Artifact detection in the PO2 and PCO2 time series monitoring data from preterm infants

Background. Artifacts in clinical intensive care monitoring lead to false a larms and complicate later data analysis. Artifacts must be identified and processed to obtain clear information. In this paper, we present a method f or detecting artifacts in PCO2 and PO2 physiological monitoring data from p reterm infants. Patients and data. Monitored PO2 and PCO2 data (1 value per minute) from 10 preterm infants requiring intensive care were used for the se experiments. A domain expert was used to review and confirm the detected artifact. Methods.Three different classes of artifact detectors (i.e., lim it-based detectors, deviation-based detectors, and correlation-based detect ors) were designed and used. Each identified artifacts from a different per spective. Integrating the individual detectors, we developed a parametric a rtifact detector, called ArtiDetect. By an exhaustive search in the space o f ArtiDetect instances, we successfully discovered an optimal instance, den oted as ArtiDetector. Results. The sensitivity and specificity of ArtiDetec tor for PO2 artifacts is 95.0% (SD = 4.5%) and 94.2% (SD = 4.5%), respectiv ely. The sensitivity and specificity of ArtiDetector for PCO2 artifacts is 97.2% (SD = 3.6%) and 94.1% (SD = 4.2%), respectively. Moreover, 97.0% and 98.0% of the artifactual episodes in the PO2 and PCO2 channels respectively are confirmed by ArtiDetector. Conclusions. Based on the judgement of the expert, our detection method detects most PO2 and PCO2 artifacts and artifa ctual episodes in the 10 randomly selected preterm infants. The method make s little use of domain knowledge, and can be easily extended to detect arti facts in other monitoring channels.