"it would help if 111operatives were at least trained nurses"
All the evidence says otherwise. It has been known for some 60 years that statistical, actuarial, prediction performs as well or better than expert opinion in every field it has ever been tried, including medicine. Paul E Meehl, a clinical researcher at the University of Minnesota, published a book in 1954 drawing this conclusion, and when he reviewed the subject 30 years later he said this:
"There is no controversy in social science which shows [so many] studies coming out so uniformly in the same direction as this one.
......When you are pushing 90 investigations, predicting everything from the outcome of football games to the diagnosis of liver disease and when you can hardly come up with half a dozen studies showing even a weak tendency in favour of the clinician, it is time to draw a practical conclusion."
It's not surprising, no human can hold a database of all the potential diagnoses, symptoms and their relative probabilities in their head like a computer can. Computers don't suffer from bias either, clinicians have been shown to see what they expect to see. A recent review of 134 studies found that clinicians outperformed statistical methods 8 times, and on 63 occasions statistical prediction fared better, the remainder were a draw. It has also been shown that clinicians fare even worse if they interview the subject rather than diagnose from a file of records. A few studies have tried combining statistics and expert opinion, they fared less well than statistics alone.
It will only work if the system is adequate, however, a few tick boxes won't do. The minimum you need is an interactive system that will choose the next question on based on the answer to the last as a clinician would. It's a win-win situation, the patient gets a better diagnosis, and the NHS frees up a huge amount of manpower.
Meehl: Clinical Versus Statistical Prediction
Myers: Intuition: Its Powers and Perils