• melsaskca@lemmy.ca
    link
    fedilink
    English
    arrow-up
    1
    arrow-down
    32
    ·
    5 days ago

    WTF? You take a reading and whatever the results are, are the results. Overestimating?! Must be “AI” then.

      • melsaskca@lemmy.ca
        link
        fedilink
        English
        arrow-up
        1
        arrow-down
        1
        ·
        3 days ago

        I’ve never seen passive-aggressive begging before. So, I guess I’m capable of learning new things, although I’m no genius. It’s not aversion, more like bliss.

    • phdepressed@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      24
      ·
      5 days ago

      Pulse oximeters do not directly read oxygen. They use light absorption to approximate how much hemoglobin is oxygenated or deoxygenated. The de/oxygenation changes the light absorption (its why arterial blood is bright red and venous blood is darker). That is then converted by mathematical algorithm to a estimate of oxygenation the “reading”.

      This is stating essentially that in black skinned people the changes in light absorption because of the skin color results in the algorithm giving a falsely higher reading than is actually present in the patient.

      The math will have to be fixed in some way for black people to receive appropriate care. Whether that is a device unaffected by skin color or different math based on skin color needs to be figured out.

      • melsaskca@lemmy.ca
        link
        fedilink
        English
        arrow-up
        1
        ·
        4 days ago

        I go by headline wording and gut feelings. It’s either my fault or I’ve been conditioned by the “algorithm” to do this. /s