AI to help ICU pharmacists prevent medication harms
Official title: Artificial intelligence-based health IT tools to optimize critical care pharmacist resources through adverse drug event prediction
Funded at University of Georgia · NIH-11187104 · Data updated 2026-11-12
Using AI to predict which critically ill patients may have medication-related harms so pharmacists can intervene sooner.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Georgia NIH-funded |
| Lab location | 1 site (Athens, United States) |
| Project start | September 1, 2022 |
| Project end | August 31, 2027 |
| Funding year | 2025 |
| Award (this year) | $377,549 |
| NIH project number | 5R01HS029009-04 |
| Project ID | NIH-11187104 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are adults receiving intensive care and multiple medications at participating hospital ICUs where critical care pharmacists are available.
✕Less likely to help
Patients treated outside participating ICUs, those on very few medications, or with medication issues not captured in the hospital record may not see direct benefit.
What this research studies
If you are in the ICU and on multiple medicines, this project aims to spot patterns in hospital records that signal preventable medication problems. Researchers will combine a new Medication Regimen Complexity-ICU (MRC-ICU) score with AI and causal-inference methods to find which medication interventions would most likely prevent adverse drug events. They will build an AI-informed dashboard to direct critical care pharmacists to patients who need medication review first. The effort is meant to help pharmacists focus their time to reduce medication harms and improve recovery.
Why it matters
Potential benefit: If successful, this could lower medication-related harms in the ICU and improve patient outcomes by helping pharmacists intervene earlier.
How similar studies have gone: AI has been used for medication safety in other settings, but applying AI plus causal-inference methods specifically to predict pharmacist-preventable adverse events in the ICU is largely new.
Where this research is happening
-
University of Georgia
Athens, United States Active
Researchers
- Principal investigator: Sikora, Andrea — University of Georgia
- Study coordinator: Sikora, Andrea
Related research
Other NIH-funded projects on the same topics.
-
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.
-
Personalized immune-based care for septic kids with organ failure
A network study helps critically ill children with sepsis who have organ failure by tailoring treatments to their individual immune profiles.
-
Collaborative Pediatric Critical Care Clinical Site for Precision Sepsis Care
A pediatric-focused research grant exploring personalized care for kids with severe sepsis to improve outcomes.
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.