Inspiration
The Project has been inspired by the fetal mortality faced by marginalized community and the lack of public awareness regarding the healthcare infrastructure and diagnosis available to them.
It aims to reduce errors during prescription of drugs especially that could happen due to communication barriers or human erros and also provides accessibility to people from different communities who may speak different language from the available physicians. It is an assistant for doctors, patients and community workers alike.
We build it using Android SDK and the backend is written with Python & Flask. We also integrated Redis to store patient and Doctor details and additionally, make use of Google CLoud technology to deploy our backend system.
Challenges we ran into We ran into
Limited public datasets for the medicine chemical composition. Also, lack of patient and doctor appointment transcript datasets, which made it difficult to create a model that could compare the appointment transcript and the prescription.
Accomplishments that we're proud of
The app is a fully functional product which connects multiple communities, we have deployed out backend to cloud, and the algorithm gives good recommendations based on publicly available datasets.
What we learned
We have learned about patient safety and problems that are faced today especially by marginalized communities.
What's next for AIHealthAssistant
Lost of possibilities, can be expanded using patient history and tracking of patient allergies or precious reactions. Can also be connected to healthcare workers.
Log in or sign up for Devpost to join the conversation.