🏥 Clinical Disease Entity Extractor

Paste any clinical free-text below and pick a model. The model will identify disease entities and return a confidence score for each.

Production — BioBERT (NCBI Disease): ugaray96/biobert_ncbi_disease_ner
Custom — Bio_ClinicalBERT (MedMentions / SNOMED): acebirim/snomed-ner-model

Model

Clinical Text

Try an example

Highlighted Entities

Confidence Score: Average softmax probability across entity tokens. Scores below 50% indicate the model is not plurality-confident in its DISEASE prediction — a natural decision boundary for a 3-class problem — a useful signal for monitoring model reliability in production.

Built as a capstone project for the Advanced ML course from https://ml.electricsheep.africa/grade2/.