Comment

Comment on Are there any genuine benefits to AI?

I read that one LLM was so good at detecting TB from Xrays that they reverse engineered the “black box” code hoping for some insight doctors could use. Turns out, the AI was biased toward the age of the Xray machine that took each photo because TB is more common in developing countries that have older equipment. Womp Womp.

source

Sort:hotnew top

sunbeam60@lemmy.one ⁨1⁩ ⁨year⁩ ago
A large language model was used to detect TB in X-ray? Do you not just mean Machine Learning?

source
- doctorcrimson@lemmy.today ⁨1⁩ ⁨year⁩ ago
  There are supposedly multiple Large Language Model Radiology Report Generators in development. Can’t say if any of them are actually useful at all, though.
  
  source
  - NeatNit@discuss.tchncs.de ⁨1⁩ ⁨year⁩ ago
    okay, but there still needs to be a part that processes the scan images and that’s not LLM.
    
    source
    doctorcrimson@lemmy.today ⁨1⁩ ⁨year⁩ ago
    So you’re saying because the LLM isn’t operating the machinery and processing the data without any non-LLM software then none of it is LLM? Stay off the drugs, kid.
    
    source
ViscloReader@lemmy.world ⁨1⁩ ⁨year⁩ ago
What’s TB?

source
- DrakeRichards@lemmy.world ⁨1⁩ ⁨year⁩ ago
  Tuberculosis
  
  source
- nihilvain@lemmy.ml ⁨1⁩ ⁨year⁩ ago
  Tuberculosis
  
  source
- NeatNit@discuss.tchncs.de ⁨1⁩ ⁨year⁩ ago
  Watch any video at random by John Green (vlogbrothers, and author of several successful books that I haven’t read) and you’ll know more than you could ever hope about TB.
  
  source
PrincessLeiasCat@sh.itjust.works ⁨1⁩ ⁨year⁩ ago
That’s super interesting, TIL

source