System for non-invasive cardiac output determination

• US 9,332,917 B2
• Filed: 01/17/2013
• Issued: 05/10/2016
• Est. Priority Date: 02/22/2012
• Status: Active Grant

• Current Assignee: PixArt Imaging Incorporated
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Zhang, Hongxuan
• Primary Examiner(s): LEVICKY, WILLIAM J
• Application Number:
  US13/743,441
• Publication Number:
  US 20130218038A1
• Time in Patent Office: 1,209 Days
• Field of Search: 600/526, 600/521, 600/516
• US Class Current: 1/1
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• 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 5/053 Measuring electrical impedance or conductance of a portion of the body
• CPC Class Codes: A61B 5/14551 for measuring blood gases
• CPC Class Codes: A61B 5/352 Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• 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 5/7285 for synchronising or triggering a physiological measurement or image acquisition with a physiological event or waveform, e.g. an ECG signal A61B6/5205, A61B6/541, A61B8/5207, A61B8/543 take precedence

Abstract

A method determines cardiac output or stroke volume by receiving signal data representing multiple parameters of a patient concurrently acquired over a particular time period and comprising at least one of, (a) a parameter derived from an ECG waveform of the patient, (b) a parameter derived from a blood pressure signal of the patient, (c) a parameter derived from signal data representing oxygen content of blood of the patient and (d) a parameter derived from a patient cardiac impedance value. A selected parameter of the multiple concurrently acquired parameters is used in calculating a heart stroke volume of the patient comprising volume of blood transferred through the blood vessel in a heart cycle, in response to, a combination of a weighted summation of values of the selected parameter over the particular time period. Data representing the calculated heart stroke volume is provided to a destination device.

Claims

1. A method for determining cardiac output or stroke volume, comprising the activities of:

receiving, by a processing device, signal data representing a plurality of parameters of a patient, said plurality of parameters being concurrently acquired from a patient over a particular time period and comprising at least two of

(a) a parameter derived from an ECG waveform of said patient,

(b) a parameter derived from a blood pressure signal of said patient,

(c) a parameter derived from signal data representing oxygen content of blood of said patient, and

(d) a parameter derived from a patient cardiac impedance value;

combining, by the processing device via a configured artificial neural network, said plurality of parameters and other information of the patient to generate coefficients as output of the artificial neural network, wherein the configured artificial neural network includes weights that are tuned using a training data set including said plurality of concurrently acquired parameters and the coefficients are generated by applying the weights between multiple layers of the artificial neural network;

calculating, by the processing device, a heart stroke volume of said patient comprising volume of blood transferred through the blood vessel in a heart cycle by determining a summation of the coefficients multiplied by selected parameters of the plurality of concurrently acquired parameters and statistical values of said selected parameters over said particular time period;

characterizing, by the processing device, cardiac arrhythmia using the calculated heart stroke volume; and

providing, by the processing device, data representing the characterized cardiac arrhythmia to a destination device.

2. The method according to claim 1, wherein the signal data representing oxygen content of blood of said patient comprises a blood oxygen saturation (SPO2) signal.

3. The method according to claim 1, wherein said plurality of parameters further comprises at least one of, (a) temperature of said patient, (b) invasive blood pressure of said patient, (c) non-invasive blood pressure of said patient and (d) a rate of change of blood pressure of said patient.

4. The method according to claim 1, wherein the statistical values comprise a standard deviation or a higher order statistical value.

5. The method according to claim 1, wherein calculating the heart stroke volume of said patient further comprises using a weighted combination of one or more parameters and a function of a form,

6. The method according to claim 1, including the steps of

receiving a factor representing reduction in blood flow volume from a patient heart to a particular anatomical location, and

calculating a heart stroke volume of said patient in response to the factor representing the reduction in blood flow volume from the patient heart to the particular anatomical location.

7. The method according to claim 1, including the step of

using predetermined mapping information associating ranges of calculated stroke volume or values derived from said calculated stroke volume with medical conditions and for mapping the calculated stroke volume to data indicating a medical condition of said patient and

providing data representing the indicated medical condition to the destination device.

8. A method for determining cardiac output or stroke volume, comprising the activities of:

receiving, by a processing device, signal data representing a plurality of parameters of a patient including first and second different parameters, said plurality of parameters being concurrently acquired from a patient over a particular time period and comprising at least two of

(a) a parameter derived from an ECG waveform of said patient,

(b) a parameter derived from a blood pressure signal of said patient, and

(c) a parameter derived from signal data representing oxygen content of blood of said patient;

combining, by the processing device via a configured artificial neural network, said plurality of parameters and other information of the patient to generate coefficients as output of the artificial neural network, wherein the configured artificial neural network includes weights that are tuned using a training data set including said plurality of concurrently acquired parameters and the coefficients are generated by applying the weights between multiple layers of the artificial neural network;

calculating, by the processing device, a heart stroke volume of said patient comprising volume of blood transferred through the blood vessel in a heart cycle by determining a first summation of values of the coefficients multiplied by the first parameter and a second summation of values of the coefficients multiplied by statistical values of the second parameter, over said particular time period;

characterizing, by the processing device, cardiac arrhythmia using the calculated heart stroke volume; and

providing data representing the characterized cardiac arrhythmia to a destination device.

9. The method according to claim 8, wherein the signal data representing oxygen content of blood of said patient comprises a blood oxygen saturation (SPO2) signal.

10. The method according to claim 8, wherein said plurality of parameters further comprises at least one of, (a) temperature of said patient, (b) invasive blood pressure of said patient, (c) non-invasive blood pressure of said patient and (d) a rate of change of blood pressure of said patient.

11. The method according to claim 8, wherein the statistical values comprise a standard deviation or a higher order statistical value.

12. The method according to claim 8, including the steps of

receiving a factor representing reduction in blood flow volume from a patient heart to a particular anatomical location, and

calculating a heart stroke volume of said patient in response to the factor representing the reduction in blood flow volume from the patient heart to the particular anatomical location.

13. The method according to claim 8, including the step of

using predetermined mapping information associating ranges of calculated stroke volume or values derived from said calculated stroke volume with medical conditions and for mapping the calculated stroke volume to data indicating a medical condition of said patient and

providing data representing the indicated medical condition to a destination device.

14. The method according to claim 8, wherein the other information of the patient includes patient demographic data.

15. The method according to claim 14, wherein said demographic data comprises at least two of age, height, weight, gender, and pregnancy status.

16. The method according to claim 8, including the steps of

using predetermined mapping information associating ranges of calculated stroke volume or values derived from said calculated stroke volume with medical conditions and for mapping the calculated stroke volume to data indicating a medical condition of said patient and

providing data representing the indicated medical condition to the destination device wherein said predetermined mapping information associates ranges of the calculated stroke volume with particular patient demographic characteristics and with corresponding medical conditions and

using patient demographic data including at least one of age, weight, gender, and height in comparing the calculated stroke volume with said ranges and generating an alert message indicating a potential medical condition.

17. A system for determining cardiac output or stroke volume, comprising:

an interface configured to receive signal data representing a plurality of parameters of a patient, said plurality of parameters being concurrently acquired from a patient over a particular time period and comprising at least one of

(a) a parameter derived from an ECG waveform of said patient,

(b) a parameter derived from a blood pressure signal of said patient,

(c) a parameter derived from signal data representing oxygen content of blood of said patient and

(d) a parameter derived from a patient cardiac impedance value;

a data processor configured to

generate coefficients as output of a configured artificial neural network based on said plurality of parameters and other information of the patient, wherein the configured artificial neural network includes weights that are tuned using a training data set including said plurality of concurrently acquired parameters and the coefficients are generated by applying the weights between multiple layers of the artificial neural network, and

calculating a heart stroke volume of said patient comprising volume of blood transferred through the blood vessel in a heart cycle, by determining a summation of the generated coefficients multiplied by the selected parameters of the plurality of concurrently acquired parameters over said particular time period and statistical values of said selected parameters;

a detector configured to characterize cardiac arrhythmia using the calculated heart stroke volume; and

an output processor configured to provide data representing the characterized cardiac arrhythmia to a destination device.

18. The system according to claim 17, wherein said data processor calculates said heart stroke volume, in response to, a combination of a weighted summation of values of a first parameter and a weighted summation of values of a second parameter, said summation being over said particular time period and the first and second parameters are selected from said plurality of parameters.