kushagrayadv/clinical-entities

Clinical Entity Extraction (NER)

Detects clinical entities (diagnosis, medical_history, medication, procedure, symptom) in clinical text with a fine-tuned GLiNER model.

API

The Space exposes a JSON endpoint at /extract_entities:

from gradio_client import Client

client = Client("https://<user>-<space>.hf.space")  # or Client("<user>/<space>", hf_token=...)
result = client.predict("Pt given gabapentin for neuropathy.", 0.5, api_name="/extract_entities")
# {"text": ..., "entities": [{"start", "end", "text", "label", "score"}, ...]}

Configuration

Set these as Space secrets/variables (Settings → Variables and secrets):