Outlier detection for patient monitoring and alerting

Authors:
Milos Hauskrecht;Iyad Batal;Michal Valko;Shyam Visweswaran;Gregory F. Cooper;Gilles Clermont
Affiliations:
Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, USA and The Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA, USA;Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, USA;Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, USA and Inria Lille-Nord Europe, equipe SequeL, Lille, France;The Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA, USA and Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA, USA;The Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA, USA and Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA, USA;CRISMA Center, Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
Venue:
Journal of Biomedical Informatics
Year:
2013

Citing 6
Cited 1

The nature of statistical learning theory

The nature of statistical learning theory
Novelty detection: a review—part 1: statistical approaches

Signal Processing
Predicting good probabilities with supervised learning

ICML '05 Proceedings of the 22nd international conference on Machine learning
Medical informatics: computer applications in health care and biomedicine (Health informatics)

Medical informatics: computer applications in health care and biomedicine (Health informatics)
Anomaly detection: A survey

ACM Computing Surveys (CSUR)
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)

Learning classification models from multiple experts

Journal of Biomedical Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We develop and evaluate a data-driven approach for detecting unusual (anomalous) patient-management decisions using past patient cases stored in electronic health records (EHRs). Our hypothesis is that a patient-management decision that is unusual with respect to past patient care may be due to an error and that it is worthwhile to generate an alert if such a decision is encountered. We evaluate this hypothesis using data obtained from EHRs of 4486 post-cardiac surgical patients and a subset of 222 alerts generated from the data. We base the evaluation on the opinions of a panel of experts. The results of the study support our hypothesis that the outlier-based alerting can lead to promising true alert rates. We observed true alert rates that ranged from 25% to 66% for a variety of patient-management actions, with 66% corresponding to the strongest outliers.