Google's AI boosts accuracy of lung cancer diagnosis, study shows - STAT

Jackson, Brian brian.jackson at ARUPLAB.COM
Tue May 21 14:03:31 UTC 2019


Yes, those are the assumptions, but for most early-cancer-detection scenarios, we don’t have great evidence that it’s working.  Gil Welch has published a lot on this topic.  In theory you could measure the benefit of early cancer detection by looking at mortality rates alongside the rates of detecting late-stage-only cancers.  But mortality improvement trends for most of these cancers are much more modest, and could be entirely attributable to improvements in therapy over the years.  Thus, early detection enthusiasts, including many smart doctors, continue to point to other statistics such as overall detection rates and survival rates, both of which are mainly functions of lead time bias.

Based on what I continue to see in the popular press, as well as trends in biotech investment, the general public continues to drink the “early detection” flavor-aid.  Not just cancer, but also other chronic diseases such as diabetes and hypertension.  Which leads to misguided investment as well as public policy.

--Brian

From: Burke Harry <harry.burke at GMAIL.COM>
Sent: Tuesday, May 21, 2019 6:20 AM
To: IMPROVEDX at LIST.IMPROVEDIAGNOSIS.ORG
Subject: Re: [IMPROVEDX] Google's AI boosts accuracy of lung cancer diagnosis, study shows - STAT

Attention: This email came from an external source. Do not open attachments or click on links from unknown senders or unexpected emails.


The assumptions of early detection are: (1) at some point in time the disease will become untreatable, (2) there is an effective treatment for the disease, and (3) if we detect the disease early, before it is untreatable, will be able to ameliorate the disease.
Harry Burke

On May 20, 2019, at 10:44 PM, Tom Benzoni <benzonit at GMAIL.COM<mailto:benzonit at GMAIL.COM>> wrote:

The question unanswered is the elephant in the room: so what?
Does this make a patient-oriented difference or only a disease-oriented one?

This may represent another cognitive error, lead time bias, or
"How To Make People Sick for Longer Times And Increase Profits"

E.g., say you have a tumor which grows from 1 to 5 cm in a year. It takes another year for the tumor to grow from 5 to 10 cm.People die at 10 cm. By changing the method of detection to a more sensitive one and finding the tumor a year earlier, we appear to make a difference, but maybe not the one we're sold.
The person may have a year of sickness added onto the front of their disease and still die at 10 cm. It only appears you've doubled longevity.

Remember the Will Rogers' effect.

tom

On Mon, May 20, 2019 at 6:19 PM HM Epstein <hmepstein at gmail.com<mailto:hmepstein at gmail.com>> wrote:
Stat reports that — in early testing — Google’s AI achieved more reliable lung cancer Dx vs. radiologists. “It detected 5% more cancers and cut false positives... by 11% from reviewing a single scan. It performed on par with the radiologists when prior images of patients were also included in the evaluation.”
https://www.statnews.com/2019/05/20/googles-ai-improves-accuracy-of-lung-cancer-diagnosis-study-shows/<https://clicktime.symantec.com/36sGSKKHEQjDGjYeYNqADgS7Vc?u=https%3A%2F%2Fwww.statnews.com%2F2019%2F05%2F20%2Fgoogles-ai-improves-accuracy-of-lung-cancer-diagnosis-study-shows%2F>

Best,
Helene
      [https://drive.google.com/uc?id=0BzqkjTYl6PKwNUhEU2NyZ2RsNW8&export=download]
Website<https://clicktime.symantec.com/3DAanEtwi8gcTAWifrmdFqH7Vc?u=http%3A%2F%2Fhmepstein.com%2F> Twitter<https://clicktime.symantec.com/3HZmH4RkRVgm13FEMrZnTzg7Vc?u=https%3A%2F%2Ftwitter.com%2Fhmepstein>
LinkedIn<https://clicktime.symantec.com/38GkoPgpXw3qBDZd8RiMNqN7Vc?u=https%3A%2F%2Fwww.linkedin.com%2Fin%2Fhelenekepstein%2F>
​
Facebook<https://clicktime.symantec.com/3SSJAZ91iTjeZgbfnpBoHh87Vc?u=https%3A%2F%2Fwww.facebook.com%2FHeleneEpsteinAuthor>

________________________________

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<https://clicktime.symantec.com/3EqARbs8eYQ6iUr7MJTq63H7Vc?u=http%3A%2F%2Flist.improvediagnosis.org%2Fscripts%2Fwa-IMPDIAG.exe%3FSUBED1%3DIMPROVEDX%26A%3D1> 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<https://clicktime.symantec.com/3MPxL2WPqxk2XYh3LyB6Wpy7Vc?u=http%3A%2F%2Flist.improvediagnosis.org%2Fscripts%2Fwa-IMPDIAG.exe%3FINDEX>
Moderator:David Meyers, Board Member, Society for Improving Diagnosis in Medicine

To learn more about SIDM visit:
http://www.improvediagnosis.org/<https://clicktime.symantec.com/37DcrtTaFRuUYKzMUSepkiB7Vc?u=http%3A%2F%2Fwww.improvediagnosis.org%2F>

________________________________

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<https://clicktime.symantec.com/3EqARbs8eYQ6iUr7MJTq63H7Vc?u=http%3A%2F%2Flist.improvediagnosis.org%2Fscripts%2Fwa-IMPDIAG.exe%3FSUBED1%3DIMPROVEDX%26A%3D1>

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<https://clicktime.symantec.com/3MPxL2WPqxk2XYh3LyB6Wpy7Vc?u=http%3A%2F%2Flist.improvediagnosis.org%2Fscripts%2Fwa-IMPDIAG.exe%3FINDEX>


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

To learn more about SIDM visit:
http://www.improvediagnosis.org/<https://clicktime.symantec.com/37DcrtTaFRuUYKzMUSepkiB7Vc?u=http%3A%2F%2Fwww.improvediagnosis.org%2F>


________________________________

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<https://clicktime.symantec.com/3EqARbs8eYQ6iUr7MJTq63H7Vc?u=http%3A%2F%2Flist.improvediagnosis.org%2Fscripts%2Fwa-IMPDIAG.exe%3FSUBED1%3DIMPROVEDX%26A%3D1>
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: https://clicktime.symantec.com/3MPxL2WPqxk2XYh3LyB6Wpy7Vc?u=http%3A%2F%2Flist.improvediagnosis.org%2Fscripts%2Fwa-IMPDIAG.exe%3FINDEX

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

To learn more about SIDM visit:
https://clicktime.symantec.com/37DcrtTaFRuUYKzMUSepkiB7Vc?u=http%3A%2F%2Fwww.improvediagnosis.org%2F

 -------------------------------------------------------------------
The information transmitted by this e-mail and any included
attachments are from ARUP Laboratories and are intended only for the
recipient. The information contained in this message is confidential
and may constitute inside or non-public information under
international, federal, or state securities laws, or protected health
information and is intended only for the use of the recipient.
Unauthorized forwarding, printing, copying, distributing, or use of
such information is strictly prohibited and may be unlawful. If you
are not the intended recipient, please promptly delete this e-mail
and notify the sender of the delivery error or you may call ARUP
Laboratories Compliance Hot Line in Salt Lake City, Utah USA at (+1
(800) 522-2787 ext. 2100


To unsubscribe from the IMPROVEDX:
mail to:IMPROVEDX-SIGNOFF-REQUEST at LIST.IMPROVEDIAGNOSIS.ORG
or click the following link: IMPROVEDX at LIST.IMPROVEDIAGNOSIS.ORG

Address messages to: IMPROVEDX at LIST.IMPROVEDIAGNOSIS.ORG

For additional information and subscription commands, visit:
http://www.lsoft.com/resources/faq.asp#4A

http://LIST.IMPROVEDIAGNOSIS.ORG/ (with your password)

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

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

To unsubscribe from the IMPROVEDX list, click the following link:<br>
<a href="http://list.improvediagnosis.org/scripts/wa-IMPDIAG.exe?SUBED1=IMPROVEDX&A=1" target="_blank">http://list.improvediagnosis.org/scripts/wa-IMPDIAG.exe?SUBED1=IMPROVEDX&A=1</a>
</p>

HTML Version:
URL: <../attachments/20190521/b9c31c66/attachment.html>


More information about the Test mailing list