News for hackers. Stuff that matters.
Re:Assessing Cardiovascular Risk Factors with Computer Vision by melling on Tuesday February 20, 2018 @03:13AM (#16418642)
“our algorithm could distinguish the retinal images of a smoker from that of a non-smoker 71% of the time.”

Wonder if smoking would decrease if people could see the change over time

Re:Assessing Cardiovascular Risk Factors with Computer Vision by dEnigma on Tuesday February 20, 2018 @04:22AM (#16418937)
People who still smoke nowadays aren't even deterred by the very graphic images of internal organs affected by smoking-related diseases that are printed on cigarette packs in many countries (next to very clear wording that smoking will harm you and people around you). So I doubt that this would make much of a difference in that regard.
Re:Assessing Cardiovascular Risk Factors with Computer Vision by moreless on Tuesday February 20, 2018 @05:13AM (#16419163)
Probably not. They already know the outcomes and don't seem to care.

However 71% seems like a very low number... Does that mean that in 7 out of 10 cases the system guesses correctly if the patient is smoker or not? That's not really impressive IMHO. What am I missing?

Re:Assessing Cardiovascular Risk Factors with Computer Vision by VMG on Tuesday February 20, 2018 @06:03AM (#16419398)
what is impressive is that humans cannot do it
Re:Assessing Cardiovascular Risk Factors with Computer Vision by TeMPOraL on Tuesday February 20, 2018 @06:39AM (#16419606)
They can get to 50% with a coin.
Re:Assessing Cardiovascular Risk Factors with Computer Vision by nicklaf on Tuesday February 20, 2018 @03:29AM (#16418709)
I seriously doubt that, just reflecting on how smokers so often remain unswayed¹ even by far more brutal prognostications about the habit's effect on their longevity.

¹well, unswayed about actually quitting now

Re:Assessing Cardiovascular Risk Factors with Computer Vision by mxschumacher on Tuesday February 20, 2018 @03:57AM (#16418831)
certainly interesting info for health insurance firms