Machine Learning , some thoughts

Heather Leslie heather.leslie at atomicainformatics.com
Fri Jun 29 01:13:24 EDT 2018


Hi Bert,

I’d really like to be careful about the terms we use here.

“But if flexibility is slowed down by years of review, discussing and consensus over the whole world for a set of archetypes, then there is not much flexibility left.”

At present, the slow part is lack of editorial resources to facilitate the reviews and achieving consensus. Until we have adequate funded resources applied to the CKM process and then still proved that it is too slow, please try not to disseminate this kind of message.

Some will use loose phrases as their ‘truth’ and perpetuate further misinformation about openEHR.

Regards

Heather

From: openEHR-clinical <openehr-clinical-bounces at lists.openehr.org> On Behalf Of Bert Verhees
Sent: Wednesday, 27 June 2018 10:00 PM
To: openehr-clinical at lists.openehr.org
Subject: Re: Machine Learning , some thoughts

Dear Seref, I do not agree with this without having explored all the possibilities. I think it is important not to jump to conclusions and keep the discussion open.
I have some ideas how to keep it interoperable. I like to discuss that with an open mindset.

Talking about interoperability.

By the way, how do you create FHIR messages from OpenEhr-compositions? Or how do you create Openehr-compositions from FHIR messages?
You have to create a template manually, fitting that item to that datapoint, isn't it?
Even within two parties using OpenEhr. You are only automagically interoperable when two parties use exact the same archetypes, else you need to puzzle the dataitems.

The same things you have to do when you need to handle a generated archetype. But it will not be that hard. Don't expect much complexity from these generated archetypes.
I called them before, micro-archetypes, containing only one datapoint, or a few closely related datapoints.
With machine learning algorithms, it must not be hard to interpret them.

Don't understand me wrong, I like OpenEhr, because of the archetyped system, and the flexibility it offers. It is not by accident that I discuss it here and not in a HL7 group, although that would bring more money.

But if flexibility is slowed down by years of review, discussing and consensus over the whole world for a set of archetypes, then there is not much flexibility left.
This can work very good for the archetypes which are in CKM, but all those new devices, all those new datatypes, all this new protocols, which cannot wait for these review-procedures, because the market will be jumped far ahead by then.

Best regards
Bert

On 27-06-18 11:50, Seref Arikan wrote:
Hi Bert,

Let me try to keep it brief: you seem to suggest breaking the openEHR methodology. If you allow downstream actors (clinical systems, guided by their users) create archetypes without going through the methodology, i.e. creating, discussing, reviewing archetypes, you'll end up with computable health with no interoperability.

This will in turn break machine learning because you cannot learn anything valuable from datasets which are created based on data, which are based on models, which are based on clinicians going siri on their systems.

As a side note, this whole domain will make much faster progress when someone starts teaching clinicians (when they're at medical school) that informatics, just like washing hands before an operation, is partly their responsibility and they cannot get much out of their systems until they start taking charge of some aspects of it, instead of waiting for vendors to present them their incorrect/biased view of clinical care.

Our fundamental problems need humans doing what needs to be done, we're still nowhere near the capability to get rid of having to do what openEHR methodology allows us to do, from and AI perspective.

All the best.
Seref (who could not keep it brief...)




On Tue, Jun 26, 2018 at 11:31 PM, Bert Verhees <bert.verhees at rosa.nl<mailto:bert.verhees at rosa.nl>> wrote:
One short addition, why this discussion, the original point:

What about machine learning?
Machine learning becomes possible when many daily health related data are available. A machine can, f.e. detect deviations.

Why generated archetypes?
Every day there are new devices, new ideas about health, we cannot wait for CKM to follow day to day inventions, and some of them only used by minorities. The EHR must be able to create archetypes when needed.

Op wo 27 jun. 2018 00:18 schreef Bert Verhees <bert.verhees at rosa.nl<mailto:bert.verhees at rosa.nl>>:
Thanks for supporting reactions.

It is really typical in western medical science that it is very problem oriented. All EHRs, even unconventional one, even the new thinking, it is very problem oriented.

All data are gathered around a problem and in relevance of a problem. All datastructures are pointing to a problem. Without problem there is no datarecording.

It is historically grown like that. Medical data collecting is only done by clinicians, and only when a patient has a problem, the data around the problem, the diagnosis, and the treatment, that is important. Data which do not have a known relevance are not recorded.

And when the patient has a new problem, the only information available are the problems in history. Information about lifestyle is unknown. One can ask the patient, but some patients have a selective memory.

But in sports this is different. Medical datarecording also happens when there is no problem, but as daily routine. But now, many people today, also no-sport people, I wrote before today, measure data many times. Apple patented a blood pressure device in Applewatch. It is cheap, easy to do.

It will not take long and people have their own EHR at Google, Amazon, Microsoft, Walmart or Apple, to record their daily medical data. They maybe will be able to demand that GP's store their findings in that EHR, so a more holistic view about the patient will become available, and maybe insurance companies will reward access to that holistic view.

We must prepare for that, the face of healthcare will change. Until now it was problem-care, which we called in Orwellian tradition Newspeak: healthcare. But it will change to really healthcare. It is something completely different, and it happens fast.

I learn also from this, while writing I learn. But I have said it all. Now it would be nice to discuss how to implement healthcare instead of problemcare.

Bert

Op di 26 jun. 2018 22:18 schreef Karsten Hilbert <Karsten.Hilbert at gmx.net<mailto:Karsten.Hilbert at gmx.net>>:
> But the person should be seen as more then a medical complaint, but as a
> complex of conditions and lifestyle.
> We need generic archetypes which can store machine generated datasets to
> store information about the whole person, instead of only the medical
> condition which is subject of conversation.
>
> I believe I am the only person in this list who thinks like that. But
> that does not matter.

Actually, any worthwhile GP thinks like that (except we don't say
things like "datasets" or "generic archetype").

I rather doubt you are alone in this. Even on-list.

Karsten

_______________________________________________
openEHR-clinical mailing list
openEHR-clinical at lists.openehr.org<mailto:openEHR-clinical at lists.openehr.org>
http://lists.openehr.org/mailman/listinfo/openehr-clinical_lists.openehr.org

_______________________________________________
openEHR-clinical mailing list
openEHR-clinical at lists.openehr.org<mailto:openEHR-clinical at lists.openehr.org>
http://lists.openehr.org/mailman/listinfo/openehr-clinical_lists.openehr.org





_______________________________________________

openEHR-clinical mailing list

openEHR-clinical at lists.openehr.org<mailto:openEHR-clinical at lists.openehr.org>

http://lists.openehr.org/mailman/listinfo/openehr-clinical_lists.openehr.org


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openehr.org/pipermail/openehr-clinical_lists.openehr.org/attachments/20180629/9753bf9f/attachment-0001.html>


More information about the openEHR-clinical mailing list