (2/8) of cN discordances. Error analysis revealed LLM challenges in handling non-mass enhancements (6 cases), selecting radiologic measurements (2 cases), identifying discrete masses (2 cases), and miscellaneous (3 cases). Conclusion: LLMs achieved human-level performance for pathological staging (98%), supporting human-in-the-loop deployment. For clinical staging (79.8% cT, 91.0% cN), future work must enhance multimodal reasoning and integrate physical examination data. Prospective validation is needed to assess real-world impact. With targeted refinements and oversight, automated staging can transform registry workflows while augmenting clinical decision-making. Citation Format: Arshad Mohammed, Umair Ayub, Pooja Advani, Shakeela W. Bahadur, Amye J. Tevaarwerk, Tufia C. Haddad, Elisabeth I. Heath, Brenda J. Ernst, Ben Zhou, Cui Tao, Sara J. Holton, Karthik V. Giridhar, Irbaz B. Riaz. Automating clinical and pathological staging for breast cancer patients [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 2744.

405 Background: Clinical trials are critical to advancing prostate cancer treatment, yet patient enrollment remains a major bottleneck. Despite strong interest in AI for trial matching, real-world use remains limited due to reasons such as complex infrastructure requirements. To address this, we developed a lightweight, scalable AI framework leveraging the Google Healthcare Search API—requiring minimal technical expertise—to automate trial eligibility screening. Methods: We used a pre-trained GPT-5 large language model (LLM) to decompose the eligibility criteria of 13 prostate cancer clinical trials into 269 YES/NO questions, such that for an eligible patient of a given trial, the chart review would yield YES for inclusion and NO for exclusion questions. From 348 patients enrolled in one of the trials, we built a dataset linking each eligibility question to each patient, resulting in 4,947 patient–question pairs (2,034 inclusion pairs with YES labels and 2,913 exclusion pairs with NO labels). The task was framed as binary classification. During evaluation, for each patient–question pair, the LLM extracted search phrases from the question to retrieve relevant EHR information via the Google Healthcare Search API, then used the question and retrieved information to predict YES or NO responses. Performance was measured using accuracy, precision, recall, specificity, and F1 score. Results: Across 4,947 question–patient pairs, our framework achieved 0.81 accuracy, 0.85 precision, 0.65 recall, 0.92 specificity and a F1 score of 0.74. Results for different phases of trials is reported in Table 1, which demonstrates the approach’s robustness across trial phases. Predictions for exclusion criteria were highly precise, while inclusion criteria were more challenging. Most errors were observed in criteria involving complex nested logical conditions, interpretable clinical definitions and data not explicitly measurable or recorded in the EHR (e.g., planned treatments or clinician-assessed scores). Conclusions: This work demonstrates a practical AI framework to support clinical trial matching. The system can identify complex disease states (biochemical recurrence vs radiographic metastasis), castration status (sensitive, resistant) and genomics. Future work should focus on developing human-in-the-loop supervision and improving question decomposition to reduce errors in complex eligibility criteria. Screening performance of the proposed framework across different phases of trials. Trial Phase #Patient-Question Pairs #YES/NO labels Accuracy Precision Recall Specificity F1 score I, II, I/II 4,227 Yes: 1,735 No: 2,492 0.80 0.84 0.66 0.92 0.74 III 720 Yes: 299 No: 421 0.82 0.90 0.63 0.95 0.74 All 4,947 Yes: 2,034 No: 2,913 0.81 0.85 0.65 0.92 0.74 #YES/NO labels: The number of patient-question pairs that are labeled YES/NO among total patient-question pairs of the same row.

Abstract Purpose Background parenchymal enhancement (BPE), the contrast enhancement of normal fibroglandular tissue on dynamic contrast-enhanced breast MRI, is hormonally dependent and fluctuates with the menstrual cycle, lactation, and pregnancy. In patients with breast cancer, both endocrine therapy and chemotherapy can decrease BPE levels during treatment. Notably, a lack of BPE suppression was associated with inferior response after neoadjuvant chemotherapy in hormone receptor-positive (HR+) cancer. In HR+ breast cancer, BPE may be particularly relevant as estrogen fuels the tumor’s growth. However, there is limited clinical research directly comparing BPE and serum estradiol levels. This study aimed to investigate 1) the correlation between BPE and serum estradiol levels in treatment-naïve premenopausal patients with HR+ breast cancer and 2) the association between BPE suppression and serum estradiol suppression during neoadjuvant endocrine therapy (NET). Methods We retrospectively reviewed data from premenopausal patients enrolled in the Endocrine Optimization Pilot (EOP), a sub-study of the I-SPY 2 TRIAL, which tests new endocrine strategies in patients with stage 2/3, MammaPrint (MP) low-risk (index 0 to 1), HR+/HER2-negative (HER2-) breast cancer. Patients with MP High1 (index -0.57 to 0) tumors were eligible if clinically node negative. This study included 58 EOP patients who had both serial serum estradiol levels (drawn monthly) and BPE data available. These patients started ovarian function suppression (OFS) at various times based on their assigned treatment regimen: before NET start, n=28; at cycle 1, n=16; at cycle 2, n=14. The average estradiol levels over six months on NET were categorized into two groups: suppressed to the postmenopausal range (<10 pg/mL) or non-suppressed (≥10 pg/mL). MRI scans at baseline (before NET) and pre-surgery (after six months of NET) were analyzed. BPE was calculated on the contralateral breast as the mean early (∼150s post-contrast injection) percent enhancement of the central 50% of the axial slices. The Spearman’s correlation coefficient and the Wilcoxon rank-sum test were used to examine the relationship between BPE and estradiol. Results Treatment-naïve estradiol levels were available for 25 of the 58 patients, with the median [1st, 3rd quartile] of 82.7 [32.4, 250] pg/mL. A positive correlation was observed between treatment-naïve estradiol and baseline BPE, with a correlation coefficient of ρ = 0.74 (p < 10-5). There was no significant difference in the treatment-naïve estradiol levels between patients who later showed estradiol suppression to the menopausal range during NET (n=14 [56 %]) and those who did not (n=11 [44 %]) (81.3 pg/mL versus 86.5 pg/mL, respectively (p=0.39)). During NET, estradiol levels were suppressed to the postmenopausal range in 26 of the 58 patients (45%). Estradiol suppression was significantly associated with greater reduction in post-treatment BPE: -42.7% [-54.3, -21.8] BPE reduction for the suppressed estradiol group versus -15.0% [-40.6, 6.85] for the non-suppressed estradiol group (p=0.002). Conclusion This study demonstrates the estrogen dependency of BPE in premenopausal patients with HR+/HER2- breast cancer. Baseline estradiol levels positively correlated with baseline BPE, and the suppression of on-treatment estradiol was associated with greater BPE suppression following NET. Our findings further support exploration of the use of BPE as a reflection of estradiol level under NET and OFS in addition to other MRI biomarkers such as functional tumor volume. These complementary imaging biomarkers could independently reflect both non-malignant and tumor-specific biological processes to improve predicted performance. Citation Format: S. Choi, N. Onishi, P. Metanat, R. Mukhtar, K. Giridhar, M. P. Goetz, L. Huppert, A. Elias, O. Olopade, I-SPY2 Imaging Working Group, I-SPY2 Investigator Network, L. Esserman, J. Chien, N. Hylton. Correlation between MRI background parenchymal enhancement and serum estradiol in premenopausal patients on neoadjuvant endocrine therapy for breast cancer [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS3-07-22.

Approximately 80% of invasive breast cancers are classified as human epidermal growth factor receptor 2 (HER2)-negative; however, many of these tumors have detectable levels of HER2 surface expression. Trastuzumab deruxtecan (T-DXd) is a HER2-directed antibody-drug conjugate with a membrane-permeable payload that is cytotoxic to both HER2-expressing tumor cells and neighboring cells via the bystander antitumor effect. T-DXd has shown significant antitumor activity in clinical trials for patients with HER2-positive (immunohistochemistry [IHC] 3+ or IHC 2+/in situ hybridization [ISH]+) breast cancer. In addition, the results of the DESTINY-Breast04 trial demonstrated the clinical benefit of T-DXd in patients with HER2-low (IHC 1+ or IHC 2+/ISH−) breast cancer after receiving prior chemotherapy. DESTINY-Breast06 demonstrated the clinical benefit of T-DXd in patients with hormone receptor (HR)-positive, HER2-low (IHC 1+ or IHC 2+/ISH−), and HER2-ultralow (IHC 0 with membrane staining) metastatic breast cancer who had not received prior chemotherapy in the advanced setting. These results validate the need for a standard-of-care diagnostic test to identify HER2-low and HER2-ultralow expression levels in patients with metastatic breast cancer to guide therapeutic decision-making. Furthermore, effective treatment sequencing strategies and adverse event management are essential for maximizing patient benefit. This review presents the identification of HER2-low and HER2-ultralow breast cancer, sequencing of T-DXd with other treatments, and management of common or clinically significant adverse events reported with T-DXd.

Abstract A blood-based multi-cancer early detection (MCED) test has demonstrated feasibility as a screening tool in large-scale clinical trials. The PATHFINDER 2 (PF2) study (NCT05155605) evaluates safety and performance of the MCED test in a diverse intended-use population. To gauge generalizability of study results, we assessed participant (ppt) baseline characteristics vs general US population data from the National Health and Nutrition Examination Survey (NHANES). PF2, a prospective, multicenter, interventional study, enrolled ppts aged ≥50 y from diverse clinical settings in North America. Enrollment targets for sex and race/ethnicity were established from the 2019 American Community Survey (US Census Bureau). Recruitment strategies were implemented to maximize enrollment for groups historically underrepresented in clinical studies. Exclusion criteria included clinical suspicion of cancer or cancer diagnosis/treatment within 3 y. Data on baseline characteristics and key cancer risk factors were collected at enrollment. We compared the PF2 study population to a nationally representative sample of US adults aged ≥50 y from 2017-2020 NHANES data. NHANES data were weighted using complex, multistage probability sampling to generate a nationally representative sample. There were 35,878 ppts enrolled in PF2; 35,307 clinically eligible and evaluable ppts were included in this analysis. Mean age was 64 y for both PF2 and NHANES; 56.2% were females in PF2 vs 53.6% (95% CI 52.0-55.3%) in NHANES. Race/ethnicity distribution for PF2 vs NHANES was 7.4 vs 11.0% (8.9-13.1%) Hispanic, 74.6 vs 69.7% (65.0-74.5%) non-Hispanic (NH) White, 8.6 vs 10.3% (7.6-13.1%) NH Black, and 5.8 vs 5.1% (3.5-6.8%) NH Asian. In terms of lifestyle characteristics for PF2 vs NHANES, 58.9 vs 29.2% (25.8-32.7%) had at least a bachelor’s degree, 74.8 vs 63.8% (60.6-67.0%) were married/living with a partner, 69.3 vs 53.8% (50.9-56.7%) had never smoked, 66.5 vs 70.4% (68.0-72.8%) were overweight/obese, and 24.2 vs 28.4% (26.4-30.3%) reported never using alcohol. PF2 enrolled a diverse ppt population that is reasonably reflective of the demographics of the US population aged ≥50 y. As is typical for clinical trials, a higher percentage of PF2 vs NHANES ppts reported lifestyle characteristics associated with better health. As the study population largely reflects the MCED test intended-use population, safety and performance results from PF2 are expected to reflect real-world clinical experience. Citation Format: Shirish Gadgeel, Nima Nabavizadeh, Dax Kurbegov, Charles McDonnell, III, James W. Lillard, Jr., Marc Matrana, Alan Roth, Andrea Johnston, Sami Tahhan, Rami Owera, Matthew Margolis, Anuraag Kansal, Margarita Lopatin, Margaret McCusker, Karthik V. Giridhar. Baseline participant characteristics from PATHFINDER 2, a prospective interventional study of a multi-cancer early detection test in a population setting [abstract]. In: Proceedings of the 18th AACR Conference on the Science of Cancer Health Disparities; 2025 Sep 18-21; Baltimore, MD. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2025;34(9 Suppl):Abstract nr C145.

e14545 Background: Next generation sequencing (NGS) identifies genomic alterations in DNA obtained from tissue biopsies and/or blood [circulating tumor (ct)DNA]. We anticipate a lower rate of copy number loss (CNL) in ctDNA compared to tissue, as lower ctDNA tumor fraction may limit the ability to detect a deletion. However, we observed several instances of a CNL in ctDNA that was not identified in a tissue specimen, prompting this systematic evaluation of an institutional dataset. We focused on BRCA1/2 pathogenic variants (PVs) given their therapeutic implications and coverage across testing platforms. Methods: Using an IRB-approved protocol, we evaluated an institutional repository of NGS results performed across the Mayo Clinic Enterprise. We focused on patients (pts) who had both tissue and blood NGS testing performed. We further narrowed this cohort to those with a BRCA1/2 PVs, somatic and/or germline, as determined by testing performed at Guardant Health, Tempus, or Foundation Medicine. We abstracted information about each variant, including type of alteration classification and functional impact. Demographic information, cancer characteristics, and germline testing information was collected. Fisher’s exact test was used to compare alteration frequencies in ctDNA vs tissue using GraphPad Prism v 10.1. Results: From Dec 2015-Sept 2024, we identified 158 unique pts with BRCA1/2 PV who had NGS results for both tissue and ctDNA. The median age at first reporting BRCA1/2 variant was 67 years (range: 29-98 years). 48% of pts were female, and the most common cancer type sites were lung (23%), colorectal (20%), and pancreaticobiliary (20%). We identified 198 unique pathogenic genomic alterations; 71 in BRCA1 & 127 in BRCA2 . Most common alteration was an SNV or indel (127/198), followed by CNL (n = 63), splice site variants (n = 5), fusions (n = 2), and rearrangements (n = 1). Of the 126 SNV or indels, 50 (39.7%) were identified in both ctDNA and tissue, 40 (31.7%) were detected in blood only, 36 (28.6%) identified only in tissue (p < 0.0001). Amongst the 63 CNL, only 3 (4.8%) were identified in both ctDNA and tissue; 41(65.1%) were only identified in ctDNA, and 19 (30.2%) in tissue only (p < 0.0001). In the 19 tissue-only CNL tests, 12/19 noted one or more additional pathogenic SNV/Indel in BRCA1/2. In the 41 ctDNA-only CNL tests, 1/41 noted one or more additional pathogenic SNV/Indel in BRCA 1/2 . Germline testing was available in 41/63 pts with copy number loss. 3/41 deletions were identified in germline (2 in ctDNA, 1 in tissue). Conclusions: We observed a low degree of concordance in CNL between tissue and ctDNA for BRCA1/2 . CNL detection in ctDNA that could not be confirmed in germline or with a second alteration warrants further attention. In particular, clinicians should be cautioned when interpreting ctDNA reports noting BRCA1/2 CNL without clarity if this represents biallelic loss or a synchronous loss of function.

1089 Background: T-DXd has become an important treatment option in mBC and other malignancies. Interstitial lung disease/pneumonitis (ILD) occurred in 10-14% of pts in the DESTINY-Breast trials (0-2% G5 ILD), and with potential lower incidence/severity in earlier line settings (Krop et al, ASCO 2023). We previously reported the Mayo Clinic Rochester, MN experience with T-DXd related ILD in mBC (Hoppenworth et al, ASCO 2024). Here, we expand the data to include patients treated at all locations of the Mayo Clinic Enterprise. Methods: We retrospectively identified pts with mBC who received ≥1 dose of T-DXd across the Mayo Clinic enterprise (Rochester, MN; Mayo Clinic Health System locations in MN/WI; Scottsdale, AZ; and Jacksonville, FL) between July 2022-December 2023. Demographic, mBC characteristics, and pulmonary clinical variables were abstracted from the clinical records. Data were summarized using descriptive statistics. Diagnosis of ILD was determined by treating clinicians, and severity was approximated to CTCAE V5 based on clinical documentation. Results: 252 pts with mBC received T-DXd during the study period. The majority were Caucasian (86%) and female (99%) with a median age of 63. 91 pts (36%) were current/formers smokers and 97 (39%) had prior pulmonary comorbidities. The majority had HER2 low (155, 62%) and HR positive (164, 65%) mBC. 35 (14%) developed any grade ILD [G1: 6 (17%), G2: 13 (37%), G3: 3 (8.6%), G4: 3 (8.6%), G5: 10 (29%)], with 15 (43%) presenting with ≥G3. 29 (83%) presented with at least 1 symptom (cough or SOB). Among those with previous pulmonary toxicity, 4 (33%) had previous pneumonitis in the ILD cohort. The median prior lines of all therapies (including endocrine therapy) were 5, with a median of 3 prior lines of chemotherapy in both the ILD (range 1-13) and non-ILD cohorts (range 1-13). Median onset to any grade ILD was 7 cycles. 20 pts (57%) received steroids for ILD. 14 (40%) had a bronchoscopy, all had a CT chest, 16 (46%) were hospitalized, 7 (20%) were intubated and 1 (3%) had a lung biopsy. Pts with G5 ILD had a median of 3 lines of chemo and a median of 8 cycles prior to onset of ILD, compared to 3 lines of chemo and a median of 7 cycles for those with G1-4 ILD. G5 pts were all Caucasian females, 5 were former smokers, 5 were non-smokers, 1 had a history of pneumonitis. T-DXd was rechallenged in 4 pts (G1-2 ILD) without ILD recurrence. Conclusions: In this retrospective case series,14% of pts treated with T-DXd experienced any grade ILD (4% G5) which is in alignment with the rate observed in the pivotal DESTINY-Breast trials, though with higher rates of G5 toxicity. Among those with ILD, increased lines of therapy were not associated with increased risk. Further research is needed to correlate risk.

TPS1125 Background: Despite the many available treatments for patients (pts) with HR+, HER2– recurrent/metastatic breast cancer (MBC), optimal treatment after progression on CDK4/6 inhibitors (CDK4/6i) is unclear. One possible CDK4/6i resistance mechanism is increased expression of Aurora kinase A (AURKA), a key mitosis regulator associated with poor prognosis. Further implicated in CDK 4/6i resistance, high c-Myc or RB1 loss of function (LOF) are associated with transcriptional co-regulation or synthetic lethality, respectively, with AURKA. Alisertib is a highly selective, reversible, ATP-competitive, orally administered, small-molecule AURKA inhibitor with antiproliferative activity in HR+ BC-derived cell lines and BC xenograft models. Models with elevated AURKA or c-Myc expression, or RB1 LOF show greater alisertib sensitivity. Alisertib had activity in phase 1 and 2 trials, including objective response rates (ORRs) of 19.6–20% and median progression-free survival (PFS) of 5.4–5.6 months alone or with fulvestrant in pts with HR+/HER2–, endocrine-resistant MBC. The most common treatment-related grade ≥3 adverse events (AEs) were neutropenia, anemia, and leukopenia. Methods: ALISCA-Breast1 (NCT06369285) is a randomized phase 2 study. Primary objective: to determine the optimal alisertib dose administered with endocrine therapy (ET) based on AEs and serious AEs per CTCAE v5.0 and efficacy (ORR, duration of response, disease-control rate, PFS, overall survival). Secondary objectives: to identify biomarkers of efficacy and alisertib pharmacokinetics (PK). Key inclusion criteria: ≥18 years; ECOG performance status 0 or 1; confirmed HR+, HER2–, recurrent/metastatic breast adenocarcinoma not amenable to curative therapy; available tumor tissue for biomarker analyses; progression on or after ≥2 prior ET lines in recurrent/metastatic setting; prior CDK4/6i with ET in recurrent/metastatic setting. Key exclusion criteria: prior chemotherapy in recurrent/metastatic setting; prior AURKA-specific or pan-Aurora-targeted agents; unstable brain metastases. Eligible pts will be randomized 1:1:1 to alisertib 30 mg, 40 mg, or 50 mg orally twice daily on days 1−3, 8–10, and 15–17 every 28 days, plus physician’s choice of anastrozole, letrozole, exemestane, fulvestrant, or tamoxifen not previously used in recurrent/metastatic setting or progressed upon in adjuvant setting; ≤50 pts will be enrolled per arm in the USA and Europe. All pts will undergo sparse PK sampling. Tumor tissue will be centrally assessed for biomarkers, including RB1, MYC, TP53, ESR1, PI3K/AKT pathway, HER2 and AURKA genomic alterations/expression levels. The study will determine the optimal alisertib dose to combine with ET and may identify biomarker(s) defining pts with the greatest benefit from alisertib-based therapy. Clinical trial information: NCT06369285 .