A probabilistic system for identifying suicide attempters
- Gustafson, D. H., Greist, J. H., etal
- Computers and Biomedical Research, I0, 1-7
- An online version of the paper can be found here
- Want a summary of academic papers with alpha? Check out our free Academic Alpha Database!
Abstract:
This paper reports the results of a study to develop and pilot test a system for screening potential suicide attempters. The system includes a computer interview of patients complaining of suicidal thoughts and Bayesian processing (using subjective probability estimation) of the results of that interview. The results suggest that the system may significantly improve the health field’s ability to identify suicide attempters.
Prediction:
The authors make a hypothesis that people could develop a system to identify patients who will attempt suicide that was significantly better than the average clinician.
Firstly, they develop a system to identify suicide attempters:
- Patients are asked to go over a computer interview (questions omitted here);
- Immediately after the interview the computer generates an estimate of probability of a suicide attempt.
- Bayes’s theorem is used as the data processing model for this system.
The authors compare computer-based probabilities against human-based probabilities. This analysis is confusing and hard to understand, but the bottom line result is that computer’s have an edge.
Later in the paper the authors talk about a study they are working on that is run like a typical controlled experiment:
- Patients are interviewed by a computer and a human.
- Computers make predictions and humans make predictions about suicide attempts.
- Compare the performance.
The sample size is only 30 patients, but here are the results:
- The computer identified 75% of the attemptors; the humans identified 22%.
Would you rely on the psychologists “gut feel” for a suicide attempt, or would you rely on the computer’s calculated logic? Or maybe both?
About the Author: Wesley Gray, PhD
—
Important Disclosures
For informational and educational purposes only and should not be construed as specific investment, accounting, legal, or tax advice. Certain information is deemed to be reliable, but its accuracy and completeness cannot be guaranteed. Third party information may become outdated or otherwise superseded without notice. Neither the Securities and Exchange Commission (SEC) nor any other federal or state agency has approved, determined the accuracy, or confirmed the adequacy of this article.
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. Our full disclosures are available here. Definitions of common statistics used in our analysis are available here (towards the bottom).
Join thousands of other readers and subscribe to our blog.