Health care systems have to be improved and gain some cleverness in the area of big data management , analyses and predictions using well-trained AI models.
What it does
MvHealthBot is providing predictive health services by using LinearRegression AI models and NLP for identifying Covid19, diagnose diseases based on symptoms and alert the patient in case of disorders. MvHealthBot also simulates the process of fetching data from a public health API using a patient's medical ID and provides a diagnosis via the well trained AI model that has been built for the purposes of the app.
How I built it
I used python and google big query for the AI models creation and training. The models were published as APIs using google AI platform and cloud functions. Dialogflow has been used for the NLP part, in order to identify free text sentences context and intents. Google cloud functions have been used as the api layer. Node.js has been used for the backend api services. Fire base database and big query for data storage. Google cdn for content management.
Challenges I ran into
Model training and accuracy was a big challenge
Accomplishments that I'm proud of
MvHealthBot could be used in the health sector and help people get faster diagnosis and results
What I learned
To never give up
What's next for MvHealthBot
MvHealthBot is a prototype now. I would like to find funds and traction to extend it in order to be used in the health sector.