Method and system for cardiovascular disease assessment and management

• US 10,420,475 B2
• Filed: 06/15/2016
• 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:
  US15/183,285
• Publication Number:
  US 20160360980A1
• Time in Patent Office: 1,196 Days
• CPC Class Codes: A61B 5/0077 Devices for viewing the surface of the body, e.g. camera, magnifying lens
• CPC Class Codes: A61B 5/02108 from analysis of pulse wave characteristics
• CPC Class Codes: A61B 5/02116 of pulse wave amplitude A61B5/02225 takes precedence
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• 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 5/4857 Indicating the phase of biorhythm clocks or watches with indicators for biological cycles G04B19/264
• CPC Class Codes: A61B 5/6898 Portable consumer electronic devices, e.g. music players, telephones, tablet computers
• 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: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 40/67 for remote 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
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

An embodiment of a method for assessing cardiovascular disease in a user with a body region using a mobile computing device including a camera module, includes receiving a time series of image data of a body region of the user, the time series of image data captured during a time period; generating a photoplethysmogram dataset from the time series of image data; generating a processed PPG dataset; determining a cardiovascular parameter value of the user based on the processed PPG dataset; fitting a chronobiological model to (1) the cardiovascular parameter value, and (2) a subsequent cardiovascular parameter value, characterizing a cardiovascular parameter variation over time of the user based on the fitted chronobiological model; and presenting an analysis of the cardiovascular parameter variation to the user at the mobile computing device.

Claims

1. A method for assessing cardiovascular disease in a user with a body region using a mobile computing device comprising a camera module, the method comprising:

receiving a first time series of image data of the body region of the user, the first time series of image data captured during a daytime period, and the first time series of image data captured at the camera module of the mobile computing device;

receiving a second time series of image data of the body region of the user, the second time series of image data captured during a nighttime period, and the second time series of image data captured at the camera module of the mobile computing device;

for each of the first and the second time series of image data;

generating a photoplethysmogram (PPG) dataset from the respective time series of image data;

generating a processed PPG dataset, comprising;

filtering the PPG dataset with a PPG acquisition model generated from historical PPG data, wherein generating the processed PPG dataset is based on the filtered PPG dataset, and wherein the processed PPG dataset is a subset of the PPG dataset;

fitting a cosinor model to the processed PPG dataset; and

determining a blood pressure parameter value of the user based on the fitted cosinor model, the blood pressure parameter value associated with one of the daytime period and the nighttime period;

fitting a chronobiological blood pressure model to (1) the blood pressure parameter value associated with the daytime period and (2) the blood pressure parameter value associated with the nighttime period;

characterizing a diurnal blood pressure variation of the user based on the fitted chronobiological blood pressure model;

generating an analysis of the diurnal blood pressure variation of the user; and

automatically facilitating therapy provision to the user based upon the analysis.

2. The method of claim 1, wherein determining the blood pressure parameter value of the user comprises:

determining an amplitude of a harmonic component of the fitted cosinor model; and

determining the blood pressure parameter value based on the amplitude of the harmonic component.

3. The method of claim 2, wherein determining the blood pressure parameter value of the user comprises:

receiving a calibration PPG dataset corresponding to a time period;

receiving a calibration blood pressure dataset corresponding to the time period; and

determining the blood pressure parameter value based on the calibration PPG dataset, the calibration blood pressure dataset, and the amplitude of the harmonic component.

4. The method of claim 1, wherein generating the processed PPG dataset further comprises generating a moving average dataset in near real-time based on the PPG dataset, wherein the processed PPG dataset is further based on the moving average dataset, and automatically facilitating therapy provision to the user based upon the analysis in near real-time.

5. The method of claim 4, wherein generating the processed PPG dataset further comprises:

filtering the PPG dataset with a bandpass filter;

deriving a first derivative dataset from the bandpass filtered PPG dataset;

generating a positive component squared dataset from the first derivative dataset; and

generating a comparison of the moving average dataset across the positive component squared dataset, wherein generating the processed PPG dataset is based on the comparison.

6. The method of claim 4, wherein generating the processed PPG dataset further comprises:

identifying heartbeat regions of interests based on the comparison of the moving average dataset across the positive component squared dataset; and

filtering the heartbeat regions of interest based on at least one of;

length of region, amplitude of positive component, and time since previous beat, wherein generating the processed PPG dataset is based on the filtered heartbeat regions of interest.

7. The method of claim 1, wherein filtering the PPG dataset with the PPG acquisition model comprises:

classifying historical PPG signals as compromised historical PPG signals or valid historical PPG signals;

generating the PPG acquisition model based on the classified historical PPG signals; and

filtering the PPG dataset using the PPG acquisition model, based on feature similarity of the PPG signals with the compromised historical PPG signals and the valid historical PPG signals, wherein generating the processed PPG dataset is based on the filtered PPG dataset.

8. The method of claim 1, wherein determining the blood pressure parameter value of the user comprises determining the blood pressure parameter value without using electrocardiogram (ECG) signals, and wherein characterizing the diurnal blood pressure variation of the user comprises characterizing the diurnal blood pressure variation without using ECG signals.