Format

Send to

Choose Destination
Physiol Meas. 2018 Dec 18. doi: 10.1088/1361-6579/aaf979. [Epub ahead of print]

An active learning framework for enhancing identification of non-artifactual intracranial pressure waveforms.

Author information

1
Department of Neurology, Columbia University Medical Center, 177 Fort Washington Ave,, 8th floor, New York, New York, New York, 10032-3784, UNITED STATES.
2
Columbia University, New York, New York, 10027-6902, UNITED STATES.
3
Columbia University Medical Center, New York, New York, 10032-3784, UNITED STATES.
4
Department of Neurology, Columbia University Medical Center, New York, New York, UNITED STATES.
5
Department of Neurosurgery, Columbia University Medical Center, New York, New York, UNITED STATES.
6
NeoGenomics Laboratories Inc Aliso Viejo, Aliso Viejo, California, UNITED STATES.
7
David Geffen School of Medicine, University of California - Los Angeles, University of California, Los Angeles, Los Angeles, CA 90024, San Francisco, 94122, UNITED STATES.
8
Columbia University Department of Neurology, New York, New York, 10032-3784, UNITED STATES.

Abstract

Intracranial pressure (ICP) is an important and established clinical measurement that is used in the management of severe acute brain injury. ICP waveforms are usually triphasic and are susceptible to artifact because of transient catheter malfunction or routine patient care. Existing methods for artifact detection include threshold-based, stability-based, or template matching, and result in higher false positives (when there is variability in the ICP waveforms) or higher false negatives (when the ICP waveforms lack complete triphasic components but are valid). We hypothesized that artifact labeling of ICP waveforms can be optimized by an active learning approach which includes interactive querying of domain experts to identify a manageable number of informative training examples. The resulting active learning based framework identified the non-artifactual ICP pulse with a superior AU-ROC of 0.96+0.012, compared to existing methods: template matching (AUC: 0.71 + 0.04), ICP stability (AUC: 0.51+0.036) and threshold-based (AUC: 0.5 + 0.02).

KEYWORDS:

Active Learning; Artifact Cleaning; Intracranial Pressure

PMID:
30562165
DOI:
10.1088/1361-6579/aaf979

Supplemental Content

Full text links

Icon for IOP Publishing Ltd.
Loading ...
Support Center