Method and system for acquiring data for assessment of cardiovascular disease

• US 10,420,515 B2
• Filed: 11/21/2016
• Issued: 09/24/2019
• Est. Priority Date: 06/15/2015
• Status: Active Grant

• Current Assignee: Riva Health, Inc.
• Original Assignee: Vital Labs, Inc.
• Inventors: Sinha, Tuhin, Eslick, Ian, Leggitt, Alan
• Primary Examiner(s): Hulbert, Amanda K
• Application Number:
  US15/357,621
• Publication Number:
  US 20170065230A1
• Time in Patent Office: 1,037 Days
• CPC Class Codes: A61B 2576/00 Medical imaging apparatus involving image processing or analysis A61B1/00009, A61B6/52 and A61B8/52 take precedence; image processing per se G06T; details of algorithms for analysing medical images G06T7/0012
• CPC Class Codes: A61B 5/0077 Devices for viewing the surface of the body, e.g. camera, magnifying lens
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/02108 from analysis of pulse wave characteristics
• CPC Class Codes: A61B 5/02427 Details of sensor
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/4812 Detecting sleep stages or cycles
• CPC Class Codes: A61B 5/6826 Finger
• CPC Class Codes: A61B 5/6843 Monitoring or controlling sensor contact pressure
• CPC Class Codes: A61B 5/7221 Determining signal validity, reliability or quality A61B5/7207 and A61B5/7217 take precedence
• CPC Class Codes: A61B 5/7239 using differentiation including higher order derivatives
• 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 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients
• CPC Class Codes: G16H 20/70 relating to mental therapies, e.g. psychological therapy or autogenous training
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

A method and system for acquiring data for assessment of cardiovascular disease, the method comprising one or more of: manipulating one or more hardware aspects of the photoplethysmography data acquisition system(s) implementing the method; manipulating or providing user experience/user interface (UX/UI) aspects of the system(s) implementing the method; acquiring, processing, and deriving insights population specific data; accounting for or controlling sampling site variability; and using other suitable sources of data in order to generate high quality data for characterization, assessment, and management of cardiovascular disease.

Claims

1. A method for assessing cardiovascular health of an individual, comprising:

transmitting light toward a body region of an individual in coordination with receiving a time series of data of the body region of the individual at a camera module of a mobile computing device;

assessing a pressure distribution, and a positional map, of the body region touching the camera module of the mobile computing device for each of a set of frames of the time series of data;

performing an active pixel analysis operation with the time series of data, wherein performing the active pixel analysis comprises distinguishing an active pixel set for each of the set of frames of the time series of data;

aggregating the pressure distributions, the positional maps, and the active pixel sets of the set of frames of the time series of data of the body region into a summed time series of data;

extracting a subportion of the summed time series of data satisfying a signal quality threshold condition, upon performing a signal quality filtering operation with outputs of the active pixel analysis;

transforming the subportion of the summed time series of data into a cardiovascular health risk assessment of the individual; and

based upon the cardiovascular health risk assessment, automatically providing an intervention to the individual.

2. The method of claim 1, further comprising:

processing each of a set of color channels of the time series of data, the set of color channels comprising at least one channel in Lumina-chroma space and red-green-blue space; and

wherein assessing the pressure distribution, and the positional map, of the body region touching the camera module of the mobile computing device for each of the set of frames of the time series of data is based upon image analysis of the time series of data with the set of color channels.

3. The method of claim 2, further comprising collecting ambient light data from a second camera module of the mobile computing device, and wherein generating the summed time series of data comprises normalizing the time series of data with ambient light data from the second camera module.

4. The method of claim 1, further comprising, from the summed time series of data:

detecting changes in pressure and position of the body region against the camera module in near-real time, upon performing a change point detection operation, and

identifying a sequence of full cardiac cycles satisfying a biometric filter threshold condition.

5. The method of claim 4, wherein extracting the subportion of the summed time series of data comprises performing the signal quality filtering operation with outputs of the active pixel analysis and the change point detection operation for the sequence of full cardiac cycles.

6. The method of claim 1, wherein transforming the subportion of the summed time series of data into the cardiovascular health risk assessment of the individual comprises transforming the subportion of the summed time series of data into a set of cardiovascular health biomarker values, including a blood pressure value and an arterial stiffness value for the individual;

and transforming the set of cardiovascular health biomarker values into the cardiovascular health risk assessment.

7. The method of claim 6, wherein automatically providing the intervention to the individual comprises, at a display of the mobile computing device, rendering information indicative of cardiovascular disease risk to the individual, based upon the blood pressure value and the arterial stiffness value.

8. The method of claim 1, further including triggering receipt of ballistocardiography data from a force sensing touch system of the mobile computing device, receiving microphone data representative of the heart beat of the individual, and, in combination with the time series of data, generating the cardiovascular health risk assessment.

9. The method of claim 1, further including:

detecting a temperature of the body region touching the camera module, generating a comparison between the temperature and a low temperature threshold, and promoting an increase in the temperature with localized heating of a heating element in communication with the mobile computing device.

10. The method of claim 1, wherein, in response to the cardiovascular health risk assessment, automatically providing the intervention comprises automatically triggering a connected audio output device in an environment of the individual to output sounds for reducing stress of the individual.

11. A method for assessing cardiovascular health of an individual, the method comprising:

transmitting light toward a body region of an individual in coordination with receiving a time series of data of the body region of the individual at a camera module of a medical device;

assessing a pressure distribution, and a positional map, of the body region touching the camera module of the medical device for each of a set of frames of the time series of data, based upon image analysis of the time series of data;

performing an active pixel analysis operation with the time series of data, wherein performing the active pixel analysis comprises distinguishing an active pixel set for each of the set of frames of the time series of data;

aggregating the pressure distributions, the positional maps, and the active pixel sets of the set of frames of the time series of data of the body region into a summed time series of data;

extracting a subportion of the summed time series of data satisfying a signal quality threshold condition, upon performing a signal quality filtering operation with outputs of the active pixel analysis;

transforming the subportion of the summed time series of data into a cardiovascular health risk assessment of the individual; and

based upon the cardiovascular health risk assessment, automatically providing an intervention to the individual.

12. The method of claim 11, wherein assessing the pressure distribution comprises processing gradients in image pixel intensity across frames of the time series of data in near-real time.

13. The method of claim 11, wherein performing the active pixel analysis comprises implementing multi-dimensional scaling techniques with principal coordinates analysis techniques to identify pixels of the time series of data characterized by an above threshold signal quality, and omitting a subset of non-active pixels from further processing.

14. The method of claim 11, wherein transforming the subportion of the summed time series of data into the cardiovascular health risk assessment comprises transforming the subportion of the summed time series of data into a set of extracted signal features characterizing waveform components representative of the sequence of full cardiac cycles.

15. The method of claim 14, wherein transforming the subportion of the summed time series of data into the set of extracted signal features comprises performing zero-crossing identification techniques upon first, second, and higher-order derivatives of signals from the summed timed series of data.

16. The method of claim 11, further comprising, from the summed time series of data, detecting changes in pressure and position of the body region against the camera module of the medical device in near real time, upon performing a change point detection operation and assessing signal quality of the summed time series of data based upon the change point detection operation.

17. The method of claim 16, wherein transforming the subportion of the summed time series of data into the cardiovascular health risk assessment comprises extracting the subportion of the summed time series of data satisfying a signal quality threshold condition, upon performing a signal quality filtering operation with outputs of the active pixel analysis and the change point detection operation.

18. The method of claim 11, further including:

in cooperation with receiving the time series of data, directing the individual to vary a configuration of the medical device according to a set of orientations, processing subportions of the time series of data at each of the set of orientations with a signal quality assessment, and directing the user, with a display of the medical device, to maintain the orientation of the set of orientations that provides a high degree of signal quality according to the signal quality assessment.

19. The method of claim 11, further including:

detecting a temperature of the body region touching the camera module, generating a comparison between the temperature and a low temperature threshold, and promoting an increase in the temperature with localized heating of a heating element in communication with the medical device.

20. The method of claim 11, wherein, in response to the cardiovascular health risk assessment, automatically providing the intervention comprises automatically triggering a connected light output device in an environment of the individual to output light effects for modulating stress of the individual.