Diabetes Terminator

version for phone
version for phone
Initial webpage
run the algorithm

Inspiration

Inspired by the potential of AI in healthcare, we decided to develop a tool to evaluate diabetes using existing data and machine learning algorithms.

What it does

Our solution is a user-friendly webpage that acts like a questionnaire to assess a person's diabetes risk. It also provides warnings if the user's symptoms are highly related to positive cases in the database.

How we built it

To build our program, we utilized the logistic regression method, which is a statistical technique commonly used for analyzing datasets. We built the program using React, Node.js, MongoDB, and Python. We calculated statistical indicators from the confusion matrix to ensure the dataset's reliability.

Challenges we ran into

One of the biggest challenges we faced was finding raw data on health topics suitable for big data and machine learning. Thanks to UC Irvine Machine Learning Repository, we were able to obtain open data on diabetes research.

Accomplishments that we're proud of

As a team, we are proud of our accomplishment in applying our knowledge of computer science to solve real-world problems in healthcare.

What we learned

The experience has taught us the value of teamwork, and how to build a full-stack program from scratch in a short time.

What's next for Diabetes Terminator

Adding data submission function to scale up our dataset and renew statistical indicators. By doing so, we aim to improve the accuracy of our program and provide even better evaluations for diabetes.