AI NLP Model Accurately Identifies Primary Cancer Types in Brain Metastases Cases

Researchers developed an AI tool using natural language processing to accurately identify primary cancer types in patients with brain metastases by analyzing clinical notes.

Key Details

• MUSC Hollings Cancer Center team created an NLP model for electronic health records (EHR) notes.
• The tool correctly identified the primary cancer in over 90% of cases (97% for common types).
• It outperformed standard ICD codes, which often lack specificity for cancer origins and subtypes.
• The study analyzed 82,000 clinical notes from more than 1,400 stereotactic radiosurgery patients.
• The approach is lightweight, scalable, and requires relatively little data or computing power.
• The model can improve research and treatment planning for patients undergoing targeted brain radiation.

Why It Matters

Accurately identifying a tumor's origin is critical for optimizing radiation therapy and cancer care. Leveraging NLP for extracting nuanced diagnosis details from clinical notes can streamline workflows, enhance treatment precision, and enable better research data quality in radiology and oncology.

Read more