Making AI alerts help pathologists give more accurate diagnoses
Optimizing the Human-Computer Interaction in Pathology: Understanding the Impact of Computer-Aided Diagnosis Tools on Pathologists' Interpretive Performance
This project tests different ways of showing AI highlights to pathologists to help improve accuracy when reading pathology slides, especially for cancer.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of California Los Angeles NIH-funded |
| Lab location | 1 site (Los Angeles, United States) |
| Project ID | NIH-11250111 on NIH RePORTER |
What this research studies
From a patient perspective, researchers will show digital pathology cases to 250 practicing pathologists and vary the kind of AI cue they see and when it appears during interpretation. Pathologists will be randomly assigned to receive either feature-only cues or feature-plus-diagnosis cues, and to different timing patterns across three interpretation phases. The team will measure how these cue types and timings change where pathologists look, how they decide, and whether diagnoses are more or less accurate. The aim is to find display methods that help pathologists without causing harmful overreliance on AI suggestions.
Who could benefit from this research
Good fit: This project enrolls practicing pathologists (especially those who read cancer biopsies) rather than patients.
Not a fit: Patients will not be directly enrolled or receive experimental treatments through this grant, so individual patients are unlikely to gain immediate direct benefit from participation.
Why it matters
Potential benefit: If successful, this work could lower diagnostic errors in pathology and lead to more accurate cancer diagnoses and safer treatment choices for patients.
How similar studies have performed: Related work in radiology has shown that some AI cue presentations can capture attention or induce overreliance and sometimes reduce accuracy, but similar effects are not yet well-studied in pathology.
Where this research is happening
Los Angeles, United States
- University of California Los Angeles — Los Angeles, United States (Active)
Researchers
- Principal investigator: Elmore, Joann G — University of California Los Angeles
- Study coordinator: Elmore, Joann G
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 below.