0% found this document useful (0 votes)
90 views4 pages

Prediction of COVID-19 Using Machine Learning Techniques: Project Title

This document proposes using machine learning techniques to predict COVID-19 from routine blood tests. A deep learning neural network model will be developed as a web application using Django as the framework. The goals are to provide fast, affordable COVID-19 diagnosis by analyzing routine blood exam data. Beneficiaries would be medical sectors able to better identify infections. Technologies like Keras will be used to train the algorithm, while Joblib and Bootstrap implement features. The project team plans to collect data, build and test modules, then integrate everything into a web application hosted on Heroku.

Uploaded by

wael El-Begearmi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
90 views4 pages

Prediction of COVID-19 Using Machine Learning Techniques: Project Title

This document proposes using machine learning techniques to predict COVID-19 from routine blood tests. A deep learning neural network model will be developed as a web application using Django as the framework. The goals are to provide fast, affordable COVID-19 diagnosis by analyzing routine blood exam data. Beneficiaries would be medical sectors able to better identify infections. Technologies like Keras will be used to train the algorithm, while Joblib and Bootstrap implement features. The project team plans to collect data, build and test modules, then integrate everything into a web application hosted on Heroku.

Uploaded by

wael El-Begearmi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

Cairo University

Faculty of Graduate Studies for Statistical Research


Professional Studies
Academic Year 2021/2022

Project Title
Prediction of COVID-19 using Machine
Learning Techniques
A Proposal Presented for Fulfillment of The Professional
Diploma Project in Software Engineering

Project Team
Wael Abbas Mohamed Baseem Elbegearmi
Eman Elsayed Elshahat

Supervisor
DR.Tarek Aly

Cairo, Egypt
2022
Introduction
The worldwide pandemic of coronavirus disease (COVID-19) has caused pressure on the health sector
around the world. Because the increasing number of cases day by day and the need to diagnose positive
cases as quickly and accurately as possible, the need for clinical decisions making system has urgently
arisen. In this study, we apply machine learning techniques to laboratory data of patients that are likely to
have received a COVID-19 disease to establish an intelligent inference system for automated diagnosis of
COVID-19.

Problem
The rRT-PCR test, the current standard for the detection of coronavirus disease (COVID-19), however
presents with known shortcomings, such as long turnaround time, potential shortage of reagents, and
expensive equipment. Machine learning techniques have been employed to detect COVID-19 from lung
CT-scans with 90% sensitivity. Although chest CTs have been found associated with high sensitivity for
the diagnosis of COVID-19(Ai et al., 2020), the hematochemical values of routine blood exams could
represent a faster and less expensive alternative.

Proposed Solution
The proposed solution is to develop web-based application for automated diagnosis of COVID-19 from
the routine blood test using neural network model (DNN). One recent study compared between seven
machine learning models over three laboratory data. Therefore, the deep learning models adopted in this
project show the best performance in diagnosing COVID-19 disease from routine blood tests.

Objectives
This project aims to provide fast and affordable ways based on knowledge and experience. In the last few
years, digital revolution has offered comparatively low-cost and obtainable means for collection and
storage of data. Machines for data collection and examination are placed in new and modern hospitals to
make them capable for collecting and sharing data in big information systems. The proposed solution will
run the proposed algorithm over correct diagnostic patient record entered in a computer as an input.
Results can be automatically obtained from the previous solved cases. The medical sector is the first
beneficiary of the proposed project.

Beneficiaries
Fast and simple solution can impact positively on hospitals system to identify infection and present
patient-specific preventive interventions. The medical sector is the first beneficiary of the proposed
project, as one of the significant benefits of machine learning in healthcare is the classification and
analysis of infections and illnesses. It makes it more manageable as it was difficult to diagnose in the past.

1
Implementation Technology
Django is a high-level Python web framework that encourages rapid development and clean pragmatic
design. Built by experienced developers, Django will be used as the web application core to manage data
models and application pages processing over HTTP protocell.

Joblib is a set of tools to provide lightweight pipelining in Python. In particular: transparent disk-caching
of functions and lazy re-evaluation, Joblib will be used to cash and reload the trained algorithm.
Bootstrap is CSS framework. It contains HTML, CSS and JavaScript-based design templates for
typography, forms, buttons, navigation, and other interface components. Bootstrap will be used to design
the user input page and result page in our project
Keras is an open-source software library that provides a Python interface for artificial neural networks. It
is designed to enable fast experimentation with deep neural networks, and Keras will be used for
Algorithm training and prediction٫
Heroku is a platform as a service (PaaS) that enables developers to build, run, and operate applications
entirely in the cloud. will be used to host the project application.

Productivity and Collab Technology


Collaboration technologies cover a wide range of tool and as far as your project will be available in
github as open source with the basic instructions for local deployment, thus further extension could
happen, as module in big software or as an extension for other softwares, and it's up to the programmers'
creativity.

Project Plan

Roles in project. You have understood each team member roles and assigned
responsibilities.

Task Name Duration (days) Status


Collect information 30 Complete
Write proposal 7 Complete
Identify Technology
2 Complete
Write research draft 5 Complete
Build module 5 Complete
Test module 2 Complete

2
Integrate 12 On going

You might also like