app.py

import streamlit as st
import pandas as pd
import numpy as np
from math import ceil
from collections import Counter
from string import punctuation
import spacy
from spacy import displacy
import en_ner_bc5cdr_md

# Store the initial value of widgets in session state
if "visibility" not in st.session_state:
    st.session_state.visibility = "visible"
    st.session_state.disabled = False

#nlp = en_core_web_lg.load()
nlp = spacy.load("en_ner_bc5cdr_md")

st.set_page_config(layout='wide')
st.title('Clinical Note Summarization')
st.sidebar.markdown('Using transformer model')

## Loading in dataset
#df = pd.read_csv('mtsamples_small.csv',index_col=0)
df = pd.read_csv('shpi_w_rouge21Nov.csv')

#Renaming column
df.rename(columns={'SUBJECT_ID':'Patient_ID',
                  'HADM_ID':'Admission_ID',
                  'hpi_input_text':'Original_Text',
                  'hpi_reference_summary':'Reference_text'}, inplace = True)
 
 #data.rename(columns={'gdp':'log(gdp)'}, inplace=True)

#Filter selection 
st.sidebar.header("Search for Patient:")

patientid = df['Patient_ID']
patient = st.sidebar.selectbox('Select Patient ID:', patientid)
admissionid = df['Admission_ID'].loc[df['Patient_ID'] == patient]
HospitalAdmission = st.sidebar.selectbox('', admissionid) 

# List of Model available
model = st.sidebar.selectbox('Select Model', ('BertSummarizer','BertGPT2','t5seq2eq','t5','gensim','pysummarizer'))

col3,col4 = st.columns(2) 
patientid = col3.write(f"Patient ID:  {patient} ")
admissionid =col4.write(f"Admission ID:  {HospitalAdmission} ")
    
col1, col2 = st.columns(2)
#_min_length = col1.number_input("Minimum Length", value=_min_length)
#_max_length = col2.number_input("Maximun Length", value=_max_length)
##_early_stopping = col3.number_input("early_stopping", value=_early_stopping)

#text = st.text_area('Input Clinical Note here')

# Query out relevant Clinical notes
original_text =  df.query(
    "Patient_ID  == @patient & Admission_ID == @HospitalAdmission"
)

original_text2 = original_text['Original_Text'].values

runtext =st.text_area('Input Clinical Note here:', str(original_text2), height=300)

reference_text = original_text['Reference_text'].values

def run_model(input_text):

    if model == "BertSummarizer":
        output = original_text['BertSummarizer'].values
        st.write('Summary')
        st.success(output[0])

    elif model == "BertGPT2":
        output = original_text['BertGPT2'].values
        st.write('Summary')
        st.success(output[0])
        
      
    elif model == "t5seq2eq": 
        output = original_text['t5seq2eq'].values
        st.write('Summary')
        st.success(output)
        
    elif model == "t5":
        output = original_text['t5'].values
        st.write('Summary')
        st.success(output)
        
    elif model == "gensim": 
        output = original_text['gensim'].values
        st.write('Summary')
        st.success(output)
        
    elif model == "pysummarizer": 
        output = original_text['pysummarizer'].values
        st.write('Summary')
        st.success(output)

col1, col2 = st.columns([1,1])

with col1:
    st.button('Summarize')
    run_model(runtext)
    sentences=runtext.split('.')
    st.text_area('Reference text', str(reference_text),label_visibility="hidden")
with col2:
    st.button('NER')
    doc = nlp(str(original_text2))
    colors = { "DISEASE": "pink","CHEMICAL": "orange"}
    options = {"ents": [ "DISEASE", "CHEMICAL"],"colors": colors}
    ent_html = displacy.render(doc, style="ent", options=options)
    st.markdown(ent_html, unsafe_allow_html=True)