HEALTHCARE CHATBOT

Submitted by

SUDARSHAN SAKHARE
VISHAL KADU
ABHIJEET KAMBLE
OM VHARE

BTech.
(Computer Science & Engineering)

Guided by
Prof. Hadiya Hashmi

Department of Computer Science & Engineering

People’s Education Society’s

P.E.S. College of Engineering, Aurangabad

(2023- 2024)
 Project Approval Sheet

SUDARSHAN SAKHARE
Prn_Number: T2021341242053

VISHAL KADU
Prn_Number: T2021341242063

ABHIJEET KAMBLE
Prn_Number: T2021341242065

OM VHARE
Prn_Number: T2021341242065

have done the appropriate work related to “ HEALTHCARE CHATBOT ” in partial

fulfilment in the academic year 2023-24 for B.Tech (Computer Science & Engineering) of
Dr. Babasaheb Ambedkar Marathwada Technological University, Lonere is being submitted
to P. E.S. College of Engineering, Aurangabad (M.S.).

Internal Examiner: (Hadiya Hashmi)

External Examiner

Date:22-11-2023

Place: P.E.S. College of Engineering, Aurangabad.

 CERTIFICATE
This is to certify that, The Project “HEALTHCARE CHATBOT”

submitted by

SUDARSHAN SAKHARE(47)
VISHAL KADU(57)
ABHIJEET KAMBLE(06)
OM VHARE(29)
has successfully submitted project under my supervision and guidance in partial fulfilment in
B.Tech in Computer Science & Engineering and in the academic year 2023- 24 of Dr.
Babasaheb Ambedkar Marathwada Technological University, Lonere and is being submitted to
P. E.S. College of Engineering, Aurangabad (M.S.).

Place : Aurangabad
Date :

Prof .Hadiya Hashmi Dr.V.B.Kamble

Guide Head
Department of
Computer science & engineering

Principal
P. E. S. College of Engineering
Aurangabad
 TABLE OF CONTENTS
List of Abbreviation I
List of figures II

1 INTRODUCTION 1-3
1.1 Introduction 1
1.2 Healthcare Chatbot 2-3
2 LITERATURE SURVEY 4-5
2.1 Literature Survey Table 4
3 SOFTWARE REQUIREMENT SPECIFICATION 6-8
3.1 General Requirements 6
3.2 Invariant Requirements 7
3.3 Modelling Requirements 8
4 SYSTEM DEVLOPMENT 9-18
4.1 Data Flow Diagram 9
4.1.1 Level 0 10
4.1.2 Level 1 11
4.2 ER Diagram 12
4.3 UML Diagram 13
4.3.1 Sequence Diagram 14
4.3.2 Use Case Diagram 15-16
4.3.3 Activity Diagram 17-18
5 PROPOSED WOK 19-32
 Coding 21-30
 Output Photos 31-32
6 PERFORMANCE ANALYSIS 33-34
7 CONCLUSION AND FUTURE SCOPE 35-36
7.1 Conclusion 35
7.2 Future Scope 36
8 REFRENCES
9 ACKNOWLEDGEMENT

List of Abbrivations
Abbreviations Explanation

EHR Electronic Health Record

PHR Personal Health Record

HIS Health Information System

EMR Electronic Medical Record

HIPAA Health Insurance Portability and

Accountability Act
NLP Natural Language Processing

ML Machine Learning

AI Artificial Intelligence

HCI Human Computer Interaction

UX User Experience

UI User Interface

List Of Figures
1. Data flow diagram
2. ER Diagram
2.1 Level 0
2.2 Level 1
3. UML Diagram
4. Sequence Diagram
5. Use Case Diagram
6. Activity Diagram
 ABSTRACT
Healthcare is very important to lead a good life. However, it is very difficult to obtain the
consultation with the doctor for every health problem. The idea is to create a medical
chatbot using Artificial Intelligence that can diagnose the disease and provide basic details
about the disease before consulting a doctor.

This will help to reduce healthcare costs and improve accessibility to medical knowledge
through medical chatbot. The chatbots are computer programs that use natural language to
interact with users. The chatbot stores the data in the database to identify the sentence
keywords and to make a query decision and answer the question.

Ranking and sentence similarity calculation is performed using n-gram, TFIDF and cosine
similarity. The score will be obtained for each sentence from the given input sentence and
more similar sentences will be obtained for the query given. The third party, the expert
program, handles the question presented to the bot that is not understood or is not present
in the database.
 SYNOPSIS

1. TITLE OF THE PROJECT:

Healthcare Chatbot
2. OBJECTIVE OF THE PROJECT: Our project focuses on providing the
users immediate and accurate prediction of the diseases based on their symptoms
3. PROJECT CATEGORY:
Artificial Intelligence / Machine Learning

4. LANGUAGE & SOFTWARE TOOLS USED:

Front End: Python
Operating System: Windows 10

5. STRUCTURE OF PROJECT:
Conversation manager: It is the module that decides the flow of the conversation or
the answers to what the user asks or requests. Basically this is the central element that
defines the conversation, the personality, the style and what the chatbot is basically
capable of offering.
6. FUTURE SCOPE:
The future scope of the healthcare chatbots is incredibly promising.Here are some key
areas where they can make a significant impact :

(1) Enhanced Patient Support

(2) Remote Monitoring and Telemedicine
(3) Health Education and informatio
1.INTRODUCTION

1.1 Introduction
A healthcare chatbot is an AI-powered virtual assistant specifically designed for the
healthcare industry. It leverages natural language processing and machine learning algorithms
to interact with users, provide information, and offer support related to various health
concerns.

The main objective of a healthcare chatbot is to improve patient experience, accessibility, and
engagement. It can assist patients in several ways, such as symptom assessment, self-care
guidance, medication reminders, appointment scheduling, and even emotional support.

One of the key advantages of a healthcare chatbot is its availability 24/7. It can
provide immediate responses to users' queries, reducing the need for waiting times or
unnecessary visits to healthcare providers. This convenience allows individuals to access
healthcare information and support at their own pace and from the comfort of their homes.

To ensure accuracy and reliability, healthcare chatbots are trained on vast amounts of medical
data and guidelines. They continuously learn and improve their responses based on user
interactions and feedback.

Additionally, healthcare chatbots can integrate with wearable devices and IoT technologies to
gather real-time health data. This integration enables personalized recommendations, remote
monitoring of health conditions, and timely interventions.

Overall, healthcare chatbots have the potential to transform the healthcare landscape
by enhancing patient care, empowering individuals to make informed decisions, and
optimizing healthcare resources.

1
1.2 Healthcare Chatbot
Healthcare chatbots are intelligent virtual assistants that use artificial intelligence and natural
language processing to interact with users and provide healthcare-related support. These
chatbots are designed to understand and respond to user queries, offer medical information,
and even assist in self-diagnosis.

One of the key features of healthcare chatbots is their ability to perform symptom assessment.
By asking users a series of questions, they can analyze symptoms and provide potential
diagnoses or recommend appropriate next steps, such as seeking medical attention or
providing self-care advice.

Healthcare chatbots can also offer personalized health support. They can provide
information about medications, dosages, and potential side effects, as well as offer reminders
for taking medications on time.

Appointment scheduling is another valuable feature of healthcare chatbots. They can help
users find available time slots with healthcare providers, book appointments, and even send
reminders leading up to the scheduled date.

Moreover, healthcare chatbots can provide general health tips, lifestyle

recommendations, and guidance for managing chronic conditions. They can promote healthy
habits, offer mental health support, and provide information about various medical
conditions.

To ensure accuracy and reliability, healthcare chatbots are typically built using extensive
medical databases, guidelines, and research. They continuously learn and improve their
responses through user interactions, feedback, and updates from medical professionals.

It's important to note that while healthcare chatbots can be valuable tools, they should not
replace the expertise and guidance of healthcare professionals. They are designed to
complement and enhance the healthcare experience by providing accessible and convenient
support.

Currently artificial intelligence has developed to a point where programs can learn and
effectively mimic human conversations. Accelerating technological progress has placed
internet-enabled machines in every institution, company, home, and eventually pocket (who
doesn’t have a smartphone nowadays?).

2
In this environment, chatbots have become increasingly popular as useful tools for companies
and institutions. One of the best known examples of chatbots in recent history is Siri – the AI
assistant that is part of Apple's standard software for its products. Siri took chatbots mainstream
in 2011.
Since then brands in every industry have started to use them, eventually sparking a new trend
– conversational UX. This refers to a User Experience in which your interaction with a
company or service is automated based on your prior behavior (like working together with
someone who is getting to know you).
If you're a programmer, you can take advantage of software like Alexa, which enables the use
of voice to control devices.
The use of chatbots has spread from consumer customer service to matters of life and death.
Chatbots are entering the healthcare industry and can help solve many of its problems.

Health and fitness chatbots have begun to attract a market. Last year Facebook has started
allowing companies to create Messenger chatbots to communicate with users. A great example
is HealthTap – the first company to release a health bot on the Messenger app. It allows users
to ask medical questions and receive answers from doctors.
Currently, there are dozens of health and fitness chatbots available online. Fitness bots
dominate this category, but there are plenty of medical bots worth attention too.

3
2.1 LITERATURE SURVEY:

In Paper 1, Most of the people detect the cancer at the last stage. Cancer is a disease which
causes due to lasting growth, and spread of abnormal cells. Cancer patients lose hope to live
longer and healthier lives. Depression is expeditiously becoming one of the difficult phases in
the health sector. In this paper, communication helps a lot to improve one’s mental health,
this problem gets solved partially if the patient tries to open up to someone, but nobody is
available at right time. This is the reason where chatbot comes into limelight. People in
distress can communicate with chatbot which uses Natural Language Processing (NLP)
[1].So here, NLP is used which is a component of artificial intelligence which makes the
computer nearer to the human level understanding. Artificial intelligence makes it possible
for the chatbot to analyze the conversation and NLP helps to interpret the text. The huge
amount of information related to the cancer is retrieved from the web and successfully stored
in its database which in return allows these bots to impart accurate and efficient information
based on the patient’s requirement. After getting enough information the chatbot can answer
to their concerns with information about treatments, symptoms and can provide remedies.
NLP is used in making of this chatbot which is a important component of artificial
intelligence, so we can imbibe same thing in our chatbot for generation of accurate and
responsive answers [2].

4
In paper 2, with the technological innovation smartphones have quickly gained the popularity
and almost all users have their smartphones with them. Here, mobile application is developed
to collect the data from user side which then gives the appropriate response to the patient.
This response helps to user which allows the early detection of a particular disease as well as
treatments, and also provides clinical assistance. The main objective was to generate a
solution which would ease the data reception and transmission in real time. This real time
data is fed to web server, encrypted and further analysis of data takes place [3]. The overview
of the development as well as implementation smart wireless interactive healthcare system is
depicted.

5
3.SOFTWARE REQUIREMENT

3.1 General Requirements : Here are some general requirements for a healthcare
chatbot:
1. Natural Language Processing (NLP): The chatbot should be able to understand and
interpret user queries and responses in a natural and conversational manner.

2. Medical Knowledge Base: The chatbot needs to have access to a comprehensive and up-to-
date medical knowledge base that includes information on symptoms, diseases, treatments,
medications, and other relevant healthcare topics.

3. Symptom Assessment: The chatbot should be able to ask relevant questions to the user to
assess their symptoms accurately and provide appropriate recommendations or next steps.

4. Personalization: The chatbot should be able to provide personalized responses and

recommendations based on the user's individual health information, such as medical history
or known conditions.

5. Data Privacy and Security: The chatbot must adhere to strict data privacy and security
protocols to protect the user's personal health information.

6. Integration with Existing Systems: The chatbot should be able to integrate with existing
healthcare systems, such as electronic health records (EHRs), appointment scheduling
systems, or telehealth platforms, to provide seamless and efficient healthcare support.

7. Multilingual Support: If the chatbot is intended for a diverse user base, it should support
multiple languages to cater to users from different linguistic backgrounds.

8. Continuous Learning and Improvement: The chatbot should be designed to continuously

learn from user interactions and feedback, allowing it to improve its responses and
recommendations over time.

6
3.2 Invariant Requirements :

When it comes to invariant requirements, these are the fundamental aspects that
remain consistent throughout the development process and are essential for the successful
implementation of a healthcare chatbot. Here are some key invariant requirements to
consider:

1. Accuracy and Reliability: The chatbot should provide accurate and reliable information to
users, especially when it comes to medical knowledge and recommendations. This requires a
robust and up-to-date medical knowledge base, as well as rigorous testing to ensure the
chatbot's responses are trustworthy.

2. User-Friendliness: The chatbot should have a user-friendly interface and interaction design
that makes it easy for users to navigate and engage with the system. This includes clear
instructions, intuitive menus, and well-designed prompts to guide users through their
interactions.

3. Accessibility: The chatbot should be accessible to a wide range of users, including those
with disabilities or special needs. This means providing support for alternative input methods,
such as voice commands or screen readers, and ensuring the chatbot's interface meets
accessibility standards.

4. Privacy and Security: As healthcare involves sensitive information, the chatbot must
prioritize user privacy and data security. This includes implementing appropriate encryption
measures, complying with data protection regulations, and ensuring user data is stored
securely.

5. Scalability: The chatbot should be designed to handle a large volume of users and
interactions without compromising performance. This requires efficient resource
management, such as optimized algorithms and scalable infrastructure, to accommodate
increasing demand.

6. Integration with Existing Systems: The chatbot should seamlessly integrate with existing
healthcare systems, such as electronic health records (EHRs) or appointment scheduling
systems. This allows for a smooth flow of information between the chatbot and healthcare
providers, ensuring continuity of care.

7
 These are some of the invariant requirements that are crucial for a healthcare chatbot
project. By addressing these requirements, you can lay a solid foundation for the development
of an effective and reliable chatbot.

3 Modelling Requirements:

In order to create an effective healthcare chatbot, it's important to consider the following
modelling requirements

1. Natural Language Processing (NLP): The chatbot should be equipped with advanced NLP
techniques to understand and interpret user queries accurately. This involves tasks such as
intent recognition, entity extraction, and sentiment analysis, which enable the chatbot to
provide meaningful and contextually appropriate responses.

2. Medical Knowledge Representation: The chatbot should have a robust knowledge

representation framework to store and organize medical knowledge. This can include
ontologies, knowledge graphs, or other structured formats that allow the chatbot to access and
retrieve relevant information when interacting with users.

3. Context Awareness: To enhance user experience, the chatbot should be able to maintain
context throughout the conversation. This means understanding the context of previous user
queries, remembering user preferences, and providing coherent and personalized responses
based on that context.

4. Decision Support: The chatbot can be designed to provide decision support to users by
leveraging machine learning algorithms. For example, it can analyze symptoms and medical
history to suggest potential diagnoses or recommend appropriate treatment options.

5. Integration with Backend Systems: The chatbot should be able to integrate with various
backend systems, such as electronic health records (EHRs), databases of medical literature, or
appointment scheduling systems. This allows the chatbot to access up-to-date information
and provide accurate and relevant responses to user queries.

6. Continuous Learning: A healthcare chatbot can benefit from continuous learning

capabilities, enabling it to improve its performance over time. This can involve techniques
such as reinforcement learning, where the chatbot learns from user feedback and adjusts its
responses accordingly.

8
 By considering these modeling requirements, you can create a healthcare chatbot that
is capable of understanding user queries, providing accurate information, and assisting users
in their healthcare needs.

4.SYSTEM DEVELOPMEMT

Initially the chatbot ask to enter the name of the user, one major symptom that they are facing
and period of facing that symptom. In the next step the chatbot ask the specific symptom the
user is facing. for example, type 0 for heavy fever or type 1 for mild fever. Next the bot will
ask some series of symptoms, and user have to answer in "yes" or "no" manner. Decision
Tree is a Supervised learning technique that can be used for both classification and
Regression problems, but mostly it is preferred for solving Classification problems. It is a
tree-structured classifier where, internal nodes represent the features of a data set branches
represent the decision rules and each leaf node represents the outcome. In a Decision tree,
there are two nodes, which are the Decision Node and Leaf Node.

Decision nodes are used to make any decision and have multiple branches, whereas Leaf
nodes are the output of those decisions and do not contain any further branches. The
decisions or the test are performed on the basis of features of the given data set. Algorithm
asks set of question to user and accordingly it arrives at a solution. It predicts the disease and
gives necessary precautions based on it

9
4.1 Data Flow Diagram

10
 Fig 4.1 Data Flow Diagram

 Level 0

11
 Level 1

12
4.2 ER Diagram

13
 Fig 4.2 ER Diagram

4.3 UML Diagram

Fig 4.3 UML Diagram

14
4.3.1 Sequence Diagram

15
 Fig 4.3.1 Sequence Diagram

4.3.2 Use Case Diagram

Fig 4.3.2 Use Case Diagram

16
4.3.3 Activity Diagram

17
Fig 4.3.3 Activity Diagram

18
5. PROPOSED WORK :

The proposed work of a healthcare chatbot project can vary depending on the specific
objectives and requirements. However, some common functionalities that a healthcare
chatbot can offer include:

1. Symptom Assessment: The chatbot can ask users about their symptoms and provide
preliminary assessments or suggestions based on the input. It can help users understand
potential causes of their symptoms and recommend appropriate actions, such as seeking
medical attention or providing self-care tips.

2. Medical Information Retrieval: The chatbot can act as a knowledge base, providing users
with accurate and reliable medical information. It can answer questions about diseases,
treatments, medications, and general health-related topics.

3. Appointment Scheduling: The chatbot can assist users in scheduling appointments with
healthcare providers. It can check the availability of doctors, provide available time slots, and
help users book appointments seamlessly.

4. Medication Reminders: The chatbot can remind users to take their medications at the
prescribed times. It can send notifications, provide dosage instructions, and track medication
adherence.

5. Health Tips and Advice: The chatbot can offer general health tips and advice on
maintaining a healthy lifestyle. It can provide information on nutrition, exercise, stress
management, and preventive measures for various health conditions.

6. Mental Health Support: The chatbot can provide mental health support by offering
resources, coping strategies, and techniques for managing stress, anxiety, or depression. It can
also suggest mindfulness exercises or relaxation techniques.

19
7. Emergency Assistance: In critical situations, the chatbot can provide immediate guidance
or connect users to emergency services. It can offer first aid instructions for common
emergencies or help users locate nearby hospitals or clinics.

8. Personalized Recommendations: By collecting user data and preferences, the chatbot can
offer personalized recommendations for healthcare services, wellness programs, or health-
related products. It can tailor its responses based on the user's specific needs and
circumstances.

These are just a few examples of the proposed work for a healthcare chatbot project. The
functionalities can be customized to meet the specific requirements and goals of the project.

20
 Coding
import re
import pandas as pd
import pyttsx3
from sklearn import preprocessing
from sklearn.tree import DecisionTreeClassifier,_tree
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.svm import SVC
import csv
import warnings
import pyscript
warnings.filterwarnings("ignore", category=DeprecationWarning)

training = pd.read_csv('Data/Training.csv')
testing= pd.read_csv('Data/Testing.csv')
cols= training.columns
cols= cols[:-1]
x = training[cols]
y = training['prognosis']
y1= y

reduced_data = training.groupby(training['prognosis']).max()

#mapping strings to numbers

le = preprocessing.LabelEncoder()
le.fit(y)
y = le.transform(y)

21
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.33, random_state=42)
testx = testing[cols]
testy = testing['prognosis']
testy = le.transform(testy)

clf1 = DecisionTreeClassifier()
clf = clf1.fit(x_train,y_train)
# print(clf.score(x_train,y_train))
# print ("cross result========")
scores = cross_val_score(clf, x_test, y_test, cv=3)
# print (scores)
print (scores.mean())

model=SVC()
model.fit(x_train,y_train)
print("for svm: ")
print(model.score(x_test,y_test))

importances = clf.feature_importances_
indices = np.argsort(importances)[::-1]
features = cols

def readn(nstr):
engine = pyttsx3.init()

22
 engine.setProperty('voice', "english+f5")
engine.setProperty('rate', 130)

engine.say(nstr)
engine.runAndWait()
engine.stop()

severityDictionary=dict()
description_list = dict()
precautionDictionary=dict()

symptoms_dict = {}

for index, symptom in enumerate(x):

symptoms_dict[symptom] = index
def calc_condition(exp,days):
sum=0
for item in exp:
sum=sum+severityDictionary[item]
if((sum*days)/(len(exp)+1)>13):
print("You should take the consultation from doctor. ")
else:
print("It might not be that bad but you should take precautions.")

def getDescription():
global description_list
with open('MasterData/symptom_Description.csv') as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')

23
 line_count = 0
for row in csv_reader:
_description={row[0]:row[1]}
description_list.update(_description)

def getSeverityDict():
global severityDictionary
with open('MasterData/symptom_severity.csv') as csv_file:

csv_reader = csv.reader(csv_file, delimiter=',')

line_count = 0
try:
for row in csv_reader:
_diction={row[0]:int(row[1])}
severityDictionary.update(_diction)
except:
pass

def getprecautionDict():
global precautionDictionary
with open('MasterData/symptom_precaution.csv') as csv_file:

csv_reader = csv.reader(csv_file, delimiter=',')

line_count = 0
for row in csv_reader:
_prec={row[0]:[row[1],row[2],row[3],row[4]]}

24
 precautionDictionary.update(_prec)

def getInfo():
print("-----------------------------------HealthCare ChatBot-----------------------------------")
print("\nYour Name? \t\t\t\t",end="->")
name=input("")
print("Hello, ",name)

def check_pattern(dis_list,inp):
pred_list=[]
inp=inp.replace(' ','_')
patt = f"{inp}"
regexp = re.compile(patt)
pred_list=[item for item in dis_list if regexp.search(item)]
if(len(pred_list)>0):
return 1,pred_list
else:
return 0,[]
def sec_predict(symptoms_exp):
df = pd.read_csv('Data/Training.csv')
X = df.iloc[:, :-1]
y = df['prognosis']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=20)
rf_clf = DecisionTreeClassifier()
rf_clf.fit(X_train, y_train)

symptoms_dict = {symptom: index for index, symptom in enumerate(X)}

input_vector = np.zeros(len(symptoms_dict))
for item in symptoms_exp:
input_vector[[symptoms_dict[item]]] = 1

25
 return rf_clf.predict([input_vector])

def print_disease(node):
node = node[0]
val = node.nonzero()
disease = le.inverse_transform(val[0])
return list(map(lambda x:x.strip(),list(disease)))

def tree_to_code(tree, feature_names):

tree_ = tree.tree_
feature_name = [
feature_names[i] if i != _tree.TREE_UNDEFINED else "undefined!"
for i in tree_.feature
]

chk_dis=",".join(feature_names).split(",")
symptoms_present = []

while True:

print("\nEnter the symptom you are experiencing \t\t",end="->")

disease_input = input("")
conf,cnf_dis=check_pattern(chk_dis,disease_input)
if conf==1:
print("searches related to input: ")
for num,it in enumerate(cnf_dis):
print(num,")",it)
if num!=0:

26
 print(f"Select the one you meant (0 - {num}): ", end="")
conf_inp = int(input(""))
else:
conf_inp=0

disease_input=cnf_dis[conf_inp]
break
# print("Did you mean: ",cnf_dis,"?(yes/no) :",end="")
# conf_inp = input("")
# if(conf_inp=="yes"):
# break
else:
print("Enter valid symptom.")

while True:
try:
num_days=int(input("Okay. From how many days ? : "))
break
except:
print("Enter valid input.")
def recurse(node, depth):
indent = " " * depth
if tree_.feature[node] != _tree.TREE_UNDEFINED:
name = feature_name[node]
threshold = tree_.threshold[node]

if name == disease_input:
val = 1
else:
val = 0

27
 if val <= threshold:
recurse(tree_.children_left[node], depth + 1)
else:
symptoms_present.append(name)
recurse(tree_.children_right[node], depth + 1)
else:
present_disease = print_disease(tree_.value[node])
# print( "You may have " + present_disease )
red_cols = reduced_data.columns
symptoms_given =
red_cols[reduced_data.loc[present_disease].values[0].nonzero()]
# dis_list=list(symptoms_present)
# if len(dis_list)!=0:
# print("symptoms present " + str(list(symptoms_present)))
# print("symptoms given " + str(list(symptoms_given)) )
print("Are you experiencing any ")
symptoms_exp=[]
for syms in list(symptoms_given):
inp=""
print(syms,"? : ",end='')
while True:
inp=input("")
if(inp=="yes" or inp=="no"):
break
else:
print("provide proper answers i.e. (yes/no) : ",end="")
if(inp=="yes"):
symptoms_exp.append(syms)

second_prediction=sec_predict(symptoms_exp)

28
 # print(second_prediction)
calc_condition(symptoms_exp,num_days)
if(present_disease[0]==second_prediction[0]):
print("You may have ", present_disease[0])
print(description_list[present_disease[0]])

# readn(f"You may have {present_disease[0]}")

# readn(f"{description_list[present_disease[0]]}")

else:
print("You may have ", present_disease[0], "or ", second_prediction[0])
print(description_list[present_disease[0]])
print(description_list[second_prediction[0]])

# print(description_list[present_disease[0]])
precution_list=precautionDictionary[present_disease[0]]
print("Take following measures : ")
for i,j in enumerate(precution_list):
print(i+1,")",j)

# confidence_level = (1.0*len(symptoms_present))/len(symptoms_given)
# print("confidence level is " + str(confidence_level))

recurse(0, 1)
getSeverityDict()
getDescription()
getprecautionDict()
getInfo()
tree_to_code(clf,cols)

29
print("--------------------------------------thank
you--------------------------------------------------")

30
 Output Photos
C:\Users\91880\Scripts\python.exe C:/Users/91880/OneDrive/Desktop/healthcare-
chatbot-master/chat_bot.py
0.9753724709150973
for svm:
1.0
-----------------------------------HealthCare ChatBot-----------------------------------

Your Name? -> Yogita

Hello, Yogita

Enter the symptom you are experiencing ->cold

searches related to input:
0 ) cold_hands_and_feets
Okay. From how many days ? : 4
Are you experiencing any
back_pain ? : yes
weakness_in_limbs ? : yes
neck_pain ? : no
dizziness ? : yes
loss_of_balance ? : yes
You should take the consultation from doctor.
C:\Users\91880\lib\site-packages\sklearn\base.py:465: UserWarning: X does not have
valid feature names, but DecisionTreeClassifier was fitted with feature names
warnings.warn(
You may have Cervical spondylosis
Cervical spondylosis is a general term for age-related wear and tear affecting the spinal
disks in your neck. As the disks dehydrate and shrink, signs of osteoarthritis develop,
including bony projections along the edges of bones (bone spurs).
Take following measures :
1 ) use heating pad or cold pack
2 ) exercise

31
3 ) take otc pain reliver
4 ) consult doctor
--------------------------------------thank you--------------------------------------------------

Process finished with exit code 0

32
6.PERFORMANCE ANALYSIS

To perform a performance analysis of a healthcare chatbot project, several factors need to be

considered. Here are some key aspects to assess:

1. Accuracy and Effectiveness: Evaluate how accurately the chatbot understands user queries
and provides relevant and helpful responses. Measure the rate of correct diagnoses,
appropriate recommendations, and accurate information retrieval.

2. Response Time: Measure the speed at which the chatbot provides responses. A fast
response time is crucial for user satisfaction and engagement. It's important to set
benchmarks for acceptable response times and monitor if the chatbot meets those standards.

3. User Satisfaction: Gather feedback from users to understand their level of satisfaction with
the chatbot's performance. Conduct surveys or interviews to gather insights on user
experiences, ease of use, and overall satisfaction. This feedback can help identify areas for
improvement.

4. Error Analysis: Identify and analyze any errors or misunderstandings that occur during
conversations with the chatbot. Determine the root causes of these errors and work on
improving the chatbot's understanding and response capabilities.

5. Scalability and Robustness: Assess how well the chatbot handles increasing user traffic and
the ability to handle a wide range of user queries. Test the chatbot's performance under
different load conditions to ensure it can handle high volumes of requests without significant
performance degradation.

6. Integration and Compatibility: Evaluate the chatbot's integration with other systems or
platforms, such as electronic health records or appointment scheduling systems. Ensure
compatibility and seamless data exchange between different components of the healthcare
ecosystem.

7. Security and Privacy: Ensure that the chatbot adheres to strict security and privacy
standards, especially when dealing with sensitive health information. Evaluate the measures
in place to protect user data and maintain confidentiality.

33
8. Continuous Improvement: Implement mechanisms to collect user feedback and monitor the
performance of the chatbot regularly. Use this feedback to make continuous improvements
and enhancements to the chatbot's capabilities.

By analyzing these factors, you can assess the performance of a healthcare chatbot
project and identify areas for improvement to enhance user satisfaction and
overall effectiveness.

34
7.CONCLUSION AND FUTURE SCOPE

7.1 Conclusion
The main aim of the project AI Based Healthcare chatbot system using Natural Language
Processing, which is easy to use and more secure than the current system it will cure the
diseases and helps to maintain proper health in the current system. This system reduces the
possibility of diseases. The information is processed and store in the database, then it is
reverted to the user. Also, it provides an accurate information about the heath symptoms and
medicines to the patients. The government will also keep the track of the medicines supplied
to the medicals and hospitals. By using diagnosis software, the results are generated accurate
and fast. For end users it became easy to gain access in healthcare website and explore
different types of services. After using such web-based applications, the results of healthcare
were affected in different countries and rate of mortality was steadily decreased. With the
help of this natural language processing the proposed system can help the government
organizations and hospitals also help in the development of the country. Thus, we
successfully build up a system for hospitals and medical institute so that user can ask their
queries with the medical assistant and book the doctor’s appointment by giving text
messages.

35
7.2 Future Scope

Future scope of the project could be AI Based Healthcare chatbot system using NLP can also
include a mobile assistant in it which will be more functions will be added and can be
accessed by many users. Which will also reduce the time and will also be accurate in the
health details of patients given to the doctors. We can add biometric system for more secure
authentication process.

36
8.REFRENCES

[1] "Real World Smart Chatbot for Customer Care using a Software as a Service (SaaS)
Architecture “Godson Michael D’silva1”, Sanket Thakare2, Shraddha More Available:
https://www.docme.ru/doc/2207164/i-smac.2017.8058261

[2] Divya Madhu, Neeraj Jain C. J, ElmySebastain, ShinoyShaji,AnandhuAjayakumar,” A

Novel Approach for Medical Assistance Using Trained Chatbot”, International Conference
2016. Available: https://www.semanticscholar.org/paper/Anovelapproachformedicalassi
stancusingMadhuJain/b9117a428a35aca643f83e6986ae2 00807cba5c7

[3] YerlanJ Saurav Kumar Mishra, Dhirendra Bharti, Nidhi Mishra,” Dr.Vdoc: A Medical
Chatbot that Acts as a Virtual Doctor”, Journal of Medical Science and Technology Volume:
6, Issue 3, 2016. Available:
http://medicaljournals.stmjournals.in/index.php/RRJoMST/article/view /30

[4] PavlidouMeropi, Antonis S. Billis, Nicolas D.Hasanagas, CharalambosBratsas, Ioannis

Antoniou, Panagiotis D. Bamidis, ”Conditional Entropy Based Retrieval Model in Patient-
Care Conversational Cases”,2017 IEEE 30th International conference on Computer-Based
Medical System. Available:- https://ieeexplore.ieee.org/abstract/document/8104260

[5] Abbas SaliimiLokman, Jasni Mohamad Zain,FakultiSistemKomputer,

KejuruteraanPerisian,” Designing a Chatbot for Diabetic Patients”, ACM Transactions on
Management Information Systems (TMIS), Volume 4, Issue 2, August 2018. Available:
http://ijircce.com/upload/2018/june/7_Pharmabot.pdf

[6] Nicolas D .Hasanagas, CharalambosBratsas, Ioannis Antoniou, Panagiotis D. Bamidis,

”Conditional Entropy Based Retrieval Model in Patient-Care Conversational Cases”,2017
IEEE 30th International conference on Computer-Based Medical System. Available:
https://scholar.google.co.in/scholar?q=International+conference+on+C
omputerBased+Medical+System.&hl=en&as_sdt=0&as_vis=1&oi=sch olart

[7] Kowatsch, T., VollanMobile Coach. In: Designingthe Digital Transformation. DESRIST
2017. Lecture Notes in Computer Science, vol 10243, pp. 485-489. Springer, Berlin;
Germany (2017). Available:
https://www.researchgate.net/publication/317181609_Design_and_Eva
luation_of_a_Mobile_Chat_App_for_the_Open_Source_Behavioral_Health_Intervention_Pla
tform_MobileCoach

[8] BenildaEleonor V. Comendador, Bien Michael B. Francisco, Jefferson S.

Medenilla,Sharleen Mae T. Nacion, “Pharmabot: A Pediatric Generic Medicine Consultant
Chatbot “,Journal of Automation and Control Engineering Vol. 3, No. 2, April 2015.
Available: http://www.joace.org/uploadfile/2014/0801/20140801025000959.pdf

[9] Ahmed Fadhil, “Beyond Patient Monitoring: Conversational Agents Role inTelemedicine
& Healthcare Support For Home-Living Elderly Individuals”, a researcharticle, April 2017.
Available :http://:www.researchgate.net/publication/323845985_Beyond_Patient
_Monitoring_Conversational_Agents_Role_in_Telemedicine_Healthca
re_Support_For_Home_Living_Elderly_Individuals.pdf

[10] Fadhil, Ahmed. ”Can a Chatbot Determine My Diet?: Addressing Challenges ofChatbot
Application for Meal Recommendation.” arXiv preprint arXiv:1802.09100(2018). Available:
http://:www.researchgate.net/publication/addressing_challanges_of_
chatbot_application_for_meal_recommendation.pdf
 ACKNOWLEDGEMENT

It is indeed with a great sense of pleasure and immense sense of gratitude that I
acknowledge the help of these individuals which led to the successful completion of
this mini-project.

I would like to thank our Head of the Department Dr. V.B.KAMBLE Sir for his
support throughout my project work.

I would like to thank our Guide PROF. HADIYA HASHMI Mam for their support
and advices while completing this mini-project.

I am extremely great full to my department staff members and friends who

helped me in successful completion of this mini-project.

SUDARSHAN SAKHARE(sudarshansakhare18@gmail.com)

VISHAL KADU(54321vishal5@gmail.com)

OM VHARE(om143vhare00@gmail.com)

ABHIJEET KAMBLE(kambleabhijeet864@gmail.com)