Citations

Abstract Introduction Revascularization to prevent limb loss is not feasible or represents a very high risk in a significant proportion of patients with chronic limb-threatening ischaemia (CLTI). No standard definition currently exists to define this population of patients. The aim of this study was to develop a consensus-based, multidomain definition to improve clinical assessment and reporting of studies in people with ‘no option’ (NO) or ‘poor option’ (PO) CLTI. Methods A modified Delphi process was conducted with 164 specialists from 30 countries. Two iterative survey rounds were used to reach consensus, defined as ≥70% agreement with a score of ≥7 on a nine-point scale. Results Some 164 international vascular specialists participated in the study, averaging 19 years of experience. A multidomain framework including arterial disease anatomy, biology, risk, function, and context (ABRFC) achieved 83% consensus. A ‘desert foot’ was defined as the absence of distal arterial revascularization targets on advanced non-invasive imaging, invasive digital subtraction angiography, and at least one failed endovascular revascularization attempt (81.6% agreement). Inadequate autogenous bypass conduit was defined as the lack of usable autologous vein across all four limbs (85% agreement). Patients were classified as NO for revascularization if they present with ‘desert foot’, prohibitive medical risk, a non-functional limb, or in those patients who refused arterial revascularization. PO revascularization patients combined factors such as severe infection, lack of autologous vein, or treatment non-compliance (72.1% agreement). Conclusion This consensus study established a structured, expert-validated definition of no option or poor option for revascularisation of patients with CLTI. The multidomain ABRFC framework provides a foundation for standardized clinical assessment, trial design, and future guideline development.

Abstract Large Language Models (LLM) are being widely adopted into the medical field for their impressive ability to analyze and summarize large amounts of text data. These models enable clinicians and researchers to extract meaningful insights from complex datasets and may assist with decision making. Here we present our workflows and application of LLM for the interpretation and summarization of clinical data related to CAR-T cell therapy. Using an LLM (Gemini 2.5 pro) in the Google Cloud Computing (GCP) environment, two applications were developed to analyze CAR-T cell therapy clinical data: 1) extracting and summarizing CRS and ICANS event-related data to streamline the compliance team workflow, and 2) identifying features available at time of CAR-T infusion able to classify patients into high- or low-monitoring needs 14 days post CAR-T. Patient data (vitals, labs, hematology notes, and EKGs) were extracted from the electronic medical record (EMR) using Google BigQuery into SQL tables in GCP. For each application, relevant data fields were retrieved, formatted into JSON objects, and embedded in the LLM prompt for context-aware processing. Both applications have undergone iterative prompt engineering after analyzing the LLM output against ground truth data in the EMR. For the application extracting and summarizing CRS and ICANS events, the LLM was optimized on Mayo Clinic Rochester data. When compared to the IEC compliance database, the LLM achieved 100% accuracy and F1 score for CRS events, and 96% accuracy and 82% F1 score for ICANS events. The match rate for CRS and ICANS grades were 83% and 89% respectively. We applied the same LLM to Mayo Clinic Arizona (MCA) and Mayo Clinic Florida (MCF) cases, who document clinical notes and toxicity flowsheet differently, and achieved an accuracy (MCA: 93%, MCF:93%) and F1 score (MCA: 96%, MCF: 96%) for CRS and accuracy (MCA: 81%, MCF:82%) and F1 score (MCA: 76%, MCF: 75%) for ICANS. LLM was able to capture events missed by manual reviews. For most of the discrepancies where compliance team final adjudication is needed, LLM will be updated to flag discrepancies for review by the compliance team. For the application related to the monitoring needs 14 days post CAR-T, the LLM identified 5 categories predictive of high or low monitoring needs post CAR-T infusion (disease status, inflammatory and tumor burden markers, hematologic status, renal function and performance status). Our model achieved a sensitivity of 85.7%, specificity of 23.8%, and F1 score of 65.5% for our first cohort, compared with data extracted by the LLM from the EMR. For our second cohort, with demographics statistically similar to cohort 1 and using the same 5 categories, the LLM achieved a sensitivity of 83.3%, a specificity of 28.6%, and F1 score of 65.4%. Our workflow and applications of LLM’s provide examples and guidance to others interested in applying LLM’s for clinical and research applications. Citation Format: Emmanuel Contreras Guzman, Matthew Jankowski, Andre De Menezes Silva Corraes, Malvika Gupta, Monica L. Shaw, Madiha Iqbal, Talal Hilal, Saurabh Chhabra, Ricardo Daniel Parrondo, Jody K. Mclean, Kim R. Riester, Kayla Joseph, Melinda Tan, Holly Ross, Cleyonia Barnett, Sylvia Carter, Semy Girmay, Rachel Wolan, Milana Ramsey, Christian Downhour, Kristy Morgan, Shae Sibley, Erica Rushing, Lucy Holmes, Allison Burgstahler, Stephen M. Ansell, Hassan Alkhateeb, Matthew Hathcock, Ramona Bruno, Allison C. Rosenthal, Hemant Murthy, Patrick B. Johnston, Jonas Paludo, Yi Lin. Applications of large language models to CAR-T cell therapy clinical data using Google cloud computing [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 2740.

Background: NCCN publishes evidence-based guidelines across the cancer care continuum that are commonly used as the standard for clinical management and policy in cancer care. Our study aimed to assess the content of survivorship recommendations within disease-based NCCN Guidelines. Methods: In January 2024, we downloaded 64 disease-based guidelines from the NCCN website; 10 were excluded. The remaining 54 guidelines were reviewed for survivorship-focused content. Content of the guidelines was systematically categorized across domains of the Quality of Cancer Survivorship Care Framework, and the level of detail was rated as not addressed, briefly addressed, mostly addressed, or fully addressed. Guidelines were re-reviewed for updates in April 2025. Results: Of 54 guidelines reviewed in 2025, 16 (30%) included a dedicated survivorship section with focused content, although sections, titles, and formats varied. Other guidelines included survivorship recommendations in algorithms and/or discussion sections. A total of 18 guidelines (33%) had neither a dedicated section nor reference to the NCCN Survivorship Guidelines. Guidelines with a dedicated section, as well as those referencing the NCCN Survivorship Guidelines (65%), generally provided more detailed survivorship content. Across all guidelines, the surveillance for recurrences/new cancers domain was most commonly included (96%) and typically the most detailed. Information on physical (81%) and psychosocial (72%) effects and health promotion (65%) was often included, but the level of detail varied. Chronic disease management (31%) was seldomly included. Information on care coordination/communication and patient education was present in 50% of the guidelines. Compared with the guidelines reviewed in 2024, the 2025 updates had limited expansion of survivorship content. Conclusions: Cancer survivorship content is inconsistently presented across disease-specific NCCN Guidelines. As these guidelines evolve, there is an opportunity to tailor, expand, and standardize the recommendations, making them easier to find by clearly labeling and integrating them within each guideline to improve accessibility and better support clinicians in delivering patient-centered care.

Background/Objectives: Surveillance for anal squamous cell carcinoma (ASCC) recurrence relies on clinical examination and imaging. Post-treatment edema, fibrosis, and inflammation can result in clinically indeterminate findings (CIFs) that delay diagnosis and increase patient and system burden. Circulating tumor tissue-modified viral (TTMV)-HPV DNA offers a biologically specific, noninvasive biomarker that may clarify equivocal assessments. Methods: In this multi-center retrospective study, 233 patients with HPV-associated ASCC were evaluated, including 185 with ≥1 post-treatment TTMV-HPV DNA test. CIFs were defined as exams or imaging results not definitively positive or negative for disease, and were paired with subsequent TTMV-HPV DNA tests. Concordance was defined by prespecified follow-up windows comparing TTMV-HPV DNA results with subsequent clinical outcomes. Results: Ninety patients (39%) experienced 214 CIFs, arising from exams (46%, 98) or imaging (54%, 116). Indeterminate rates by assessment were 7% for exams, 17% for imaging, and 1.3% for TTMV-HPV DNA testing. Overall, 52 CIF/TTMV-HPV DNA pairs were eligible for analysis, and TTMV-HPV DNA resolved disease status accurately for 48/52 (92%, 95% CI: 81.5–97.9). Negative tests predicted cancer-free status for 37/41 CIFs (90%), while 100% of positive tests (11/11) were concordant with clinically confirmed recurrence. In 73% of positive cases (8/11), TTMV-HPV DNA was the first indication of recurrence (median lead-time 29 days; IQR 25–147). Conclusions: TTMV-HPV DNA testing reliably clarifies clinically indeterminate findings during ASCC surveillance, demonstrating high accuracy (92%) and earlier detection of recurrence. These data support integration into post-treatment management to reduce diagnostic uncertainty and guide timely care.

Abstract Introduction: CAR-T therapy has transformed cancer therapy. with its first Food and Drug Administration (FDA) approved product in August 2017. Given the expanding indications and growing experience, particularly with management of immediate toxicities requiring specialized expertise such as Cytokine Release Syndrome (CRS) and Immune Effector Cell-Associated Neurotoxicity syndrome (ICANS), FDA recently removed the Risk Evaluation and Mitigation Strategies (REMS) for CD19 and BCMA targeting CAR-T on June 26th2025. In particular, given that CRS and ICANS typically occur in the first 2 weeks post CAR-T infusion, the minimum required stay near CAR-T treatment center is reduced from one month to 2 weeks. While this could reduce treatment burden for patients (pts) who need to travel away from home to receive CAR-T, there is a need to update the transition of care from CAR-T center to pts' local oncology practice. Pts carry in their rate of recovery and have varying supportive care needs in the second half of the month post CAR-T infusion. To assist with care transition and planning, we examine the use of AI multimodal large language model (LLM) to predict patients' supportive care needs 2 weeks after CAR-T infusion based on the clinical data at the time of CAR-T evaluation, prior to leukapheresis. This timepoint was selected to also maximize travel, lodging and caregiver planning for pts and family as well. Methodology: Pts who were treated with FDA-approved CAR-T at Mayo Clinic Rochester between December 2022 and June 2025 were examined. Based on experiences with referral practices in the Midwest region, we defined patients with high monitoring needs as those who between day 14-30 post CAR-T had either hospital admission due to recurrent CRS or ICANS or required transfusion of more than 1 blood product per week (red blood cell or platelets). Others were classified as low monitoring needs. Clinical notes, labs, vital signs and electrocardiogram at the time of CAR-T evaluation were abstracted and summarized by Gemini LLM for association with patients with high versus low monitoring needs post CAR-T. Model was developed and tested for predicted needs and concordance with actual outcome of these pts. Results: Among the 362 pts who received FDA approved CAR-T in the timeframe, 84 pts had high monitoring needs. An additional 84 pts with low monitoring needs were randomly selected from 278 pts. These were divided into a training cohort and test cohort of 84 pts each, with 42 pts with high and 42 pts with low monitoring needs. Demographics of the two cohorts displayed no statistical difference. LLM analysis of the clinical data at the time of CAR-T eval identified 5 categories associated with risk for high monitoring needs: 1) Disease status (clinical notes about bulky, progressive disease or CNS involvement); 2) inflammatory and tumor burden markers (CRP, LDH); 3) hematologic status (platelet, plt; neutrophil count ANC); 4) renal function; 5) performance status. Using common clinical lab parameter convention (platelets <100, ANC< 1, CrCl< 30ml/min), and prioritizing for not missing pts with high monitoring needs, LLM model was defined to predict patients for high monitoring needs if high risk feature was identified in category 1 or any category combinations; whereas patients with no high risk feature or only 1 category that is not disease status was predicted as low monitoring needs. In this model, the sensitivity was 85.7%, specificity 23.8%, F1 score 65.5%. Applying this model to test cohort 2, the sensitivity was 83.3%, specificity 28.6%, and F1 score 65.4%. Discussion: We demonstrate proof-of-concept that LLM can be used to analyze clinical data at the time of evaluation for CAR-T eligibility to predict for supportive care needs post treatment. Not surprisingly, features identified by LLM to be associated with high monitoring needs are those previously reported by us and others at the time of CAR-T evaluation and or pre-lymphodepletion to be associated with risk for cytopenia, infection, hospitalization and non-relapse mortality. Based on the summary output generated by LLM, additional opportunities for classification methods were identified to improve specificity and balanced accuracy of the LLM model. This is a promising tool for further development to assist clinicians and patients to plan their treatment journey.

Abstract Introduction: Reporting patient outcomes by CAR-T treatment centers is part of the accreditation requirement under the FACT (Foundation for Accreditation of Cell Therapy) Immune Effector Cell (IEC) Program standard. Currently, this is a time-consuming and manual process, making it increasingly difficult to sustain with the growing CAR-T applications and patient volume. The objective of this study is to evaluate how a Large Language Model (LLM) can be used to automate the abstraction and summarization of medical record for CAR-T toxicities. Methods: Clinical data from patients treated with CAR-T between January 2018 and June 2025, including hematology clinical notes, lab results, flowsheets, vital signs, and medication administration record, were used as the source of patient information. The American Society of Transplant and Cell Therapy (ASTCT) CAR-T toxicity grading guideline for cytokine release syndrome (CRS) and immune effector cell associated neurologic syndrome (ICANS) were used to define these toxicities. With the large context window of the LLM (Gemini 2.5 pro), we created a prompt by embedding both the patient data and the ASTCT guidelines for CRS and ICANS, along with an outline of specific information we aimed to abstract from the data. Additionally, the LLM was instructed to provide contextual justification for the data it extracted from patient information. The LLM-generated output included event onset date, resolution date, maximum grade, date of maximum grade, and medications given for management. The CRS and ICANS outcome reports generated by the LLM were then compared to the IEC compliance program data. Any discrepancies identified were reviewed manually. Results: Among patients (pt) treated with CAR-T in the specified timeframe, 47 were selected as training cohort. This cohort included pt with toxicities events, no events, and a mix of events of varying grades. For the test cohort, 66 pts who received CAR-T from March to June 2025 were included. Demographics for the training and test cohorts are reflective of evolving clinical practice (training, test cohorts: median age 69, 65; male 55%, 74%; lymphoma/leukemia 66%, 48%; multiple myeloma 34%, 52%; CD19 CAR-T 46%, 50%). Compared to data from the IEC compliance program, the LLM-generated summaries for CRS events demonstrated an accuracy of 90%, precision 95%, sensitivity 100%, specificity 80%, F1 score 97%, and Matthew's correlation coefficient 87%. For ICANS event, the LLM achieved an accuracy of 91%, precision 92%, sensitivity 92%, specificity 90%, F1 score 92%, Matthew's correlation coefficient 83%. Maximum grade, for both CRS and ICANS, were identified with >90% accuracy. However, dates for CRS and ICANS were less accurate, with the lowest accuracy noted in identifying the event resolution date, 45% for CRS and 67% for ICANS. Medical records were reviewed for all discrepancies between the LLM and the IEC Compliance Program data. The most common discrepancy was a mismatch in event resolution date, determined to be due to differing criteria used by the compliance team and the LLM prompt. Of note, a few discrepancies were attributed to missed information by the IEC Compliance Team, which was correctly identified and categorised by the LLM. An updated LLM prompt (LLMv2) was developed and applied to the test cohort. In version 2, the prompt was revised to include clearer instructions on how to summarize CRS and ICANS events, as well as new instructions on additional data elements to be summarized. The performance of LLMv2 on this cohort for CRS event identification was 100% across all categories (accuracy, precision, sensitivity, specificity, F1 score, and Matthew's correlation coefficient). For ICANS the LLMv2 achieved accuracy of 96%, precision 69%, sensitivity 100%, specificity 93%, F1 score 82%, Matthew's correlation coefficient 80%. Accuracy in identifying event resolution date improved significantly from 64% to 99%. Conclusions: Our study demonstrates that LLMs can significantly reduce the time required to abstract and summarize CAR-T toxicities, while maintaining high accuracy. One limitation of our study is that it is based on data from a single institution. However, plans are already underway to evaluate the use of LLMs in a multi-institutional setting.

Abstract Introduction: Suboptimal response to therapy, early disease relapse, and limited long-term survival remain critical challenges in a substantial number of patients with multiple myeloma (MM). While cross-sectional imaging studies are commonly obtained in clinical practice, only limited information is currently incorporated into risk stratification efforts and clinical decision making. Here, we investigate the use of novel image-based biomarkers to identify patients at high risk for adverse outcomes. Methods: We obtained the pretreatment 18F-FDG PET/CT scans of patients with newly diagnosed MM with available clinical and laboratory data seen at Mayo Clinic between 2006 and 2022. In this analysis, we included 637 patients with detectable metabolic tumor volume on their pretreatment scan. The native DICOM images were pre-processed and subjected to automated image segmentation using nnU-Net (nnU-Net v1.0, inference using a pre-trained hematologic malignancies model). Limitations of this automated segmentation approach include heterogeneity introduced by varying image quality, technical variability in PET reconstruction, and potential inclusion of non-neoplastic FDG-avid lesions in segmented regions. PyRadiomics was used to extract quantitative radiomics features for clinical prediction modeling. We evaluated the predictive power of tumor size-, shape-, and texture-related radiomics features for identifying high-risk disease (advanced ISS stage at diagnosis, the presence of high-risk FISH abnormalities, failure to achieve a stringent complete response [sCR] to first-line therapy by IWMG criteria, and early mortality). All radiomics features were quantile-normalized for downstream modeling. Forward and backward feature selection as well as testing for multicollinearity were used to remove redundant features. Results: Median age at diagnosis of the 637 myeloma patients was 64 years (range 22–90), and 387 patients (61%) were male. After a median follow-up of 4.4 years (95% CI 0.2–11.7), median overall survival (OS) was 7.3 years (95% CI 6.3–8.3). Increased total tumor volume (upper tertile vs lower tertiles), measured by the total tumor surface area, was associated with advanced ISS stage (III vs I+II; OR 1.73, 95% CI 1.24–2.42, p=0.001, n=637). Increased tumor density (dichotomized at the median), measured by the median gray level intensity (OR 1.93, 95% CI 1.94–3.12, p=0.007, n=303), and decreased tumor heterogeneity (lower tertile vs upper tertiles), measured by the variability of gray-level intensities (OR 1.88, 95% CI 1.49–3.12, p=0.012, n=303), were associated with the presence of high-risk cytogenetics. Both increased total tumor volume (4.9% increase per tertile, 95% CI 2.2–7.6, p<0.001, n=600) and tumor density (8.9% increase per tertile, 95% CI 4.5–13.3, p<0.001, n=600) were independently associated with more extensive bone marrow involvement at diagnosis. Increased tumor heterogeneity (upper tertiles vs lower tertile), as measured by rapid changes of gray level intensities, was associated with failure to achieve a stringent complete response to first-line therapy (OR 0.50, 95% CI 0.30–0.82, p=0.006, n=351). Increased tumor volume was associated with shorter OS (HR 1.35 per tertile, 95% CI 1.11–1.63, p=0.002, n=301), independent of age, sex, ISS stage, and the presence of high-risk cytogenetics. A simple additive score consisting of tertiles of total tumor volume, ISS stage, and plasma cell labeling index ≥2% identified patients at risk of mortality within 3 years of diagnosis (OR 2.00, 95% CI 1.40–2.85, p<0.001, n=126), with moderate discrimination (AUC=0.71). Sensitivity analysis demonstrated total tumor volume and texture as most predictive of overall survival in a random forest survival model (C-index 0.712, 95% CI 0.649–0.775) and tumor texture as most predictive of response to therapy in a random forest classification model (C-index 0.693, 95% CI 0.607–0.779). Conclusions: Automated image segmentation and radiomics feature extraction from 18F-FDG PET/CT scans produces biomarkers that capture disease stage, burden, and risk in newly diagnosed MM. Total tumor volume and heterogeneity are strongly associated with important disease characteristics and can be used to identify patients at high risk for therapeutic resistance, early mortality, and inferior long-term outcomes.

Abstract Despite a characteristic indolent course, a substantial subset of follicular lymphoma (FL) patients has an early relapse with a poor outcome. Thus far, efforts to identify factors that predict survival have been unsuccessful. However, we and others have demonstrated the prognostic relevance of CD4+ T cells in the tumor microenvironment (TME) of FL and developed a bio-clinical risk model (called BioFLIPI) that offers improved risk stratification (Mondello et al, BCJ 2021). However, the mechanisms defining different BioFLIPI scores remain to be fully understood. To identify the programs associated with the BioFLIPI scores, we first interrogated the RNA-seq of purified B cells from 67 newly diagnosed FL1-3A (BioFLIPI 1 n=21; BioFLIPI 2-3 n=36; BioFLIPI 4 n=10). We found 1,156 upregulated genes and downregulation of 930 genes in BioFLIPI 4 vs 1, including well-known immune molecules such as CD70, IL10RA, CD69, and CCR6 (FDR<0.05). Gene set enrichment analysis (GSEA) using the MSigDB confirmed a negative enrichment in multiple immune response and interferon gamma signatures and revealed striking positive enrichment for cell proliferation and antigen presentation pathways in BioFLIPI 4 compared to BioFLIPI 1 tumors. The same pathways were dysregulated in BioFLIPI 2-3 but a lower magnitude. To investigate the somatic mutations associated with different BioFLIPI scores, we performed WES of the same 67 FLs and further expanded this cohort for a total of 90 patients (BioFLIPI 1 n=26; BioFLIPI 2-3 n=51; BioFLIPI 4 n=13). We found enrichment for mutations in several regulators of the germinal center in BioFLIPI 4 and 2-3, such as MEF2B (p=0.029), FOXO1 (p=0.038) and IRF8 (p=0.035), suggesting the cooperation of multiple oncogenic events promoting lymphomagenesis. In contrast, BioFLIPI 1 tumors harbored a higher rate of mutations in TNFRSF14 gene, known to enhance anti-lymphoma immune response. To investigate whether BioFLIPI modulates immune signatures of the microenvironment, we performed TME deconvolution by applying CIBERSORTx to bulk RNA-seq of these 67 FLs. We found that FLs with BioFLIPI 4 and 2-3 were enriched for CD4+ Tcm exh (p=0.02), Tem exh (p=0.04), Tfhexh (p=0.07) and NK cells (p=0.01) compared to BioFLIPI 1. In line with this data, CyTOF performed on a subset of these patients (BioFLIPI 1 n=12; BioFLIPI 2-3 n=25; BioFLIPI 4 n=6) confirmed progressive increase of CD4+ Tcm exh (p=0.006), Tem exh (p=0.009) and Tfh exh (p=0.025) cells from BioFLIPI 1 to BioFLIPI 4. Single cell RNA/BCR-seq of 21 FLs (BioFLIPI 1 n=6; BioFLIPI 2-3 n=12; BioFLIPI 4 n=3) corroborated a higher abundance of Tem exh, cytotoxic (CTL) Tem exh, Tfhexh and NK cells in BioFLIPI 4 and 2-3. Conversely, CD8+ naïve T cells were prevalent in BioFLIPI 1 tumors. Differential gene expression in T cell clusters from BioFLIPI 4 vs BioFLIPI 1 FL revealed a marked upregulation of multiple immune genes involved in antigen presentation (e.g., HLA-DRB, HLA-DQA, HLA-DPA/B) and immune response (e.g., ETS1, TNFSF8, IL7R). GSEA showed a positive enrichment for antigen presentation signatures and negative enrichment for TNFα signaling and Oxphos metabolism. Similar findings were observed in BioFLIPI 2-3 FLs. Using CellChat analysis, we found a stronger interaction between malignant B cells and Tem exh and CTL Tem exh cells in BioFLIPI 4 and 2-3 vs BioFLIPI 1 tumors. This was linked to an increased strenght of MHCI-CD8 interaction and concordant decrease of MHCII-CD4. Notably, the suppressive BTLA-TNFRSF14 signaling axis was present in BioFLIPI 4 and 2-3 but not in BioFLIPI 1 FLs. This was accompanied by a decreased signaling through TNF/LTA-TNFRSF1B, CD80/CD86-CD28/CTLA4. Linking the BioFLIPI-specific immunogenicity to lymphomagenesis, we found that FL patients with BioFLIPI 4 had two-three folds higher risk of transformation to an aggressive lymphoma (12% vs 7%) or death (21% vs 3%) than those with BioFLIPI 1, suggesting that this immune dysfunction favors the expansion of a dominant tumor clone and promotes a more aggressive form of FL. Collectively, our findings demonstrate that BioFLIPI scores in FL reflect distinct patterns of tumor immunogenicity that shape the TME. Notably, high BioFLIPI scores are paradoxically associated with enhanced antigen presentation alongside a suppressed immune response. This suggests a sustained antigen-specific T cell response that may drive immune exhaustion, promote tumor progression, and ultimately lead to histologic transformation

Abstract Introduction: Although current clinical treatment approaches targeting Bruton Tyrosine Kinase (BTK) and BCL2, either as monotherapy or in combination are highly effective in chronic lymphocytic leukemia (CLL), CLL remains incurable. Identifying novel drugs that are potent and effective in the relapsed/refractory (RR) setting remains an unmet need. Methods: Utilizing the CellTiter-Glo 2.0 Cell Viability Assay, we have developed a preclinical drug screening platform which allows conducting drug sensitivity profiling of primary peripheral blood mononuclear cells (PBMCs) collected from CLL patients to a panel of drugs, in the presence and/or absence of bone marrow stromal cells (BMSCs). This unique system mimics the in vivo stromal microenvironment in CLL and enables testing of multiple drug responses in primary patient samples, particularly when leukemic cell numbers are low. In this study, we employed this high throughput drug screening platform to profile drug sensitivity in CLL B cells after disease progression on a BTK inhibitor (BTKi) to a panel of 12 drugs, including inhibitors of BCL2 (venetoclax and LP-118 [Newave]), AXL (TP-0903), histone deacetylase (panobinostat and belinostat), p53 (eprenetapopt and idasanutlin), proteasome (carfizomib) and Type III Receptor Tyrosine Kinase (crenolanib), next generation BTKi (LP-168 [Newave]), as well as a novel anti-cancer drug transcriptional chemical inducer of proximity (TCIP1) and the natural green tea extract (GTE) product Sunphenon 90D (Taiyo International). After 24-hour drug exposure, leukemic cell viability was measured, killing curves and IC50 levels generated and calculated by nonlinear curve regression in GraphPad Prism. Results: Using the Mayo Clinic CLL Database and the Mayo Clinic CLL Tissue Bank, we identified 47 patients with RR CLL, all of whom experienced disease progressionon a BTKi (35 ibrutinib +/- CD20 antibody, 10 acalabrutinib +/- CD20 antibody, 2 other). Median age at BTKi initiation was 64 years (range, 41-82), and 36 (77%) were male. IGHV status was unmutated in 44 (94%) patients, FISH at diagnosis showed del17p in 11 (27%), del11q in 6 (15%), +12 in 5 (12%), del13q in 12 (30%), and not detected in 6 (15%) patients. TP53 mutation was seen in 13 (32%) patients at the start of BTKi therapy. Median number of lines of CLL therapy prior to start of BTKi was 2 (range, 0–8); 13 patients received BTKi as their first-line therapy. Our drug screening results showed definite responses to all tested drugs based on dose range generated killing curves and IC50 levels for 30 RR CLL patient samples, though results varied. Among 12 drugs tested, LP-118 (0.1nM), venetoclax (2.6nM), carfizomib (2.2nM), TP-0903 (116.2nM), crenolanib (1769nM), and TCIP1 (1805nM) demonstrated the highest killing effects, while the remaining generated killing but at higher doses: belinostat (6800nM), eprenetapopt (4500nM), idasanutlin (4900nM), LP-168 (7500nM) and GTE (55.6uM). We also observed that RR CLL cohort exhibited significantly increased drug resistance to most of the tested drugs in the presence of BMSCs with corresponding increases in IC50s (with vs. without BMSCs, fold-change respectively): LP-118 3.92-fold, venetoclax 1.98-fold, carfilzomib 2.58-fold, TP-0903 1.65-fold, panobinostat 204.23-fold, TCIP1 1.91-fold, crenolanib 1.31-fold, idasanutlin 1.69-fold, belinostat 6.14-fold, LP-168 1.29-fold, eprenetapopt 3.44-fold and GTE 1.08-fold (11 out of 12 with p-values <0.05 except for GTE which was not significant, Mann-Whitney U test). We found that even for three drugs with the strongest killing effect based on IC50 levels (LP-118, venetoclax, carfilzomib), their killing effects were significantly reduced in the presence of BMSC (p=0.0002, 0.0002, and <0.0001, respectively). Conclusions: Our results highlight the spectrum of currently available drugs that show promise for therapeutic use in patients with RR CLL who experience disease progression on BTKi. The killing impact was still seen, albeit diminished, even in the presence of BMSC. Our ongoing work will be to associate the drug profiles with each patient's clinical history, as well as to the comprehensive genetic and epigenetic features of the CLL B cell clone.

Abstract Background Chimeric-antigen-receptor (CAR) T-cell therapy has transformed outcomes for relapsed or refractory hematologic malignancies, yet early identification of patients at highest risk for death remains elusive. A prognostic model that leverages only the information routinely available at the time of CAR-T evaluationcould guide pre-infusion counseling, intensity of follow-up, and resource allocation. Methods We analyzed a prospectively maintained cohort of CAR-T recipients treated at Mayo Clinic to develop and test our model. For each patient, data (vital signs, lab results, cardiac assessments [ECG and echocardiography], and PET/CT images) from initial CAR-T evaluation (up to 60 days prior to CAR-T infusion) was considered. Vital signs and labs were left un-imputed, while ECG, echocardiographic parameters, and PET/CT features were forward-filled from the preceding 60 days. Each patient-day was labeled as “outcome present” or “no outcome,” enabling supervised training of gradient-boosting models to predict overall survival (OS) at 6 months post CAR-T infusion. Model performance was evaluated using the area under the ROC curve (AUC) with 10,000-fold bootstrapping with data shuffling between each iteration to derive confidence intervals for stability. To enhance interpretability, we also developed a simplified model using the top 19 features (determined by Shapley value-based importance), aiming to preserve predictive accuracy with a smaller feature set. Results A total of 570 CAR-T cell treated patients were included in this study (476 patients in the training cohort and 94 patients in the validation cohort). The median age was 64 years and 61% males. The primary diagnoses were B-cell lymphoma (324 patients) and multiple myeloma (246 patients). A total of 4,851 individual vital-sign readings, 11,781 laboratory measurements were included. PET/CT images were available in 318 patients. The ML model demonstrated high discriminative ability for predicting OS at 6 months post CAR-T infusion. Vital signs alone produced a mean AUC of 0.63; radiomics features alone produced a mean AUC of 0.71, while laboratory tests alone produced a mean AUC of 0.84. The features most contributory to each single-modality model were then combined into a simplified multimodal model with a total of 19 features, which produced a mean AUC of 0.87, with a 95% CI of 0.73 - 0.97. The 19 features included in the simplified model were: LDH, ferritin, uric acid, eosinophils, fibrinogen, D-dimer, heart rate, mean arterial blood pressure, QTc, QT interval, and the radiomics features of sphericity, first-order Kurtosis, first-order mean, first-order energy, first-order total energy, shape maximum2D diameter (sagittal plane), SUV CoV, SUVp90, shape flatness. This multimodal predictive model was then applied to the validation cohort (uninvolved with model training or testing), which produced an AUC of 0.93, with a 95% CI of 0.84 - 0.98. Conclusions Our ML-driven approach successfully predicts overall survival 6 months post CAR-T infusion, highlighting those individuals at most risk of poor outcomes at the time of CAR-T evaluation. The strong performance of the multimodal version of the model suggests that each data domain contributes complementary resolving power, and by including novel data types, such as PET CT radiomics features, the most accurate predictions could be realized. By providing accurate, near-real-time risk stratification for poor outcomes within 6 months of CAR-T infusion, the model could facilitate proactive patient management. Prospective studies of the integration of this ML model into CAR-T treatment workflows will be crucial to confirm its clinical benefits and to facilitate its adoption in practice.