Machine learning model for Cardio vascular risk assessment

Project Title

Machine learning model for Cardio vascular risk assessment

Project Area of Specialization Artificial IntelligenceProject Summary

Cardiac Diseases? in Pakistan is the riskiest factor of death. 30 to 40 % of all deaths are due to cardiovascular diseases (CVD). Risk factor reaches up to 200,000 per year 2.1 million adults were estimated to have cardiovascular diseases, and 43.9% of the adult population is projected to have some form of cardiovascular disease by 2030. In random or remote situation, it couldn’t be possible to cure heart attack but we can predict the risk factor using cardiac escalation. Cardiac auscultation is a cost-effective, noninvasive screening tool that can provide information about cardiovascular hemodynamics and disease. However, with advances in imaging and laboratory tests, the importance of cardiac auscultation is less appreciated in clinical practice. The widespread use of smartphones provides opportunities for nonmedical expert users to perform self-examination before hospital visits. We are developing user friendly application help in real time simulation of heart auscultation and thus help in predicting heart attack in reliable manner. Objective is to provide handy solution regarding predicting heart attack.

Project Objectives

• Real time cardiac auscultation simulation using smart phone with no add-on devices for use at pre hospital stage
• Efficient recommendation system allows user to know about chance of heart attack
• Provide facility to common person either on journey or in remote location
• Reliable assessment regarding prediction of heart attacks
• Helpful for future care like precautionary measures or health care steps.

Project Implementation Method

We will be developing our project in the following modules:

Data Collection:

During this stage, we will be collecting Heart ascultation record to train and evaluate the model. Data set will be collected and benchmarked dataset of recordings will also be used in trainig and evaluation of the model

User Interface:

Android application will be developed through which the user will be able:

• To Register themselves
• To record heart auscultation and visualize waveform.
• Send a request to the server via REST API
• Get the Response back from the server, reporting and visualizing the result to the user
• Display the assessment in the category of heart auscultation as good, normal or bad condition.

Django REST API:

Django rest framework will be used to create a REST API

• A request from user through android application will be send to the server
• REST API will be used to CREATE, RETRIVE, UPDATE, and DELETE data from the server
• Once recording sent to the server, the REST API will be used to report the result to the client

Machine Learning Model:

The Heart auscultation estimation model will have sub modules implemented:

•  Preprocessing of recorded sounds
• Convolutional Neural Network

Technologies:

• Java
• Xml
• Python
• Django Rest Framework

Tool:

• Android studio
• Android Emulator
• Visual Studio Code
• Anaconda Distribution

Benefits of the Project

• Runtime assessment and simulation of cardiac auscultation and prediction of heart attack
•  using smart phones with no add-on devices at prehospital stage that reduce extra load
• Overcome the expenditure on dues. We want to assist the common person by detecting early heart attack caution.
• Target is to reduce the tension of the person who is suffering from pain while in traveling or in remote location.

Technical Details of Final Deliverable

Our software system will include following modules:-

User Interface:

Android application will be developed through which the user will be able:

• To record the heart sound
• Send a request to the Django server via REST API
• Get the Response back from the server, reporting the result to the user

Django REST API:

Django rest framework will be used to create a REST API

• A request from user through android application will be send to the server
• REST API will be used to CREATE, RETRIVE, UPDATE, and DELETE data from the server
• Once sound sent to the server, the REST API will be used to report the result to the client

Reliable Machine Learning Model:

A Reliable Machine Learning model to predict heart attack.

DOCUMENTATION

A complete user manual.

Final Deliverable of the Project Software SystemType of Industry Medical , Health Technologies Artificial Intelligence(AI)Sustainable Development Goals Good Health and Well-Being for PeopleRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	80000
Sound acquisition device	Equipment	1	35000	35000
stationary, printing etc	Miscellaneous	1	10000	10000
4G internet device	Equipment	1	12000	12000
Application server for hosting service	Equipment	1	23000	23000