Altrue | Bridging the gap in specialized healthcare

Home Screen
My Treatments Screen
Compare Treatments Screen
Add a new condition...
Searching for matching treatment plans....

Inspiration

When it comes to Cole and Matt, you know healthcare will enter the conversation some way some how.

Well, the whole idea started with the thought of mechanics. We were discussing the economics of mechanics, and how they can charge us pretty much anything they want because of our lack of knowledge of car parts. But that got us thinking, what other information gaps are there still remaining in this digitally-informed world?

As relatively sporty individuals, we related to how we've both spent a lot of time in doctor's offices for longer-term injuries and conditions, and we reflected on how little we actually knew about our treatment plans in the past. As we continued to do research and call up friends and family asking about their experiences in specialized treatment, we realized that most people aren't well-informed on treatment options and medications before walking into the doctor's office, causing a pretty large information gap.

We built Altrue to bridge this gap and educate patients on what types of treatments could potentially work for them. That way, patients could start more two-way dialogues with their specialists and become more literate in their personal health journeys.

What it does

The Altrue platform collects user information such as age, sex, ethnic group, and family history, as well as health information like medical symptoms and their respective severities and uses them as parameters to match the user with treatment plans used by other patients in the past. Using the data entry points as parameters to determine the closest matches, Altrue personalizes the treatment plan so that the user can get a good scope of what medications and treatments may be right for them.

How we built it

We built the Altrue application using the MERN Native stack, employing a React Native front-end, Express.js and Node.js middleware, and MongoDB database. That way, the platform can be easily converted into a web application for laptops and desktops.

Also, since the platform relies heavily on user-inputted data and the utilization of that data for matching patient cases, we hope to use this de-identified data to look for treatment trends and potentially uncover insightful findings in regards to the timeline of procedures and prescriptions.

Challenges we ran into

A big challenge we ran into is how to calculate the weights for the different information parameters. We spent some time doing research and eventually came up with a combination of weights that did a good job of matching similar patient cases.