Models vs. Experts #5: Health Care Protocol
Experience with a computerized interactive protocol system using HELP
- Cannon, S. R., & Gardner, R. M.
- Computers in Biomedical Research,13, 399-409.
- 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 computerized, interactive audit and decision making system based on the HELP system is proposed for non-physician providers in ambulatory health care. Four protocols were implemented: upper respiratory-ear, nose, and throat; urinary tract infection; chronic hypertension; and chronic diabetes. Two physicians’ assistants used the system for 175 patient encounters. Data entry error rates (1%) were significantly less than those of paper protocols, For the upper respiratory, ear, nose, and throat protocol, I I percent of the encounters resulted in physician referrals with one false-negative and four false-positive decisions. False-positive antibiotic therapy decisions by assistants were safely reduced. Patient acceptance of the automated self-history was good. No alienation of the assistants was noted. Less than two minutes per patient terminal time was required by the assistants.
The authors study paper-based protocol tools vs. computerized protocol tools. Paper-based protocols are fixed, prone to human error, and alienate physician assistants. Computer-based protocol algorithms are dynamic, more sophisticated, and more accruate (PA alienation is still an issue–ie, “What, a computer can do my job?”) . An example computerized logic system that tells PAs what to do:
There isn’t much in this paper about comparing human vs computer predictions. This is a paper more focused on showing that integrating computers into the decision making process makes human more efficient and accurate. However, this is one table comparing antibiotic treatment decisions by the humans and the machine. In the words of the authors:
In comparing the decisions to perform a throat culture with the actual culture outcomes (Table II), a slightly higher success rate was noted from the computerized protocol.
The use of computerized algorithms increases efficiency and efficacy.
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)