Citations

e13622 Background: Chimeric antigen receptor T-cell (CAR-T) therapy has revolutionized treatment of hematologic malignancies; however, severe toxicities like cytokine release syndrome (CRS) remain a limitation to broader utilization. Using a large dataset of patients treated with CAR-T, we developed a machine learning (ML) model leveraging multi-model patient characteristics to predict the risk of CRS onset with clinically meaningful lead times. Methods: A prospectively maintained dataset of CAR-T patients treated at Mayo Clinic was used. Baseline disease/patients characteristics, labs, ECG, echocardiogram, and vital signs (including data from remote patient monitoring program) were collected. A 24-hour rolling window was used to generate daily averages, maximum, minimum, and deltas for each parameter. ECG and echocardiogram data were forward-imputed; vital signs and labs were not imputed. Each day-post-infusion served as a potential event (CRS onset vs. no CRS). A gradient boosting classifier was trained and tested on a subset of patients (n = 351) using 1,000 bootstrap iterations, evaluating 24-, 48-, and 72-hour lead times. Shapley-based feature importance guided simplification to an 11-feature model, externally validated on an independent cohort (n = 51). Models’ performance assessed using the area under the receiver operating characteristic curve (AUC). Results: A total of 402 patients treated with CAR-T were examined. Median age was 64 years and 36% were female. Primary diagnosis was B-cell lymphoma (n = 240) or multiple myeloma (n = 162). A total of 226,332 vital sign measurements and 372,871 lab values, as well as ECG and echocardiogram data, were collected for 30 days post-infusion. Overall, 79.8% of patients experienced CRS within 30 days. The full ML model demonstrated AUCs of 0.90 (95% CI 0.86–0.93), 0.83 (95% CI 0.77–0.88), and 0.82 (95% CI 0.77–0.87) for 24-, 48-, and 72-hour predictions of CRS, respectively. Including “day of CRS onset post CAR-T” as a feature improved the 72-hour AUC to 0.87 (95% CI 0.83–0.90). A model restricted to vital signs alone showed AUCs of 0.88, 0.75, and 0.71 for 24-, 48-, and 72-hour horizons. An 11-feature model—focusing on temperature, blood pressure, fibrinogen, CRP, serum sodium level, QRS interval, and lymphocyte counts—maintained high accuracy at 24 hours (AUC 0.90, 95% CI 0.86–0.93) and was validated externally using an independent dataset with an AUC of 0.92. Conclusions: Our ML model provides a reliable approach for predicting if/when CRS will occur, with up to three days of lead time before clinical manifestation, offering an opportunity for proactive management. The robust performance of a parsimonious 11-feature model supports practical adoption across clinical settings and real-time risk stratification to enhance patient safety. Prospective validation and integration into clinical workflows will be critical to translating these findings into practice.

Introduction The tumor ecosystem in multiple myeloma (MM) involves complex interactions among various cell types, including clonal plasma cells (PCs) and immune cells. Previous research has indicated that the bone marrow (BM) microenvironment's metabolite and lipid profiles differ between MM patients and those with precursor conditions. This study aims to explore if differences in cell composition, metabolic phenotype of clonal PCs, and the spatial organization of various cell types are linked to the early versus late progression of high-risk smoldering MM (SMM) to MM. Methods We identified high-risk SMM patients using the IMWG 20-2-20 criteria, focusing on early progressors (EP), who progressed to MM within one year, and later progressors (LP), who progressed after more than four years. Using a high-dimensional single-cell spatial imaging platform, CODEX (CO-Detection by indEXing), we identified clonal PCs and immune cell types as well as their metabolic phenotypes at the single-cell level, in paired FFPE BM samples at SMM diagnosis and at the time of progression to MM. Our validated panel included markers such as CD3e, CD4, CD8, CD14, CD20, CD31, CD38, CD45, CD66a, CD68, CD138, HLA-DR, ASCT2, pNRF2, GLUT1, LDHA, ATPA5, CPT1A, and Citrate synthase. We employed single-cell segmentation, artifact cleanup, signal thresholding, and spatial analysis. Repeated measure models accommodated multiple regions of interest (ROIs) per patient and accounted for potential intrapatient correlation, while Poisson models estimated incidence rate ratios (RR) of cell types. Spatial statistical models evaluated cell type segregation and integration at the time of SMM diagnosis. Results Single cell events were acquired from 6 unique SMM patients who had paired FFPE BM samples from the time of their SMM diagnosis and at the time of their progression to MM. There were 3 EP SMM patients (Time to Progression (TTP):8, 8, 10 mos) and 3 LP SMM patients (TTP: 51, 58, 117 mos). The median number of single cell events identified per patient slide sample was 104,390 (Range: 24,357 - 314,877). We identified 8 main cell types: PCs, CD4+ T-cells, CD8+ T-cells, B-cells, granulocytes, Monocyte/Macrophages and two groups of other immune cells. The PCs and the remainder of the non-PCs were further classified based on the expression of the following metabolic markers: ASCT2 (Glutamine importer), CPT1A (Fatty acid metabolism), GLUT1 (Glucose importer), LDHA (Glycolysis), Citrate synthase and ATPA5 (Oxidative Phosphorylation). There was a higher RR of granulocytes (RR 2.1, CI 1.6-2.8, p<0.001) in EP compared to LP samples at the time of SMM diagnosis, but a lower RR of CD4 T cells (RR 0.40, CI 0.3-0.6, p< 0.001). Focusing on metabolic phenotypes of the PCs, we observed higher incidence RR of most metabolic markers: ASCT2 (RR=1.77; p=0.032), ATPA5 (RR=1.25; p<0.001), CPT1a (RR=2.42; p=0.015), and LDHA (RR 2.13; p<0.001) in EP compared to LP samples at the time of SMM diagnosis. However, GLUT1 had a lower incidence RR in EP patients (RR=0.79; p<0.001). The same modeling for non-PCs at the time of SMM diagnosis yielded higher expression of LDHA (RR=1.98; p<0.001) and ASCT2 (RR=3.3; p=0.002). Using the x and y coordinates and the corresponding phenotype classifications, we performed spatial statistical modeling based on spatial point processes to generate aggregated measures of how different types of cells of interest interacted. CD4 T cells were more isolated in LPs compared to EPs (p =0.046). Segregation indices for PCs and CD4 T cells indicated that they were more integrated/collocated in EPs. Granulocytes were more isolated in EPs although the difference was not as pronounced (p= 0.07). PCs were more integrated with granulocytes (p=0.06) and B cells (p=0.07) in LP patients. Further analyses of paired samples at the time of progression to MM will be reported at the time of the presentation. Conclusion This study is the first to provide whole-slide, single-cell, spatial proteomic characterization of clonal PCs and immune cells in the FFPE BMs of high-risk SMM patients with varying progression times to MM. Distinct metabolic pathway markers in clonal PCs and their spatial relationships with immune cell subsets are closely associated with the risk of progression to MM. These findings illuminate the complex interactions between the metabolic states of clonal PCs and their spatial orientation relative to immune cells in the pathogenesis of MM.

Introduction: In myeloma, accurate risk stratification remains a challenge due to substantial biological heterogeneity and highly variable survival outcomes. Cross-sectional imaging is commonly obtained at the time of diagnosis, but imaging findings are not currently incorporated into risk stratification efforts in a standardized manner, despite their prognostic significance. Here, we investigate the use of novel image-based prognostic biomarkers obtained by automated image segmentation and radiomics feature extraction using machine learning methods. Methods: We obtained the pre-treatment 18F-FDG PET/CT scans of 443 patients with newly diagnosed myeloma and complete demographic and cytogenetic data (seen at Mayo Clinic between 2005 and 2019). The native DICOM images were pre-processed and subjected to automated image segmentation using 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 differences related to PET reconstruction, and potential inclusion of non-neoplastic FDG-avid lesions in segmented regions. The quality of the automated image segmentation was evaluated by comparing the radiomics features obtained from ground-truth segmentation (manual lesion segmentation) and model segmentation in a separate cohort of patients with hematologic malignancies (n=72). We selected 42 radiomics features that moderately (r≥0.30, p<0.005, n=23) or strongly (r≥0.50, p<0.001, n=19) correlated between ground-truth (manual) and model (automated) segmentation for further evaluation in myeloma patients. PyRadiomics was used to extract discrete radiomics features for clinical prediction modeling. We evaluated the prognostic significance of tumor size-, shape-, and texture-related radiomics features and compared their predictive power to established prognostic factors (International Staging System [ISS], Revised ISS [R-ISS] stage and high-risk FISH cytogenetics). The outcome of interest was overall survival and the predictive power of competing proportional hazards regression models was assessed using Harrell's C-statistic. For modeling purposes, patients without measurable tumor volume were categorized as having undetectable radiomics features (0 for all features). All radiomics features were median dichotomized for downstream modeling. Forward feature selection and testing for multicollinearity were used to remove redundant features. Select radiomics features were divided into quintiles to generate an additive radiomics risk score and associated risk strata. Results: Median age at diagnosis of the 443 myeloma patients was 63 years (32-91) and 270 patients (62%) were men. After a median follow-up of 2.4 years (95% CI 0.1-7.4), median overall survival was 6.5 years (95% CI 5.5-NR). Most patients had detectable metabolic tumor volume (n=309, 70%) on their pre-treatment 18F-FDG PET/CT scan. Several of the 42 radiomics features were intercorrelated and two features were selected for further investigation based on their independent prognostic significance (forward feature selection). Higher maximum axial tumor diameter (HR 1.90, 95% CI 1.31-2.76, p=0.001) and a lower concentration of low gray-level values in the tumor (HR 1.73, 95% CI 1.20-2.49, p=0.004) were independently associated with overall survival in newly diagnosed myeloma. These associations were independent of age at diagnosis, sex, and R-ISS stage. We devised a simple additive risk score representing the sum of quintiles of the two radiomics features and divided the patients into three risk categories akin to the R-ISS. The predictive power of this radiomics risk score (Harrell's C=0.60) was comparable to the ISS (C=0.59) and the R-ISS (C=0.57). Conclusions: Automated image segmentation and radiomics feature extraction from 18F-FDG PET/CT scans is feasible. This approach yields image-based biomarkers that correlate with results obtained by manual imaging segmentation. Several radiomics features such as tumor size and heterogeneity have independent prognostic significance in newly diagnosed myeloma. These novel biomarkers rival the predictive power of the currently established risk stratification methods and may be used to improve risk stratification in myeloma.

CD19-targeted chimeric antigen receptor T (CART19) cell therapy has shown outstanding clinical success. However, patients can develop CART-induced toxicities, including cytokine release syndrome (CRS) and neurotoxicity. Studies have found that activation of myeloid cells by granulocyte monocyte-colony stimulating factor (GM-CSF) can contribute to toxicity development. GM-CSF depletion leads to reduced myeloid activation, prevention of CART-induced toxicities, and improved CART efficacy. CART cells upregulate cytokine receptors upon activation, and our results indicate that CART19 cells significantly upregulate GMCSFR upon antigen-specific stimulation (<10% vs >30%, p<0.01). This led us to hypothesize that GMCSFR signaling contributes to CART cell activity. To understand the role of GM-CSFR upregulation on CART cell functions, we compared the impacts of neutralizing GM-CSF or blocking GM-CSF receptor alpha (GM-CSFRα) on CART19. First, 4-1BB-costimulated CART19 cells generated from healthy donors were stimulated with CD3/CD28 beads at a 1:3 ratio for 6 days. CART cells were maintained at 1 x 106/mL throughout the culture and supplemented with IgG isotype control, GM-CSF neutralizing antibody, or GM-CSFRα blockade at 10 μg/mL, 20 μg/mL, or 100 μg/mL. On day 6, cells were debeaded and rested for 2 days. Then, CART cells were cocultured with NALM6, a CD19+ acute lymphoblastic leukemia cell line, at a ratio of 1:1 for 3 days. The cocultures were supplemented with the same doses of antibodies listed above. Antigen-specific proliferation of CART cells was measured by flow cytometry. Our data suggested that CART19 proliferated is not impacted by GM-CSF neutralization but is inhibited by GM-CSFRα blockade (IgG isotype vs 10 μg/mL GM-CSFRα blockade, p<0.0001; IgG isotype vs 20 μg/mL GM-CSFRα blockade, p<0.0001; IgG isotype vs 100 μg/mL GM-CSFRα blockade, p=0.009). CART cells were assessed in a cytotoxicity assay with NALM6 luciferase+ cells as well, which did not show significant impacts from GM-CSF neutralization or GM-CSFRα blockade. To evaluate the impacts of GM-CSF neutralization and GM-CSFRα blockade in a mouse model, we engrafted NSG mice with 1 million NALM6 luciferase+ cells intravenously. Mice were then treated with 1.4 million CART19 plus 10 mg/kg IgG isotype control, GM-CSF neutralizing antibody, or GM-CSFRα blockade intraperitoneally. GM-CSFRα blockade drastically suppressed antitumor activities of CART (CART19+GM-CSFRα blockade vs CART19+IgG isotype control, p<0.0001; CART19+GM-CSFRα blockade vs CART19+GM-CSF neutralizing antibody, p<0.0001; CART19+ GM-CSFRα blockade vs untransduced T cell, n.s.). Serum cytokines were analyzed 2 days after CART treatment, showing that mice with GM-CSFRα blockade had significantly lower levels of human IFNγ (p=0.0189) and IL-2 (p=0.0121) compared to IgG isotype control group, while GM-CSF neutralization did not show significant impacts. Mice treated with CART plus IgG isotype control or GM-CSF neutralizing antibody showed prolonged survival compared to mice treated with GM-CSFRα blockade or untransduced T cells (p=0.0285). To unravel the mechanisms behind functional differences between GM-CSFRα blockade and GM-CSF neutralization, CART cells (n = 3 biological replicates) were cocultured with NALM6 at a 1:1 ratio supplemented with 10 μg/mL GM-CSF neutralizing antibody, GM-CSFRα blockade, or IgG isotype control overnight, followed by T cell isolation, bulk RNA isolation, and RNA sequencing (RNAseq) analysis. Our RNAseq data indicated significant upregulation (Log2FC>0.5, padj. <0.05) of T cell exhaustion- and dysfunction-associated genes (RGS16, PDCD1, CTLA4, NR4A3, CD101, LAG3) as well as negative regulators of T cell functions (G0S2, PIK3IP1, LGALS3) in the GM-CSFRα blockade group compared to GM-CSF neutralizing antibody or IgG isotype control groups. T cell activation-associated pathways were enriched in the GM-CSFRα blockade group. Overall, our data show that GM-CSFRα blockade impacts CART functions differently from GM-CSF neutralization. Specifically, GM-CSFRα blockade inhibits CART proliferation in vitro and antitumor activity in vivo. Interestingly, GM-CSFRα blockade leads to enrichment of T cell exhaustion- and dysfunction-associated genes in CART19, which is worth further investigation. These findings may be applicable to other cytokine receptors upregulated on activated CART cells.