Real alerts and artifact classification in archived multi-signal vital sign monitoring data: implications for mining big data
- 5 October 2015
- journal article
- research article
- Published by Springer Science and Business Media LLC in Journal of Clinical Monitoring and Computing
- Vol. 30 (6), 875-888
- https://doi.org/10.1007/s10877-015-9788-2
Abstract
Huge hospital information system databases can be mined for knowledge discovery and decision support, but artifact in stored non-invasive vital sign (VS) high-frequency data streams limits its use. We used machine-learning (ML) algorithms trained on expert-labeled VS data streams to automatically classify VS alerts as real or artifact, thereby “cleaning” such data for future modeling. 634 admissions to a step-down unit had recorded continuous noninvasive VS monitoring data [heart rate (HR), respiratory rate (RR), peripheral arterial oxygen saturation (SpO2) at 1/20 Hz, and noninvasive oscillometric blood pressure (BP)]. Time data were across stability thresholds defined VS event epochs. Data were divided Block 1 as the ML training/cross-validation set and Block 2 the test set. Expert clinicians annotated Block 1 events as perceived real or artifact. After feature extraction, ML algorithms were trained to create and validate models automatically classifying events as real or artifact. The models were then tested on Block 2. Block 1 yielded 812 VS events, with 214 (26 %) judged by experts as artifact (RR 43 %, SpO2 40 %, BP 15 %, HR 2 %). ML algorithms applied to the Block 1 training/cross-validation set (tenfold cross-validation) gave area under the curve (AUC) scores of 0.97 RR, 0.91 BP and 0.76 SpO2. Performance when applied to Block 2 test data was AUC 0.94 RR, 0.84 BP and 0.72 SpO2. ML-defined algorithms applied to archived multi-signal continuous VS monitoring data allowed accurate automated classification of VS alerts as real or artifact, and could support data mining for future model building.Keywords
Funding Information
- National Institute of Nursing Research (RO1 NR13912)
- National Science Foundation (NSF 1320347)
This publication has 43 references indexed in Scilit:
- Novel Methods to Predict Increased Intracranial Pressure During Intensive Care and Long-Term Neurologic Outcome After Traumatic Brain InjuryCritical Care Medicine, 2013
- Combining an Expert-Based Medical Entity Recognizer to a Machine-Learning System: Methods and a Case StudyBiomedical Informatics Insights, 2013
- Continuous Quantitative Monitoring of Cerebral Oxygen Metabolism in Neonates by Ventilator-Gated Analysis of NIRS RecordingsPublished by Springer Science and Business Media LLC ,2012
- Clinician blood pressure documentation of stable intensive care patients: An intelligent archiving agent has a higher association with future hypotensionCritical Care Medicine, 2011
- Multiparameter Intelligent Monitoring in Intensive Care II: A public-access intensive care unit database*Critical Care Medicine, 2011
- Intensive care unit alarms—How many do we need?*Critical Care Medicine, 2010
- Reducing false alarm rates for critical arrhythmias using the arterial blood pressure waveformJournal of Biomedical Informatics, 2008
- The Problem of Artifacts in Patient Monitor Data During Surgery: A Clinical and Methodological ReviewAnesthesia & Analgesia, 2006
- Adaptive filtering for ECG rejection from surface EMG recordingsJournal of Electromyography and Kinesiology, 2005
- Physiologic data acquisition system and database for the study of disease dynamics in the intensive care unit*Critical Care Medicine, 2003