CoHerent

Be Coherent with your Cost of Health. Predict and Prepare for your Future Medical Costs.

Inspiration

3 P’s: Patients, Providers, Payers Multi-Billion dollar companies supporting Payers and Providers, but nothing for Patients Personal Experience. We have personally seen the in’s and out’s of the healthcare industry from our past internships. We all know people struggling with healthcare costs. There has been lots of social unrest in recent months around healthcare costs, our goal is to make healthcare costs clear and concise.

What it does

Lets users input their personal data along with possible health conditions or concerns. The model calculates predicted future costs based on a cleaned and processed synthetic data set.

How we built it

Processed data and put into a model and ultimately built a full stack app with the model.

Challenges we ran into

Formatting the data was a definitely big challenge since healthcare data is hard to acquire. It took us a long time to find a dataset that we wanted to work with. Even then, cleaning and processing 13 different CSV files into a final data frame was challenging. Determining model metric and deploying model / structuring inputs was another challenge we spent a lot of time on.

Accomplishments that we're proud of

Process and cleaning a complex, synthetic healthcare data set. We are proud of completing and providing a working model.

What we learned

We learned how to build a model from data processing, to training, and to deployment.

What's next for CoHerent

Our model performs well but it could be better. Since we only included encounter claim costs, we also want to include other costs such as medicine / immunization and procedure costs. We could also explore other model architectures. More and better data will ultimately help to reach a better model.

We hope that our model is the first step towards a more transparent and equitable healthcare system