Identifying different types of sepsis linked to antibiotic-resistant infections using advanced technology.

Identifying Sepsis Phenotypes Associated with Antibiotic-Resistant Pathogens Using Large Language Models and Machine Learning

NIH-funded research Massachusetts General Hospital · NIH-10948425

This study is looking to help doctors treat sepsis better by using advanced technology to find out which types of sepsis are caused by germs that don't respond to common antibiotics, so they can give the right medicine to patients and avoid using antibiotics that aren't needed.

Quick facts

Grant typeCareer grant
Study typeNIH-funded research
Funding institutionMassachusetts General Hospital NIH-funded
Lab location1 site (Boston, United States)
Project IDNIH-10948425 on NIH RePORTER

What this research studies

This research aims to improve the treatment of sepsis by using large language models and machine learning to identify specific phenotypes of sepsis associated with antibiotic-resistant pathogens. By analyzing detailed electronic health record data, including clinical notes and patient histories, the study seeks to develop more accurate models that can help clinicians determine when to use narrow-spectrum antibiotics instead of broad-spectrum ones. This could lead to more targeted treatments, reducing unnecessary antibiotic use and the associated risks of resistance and side effects. The research will involve collecting and analyzing data from patients with suspected sepsis to enhance understanding of their conditions.

Who could benefit from this research

Good fit: Ideal candidates for this research are patients diagnosed with sepsis or suspected of having sepsis who are receiving or may require antibiotic treatment.

Not a fit: Patients with sepsis caused by non-resistant pathogens or those who do not require antibiotic therapy may not benefit from this research.

Why it matters

Potential benefit: If successful, this research could lead to more effective and safer antibiotic treatments for patients with sepsis, minimizing the risks of antibiotic resistance and adverse effects.

How similar studies have performed: Previous studies have shown promise in using clustering methods to understand sepsis subtypes, but this approach of integrating clinical notes with machine learning is relatively novel.

Where this research is happening

Boston, 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.