A Web Application Prototype built for Doctors to find out whom to test for the infection first under a limited testing capacity by finding out the probability of a person having the infection.
My Final Project
In light of the ever-evolving Covid-19 situation. One day I was reading the news that CoronaVirus is spreading very quickly and highly developed countries like the USA and Italy are not capable of handling this virus. Most striking news was earlier it takes up to 2 days for just testing whether the patient is COVID positive or not. Then after some advancements also, it is taking some hours to test. So, I thought there should be the minimum time to test this virus so that actions can be taken as soon as possible because of its highly contagious nature.
Demo Link
Link to Code
https://github.com/ayushman17/COVID-19-Detector
What it does
This project is my contribution to helping to analyze the probability of a person having the infection. Technologies that were made to convert information so that it can be accessible to computers are used to aid people and I can contribute to a social cause. COVID 19 Detector is a Web Application Prototype Developed by ME and built for Doctors to find out whom to test for the infection first under a limited testing capacity by finding out the probability of a person having the infection. It takes the symptoms of the patient and within seconds it will try to predict the probability of whether the patient may be positive for coronavirus or not.
How I built it
This Web App is a dashboard developed in Flask (Python), HTML, Bootstrap/CSS, and using Machine Learning. World map is created using Mapbox-Map-GL. Currently, I'm using pythonanywhere.com 's server for the deployment of this web app.
Challenges I ran into
Accuracy was the greatest challenge because symptoms of a pneumonic patient and a person having COVID can be similar. After all, pneumonia can be a symptom of COVID-19. So, to classify COVID cases from pneumonic cases separate was a big challenge in itself.
Accomplishments that I'm proud of
What makes my model different from other detectors out there is I didn't use transfer learning for training my model. This model uses a technique called Logistic regression. By training the Database and import the machine learning model into an HTML file with the Flask (web framework).Data to be randomly generated for this Prototype. I tested my model the data and achieved 81% accuracy on the training set and 80% accuracy on the test set.
What I learned
During developing this system, I learned how new technologies like AI and ML can be helpful in any field like healthcare. Understand the important effect that technology has on the medical facility today.
What's next for COVID-19-Detector
For future work
- This model allows better priority to certain people who are affected by the virus.
- Right now I have designed the project for One Disease but it can be designed for more diseases.
- It acts as a life-saving device. -All the tools and technologies used for developing COVID-19 detectors are free hence the cost of production and development is close to NULL.
- COVID-19 detector required is an internet connection which makes it affordable for everyone.
- Also, I am doing more research on how to make this system even more accurate so that govt. and hospitals can make use of this system at a higher scale and people can be benefited from this.
Top comments (0)