Conversion of Automated 12-Lead Electrocardiogram Interpretations to OMOP CDM Vocabulary

Abstract

Background: A computerized 12-lead electrocardiogram (ECG) can automatically generate diagnostic statements, which are helpful for clinical purposes. Standardization is required for big data analysis when using ECG data generated by different interpretation algorithms. The common data model (CDM) is a standard schema designed to overcome heterogeneity between medical data. Diagnostic statements usually contain multiple CDM concepts and also include non-essential noise information, which should be removed during CDM conversion. Existing CDM conversion tools have several limitations, such as the requirement for manual validation, inability to extract multiple CDM concepts, and inadequate noise removal.

Objectives: We aim to develop a fully automated text data conversion algorithm that overcomes limitations of existing tools and manual conversion.

Methods: We used interpretations printed by 12-lead resting ECG tests from three different vendors: GE Medical Systems, Philips Medical Systems, and Nihon Kohden. For automatic mapping, we first constructed an ontology-lexicon of ECG interpretations. After clinical coding, an optimized tool for converting ECG interpretation to CDM terminology is developed using term-based text processing.

Results: Using the ontology-lexicon, the cosine similarity-based algorithm and rule-based hierarchical algorithm showed comparable conversion accuracy (97.8 and 99.6%, respectively), while an integrated algorithm based on a heuristic approach, ECG2CDM, demonstrated superior performance (99.9%) for datasets from three major vendors.

Conclusion: We developed a user-friendly software that runs the ECG2CDM algorithm that is easy to use even if the user is not familiar with CDM or medical terminology. We propose that automated algorithms can be helpful for further big data analysis with an integrated and standardized ECG dataset.

Fig. 1

Two examples of ECG interpretation syntax mapping by similarity. The first example completely matches the syntax existing in the ontology-lexicon with the patient's diagnosis, and the second example shows that the patient's diagnosis has the highest similarity to the syntax existing in the ontology-lexicon except for a few notes. ECG, electrocardiogram.

Fig. 2

Examples of an ECG interpretation syntax mapping in one-to-many correspondence. Panel (A) is an example of a rule in which the entire diagnosis is not mapped by the term “has replaced.” In panel (B) , ECG interpretations generated by the rules of combining multiple ontologies have all the characteristics of each ontology. ECG, electrocardiogram.

Fig. 3

Flowchart of the ECG2CDM algorithm. The structure of ECG2CDM is designed to apply both similarity-based and rule-based algorithms. When the similarity score obtained from the cosine similarity is above a certain threshold, ECG2CDM emits the result of the similarity-based algorithm. For the other case, ECG2CDM emits the result of the rule-based algorithm.

Fig. 4

Variation in the accuracy of ECG2CDM algorithm according to the threshold. The result shows an upward trend as the threshold increases, but at a threshold of 0.9 or higher, it slightly decreases and shows a tendency to remain as it is.

Fig. 5

ECG2CDM software interfaces provided as a (A) web-based software and (B) stand-alone software. Both software accepts statements from the ECG test as input. ECG, electrocardiogram.