Excellent observations!!!
Carol
Hello Bert and all
I wonder if besides that approach an approach of archetypes growing in the wild could be of use. They could be used beside the predefined archetypes.
I don't think that enabling people to create local fragmented subsets of information is a step in the right direction. We still
need the functionality of the CKM, in the same way that you need consensus in an open source project. You need to file
issues, that are reproducible and reasonable and someone takes responsibility for dealing with them and there is a cycle
of "refreshing" the current best knowledge and so on.
I am hoping that somewhere, some junior doctors are taking up projects in defining Archetypes and Templates and buddy up
with their friends who joined Computer Science instead and they all become a tribe too.
They could be working on "Archetypes & Templates for Secondary Uses of Routinely Collected Data" and that could be a lab for development of new things
away from "practice".
As a side comment: I think that you are also speaking from different experiences. There is still some way to go in the transition to an electronic HER that would
enable all this. Maybe things are progressing faster where you are (?)
All the best
Athanasios Anastasiou
It is a truth that, in the case of GP’s, almost always they deal with Complaints, Tentative diagnosis or estimation of the Seriousness (good/bad feeling), some trial Therapies and some addition investigations/tests, plus finally some time to observe the evolution of the complaints over time; await the test results, and after a while get an idea of a possible diagnosis or a complaint free patient.
Rarely one consultation resulted in a distinct diagnosis.
The patient population of GP’s is very amorf. There are a lot of haystacks and a few needles.
In hospitals it is somewhat different. It is much more finding a diagnosis and treatment or proving that there some diagnosis do not apply.
Hospital patient are a highly selected group of patients.
Gerard Freriks
+31 620347088
gfrer@luna.nl
Kattensingel 20
2801 CA Gouda
the Netherlands
Hello Bert and all
I wonder if besides that approach an approach of archetypes growing in the wild could be of use. They could be used beside the predefined archetypes.
I don't think that enabling people to create local fragmented subsets of information is a step in the right direction. We still
need the functionality of the CKM, in the same way that you need consensus in an open source project. You need to file
issues, that are reproducible and reasonable and someone takes responsibility for dealing with them and there is a cycle
of "refreshing" the current best knowledge and so on.
I believe were are in misunderstanding. I am not against CKM. I am for an addition on CKM, and then it is an addition which can enclose unexpected functionality, new desirable datapoints, and which will have a flat structure so it is easy to use for machine searching/learning processing.
Machine learning in combination with revolutionary GUI enhancements, in combination with third-party devices, home-devices, IoT, phone-apps, references to blockchained applications, surgery or other treatment abroad, it can bring new insights, new datapoints, more datapoints, it can change parts of healthcare.
I think knowledge-gathering must change. It must also happen also more implicitly, automatically.
One needs patters that document the documentation process in general for Medical Statements, Evaluations, Orders, Actions
Patterns to Collect Complaints
Patterns to Collect Observations by tractus
Patterns to collect complaint specific data
Patterns to collect Diagnosis specific data
Patterns to collect data for ordering of procedures (diagnostic, treatment)
Gerard Freriks
+31 620347088
gfrer@luna.nl
Kattensingel 20
2801 CA Gouda
the Netherlands
Pattern recognition could be done with AI systems using a large selection of health records, to suggest new, possibly unexpected archetypes, but not yet.
As commented earlier, data are not sufficiently recorded yet, specialists are too busy; responsibilities are left undefined as patients move from one hospital department to another; discharge records written by subordinates are incomplete summaries of partial records.
I can only hope that better systems will be developed to reduce the workload of recording the complexity of patient progression.
Then the production of archetypes could be semi-automated: clinical review will still be necessary.
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
Many Machine learning applications are analogous to "experience’ ie pattern recognition
Typical ML algorithms require training data where the results are known . They seem to have most application in areas where there are massive amounts of data which a human cannot comprehend - eg facial recognition in a crowd
Clinical problems on a one to one basis are a different problem - encoding the symptoms/signs will be an issue
Interesting idea though
Doctors are not too good at sticking to known protocols where the condition is known - machines might do better here
R
Dear Bert, all!
Sorry if this consumes excess bandwith, feel free to delete.
The case you describe clearly provides a sound reason why “generic archetypes will remain necessary”.
I agree completely. This use case must always be satisfied.
It does not include automated processing at the receiving end. The receiving party must read the information and decide what to do, using their human brain cells, no 100% reliable computer aided decision support (as in medical devices).
In this use case, I see no difference between:
- transmitting information within a “generic archetype”
- transmitting the same information in unstructured free text.
Both technologies provide a useful solution for the use case.
- So (in my humble view) this specific use case does not demand a “generic archetype”. In other words, it needs no archetype at all.
- A generic archetype does not hurt, of course.
- If a community decides to store ALL information in archetyped ways, then so be it. There then MUST be structured and unstructured archetypes.
My engineering mind puts up behavioural resistance, if unstructured information is stored in a structure, like an archetype. I can happily educate my mind to stop this, and get acquainted with the view that:
- all medical information can be stored in archetypes
- some archetypes are more restrained than others
- the “generic archetype” does not restrain at all
- decision support and advanced, automated analysis will only be available for information stored in the more restrained archetypes, if reliability is needed
- information contained in the “generic archetype” must be interpreted by human experts
I am very sorry if I missed basic truth, that everybody else is fully aware of.
All the best,
greetings from Vienna,
Stefan
Just a few days ago I heard about Google scanning a great number of files of all kind and format, searching for medical information. The results were quite remarkable.
But unstructured information is not what I am aiming for.
There will be some semantics.
A clinician can indicate that data are from the user story, or from the observation, so, that is already some information.
While talking with the patient, the doctor can measure heartbeat, bloodpressure, saturation, temperature, bloodsugar, even almost without touching de patient. It will be more soon.
Development goes so fast.
And patients can also measure data at home, or at work, or wherever.
Context is also location, patient personal data, time of the day, jet-lag, season of the year, weather conditions, other medical conditions, alcohol consumption, social status
Most of these data are not regarded as relevant in the actual medical condition. So archetypes do not have items for this.
There are two kind of medical data.
a) Medical data which are relevant in the context of a specific medical condition.
b) Medical data of which the relevancy is not yet known in the context of a medical condition, or another medical condition, which maybe is also not known at the moment.
The data of the second kind are also medical data, so why not store them?
Karsten yesterday said, a person at the doctor should be more then a medical complaint. I agree with that. But the current medical practice is not like that.
You go to the doctor with a medical complaint, and you talk about that, the doctor does research in that context, and the software finds some archetypes which fit to that.
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.
Have a nice day
Bert
Bert nurses think like you, they need to view every patient within the context of the person's response to their complaint, injury, procedures performed or treatments provide and the person's individual social network, family commitments, lifestyle, home and workplace environments, location exposures (current and/or past) etc. We should be able to collect and store information about these aspects in lifelong EHRs.
Evelyn
Doctors too. More here http://ubplj.org/index.php/ejpch/article/view/766
Dear Bert,
You mention:
“There will be some semantics.
A clinician can indicate that data are from the user story, or from the
observation, so, that is already some information.”
If there is some semantics: The archetype to store this information will then need at least some structure, and not be “completely generic”?
(I try to better understand your use case. Probably “generic” needs a definition to agree on?)
Greetings, all the best,
Stefan
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
I agree fully.
This implies that on the fly small archetypes need to be used to store one or more aspects.
Gerard Freriks
+31 620347088
gfrer@luna.nl
Kattensingel 20
2801 CA Gouda
the Netherlands
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
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.
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…)
Dear all,
please be assured that myself and many others here and elsewhere support the need to record information, for the sake of treating patients, no matter if there is an archetype or not.
Probably this discussion circles around the fact that “informatics” types of persons always are looking for structures in information. This is their job. They care for information. This always starts with a well-defined use case, and introduces limits.
Doctors and nurses deal with information, in any way it comes. They care for the patients. They can not accept limits on the information they must store. I agree completely that it is not possible to know which information is relevant, and that all information is better recorded just in case (accepting only the limits of resources and time for those who do the recording).
Both is fine and exactly as it should be (to my mind).
We are lucky, in that all information can be stored and processed, no matter if structured or unstructured.
Again this confirms my observation that we need to cooperate across our disciplines, to get the most out of all fields. Great job for me!!
Looking forward,
Stefan
Not that I like the fact but that is currently illegal under EU GDPR.
Karsten