Inspiration
We aim to provide users with a data-driven, personalized approach to understanding their potential risk for diabetes. Our application strives to bridge the gap between medical assessments and daily health awareness, allowing users to make informed decisions about their well-being.
What it does
Our application utilizes machine learning models that are trained with 6 years of NHANES data on factors such as age, BMI, blood pressure, and more that are used to predict the risk of diabetes.
How we built it
We built this using Flask and python's scikit-learn machine-learning library for our model. We also build a simple user interface with a home, results, and about page.
Challenges we ran into
Collecting enough relevant data for the model was a challenge. Due to restrictions from both the federal level and from the institutions that generate data we had a limited amount of training data. This is one of the limitations of our model.
Accomplishments that we're proud of
Model accuracy
What we learned
Machine learning, Flask web application development
What's next for GluCause
Training on more data can improve the accuracy of the model. The data that it is trained on could be expanded to include more factors. By applying an epidemiological approach, GluCause can identify correlations between specific risk factors and an increased likelihood of developing diabetes. The user interface can be improved, such as the design of the questionnaire and how the diabetes risk result is displayed. To further support users, the platform could provide personalized recommendations for reducing diabetes risk based on their assessed risk level.
Log in or sign up for Devpost to join the conversation.