Improving short-term prandial blood glucose outcomes for people with type 1 diabetes, a complex disease that affects nearly 10 million people worldwide. We aim to leverage semi-supervised learning to identify unlabelled meals in time-series blood glucose data, develop meal-scoring functions, and explore causal machine-learning techniques.
Incorporating glycemic load and glycemic index datasets could improve our modeling. We should automate incorporating the data from some open-source datasets into our project:
Incorporating glycemic load and glycemic index datasets could improve our modeling. We should automate incorporating the data from some open-source datasets into our project:
https://world.openfoodfacts.org/data
https://fdc.nal.usda.gov/download-datasets.html
It is also worth investigating if more data sources are available and scrapable.