Surely this study should have gone one step further to compare the expert panel's diagnosis against ResApp's diagnosis? Its all well and good to say "you are making bad calls mr medicine" but in our case, shouldn't that be followed with statistical evidence that ResApp will reduce incorrect diagnoses by X% in XYZ respiratory diseases? Or would that need to be another paper? Surely while they had all the participants there they actually used the app and compared it.
RAP Price at posting:
4.3¢ Sentiment: Hold Disclosure: Held