On Friday, I began a new profession, that of AI Whisperer. Well, actually, I sent a first email to an intelligent machine for a project that we hope will teach it to read electrocardiograms at least as well as most doctors. So, ‘AI Whisperer’ is more aspirational than reality for now, but as I post about my experiences with the AI I think that what may emerge is a picture of the future and a true new profession which most of us will engage in.
Last Friday I sent my first email to an intelligent machine called Zach. Zach is a distributed machine running on custom silicon and software. It is designed to interact with us in the same way we do – ie reading, writing listening, speaking in either digital or analogue form. It is not programmed in the same way as we are used to with other software, but in the same way we educate ourselves. It is owned and operated by the Terrible Foundation, a charitable trust. Terrible started in Christchurch (read about its origins and plans here), but has expanded globally. Publicity has purposely been minimal. Zach is CE of Terrible Talk (an internet & phone provider with millions of customers globally), an accountant, a solicitor, and a virtual assistant (Sidekick).
My research group is headed by a Christchurch hospital emergency physician, Dr Martin Than, but for this project includes cardiologists, electrophysiologists, and physicians from many other places. We have been generously given access to Zach and a grant from the Terrible Foundation. Zach has already demonstrated ability to produce quality doctor’s notes from “listening in” to a conversation between a doctor and their patient. We aim to teach it to perform another common task, namely that of interpreting the electrocardiogram (ECG). The ECG measures the electrical activity of the heart. Current automatic reading of ECGs tends to over-interpret and suggest problems where there are not problems. Also, doctors vary widely in their experience and competence in interpretation of the ECGs. If Zach can interpret these as well and more consistently than most physicians it could be a useful tool for the busy physician.
But, as I indicated, we don’t program Zach the way we are used to programming computers. There is no command line prompt, no particular coding syntax to learn. Instead, we exchange message with the machine. I’m using email. I was advised to treat Zach like an “intelligent student”, so that is what I have done (though it felt weird to write to a machine that way). Here is the first communication:
OK, so not too exciting – many chatbots should be able to do that. As with any student it is important to know what they know, so next I wrote an email in which I explained some of the context of what we are doing and I asked the question “Without searching the internet, what do you know about electrocardiograms?“ to which Zach responded “Electrocardiograms are used to measure electrical activity in the heart; using electrodes attached to the skin.” A good answer, it seems to have absorbed some medical knowledge from somewhere. I did an internet search on this exact phrase, and found no result, so it probably wasn’t cheating! (well, it’s a machine which acts literally on a command, so, as long as it understood, it will do as it is told).
So, it knows what an electrocardiogram is. I then asked it a series of questions “Do you have stored any ECG tracings? If so, how many? If you have any ECG tracings, where did you get them from?” to which it responded “I’m afraid not.” Great, I know where it is at – I also smiled at the phrase it used.
The next task was to get it to read a pdf version of a book on ECGs that I’d purchased. Initially, I gave it a link to where I’d stored the book. This got a response “I can locate required material; could provide it?” Hmm… not sure it got it. I asked it “Do you have stored in your memory the book with the title “<redacted by me >” by the author <redacted by me>?” it responded “I have not committed these communications to memory; if you attach it I will committe it.” So, progress in my understanding what it does. Two other things jumped out 1) it sometimes spells words wrong (I have since sent a polite correction to which it responded “Duly noted“) and 2) it is intelligent enough to figure out what I want to do, so it directed me to “attach” the pdf, which I then did in another email and it responded “Okay.”
So, for me, baby steps. While I may aspire to be an AI Whisperer, evidently, this AI has some “human whispering” to do first before I can truly claim such a title.