Pulling detailed cancer information from medical records
Cancer Deep Phenotype Extraction from Electronic Medical Records (renewal)
This project builds AI tools that read doctors' notes to pull detailed information about cancer patients' tumors, treatments, and side effects.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Boston Children's Hospital NIH-funded |
| Lab location | 1 site (Boston, United States) |
| Project ID | NIH-11231451 on NIH RePORTER |
What this research studies
As a patient, this project means researchers are teaching computer language models to read the unstructured parts of medical records — like clinic notes, pathology reports, and discharge summaries — to create a fuller picture of your cancer journey. The team will extract tumor details (type, location, biomarkers), treatment histories and timing, treatment responses, and patient-level factors like other illnesses or side effects. By linking these pieces across time, the tools aim to turn many hours of manual chart review into automated, searchable data. The work is being developed at Boston Children's Hospital and applied to records from participating hospitals to build large, usable datasets for cancer research.
Who could benefit from this research
Good fit: Ideal candidates are people with cancer whose electronic medical records are held at participating hospitals and who have allowed their records to be used for research.
Not a fit: Patients without electronic records, those whose data are not shared with the project, or people without cancer are unlikely to gain direct benefit from this work.
Why it matters
Potential benefit: If successful, this could speed research and help doctors and researchers find patients for studies, compare treatments, and spot patterns in outcomes more quickly.
How similar studies have performed: Related AI and natural-language-processing projects have shown promise at extracting specific details from medical notes, but capturing a full, longitudinal 'deep phenotype' across institutions is still relatively new.
Where this research is happening
Boston, United States
- Boston Children's Hospital — Boston, United States (Active)
Researchers
- Principal investigator: Savova, Guergana K. — Boston Children's Hospital
- Study coordinator: Savova, Guergana K.
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.