Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
|
3 |
+
|
4 |
+
# Set Streamlit page config
|
5 |
+
st.set_page_config(page_title="Disease NER", layout="centered")
|
6 |
+
|
7 |
+
# Title of the app
|
8 |
+
st.title("🧠 Disease Named Entity Recognition (NER)")
|
9 |
+
st.write("This app uses a BioBERT model to detect **disease entities** in clinical or medical text.")
|
10 |
+
|
11 |
+
# Load the model
|
12 |
+
@st.cache_resource
|
13 |
+
def load_model():
|
14 |
+
model_name = "Ishan0612/biobert-ner-disease-ncbi"
|
15 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
16 |
+
model = AutoModelForTokenClassification.from_pretrained(model_name)
|
17 |
+
ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple")
|
18 |
+
return ner_pipeline
|
19 |
+
|
20 |
+
ner = load_model()
|
21 |
+
|
22 |
+
# Input from user
|
23 |
+
text_input = st.text_area("Enter a medical sentence below:",
|
24 |
+
"The patient was diagnosed with diabetes mellitus and rheumatoid arthritis.")
|
25 |
+
|
26 |
+
# Run model when button is clicked
|
27 |
+
if st.button("Find Disease Entities"):
|
28 |
+
if text_input.strip() == "":
|
29 |
+
st.warning("Please enter some text.")
|
30 |
+
else:
|
31 |
+
results = ner(text_input)
|
32 |
+
|
33 |
+
if results:
|
34 |
+
st.subheader("🧬 Disease Entities Found:")
|
35 |
+
for e in results:
|
36 |
+
st.markdown(f"- **{e['word']}** ({e['entity_group']}) – Score: `{e['score']:.2f}`")
|
37 |
+
else:
|
38 |
+
st.info("No disease entities found in the given text.")
|