Warning: Undefined array key "mm" in /www/wwwroot/www.ai-bt.com/si.php on line 10 Deprecated: trim(): Passing null to parameter #1 ($string) of type string is deprecated in /www/wwwroot/www.ai-bt.com/si.php on line 10 Outlier detection for patient monitoring and alerting.

Literature DB >> 22944172

Outlier detection for patient monitoring and alerting.

Milos Hauskrecht¹, Iyad Batal, Michal Valko, Shyam Visweswaran, Gregory F Cooper, Gilles Clermont.

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.

Entities: Chemical Disease Gene Species

Mesh：

Year: 2012 PMID： 22944172 PMCID： PMC3567774 DOI： 10.1016/j.jbi.2012.08.004

Source DB: PubMed Journal: J Biomed Inform ISSN： 1532-0464 Impact factor: 6.317

26 in total

Outlier detection for patient monitoring and alerting.

1. Ten commandments for effective clinical decision support: making the practice of evidence-based medicine a reality.

2. Clinical monitoring using regression-based trend templates.

3. Costs of medical injuries in Utah and Colorado.

4. The meaning and use of the area under a receiver operating characteristic (ROC) curve.

5. Temporal trends in rates of patient harm resulting from medical care.

6. Adverse drug event trigger tool: a practical methodology for measuring medication related harm.

7. Crying wolf: false alarms in a pediatric intensive care unit.

8. Managing temporal worlds for medical trend diagnosis.

9. Physicians' decisions to override computerized drug alerts in primary care.

10. Computerized surveillance of adverse drug events in hospital patients.

1. A Regularized Linear Dynamical System Framework for Multivariate Time Series Analysis.

2. Hierarchical Active Learning with Proportion Feedback on Regions.

3. An Efficient Pattern Mining Approach for Event Detection in Multivariate Temporal Data.

4. A Personalized Predictive Framework for Multivariate Clinical Time Series via Adaptive Model Selection.

5. A Mixtures-of-Trees Framework for Multi-Label Classification.

6. Response score of deep learning for out-of-distribution sample detection of medical images.

7. Efficient Learning of Classification Models from Soft-label Information by Binning and Ranking.

8. Learning Adaptive Forecasting Models from Irregularly Sampled Multivariate Clinical Data.

9. A Generalized Mixture Framework for Multi-label Classification.

10. Improving Prediction of Low-Prior Clinical Events with Simultaneous General Patient-State Representation Learning.