US20230293082A1 - Systems and methods for measuring hemodynamic parameters with wearable cardiovascular sensing - Google Patents

Systems and methods for measuring hemodynamic parameters with wearable cardiovascular sensing Download PDF

Info

Publication number
US20230293082A1
US20230293082A1 US18/200,393 US202318200393A US2023293082A1 US 20230293082 A1 US20230293082 A1 US 20230293082A1 US 202318200393 A US202318200393 A US 202318200393A US 2023293082 A1 US2023293082 A1 US 2023293082A1
Authority
US
United States
Prior art keywords
user
scg
sensor
signals
signal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
US18/200,393
Other languages
English (en)
Inventor
Omer T. Inan
Varol Burak Aydemir
James Rehg
Md Mobashir Hasan Shandhi
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Georgia Tech Research Corp
Original Assignee
Georgia Tech Research Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Georgia Tech Research Corp filed Critical Georgia Tech Research Corp
Priority to US18/200,393 priority Critical patent/US20230293082A1/en
Publication of US20230293082A1 publication Critical patent/US20230293082A1/en
Pending legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/021—Measuring pressure in heart or blood vessels
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/021—Measuring pressure in heart or blood vessels
    • A61B5/02108—Measuring pressure in heart or blood vessels from analysis of pulse wave characteristics
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/02416—Detecting, measuring or recording pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1102—Ballistocardiography
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/332—Portable devices specially adapted therefor
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/683—Means for maintaining contact with the body
    • A61B5/6832—Means for maintaining contact with the body using adhesives
    • A61B5/6833—Adhesive patches
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2560/00—Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
    • A61B2560/02—Operational features
    • A61B2560/0223—Operational features of calibration, e.g. protocols for calibrating sensors
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2560/00—Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
    • A61B2560/02—Operational features
    • A61B2560/0242—Operational features adapted to measure environmental factors, e.g. temperature, pollution
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2560/00—Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
    • A61B2560/02—Operational features
    • A61B2560/0242—Operational features adapted to measure environmental factors, e.g. temperature, pollution
    • A61B2560/0247—Operational features adapted to measure environmental factors, e.g. temperature, pollution for compensation or correction of the measured physiological value
    • A61B2560/0252—Operational features adapted to measure environmental factors, e.g. temperature, pollution for compensation or correction of the measured physiological value using ambient temperature
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
    • A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/06—Arrangements of multiple sensors of different types
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/021—Measuring pressure in heart or blood vessels
    • A61B5/0215—Measuring pressure in heart or blood vessels by means inserted into the body
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/026—Measuring blood flow
    • A61B5/029—Measuring or recording blood output from the heart, e.g. minute volume
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1118—Determining activity level
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6846—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be brought in contact with an internal body part, i.e. invasive
    • A61B5/6847—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be brought in contact with an internal body part, i.e. invasive mounted on an invasive device
    • A61B5/6852—Catheters
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • A61B5/7207—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7221—Determining signal validity, reliability or quality
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7246—Details of waveform analysis using correlation, e.g. template matching or determination of similarity
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems

Definitions

  • the present disclosure relates to health systems and methods.
  • the disclosed technology includes a system for assessing heart health of a user.
  • the present invention is an apparatus comprising one or more sensors configured to measure an electrocardiogram (ECG) signal of a user and configured to measure one or more seismocardiogram (SCG) signals of the user, a memory, and a processing system comprising one or more processors operatively coupled to the memory and one or more of the sensors, the processing system configured to receive the ECG signal, receive at least one of the SCG signals, and generate an assessment of heart health of the user by determining one or more hemodynamic parameters based on the ECG signal and the received at least one SCG signal.
  • ECG electrocardiogram
  • SCG seismocardiogram
  • At least one of the hemodynamic parameters can include a filling pressure of the user or a change in the filling pressure of the user.
  • At least one of the hemodynamic parameters can include a pulmonary artery (PA) pressure of the user or a change in the PA pressure of the user.
  • PA pulmonary artery
  • At least one of the hemodynamic parameters can include a pulmonary capillary wedge pressure (PCWP) of the user or a change in PCWP of the user.
  • PCWP pulmonary capillary wedge pressure
  • the processing system can be further configured to, prior to generating the assessment of heart health, determine a baseline value of at least one of the hemodynamic parameters for the user, the processing system being further configured to generate the assessment of heart health based on the baseline value.
  • the apparatus can further comprise a third sensor configured to measure an environmental parameter, the processing system being further configured to determine at least one of the hemodynamic parameters based on the environmental parameter.
  • the apparatus can further comprise a third sensor configured to measure a gyrocardiogram signal of the user.
  • the processing system being further configured to determine at least one of the hemodynamic parameters based on the gyrocardiogram signal.
  • the environmental parameter can include at least one of a temperature, a humidity, or an altitude.
  • the assessment of heart health can include data indicative of an indication of a change in hemodynamics of the user.
  • the third sensor can be configured to measure environmental parameters.
  • the second sensor can be configured to measure a gyrocardiogram signal of the user.
  • the disclosed technology includes a wearable system for assessing heart health of a user.
  • the wearable system for assessing heart health can include a first sensor, a second sensor, and a controller.
  • the first sensor can be configured to measure at least one electrical characteristic of a heart of the user.
  • the second sensor can be configured to measure cardiogenic vibrations of the user.
  • the controller can be configured to perform a calibration step to create a baseline of one or more parameters associated with a heart health of the user.
  • the controller can be configured to generate an assessment of the heart health of the user comprising data indicative of filling characteristics of the heart based, at least in part, on the baseline and measurements from the first sensor and the second sensor.
  • the wearable system for assessing heart health can include a third sensor.
  • the third sensor can be configured to measure environmental parameters.
  • the third sensor can be configured to measure a photoplethysmography signal of the user.
  • the wearable system for assessing heart health can include an output indicative of the heart health of the user.
  • the first signal can be indicative of an ECG signal of the user.
  • the assessment of heart health can include data indicative of an indication of a change in filling pressure of the user.
  • the personalized data can include data from a right heart catherization.
  • the wearable device can be placed proximate the heart.
  • the third signal can be indicative of at least one environmental parameter.
  • FIG. 2 B provides a diagram of steps used for a method of processing data.
  • FIG. 5 provides a graph of windowing experiment results, in accordance with the present disclosure.
  • FIG. 9 B provides a chart of correlation analyses, in accordance with the present disclosure.
  • FIG. 10 A provides a graph of relative weights of algorithm features, in accordance with the present disclosure.
  • FIG. 10 B provides a graph of relative weights of algorithm features, in accordance with the present disclosure.
  • FIG. 13 A provides a receiver operating characteristics (ROC) curve for the best classifier using the downselected feature set on the training set, in accordance with the present disclosure.
  • ROC receiver operating characteristics
  • FIG. 14 A provides three example beats from one decompensated subject along with base feature (srPower) calculations, in accordance with the present disclosure.
  • FIG. 14 B provides three example beats from one compensated subject along with base feature (srPower) calculations, in accordance with the present disclosure.
  • FIG. 15 A provides a plot of power spectral density (PSD) based on an average of each PSD of each individual SCG beat for a decompensated curve from a randomly selected decompensated subject and a compensated curve from a randomly selected compensated subject, in accordance with the present disclosure.
  • PSD power spectral density
  • FIG. 15 C provides a callout of the higher frequency range (200-250 Hz) of FIG. 15 A , in accordance with the present disclosure.
  • FIG. 16 A provides a bar graph showing the number of times a feature is selected using SFS in performing five-fold cross validation, in accordance with the present disclosure.
  • the present disclosure can include a system and method for assessing heart health.
  • FIG. 1 A components of the system for assessing heart health is shown in FIG. 1 A and will be discussed first.
  • signal refers to one or more signals.
  • the wearable device 110 can include one or more sensors.
  • the wearable device 110 can include a first sensor 112 .
  • the wearable device 110 can include a second sensor 114 .
  • the second sensor 114 can be configured to measure cardiogenic vibrations of the user.
  • the second sensor can be configured to measure a seismocardiogram (SCG) signal of the user 130 .
  • SCG seismocardiogram
  • the second sensor 114 can be configured to measure tri-axial SCG signals.
  • tri-axial SCG signals can include the DV, Lat, and/or HtoF axis.
  • the second sensor 114 can be configured to measure a gyrocardiogram signal of the user.
  • the wearable device 110 can include a first side 150 and a second side 160 .
  • the wearable device can have an external structure that includes a first side 150 and second side 160 .
  • the first side 150 and second side 160 can be connectable and separable structures.
  • the first side 150 and second side 160 can be generally round in shape and connectable to create a generally puck-like shape.
  • the wearable device 110 can include electronics 170 for carrying out the various operations of the wearable device 110 .
  • the electronics 170 can be located inside the wearable device 110 between the first side 150 and second side 160 .
  • the first side 150 can be configured to face away from the body of a user 130 (e.g., distal the heart 120 ).
  • the first side 150 can include an alignment marker 152 .
  • the alignment marker 152 can be an arrow for indicating a direction that the wearable device 110 should be oriented when worn by a user (e.g., arrow should face towards head of user 130 ).
  • the second side 160 can be configured to face the body of a user 130 (e.g., proximal the heart 120 ).
  • the second side 160 can include connectors 162 .
  • the connectors 162 can connect to the first sensor 112 .
  • the first sensor 112 can include one or more electrodes that can be stuck on the body of the user 130 and the connectors 162 can connect the second side 160 to the one or more electrodes.
  • the wearable device 110 can be affixed to the user by the one or more electrodes of the first sensor 112 being stuck to the user 130 and the other portions of the wearable device 110 (e.g., second sensor 114 , first side 150 , second side 160 , and electronics 170 ) being connected to the one or more electrodes by the connectors 162 .
  • the connectors 162 can be any connector known in the art, including, but not limited to buttons, snap buttons, press buttons, adhesive, hook and loop, and the like, or any combination thereof.
  • the plug 172 can be a USB connector.
  • the electronics 170 can include a power source.
  • the power source can be a battery for powering the components of the wearable device (e.g., first sensor 112 , second sensor 114 , processor, transceiver).
  • the electronics can include one or more additional sensors (in addition to the first and second sensors 112 , 114 ).
  • the electronics can include a third sensor.
  • the method 1100 can include receiving 1102 data from a first sensor.
  • the data from the first sensor can relate to at least one electrical characteristic of the heart of a user.
  • the first sensor can measure an ECG signal of a user.
  • the method 1100 can include determining 1106 , based on data from the first and second sensors, filling characteristics of the heart.
  • the filling characteristics of the heart can be is based, at least in part one or more axes of a SCG signal (e.g., Lat, HtoF, DV).
  • the filling characteristics can be based, at least in part, on the SCG signal during a diastolic portion of a heartbeat.
  • the method 1200 can include receiving 1204 data from a first sensor.
  • the data from the first sensor can relate to at least one electrical characteristic of the heart of a user.
  • the first sensor can measure an ECG signal of a user.
  • beat segmentation of SCG signal was carried out in the following way: 200 ms before the R-peak and 700 ms after the R-peak was delimited as the start and end of a beat, respectively.
  • SCG beat arrays for each channel of SCG. Note that, in contrast to other prior work that typically performs beat segmentation from the Rpeak (i.e., 0 ms before/after the R-peak) to approximately 700 ms after the R-peak, in this work we deliberately included ventricular diastolic timing since we expected that the features observed during this time may be quite relevant for estimating filling pressures.
  • FIG. 3 illustrates examples of such artifacts in one recording.
  • FIG. 3 provides an illustration of motion artifact rejection on the DV channel of SCG with FIG. 3 A showing the full recording obtained from one representative subject, FIG. 3 B showing a zoomed in visualization of the recording with a segment contaminated by a motion artifact, FIG. 3 C showing an illustration of the most similar consecutive two beats in the recording, and FIG. 3 D showing an illustration of the motion artifact corrupted beats in the full recording, with beats 310 indicating the samples where the magnitude channel exceeds the threshold.
  • Motion Artifact Detection 1 procedure DETECTMOTIONARTIFACT(SCG x , SCG y , SCG z , SCG Mag ) 2: inds ⁇
  • Initialize empty list 3 j ⁇ CompSimBeats(SCG x , SCG y , SCG z ) Find two consecutive beats that are the most similar 4: 0 ⁇ 1.5 times the range of values in the beats indexed by j in the magnitude channel.
  • Compute motion artifact threshold 5 for each beat in SCG Mag do 6: if any sample of the current beat > 0 then 7: add the beat index to the list inds 8: end if 9: end for 10: return inds 11: end procedure 12: procedure COMPSIMBEATS(SCG x , SCG y , SCG z ) 13: maxSim ⁇ 0 14: for each two consecutive beats (i, i+1) in SCG x , SCG y , SCG z do 15: sim X ⁇ Similarity( b i x , b i+ 1 x ) 16: sim Y ⁇ Similarity( b i y , b i+ 1 y ) 17: sim Z ⁇ Similarity( b i z , b i+ 1 z ) 18: if average(simX, simY, simZ) > maxSim then 19: max Sim ⁇ average(simX, simY
  • the time windows in the table were chosen in a way to reflect ventricular diastolic ( ⁇ 200 ms to 0 ms and 300 ms to 600 ms) and systolic ( ⁇ 50 ms to 250 ms) regimes of the cardiac cycle.
  • FIG. 2 provides an of the processing of the wearable patch data.
  • FIG. 2 A provides a block diagram representation of the processing.
  • FIG. 2 B provides a brief mathematical explanation of the steps used for the processing.
  • FIG. 2 C provides visualizations of the processing from a 10s window of data from a representative participant. In the visualizations, only the DV channel of the SCG is shown for ease of visualization; other SCG channels undergo the same processing.
  • SVM support vector machines
  • rbf polynomial and radial basis function
  • the first goal in the experiments was to analyze the capability of SCG features to discriminate HF clinical status.
  • we treated the problem as binary classification where the input was SCG features and the output was whether the patient was in a decompensated or compensated state.
  • LOSOCV leave-one-subject-out cross validation
  • SFFS sequential forward feature selection
  • SFFS helps in addressing the curse of dimensionality, as there were more features extracted (690) than data points (51). Additionally, SFFS is informative in which features are more important in the classification.
  • FIG. 4 provides receiver operation characteristics (ROC) curves for different classifiers trained and tested (using best feature 410 ; using all features 420 ; using three features 430 ; using four features 440 ; using five features 450 ; random chance 460 ).
  • the 420 curve is the ROC curve of the RBF kernel SVM that is used in the SFFS. Based on these results, using smaller number of features improves performance as expected because of curse of dimensionality.
  • FIG. 5 provides performance of the best classifier under different window lengths showing AUC 510 and accuracy 520 . According to these results, Degradation in the performance of the classifier is observed with smaller window length until ten minutes. After ten minutes of recording, performance plateaus.
  • These examples further include a low-cost system that can track changes in hemodynamic congestion has the potential to help millions of people affected by HF.
  • the increased intracardiac filling pressure provides an early and actionable indication of the onset of congestion in HF.
  • Hemodynamic changes precede progression of chronic compensated HF to acute decompensated HF (ADHF) by several week.
  • ADHF acute decompensated HF
  • Recent research also shows that the product of small changes in pulmonary pressure over an extended period of time is closely associated with the transition to ADHF. Accordingly, tracking hemodynamics using an implantable hemodynamic congestion monitoring system and subsequent proactive HF management therapies (e.g., titration of medications, early follow-up clinic visits, etc.) to reduce subclinical congestion have demonstrated efficacy in reducing HF-related rehospitalization.
  • proactive HF management therapies e.g., titration of medications, early follow-up clinic visits, etc.
  • Seismocardiography the local mechanical vibration of the chest wall associated with the movement of the heart and blood within the vasculature, can be used to monitor cardiovascular health.
  • SCG timings can be used to assess changes in cardiac contractility via estimating the pre-ejection period of the heart, with exercise and physiological perturbation.
  • SCG can be used to assess the clinical status of patients with decompensated HF.
  • SCG has exhibited efficacy in tracking instantaneous oxygen uptake during cardiopulmonary exercise tests in patients with HF and uncontrolled daily life activities in healthy individuals. Based on these results in tracking hemodynamics with SCG for both healthy individuals and patients with HF, changes in hemodynamic congestion can be tracked with the simultaneously recorded SCG signal via estimating changes in PAP and PCWP.
  • SCG and ECG signals were recorded from patients with HF using a custom-built wearable patch during RHC, the gold standard of measuring hemodynamic congestion via PAP and PCWP.
  • the PAP and PCWP were modulated by infusing systemic vasodilators, and changes in the mean pressure values were estimated via tracking the changes in simultaneously recorded SCG signals.
  • Various portions of the SCG signals were analyzed to understand the important segments that are providing salient information regarding changes in PAP and PCWP.
  • FIGS. 1 A- 1 C illustrate the experimental setup and placement of different sensors on each patient.
  • FIG. 1 A provides the experimental setup with a wearable patch placed on a subject undergoing RHC procedure, with axes (on the upper-right) showing the axes of the SCG signal.
  • FIG. 1 B provides a top, bottom, and inside view of a wearable patch.
  • FIG. 1 C provides a front (left) and side (right) view of a wearable patch placed on a representative subject.
  • the custom-built wearable patch was placed just below the suprasternal notch, and the cath lab recording system was time-synchronized with the wearable patch.
  • the SCG heartbeats were cropped to a duration of 500 ms before and after the R-peak that roughly represents most of the relevant diastolic and systolic cardiac events of interest (e.g., rapid inflow, atrial systole, isovolumetric contraction, ventricular ejection, etc.).
  • FIG. 7 shows the ensemble-averaged SCGDV heartbeats from the BL and VI states and corresponding PAP and PCWP heartbeats.
  • FIG. 8 provides in FIG. 7 A changes in PAP showing PAPBL 710 and PAPVI 720
  • FIG. 7 B changes in PCWP showing PCWPBL 730 and PCWPVI 740
  • FIG. 7 C changes in SCG in the DV direction (SCGDV) showing SCGBL 750 and SCGVI 760 with the infusion of vasodilator for a representative subject, with arrows showing the changes in the respective signals.
  • Time “0” indicates the location of the corresponding ECG R-peak.
  • FIG. 9 provides correlation analysis of the target variable, in FIG. 9 A ⁇ PAM and in FIG. 9 B ⁇ PCWP, with different DTW distances of corresponding SCG signals for the training-testing set, with the colorbar showing the R 2 values and the dotted line 910 indicating the division between ventricular diastole and systole (i.e., R-peak of corresponding ECG).
  • the DTW is a time-series analysis method to align signals and find similarities between signals.
  • the preprocessing and feature extraction process described above were performed in the same way for both the training-testing and validation dataset. Following the feature extraction process, only the data from the training-testing set were used to develop a regression algorithm using LOSO cross-validation. The model's hyperparameters were tuned in this step to maximize the performance (maximize the coefficients of determination, R 2 , and minimize the RMSE of the developed model on the training-testing set. The resulting trained model was later validated on the independent validation set to showcase the generalizability of the developed models. The details of this step are given in the following section.
  • the features i.e., DTW distances
  • R 2 the coefficients of determination
  • the regression model (with the optimized hyperparameters) was trained on the whole training-testing set (data from 15 subjects) and tested on the separate validation set (data from five subjects). As a result, all the target variables were predicted, from all 20 subjects.
  • FIG. 7 shows the changes in PAP and PCWP signals and the changes in SCG DV with vasodilator infusion for one representative subject. Note that all the signals shown in the figure are synchronized with the corresponding R-peak. The overall mean of the PAP and PCWP signals decreased with vasodilator infusion, whereas the systolic portion of the SCG DV signal shifted later with respect to the ECG R-peak following vasodilator infusion.
  • FIG. 8 shows the correlation analysis between the actual (measured) and the estimated ⁇ PAM and ⁇ PCWP values for both the training-testing and validation set.
  • FIG. 8 provides correlation analysis for ⁇ PAM predicted vs. ⁇ PAM actual on the training-testing set ( FIG. 8 A ) and validation set ( FIG. 8 B ).
  • the correlation results show an RMSE of 3.2 mmHg and an R 2 of 0.8 for the training-testing set and an RMSE of 3 mmHg and an R 2 of 0.77 for the validation set for ⁇ PAM, and an RMSE of 3.6 mmHg and an R 2 of 0.87 for the training-testing set and an RMSE of 6 mmHg and an R 2 of 0.78 for the validation set for ⁇ PCWP.
  • the ECG signal (in the 20-second frame) was amplitude-normalized and the R-peaks of the ECG signal were detected using the Pan Tompkins method.
  • the SCG signals (four axes of SCG) were segmented into individual heartbeats using the R-peaks of the ECG signal. Each heartbeat was cropped to a duration of 500 ms before and after the R-peak.
  • the 500 ms SCG frame before the R peak roughly represents the ventricular diastolic phase
  • the 500 ms SCG frame after the R peak roughly represents the ventricular systolic phase of the cardiac cycle.
  • the duration of 500 ms before and after the R-peak was chosen as most of the relevant diastolic and systolic cardiac events of interests (e.g., rapid inflow, atrial systole, isovolumetric contraction, ventricular ejection, etc.) occur within this time frame, with respect to the corresponding R-peak of ECG.
  • a constant time window was chosen to crop the ECG and SCG signals to have a repeatable and globalized feature extraction process.
  • SCG Outlier Heartbeats Removal Following the heartbeat segmentation of the wearable SCG signals, the outlier heartbeats were removed from the SCG for the two distribution from the two states (baseline, BL and vasodilator-infused, VI) for each axis and each portion (diastolic and systolic) of the SCG signals separately.
  • the dimension of the 500 sample long SCG heartbeats was reduced into three dimensions by using principal component analysis (PCA) and taking the first three principal components (PC).
  • This low-level representation of the SCG heartbeats was used in a Gaussian-mixture model (GMM) to determine the probability that each sample belongs to a particular distribution (BL or VI) for a particular portion and a particular axis of SCG. For a particular distribution, the points with the lowest 20% probability were detected as the outlier for the distribution. The cut-off of 20% was chosen based on the initial analysis, with 10%, 20%, and 30% beats removed as outliers. The number of principal components (e.g., three in this case) to create the GMM for a particular distribution was based on the analysis on the percentage of variance explained by the number of PCs and the overall estimation accuracy.
  • GMM Gaussian-mixture model
  • the changes in the SCG during the late diastole (atrial systole) phase provided the most relevant information related to changes in PCWP, with changes in SCG magnitude signal (SCG Mag ) during the late diastole period (atrial systole) showing the highest R 2 of 0.87 with ⁇ PCWP.
  • SCG Mag SCG magnitude signal
  • ⁇ PCWP is more related to the changes in the late ventricular diastole (i.e., atrial systole) portion of the SCG.
  • FIG. 10 shows the relative weights of the features in the support vector regression with linear kernel for the estimation of ⁇ PAM and ⁇ PCWP in the training-testing set, with the top feature related to both ⁇ PAM and ⁇ PCWP being the change SCG Lat during the IVC period.
  • the top feature related to both ⁇ PAM and ⁇ PCWP being the change SCG Lat during the IVC period.
  • all the top five features for the ⁇ PAM are from the systolic portion of the SCG.
  • ⁇ PCWP three of the top five are from the systolic portion of the SCG, and two are from the diastolic portion of the SCG.
  • FIGS. 10 and 11 show the importance of the diastolic portion of the SCG in estimating ⁇ PCWP.
  • Most of the SCG research works are concentrated on the systolic portion of the signal. These results suggest that the diastolic portion of the SCG signal also has the potential to provide relevant information regarding pulmonary congestion.
  • Example 2 we present a wearable, inexpensive, minimally obtrusive system to remotely monitor HF patients using wearable SCG.
  • the SCG signal captures the vibrations of the chest wall in response to the cardiac ejection of blood and the movement of the heart.
  • the use of SCG signals was investigated to classify the clinical status of HF patients in a resting state. Specifically, in this Example, it is demonstrated the accurate classification of the clinical status of HF patients in a resting state. This classification provides an indication of elevated filling pressures and decreased CI as the clinical status of the patients are determined using PCWP and CI.
  • SVM support vector machines
  • kernels SVM can model non-linear relationships between the input, SCG features, and the output, clinical status.
  • polynomial and rbf kernels were considered to capture possible non-linear relation.
  • five-fold cross validation was performed to compute classification accuracy and AUC on the training set.
  • training and validation data consisted of different subjects, which allow cross-validation performance to be reflective of generalization performance on the unseen new patient data. The results of the experiments are summarized in TABLE IX and FIGS. 13 A-B .
  • ventricular diastolic 1 dias1 from ⁇ 150 ms to 0 ms
  • systolic sys, from 0 ms to 300 ms
  • ventricular diastolic 2 dias2, from 300 ms to 650 ms
  • the descriptive statistics such as standard deviation, provide a fixed feature representation across the different length recordings (which will have different numbers of beats). Since standard deviation is computed on each one of the six base level features, six statistical features were computed from the collection of beats.
  • Frequency Domain Features The third set of features examined are frequency domain features.
  • FIGS. 15 A-C normalized PSD of a randomly selected compensated and decompensated recording are visualized. In these visualizations, it can be seen that frequency characteristics around 200-250 Hz and 0-50 Hz are different for decompensated and compensated recordings. Hence, from an SCG recording, two frequency domain features are extracted: ratio of the signal power between 205-250 Hz; and 5-40 Hz and ratio of the signal power between 0-5 Hz to 5-40 Hz.
  • permutation feature importance analysis is run where each one of the feature's values is shuffled and the resultant decrease in performance is observed. The higher the decrease in the performance by permutation, the more important is the feature.
  • the results of permutation feature importance are shown in FIG. 16 C .
  • the top two features remain the same. Both features are extracted from the lateral axis of the SCG, and the second feature is directly computed from the diastolic portion of the SCG beats.
  • FIGS. 14 A-B and TABLE IX demonstrate that accurate classification of HF patients' clinical status is possible using SCG features.
  • the determination of the clinical status of HF patients for physiological decompensation requires catheterization, which is expensive and invasive. If this wearable device can provide data that facilitates accurate classification of clinical status, it can be used as a pre-screening tool to reduce the number of RHC procedures, which can reduce HF care costs and improve quality of life. The results from this study suggest that such pre-screening with SCG holds promise.
  • HF clinical status is significant as it demonstrates that elevated filling pressures can potentially be detected from patients with HF.
  • Accurate classification of clinical status at home with a wearable device can greatly improve HF care through reduced hospitalizations.
  • Daily or more frequent assessment of the clinical status with the wearable device can allow filling pressure guided therapy similarly to the approach used in prior work with implantable hemodynamic monitors.
  • physicians can better engage with the process with explainable and interpretable results; moreover, existing flow charts and guidelines can be directly leveraged.
  • the finding that the Lat channel of the SCG provides key hemodynamic information is also supported by recent work.
  • the top feature stems from the frequency domain and has not been previously studied: the ratio of higher frequency components (205-250 Hz) to lower frequency components (4-50 Hz) is a discriminatory feature. This could be due to higher filling pressures in the decompensated patients. Higher filling pressures could lead to louder or more rapid valve closures which can reflect as higher frequency components of the acceleration signal captured on the chest. Future work should study the lateral SCG measurements to better understand the physiological origin of these vibrations to provide mechanistic insight into the reasons behind their important contribution to clinical status estimation.
  • the aim of the study was to explore the discriminative features of SCG in differentiating the clinical status (i. e. decompensated and compensated states) of HF patients in a resting state and investigating the correlation between SCG and hemodynamic parameters.
  • Data are collected from a cohort of patients for whom RHC (performed using Mac-Lab Hemodynamic Recording System) was prescribed to determine the clinical status and capture the hemodynamic parameters.
  • the study was administered under a protocol reviewed and approved by the University of California, San Francisco (UCSF) Institutional Review Board and the Georgia Institute of Technology Institutional Review Board. A total of 63 subjects diagnosed with HF were enrolled in the study. Exclusion criteria were patients in cardiogenic shock, or with implanted ventricular assist devices or prior heart transplantation. Demographics of the study population are shown in TABLE VII (training set) and TABLE VIII (validation set). Each subject provided written informed consent before the data collection.
  • SCG x [n] SCG y [n] and SCG z [n] are the Lat, HtoF and DV channels of SCG, respectively.
  • R-peaks in the ECG signal were detected and subsequently beat segmentation in SCG signals was performed.
  • R-peak detection two algorithms were used: Pan-Tompkins, implemented by Physionet; and the Phasor Transform, with a custom implementation. R-peaks that were detected from both algorithms were selected to reduce false positives in R-peak detection. For detection, 12 second windows were used to detect the R-peaks.
  • beat segmentation of SCG signal was carried out in the following way: 150 ms before the R-peak (to include ventricular diastole) and 15 th percentile of RR intervals after the R-peak (to include only the current beat) was delimited as the start and end of a beat, respectively.
  • SCG beat arrays were constructed for each channel of SCG. Note that in contrast to prior works that perform beat segmentation from the R-peak (i.e., 0 ms before/after the R-peak) to approximately 700 ms after the R-peak, in this example, ventricular diastolic timing was deliberately included since it was expected that the SCG features observed during this time may be quite relevant for including information about filling pressures.
  • SCG signals are susceptible to motion artifacts: when a subject moves, SCG vibrations are contaminated by higher amplitude motion artifacts. In the collected dataset, even though patients were instructed to remain as still as possible, motion artifacts were still present in recordings.
  • FIGS. 3 A-D illustrate examples of such artifacts in one recording.
  • One approach can result in a family of templates being extracted from a set of subjects and then used to analyze SCG recordings from subsequent subjects. While this approach attempts to generalize across subjects, it was found to yield unsatisfactory templates in this application. It is hypothesized that the use of healthy subjects in a prior work made it relatively straightforward to extract a generalizable set of templates, while in this case the HF population exhibits significantly greater heterogeneity.
  • the solution is to use a specific set of templates from each recording (i.e., from each patient). Specifically, one template per each channel of SCG for a subject.
  • Standard analyses were used to evaluate the classification quality of clinical status estimation models.
  • the ground truth data is collected from catheter measurements. Specifically, five-fold cross validation was performed on a training set and estimated performance on separate unseen validation set.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Cardiology (AREA)
  • Physiology (AREA)
  • Artificial Intelligence (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Vascular Medicine (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Mathematical Physics (AREA)
  • Fuzzy Systems (AREA)
  • Evolutionary Computation (AREA)
  • Hematology (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
US18/200,393 2020-11-24 2023-05-22 Systems and methods for measuring hemodynamic parameters with wearable cardiovascular sensing Pending US20230293082A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/200,393 US20230293082A1 (en) 2020-11-24 2023-05-22 Systems and methods for measuring hemodynamic parameters with wearable cardiovascular sensing

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US202063117766P 2020-11-24 2020-11-24
PCT/US2021/058429 WO2022115228A1 (fr) 2020-11-24 2021-11-08 Systèmes et procédés de mesure de paramètres hémodynamiques avec détection cardiovasculaire portable
US18/200,393 US20230293082A1 (en) 2020-11-24 2023-05-22 Systems and methods for measuring hemodynamic parameters with wearable cardiovascular sensing

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2021/058429 Continuation WO2022115228A1 (fr) 2020-11-24 2021-11-08 Systèmes et procédés de mesure de paramètres hémodynamiques avec détection cardiovasculaire portable

Publications (1)

Publication Number Publication Date
US20230293082A1 true US20230293082A1 (en) 2023-09-21

Family

ID=81754950

Family Applications (1)

Application Number Title Priority Date Filing Date
US18/200,393 Pending US20230293082A1 (en) 2020-11-24 2023-05-22 Systems and methods for measuring hemodynamic parameters with wearable cardiovascular sensing

Country Status (8)

Country Link
US (1) US20230293082A1 (fr)
EP (1) EP4251032A1 (fr)
JP (1) JP2023552725A (fr)
KR (1) KR20230132445A (fr)
CN (1) CN116744843A (fr)
AU (1) AU2021387667A1 (fr)
CA (1) CA3199919A1 (fr)
WO (1) WO2022115228A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220354432A1 (en) * 2021-05-07 2022-11-10 Cortery AB Cardiac health assessment systems and methods

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117648557A (zh) * 2024-01-30 2024-03-05 山东科技大学 一种基于soh联合降噪的soh预测方法及设备

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180160917A1 (en) * 2015-05-05 2018-06-14 The Johns Hopkins University A device and method for non-invasive left ventricular end diastolic pressure (lvedp) measurement
US11464451B1 (en) * 2020-03-11 2022-10-11 Huxley Medical, Inc. Patch for improved biometric data capture and related processes

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160206292A1 (en) * 2008-08-05 2016-07-21 Guardsman Scientific, Inc. Systems and methods for managing a patient
US8870780B2 (en) * 2008-10-15 2014-10-28 The Board Of Trustees Of The Leland Stanford Junior University Systems and methods for monitoring heart function
CA2834102A1 (fr) * 2011-05-03 2012-11-08 Heart Force Medical Inc. Procede et appareil d'estimation de la contractilite du myocarde au moyen de signaux de vibration precordiaux
FI126008B (en) * 2013-09-13 2016-05-31 Murata Manufacturing Co cardiac monitoring system
US10806374B2 (en) * 2014-08-25 2020-10-20 Georgia Tech Research Corporation Noninvasive systems and methods for monitoring health characteristics
EP3096254A1 (fr) * 2015-05-21 2016-11-23 Universität Zürich Procédé de surveillance et de visualisation de l'état médical d'un patient
WO2017100185A1 (fr) * 2015-12-07 2017-06-15 Medici Technologies, LLC Système de surveillance d'insuffisance cardiaque observationnel
EP3840639A4 (fr) * 2018-08-20 2022-04-06 MacDonald, Dettwiler and Associates Inc. Procédé et appareil pour dériver des informations biométriques à l'aide d'une sismocardiographie à axes multiples
AU2019403560B2 (en) * 2018-12-21 2023-03-16 W. L. Gore & Associates, Inc. Medical treatment system using measurement data from multiple sensors

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180160917A1 (en) * 2015-05-05 2018-06-14 The Johns Hopkins University A device and method for non-invasive left ventricular end diastolic pressure (lvedp) measurement
US11464451B1 (en) * 2020-03-11 2022-10-11 Huxley Medical, Inc. Patch for improved biometric data capture and related processes

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220354432A1 (en) * 2021-05-07 2022-11-10 Cortery AB Cardiac health assessment systems and methods

Also Published As

Publication number Publication date
KR20230132445A (ko) 2023-09-15
EP4251032A1 (fr) 2023-10-04
AU2021387667A1 (en) 2023-06-22
WO2022115228A1 (fr) 2022-06-02
CN116744843A (zh) 2023-09-12
JP2023552725A (ja) 2023-12-19
CA3199919A1 (fr) 2022-06-02

Similar Documents

Publication Publication Date Title
JP6721153B2 (ja) 生体情報分析装置、システム、及び、プログラム
US11445983B2 (en) Non-invasive determination of disease states
Gaurav et al. Cuff-less PPG based continuous blood pressure monitoring—A smartphone based approach
US20230293082A1 (en) Systems and methods for measuring hemodynamic parameters with wearable cardiovascular sensing
Iftikhar et al. Multiclass classifier based cardiovascular condition detection using smartphone mechanocardiography
US8369936B2 (en) Wearable apparatus for measuring heart-related parameters and deriving human status parameters from sensed physiological and contextual parameters
US20120123232A1 (en) Method and apparatus for determining heart rate variability using wavelet transformation
Rathore et al. A survey on heart biometrics
Aydemir et al. Classification of decompensated heart failure from clinical and home ballistocardiography
JP2015536692A (ja) 携帯型心臓健康モニタリング
Shandhi et al. Estimation of changes in intracardiac hemodynamics using wearable seismocardiography and machine learning in patients with heart failure: a feasibility study
EP2375973A2 (fr) Procédé et appareil de détermination de la variabilité de la fréquence cardiaque utilisant la transformation en ondelettes
US20230082362A1 (en) Processes and methods to predict blood pressure
US20220095955A1 (en) Method and system to assess disease using multi-sensor signals
US20230131629A1 (en) System and method for non-invasive assessment of elevated left ventricular end-diastolic pressure (LVEDP)
US20220031220A1 (en) Model-based sensor technology for detection of cardiovascular status
Zhi et al. Wavelet based machine learning techniques for electrocardiogram signal analysis
Sarada Basics and Descriptions of Different Biomedical Signals
Bassiouni et al. Combination of ECG and PPG Signals for Healthcare Applications: A Survey
Khomidov et al. Camera Sequence based Multi Bio Signal Estimation Algorithm for Remote Healthcare Monitoring
Moharir et al. Sensor Data Analytics for Health Care
Shoushan Remote monitoring of vital physiological signals using smartphone during controlled and uncontrolled respiratory conditions
US10398321B2 (en) Thermal patient signal analysis
WO2023026154A1 (fr) Procédés et systèmes de conception de caractéristiques basées sur des ondelettes à partir de signaux biophysiques destinés à être utilisés dans la caractérisation de systèmes physiologiques
CN114271800A (zh) 一种办公环境下的非侵扰式连续血压监测方法及应用

Legal Events

Date Code Title Description
STPP Information on status: patent application and granting procedure in general

Free format text: NON FINAL ACTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER

STPP Information on status: patent application and granting procedure in general

Free format text: FINAL REJECTION MAILED