AI to predict and reduce emergency care during cancer treatment
Multi-institutional validation of a multi-modal machine learning algorithm to predict and reduce acute care during cancer therapy
['FUNDING_R01'] · UNIVERSITY OF CALIFORNIA, SAN FRANCISCO · NIH-11285217
Uses machine learning to predict who receiving cancer therapy may need an emergency visit or hospital stay and helps prompt support to reduce those events.
Quick facts
| Phase | ['FUNDING_R01'] |
|---|---|
| Study type | Nih_funding |
| Sex | All |
| Sponsor | UNIVERSITY OF CALIFORNIA, SAN FRANCISCO (nih funded) |
| Locations | 1 site (SAN FRANCISCO, UNITED STATES) |
| Trial ID | NIH-11285217 on ClinicalTrials.gov |
What this research studies
This project uses medical record information and wearable activity (like daily step counts) to build and test an AI tool that forecasts which patients getting outpatient chemotherapy or radiation might need urgent care. The tool will be validated across multiple hospitals and clinics so it works well for people of different races, incomes, and regions. When the AI flags someone at higher risk, care teams can offer timely supportive interventions aimed at preventing emergency visits or admissions. The team will measure accuracy and fairness and adjust the approach to improve outcomes for diverse patients.
Who could benefit from this research
Good fit: People receiving outpatient systemic therapy or radiation for cancer at participating hospitals who can share medical records and, if asked, wearable activity data.
Not a fit: Patients not receiving outpatient cancer therapy, those treated only as inpatients, or those without accessible medical records or wearable data are unlikely to benefit from this project.
Why it matters
Potential benefit: Could lower emergency department visits and hospitalizations during cancer treatment, improving patient safety and reducing costs.
How similar studies have performed: The team previously ran a randomized trial showing an ML approach using EHR data decreased acute care needs, but broad multi-center validation remains novel.
Where this research is happening
SAN FRANCISCO, UNITED STATES
- UNIVERSITY OF CALIFORNIA, SAN FRANCISCO — SAN FRANCISCO, UNITED STATES (ACTIVE)
Researchers
- Principal investigator: HONG, JULIAN CLINT — UNIVERSITY OF CALIFORNIA, SAN FRANCISCO
- Study coordinator: HONG, JULIAN CLINT
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.