Models vs. Experts #4: Electrocardiogram
Performance of the computer and physician in the analysis of the electrocardiogram
- Caceres, C. A., & Hochberg, H. H.
- American Heart Journal, 79, 439-443
- A version of the paper can be found here.
- Want a summary of academic papers with alpha? Check out our free Academic Alpha Database!
A sustained level of measurement accuracy possible by computers is not often achieved by physicians Similarly, once programmed to repeat interrelation of measurements in a set of criteria, the computer is far more reliable than man, as the machine system always follows designated logic without subjectivity.
Why Humans Disagree?
In the context of electrocardiograms the arguments in favor of computer use appear overwhelming and the profession has moved in the direction of computer analysis. This paper is not directly engaging in the model vs. expert debate. This paper tries to understand WHY humans disagree with computer outputs in the context of electrocardiogram outputs.
Technicians feed the computer recordings. Some recordings are noisy and contain error (poor technical recordings) and some are clean (good technical recordings). In this study, the authors disregard “poor technical recordings” because this is a case of “garbage in, garbage out.” The focus throughout is on good technical recordings, where the computer is known to perform at a very high level of accuracy.
Among good recordings:
- Humans only agree with the computer 58% of the time
- Humans disagree 42% of the time
- 13% due to physician error (they are simply wrong)
- 13% due to “criteria” differences. The computer isn’t wrong, the human isn’t wrong, but it is unclear what the standard is
- 10% due to imprecise criteria (computer wasn’t programmed correctly)
- 6% general computer error
Thoughts on the paper?
Note: This site provides NO information on our value investing ETFs or our momentum investing ETFs. Please refer to this site.
Join thousands of other readers and subscribe to our blog.
Please remember that past performance is not an indicator of future results. Please read our full disclosures. The views and opinions expressed herein are those of the author and do not necessarily reflect the views of Alpha Architect, its affiliates or its employees. This material has been provided to you solely for information and educational purposes and does not constitute an offer or solicitation of an offer or any advice or recommendation to purchase any securities or other financial instruments and may not be construed as such. The factual information set forth herein has been obtained or derived from sources believed by the author and Alpha Architect to be reliable but it is not necessarily all-inclusive and is not guaranteed as to its accuracy and is not to be regarded as a representation or warranty, express or implied, as to the information’s accuracy or completeness, nor should the attached information serve as the basis of any investment decision. No part of this material may be reproduced in any form, or referred to in any other publication, without express written permission from Alpha Architect.
Definitions of common statistics used in our analysis are available here (towards the bottom)