Transcript Presentation1 (1)

Smart Health
Prediction System
Project Supervisor :Dr.Badar Sami
Internal Supervisor :Dr.Tehseen Ahmed Jilani
Team Introduction
 Amna Khan (Ep#1249006) [email protected]
 Areeba Jabeen (Ep#1249009) [email protected]
 Bushra Mansoor (EP#1249012) [email protected]
 Muhammad Faizan Khan(EP#1249051 ) [email protected]
Why This ?
It might have happened so many times that you or someone yours
need doctors help immediately, but they are not available due to
some reasons or also sometimes it happens that we could not find
the correct doctor for the treatment so to solve this problem we
will implement the online intelligent Smart Health prediction web
based application that will facilitate the patient to get instant
guidance on their health issues
Project Summery
The core idea behind the project is to propose a system that allows
users to get instant guidance on their health issues .This system is
fed with various symptoms and the disease/illness associated with
those systems. This system allows user to share their symptoms
and issues It then processes user’s symptoms to check for various
illnesses that could be associated with it If the system is not able to
provide suitable results, it informs the user about the type of
disease or disorder it feels user’s symptoms are associated with
and also suggest the doctor to whom he or she can contact.
Software Requirements
•
•
•
•
•
•
Windows 7 and above
Mysql server
Html
Php
Jquery
Xamp Server
Hardware Requirement
• Processor – Dual Core
• Hard Disk – 50 GB
• Memory – 1GB RAM
Modules
• Admin Module
1. Admin Login: Admin can login to the system using his ID and Password.
2. Add Doctor: Admin can add new doctor details into the database.
3. Add Disease: Admin can add disease details along with symptoms and
type.
4. View Doctor: Admin can view various Doctors along with their personal
details.
5. View Disease: Admin can view various diseases details stored in database.
6. View Patient: Admin can view various patient details who had accessed the
system
Some Screen shots Of Admin Module
• Patient Module
1. Patient Login: Patient can Login to the system using his ID and Password.
2. Patient Registration: If Patient is a new user he will enter his personal
details and he will have user Id and password through which he can login
to the system.
3. My Details: Patient can view his personal details.
4. Edit Patient Record : Patient can Edit his personal details.
5. Disease Prediction: - Patient will specify the symptoms caused due to his
illness. System will ask certain question regarding his illness and predict
the disease based on the symptoms and also suggest doctors based on
the disease.
6. Search Doctor: Patient can search for doctor by specifying name or type.
7. My stuff : Patient also have the facility to manage their reports .
Some Screen Shots of Patient Module
• Doctor Module
1.
2.
3.
4.
Doctor Login: Doctor Login to the system using his ID and Password.
Doctor Registration: doctor can register them selves in the system
My Details: Doctor can view his personal details.
Edit Patient Record : Doctor can Edit his personal details.
5. My stuff : Doctor also have the facility to manage their files reports or any thing
Some Screen shots Of Doctor Module
Data Collection
We have studied diseases of many areas such as:
LUNGS:
DISEASES
Idiopathic Pulmonary Fibrosis (a
disease in which tissues in your lungs
becomes thick & stiff or scarred
overtime).
SYMPTOMS
Shortness of breath
A dry, hacking cough
Rapid breathing
Gradual , unintended weight loss
Tiredness
Clubbing, which is the widening &
rounding of the tips of the fingers or
toes.
Influenza (flu)
Fever
Dry persistent
Cough
Fatigue & weakness
Nasal congestion
Sore throat
A cough that does not go away or gets
worse
Fever
Chest pain
Hoarseness
Weight loss & loss of appetite
Coughing up blood or rust-colored spit
Runny nose
Nasal congestion
Red , watery eyes
Fever
Cough
Lung cancer
Pertussis (whooping cough)
CHEST:
DISEASES
SYMPTOMS
Heart attack
Chest pain
Sweating
Pressure
Fullness or tightness in your chest
Crushing or searing pain radiating
to your back, neck, jaws,
shoulders & arms particularly left
arms.
Shortness of breath
Dizziness or weakness
Nausea or vomiting
Angina
Chest pain
Sweating
Pressure
Fullness or tightness in your chest
Crushing or searing pain radiating
to your back, neck, jaws,
shoulders & arms particularly left
arms.
Shortness of breath
Dizziness or weakness
Nausea or vomiting
LIVER:
DISEASES
Acute liver failure
SYMPTOMS
Yellowish of your skin and eye balls
(jaundice).
Pain in your upper right abdomen.
Abdominal swelling.
Nausea.
Vomiting.
A general sense of felling unwell
(malaise).
Disorientation and confusion.
Sleepiness.
Cirrhosis
Loss of appetite.
Lack of energy which may be
debilitating.
Weight loss or sudden weight gain.
Bruises.
Yellowing of skin or the whites of eyes
(jaundice)
Itchy skin.
Fluid retention (edema) and swelling in
the ankles, legs and abdomen.
A brownish and orange tint of the wine
Light colored stools.
Confusion disorientation, personality
changes.
Blood in the stool.
Fever.
Non-alcoholic fatty disease
Fatigue.
Pain in upper right abdomen.
Weight loss.
Alagille syndrome
Jaundice.
Naive bayes algorithm
Naive Bayes algorithm is a classification algorithm based on Bayes’
theorems use in predictive modeling and this algorithm uses Bayesian
techniques .This algorithm is less computationally intense then other
and therefore is useful for quickly generating mining models to
discover relationships between input columns and predictable
columns.
Data required for naive bayes models
requirements for a Naive Bayes model
• A single key column Each model must contain one numeric or text
column that uniquely identifies each record. Compound keys are not
allowed.
• Input columns In a Naive Bayes model, all columns must be either
discrete or discretized columns it is also important to ensure that the
input attributes are independent of each other
• At least one predictable column The predictable attribute must
contain discrete or discretized values. The values of the predictable
column can be treated as inputs
Viewing the Model :To explore the model we can use the Microsoft
Naive Bayes Viewer. The viewer shows you how the input attributes
relate t
• Making predictions
After the model has been trained, the results are stored as a set of
patterns, which we use to make predictions.
We can create queries to return predictions about how new data
relates to the predictable attribute.
Remarks
• Supports the use of Predictive Model Markup Language (PMML) to
create mining models.
• Supports drill through.
• Does not support the creation of data mining dimensions.
• Supports the use of OLAP mining models.
Database (ERD)
• Data base on which we are working is Relational database
DFD
Use Case Diagram
References
• https://healthpredictionfyp.wordpress.com/2015/09/13/projectmodules/
• https://msdn.microsoft.com/en-us/library/ms174806.aspx
• https://en.wikibooks.org/wiki/Data_Mining_Algorithms_In_R/Classifi
cation/Na%C3%AFve_Bayes
• http://www.mayoclinic.org/diseases-conditions
• https://labtestsonline.org/understanding/conditions/liver-diseasetypes/start/