Fwd: Interesting report on Watson as a diagnostitian

Mark Graber graber.mark at GMAIL.COM
Mon Aug 15 18:36:03 UTC 2016

Thanks to Ted Winslow for forwarding the story about Watson’s catching a diagnostic error.  If anyone knows the real details, I’d be interested.  If Watson really did ‘save the day’ in this case, that’s a pretty impressive feather in its cap.


Begin forwarded message:

From: Edward Winslow <edbjwinslow at gmail.com>
Subject: Interesting report on Watson as a diagnostitian
Date: August 15, 2016 at 2:26:05 PM EDT
To: "Art Papier, MD" <apapier at visualdx.com>, Mark Graber <graber.mark at gmail.com>, "Paul L. Epner" <paul.epner at improvediagnosis.org>

I am well aware that "The plural of anecdote is not data", but this is an interesting anecdote.

There was also a report on improvement in EHR. I wonder whether Art & Ted might want to look at how the EHR, as currently configured, might interfere with the diagnostic process by making thinking more difficult because clinicians (physicians) get frustrated with all the detritus in the EHR. We have discussed this some over the past few months.

Edward B, J. Winslow, MD, MBA
Home 847 256-2475; Mobile 847 508-1442
edbjwinslow at gmail.com <mailto:edbjwinslow at gmail.com>
winslowmedical.com <http://winslowmedical.com/>

"The only thing new in the world is the history that you don't know"
       Harry S. Truman, 33rd President of US (1945-1953)

"... it can be argued that underinvestment in assessing the past is likely to
lead to faulty estimates and erroneous prescriptions for future action."
        Eli Ginzberg, 1997

Moderator: David Meyers, Board Member, Society to Improve Diagnosis in Medicine

HTML Version:
URL: <../attachments/20160815/bc7ae572/attachment.html> ATTACHMENT:
Name: IBM Watson pinpoints rare form of leukemia after doctors misdiagnosed patient.docx Type: application/vnd.openxmlformats-officedocument.wordprocessingml.document Size: 140370 bytes Desc: not available URL: <../attachments/20160815/bc7ae572/attachment.docx> HTML Version:
URL: <../attachments/20160815/bc7ae572/attachment-0001.html>

More information about the Test mailing list