liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Neural network for photoplethysmographic respiratory rate monitoring
Linköping University, Department of Biomedical Engineering. Linköping University, The Institute of Technology.
2003 (English)In: Medical and Biological Engineering and Computing, ISSN 0140-0118, E-ISSN 1741-0444, Vol. 41, no 3, 242-248 p.Article in journal (Refereed) Published
Abstract [en]

The reflection mode photoplethysmographic (PPG) signal was studied with the aim of determining respiratory rate. The PPG signal includes respiratory synchronous components, seen as frequency modulation of the heart rate (respiratory sinus arrhythmia), amplitude modulation of the cardiac pulse and respiratory-induced intensity variations (RIIVs) in the PPG baseline. PPG signals were recorded from the foreheads of 15 healthy subjects. From these signals, the systolic wavefrm diastolic waveform, respiratory sinus arrhythmia, pulse amplitude and RIIVs were extracted. Using basic algorithms, the rates of false positive and false negative detection of breaths were calculated separately for each of the five components. Furthermore, a neural network was assessed in a combined pattern recognition approach. The error rates (sum of false positive and false negative breath detections) for the basic algorithms ranged from 9.7% (pulse amplitude) to 14.5% (systolic waveform). The corresponding values for the neural network analysis were 9.5–9.6%. These results suggest the use of a combined PPG system for simultaneous monitoring of respiratory rate and arterial oxygen saturation (pulse oximetry).

Place, publisher, year, edition, pages
2003. Vol. 41, no 3, 242-248 p.
National Category
Medical and Health Sciences
URN: urn:nbn:se:liu:diva-24477DOI: 10.1007/BF02348427Local ID: 6593OAI: diva2:244797
Available from: 2009-10-07 Created: 2009-10-07 Last updated: 2013-02-19
In thesis
1. Photoplethysmography in multiparameter monitoring of cardiorespiratory function
Open this publication in new window or tab >>Photoplethysmography in multiparameter monitoring of cardiorespiratory function
2000 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Photoplethysmography (PPG) is an optical, non-invasive method to assess tissue blood volume/perfusion. When measured on human skin, the PPG signal includes both cardiac synchronous variations (AC) and respiratory induced intensity variations (RIIV). This makes the PPG signal appropriate for cardiorespiratory monitoring, as a single non-invasive sensor extracts both cardiac and respiratory information.

In this thesis, the origin of the RIIV signal is discussed, and invasive measurements of pressures in the circulatory system support the hypothesis of a venous origin. Important factors are intrathoracic and intra-abdominal pressure fluctuations, affecting venous return from the extrathoracic veins and the peripheral venous bed.

Previous reports have demonstrated a possibility to extract the RIIV signal for assessing respiratory rates. A more effective and reliable monitoring would be achieved if tidal volumes could be estimated from the PPG signal in addition to respiratory rates. This would provide a possibility to calculate and detect ventilatory trends. A relationship between the RIIV amplitude and the tidal volume was hypothesised, demonstrated in healthy subjects and verified in a theoretical (Windkessel) model of the circulatory system. Other factors than tidal volume influence intrathoracic and intra-abdominal pressures. Effects of thoraco-abdominal separation, posture and respiratory rate were observed, and their influence in tidal volume/ventilation monitoring was discussed.

Monitoring the cardiorespiratory function is essential in the postoperative and neonatal care environments. Studies have been performed in clinical settings including comparisons between the PPG method and more established monitoring systems. PPG was found to be suitable for monitoring heart and respiratory rates in these environments.

The arterial blood pressure contains respiratory related information, including heart rate fluctuations (respiratory sinus arrhythmia, RSA) and respiratory variations in cardiac stroke volume. These phenomena are seen in the PPG signal as frequency and amplitude modulation of the AC signal. An algorithm based on pattern recognition (neural networking) is presented, in which these respiratory components are extracted and combined with the RIIV signal. As the respiratory components are of different origins, the neural network algorithm is robust and more accurate for breath detection than algorithms utilising the components separately.

The main purposes of cardiorespiratory monitoring are to detect pathologic minute ventilation, apnoea, hypoxaemia, cardiac arrest, arrhythmia, and trends in heart rate. By using PPG, simultaneous information about heart rate, respiratory rate and tidal volume is obtained. Furthermore, as the measurement of arterial oxygen saturation by PPG is well established, a good coverage of the cardiorespiratory function can be obtained from a single non-invasive sensor.

Place, publisher, year, edition, pages
Linköping: Linköpings universitet, 2000. 63 p.
Linköping Studies in Science and Technology. Dissertations, ISSN 0345-7524 ; 629
National Category
Medical and Health Sciences
urn:nbn:se:liu:diva-29446 (URN)14793 (Local ID)91-7219-715-3 (ISBN)14793 (Archive number)14793 (OAI)
Public defence
2000-04-28, Elsa Brändströms sal, Universitetssjukhuset, Linköping, 13:15 (Swedish)
Available from: 2009-10-09 Created: 2009-10-09 Last updated: 2013-02-19

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Johansson, Anders
By organisation
Department of Biomedical EngineeringThe Institute of Technology
In the same journal
Medical and Biological Engineering and Computing
Medical and Health Sciences

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 885 hits
ReferencesLink to record
Permanent link

Direct link