rmstein@ieee.org
Date: Mon, 11 Feb 2019 21:38:56 -0800
https://www.scientificamerican.com/article/a-machine-gets-high-marks-for-diagnosing-sick-children/
"The machine received good grades, agreeing with the humans about 90 percent
of the time. It was especially effective at identifying neuropsychiatric
conditions and upper respiratory diseases. For acute upper-respiratory
infection, the most common diagnosis in the huge patient group, the AI
system got it right 95 percent of the time. Would 95 percent be good enough?
One of the next questions that needs to be researched, Zhang says, is
whether the system will miss something dire. The benchmark, he says, should
be how senior physicians perform, which also is not 100 percent."
"Study Suggests Medical Errors Now Third Leading Cause of Death in the U.S." https://www.hopkinsmedicine.org/news/media/releases/study_suggests_medical_errors_now_third_leading_cause_of_death_in_the_us says, "using hospital admission rates from 2013, they extrapolated that based on a total of 35,416,020 hospitalizations, 251,454 deaths stemmed from a medical error, which the researchers say now translates to 9.5 percent of all deaths each year in the U.S."
"Medical errors" are categorized by a spectrum.
http://www.covermd.com/Resources/Medical-Errors-List.aspx identifies "The
Ten Most Common Medical Errors in the US."
When a "difference of diagnostic opinion" arises between the silicon-based physician-assistant (SiMD) and the carbon-based attending physician (CMD), how are these conflicts resolved? Will a hospital require a "vote" by multiple CMDs to overrule the SiMD's? What is the protocol?
What happens when both SiMD and CMD diagnostic opinions align, but they are both wrong, and the patient is given inappropriate treatment? In an emergency situation where CMD resource is stretched, what priority will be given to the SiMD's diagnostic findings?
If SiMD's can be shown to reduce medical error rates, then their role as an adjunct to a physician's judgment may be appropriate.