Health Care Chatbot Using NLP and Flask

Authors: Kshitij Thakre, Dr. P. R. Rothe, Sakshi Kukade, Pranali Shinde, Komal Madame

DOI Link: https://doi.org/10.22214/ijraset.2022.42854

Abstract

Health care is very important to start a good life. However, if you have a health problem, it is very difficult to talk to your doctor. Chatbots can be used to communicate with text or voice interfaces and receive responses via artificial intelligence. Chatbots are programs designed to automatically interact with incoming messages. Chatbots can be programmed to respond the same each time and respond differently to messages containing specific keywords. In addition, you can use machine learning to adapt your response to your situation. More and more hospitals, nursing homes, and even private centers are now using online human service chatbots on their websites. These bots connect with potential patients accessing the site, find specialists, make appointments, and ensure appropriate treatment. In any case, the use of artificial intelligence in industries where people\'s lives can be a problem still raises personal concerns. The question arises whether the above tasks should be left to human staff. This healthcare chatbot system helps hospitals provide 24/7 online healthcare support. It answers both deep and general questions. It also helps generate leads and automatically delivers lead information to sales. Asking in turn helps the patient by guiding them on exactly what they are looking for.

Introduction

I. ACKNOWLEDGEMENT

Priyadarshini College of Engineering is a well established & renowned institute and follows a goal of creating technocrats and brings it into reality, which will perform challenging endeavor in technical field for welfare of human being.

We wish to avail this opportunity to express our sincere thanks to our Guide Dr.P.R.Rothe & Mr.Deoram G. Gahane , who continuously supervised our work with utmost care and zeal. They have always guided us in our endeavor to present our project on “HEALTH CARE CHATBOT USING NLP AND FLASK”.

It’s a great pleasure to express our deep sense of gratitude and the whole hearted thanks to our principal

Dr.S.A.Dhale, Priyadarshini College of Engineering, Nagpur.

We offer special thanks to our Head of the Department Dr.V.K.Takasande, for giving us the opportunity to undertake this project.

We offer hearty gratitude to, Lab assistants of ET Department, PCE, for their valuable support during the execution of the project work. Lastly, we express our deep sense of gratitude to all teaching and non-teaching staff of the Institute and all our friends, family members, who directly and indirectly helped us to complete our project successfully and to bring it into reality.

II. INTRODUCTION

Today, our lives require great health care. Today, people are busy with work receptions, work at work, and additional addictions to the Internet. You are not involved in your health. So you avoid going to the hospital because of a small problem. This can be a significant disadvantage. Therefore, before consulting your doctor, consider developing a health chatbot system with AI that can identify the illness and provide basic information about the illness. Chatbots are software programs used to interact with customers using natural language processing in text or text-to-speech format. Chatbots were originally developed to interact with humans only for entertainment purposes. In modern times, the biggest challenge facing India as a country is to provide quality and affordable medical services to a growing population, while at the same time not being cost-effective. Difficulty in accessing and transporting medical facilities, especially in rural areas, means that patients postpone treatment or seek closer but at the same timeless cost-effective medical facilities to meet their medical needs. It means that. The role of medical chatbots, which is an efficient way to provide patients with the timely quality of care, access, and treatment, is to connect patients to chatbots and administer appropriate antibiotics/drugs and precautions. Useful for.

A. Necessity

The healthcare industry is no stranger to emergencies. And time plays a very crucial role in tackling them! Healthcare chatbots provide helpful information instantly, especially in times where every second is important. For example, if a patient rushes in with an attack, the doctor can get the patient’s information like previous records, other diseases, allergies, check-ups, etc., instantly over a bot.

B. Objectives

A chatbot is a piece of software that conducts a conversation with users via auditory or textual methods. A medical chatbot facilitates the job of a healthcare provider and helps improve their performance by interacting with users in a human-like way.

There are countless cases where intelligent medical chatbots could help physicians, nurses, therapists, patients, or their families. They can step in and minimize the amount of time they spend on tasks like:

Providing health-related information to users
Guidance for patient
Medication management and dosage
Connecting people and organizations with first responders
FAQ-type queries (contact details, directions, opening hours and service/treatment details)

It’s important to note that despite the fact that chatbots can offer valuable facts and symptoms, they aren’t qualified to give an official diagnosis. The main premise behind these talking or texting smart algorithms is to become the first point of contact before any human involvement is needed.

III. LITERATURE SURVEY

In paper[1] it reviews the present evidence for the feasibility and effectiveness of online one-on-one psychological state interventions that use the text-based synchronous chat. Synchronous written conversations (or "chats") are getting increasingly popular as Web-based psychological state interventions. This review provides an evaluation of individual synchronous Web-based chat technologies as a mode of psychological intervention and supports supported the present evidence of the appliance of this technology during this area of psychological state research, we see tentative support for this mode of intervention. Interventions utilizing text-based synchronous communication showed better outcomes compared with Waitlist conditions and overall equivalent outcomes compared with Treatment as was common and were a minimum of nearly as good because of the comparison interventions. However, the difficulty of whether these technologies are cost-effective in clinical practice remains a consideration for future research studies. In paper [2] the chatbot will act as a virtual doctor and makes it possible for the patient to interact with a virtual doctor. linguistic communication processing and pattern matching algorithm for the event of this chatbot. it's developed using the python language. supported the survey given it's found at the no of the proper answer given by the chatbot is 80% and incorrect/ambiguous answer given is 20%. This survey of chatbots and analysis of the results suggested that this software is used for teaching and as a virtual doctor for awareness and first care. [3] This literature review presents the History, Technology, and Existing Work of the Chat-Bots. Chatbots have good conversational abilities they're good at emulating a personality's conversation, and they learn through knowledge Evolution of chatbots• TURING TEST 1950 ELIZA 1960. PARRY (1972) RACTER 1984 ALEXA. GOOGLES MEENA IBM WATSON APPLE SIRI Chats-Bots mentioned during this Literature survey are additionally supported for a medicinal purpose like K-Bot

IV. SYSTEM MODELING

In our proposed system the user can chat with the bot regarding the query through text. The system uses an expert system to answer the queries. Users can also view the available doctors for that particular disease. This system can be used by multiple users to get counseling sessions online. The data of the chatbot is stored in the database in the form of a pattern template.

B. Description of Programming Languages

Python: It is a general-purpose coding language which means that, unlike HTML, CSS, and JavaScript, it can be used for other types of programming and software development besides web development.
Machine Learning: Machine learning (ML) is the study of computer algorithms that improve automatically through experience and by the use of data. It is seen as a part of artificial intelligence. Machine learning algorithms build a model based on sample data, known as "training data", in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as in medicine, email filtering, and computer vision, where it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.
NLP (Natural Language Processing): Natural language processing (NLP) refers to the branch of computer science—and more specifically, the branch of artificial intelligence or AI—concerned with giving computers the ability to understand the text and spoken words in much the same way human beings can.
Flask: Flask is a micro web framework written in Python. It is classified as a microframework because it does not require particular tools or libraries description

C. Description of Libraries use

Numpy: NumPy, which stands for Numerical Python, is a library consisting of multidimensional array objects and a collection of routines for processing those arrays. Using NumPy, mathematical and logical operations on arrays can be performed.NumPy is a Python package. It stands for ‘Numerical Python’. It is a library consisting of multidimensional array objects and a collection of routines for processing of array.
Pandas: Pandas is an open source Python package that is most widely used for data science/data analysis and machine learning tasks. It is built on top of another package named Numpy, which provides support for multi-dimensional arrays. As one of the most popular data wrangling packages, Pandas works well with many other data science modules inside the Python ecosystem, and is typically included in every Python distribution, from those that come with your operating system to commercial vendor distributions like ActiveState’s ActivePython.
Matplotlib: Matplotlib is a plotting library available for the Python programming language as a component of NumPy, a big data numerical handling resource. Matplotlib uses an object oriented API to embed plots in Python applications.

V. IMPLEMENTATION

In our chatbot, you must first register with our chatbot system. Then this data will be stored in our system. You will then connect to the chatbot. First, you will see the option to start the chatbot. When you click the start button, the chatbot will ask you questions like "What kind of symptoms are you experiencing", then the bot will show you some symptoms on the display screen. You just need to answer "yes" or "no". If you say yes, these types of symptoms happen to me, the Chatbot will match the symptoms from its dataset and accordingly it will prescribe the original medication and doctor's contact details, so you can contact your doctor directly or make an appointment at the doctor. In this chatbot, we can contact the doctor directly by clicking on the website link provided on the chatbot.

A. Software Development and Implementation

. Main Program:

QuestionDiagonosisTkinter.

# Importing the libraries

from tkinter import *

from tkinter import messagebox

import os

import webbrowser

import numpy as np

import pandas as pd

class HyperlinkManager:

def __init__(self, text):

self.text = text

self.text.tag_config("hyper", foreground="blue", underline=1)

self.text.tag_bind("hyper", "<Enter>", self._enter)

self.text.tag_bind("hyper", "<Leave>", self._leave)

self.text.tag_bind("hyper", "<Button-1>", self._click)

self.reset()

def reset(self):

self.links = {}

def add(self, action):

# add an action to the manager. returns tags to use in

# associated text widget

tag = "hyper-%d" % len(self.links)

self.links[tag] = action

return "hyper", tag

def _enter(self, event):

self.text.config(cursor="hand2")

def _leave(self, event):

self.text.config(cursor="")

def _click(self, event):

for tag in self.text.tag_names(CURRENT):

if tag[:6] == "hyper-":

self.links[tag]()

return

# Importing the dataset

training_dataset = pd.read_csv('Training.csv')

test_dataset = pd.read_csv('Testing.csv')

# Slicing and Dicing the dataset to separate features from predictions

X = training_dataset.iloc[:, 0:132].values

Y = training_dataset.iloc[:, -1].values

# Dimensionality Reduction for removing redundancies

dimensionality_reduction = training_dataset.groupby(training_dataset['prognosis']).max()

# Encoding String values to integer constants

from sklearn.preprocessing import LabelEncoder

labelencoder = LabelEncoder()

y = labelencoder.fit_transform(Y)

# Splitting the dataset into training set and test set

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)

# Implementing the Decision Tree Classifier

from sklearn.tree import DecisionTreeClassifier

classifier = DecisionTreeClassifier()

classifier.fit(X_train, y_train)

# Saving the information of columns

cols = training_dataset.columns

cols = cols[:-1]

# Checking the Important features

importances = classifier.feature_importances_

indices = np.argsort(importances)[::-1]

features = cols

# Implementing the Visual Tree

from sklearn.tree import _tree

# Method to simulate the working of a Chatbot by extracting and formulating questions

def print_disease(node):

#print(node)

node = node[0]

#print(len(node))

val = node.nonzero()

#print(val)

disease = labelencoder.inverse_transform(val[0])

return disease

def recurse(node, depth):

global val,ans

global tree_,feature_name,symptoms_present

indent = " " * depth

if tree_.feature[node] != _tree.TREE_UNDEFINED:

name = feature_name[node]

threshold = tree_.threshold[node]

yield name + " ?"

# ans = input()

ans = ans.lower()

if ans == 'yes':

val = 1

else:

val = 0

if val <= threshold:

yield from recurse(tree_.children_left[node], depth + 1)

else:

symptoms_present.append(name)

yield from recurse(tree_.children_right[node], depth + 1)

else:

strData=""

present_disease = print_disease(tree_.value[node])

# print( "You may have " + present_disease )

# print()

strData="You may have :" + str(present_disease)