DMCA
Evidence-based Anomaly Detection in Clinical Domains (2007)
Cached
Download Links
| Venue: | Annual American Medical Informatics Association Symposium |
| Citations: | 8 - 5 self |
BibTeX
@MISC{Hauskrecht07evidence-basedanomaly,
author = {Milos Hauskrecht and Michal Valko and Branislav Kveton and Shyam Visweswaran Md and Gregory F. Cooper},
title = {Evidence-based Anomaly Detection in Clinical Domains},
year = {2007}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Anomaly detection methods can be very useful in identifying interesting or concerning events. In this work, we develop and examine new probabilistic anomaly detection methods that let us evaluate management decisions for a specific patient and identify those decisions that are highly unusual with respect to patients with the same or similar condition. The statistics used in this detection are derived from probabilistic models such as Bayesian networks that are learned from a database of past patient cases. We evaluate our methods on the problem of detection of unusual hospitalization patterns for patients with community acquired pneumonia. The results show very encouraging detection performance with 0.5 precision at 0.53 recall and give us hope that these techniques may provide the basis of intelligent monitoring systems that alert clinicians to the occurrence of unusual events or decisions.
Keyphrases
clinical domain evidence-based anomaly detection alert clinician management decision unusual hospitalization pattern probabilistic model new probabilistic anomaly detection method specific patient bayesian network past patient case similar condition unusual event anomaly detection method encouraging detection performance
