Astro Hacker News - Show HN: I have trained 15 blood glucose forecasting models on my own data

srdjanb |next [-]

This is cool. The accuracy looks good too, except for a few time windows. Do these models take into account dietary info, and if yes, how?

0xdeadf1sh |root |parent [-]

Carbohydrates & insulin are both accounted for during inference. I'm not sure if that's what you meant by dietary info though.

nuthje |next |previous [-]

89% TIR, well done! Cool to see the research, I’m surprised there aren’t more in-depth n=1 studies out there from statistics/data-savvy diabetics. I built a small dashboard exactly collating carb, insulin, sleep, and movement data and trying to coax out useful correlations to help manage. Some interesting insights, but clearly I should eat less and move more. Keep up the good work, and thanks for sharing!

0xdeadf1sh |root |parent [-]

Yeah I'm thinking of adding more (especially recent) models and compare their published metrics with those of mine to see how they hold up. Then I'll likely post about it here again. See you then!

zenpositive |next |previous [-]

Very cool very nice work!

orasul |next |previous [-]

awesome

Bigchrome |next |previous [-]

I achieved 100% TIR with my model. I'm not T1D, but same same.

JK, as the spouse of someone with T1D I really appreciate seeing this!

ekg2 |previous [-]

[dead]