P.S.N.A.

COLLEGE OF ENGINEERING & TECHNOLOGY, DINDIGUL

Department of Computer Science and Engineering
​ Project First Review

​Project Title : Personal Health Advisor Bot

Section : CSE-B

Batch No : 11

Team Members : T.Kali Kousik (921316104083)

G.G.Karthik (921316104085)

T. Jayasurya (921316104077)

P.V.K.Durai Gopalsamy(921316104051)

Internal Guide Name : Dr.R. Karthikeyan M.Tech , Ph.D.

If it is Industry/Company project,

Specify Company name : Nil

Address with contact number : Nil

External Guide Name : Nil

Contact mail id & Phone number : Nil

 PERSONAL HEALTH ADVISOR BOT

Introduction:

Artificial Intelligence gives the supreme power to mimic the human way of thinking and
behaving to a computer. Chatbots are such kind of computer programs that interact with users
using natural language. Chatbot works basically on Artificial Intelligence. Using this capability
we have decided to add some contribution to the Health Informatics.

Our project builds a text-to-text conversational agent that diagnoses patients explaining their
condition using natural language. The bot asks for relevant information, e.g., age and sex, and
requests a list of symptoms. The system remembers past responses and asks progressively more
specific questions in order to obtain a good diagnosis. The three primary components of our
system are (1) identification and extraction of symptoms from the conversation with the user, (2)
accurate mapping of extracted symptoms to documented symptoms and (3)Specifying the
disease and referring to an appropriate specialist if necessary. In its current form, our bot’s best
application would be as a preliminary diagnosis tool that patients could use to assess their
symptoms before going to the doctor, perhaps using the bot’s specialist referral feature to choose
the right care provider.

Merits:

The basic need of every person in a country is the availability of medical services in
emergency and critical periods. Medical details of a person are registered in our application that
gives suggestions to diet habits and specialists treatment which helps in sudden and emergency
situations. The location of specialists are given as links to google maps.

Objectives:

● Identification and extraction of symptoms from the conversation with the user.
 ● Accurate mapping of extracted symptoms to documented symptoms.

● Specifying the disease and referring to an appropriate specialist if necessary.

Literature Survey:

PROJECT TECHNIQUES RESULT ISSUES

Application of Web-based chat The review provides The issue of whether

synonous text-based technologies are an evaluation of these technologies are
dialogue system in compared individual cost effective in
mental health synchronous clinical practice
interventions Web-based chat remains a
technologies as a consideration for
mode of psychological future research studies.
intervention and
support.

Dr.Vdoc: A medical Natural language 80% of accuracy. The full consultation is

chatbot that acts as a processing and pattern given at a free of cost,
virtual doctor matching algorithm. which is not a good
practice.

A Novel approach for Natural language It is possible to predict Provides the

medical assistant using processing and pattern any possible problem prescription and
trained chatbot matching algorithm. even before they start composition of
to cause any damage medicine without
to the body. consultation of a
doctor.

Medical predictions Natural language These systems are Won’t be able to

system processing. created only to suggest replace the most
a solution. important factor in
decision making.
Conditional entropy Natural Language The results show that The issue here is,it
based Retrivel model Processing. even in small training requires a compact
in Patient-Carer datasets, this method Adjacency Matrix
Conersational cases outperforms up to date based on the
methods for automated dialogues.
communication.

Towards a chatbot for Natural language 60% of accuracy The issue here is to
digital counselling processing and pattern maintain the ethical
matching algorithm. considerations.
Architecture Diagram:
System High Level Design:
Low Level Design:

Modules:

The system comprises of 3 major modules and their sub modules as follows:

❖ Medical Details:

o Register: User needs to register their basic registration details and user create an
id and password.
o Login:​ User can login their personal account using valid login credentials.
o Medical Form: ​Medical details are also received from the user. It can be
Updated.
 ❖ Chatbot:

o Chatbot: Chatbot asks for the details of the symptoms from the user. This uses
Natural Language Processing for understanding the inputs from the user.

o Algorithm: This analyses the symptoms and finds out similar diseases that relate
with the health details of the user and the symptoms. This uses Convolutional
Neural Networks which produces results of the disease for the given symptoms.

o Diet suggestion: ​This module is displayed after the analysis of disease is

received. The suggestions are based on the disease and the diseases are connected
with doctors and the diet charts in the database.

❖ Doctor Locator:

o Mapping: ​The suggested disease symptoms are then retrieved and the
corresponding specialists are searched in the map which are registered in the
database.
o Listing Doctors: The list of specialists and their corresponding location in the
google maps are produced as links.

Algorithm - CNN

Step 1 : Add an Input Layer

Step 2 : Add the word embedding Layer

Step 3 : Add the convolutional Layer

Step 4 : Add the pooling Layer

Step 5 : Add the output Layers

Step 6 : Compile the model

Software Requirements:

1. Laptop or PC
Windows 7 or higher.
Python
Anaconda
React Native
2. Android Phone or Tablet
Android v5.0 or Higher

Hardware Components:
1. Laptop or PC

I5Processor Based Computer

4GB RAM
1 TB Hard Disk
2. Android Phone or Tablet
1.2 Quad core Processor or higher.
2 GB RAM

Advantages:

● Easily locates specialists based on the disease symptoms.

 ● Friendly chatbot application that is user comfortable.
● Understands the user better and suggests diet according to ailments.

Database Design:

User Table:

Name Varchar(50)

Email Id Varchar(50)

Password Varchar(50)

Age Integer(2)

Gender Char

Height_Weight Integer(10)

Gym practices Boolean

Food habits Varchar(5)

Yoga_Meditation Boolean

Disease Table:

Disease Varchar(30)

Diets Varchar(50)

Doctor_location Varchar(100)

References:

[1] Divya S, Indumathi V, Ishwarya S, Priyasankari M and Kalpana Devi S,UG students,
Assistant Professor, “Survey on Medical Self-Diagnosis Chatbot for Accurate Analysis Using
Artificial Intelligence, International Journal of Trend in Research and Development, Volume
5(2), April 2018.

[2] Simon Hoermann, Kathryn L McCabe, David N Milne,Rafael A Calvo1,“ Application of

Synchronous Text- Based Dialogue Systems in Mental Health Interventions: Systematic
Review”, Journal of Medical Internet Research ,volume: 19 , issue 8 , August 2017.

[3] 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 3,2017.

[4] Divya Madhu,Neeraj Jain C. J, Elmy Sebastain, Shinoy Shaji, Anandhu Ajayakumar,” A
Novel Approach forMedical Assistance Using Trained Chatbot”,International Conference on
Inventive Communication and Computational Technologies(ICICCT 2017).

[6] Doina Drăgulescu,Adriana Albu,”Medical Predictions System”, International Journal of

Engineering Research and Applications , ISSN: 2248-9622 ,Vol. 2, Issue 3 , pp.1988-1996,
May-Jun 2015.

[7] Abbas Saliimi Lokman, Jasni Mohamad Zain,FakultiSistem Komputer, Kejuruteraan

Perisian,” Designing a Chatbot for Diabetic Patients”. o.17, October 2016.
[8] Pavlidou Meropi,Antonis S. Billis,Nicolas D. Hasanagas, Charalambos Bratsas,Ioannis
Antoniou, Panagiotis D. Bamidis,” Conditional Entropy Based Retrieval Model in Patient-Carer
Conversational Cases”,2017 IEEE 30th International conference on Computer-Based Medical
System.

[9] Gillian Cameron, David Cameron, Gavin Megaw, Raymond Bond,Maurice Mulvenna
,Siobhan O’Neill, Cherie Armour, Michael McTear, “Towards a chatbot for digital counselling”,
Journal of Medical Internet Research, 4(1), pp. e3.[5] Hameedullah Kazi,B.S. Chowdhry,Zeesha
Memon,”MedChatBot: An UMLS based Chatbot for Medical Students”, International Journal of
Computer Applications (0975 – 8887)Volume 55– N

Project Guide Project Coordinator HOD-CSE