Citations

Abstract Real-time, proactive detection has become a necessity as health systems face converging pressures that legacy tools cannot solve: rising acuity, workforce strain, and persistent quality gaps that erode margins, capacity, and reputation. Clinical decision support has historically lagged because rudimentary rules-based systems drown clinicians in false alerts, eroding trust without reliably changing outcomes at the bedside. Bayesian Health’s real-time clinical intelligence platform was built to close this gap by continuously synthesizing multimodal EHR data (vitals, labs, medications, procedures, and longitudinal history) to learn patient-specific baselines and surface only the most actionable, high-precision signals to care teams. Across diverse health systems, this platform has been used to enable earlier recognition and intervention for a range of high-impact conditions, improving both bedside care and system performance. This talk will focus on concrete, real-world applications of the platform for sepsis, clinical deterioration, and palliative care needs, illustrating how earlier detection and workflow-integrated interventions drive measurable gains in clinical outcomes and margins, and why the value of early, precise detection is amplified in high-risk populations such as oncology patients, whose higher baseline acuity and treatment-related toxicities both elevate their risk of harm and make emerging deterioration harder to recognize. Case Study: Detecting Sepsis within a Oncology Patient Subpopulation. Background: Sepsis remains one of the leading causes of in-hospital mortality, and traditional rules-based alerts have struggled to deliver timely, actionable detection without overwhelming clinicians with false alarms. Oncology patients experience an elevated risk for sepsis and septic shock, and those who experience sepsis are more likely to suffer in-hospital mortality than non-cancer patients with sepsis. Early recognition of sepsis onset is challenging due to the overlap between signs of sepsis and inflammation and tumor- and treatment-related toxicities. We investigated the ability of Bayesian Health’s real-time artificial intelligence-based computational algorithm to perform timely detection of sepsis onset in hospitalized patients with cancer. This algorithm ingests data directly from the electronic health record, such as vital signs, laboratory results, medications, procedures, and patient-specific historical results, processing it in a continuous manner to flag presence of sepsis as early as possible. Methods: Analysis included 7480 adult emergency and inpatient encounters from three tertiary and quaternary academic centers (Cleveland Clinic Main Campus, Sinai Hospital of Baltimore, and Strong Memorial Hospital) and one community hospital (Cleveland Clinic Fairview Hospital) with sufficient data for inclusion (age ≥ 18, presence in an emergency or inpatient care unit, and at least one measurement of a panel of vital signs). Patients with cancer (including subgroups of solid tumor and hematologic malignancy) were identified by current or past recorded diagnoses (ICD-10 codes). All included patient records underwent a multi-tiered retrospective adjudication process. An automated screen labeled records with no evidence of infection or organ dysfunction as non-sepsis, removing them from need for manual review. Two independent physicians then adjudicated a sample of the eliminated records in addition to each remaining record for both presence of sepsis and time of onset, with a third physician reconciling disagreements. Evaluation of the algorithm included all discrete flags generated by the system during a period of time it was not in clinical use and not visible to care teams. Results: In the overall population, 3.1% of all patients and 6.0% of cancer patients were adjudicated to have had sepsis, including zero from a sample of 200 of the records marked as non-sepsis in automated screening. The detection algorithm identified sepsis with high and consistent accuracy across all patients and across cancer patients, including those with solid tumors and with hematologic malignancies (Table). A flag for sepsis occurred in 85.8% of all sepsis patients and 86.1% of cancer patients with sepsis within 4 days of sepsis onset. Sepsis was present in 24.2% of all cancer patients flagged (22.9% of solid tumor patients and 27.9% of hematologic malignancy patients). Compared to patients who were never flagged, all patients who were flagged, whether they had sepsis or not, were more likely to experience in-hospital mortality (7.9% vs 0.3%, p < 0.001) or ICU transfer (38.2% vs 7.9%, p < 0.001). This was also true within oncology patients (in-hospital mortality: 8.8% vs 0.4%, p < 0.001; ICU transfer: 34.7% vs 9.7%, p < 0.001). Implementation of an automated sepsis detection system with high accuracy in populations such as cancer patients, who have elevated risk of poor outcomes following sepsis, provides an opportunity to meaningfully improve timely delivery of care and reduce subsequent morbidity and mortality while minimizing alert fatigue for clinicians. Citation Format: Suchi Saria, Varesh Prasad, Nicasia Beebe-Wang, Ellie Zhang, Neri Cohen, David Graham, Conrad Gleber, James Morrison, Jacob Strand, Alexandra Tallman. Real-time multimodal AI enables individualized care in challenging subpopulations [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(8_Suppl):Abstract nr PL03-03.

Abstract Matrix metalloproteinases (MMPs) are key regulators of tumor progression, invasion, and metastasis; however, clinical efforts to inhibit MMPs have largely failed due to a lack of selectivity and unintended suppression of protective family members. In triple-negative breast cancer (TNBC), MMP-9 (gelatinase B) is strongly associated with tumor aggressiveness, extracellular matrix remodeling, and metastatic dissemination. In contrast, MMP-8 has been shown to exert anti-tumorigenic effects in breast cancer by limiting inflammation and suppressing metastasis. This functional divergence underscores the importance of selectively targeting MMP-9 while preserving MMP-8 activity as a rational therapeutic strategy in TNBC. To address this challenge, we engineered variants of the endogenous MMP inhibitor tissue inhibitor of metalloproteinases-1 (TIMP-1) with enhanced selectivity for MMP-9 over MMP-8. A yeast surface display library of human TIMP-1 was constructed and screened using fluorescence-activated cell sorting through iterative rounds of positive selection for recombinant MMP-9, followed by competitive counter-selection against MMP-8 to eliminate off-target binders. This strategy enabled enrichment of TIMP-1 variants with improved specificity for MMP-9 compared with wild-type TIMP-1. Several TIMP-1 variants exhibited enhanced binding and inhibitory selectivity toward MMP-9, with TIMP-1-C6.2 emerging as the most promising candidate. TIMP-1-C6.2 preferentially inhibited MMP-9 with a Ki of 0.3 ± 0.04 nM, while demonstrating substantially weaker inhibition of MMP-8 (Ki = 6.8 ± 0.27 nM), corresponding to an approximately 23-fold selectivity for MMP-9. Importantly, functional evaluation in Matrigel invasion assays using MDA-MB-231 TNBC cells revealed that TIMP-1-C6.2 significantly enhanced inhibition of tumor cell invasion compared with wild-type TIMP-1 in a dose-dependent manner (p < 0.0001). This improved anti-invasive activity reflects refined target selectivity rather than a generalized increase in inhibitory potency. Collectively, these findings demonstrate that selective engineering of TIMP-based inhibitors can overcome a central limitation of MMP-targeted therapies by suppressing pro-tumorigenic MMP-9 while sparing anti-tumorigenic MMP-8. This work provides a strong foundation for the development of selective MMP-9 inhibitors with improved safety and therapeutic potential for TNBC and other MMP-driven cancers. Citation Format: Alireza Shoari, Alexandra Hockla, Mathew A. Coban, Ella E. Aitchison, Alexandra M. Dimesa, Evette S. Radisky. Protein engineering of selective MMP-9 inhibitors reveals a therapeutic strategy for triple-negative breast cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(8_Suppl):Abstract nr LB233.

Cognitive impairment in sepsis survivors is a growing clinical challenge as the number of sepsis cases rise and acute mortality rates fall. It is estimated that up to 70% of sepsis patients experience cognitive dysfunction and many report persistent dysfunction post‐sepsis. Cognitive impairment is a broad term that refers to sepsis‐associated brain dysfunction or encephalopathy (SABD or SAE, respectively). While many contributors, such as inflammation, blood–brain barrier dysfunction, and extended microglial activation are implicated in SABD/SAE development, much is still unknown regarding the underlying mechanistic causes of persistent cognitive defects in sepsis survivors. Here, we employed cecal ligation and puncture (CLP) to model surgical sepsis in mice, after which mice were subjected to multiple memory function assays for up to 2 months post‐sepsis. Furthermore, single‐cell RNA sequencing and validation studies were performed with murine hippocampi to query alterations in the brain microenvironment. Our study shows that CLP mice exhibited decreased spontaneous alternation at 4 weeks and decreases in both short‐ and long‐term recognition (at 6 weeks and 2 weeks, respectively) accompanied by substantially altered cell type makeup of the hippocampus, including hippocampal neuron and pericyte loss. Finally, transcriptional alterations in the macrophage populations implicate aberrant activation in CLP survivors. In conclusion, post‐sepsis mice exhibit reduced memory capacity and altered hippocampal cell composition and transcriptional profiles. This study and associated data set will be valuable for further investigation of the underlying pathophysiology of SABD/SAE and elucidation of potential therapeutic candidates.

BACKGROUND: The metabolic mechanisms underlying right ventricular (RV) dysfunction are poorly understood, particularly outside of group 1 pulmonary hypertension (PH). We aimed to identify metabolites and pathways associated with RV systolic function and explored whether associations differed by pulmonary vascular resistance, PH group 1 status, and sex. METHODS: We analyzed data from the multicenter PVDOMICS (Pulmonary Vascular Disease Phenomics) cohort. RV systolic function metrics included fractional area change (echo), global longitudinal strain (echo), and ejection fraction (cardiac magnetic resonance). We used linear regression adjusted for age, sex, body mass index, and PH group to assess associations between metabolites and RV function. Pathway enrichment analyses were used to identify pathways significantly associated with RV function. Interaction terms were assessed to determine whether metabolite associations were modified by pulmonary vascular resistance, group 1 PH status, or sex. Least absolute shrinkage and selection operator regression was used to develop metabolite-based scores for RV function, and prognostic performance was assessed. RESULTS: There were 979 participants with plasma metabolomics and RV function data. Linear regression identified 170 metabolites that were significantly associated with all 3 RV metrics. Androgenic steroid, gamma-glutamyl amino acid, polyamine, vitamin A, fatty acid, and sterol pathways are most strongly associated with RV systolic function. Two metabolites interacted with group 1 PH status, and 6 interacted with pulmonary vascular resistance. Four androgenic steroids are associated more strongly with RV systolic function in women compared with men. Metabolite-based scores were prognostically equivalent to RV systolic function metrics and less accurate than REVEAL Lite 2 scores. CONCLUSIONS: We provide a blueprint of metabolites and metabolic pathways associated with RV systolic function across the spectrum of PH. Novel links to vitamin A and glutathione metabolites were observed. We detected few metabolites that associated with RV systolic function differentially by group 1 PH status or degree of pulmonary vascular resistance elevation. Androgenic steroids may associate more strongly with RV systolic function in women compared with men.

Background Acute kidney injury (AKI) is associated with high morbidity and mortality in critically ill patients. Multicenter analyses describing the epidemiology of AKI in the cardiac intensive care unit (CICU) are scarce. Here, we describe the prevalence, predictors, and outcomes associated with AKI in a contemporary multicenter CICU population. Methods The Critical Care Cardiology Trials Network (CCCTN) is a collaboration of CICUs in North America coordinated by the TIMI Study Group (Boston, MA). We evaluated patient and hospital-level outcomes as a function of creatinine-only Kidney Disease: Improving Global Outcomes (KDIGO) AKI stage within the CCCTN registry. Logistic regression was used to assess associations with in-hospital mortality. Results Among 21 603 admissions, the overall prevalence of AKI was 23.7%, which was composed of KDIGO stage 1: 12.7%, stage 2: 1.7%, and stage 3: 9.2%. A higher prevalence and severity of AKI were seen in patients with baseline kidney disease, hypertension, or diabetes and in admissions with heart failure, cardiogenic shock, and cardiac arrest ( P < .001 for all). There was a stepwise increase in hospital mortality across AKI stages (stage 1: 23%, stage 2: 39%, stage 3: 42%; P < .0001). The increased risk of death associated with progressive AKI stage persisted after multivariate adjustment (adjusted OR: stage 1: 2.1, stage 2: 3.7, stage 3: 3.4). Conclusions AKI occurs in 1 in 4 admissions to the CICU, and a higher AKI stage is incrementally associated with in-hospital mortality, highlighting a need to develop strategies to mitigate AKI and its complications.

Abstract Background: Mantle cell lymphoma (MCL) is an aggressive and rare B-cell non-Hodgkin lymphoma with poor prognosis, even with treatment. Despite its clinical importance, the etiology of MCL remains largely unknown. Some studies have reported a positive association with family history, suggesting that genetic factors could contribute to risk. Methods: To identify germline genetic variants associated with risk, we conducted the first genome-wide association studies (GWAS) and GWAS meta-analysis for MCL, comprising 1,163 cases and 61,271 controls. The most significant loci were taken forward for replication in three independent studies, including 576 cases and 771,773 controls. To identify potential target genes and pathways of discovered loci, we conducted F-MAGMA, colocalization, and transcriptome-wide association study (TWAS) analyses. To gain insight into underlying regulatory mechanisms, we performed integrative epigenomic analyses using DNase I hotspots and histone mark ChIP-seq data across diverse cell types applying the FORGE2 framework. Results: In the joint analyses, we identified eight genome-wide significant loci (P&lt;5x10-8) associated with MCL risk, several of which were located near genes with known DNA repair (ATM), telomere (TERT), or RNA-binding functions (RBM20). Further analyses using F-MAGMA, which uses DNase-seq data to prioritize genes from GWAS, identified genes that were significantly associated with risk, including SP140, a chromatin reader and immune regulator of pathogen response. This gene also displayed strong colocalization with our lead variant in whole blood (COLOC posterior probability PP4=0.97). TWAS demonstrated significant associations with SP140 and ACTA2, which has been linked to cell proliferation (P&lt;3x10-6). Enrichment for DNase I hotspots was observed in B and T lymphocytes (q-value&lt;0.05), providing evidence for a role in immune cell-specific regulatory regions. Enrichment for enhancer-associated histone mark H3K4me1 was observed in B cells (q-value&lt;0.01), highlighting a role for immune cell-specific enhancers. Transcription factor (TF) motif enrichment analysis pointed to TFs critical for B-cell development and differentiation, notably TCF3 and EP300 (q&lt;0.01 for both), suggesting an association between B-cell lineage regulation and MCL risk. Finally, genome-wide SNP-based heritability was estimated to be 17%, underscoring the importance of common variants in MCL risk. Conclusion: Our study provides novel insight into the inherited susceptibility of MCL by identifying eight significant loci and estimating substantial common variant heritability. These findings highlight a role for several distinct biological pathways -specifically DNA repair, telomerase function, and B-cell differentiation- in the etiology of MCL, offering new targets for mechanistic investigation. Citation Format: Charles E. Breeze, Alyssa Clay-Gilmour, Hanla A. Park, Ólafur B. Davíðsson, Angelica Macauda, Brenda M. Birmann, Elizabeth E. Brown, Murat Güler, Michelle A. T. Hildebrandt, Alexandra Nieters, Krystle Ong, Jojo Biel-Nielsen Dietz, Karin E. Smedby, Karl Smith-Byrne, Rosalie Griffin, Sophia S. Wang, Susan Slager, James R. Cerhan, Jonathan N. Hofmann, Qing Lan, Nathaniel Rothman, Ingrid Glimelius, Henrik Hjalgrim, James Mckay, Sonja I. Berndt. Genome-wide association study of mantle cell lymphoma identifies novel loci suggesting a critical role for B-cell chromatin readers and DNA repair mechanisms [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 3602.

Abstract The detection of genetic abnormalities is required during diagnostic workup and for potential individualization of therapy selection in multiple myeloma (MM) and its precursor conditions. At present, this relies on invasive bone marrow (BM) biopsies, severely limiting early detection, frequent longitudinal monitoring, and the precise selection of therapy. The current standard for detecting genetic alterations in MM is fluorescence in situ hybridization (FISH), which cannot detect point mutations and other clinically relevant alterations. Consequently, the IMS-IMWG guidelines were recently updated to require next-generation sequencing for the classification of high-risk MM. To address these needs, we recently launched GenoPredicta, a CLIA-approved LDT that enables routine monitoring, informing diagnosis, and treatment selection by comprehensively characterizing MM genomes with whole genome sequencing (WGS) from as few as 50 circulating tumor cells (CTCs) isolated from peripheral blood (PB) or tumor cells from BM. Briefly, tumor cells are isolated from samples using fluorescence-activated cell sorting and subjected to WGS, from which copy number alterations, structural variants, and short variants (SNVs/indels) are identified using a fully automated pipeline generating physician-ready clinical reports from raw sequencing data in ∼6h. Analytical validation of GenoPredicta showed complete concordance with FISH results. Identifying alterations in therapeutic targets (e.g., BCMA, GPRC5D) for guiding MM immunotherapies is becoming increasingly important. Here, we describe GenoPredicta results from relapsed/refractory MM patients, highlighting resistance-conferring alterations that can only be detected by WGS, such as deletions in the kilo- to megabase scales that are observed in conjunction with SNVs and indels, leading to biallelic loss/inactivation of the gene, including at subclonal levels. In addition to biallelic loss of BCMA and GPRC5D in response to CAR T or T cell engager therapies, we observed similar resistance mechanisms for targets of immunomodulatory drugs, e.g., CRBN. The observation of these resistance mechanisms was consistent with patients’ clinical histories. In summary, we demonstrate that low input WGS-based characterization of MM from BM or CTCs is a viable replacement for FISH for clinical diagnosis and monitoring, with CTC-based measurements enabling comprehensive profiling of the MM genome. Crucially, this includes genetic alterations that confer resistance to therapy, allowing for both early detection of such alterations and more precise selection and guidance of therapy. The dramatically improved variant calling ability from WGS, especially in low-input CTC applications, extends to other malignancies and will gain wider adoption as sequencing costs continue to decrease. Citation Format: Bruno Paiva, Peter Voorhees, Patricia T. Greipp, Danielle Sookiasian, Julian Hess, Marisa DeMeo, Vicki Pounder, Sarah Calkins, Reid Meyer, Linda B. Baughn, Christine-Ivy Liacos, Meletios-Athanasios Dimopoulos, Alexandra Papadimou, Taouxi Konstantina, Efstathios Kastritis, Jesus Berdeja, Daniel Auclair, Valentina Nardi, Thomas Mullen, Francois Aguet, Shaji Kunnathu Kumar. Whole genome sequencing of multiple myeloma genomes with a novel clinical assay enables identification of genetic alterations underlying immunotherapy resistance [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 1067.

ABSTRACT The epidemiology of myelodysplastic syndromes/neoplasms (MDS) is challenging to define due to inconsistent reporting, complex diagnostic procedures, and evolving diagnostic criteria. Using the National MDS Natural History Study—a prospective cohort with centrally adjudicated histopathology and genetic variant review—we characterized the landscape of MDS across the United States and identified differences across demographics. Among 2115 participants, 64% (1346) had an MDS spectrum condition, including MDS (24%), MDS/myeloproliferative neoplasm (5%) and precursor conditions—clonal cytopenia of undetermined significance (22%) and idiopathic cytopenia/dysplasia of undetermined significance (13%). The median age was 74 years, and participants were predominantly male (66%), White (91%), and Non‐Hispanic (92%). Myeloid‐associated variants were detected in 68% of participants, most commonly in TET2, DNMT3A, ASXL1, SF3B1, and SRSF2 . Black, compared to White, participants were younger at diagnosis (69 vs. 74 years, p = 0.01), had equal or increased prevalence of higher‐risk MDS, lower hemoglobin, and higher peripheral blood blasts, yet were less likely to receive MDS‐directed therapy (14% vs. 42%, p = 0.008). Black and Hispanic participants had fewer detectable gene mutations than White participants. Females had lower variant allele frequencies and fewer RNA splicing gene mutations than males. After multivariable adjustment, TP53 mutations, MDS diagnosis, and higher‐risk disease were associated with worse progression‐free and overall survival; age was also associated with overall survival. Black race trended toward improved progression‐free survival. These findings highlight the need for enhanced understanding of MDS pathogenesis across patient groups and refined prognostic tools to improve personalized management of MDS spectrum conditions. Trial Registration: ClinicalTrials.gov identifier: NCT02775383