Inprovisus

• This image is currently processing. Please be patient...
  

• 

Inspiration

The market potential was discovered from the vacancy of intervention before the patient gets his foot into the hospital door. ER costs are quite high which makes visit to ER a hard decision, passing critical time threshold. ER is also where hospitals lose a lot of money in as well and could use operational improvement.

What it does

Inprovisus is on track with patient care; first, it improves patient outcome by alerting patients to receive treatment on time. Second, it also aids in patient predictability by understanding the disease factors and predicting the outcome.

How we built it

The team used Python and Watson API which trains on NPL on the backend. For front end, Node.Js was used for processing and querying to the chatbot. HTML, CSS was used for website creation.

Challenges we ran into

Many decision-making processes, including medical, is intuitive with many unpredictable factors and is not as structured.

Accomplishments that we're proud of

The application is not only technologically accomplished but also medically accurate which we achieved by interviews and research.

What we learned

The member's expertise in each field was truly beneficial.

What's next for Inprovisus

Partnership for predictive analysis of symptoms and expansion to other emergency conditions that can benefit from early decision for treatment.

Built With

• watson-api