Inflammatix Publishes Breakthrough Sepsis Research in Nature Medicine, Validates AI-Powered TriVerity Test
核心洞察
Inflammatix published three landmark studies in Nature Medicine that redefine sepsis (搜索) diagnosis and treatment through AI-powered immune profiling and consensus frameworks.
The SEPSIS (搜索)-SHIELD study validated TriVerity (搜索)'s ability to distinguish bacterial from viral infections and predict illness severity in over 1,200 patients with high sensitivity and specificity.
Two new consensus frameworks, HI-DEF and CTS, identified distinct immunological states in sepsis (搜索) patients, with dysregulated patients showing 5-7 times higher mortality risk.
Inflammatix announced the publication of three manuscripts in Nature Medicine that represent a paradigm shift in sepsis (搜索) diagnosis and treatment, centered around the company's AI-powered TriVerity (搜索) test and new consensus frameworks for understanding sepsis as distinct immunological states rather than a single syndrome.
The publications address a critical healthcare challenge: sepsis (搜索) remains the leading cause of death in U.S. hospitals despite billions spent on new tests, drugs, and policies. Current protocols lack clear definitions of what constitutes "sepsis" or "not sepsis," making clinical decision-making difficult and contributing to poor outcomes.
SEPSIS-SHIELD Study Validates TriVerity Test
The pivotal SEPSIS (搜索)-SHIELD study (NCT04094818) confirmed the clinical utility of TriVerity (搜索), a molecular test that rapidly distinguishes between bacterial infection (搜索), viral infection (搜索), and non-infectious inflammation while simultaneously predicting illness severity. The study demonstrated high sensitivity and specificity across more than 1,200 patients with suspected acute infection or sepsis.
"TriVerity (搜索) radically improves early decisions, telling clinicians whether patients need antibiotics, other diagnostics, or a higher level of care," said Tim Sweeney, MD, PhD, co-founder and CEO of Inflammatix. "That clarity can not only drive better outcomes, it also protects hospitals from costly denials."
The TriVerity (搜索) Test System incorporates a panel of 29 patient messenger RNAs (mRNAs) to interpret the body's immune response using machine learning-derived algorithms. Results are delivered in approximately 30 minutes, enabling real-time clinical decision-making in emergency departments. The test received FDA Breakthrough Device Designation and FDA 510(k) clearance in January 2025.
HI-DEF Framework Identifies Four Immune States
The second Nature Medicine paper introduced the Human Immune Dysregulation Evaluation Framework (HI-DEF), the first consensus immune dysregulation network for critical illnesses. Developed by the SUBSPACE consortium (搜索) through analysis of transcriptomic data from more than 7,000 patient samples across 37 cohorts worldwide, HI-DEF measures dysregulation in myeloid cells (搜索) (neutrophils (搜索), monocytes (搜索)) and lymphoid cells (搜索) (T cells (搜索), natural killer cells (搜索)).
The framework classifies patients into four states: balanced, myeloid-dysregulated, lymphoid-dysregulated, or system-wide dysregulated. Patients with myeloid or lymphoid dysregulation were 5-7 times more likely to die or require intensive care unit-level care, with mortality highest among those with system-wide dysregulation.
"By moving beyond syndromic definitions and directly measuring immune cell dysfunction, HI-DEF offers a practical tool for precision medicine in the ICU," noted Purvesh Khatri, PhD, professor of medicine at Stanford School of Medicine (搜索) and co-founder of Inflammatix. "Physicians can use this framework as a roadmap for tailoring treatment plans and avoiding use of harmful therapies."
Analysis of multiple randomized controlled trials using HI-DEF scores found associations with differential mortality in patients treated with immunomodulatory drugs such as anakinra and corticosteroids (搜索), highlighting the framework's potential for therapeutic applications.
Consensus Transcriptomic Subtypes Emerge
The third publication identified three robust consensus transcriptomic subtypes (CTS1, CTS2, and CTS3) of sepsis (搜索) based on analysis of 2,142 blood samples from patients across four cohorts. ICU mortality was highest within CTS2 at 28.6%, compared to 16% in CTS1 and CTS3. The CTS clusters also facilitated identification of patients who may or may not respond to steroid treatment.
Notably, the three CTS endotypes corresponded to three of the four HI-DEF endotypes, demonstrating robustness across diverse patient populations with sepsis (搜索).
Clinical Implementation and Impact
Edward A. Panacek, MD, professor and chair of Emergency Medicine at the University of South Alabama, emphasized the practical implications: "We have never had a tool that can both improve patient care and reduce costs — until now. The collective results across three manuscripts show that host response can provide important guidance to physicians, who can now use a simple blood test like TriVerity (搜索) to identify which patients with sepsis (搜索) need aggressive therapy and which might be harmed by it."
The research supports a transition from "one-size-fits-all" sepsis (搜索) care toward precision medicine approaches in emergency departments and ICUs. TriVerity (搜索) development was supported in part by funding from the U.S. Department of Health and Human Services Biomedical Advanced Research and Development Authority (BARDA) under multiple contracts.