Hacker News new | ask | show | jobs
by epaladin 4285 days ago
Which just made me wonder if it's possible to train a hidden markov model for detecting that. Trigger a flag that says "wowzers, now you're in unhealthy state territory". Otherwise it's real hard to tell if occasional engagements with unhealthy behaviors are having an impact on health overall. I imagine we'll get to the point of being able to do this sort of thing in about five years.
2 comments
bitexploder 4285 days ago
"In about 5 years" is often code for, "It is really cool, and it seems feasible, but I have no idea how difficult it really is."

Also, we have the basic capability for this now. Regular blood testing, etc. Get a physical. Get blood work every 3-6 months. Its just basic stats for your body. I do this. To me it is like checking the oil levels in a car. Why would you not collect this type of data for your body, which is arguably one of the most important "possessions" a person can own?

link
graeme 4284 days ago
What's included in the blood testing?

I'm in Canada, and the idea of routine blood testing for young people (I'm 29) doesn't seem to have caught on.

link
danudey 4284 days ago
That's because our medical system isn't for-profit, so we only get blood tests when they're medically necessary and not just for convenience.
link
dragonwriter 4284 days ago
> Which just made me wonder if it's possible to train a hidden markov model for detecting that. Trigger a flag that says "wowzers, now you're in unhealthy state territory".

Unlikely, because how much "less healthy" becomes "unhealthy" is an arbitrary subjective point rather than being something fixed and objective (and because the degree of health impact of various decisions varies widely based on individual factors that aren't all known with any kind of precision, so, even with a fixed objective of 'healthy state', the point at which the average person would reach it and the point at which you reach it may be not at all similar.)

> I imagine we'll get to the point of being able to do this sort of thing in about five years.

I imagine we'll not be meaningfully closer to being able to do this than we are now in about five years. (OTOH, I wouldn't be surprised to see someone marketing something that purports to do this in that time.)

link