The problem Aarogya solves

Rural and Remote residents encounter barriers to healthcare that restrain their ability to get the medical services they need. The problem of handling and keeping a note and regular monitoring is serious in India. Also, it has been continuously observed in no. of surveys that the nurses and doctors in India suffer through burnout due to heavy workload and hectic schedule, which is a matter of concern. The records of patients are not well-maintained on either grounds and hence seems to be a greater problem in the picture.

Also, in the current synopsis, extremely transmittable diseases like COVID-19 have forced people to avail of home hospitalization and treatment and, that's why treating everyone in need of continuous monitoring and regular checkup is difficult.

May it be a pandemic or the problem of distance, consulting a good doctor even for a regular checkup and urgent situations that need to be dealt with as soon as possible is a big issue. There's a need for proper management of a patient's historical record and, tracking of current health-stats is one of the challenges in front of the Medical System in India.

Hence, a solution needs to be proposed that solves the problems efficiently and is even accessible to all.

Challenges we ran into

• Dialogflow often gave unpredictable results, the accuracy threshold for choosing the right intent was a little challenging to find. Especially when we might be dealing with a person who may have a sensitive state of mind.

• Most web browsers don't support the tiff image format, which is contained in the dataset. While preprocessing the same for our web application we converted the images to .png format such that the model is trained with data i.e. similar to the expected input..

• Because Tensorflowjs is a new technology, web apps bulit using it may not work in some browsers. The user will see a message saying the "Ai is loading..." but that message will never go away because the app is actually frozen. It's better to advise users to use the latest version of Chrome.

• The web app for this project uses the Javascript language for the most part. We also used Javascript to feed the images to the model. The challenge is that Javascript is very fast whereas the model isn't fast enough to keep up. This difference in speed can lead to incorrect predictions. We used async/await to fix this.

• Integrating the Machine Learning models in the web application.