Automatic generation of computable implementation guides from clinical information models

A universal diagnosis syntax

BACKGROUND

Diagnoses are crucial assets of clinical work and provide the foundation for treatment and follow up. They should be informative and customized to the patient's problem. Common prefixes, morphemes, and suffixes may aid the implementation of expressions that generate diagnoses.

RESULTS

Apt choices of symbols plays a major role in science. In this study, the variables e, o, and p are assigned to names of an etiological agent, a disorder, and a pathogenetic mechanism, respectively. The suffix -itis designates infections, allergies, inflammation, and/or immune reactions. Diagnoses (d) are generated by the formula d:= e&o&p where '&' means concatenation and ':= ' means assignment. Thus, with e:= 'Staphylococcus aureus ', o:= 'endocard', and p:= 'itis', d:= e&o&p generates the diagnosis d = 'Staphylococcus aureus endocarditis'. Diagnoses formed this way comply with common clinical diagnoses. Certain extensions generate complete, systematic medical diagnoses that are applicable to all medical specialties. For example, common medical prefixes, morphemes, and suffixes give rise to o = 'hypothyroidism', o = 'tachycardia', and o = 'hypophagocytosis'. The formula scales well with the developments in clinical medicine, systems biology, molecular biology, and microbiology. The diagnosis generating formula d:= e&o&p requires meticulous analysis of the components of diagnoses plus the introduction of appropriate variables and terms. Terms partition on established clinical categories and adhere to established clinical nomenclature. The syntax generates universal medical diagnoses.

CONCLUSIONS

The present study concerns a universal diagnosis syntax (UDS) that generates diagnoses using the formula d:= e&o&p with several extensions described in the study. The formula is easy to learn and covers diagnoses in all medical specialties. The present work succeeded in creating diagnoses from the formula. The fundamental insight is that no matter how complicated a diagnosis is it can be generated by a systematic process, which adds terms one by one. UDS may have implications for medical education and classifications. The formula lays a foundation for structured clinical decision-making. Formulas are hallmarks of hard science. So, d:= e&o&p anticipates a scientific medical revolution.

Automated population of an i2b2 clinical data warehouse from an openEHR-based data repository

BACKGROUND

Detailed Clinical Model (DCM) approaches have recently seen wider adoption. More specifically, openEHR-based application systems are now used in production in several countries, serving diverse fields of application such as health information exchange, clinical registries and electronic medical record systems. However, approaches to efficiently provide openEHR data to researchers for secondary use have not yet been investigated or established.

METHODS

We developed an approach to automatically load openEHR data instances into the open source clinical data warehouse i2b2. We evaluated query capabilities and the performance of this approach in the context of the Hanover Medical School Translational Research Framework (HaMSTR), an openEHR-based data repository.

RESULTS

Automated creation of i2b2 ontologies from archetypes and templates and the integration of openEHR data instances from 903 patients of a paediatric intensive care unit has been achieved. In total, it took an average of ∼2527s to create 2.311.624 facts from 141.917 XML documents. Using the imported data, we conducted sample queries to compare the performance with two openEHR systems and to investigate if this representation of data is feasible to support cohort identification and record level data extraction.

DISCUSSION

We found the automated population of an i2b2 clinical data warehouse to be a feasible approach to make openEHR data instances available for secondary use. Such an approach can facilitate timely provision of clinical data to researchers. It complements analytics based on the Archetype Query Language by allowing querying on both, legacy clinical data sources and openEHR data instances at the same time and by providing an easy-to-use query interface. However, due to different levels of expressiveness in the data models, not all semantics could be preserved during the ETL process.