Limits...
Estimation of cardiac output and systemic vascular resistance using a multivariate regression model with features selected from the finger photoplethysmogram and routine cardiovascular measurements.

Lee QY, Redmond SJ, Chan GSh, Middleton PM, Steel E, Malouf P, Critoph C, Flynn G, O'Lone E, Lovell NH - Biomed Eng Online (2013)

Bottom Line: Spectral and morphological features were extracted from the finger photoplethysmogram, and added to heart rate and mean arterial pressure as input features to a multivariate regression model to estimate CO and SVR.A stepwise feature search algorithm was employed to select statistically significant features.The Bland-Altman bias ±precision (1.96 times standard deviation) for CO was -0.01 ±2.70 L min-1 when only photoplethysmogram (PPG) features were used, and for SVR was -0.87 ±412 dyn.s.cm-5 when only one PPG variability feature was used.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia. qimyi.lee@unsw.edu.au

ABSTRACT

Background: Cardiac output (CO) and systemic vascular resistance (SVR) are two important parameters of the cardiovascular system. The ability to measure these parameters continuously and noninvasively may assist in diagnosing and monitoring patients with suspected cardiovascular diseases, or other critical illnesses. In this study, a method is proposed to estimate both the CO and SVR of a heterogeneous cohort of intensive care unit patients (N=48).

Methods: Spectral and morphological features were extracted from the finger photoplethysmogram, and added to heart rate and mean arterial pressure as input features to a multivariate regression model to estimate CO and SVR. A stepwise feature search algorithm was employed to select statistically significant features. Leave-one-out cross validation was used to assess the generalized model performance. The degree of agreement between the estimation method and the gold standard was assessed using Bland-Altman analysis.

Results: The Bland-Altman bias ±precision (1.96 times standard deviation) for CO was -0.01 ±2.70 L min-1 when only photoplethysmogram (PPG) features were used, and for SVR was -0.87 ±412 dyn.s.cm-5 when only one PPG variability feature was used.

Conclusions: These promising results indicate the feasibility of using the method described as a non-invasive preliminary diagnostic tool in supervised or unsupervised clinical settings.

Show MeSH

Related in: MedlinePlus

Bland-Altman plot of the SVR estimation. The solid line in the middle is the bias and the two lines above and below are the limits of agreement, calculated as bias ±1.96×s.d.. Bias = -0.87 dyn.s.cm-5, 1.96×s.d. = 412 dyn.s.cm-5.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3649882&req=5

Figure 7: Bland-Altman plot of the SVR estimation. The solid line in the middle is the bias and the two lines above and below are the limits of agreement, calculated as bias ±1.96×s.d.. Bias = -0.87 dyn.s.cm-5, 1.96×s.d. = 412 dyn.s.cm-5.

Mentions: Figures4 and5 show plots of the estimated variable plotted against the measured variable, along with the line of equality, for the best CO and SVR models, respectively. The Bland-Altman plot of the best CO and SVR estimations are depicted in Figures6 and7.


Estimation of cardiac output and systemic vascular resistance using a multivariate regression model with features selected from the finger photoplethysmogram and routine cardiovascular measurements.

Lee QY, Redmond SJ, Chan GSh, Middleton PM, Steel E, Malouf P, Critoph C, Flynn G, O'Lone E, Lovell NH - Biomed Eng Online (2013)

Bland-Altman plot of the SVR estimation. The solid line in the middle is the bias and the two lines above and below are the limits of agreement, calculated as bias ±1.96×s.d.. Bias = -0.87 dyn.s.cm-5, 1.96×s.d. = 412 dyn.s.cm-5.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3649882&req=5

Figure 7: Bland-Altman plot of the SVR estimation. The solid line in the middle is the bias and the two lines above and below are the limits of agreement, calculated as bias ±1.96×s.d.. Bias = -0.87 dyn.s.cm-5, 1.96×s.d. = 412 dyn.s.cm-5.
Mentions: Figures4 and5 show plots of the estimated variable plotted against the measured variable, along with the line of equality, for the best CO and SVR models, respectively. The Bland-Altman plot of the best CO and SVR estimations are depicted in Figures6 and7.

Bottom Line: Spectral and morphological features were extracted from the finger photoplethysmogram, and added to heart rate and mean arterial pressure as input features to a multivariate regression model to estimate CO and SVR.A stepwise feature search algorithm was employed to select statistically significant features.The Bland-Altman bias ±precision (1.96 times standard deviation) for CO was -0.01 ±2.70 L min-1 when only photoplethysmogram (PPG) features were used, and for SVR was -0.87 ±412 dyn.s.cm-5 when only one PPG variability feature was used.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia. qimyi.lee@unsw.edu.au

ABSTRACT

Background: Cardiac output (CO) and systemic vascular resistance (SVR) are two important parameters of the cardiovascular system. The ability to measure these parameters continuously and noninvasively may assist in diagnosing and monitoring patients with suspected cardiovascular diseases, or other critical illnesses. In this study, a method is proposed to estimate both the CO and SVR of a heterogeneous cohort of intensive care unit patients (N=48).

Methods: Spectral and morphological features were extracted from the finger photoplethysmogram, and added to heart rate and mean arterial pressure as input features to a multivariate regression model to estimate CO and SVR. A stepwise feature search algorithm was employed to select statistically significant features. Leave-one-out cross validation was used to assess the generalized model performance. The degree of agreement between the estimation method and the gold standard was assessed using Bland-Altman analysis.

Results: The Bland-Altman bias ±precision (1.96 times standard deviation) for CO was -0.01 ±2.70 L min-1 when only photoplethysmogram (PPG) features were used, and for SVR was -0.87 ±412 dyn.s.cm-5 when only one PPG variability feature was used.

Conclusions: These promising results indicate the feasibility of using the method described as a non-invasive preliminary diagnostic tool in supervised or unsupervised clinical settings.

Show MeSH
Related in: MedlinePlus