Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 28, 2014Scientific ReportsOpen Access

Surface Chest Motion Decomposition for Cardiovascular Monitoring

View Full Paper
Ask AI
Bookmark
Share

Key result

Independent Component Analysis with reference (ICA-R) using ECG or delayed autocorrelation yielded superior separation of precordial motion from respiratory motion compared to conventional bandpass filtering.

Population

9 healthy male subjects, age 22-32 (mean 25.6) years, BMI 18.3-27.2 (mean 21.86) kg/m2

Comparison

Independent Component Analysis with Reference… vs Conventional FastICA and zero-phase 4th order…

Design

Other

Authors

GSGhufran ShafiqCOMSATS University IslamabadKVKalyana C. VeluvoluKyungpook National University

Discussion

Loading...

Member takes

Implication

May aid unobtrusive cardiac monitoring from chest signals; leaves open prospective validation before clinical adoption.

Structured PICO

P
Population
9 healthy male subjects aged 22-32 years underwent surface chest motion recording under normal breathing and post-exercise conditions to validate motion decomposition algorithms.
I
Intervention
Independent Component Analysis with Reference (ICA-R) using delayed autocorrelation and ECG-based reference generation
C
Comparator
Conventional FastICA and zero-phase 4th order Butterworth bandpass filter
O
Outcome
Separation of precordial motion from respiratory motion, measured by Improvement in Normalized Power Spectrum Ratio (INPS) and Peak-R offsetsurrogate

ICA-R with delayed autocorrelation effectively separates cardiac motion from dominant respiratory motion in surface chest motion signals, offering a potential method for unobtrusive cardiovascular monitoring.

Limitations

  • The template generation for ICAR-ECG requires the subject to hold breath once for adequate time (10-15 seconds), which can be inconvenient for patients with respiratory conditions.
  • The separation performance of ICAR-Correlation depends on the proper selection of time delay.
  • Decreased performance in post-exercise trials as compared to free breathing trials due to changing characteristics of heart and respiratory motion.
  • Current work relies on optical sensors; employing accelerometers to obtain displacement is a major challenge.
  • Template generation for ICAR-ECG requires breath hold which can be inconvenient for patients with respiratory conditions
  • Separation performance of ICAR-Correlation depends on proper selection of time delay
  • Band-pass filter approach relies on subject specific tuning
  • Decreased performance of all methods in post-exercise trials compared to free breathing trials

Cite This Study

Shafiq et al. (2014) studied Healthy subjects (n=9). Independent Component Analysis with Reference (ICA-R) vs. Band pass filtering and FastICA was evaluated on Improvement in Normalized Power Spectrum Ratio (INPS) and Peak-R offset. Independent Component Analysis with reference (ICA-R) using ECG or delayed autocorrelation yielded superior separation of precordial motion from respiratory motion compared to conventional bandpass filtering.

synapsesocial.com/papers/6a95a432291973b08cfbfe0ehttps://doi.org/10.1038/srep05093
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Auto-threshold peak detection in physiological signals2005 · 77 citations
  2. 2Discrete Event Simulation Model of Sudden Cardiac Death Predicts High Impact of Preventive Interventions2013 · 13 citations
  3. 3Precordial Vibrations Provide Noninvasive Detection of Early-Stage Hemorrhage2013 · 57 citations
  4. 4Prognosis—A Wearable Health-Monitoring System for People at Risk: Methodology and Modeling2010 · 134 citations
  5. 5If We Build It, Who Will Come?2011 · 41 citations