Machine Learning , some thoughts
a.anastasiou at swansea.ac.uk
Wed Jun 27 08:21:44 EDT 2018
>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.
I think that this is the bit that causes the “friction” ☺
“Archetype” is not a “value”. It is a type.
What you are describing refers to re-packaging or translations between values. Not types.
A type is stricter.
There is a lot of “fuss” around whether something has to be a cluster or a list. For very good reasons.
A condition where you have a Set that behaves “kind of like” a Set but if you need it, it could also be a List ALONGSIDE an existing List type
doesn’t get you anywhere.
So, Archetypes are supposed to be elementary types. Not necessarily in the computer science meaning of the term. But more in the logic meaning of the term.
You use types that can compose to more complex types and they might even have operations associated with them to make inferences about what they describe.
This is why, the Archetype is like saying the set of integers (Z) rather than uint8 which is a subset of Z.
If you have a unit8 level of Archetype, you subclass the corresponding archetype at the Integer level.
Archetypes help you think conceptually about the domain. They are not supposed to be fancy containers (That’s what Templates are for ☺ ).
Conversions between Whatever <-> openEHR are supposed to happen at the conceptual level.
Automatically constructing archetypes would look into the minimal subset of (currently used) clinical encodings
that tend to be used together in the context of a disease. Having this subset you would then use their mappings to SNOMED
__concepts__ and from SNOMED you would start constructing the Archetypes respecting the relationships between the represented concepts.
>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.
Indeed, but look at it as if it were a type Universe. Or a programming language that gives you access to a type system.
When you express any kind of data transformation in this programming language, you would have to express it in the types it supports. If the types imply values that are all over the place you cannot even do data validation.
>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.
The pressure is real, I agree but I feel more comfortable having a CKM as our modelling CANVAS which helps you identify the correct position for inserting Archetypes that result from a new device.
All the best
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the openEHR-clinical