import streamlit as st
import streamlit.components as components 
from annotated_text import annotated_text, annotation
from htbuilder import h3
import pandas as pd
import numpy as np
from math import ceil
from collections import Counter
from string import punctuation
import spacy
from negspacy.negation import Negex
from spacy import displacy
from spacy.lang.en import English
from spacy.matcher import PhraseMatcher
from spacy.tokens import Span
#import en_ner_bc5cdr_md
import re
from streamlit.components.v1 import html
import pickle
from functools import reduce
import operator
import itertools
from itertools import chain
from collections import Counter
from collections import OrderedDict

### ========== Loading Dataset ==========
## ======== Loading dataset ========
## Loading in Admission Dataset
##   df  = Admission 
##   df2 = Admission Chief Complaint and Diagnosis 
##   df3 = Discharge History 
##   df4 = Daily Narrative
# #=================================
nlp = spacy.load("en_ner_bc5cdr_md")

df = pd.read_csv('shpi25nov.csv')
df.sort_values(by='SUBJECT_ID',ascending = True, inplace=True)

df2 = pd.read_csv('cohort_cc_adm_diag.csv')

df3 = pd.read_csv('cohort_past_history_12072022.csv')
df3.sort_values(by='CHARTDATE',ascending = False, inplace=True)

df4 = pd.read_csv('24houreventsFulltextwdifference.csv')
#df4.sort_values(by=['hadmid','DATETIME'],ascending = True, inplace=True)

# Loading in Daily Narrative - refreshed full 24 hr text
df5 = pd.read_csv('24hourevents10Jan.csv')
df5.sort_values(by=['hadmid','DATETIME'],ascending = True, inplace=True)

#Append the updated 24 hr text and changes column 
df5.rename(columns={'hadmid':'HADM_ID',
                   'DATETIME':'STORETIME'}, inplace = True) 
df4 = pd.merge(df4[['HADM_ID','DESCRIPTION','SUBJECT_ID','CHARTTIME','STORETIME','CGID','TEXT','checks','_24_Hour_Events','Full_24_Hour_Events']],df5[['HADM_ID','STORETIME','full_24 Hour Events:','24 Hour Events:']], on = ['HADM_ID','STORETIME'], how = 'left')

hr24event_pattern = re.compile('((24 Hour Events):\\n(?s).*?Allergies:)')

#there are some records with full_24 Hour Events: null, hence replaced these text with the extracted text from the progress note
df4['hr24event_extracted'] = ''
for (idx, row) in df4.iterrows():
    try:
        text = df4['TEXT'][idx]
        df4['hr24event_extracted'][idx] = re.findall(hr24event_pattern,text)
        df4['hr24event_extracted'][idx] = [x for x in chain.from_iterable(df4['hr24event_extracted'][idx])]
    except:
        df4['hr24event_extracted'][idx] = ''

df4 = df4.reset_index(drop=True)
df4['hr24event_extracted'] = df4['hr24event_extracted'].apply(' '.join)
df4['hr24event_extracted'] = df4['hr24event_extracted'].str.replace('\s+[a-z]+:\\n', ' ')
df4['hr24event_extracted'] = df4['hr24event_extracted'].str.replace('24 Hour Events:|24 Hour Events|Allergies:', '')
df4['hr24event_extracted'] = df4['hr24event_extracted'].str.replace('\s+', ' ')
df4['hr24event_extracted'] = df4['hr24event_extracted'].str.replace('\.\s+\.', '.')
df4['hr24event_extracted'] = df4['hr24event_extracted'].replace(r"^ +| +$", r"", regex=True)

df4.loc[df4['full_24 Hour Events:'].isnull(),'full_24 Hour Events:'] = df4['hr24event_extracted']
df4.loc[df4['24 Hour Events:'].isnull(),'24 Hour Events:'] = df4['_24_Hour_Events']

# combining both data into one 
df = pd.merge(df, df2, on=['HADM_ID','SUBJECT_ID'])
# Deleting admission chief complaint and diagnosis after combining
del df2

# Remove decimal point from Admission ID and format words 
df['HADM_ID'] = df['HADM_ID'].astype(str).apply(lambda x: x.replace('.0',''))
df3['HADM_ID'] = df3['HADM_ID'].astype(str).apply(lambda x: x.replace('.0',''))
df4['HADM_ID'] = df4['HADM_ID'].astype(str).apply(lambda x: x.replace('.0',''))
df3['INDEX_HADM_ID'] = df3['INDEX_HADM_ID'].astype(str).apply(lambda x: x.replace('.0',''))
df3["CHARTDATE_HADM_ID"] = df3["CHARTDATE"].astype(str) +' ('+ df3["HADM_ID"] +')'
df3["DIAGNOSIS"] = df3["DIAGNOSIS"].str.capitalize()
df3["DISCHARGE_LOCATION"] = df3["DISCHARGE_LOCATION"].str.capitalize()

df3["Diagnosis_Description"] =df3["Diagnosis_Description"].replace(r'\n','  \n ', regex=True)
df3["TEXT"] =df3["TEXT"].replace(r'\n','  \n ', regex=True)
df3["TEXT"] =df3["TEXT"].replace(r'#',' ', regex=True) 
df3["BertSummarizer"] =df3["BertSummarizer"].replace(r'#',' ', regex=True) 


#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)
df3.rename(columns={'SUBJECT_ID':'Patient_ID',
                   'HADM_ID':'PAST_Admission_ID',
                   'INDEX_HADM_ID':'Admission_ID'}, inplace = True) 

df4.rename(columns={'HADM_ID':'Admission_ID',
                   'full_24 Hour Events:':'Full Text',
                   '24 Hour Events:':'Change_Note',
                   'past_24 Hour Events:':'Past_Change_Note'}, inplace = True)
                   
df4["Full Text"] =df4["Full Text"].replace('["[','').replace(']"]','')

## ========== Setting up Streamlit Sidebar ==========
st.set_page_config(page_title ='Patient Inpatient Progression Dashboard', 
                   #page_icon= "Notes",
                   layout='wide')
st.title('Patient Inpatient Progression Dashboard')
st.markdown(
    """
    <style>
    [data-testid="stSidebar"][aria-expanded="true"] > div:first-child {
        width: 400px;
    }
    [data-testid="stSidebar"][aria-expanded="false"] > div:first-child {
        width: 400px;
        margin-left: -230px;
    }
    </style>
    """,
    unsafe_allow_html=True,
)
st.sidebar.markdown('Using transformer model')

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

# ===== Initial filter for patient and admission id =====
patientid = df['Patient_ID'].unique()
patient = st.sidebar.selectbox('Select Patient ID:', patientid)    #Filter Patient
admissionid = df['Admission_ID'].loc[df['Patient_ID'] == patient]  #Filter available Admission id for patient
HospitalAdmission = st.sidebar.selectbox(' ', admissionid)   
pastHistoryEpDate = df3['CHARTDATE_HADM_ID'].loc[(df3['Patient_ID'] == patient) & (df3['Admission_ID']== HospitalAdmission)] 
countOfAdmission = len(pastHistoryEpDate)

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

original_text =  df.query(
    "Patient_ID  == @patient & Admission_ID == @HospitalAdmission"
)

original_text2 = original_text['Original_Text'].values
AdmissionChiefCom = original_text['Admission_Chief_Complaint'].values
diagnosis =original_text['DIAGNOSIS'].values
reference_text = original_text['Reference_text'].values
dailyNoteChange =df4[['STORETIME','Change_Note','Full Text']].loc[(df4['Admission_ID']==HospitalAdmission) & df4['_24_Hour_Events'].notnull()]

dailyNoteFull =df4[['STORETIME','Change_Note','Full Text']].loc[(df4['Admission_ID']==HospitalAdmission) & df4['_24_Hour_Events'].notnull()]
                        
dailyNoteChange.rename(columns={'STORETIME':'Time of Record',
                   'Change_Note':'Note Changes'}, inplace = True) 

#dailyNoteChange['Time of Record'] =  pd.to_datetime(dailyNoteChange['Time of Record'])

dailyNoteChange['TimeDiff'] = pd.to_datetime(dailyNoteChange["Time of Record"], format='%Y/%m/%d %H:%M')
#dailyNoteChange['TimeDiff'] = pd.to_datetime(dailyNoteChange["Time of Record"], format='%d/%m/%Y %H:%M')
dailyNoteChange['TimeDiff'] = dailyNoteChange['TimeDiff'] -dailyNoteChange['TimeDiff'].shift()
dailyNoteChange['TimeDiff'] = dailyNoteChange['TimeDiff'].fillna(pd.Timedelta(seconds=0))
dailyNoteChange['TimeDiff']= dailyNoteChange['TimeDiff'].dt.total_seconds().div(60).astype(int)
dailyNoteChange['Hour'] = dailyNoteChange['TimeDiff'] // 60
dailyNoteChange['Mins'] = dailyNoteChange['TimeDiff']- dailyNoteChange['Hour'] * 60
dailyNoteChange["TimeDiff"] = dailyNoteChange['Hour'].astype(str) + " hours " + dailyNoteChange['Mins'].astype(str) + " Mins"
del dailyNoteChange['Hour']
del dailyNoteChange['Mins']

dailyNoteChange["PreviousRecord"] = dailyNoteChange["Time of Record"].shift()

dailyNoteChange.sort_values(by=['Time of Record'],ascending = False, inplace=True)

dailyNoteFull.rename(columns={'STORETIME':'Time of Record',
                   'Change_Note':'Note Changes'}, inplace = True) 

dailyNote = df4['Full Text'].loc[(df4['Admission_ID']==HospitalAdmission)]
dailyNote = dailyNote.unique()

try:
    mindate = min(dailyNoteFull['Time of Record'])
except:
    mindate = ''

# ===== to display selected patient and admission id on main page
col3,col4 = st.columns(2) 
patientid = col3.write(f"Patient ID:  {patient} ")
admissionid =col4.write(f"Admission ID:  {HospitalAdmission} ")

##========= Buttons to the 3 tabs ======== Temp disabled Discharge Plan and Social Notes 
col1, col2, col3 = st.columns([1,1,1])
#col6, col7 =st.columns([2,2])
with st.container():
    with col1:
        btnAdmission = st.button("🏥 Admission")
    with col2:
        btnDailyNarrative = st.button('📆Daily Narrative')
    with col3:
        btnPastHistory = st.button('📇Past History (6 Mths)')


##======================== Start of NER Tagging ========================
                 
#lemmatizing the notes to capture all forms of negation(e.g., deny: denies, denying)
def lemmatize(note, nlp):
    doc = nlp(note)
    lemNote = [wd.lemma_ for wd in doc]
    return " ".join(lemNote)

#function to modify options for displacy NER visualization
def get_entity_options():
    entities = ["DISEASE", "CHEMICAL", "NEG_ENTITY"]
    colors = {'DISEASE': 'pink', 'CHEMICAL': 'orange', "NEG_ENTITY":'white'}
    options = {"ents": entities, "colors": colors}    
    return options

#adding a new pipeline component to identify negation
def neg_model():
    nlp.add_pipe('sentencizer')
    nlp.add_pipe(
    "negex",
    config={
        "chunk_prefix": ["no"],
    },
    last=True)
    return nlp

def negation_handling(note, neg_model):
    results = []
    nlp = neg_model() 
    note = note.split(".") #sentence tokenizing based on delimeter 
    note = [n.strip() for n in note] #removing extra spaces at the begining and end of sentence
    for t in note:
        doc = nlp(t)
        for e in doc.ents:
            rs = str(e._.negex)
            if rs == "True": 
                results.append(e.text)
    return results

#function to identify span objects of matched negative phrases from text
def match(nlp,terms,label):
    patterns = [nlp.make_doc(text) for text in terms]
    matcher = PhraseMatcher(nlp.vocab)
    matcher.add(label, None, *patterns)
    return matcher

#replacing the labels for identified negative entities
def overwrite_ent_lbl(matcher, doc):
    matches = matcher(doc)
    seen_tokens = set()
    new_entities = []
    entities = doc.ents
    for match_id, start, end in matches:
        if start not in seen_tokens and end - 1 not in seen_tokens:
            new_entities.append(Span(doc, start, end, label=match_id))
            entities = [e for e in entities if not (e.start < end and e.end > start)]
            seen_tokens.update(range(start, end))
    doc.ents = tuple(entities) + tuple(new_entities)
    return doc

#deduplicate repeated entities 
def dedupe(items):
    seen = set()
    for item in items:
        item = str(item).strip()
        if item not in seen:
            yield item
            seen.add(item)
     
 ##======================== End of NER Tagging ========================


def run_model(input_text):    
    if model == "BertSummarizer":
        output = original_text['BertSummarizer2s'].values
        st.write('Summary')

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


    
    st.success(output)
    
def Admission():

    with st.container():
        
        runtext =st.text_area('History of presenting illnesses at admission', str(original_text2)[1:-1], height=300)  
        lem_clinical_note= lemmatize(runtext, nlp)
        #creating a doc object using BC5CDR model
        doc = nlp(lem_clinical_note)
        options = get_entity_options()

        #list of negative concepts from clinical note identified by negspacy
        results0 = negation_handling(lem_clinical_note, neg_model)

        matcher = match(nlp, results0,"NEG_ENTITY")

        #doc0: new doc object with added "NEG_ENTITY label"
        doc0 = overwrite_ent_lbl(matcher,doc)

        #visualizing identified Named Entities in clinical input text 
        ent_html = displacy.render(doc0, style='ent', options=options)
    
    col1, col2 = st.columns([1,1])      
    with st.container():
        with col1:
            st.button('Summarize')
            run_model(runtext)

        with col2:
            st.button('NER')
            # ===== Adding the Disease/Chemical into a list =====    
            problem_entities = list(dedupe([t for t in doc0.ents if t.label_ == 'DISEASE']))
            medication_entities = list(dedupe([t for t in doc0.ents if t.label_ == 'CHEMICAL']))
            st.markdown('**CHIEF COMPLAINT:**')
            st.write(str(AdmissionChiefCom)[1:-1])
            st.markdown('**ADMISSION DIAGNOSIS:**')
            st.markdown(str(diagnosis)[1:-1].capitalize())
            st.markdown('**PROBLEM/ISSUE**')
            #st.markdown(problem_entities)
            st.markdown(f'<p style="background-color:PINK;color:#080808;font-size:16px;">{str(problem_entities)[1:-1]}</p>', unsafe_allow_html=True)
            #genEntities(trans_df, 'DISEASE')
            st.markdown('**MEDICATION**')
            st.markdown(f'<p style="background-color:orange;color:#080808;font-size:16px;">{str(medication_entities)[1:-1]}</p>', unsafe_allow_html=True)
            #genEntities(trans_df, 'CHEMICAL')
            #st.table(trans_df)   
            st.markdown('**NER**')
            with st.expander("See NER Details"):
                st.markdown(ent_html, unsafe_allow_html=True)

alphabets= "([A-Za-z])"
prefixes = "(mr|st|mrs|ms|dr)[.]"
suffixes = "(inc|ltd|jr|sr|co)"
starters = "(mr|mrs|ms|dr|he\s|she\s|it\s|they\s|their\s|our\s|we\s|but\s|however\s|that\s|this\s|wherever)"
acronyms = "([A-Z][.][A-Z][.](?:[A-Z][.])?)"
websites = "[.](com|net|org|io|gov)"
digits = "([0-9])"

def split_into_sentences(text):
#     text = str(text)
    text = " " + text + "  "
    text = text.replace("\n"," ")
#     text = text.replace("[0-9]{4}-[0-9]{1,2}-[0-9]{1,2} [0-9]{2}:[0-9]{2}:[0-9]{2}"," ")
    text = re.sub(prefixes,"\\1<prd>",text)
    text = re.sub(websites,"<prd>\\1",text)
    text = re.sub(digits + "[.]" + digits,"\\1<prd>\\2",text)
    if "..." in text: text = text.replace("...","<prd><prd><prd>")
    if "Ph.D" in text: text = text.replace("Ph.D.","Ph<prd>D<prd>")
    text = re.sub("\s" + alphabets + "[.] "," \\1<prd> ",text)
    text = re.sub(acronyms+" "+starters,"\\1<stop> \\2",text)
    text = re.sub(alphabets + "[.]" + alphabets + "[.]" + alphabets + "[.]","\\1<prd>\\2<prd>\\3<prd>",text)
    text = re.sub(alphabets + "[.]" + alphabets + "[.]","\\1<prd>\\2<prd>",text)
    text = re.sub(" "+suffixes+"[.] "+starters," \\1<stop> \\2",text)
    text = re.sub(" "+suffixes+"[.]"," \\1<prd>",text)
    text = re.sub(" " + alphabets + "[.]"," \\1<prd>",text)
    if "”" in text: text = text.replace(".”","”.")
    if "\"" in text: text = text.replace(".\"","\".")
    if "!" in text: text = text.replace("!\"","\"!")
    if "?" in text: text = text.replace("?\"","\"?")
    text = text.replace(".",".<stop>")
    text = text.replace("?","?<stop>")
    text = text.replace("!","!<stop>")
    text = text.replace("[0-9]{2}:[0-9]{2}:[0-9]{2}:","[0-9]{2}:[0-9]{2}:[0-9]{2}:<stop>")
    text = text.replace("[0-9]{4}-[0-9]{1,2}-[0-9]{1,2}\s[0-9]{2}:[0-9]{2}:[0-9]{2}","[0-9]{4}-[0-9]{1,2}-[0-9]{1,2}\s[0-9]{2}:[0-9]{2}:[0-9]{2}<stop>")
    # text = text.replace("-","-<stop>")
#     text = text.replace("- -","- -<stop>")
    text = text.replace("<br><br>","<stop><br><br>")
    text = text.replace("<prd>",".")
    sentences = text.split("<stop>")
#     sentences = text.split('-')
#     sentences = sentences[:-1]
    sentences = [s.strip() for s in sentences]
    return sentences

def DailyNarrative():
    with st.container(): 
        dailyNarrativeTime= st.selectbox('',dailyNoteChange['Time of Record'])
        
        if df4[['Change_Note']].loc[(df4['Admission_ID']==HospitalAdmission) & (df4['STORETIME'] == dailyNarrativeTime)].size != 0:
            changeNote = df4[['Change_Note']].loc[(df4['Admission_ID']==HospitalAdmission) & (df4['STORETIME'] == dailyNarrativeTime)].values[0]
        else: 
            changeNote = 'No records'

        
        if dailyNoteChange['TimeDiff'].loc[(dailyNoteChange['Time of Record']==dailyNarrativeTime)].empty: 
            changeNoteTime = 'No records'
            previousRecord = ' '
        else:
            changeNoteTime =dailyNoteChange['TimeDiff'].loc[(dailyNoteChange['Time of Record']==dailyNarrativeTime)].values[0]
            previousRecord =dailyNoteChange['PreviousRecord'].loc[(dailyNoteChange['Time of Record']==dailyNarrativeTime)].values[0]
        
        if dailyNarrativeTime == mindate:
            changeNote = 'Nil'    
        else:
            changeNote = str(changeNote).replace('["[','').replace(']"]','').replace("'","").replace('"','').replace(',','').replace('\\','').replace('[','').replace(']','').replace('\\','')
            changeNote = changeNote.strip("[-,]").strip("")
            changeNote = ' '.join(changeNote.split())
        # changeNote_split = re.split(r'(?<=[^A-Z].[.?]) +(?=[A-Z])|-', changeNote)
        # changeNote_split = [x.strip(' ') for x in changeNote_split]
        
        changeNote_split = split_into_sentences(changeNote)
        changeNote_split = [x for x in changeNote_split if x]

        latestRecord = dailyNoteChange['Time of Record'].max()
        st.markdown('Changes: ' + changeNote)
        st.markdown('Changes recorded from previous record at ' + str(previousRecord) + ' ,  ' + str(changeNoteTime) + ' ago') 
            
        if df4[['Full Text']].loc[(df4['Admission_ID']==HospitalAdmission) & (df4['STORETIME'] == dailyNarrativeTime)].empty:
            dailyNarrativeText = 'No Records' 
        else:  
            dailyNoteChange.sort_values(by='Time of Record',ascending = True, inplace=True)
            dailyNoteChange["Combined"] = ''
            count = 0 
            text ='' 
            for index, row in dailyNoteChange.iterrows():
                text =  '[**' + str(row['Time of Record']) + '**]' + ':<stop> ' + row['Full Text'] + '<br>' + '<br>' +  text  
                dailyNoteChange['Combined'].iloc[count] = text
                count = count + 1
            dailyNarrativeText =dailyNoteChange[['Combined']].loc[(dailyNoteChange['Time of Record'] == dailyNarrativeTime)].values[0]
            #dailyNarrativeText =df4[['Full Text']].loc[(df4['Admission_ID']==HospitalAdmission) & (df4['DATETIME'] == dailyNarrativeTime)].values[0]
            
        
        dailyNarrativeText = str(dailyNarrativeText).replace('["[','').replace(']"]','').replace("'","").replace(',','').replace('"','').replace('[','').replace(']','').replace('\\','')
        dailyNarrativeText = dailyNarrativeText.strip("[-,]").strip(" ")
        dailyNarrativeText = ' '.join(dailyNarrativeText.split())
        # dailyNarrativeText_split = re.split(r'(?<=[^A-Z].[.?]) +(?=[A-Z])|-|<br><br>', dailyNarrativeText)
        # dailyNarrativeText_split = [x.strip(' ') for x in dailyNarrativeText_split]
        
        dailyNarrativeText_split = split_into_sentences(dailyNarrativeText)
        
        #st.table(dailyNoteChange)  # testing to see if data calculate correctly 
        
        annt_ls = []
        for sent in dailyNarrativeText_split:
            if '<br><br>' in sent:
                break    # one item didn't complete the condition, get out of this loop
            else:
                end_index = dailyNarrativeText_split.index(sent) + 1
                annt_ls.append(sent)
        
        non_annt_ls = dailyNarrativeText_split[end_index:]
        
        with st.expander("See in detail"):

                             
                ls = []

                for sent in annt_ls:
                    if sent in changeNote_split:
                        sent = sent.replace(str(sent),str(annotation(sent)))
                        ls.append(sent)
                    else:
                        ls.append(sent)
                        
                ls2 = ls + non_annt_ls
                highlight = ' '.join(ls2)
                st.markdown(highlight, unsafe_allow_html=True)

            

def PastHistory(): 
    col6, col7 =st.columns([2,2])
    with st.container(): 
        with col6: 

            st.markdown('**No. of admission past 6 months:**')
            st.markdown(countOfAdmission)
       
        with col7:
            #st.date_input('Select Admission Date') # To replace with a dropdown filter instead 
            #st.selectbox('Past Episodes',pastHistoryEp)
            pastHistory = st.selectbox('Select Past History Admission', pastHistoryEpDate, format_func=lambda x: 'Select an option' if x == '' else x)        
    
    historyAdmission =  df3.query(
                "Patient_ID  == @patient & CHARTDATE_HADM_ID == @pastHistory"
                )
    
   
    if historyAdmission.shape[0] == 0:
        runtext = "No past episodes" 
    else: 
        #runtext = historyAdmission['hospital_course_processed'].values[0]
        runtext = historyAdmission['hospital_course_processed'].values[0]
    
    lem_clinical_note= lemmatize(runtext, nlp)
    #creating a doc object using BC5CDR model
    doc = nlp(lem_clinical_note)
    options = get_entity_options()

    #list of negative concepts from clinical note identified by negspacy
    results0 = negation_handling(lem_clinical_note, neg_model)

    matcher = match(nlp, results0,"NEG_ENTITY")

    #doc0: new doc object with added "NEG_ENTITY label"
    doc0 = overwrite_ent_lbl(matcher,doc)

    #visualizing identified Named Entities in clinical input text 
    ent_html = displacy.render(doc0, style='ent', options=options)
    
# ===== Adding the Disease/Chemical into a list =====    
    problem_entities = list(dedupe([t for t in doc0.ents if t.label_ == 'DISEASE']))
    medication_entities = list(dedupe([t for t in doc0.ents if t.label_ == 'CHEMICAL']))
    if historyAdmission.shape[0] == 0:
        st.markdown('Admission Date: NA')
        st.markdown('Date of Discharge: NA') 
        st.markdown('Days from current admission: NA')
    else: 
        st.markdown('Admission Date: ' + historyAdmission['ADMITTIME'].values[0])
        st.markdown('Date of Discharge: ' + historyAdmission['DISCHTIME'].values[0])
        st.markdown('Days from current admission: ' + str(historyAdmission['days_from_index'].values[0]) +' days')

    #st.markdown('Summary: ')
    st.markdown(f'<p style="color:#080808;font-size:16px;"><b>Summary: </b></p>', unsafe_allow_html=True)
    
              
    if model == "BertSummarizer":
        if historyAdmission.shape[0] == 0:
            st.markdown('NA')
        else: 
            st.markdown(str(historyAdmission['BertSummarizer'].values[0]))
    elif model == "t5seq2eq":
        if historyAdmission.shape[0] == 0:
            st.markdown('NA')
        else: 
            st.markdown(str(historyAdmission['t5seq2eq'].values[0]))     
    st.markdown(f'<p style="color:#080808;font-size:16px;"><b>Diagnosis: </b></p>', unsafe_allow_html=True)
    
    if historyAdmission.shape[0] == 0:
        st.markdown('NA')
    else:
        st.markdown(str(historyAdmission['Diagnosis_Description'].values[0]))
        st.markdown('**PROBLEM/ISSUE**')
        st.markdown(f'<p style="background-color:PINK;color:#080808;font-size:16px;">{str(problem_entities)[1:-1]}</p>', unsafe_allow_html=True)
        st.markdown('**MEDICATION**')
        st.markdown(f'<p style="background-color:orange;color:#080808;font-size:16px;">{str(medication_entities)[1:-1]}</p>', unsafe_allow_html=True)        
        st.markdown('Discharge Disposition: ' + str(historyAdmission['DISCHARGE_LOCATION'].values[0]))
        with st.expander('Full Discharge Summary'):
                #st.write("line 1  \n  line 2  \n line 3")
                fulldischargesummary = historyAdmission['TEXT'].values[0]
                st.write(fulldischargesummary)

if "load_state" not in st.session_state: 
    st.session_state.load_state = False

if "button_clicked" not in st.session_state: 
    st.session_state.button_clicked = False

if "admission_button_clicked" not in st.session_state: 
    st.session_state.admission_button_clicked = False
    
if "daily_button_clicked" not in st.session_state: 
    st.session_state.daily_button_clicked = False

if "past_button_clicked" not in st.session_state: 
    st.session_state.past_button_clicked = False
    
    

if btnAdmission or st.session_state["admission_button_clicked"] and not btnDailyNarrative and not btnPastHistory:
    st.session_state["admission_button_clicked"] =  True
    st.session_state["daily_button_clicked"] =  False
    st.session_state["past_button_clicked"] =  False
    Admission()
    
if btnDailyNarrative or st.session_state["daily_button_clicked"] and not btnAdmission and not btnPastHistory:
    st.session_state["daily_button_clicked"] =  True
    st.session_state["admission_button_clicked"] =  False
    st.session_state["past_button_clicked"] =  False
    DailyNarrative()

    
if btnPastHistory or st.session_state["past_button_clicked"] and not btnDailyNarrative and not btnAdmission:
    st.session_state["past_button_clicked"] =  True
    st.session_state["admission_button_clicked"] =  False
    st.session_state["daily_button_clicked"] =  False
    PastHistory()