Machine Learning , some thoughts

Bert Verhees bert.verhees at rosa.nl
Mon Jun 25 17:32:10 EDT 2018


> Therefore I conclude for myself that I will not trust (and recommend to
> trust) automatically found archetypes, because you can not derive
> reliable conclusions from them at a defined level of reliability.

Stefan, I give a short reply, I have already given much input in this
discussion and want others to let give their opinion.

Suppose an IoT device gives an output which is not covered by a CKM
archetype. Suppose someone is treated in Georgia with bacteriaphages
therapy. Someone having strange skin marks which do not fit in the CKM
evaluation archetype, but which is recognized by a machine learning app.
What to do, not accept this medical relevant information, or create an a
on-the-fly archetype, or let a computer create it, so the information can
be stored?

Suppose we had a situation like In the eighties, it would be difficult to
enter in an EHR that someone having AIDS, because no software would support
that, it was a new disease. All those rare symptoms coming together. How
would we handle that? It is clear that generic archetypes will remain
necessary, and generic flat archetypes are perfect to be used by computers
to store generated datasets. That is in fact a good possibility to store
unexpected datapoints.

Today we have in the Netherlands rare diseases caused by chemical
substances where people worked with thirty years ago. It is so complex, so
many kinds of poison, all kind of symptoms and treatments can be
necessary,  how to handle this without generic archetypes?

I wanted to keep it short. So best regards
Bert Verhees

Op ma 25 jun. 2018 18:31 schreef Stefan Sauermann <
sauermann at technikum-wien.at>:

> Dear Bert!
> Sorry, I did not want to be a nuisance.
> I agree that AI makes sense in healthcare! I also agree that progress
> has been made.
>
> My experience especially in information modelling (10 years within the
> electronic health record in Austria, leading role in designing the
> implementation guides for laboratory report, infection report,
> antibiotics resistance report, cancer statistics report) tells me that
> information modelling better is not done by a machine.
> Therefore I conclude for myself that I will not trust (and recommend to
> trust) automatically found archetypes, because you can not derive
> reliable conclusions from them at a defined level of reliability.
>
> My feeling is that you can not (today) put an "automated archetype
> design machine" through medical device regulations. This is a "must
> have" if anybody uses results in clinical practice. That was my few
> cents, I am sorry if I put it into the discussion in a cumbersone way.
>
> If you are interested in going deeper, we are definitely interested. We
> do a lot of work in information modelling, and also in sharing and
> making use of information.
> My feeling is that the reflector is not an appropriate tool to
> accomodate this discussion, and structured cooperations. We will be
> happy to engage in a structured discussion elsewhere.
>
> Looking forward to hear more,
> greetings from Vienna,
>
> Stefan Sauermann
>
> Program Director
> Biomedical Engineering Sciences (Master) ->
> Medical Engineering & eHealth (Master) in September 2018!
>
> University of Applied Sciences Technikum Wien
> Hoechstaedtplatz 6, 1200 Vienna, Austria
> P: +43 1 333 40 77 - 988
> M: +43 664 6192555
> E: stefan.sauermann at technikum-wien.at
> I: www.technikum-wien.at/mme
> I: www.technikum-wien.at/bhse
> I: healthy-interoperability.at
> fb: www.facebook.com/uastwMME
> portfolio: https://mahara-mr.technikum-wien.at/user/sauermann
>
> Am 25.06.2018 um 12:53 schrieb Bert Verhees:
> > On 25-06-18 12:21, Stefan Sauermann wrote:
> >> Hope this helps,
> >
> > Not really Stefan, but thanks for trying.
> >
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openehr.org/pipermail/openehr-clinical_lists.openehr.org/attachments/20180625/740cfef1/attachment-0001.html>


More information about the openEHR-clinical mailing list