Method for determining cardiac output

• US 8,920,327 B2
• Filed: 11/08/2006
• Issued: 12/30/2014
• Est. Priority Date: 11/08/2005
• Status: Active Grant

• Current Assignee: ARC Seibersdorf Research GmbH
• Original Assignee: ARC Seibersdorf Research GmbH
• Inventors: Wassertheurer, Siegfried, Mayer, Christopher
• Primary Examiner(s): Brown, Melanie Y
• Assistant Examiner(s): Crawford, Erik B
• Application Number:
  US12/084,668
• Publication Number:
  US 20090287095A1
• Time in Patent Office: 2,974 Days
• Field of Search: 128/925, 600/408, 700/48
• US Class Current: 600/485
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/029 Measuring or recording blood output from the heart, e.g. minute volume A61B8/065 takes precedence
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

In a method for determining cardiac output from an arterial blood pressure curve measured at the periphery, in which the blood pressure curve measured at the periphery is arithmetically transformed into the corresponding central blood pressure curve and the cardiac output is calculated from the central blood pressure curve, the transformation of the blood pressure curve measured at the periphery into the corresponding central blood pressure curve is performed by the aid of an artificial neural network whose weighting values are determined by learning.

Claims

1. A method for determining cardiac output from an arterial blood pressure curve measured at a peripheral region, comprising the steps of:

measuring the arterial blood pressure curve at the peripheral region;

arithmetically transforming the measured arterial blood pressure curve to an equivalent aortic pressure; and

calculating the cardiac output from the equivalent aortic pressure, wherein

the arithmetic transformation of the arterial blood pressure curve measured at the peripheral region into the equivalent aortic pressure is performed by the aid of an artificial neural network having weighting values that are determined by learning.

2. The method according to claim 1, wherein the artificial neural network is configured as a feed-forward network.

3. The method according to claim 1, wherein the artificial neural network is comprised of at least three layers.

4. The method according to claim 1, wherein

the artificial neural network is comprised of three layers, and

a number of neurons contained in the first layer and a number of neurons contained in the third layer are each selected to be at least three times a number of neurons contained in the second layer, which is a central layer.

5. The method according to claim 1, wherein

the artificial neural network is comprised of three layers,

the first layer and the third layer of the artificial neural network are each composed of at least 100 neurons, and

the second layer is a central layer and is composed of at least 10 neurons.

6. The method according to claim 1, wherein said learning is performed by supervised learning and the weighting values are determined by the aid of a backpropagation algorithm.

7. The method according to claim 1, wherein the determination of the cardiac output is performed departing from a system dynamics described by a windkessel equation in regard to an optimization of an ejection rate of a left ventricle by applying a variation calculation.

8. The method according to claim 2, wherein the network is a completely connected feed-forward network.

9. The method according to claim 1, wherein

the artificial neural network is comprised of three layers, and

a number of neurons contained in the first layer and a number of neurons contained in the third layer are each selected to be at least five times a number of neurons contained in the second layer, which is a central layer.

10. The method according to claim 1, wherein

the artificial neural network is comprised of three layers, and

a number of neurons contained in the first layer and a number of neurons contained in the third layer are each selected to be at least ten times a number of neurons contained in the second layer, which is a central layer.