Thermal patient signal analysis

• US 10,398,321 B2
• Filed: 09/01/2015
• Issued: 09/03/2019
• Est. Priority Date: 09/01/2015
• Status: Active Grant

• Current Assignee: PixArt Imaging Incorporated
• Original Assignee: Siemens Healthcare GMBH (Siemens AG)
• Inventors: Zhang, Hongxuan
• Primary Examiner(s): Jackson, Gary
• Assistant Examiner(s): Kuo, Jonathan
• Application Number:
  US14/842,606
• Publication Number:
  US 20170055849A1
• Time in Patent Office: 1,463 Days
• Field of Search: 128920-925, 374100-107, 600300-301, 600473-475, 600481, 600483, 600500, 600508, 600513-519, 600526, 600549
• CPC Class Codes: A61B 5/01 Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue clinical contact thermometers G01K13/20
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/14552 Details of sensors specially adapted therefor
• CPC Class Codes: A61B 5/7235 Details of waveform analysis A61B5/349 takes precedence
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 40/67 for remote operation

Abstract

Disclosed herein is a framework for facilitating thermal patient signal analysis. In accordance with one aspect, the framework receives patient signal data including thermal signal data. The framework then segments a waveform of the thermal signal data into portions and extracts thermal parameters based on the segmented portions. The framework then determines one or more thermal indices based at least in part on the thermal parameters and generates a report that presents cardiac event detection results determined based at least in part on the one or more thermal indices.

Claims

1. A system for patient signal analysis, comprising:

a patient monitor including a sensor system with a non-thermal sensor and multiple thermal sensors that simultaneously acquires multiple types of patient signal data including non-thermal signal data, first and second different types of thermal signal data, wherein the multiple thermal sensors acquire the first and second different types of thermal signal data that is generated in response to heat from blood flowing in blood vessels of a patient; and

a computer system communicatively coupled to the patient monitor to receive the patient signal data, wherein the computer system includes

a non-transitory memory device for storing computer readable program code, and

a processor in communication with the memory device, the processor being operative with the computer readable program code to perform steps including

determining continuous temperature cycles from the first and second different types of thermal signal data,

synchronizing a first waveform of the continuous temperature cycles from the first or second different type of thermal signal data with a second waveform of the non-thermal signal data by determining time durations between peaks of the first waveform and peaks of the second waveform within a predetermined time window,

determining at least one synchronicity value based at least in part on the time durations, and

generating a report that presents cardiac event detection results determined based at least in part on the at least one synchronicity value.

2. The system of claim 1 wherein the patient monitor comprises a smart device.

3. The system of claim 1 wherein the multiple thermal sensors acquire the first and second different types of the thermal signal data from different locations on a body surface.

4. The system of claim 1 wherein the first and second different types of the thermal signal data each comprises at least one of temperature signal data, temperature speed signal data, temperature acceleration signal data, thermal pulse or temperature variation pulse waveform.

5. The system of claim 1 wherein the processor is operative with the computer readable program code to determine one or more thermal indices based at least in part on the first and second different types of thermal signal data and the non-thermal signal data.

6. The system of claim 1 wherein the non-thermal signal data comprises electrocardiogram (ECG) signal data, oximetric signal data, or a combination thereof.

7. The system of claim 1 wherein the synchronicity value comprises a mean, standard deviation or variance of the time durations.

8. A method of patient signal analysis, comprising:

receiving, from a patient monitor, patient signal data acquired at one or more sensors and including first and second different types of thermal signal data, wherein multiple thermal sensors acquire the first and second different types of thermal signal data, wherein the first and second different types of thermal signal data is generated in response to heat form blood flowing in blood vessels of a patient;

determining continuous temperature cycles from the first and second different types of thermal signal data;

segmenting, by a computer system, a waveform of the continuous temperature cycles into portions, including separating the waveform according to temperature threshold values that are predefined as different percentages of an amplitude range of the waveform;

extracting, by the computer system, thermal parameters based on the segmented portions;

determining, by the computer system, one or more thermal indices based at least in part on the thermal parameters; and

generating, by the computer system, a report that presents cardiac event detection results determined based at least in part on the one or more thermal indices.

9. The method of claim 8 wherein extracting the thermal parameters comprises determining time durations from time stamps of start or end point of the segmented portions with respect to a time stamp of an amplitude peak of the waveform.

10. The method of claim 8 wherein extracting the thermal parameters comprises determining time intervals of the segmented portions.

11. The method of claim 8 wherein determining the one or more thermal indices comprises determining a single time ratio based on time intervals or time durations extracted from the segmented portions.

12. The method of claim 8 wherein determining the one or more thermal indices comprises determining a cross time ratio based on time intervals or time durations extracted from the segmented portions.

13. The method of claim 8 wherein determining the one or more thermal indices comprises determining a time duration variability based on time intervals or time durations extracted from the segmented portions.

14. The method of claim 8 wherein extracting the thermal parameters comprises extracting a frequency spectrum from the thermal signal data.

15. The method of claim 14 wherein determining the one or more thermal indices comprises determining a single frequency ratio based on frequency magnitudes extracted from the frequency spectrum.

16. The method of claim 14 wherein determining the one or more thermal indices comprises determining a cross frequency ratio based on frequency magnitudes extracted from the frequency spectrum.

17. The method of claim 8 further comprising:

synchronizing the waveform of the continuous temperature cycles with another waveform of the patient signal data by determining time durations between peaks of the waveform and peaks of the another waveform within a predetermined time window; and

determining a synchronicity value based at least in part on the time durations.

18. A non-transitory computer readable medium embodying a program of instructions executable by machine to perform steps for patient signal analysis, the steps comprising:

receiving patient signal data acquired at one or more sensors and including first and second different types of thermal signal data, wherein multiple thermal sensors acquire the first and second different types of thermal signal data, wherein the first and second different types of thermal signal data is generated in response to heat from blood flowing in blood vessels of a patient;

determining continuous temperature cycles from the first and second different types of thermal signal data;

segmenting a waveform of the continuous temperature cycles into portions, including separating the waveform according to temperature threshold values that are predefined as different percentages of an amplitude range of the waveform;

extracting thermal parameters based on the segmented portions;

determining one or more thermal indices based at least in part on the thermal parameters; and

generating a report that presents cardiac event detection results determined based at least in part on the one or more thermal indices.