Fast, detailed overdose monitoring using smart reading of medical records
Fast and fine: NLP methods for near real-time and fine-grained overdose surveillance
This project uses advanced computer language tools to find and report opioid overdoses quickly from emergency and ambulance records to help communities and health workers.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Kentucky NIH-funded |
| Lab location | 1 site (Lexington, United States) |
| Project ID | NIH-11360424 on NIH RePORTER |
What this research studies
If I needed emergency care for a suspected overdose, this project would use the notes in my ED or ambulance record to teach computer models to recognize overdose events and the specific drugs involved. The team will combine billing codes with narrative text and train deep neural network models to catch cases that simple code-based or keyword searches miss. The goal is near real-time detection and fine-grained identification of substances so public health teams can respond faster. Data come from participating hospitals and EMS systems and the work focuses on building and testing algorithms that read clinical text.
Who could benefit from this research
Good fit: This work involves people who have emergency department or EMS encounters for suspected or confirmed overdoses whose records include clinical notes or narratives.
Not a fit: People who never go to the ED or use EMS, or whose records lack narrative detail, are less likely to be captured and may not directly benefit from this surveillance work.
Why it matters
Potential benefit: If successful, public health agencies and hospitals could detect overdose spikes faster and direct prevention and treatment resources where they are most needed.
How similar studies have performed: Prior approaches using diagnosis codes or simple keyword rules have missed many cases, and early NLP efforts show promise, but near real-time deep-learning models for fine-grained overdose detection are relatively new.
Where this research is happening
Lexington, United States
- University of Kentucky — Lexington, United States (Active)
Researchers
- Principal investigator: Kavuluru, Venkata Naga Ramakanth — University of Kentucky
- Study coordinator: Kavuluru, Venkata Naga Ramakanth
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.