1. Project Review-0
on
MULTIPLE DISEASE PREDICTION SYSTEM
by
Lohiith Dinesh Ramiya (RA1911043010051)
G .Lakshmi Reethika(RA1911043010053)
A.S.Raghavendra (RA1911043010065)
Under the guidance of
Dr.S.Murugaveni
Assistant Professor, Departmentof ECE
3. Abstract
• Many of the existing machine learning models for health care analysis are concentrating
on one disease per analysis. Like one analysis if for diabetes analysis, one for cancer
analysis, one for skin diseases like that.
• There is no common system where one analysis can perform more than one disease
prediction. In this project proposing a system which used to predict multiple diseases by
using StreamLit API.
• In this project used to analyse Diabetes analysis, Heart disease and Parkinson’s analysis.
Later other diseases like skin diseases, fever analysis and many more diseases can be
included.
• To implement multiple disease analysis used machine learning algorithms, tensorflow and
StreamLit API. Python pickling is used to save the model behaviour and python
unpickling is used to load the pickle file whenever required.
4. Motivation
• There are multiple techniques in machine learning that can in a variety of industries,
do predictive analytics on large amounts of data. Predictive analytics in healthcare is
a difficult endeavour, but it can eventually assist practitioners in making timely
decisions regarding patients' health and treatment based on massive data.
• Diseases like Breast cancer, diabetes, and heart-related diseases are causing many
deaths globally but most of these deaths are due to the lack of timely check-ups of the
diseases. The above problem occurs due to a lack of medical infrastructure and a low
ratio of doctors to the population.
• This Prediction System, using various parameters helps to overcome the above
problem of lack of medical infrastructure and a low ratio of doctors to population.
• It acts as an immediate disease detector helping the doctors to treat the patient as
early as possible.
5. Literature Review
AUTHORS, TITLE, JOURNAL INFERENCE PARAMETER
Multi Disease Prediction Model by
using Machine Learning and Flask API
Author
Akkem Yaganteeswarudu
• Multi disease prediction model is used
to predict multiple diseases at a time.
• Here based on the user input disease
will be predicted.
• The choice will be given to user. If the
user want to predict particular disease
or if the user don't enter any disease
type then based on user entered inputs
corresponding disease model will be
invoked and predicted.
∙ parameters like :
∙ age, sex, bmi, insulin, glucose, blood pressure,
diabetes pedigree function, pregnancies,
considered in addition to age, sex, bmi,
insulin, glucose, blood pressure, diabetes
pedigree function, pregnancies are used
∙ Naive Bayes, Decision Tree, Random Forest is
used
Multiple Disease Prediction System
Author
Ankush Singh, Ashish Yadav, Saloni
Shah,Prof. Renuka Nagpure
• The main objective of this project was
to create a system that would predict
more than one disease and do so with
high accuracy.
• Because of this project the user doesn’t
need to traverse different websites
which saves time as well.
• Diseases if predicted early can
increase your life expectancy as well as
save you from financial troubles.
For the prediction the authors have used various
machine learning algorithms like
• Random Forest
• XGBoost
• K nearest neighbor (KNN) to achieve maximum
accuracy.
6. Literature Review
AUTHORS, TITLE, JOURNAL INFERENCE PARAMETER
Multi Disease Prediction
System
Author
K.M. Al-Aidaroos, A.A. Bakar, and Z. Othman
• For this study, the authors compared
Nave Baeyes to five other classifiers:
LR, KStar (K*), Decision Tree (DT),
Neural Network (NN), and a basic rule-
based algorithm (ZeroR).
• In the experiment, NB outperformed the
other algorithms in 8 of the 15 data
sets, leading to the conclusion that the
predictive accuracy results in Nave
Baeyes are superior to other
techniques.
∙ The criteria used in this study were age,
sex, smoking, being overweight, drinking
alcohol, blood sugar, heart rate, and blood
pressure. The risk level for various
parameters is saved with their ids ranging
from 1 to 100.
Diabetes Prediction using
Machine Learning
Techniques
Author
N. Joshi ,K.VijiyaKumar
• The proposed model gives the best
results for diabetic prediction and the
result showed that the prediction
system is capable of predicting the
diabetes disease effectively, efficiently
and most importantly, instantly.
• This project proposes an effective
technique for earlier detection of the
diabetes disease.
● The proposed approach uses various
classification and ensemble learning
method in which SVM, Knn, Random
Forest, Decision Tree, Logistic
Regression and Gradient Boosting
classifiers are used
7. Objectives
• The objective is to build a multi disease prediction system which will use real time
parameter such as glucose level, blood pressure value, Insulin level, BMI value to
predict the type of disease that person would likely be suffering at that particular point of
time.
• The model will learn the health conditions of a person, not only this, it will also learn
about the internal body parameters and will predict if the person is diseased according to
the features uploaded to the model.
• This will help to save person time as the model will learn the person’s body conditions
and will predict the if the person’s health is fine or not.
• The prediction system can also be used as a backend technologies and in other social
media app as a link to recommend the web application to the user
8. Design Methodology
• Dataset Collection (Real time data)
• Data Cleaning
• Data Preprocessing
1)Missing Values removal
2)Splitting of data
• Apply Machine Learning Algorithm
• Improving the accuracy
• Deploying the model as Web App
9. Project Plan
• Our plan is to collect the real parameters through various sources convert it into excel
sheet/csv file according to the parameters we have mentioned earlier.We can also
collect the data from various sites such as Kaggle, Saarbruecken etc.
• This will create our traning data set after which we will apply various data cleaning
methods to clean the data,after which we will process our data with the help of data
preprocessing methods.
• When the data is cleaned and processed we will train the data with help of various
Machine learning as well as Deep leaning algorithm and will choose the best performing
algorithm with high accuracy.
• When we will get the algorithm we will try to improve its accuracy by reducing the
errors and processing the data more.
• We will try to make and user iterface once the model starts predicting the data
accurately and deploy the model through User-Interface so that it can be used by
anyone.
10. Project Timeline
Review 1 Diabetes disease detection model to be shown for the
first review.
Review 2 Heart disease detection and Parkinson’s detection
model to be shown for the second review. The front
end to the web app is also shown.
Review 3 The fully functioning webapp to be presented for the
final review.
11. Requirements and Proposed Budget
As we are doing a machine learning based project so we will be using the free software's
only like Jupiter notebook, google colab and python and python libraries. All of these
requirements are free of cost and can be developed by just having a desktop/laptop.
Since We are using Open source software's there is no budget for this project
12. Project Deliverables
• Predict if the person is suffering from the particular disease.
• Input real-time parameters like glucose level, blood pressure value, Insulin level, BMI
value
• Analyse the parameters input by the user.
• Based on the parameters and body values we predict if the person is diseased.
• Develop the front end user interface to take input and predict.
13. Conclusion
The proposed work brings diabetes, heart disease, and Parkinson’s under
a single platform by deploying the trained models using the StreamLit
API framework which is a lightweight framework. Three classification
algorithms are used for training the models, in which the Support Vector
Machine gave good accuracy values for the disease prediction of diabetes
and Parkinson’s and Logistic Regression for the disease prediction of
heart disease.In the future, we can expand this work by adding more
diseases that are trained by machine learning models and also can include
the disease that involves deep learning models.
14. References
• [1] Naveen Kishore G,V .Rajesh ,A.Vamsi Akki Reddy, K.Sumedh,T.rajesh Sai Reddy, ”Prediction Of Diabetes Using
Machine Learning Classification Algorithms”.
• [2] Gavin Pinto, Sunil Jangid, Radhika Desai, ”Understanding the Lifestyle of people to identify the reasons of Diabetes
using data mining”.
• [3] M.Marimuthu ,S.Deivarani ,R.Gayatri, “Analysis of Heart Disease Prediction using Machine Learning Techniques”.
• [4] Purushottam, Richa Sharma ,Dr. Kanak Saxena, ”Efficient Heart Disease Prediction System”.
• [5] Adil Hussain She, Dr. Pawan Kumar Chaurasia,” A Review on Heart Disease Prediction using Machine Learning
Techniques”.