What is evidence in diagnosis

Bob Latino blatino at RELIABILITY.COM
Mon Mar 26 11:01:57 UTC 2018


Hi Phillip


I recall you trying to launch a project like this in the past, less the AI piece.


Seems like you already have an RCA partner with Chris Eckert at Sologic on the AI/RCA piece.  I know he has been toying with Watson to see how it works with his Sologic application.  I heard him present last year on his testing thus far.  He and I are on the same page when it comes to our world view of RCA.


We are doing similar via our partners as GE Digital (GED), but I will admit that GE handles most of the AI/IIoT/ML & DL integrations into our PROACT RCA module that we license to them.  They have many more resources than we do in that arena.


I certainly see promise in this area and always have.  However, the technology piece will still be dependent on the depth and breadth of the quality of the initial RCA.  In my experience HC overall, is not adept at conducting effective RCA's.


Most of what I have seen is an emphasis on 'compliant RCA's' versus 'effective RCA's'.  Since most hospitals are accredited in the U.S., and deaths due to medical error continue to rise, there does not appear to be a correlation between compliance and patient safety.  That's the core problem as I see it.  If the AI technology side is built on bad data, it will fail also.


Good luck with your proposal and if I can contribute, let me know how.


Take care Phillip

Bob


________________________________
From: pgbentonmd at aol.com <pgbentonmd at aol.com>
Sent: Friday, March 23, 2018 2:48 PM
To: IMPROVEDX at LIST.IMPROVEDIAGNOSIS.ORG; Bob Latino
Subject: Re: [IMPROVEDX] What is evidence in diagnosis

Bob,
Attached is a project that is still in the concept stage, planning for grant application. The first major hurdles are the advancement of artificial intelligence (AI) capabilities AND the expansion of EHR to include all of the necessary elements without being prohibitively burdensome on the persons with the facts.

The AI conclusion would be a probable root / contributing causal analysis to be confirmed by humans with the proper experience. It might enter into mediations and lead to  more just settlements, but would not be admissible in court like all other things occurring in court ordered mediation.
 
The big thing would be that remedial measures would be mandated and the information disseminated (without names of the parties), rather than hidden in a non-disclosure agreement as is done now. Its whole purpose is for medical education and prevention of future medical error and significant patient harm.
 
Some, like The Joint Commission, will complain that legislation that requires mandatory RCA and appropriate remedial measures is too proscriptive, but isn't Public Safety the basic point of most of our laws that determine conduct?

This is admittedly aspirational but I think the result could be worth all of the effort required. Please give me your thoughts.
PGB

Phillip G. Benton, MD, JD
Orthopedic Spinal Surgeon (ret.)
Adjunct Prof., Emory Law School
Atlanta, Georgia
pgbentonmd at aol.com


-----Original Message-----
From: Bob Latino <blatino at RELIABILITY.COM>
To: IMPROVEDX <IMPROVEDX at LIST.IMPROVEDIAGNOSIS.ORG>
Sent: Wed, Mar 21, 2018 2:28 pm
Subject: Re: [IMPROVEDX] What is evidence in diagnosis

Thank you Bimal.

Tell me if I am making a correct analogy to your point below.

I am in the investigative/RCA business.  I see it all the time in healthcare when observing RCA teams, they will use a 'literature search' to validate a hypothesis in any given RCA on some undesirable outcome.  I tell them while a literature search may help somewhat determine the probability of that hypothesis occurring overall, it is not a valid form of evidence to conclude it occurred in this particular case.  A literature search is representative of experience outside of this case, which cannot conclude anything about this specific case.

I can't imagine a detective doing a literature search to draw a conclusion about how and/or why a certain crime occurred.

Many are not receptive to this perspective of mine as oftentimes literature searches are acceptable forms of evidence in healthcare RCAs.

Am I comparing apples to apples?

Bob

Robert J. Latino, CEO
Reliability Center, Inc.
1.800.457.0645
blatino at reliability.com<mailto:blatino at reliability.com>
www.reliability.com<http://www.reliability.com>
[linkedin logo signature file]<https://www.linkedin.com/company/958495?trk=tyah&trkInfo=clickedVertical%3Acompany%2CclickedEntityId%3A958495%2Cidx%3A1-1-1%2CtarId%3A1464096807851%2Ctas%3Areliability%20center%2C%20inc.>

From: Jain, Bimal P.,M.D. [mailto:BJAIN at PARTNERS.ORG<mailto:BJAIN at PARTNERS.ORG?>]
Sent: Wednesday, March 21, 2018 1:00 PM
To: IMPROVEDX at LIST.IMPROVEDIAGNOSIS.ORG<mailto:IMPROVEDX at LIST.IMPROVEDIAGNOSIS.ORG>
Subject: [IMPROVEDX] What is evidence in diagnosis

In this attached paper, I discuss how evidence is assessed during diagnosis in practice .I argue that evidence is not assessed by a probability as prescribed because a probability which is a frequency in a population fails to represent evidence for a disease in a given, individual patient in whom diagnosis is performed. Instead evidence is assessed in terms of likelihood ratio and a disease diagnosed from it in practice as we see in all published CPCs and clinical problem solving exercises.
Please review and comment on this paper.
Thanks.

Bimal

Bimal P Jain MD
Northshore Medical Center
Lynn MA 01904.
The information in this e-mail is intended only for the person to whom it is
addressed. If you believe this e-mail was sent to you in error and the e-mail
contains patient information, please contact the Partners Compliance HelpLine at
http://www.partners.org/complianceline . If the e-mail was sent to you in error
but does not contain patient information, please contact the sender and properly
dispose of the e-mail.

________________________________

Address messages to: IMPROVEDX at LIST.IMPROVEDIAGNOSIS.ORG<mailto:IMPROVEDX at LIST.IMPROVEDIAGNOSIS.ORG>

To unsubscribe from IMPROVEDX: click the following link:
http://list.improvediagnosis.org/scripts/wa-IMPDIAG.exe?SUBED1=IMPROVEDX&A=1
or send email to: IMPROVEDX-SIGNOFF-REQUEST at LIST.IMPROVEDIAGNOSIS.ORG<mailto:IMPROVEDX-SIGNOFF-REQUEST at LIST.IMPROVEDIAGNOSIS.ORG>

Visit the searchable archives or adjust your subscription at: http://list.improvediagnosis.org/scripts/wa-IMPDIAG.exe?INDEX

Moderator:David Meyers, Board Member, Society for Improving Diagnosis in Medicine

To learn more about SIDM visit:
http://www.improvediagnosis.org/

________________________________

Address messages to: IMPROVEDX at LIST.IMPROVEDIAGNOSIS.ORG<mailto:IMPROVEDX at LIST.IMPROVEDIAGNOSIS.ORG>

To unsubscribe from IMPROVEDX: click the following link:
http://list.improvediagnosis.org/scripts/wa-IMPDIAG.exe?SUBED1=IMPROVEDX&A=1
or send email to: IMPROVEDX-SIGNOFF-REQUEST at LIST.IMPROVEDIAGNOSIS.ORG<mailto:REQUEST at LIST.IMPROVEDIAGNOSIS.ORG>

Visit the searchable archives or adjust your subscription at: http://list.improvediagnosis.org/scripts/wa-IMPDIAG.exe?INDEX

Moderator:David Meyers, Board Member, Society for Improving Diagnosis in Medicine

To learn more about SIDM visit:
http://www.improvediagnosis.org/






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


HTML Version:
URL: <../attachments/20180326/ed7cd62d/attachment.html> ATTACHMENT:
Name: image001.jpg Type: image/jpeg Size: 17486 bytes Desc: image001.jpg URL: <../attachments/20180326/ed7cd62d/attachment.jpg>


More information about the Test mailing list