An Interoperable System for Automated Diagnosis of Cardiac Abnormalities from Electrocardiogram Data

Electrocardiogram (ECG) data are stored and analyzed in different formats, devices, and computer platforms. As a result, ECG data from different monitoring devices cannot be displayed unless the user has access to the proprietary software of each particular device. This research describes an ontology and encoding for representation of ECG data that allows open exchange and display of ECG data in a web browser. The ontology is based on the Health Level Seven (HL7) medical device communication standard. It integrates ECG waveform data, HL7 standard ECG data descriptions, and cardiac diagnosis rules, providing a capability to both represent ECG waveforms as well as perform automated diagnosis of 37 different cardiac abnormalities. The ECG ontology is encoded in XML, thus allowing ECG data from any digital ECG device that maps to it to be displayed in a general-purpose Internet browser. An experiment was conducted to test the interoperability of the system (ability to openly share ECG data without error in a web browser) and also to assess the accuracy of the diagnosis model. Results showed 100% interoperability using 276 ECG data files and 93% accuracy in diagnosis of abnormal cardiac conditions.

[1]  Herman Burstein.  Attribute sampling: tables and explanations;: Tables for determining confidence limits and sample size based on close approximations of the binomial distribution , 1971 .

[2]  H. Wang,et al.  Methods and tools for generating and managing ecgML-based information , 2004, Computers in Cardiology, 2004.

[3]  Raymond H. Myers,et al.  Probability and Statistics for Engineers and Scientists. , 1973 .

[4]  M. Arstila,et al.  Computer-assisted electrocardiography in structured diagnosis of acute myocardial infarction. , 1999, Scandinavian cardiovascular journal : SCJ.

[5]  R. Hall.  Rapid Interpretation of EKG's. , 1971 .

[6]  M Billinghurst,et al.  New interface metaphors for complex information space visualization: an ECG monitor object prototype. , 1997, Studies in health technology and informatics.

[7]  L. Edenbrandt,et al.  Acute myocardial infarction detected in the 12-lead ECG by artificial neural networks. , 1997, Circulation.

[8]  N Kawai,et al.  New electrocardiographic criteria for diagnosing right ventricular hypertrophy in mitral stenosis--comparison with the Bonner's and Mortara's criteria. , 1988, Japanese circulation journal.

[9]  Vaishali Dixit Schuchert.  ECG Library , 2006, Critical Care.

[10]  A. Murray,et al.  Pan F, He P, Liu C, Li T, Murray A, Zheng D. Variation of the Korotkoff stethoscope sounds during blood pressure measurement: Analysis using a convolutional neural network. IEEE Journal of Biomedical and Health Informatics , 2017 .

[11]  Ross Ward.  ECG learning center , 2011 .

[12]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[13]  Urtzi Ayesta,et al.  Complexity measure revisited: a new algorithm for classifying cardiac arrhythmias , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[14]  Stephen J. Roberts,et al.  Markov Models for Automated ECG Interval Analysis , 2003, NIPS.