During the ideation phase, our team discussed our relevant background experiences. In addition to technical expertise, we had two team members that came from the life science industry who observed similar pain points with regards to clinical trial managers lamenting the pain of patient dropouts. More specifically, a drug that could potentially save the lives of millions of people is sometimes rejected due to patient dropouts rather than the effectiveness of the drug itself.
What it does
ClinSense is a predictive analytics tool that estimates patient dropout likelihood during clinical trials to predict dropouts, manage patient relationship, and improve patient retention. The reasons for patient dropouts are very well established, and yet there hasn’t been a product in the market that leverages these reasons to develop relevant metrics. Industries like healthcare and education have been adopting the use of predictive analytics to predict patient cancellations and student dropouts, so we were absolutely convinced that the same application could be used with clinical trials.
How we built it
For user interface design, we used Adobe illustrator to design the mockup screens. For the prototype, we built a web app with Flask and SQLite for the back-end framework and Materialize for the front-end.
Challenges we ran into
This is our first hackathon, so we were all beginner hackers with limited amount of coding experience. We came in having only a vision of the idea we wanted to pursue, and it took some time to design the technical architecture and learn to use the frameworks.
Accomplishments that we're proud of
We made the first functional prototype and deployed it live. It is looking pretty awesome!
What we learned
We learned to design for web architecture and use Flask and Materialize frameworks. We defined a preliminary algorithm, based on 40 different metrics (i.e. socioeconomic status, side effects of intervention, distance from trial site) that would score a patient’s risk of dropout, based on our research and readings on this topic.
What's next for ClinSense
To refine our model, we would like to partner with pharmaceutical companies to obtain (potentially masked) clinical trial data. We are in parallel developing a business plan. Our next milestone is to develop a fully functional product to demonstrate the proof of concept. We plan to present to potential investors and secure seed round investment.