King's College London

Research portal

Non-invasive attractor reconstruction analysis for early detection of deteriorations

Research output: Other contribution

Peter Charlton, Luigi Camporota, John Smith, Manasi Nandi, Mark Ian Christie, Philip Aston, Richard Beale

Original languageEnglish
TypePoster Presentation

Bibliographical note

This contribution won an award for the best poster presentation at the Imaging Sciences and Biomedical Engineering Divisional Symposium, King's College London, October 2015


  • Att_Recon_Poster

    Att_Recon_Poster.pdf, 890 KB, application/pdf

    Uploaded date:20 Oct 2015

    Version:Accepted author manuscript

King's Authors


Acutely-ill hospital patients are at risk of clinical deteriorations. Attractor reconstruction (AR) analysis of the arterial blood pressure (ABP) signal has recently been proposed as a method for measuring the changes in cardiovascular state which accompany deteriorations. Since ABP signals are only available in a minority of clinical scenarios, we sought to determine whether AR could also be performed on more widely available pulse oximetry (photoplethysmogram, PPG) signals. AR analysis was performed on simultaneous ABP and PPG signals before, during and after a change in cardiovascular state. A novel quality metric was used to eliminate windows of low quality AR. A high level of agreement was found between the detected periodicity of each signal. The remaining cardiovascular parameters derived using AR analysis exhibited similar trends between the two signals in response to the change in state, although there was poor agreement between their absolute values. This demonstrates the feasibility of applying AR to the PPG signal. Since the PPG signal is measured every 4-6 hours during routine nursing observations, this suggests that AR analysis could be performed automatically as part of routine practice. This may facilitate early identification of deteriorations such as sepsis, which has a profound effect on cardiovascular state.

Download statistics

No data available

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454