Classification, Ontology, and Precision Medicine
Now I know the meaning of classification and precision, but ontology was the study of "being". The Ontological Proof of the Existence of God and all that. But here the authors have abandoned this millennial old meaning to define it as:
Ontologies are systematic representations of knowledge that can be used to integrate and analyze large amounts of heterogeneous data, allowing precise classification of a patient. In this review, we describe ontologies and their use in computational reasoning to support precise classification of patients for diagnosis, care management, and translational research.
Got that? I have had to read this more than a dozen times, through my mild dyslexia and all, still do not get it. I think I get the point they are making that we now have vast amounts of data on patients and that data may dramatically change the way we do diagnosis. No surprise there.
So just what are these "systematic representations of knowledge" they are opining about? Well we have all this data, not that I would call it "knowledge". It seems that every time we have a discovery of some new gene interaction in say cancer, a few months later there is another. Add to that the networking of these genes, then add to that the in vivo interaction, and so forth. I suspect we may have just begun to understand some issue in cancer, some very few, but important issues.
The problem however is that data is not knowledge. Eliciting from data fundamental principles and then validating them and then creating "tools" to measure then is critical. Even then the tools we have to measure stuff may elicit a cloudy picture, take the PSA test as a simple example.
The authors further state:
Conventionally, most of us think about structure as the arrangement of data, either on an EHR screen or as a database schema behind the scenes. Semantics, in turn, refers to concepts and the relationships between them. Software systems require assertions about term equivalence. ... Semantics and structure are not orthogonal but deeply intertwined.
Again I think I get the point. Syntax is how we put words together to form a sentence, semantics is how we obtain meaning from the sentence. At least that is what it was sixty years ago when I first grasped the idea. They conclude:
The second barrier is the cost and effort of getting data into and out of EHRs. Manual input of structured data by clinicians is not scalable and is not a good use of clinicians’ time. Emerging efforts on standard application interfaces with EHRs from devices and data sources could help, as could patient-collected and patient-entered information. Systematically harvesting signs, symptoms, severity, and other clinical details from dictated notes or even from audio capture of the patient encounter is becoming increasingly practical.
I believe it is fair to say that the EHR was not to be used by anyone professionally but was developed as part of the OCare system to oversee physicians and hospitals. Fundamentally as we have argued for over a decade the implementation and execution if fatally flawed. It is not patient centered. It is a check mark that all providers must meet. "Meaningful Use" is the greatest misnomer in the world. It just added costs to the system without any fundamental benefit. Thus this conclusion is useful but limited.
Posts
