This Article Full Text (PDF) Submit a scholarly reply Alert me when this article is cited Alert me when eLetters are posted Alert me if a correction is posted Services Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Ansermino, M. Articles by Ries, C. R Search for Related Content PubMed Articles by Ansermino, M. Articles by Ries, C. R

ADAPTIVE CHANGE POINT DETECTION ALGORITHM FOR HEART RATE IN CHILDREN

Department of Pediatric Anesthesia, B.C. Children’s Hospital, 4480 Oak Street, Vancouver, BC V6H 3V4
Department of Electrical and Computer Engineering, The University of British Columbia, 2356 Main Mall, Vancouver, BC V6T 1Z4

INTRODUCTION: The astute pediatric anesthesiologist uses subtle changes in patient heart rates to monitor changes in anesthesia depth and dictate fluid administration. Clinicians can perceive fluctuations of three to four beats per minute from auditory signals¹; but may become distracted by simultaneous tasks. We have attempted to replicate optimum clinician performance in an automated system.

METHODS: Following institutional ethical approval, trend heart rate data was collected from 53 children. Clinically detected changes in heart rate, using standard auditory and visual monitoring, were recorded in synchrony with the trend data. A purpose-built graphical interface was used for post-hoc expert marking of episodes of heart rate increase; graded as definitely or likely significant/ insignificant or artifact using predefined criteria. Following data segmentation, an automated change-point detection algorithm, with adaptive Kalman filtering and a local CUSUM, was used to identify points of increasing heart rate. The relative performance of the algorithm and real-time clinicians was compared against the post-hoc expert review.

RESULTS: Five cases were excluded due to incomplete data. Results from the remaining sample indicated that the automated trend detection algorithm performed as well as clinicians under test conditions, without a significant increase in the false positive detection rate.

Monitoring Performance Post Hoc Expert Automated Algorithm Real Time Clinician True HR increase 109 79 80 Missed HR increase 0 30 29 False HR increase 0 27 33

DISCUSSION: The exponential increase in monitored physiological parameters within the operating room has raised the cognitive burden of anesthesiologists faced with interpreting the resultant streams of data. By improving time series analysis, computational pattern recognition, knowledge representation, automated reasoning and intelligent communication, human performance can be enhanced.

The automated method seems to describe the signal efficiently; however, it is unlikely to be applicable to all physiological signals without significant tuning. Further work is needed on the classification and organization of change points and the simultaneous integration of multiple signals.

REFERENCES:

1 Anesth Analg 2004; 98:A76.

This Article Full Text (PDF) Submit a scholarly reply Alert me when this article is cited Alert me when eLetters are posted Alert me if a correction is posted Services Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Ansermino, M. Articles by Ries, C. R Search for Related Content PubMed Articles by Ansermino, M. Articles by Ries, C. R