Multiple Disease prediction web app

Deployment

To deploy this project run the given snippet in terminal.

  streamlit run main.py

A disease predictive system using machine learning can mainly for diabetes and heart disease related make existing healthcare tasks easier, safer, and more effective by providing accurate predictions and personalized recommendations based on individual health data. It has the potential to revolutionize healthcare by enabling earlier detection, more effective prevention, and better treatment of diseases.

GOAL

This project involves disease prediction app using various machine learning algorithm where we can find if a person is suffering from disease or not

DATASET

The data set used in this is for diabetes prediction is -: https://www.kaggle.com/datasets/mathchi/diabetes-data-set
The data set used in this is for Parkinson's Disease prediction is -: https://www.kaggle.com/datasets/thecansin/parkinsons-data-set
The data set used in this is for Heart Disease prediction is -: https://www.kaggle.com/datasets/johnsmith88/heart-disease-dataset

DESCRIPTION

After using machine learning algorithm like logistic regression , SVM we will improve the model performance Them we will use stream lit cloud to deploy our app from where user fill the required values and app will tell whether it suffering from that disease or not

The ML model will be designed and trained using the collected dataset.
Once the ML models is trained, it will be tested using a separate set of data to evaluate its accuracy and performance.

MODELS USED

In this project I have used machine learning model like support vector machine or logistic regression.

LIBRARIES NEEDED

pickle-mixin
scikit-learn
pandas
matplotlib.pyplot
numpy
streamlit

VISUALIZATION

ACCURACIES

Accuracies and results of Algorithms used
The accuracy score achieved using SVM in Diabetes prediction is: 79.15 %
The accuracy score achieved using SVM in Parkinson's Disease prediction is: 87.17 %
The accuracy score achieved using Logistic Regression Heart Disease prediction is: 88.5 %

CONCLUSION

Implementing a Machine learning algorithms for disease detection aims to improve the accuracy, efficiency, and effectiveness of disease identification and management in health care sectors , leading to early disease detection losses. After building the model we can deploy a web app so that it can be easily accessible to public

Shubham kumar singh