Machine Learning , some thoughts

Anastasiou A. a.anastasiou at swansea.ac.uk
Thu Jun 28 04:05:26 EDT 2018


>>>>> Maybe it is not really generated but delivered by the producer of the device, a minimalistic archetype, it is not important, important is that it a minimalistic archetype is which can contain the data which are to delivered.
>>>>> Most manufacturers will not write archetypes, so a software vendor selling an openehr system is to deliver an archetype in which the data can be enveloped.
>>>> What would be great for manufacturers would be to tell "us" what it is that their device measures. If they could do it with proposing an Archetype hierarchy for vitals derived by consumer devices that would be even better.
>>> Of course they will tell people and let them write archetypes, if they want to support OpenEhr. But mostly they do not want that. They deliver the Watts/Kg on a webservice as just a number. We envelop it in a micro-archetype, so it can find a place in an OpenEhr database.
>> It is not up to them. There is nothing stopping people to start modelling the outputs of these devices on CKM.
>> And by the way, if anyone wants to do it (https://www.kickstarter.com/discover/tags/science), let me know, I'd give it a try.
>I don't see it happening, this is also because the community on OpenEhr is health-problem-centric thinking, and what we also need is health-lifestyle/sport/consumer thinking.
>The culture change from problem-centric-care to health-centric-care is not yet happening on CKM.

I see a lot of overlap there between what you refer to as health-lifestyle and secondary uses of routinely collected data.
This is definitely changing with the availability of platforms that support openEHR (beyond what we had previously)

> That is with communities, you get what you get. And even if they were, would they be able to keep up with the industry?
> And why not let the industry design their own archetypes? Or the software vendors?
> I don't see why that is such a big deal for you.

The "big deal" for me is people developing Archetypes together and on one coherent model. 

>> The webservice example is what I would consider a hack. It produces an isolated Archetype just for the sake of storing it in the EHR in a convenient form.
>> What is Watts/kg as an observation?

>It is used by runners and cyclists, the more watts per kg you can produce the faster you can run or ride. Especially in the mountains, weight is a real enemy. They say that every kg above the ideal weight 
>cost 30 seconds on Alpe d'Huez. Froome is now 68 kg. When you have less kg, then you need less Watts to ride and every Watt makes you faster. So Watts per Kg is very important.
>But you want software for many more things, how is your heart doing when riding at steep sloop of 10%, and what if you push the rate 5 beats higher, how long can you do that? Does it improve or does >it slowly go down?

Thank you for letting me know, my question refers to what is Watts/kg as an observation. Not at what is "Watts/kg" literally. As an OBSERVATION (openEHR class), where does it descend from? What does it mean? What is it?


>>>> I do not think that this means "Any permissible". I think that this 
>>>> means "It is too early to tell". When we have Archetypes for those other RMs / Formalisms then these slots will need to be specified too.
>>> I do not want to discuss the hard and good work reviewers do. And I do not want to criticize them.
>>> Their task is hard. Maybe too hard. Maybe CKM should not be the only 
>>> source of truth
>> What makes you think that the people working in an alternative form of CKM would not come across the same modelling problems?
>If more people are busy with archetypes writing, CKM can do the problem-related, others can do the sport-related. They do not need to know about each other. Some vendors like to work in secrecy. >They do not want to give away their ideas before they come to market.

"Secrecy" is costly, or at least this is how I perceive it.

Whether you call it "problem-related" or "sport-related" or "research-related", these parameters all observe the same phenomenon: Life, from birth to death.
Therefore, you will have a set of concepts (which may well be expanding, because the phenomenon does not wait for "you" to study it) but a number of "perspectives" around the concepts.
"Blood pressure" can participate in a Template with one role in the context of pregnancy and in another Template with a completely different role in the context of diabetes.

So, really, the notion that people started working in problems first probably stems from necessity. This is what is immediately needed.


>> It is hard to create a coherent model by which to express what is happening in the domain but it has been done in Mathematics.
>> Why not in Medicine too? (Or maybe the informatics aspects of it).
>
> I believe you want to recall this. This is blasphemy, comparing healthcare with mathematics. May will disagree with you, and I think they are right.

I don't know who May is but there certainly is a set of people who will feel negatively towards the idea but will keep on reaping its fruits unknowingly.

Archetypes are "Types", not values, or "objects". There is no point in equipping a ->value<- with Inheritance or the ability to constrain its attributes.

As Types, they imply established ways of thinking about them and developing them. Inevitably, the "dimensions of Health" will compose a Universe.

You are trying to make data ->computable<-, not just easily transportable.


I am not dug into any trench. On the contrary, the feedback I decided to provide is towards the realisation of what you proposed, not against it.



More information about the openEHR-clinical mailing list