AbstractIntroduction: The 12-lead Electrocardiogram (ECG) has been used to detect cardiac abnormalities in the same format for more than 70 years. However, due to the complex nature of 12-lead ECG interpretation, there is a significant cognitive workload required from the interpreter. This complexity in ECG interpretation often leads to errors in diagnosis and subsequent treatment.
Objectives: To improve interpretation accuracy and reduce missed co-abnormalities.
1) An interactive computing system was developed to guide the decisionmaking process of a clinician when interpreting the ECG. The system decomposes the interpretation process into a recognised series of sub-tasks and encourages the clinician to systematically interpret the ECG, coined ‘Interactive Progressive based Interpretation’ (IPI).
2) A Differential Diagnoses Algorithm (DDA) was developed to compare human ECG annotations, collected using the IPI system, against recognised diagnostic criteria. This enabled diagnostic suggestions to be generated using a novel man-machine model. The subsequent system was created using web technologies. The hypothesis was tested using a one-arm (IPI) and counterbalanced studies (IPI+DDA).
Results: A total of 558 interpretations were collected from 80 participants. The IPI model increased accuracy by 13.4%, whilst the IPI+DDA approach was also shown to improve diagnostic accuracy (8.7%). In both studies, interpreter self-rated confidence increased but interpretation duration increased six fold. The IPI+DDA suggested the correct interpretation more often than the human interpreter in 7/10 cases. Human interpretation accuracy increased to 70% when seven suggestions were generated.
Conclusion: The IPI and IPI+DDA models improve diagnostic accuracy, at the expense of time. It was found; 1) the decision support tool increased the number of correct interpretations, 2) the DDA algorithm suggested the correct interpretation more often than humans, and 3) as many as 7 computerized diagnostic suggestions augmented human decision making in ECG interpretation
|Date of Award||Jun 2018|
|Supervisor||Dewar Finlay (Supervisor) & Raymond Bond (Supervisor)|
- Cognitive engineering
- Computer science
Interactive computing to augment the human interpretation of the 12-lead electrocardiogram
Cairns, A. (Author). Jun 2018
Student thesis: Doctoral Thesis