Using Confidence Intervals to Assess the Reliability of Instantaneous Heart Rate and Respiratory Rate

Abstract

Physiological waveform signals collected from unstructured environments are noisy, requiring automated algorithms to assess the reliability of the derived vital signs, such as heart rate (HR) and respiratory rate (RR), before they can be used for automated decision support. We recently proposed a weighted regularized least squares method to estimate instantaneous HR (HRR), which readily provides analytically based confidence intervals (CIs). Accordingly, this method can be extended to the estimation of instantaneous RR (RRR). In this study, we aim to investigate whether we can use CIs to select reliable HRR and RRR. We calculated HRR and RRR for 532 and 370 trauma patients, respectively, grouped the rates according to their CIs, and investigated their reliability by determining their ability to diagnose major hemorrhage. The areas under a receiver operating characteristic curve of HRR and RRR with CI &#8804; 5 bpm (beats per minute for HR and breaths per minute for RR) were 0.70 and 0.66, respectively. RRR was superior to the average output of the clinical monitor (p < 0.05 by DeLong's test), while HRR was equivalent. HRR and RRR provide a new approach to systematically and automatically assess the reliability of noisy, field-collected vital signs.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2011
Accession Number
ADA571024

Entities

People

  • Andrew T. Reisner
  • Jaques Reifman
  • Liangyou Chen
  • Xiaoxiao Chen

Organizations

  • United States Army Medical Research and Development Command

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Algorithms
  • Application Software
  • Casualties
  • Data Analysis
  • Data Science
  • Databases
  • Electrocardiography
  • Electronic Mail
  • Health Services
  • Heart Rate
  • Hemorrhage
  • Information Science
  • Intervals
  • Reliability
  • Statistics
  • Vital Signs
  • Waveforms

Fields of Study

  • Medicine

Readers

  • Cardiovascular Physiology
  • Geospatial Intelligence and Artificial Intelligence Analytics
  • Sensor Fusion and Tracking Systems.