Prescriptive AI for ICU shock care: a patient-facing decision support system
Official title: Designing a Comprehensive Machine Learning-driven Prescriptive Clinical Decision Support System for Shock and Associated Critical Care Conditions
Funded at University of Pittsburgh at Pittsburgh · NIH-11393886 · Data updated 2026-11-12
A hospital-based project aims to help ICU doctors make faster, safer decisions for patients in shock using a smart AI tool.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Pittsburgh at Pittsburgh NIH-funded |
| Lab location | 1 site (Pittsburgh, United States) |
| Project start | August 15, 2025 |
| Project end | July 31, 2030 |
| Funding year | 2026 |
| Award (this year) | $433,710 |
| NIH project number | 5R35GM159939-02 |
| Project ID | NIH-11393886 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults treated in ICUs with shock or related critical conditions in participating hospitals.
✕Less likely to help
Patients not experiencing shock or those treated outside ICU settings may not receive direct benefits.
What this research studies
This project will develop a machine learning driven system that supports clinicians in choosing the best treatments for patients with shock and related critical conditions. It will focus on making the decision process faster, safer, and easier to follow at the bedside in the ICU. The work will address data challenges, model development, and methods to monitor safety and performance during real-world use.
Why it matters
Potential benefit: If successful, the tool could help ICU teams choose better treatments more quickly, potentially improving survival and recovery for seriously ill patients.
How similar studies have gone: Previous AI models in critical care have struggled to translate to bedside use, making this translational effort notably important.
Where this research is happening
-
University of Pittsburgh at Pittsburgh
Pittsburgh, United States Active
Researchers
- Principal investigator: Yoon, Joo Heung — University of Pittsburgh at Pittsburgh
- Study coordinator: Yoon, Joo Heung
Related research
Other NIH-funded projects on the same topics.
-
Pragmatic midodrine trial to reduce ICU vasopressor use in septic shock
A practical, patient-focused trial tests whether taking oral midodrine can lessen the need for IV vasopressors and shorten ICU stays for people with sepsis-related low blood pressure.
-
Understanding how small heat shock proteins protect our cells
A study from the University of Washington explores how tiny chaperone proteins protect eye and other cells from damage, which could help prevent conditions like cataracts and age-related macular degeneration.
-
Collaborative Pediatric Critical Care Clinical Site (CPCCRN)
A nationwide network is testing personalized care approaches for seriously ill children with sepsis to improve outcomes.
-
Collaborative Pediatric Critical Care Research Network: personalized care for septic kids
A nationwide network is testing personalized treatment approaches for children with sepsis-related organ failure to improve outcomes.
-
Collaborative Pediatric Critical Care Network Site: Kids’ Sepsis Care
A pediatric-focused NIH grant supports a network site that helps tailor sepsis care for critically ill children across multiple centers.
-
Personalized care for septic children through immunomodulation in MODS
This project tests a custom approach to treating pediatric sepsis in kids with organ failure by tailoring treatments to each child’s immune profile.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.