Improving sepsis detection and classification using hospital electronic health records

Integrated Detection and Classification of Sepsis via Tensor Methods Using EHR

NIH-funded research Duke University · NIH-11332721

This project uses hospital electronic health records and advanced math to spot sepsis earlier and group adult patients into types to help guide treatment.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionDuke University NIH-funded
Lab location1 site (Durham, United States)
Project IDNIH-11332721 on NIH RePORTER

What this research studies

You would be part of a project where researchers analyze large numbers of hospital electronic health records from adult patients to find patterns linked to sepsis. They convert the data into a three-way tensor format that captures patient, clinical features, and time, then apply advanced mathematical and machine‑learning methods to handle sparse and changing data. The goal is to detect sepsis earlier, sort patients into distinct disease types or phenotypes, and suggest more personalized treatment paths. Work is done with existing EHR data across participating hospitals, so there is no new medical procedure for most patients beyond data use or routine care.

Who could benefit from this research

Good fit: Adults aged 21 and over who are hospitalized or receiving care at participating hospitals, especially those with infections or suspected sepsis, are the main candidates for inclusion.

Not a fit: Children under 21, people treated outside participating hospital systems, or anyone whose records are not included or shared would be unlikely to benefit directly from this project.

Why it matters

Potential benefit: If successful, this could lead to earlier warnings for sepsis and more tailored treatments, potentially reducing deaths and complications.

How similar studies have performed: Previous machine‑learning work on EHRs has sometimes improved early sepsis alerts but produced mixed clinical outcomes, and the tensor-based approach here is relatively new with limited prior testing.

Where this research is happening

Durham, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.