While I’m sure the obvious systemic issues contribute to not looking for alternatives, that does sound like largely an issue inherent to optical pulse oximeters. Engineers aren’t miracle workers, they can’t change physics to their liking.
I’m sure pulse oximeters now are more accurate than they were 20 years ago. The fact we’re still using them is because no alternatives have been found which are as easy to use, reliable, and non-invasive as pulse oximeters, even with the known downsides.
That graph is hilarious. Enormous error bars, totally arbitrary quantization of complexity, and it’s title? “Task time for a human that an AI model completes with a 50 percent success rate”. 50 percent success is useless, lmao.
On a more sober note, I’m very disappointed that IEEE is publishing this kind of trash.