IP Library › Granted Patent US 12,745,974
Granted Patent B2
US 12,745,974 · App. 18/735,337 · Granted Sep 29, 2026

Medical decision support system

Inventors: Brian J. Booth (Munster, CA); Marina Vernalis (Silver Spring, MD); Bahareh Taji (Ottawa, CA); Fatma Usta (Nepean, CA); David Gloag (Kanata, CA); Sergey A. Telenkov (Ottawa, CA); Robin F. Castelino (Kanata, CA)
Assignee: AUSCULSCIENCES, INC.
A61B7/04A61B5/0245A61B5/7246A61B5/725A61B5/7257A61B5/7264A61B5/7267G16H50/20G16H50/30
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,745,974
App. No.
18/735,337
Granted
Sep 29, 2026
Kind
B2
Abstract

A Support Vector Machine trained responsive to mean and median values of standard and Shannon energy for a plurality of time and frequency intervals within a heart cycles provides for detecting coronary artery disease (CAD). A quality of an auscultatory sound time-series vector is assessed responsive to a vector distance and angle thereof in relation to a median heart cycle vector.

Claims (54)

1 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal, comprising:

a. receiving an electrographic signal from an electrocardiogram (ECG) sensor;

b. receiving at least one auscultatory sound signal responsive to a corresponding at least one auscultatory sound sensor operatively associated with a test-subject;

c. generating a feature set of data responsive to said at least one auscultatory sound signal, wherein said feature set of data provides for input to a support vector machine (SVM) that is pretrained to detect the cardiac condition, wherein the operation of generating said feature set of data comprises:

i. for each frequency interval of a plurality of frequency intervals:

a) bandpass filtering said at least one auscultatory sound signal so as to generate a corresponding time series of bandpass-filtered data;

b) segmenting said corresponding time series of bandpass-filtered data responsive to said electrographic signal so as to associate a plurality of heart-cycle time series with said corresponding time series of bandpass-filtered data, wherein each heart-cycle time series of said plurality of heart-cycle time series spans a single corresponding heart cycle;

c) identifying a start of an S 1 heart sound in each of said plurality of heart-cycle time series;

d) temporally aligning each of said plurality of heart-cycle time series with respect to said start of said S 1 heart sound therein;

e) identifying a longest said heart-cycle time series of said plurality of heart-cycle time series corresponding to a slowest heart cycle of a plurality of heart cycles that correspond to said plurality of heart-cycle time series;

f) for each relatively-shorter said heart-cycle time series of said plurality of heart-cycle time series that is shorter in duration than said longest said heart-cycle time series, temporally scaling and temporally interpolating said each relatively-shorter said heart-cycle time series so as to generate a corresponding temporally-scaled heart-cycle time series that is temporally synchronized with, and of the same length, as said longest said heart-cycle time series;

g) determining an average heart-cycle time series for said frequency interval, wherein each sample of said average heart-cycle time series is responsive to an average of corresponding samples of a) each said heart-cycle time series of said plurality of heart-cycle time series having said same length as said longest said heart-cycle time series and b) each said corresponding temporally-scaled heart-cycle time series associated with remaining said heart-cycle time series of said plurality of heart-cycle time series;

h) determining at least one energy time series selected from the group of energy time series consisting of a standard-energy time series determined from said average heart-cycle time series, and a Shannon-energy time series determined from said average heart-cycle time series, wherein each sample of said standard-energy time series is responsive to a sum squares of values of samples of said average heart-cycle time series for a subset of samples of said average heart-cycle time series within an associated time interval within said average heart-cycle time series, and each sample of said Shannon-energy time series is responsive to a sum of products for a subset of said samples of said average heart-cycle time series within an associated time interval within said average heart-cycle time series;

i) locating at least one first time interval within said average heart-cycle time series, wherein a temporal duration of each first time interval of said at least one first time interval is shorter than a temporal duration of said average heart-cycle time series, and each said first time interval is selected from the group of first time intervals consisting of an S 1 -heart-sound time interval, a systolic time interval, an S 2 -heart-sound time interval, a pre-S 3 -heart-sound time interval, an S 3 -heart-sound time interval, a diastasis time interval, and an S 4 -heart-sound time interval; and

j) determining a plurality of features of said feature set of data, wherein each feature of said plurality of features is selected from the group of energy measures consisting of a plurality of integrals of said standard-energy time series over a corresponding plurality of second time intervals, a plurality of mean values of said standard-energy time series over said corresponding plurality of second time intervals, a plurality of median values of said standard-energy time series over said corresponding plurality of second time intervals, a plurality of integrals of said Shannon-energy time series over said corresponding plurality of second time intervals, a plurality of mean values of said Shannon-energy time series over said corresponding plurality of second time intervals, and a plurality of median values of said Shannon-energy time series over said corresponding plurality of second time intervals, wherein each second time interval of said corresponding plurality of second time intervals is selected from the group of second time intervals consisting of the entirety of said at least one energy time series and said at least one first time interval; and

d. using said support vector machine (SVM) to generate an estimate of whether or not said test-subject exhibits said cardiac condition responsive to said feature set of data.

2 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 1 , wherein at least one said frequency interval of said plurality of frequency intervals is selected from the group of frequency intervals consisting of within the range of 1 Hz to 10 Hz, within the range of 11 Hz to 30 Hz, within the range of starting at between 3 Hz and 31 Hz and ending at 80 Hz, within the range of 81 Hz to 120 Hz, and within the range of 12 1 Hz to 1,000 Hz.

3 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 1 , wherein a start of each said time window is aligned with a corresponding sample of said at least one energy time series.

4 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 1 , wherein a start of said S 1 -heart-sound time interval is coincident with the beginning of said average heart-cycle time series, and an end of said S 1 -heart-sound time interval is responsive to a root of a quadratic equation model of an S 1 -heart-sound region of said average heart-cycle time series.

5 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 4 , wherein said end of said S 1 -heart-sound time interval is responsive to a second root of said quadratic equation model of said S 1 -heart-sound region of said average heart-cycle time series.

6 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 1 , wherein a start of said S 2 -heart-sound time interval is responsive to a first root of a quadratic equation model of an S 2 -heart-sound region of said average heart-cycle time series, and an end of said S 2 -heart-sound time interval is responsive to a second root of said quadratic equation model of said S 2 -heart-sound region of said average heart-cycle time series.

7 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 1 , wherein a start of said systolic time interval is coincident with the beginning of said average heart-cycle time series, and an end of said systolic time interval is coincident with the beginning of diastole in said average heart-cycle time series.

8 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 7 , wherein said beginning of said diastole in said average heart-cycle time series is responsive to a second root of a quadratic equation model of an S 2 -heart-sound region of said average heart-cycle time series.

9 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 1 , wherein a start of said S 4 -heart-sound time interval is assumed to occur at a point in time relative to the beginning of said average heart-cycle time series that is 80 percent of the duration of said average heart-cycle time series and an end of said S 4 -heart-sound time interval is coincident with the end of said average heart-cycle time series.

10 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 1 , wherein a start of said diastasis time interval is assumed to occur at a temporal offset relative to the beginning of said average heart-cycle time series, wherein said temporal offset is given in milliseconds by 350 plus 0.3 times the quantity (TRR-350), wherein said TRR is the duration of said average heart-cycle time series in milliseconds, and an end of said diastasis time interval is assumed to be coincident with a start of said S 4 -heart-sound time interval.

11 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 10 , wherein said start of said S 4 -heart-sound time interval is assumed to occur at a point in time relative to the beginning of said average heart-cycle time series that is 80 percent of the duration of said average heart-cycle time series.

12 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 1 , wherein a start of said S 3 -heart-sound time interval is assumed to occur at a first temporal offset prior to a start of said diastasis time interval, and an end of said S 3 -heart-sound time interval is assumed to occur at a second temporal offset after said start of said diastasis time interval, wherein said start of said diastasis time interval is assumed to occur at a third temporal offset relative to the beginning of said average heart-cycle time series, wherein said third temporal offset is given in milliseconds by 350 plus 0.3 times the quantity (TRR-350), wherein said TRR is the duration of said average heart-cycle time series in milliseconds.

13 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 12 , wherein said first temporal offset is within the range of 60 to 100 milliseconds, and said second temporal offset is within the range of 0 to 60 milliseconds.

14 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 1 , wherein a start of said pre-S 3 -heart-sound time interval is coincident with the beginning of diastole in said average heart-cycle time series, and an end of said pre-S 3 -heart-sound time interval is coincident with a start of said S 3 -heart-sound time interval.

15 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 14 , wherein said beginning of said diastole in said average heart-cycle time series is responsive to a second root of a quadratic equation model of an S 2 -heart-sound region of said average heart-cycle time series.

16 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 14 , wherein said start of said S 3 -heart-sound time interval is assumed to occur at a first temporal offset prior to a start of said diastasis time interval, said start of said diastasis time interval is assumed to occur at a second temporal offset relative to the beginning of said average heart-cycle time series, said second temporal offset is given in milliseconds by 350 plus 0.3 times the quantity (TRR-350), and said TRR is the duration of said average heart-cycle time series in milliseconds.

17 . A computer-implemented metho of detecting a cardiac condition from an auscultatory sound signal as recited in claim 16 , wherein said first temporal offset is within the range of 60 to 100 milliseconds.

18 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 1 , wherein each product of said sum of products of said Shannon-energy time series comprises a square of a value of a sample of said subset of samples of said average heart-cycle time series multiplied by a logarithm of said square of said value.

19 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 1 , further comprising:

a. repeating steps a-c of claim 1 for each training-test-subject of a plurality of training-test-subjects so as to generate a composite feature set of data, wherein said composite feature set of data comprises a composite of said feature set of data from said each training-test-subject of said plurality of training-test-subjects, a first non-null subset of said plurality of training-test-subjects is known a priori to exhibit said cardiac condition, and a remaining subset of said plurality of training-test-subjects is known a priori to not exhibit said cardiac condition;

b. for each said each training-test-subject of said plurality of training-test-subjects, including in said composite feature set of data an indication of whether or not said each training-test-subject exhibits said cardiac condition; and

c. training said support vector machine (SVM) with said composite feature set of data from said plurality of training-test-subjects so as to provide for estimating therewith whether or not a test-subject exhibits said cardiac condition responsive to a corresponding feature set of data associated with said test-subject for the same features as had been incorporated for each said each training-test-subject in said composite feature set of data.

20 . A computer-implemented method of detecting a cardiac condition from an auscultatory sound signal as recited in claim 19 , wherein the features incorporated in said feature set of data used in step d of claim 1 are the same features used in step c of claim 19 to train said support vector machine (SVM).

21 . A computer-implemented method of assessing the quality of an auscultatory sound signal for use in detecting a cardiac condition, comprising:

a. receiving an electrographic signal from an electrocardiogram (ECG) sensor;

b. receiving at least one auscultatory sound signal responsive to a corresponding at least one auscultatory sound sensor operatively associated with a test-subject;

c. segmenting said at least one auscultatory sound signal responsive to said electrographic signal so as to associate a plurality of heart-cycle time series with said at least one auscultatory sound signal, wherein each heart-cycle time series of said plurality of heart-cycle time series spans a single corresponding heart-cycle;

d. temporally aligning each of said plurality of heart-cycle time series with respect to a start of said single corresponding heart-cycle thereof;

e. identifying a longest said heart-cycle time series of said plurality of heart-cycle time series corresponding to a slowest heart-cycle of a plurality of heart-cycles that correspond to said plurality of heart-cycle time series;

f. for each relatively-shorter said heart-cycle time series of said plurality of heart-cycle time series that is shorter in duration than said longest said heart-cycle time series, forming a corresponding zero-padded heart-cycle time series from said each relatively-shorter said heart-cycle time series by also padding said each relatively-shorter said heart-cycle time series with a sufficient number of zero-valued samples at the end of said each relatively-shorter said heart-cycle time series so that a length of said corresponding zero-padded heart-cycle time series is the same as a length of said longest said heart-cycle time series;

g. determining a composite heart-cycle time series, wherein each sample of said composite heart-cycle time series is responsive to a composite of corresponding samples of a) each heart-cycle time series of said plurality of heart-cycle time series having the same said length as said longest said heart-cycle time series and b) each said corresponding zero-padded heart-cycle time series associated with remaining heart-cycle time series of said plurality of heart-cycle time series; and

h. assessing a quality of said at least one auscultatory sound signal responsive to said composite heart-cycle time series, wherein the operation of assessing said quality of said at least one auscultatory sound signal is responsive to a value of at least one scaler selected from the group of scalers consisting of a difference-vector magnitude and an angular deviation, wherein said difference-vector magnitude is responsive to a vector distance between a first vector responsive to said composite heart-cycle time series and a second vector responsive to one of said plurality of heart-cycle time series, wherein said second vector is responsive to a time series selected from the group of time series consisting of one of said longest said heart-cycle time series and one of said corresponding zero-padded heart-cycle time series, and said angular deviation is responsive to a vector angle between said first and second vectors.

22 . A computer-implemented method of assessing the quality of an auscultatory sound signal for use in detecting a cardiac condition as recited in claim 21 , wherein said composite heart-cycle time series comprises a median heart-cycle time series, and each sample of said median heart-cycle time series is responsive to a median of values of corresponding samples of a) each said heart-cycle time series of said plurality of heart-cycle time series having the same said length as said longest said heart-cycle time series and b) each said corresponding zero-padded heart-cycle time series associated with said remaining heart-cycle time series of said plurality of heart-cycle time series.

23 . A computer-implemented method of assessing the quality of an auscultatory sound signal for use in detecting a cardiac condition as recited in claim 21 , wherein a cosine of said vector angle is responsive to a dot product of said first and second vectors divided by a product of magnitudes of said first and second vectors.

24 . A computer-implemented method of assessing the quality of an auscultatory sound signal for use in detecting a cardiac condition as recited in claim 21 , further comprising for each said heart-cycle time series of said plurality of heart-cycle time series, causing a corresponding heart-cycle corresponding to said each said heart-cycle time series to be ignored in subsequent calculations if a corresponding said difference-vector magnitude is in excess of a corresponding difference-vector-magnitude threshold.

25 . A computer-implemented method of assessing the quality of an auscultatory sound signal for use in detecting a cardiac condition as recited in claim 21 , further comprising for each said heart-cycle time series of said plurality of heart-cycle time series, causing a corresponding heart-cycle corresponding to said each said heart-cycle time series to be ignored in subsequent calculations if a corresponding said angular deviation is in excess of a corresponding angular-deviation threshold.

26 . A computer-implemented method of assessing the quality of an auscultatory sound signal for use in detecting a cardiac condition as recited in claim 21 , further comprising assessing said quality of said at least one auscultatory sound signal responsive to a heart-cycle-duration deviation of at least one said heart-cycle time series of said plurality of heart-cycle time series.

27 . A computer-implemented method of assessing the quality of an auscultatory sound signal for use in detecting a cardiac condition as recited in claim 26 , wherein said heart-cycle-duration deviation is responsive to a temporal deviation selected from the group of temporal deviations consisting of a first temporal deviation relative to said longest said heart-cycle time series, a second temporal deviation relative to a length of any of said plurality of heart-cycle time series, a third temporal deviation relative to a mean length of said plurality of heart-cycle time series, and a fourth temporal deviation relative to a composite length of said plurality of heart-cycle time series.

28 . A computer-implemented method of assessing the quality of an auscultatory sound signal for use in detecting a cardiac condition as recited in claim 26 , further comprising for each said heart-cycle time series of said plurality of heart-cycle time series, causing a corresponding heart-cycle corresponding to said at least one said heart-cycle time series to be ignored in subsequent calculations if a corresponding said heart-cycle-duration deviation is in excess of a corresponding heart-cycle-duration-deviation threshold.

Assignments (2)
CORRECTIVE ASSIGNMENT TO CORRECT THE THE FILING YEAR OF PCT/US2021/044854 ON ASSIGNMENT TO BE 2021 PREVIOUSLY RECORDED AT REEL: 67951 FRAME: 868. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Jul 22, 2024
From: VERNALIS, MARINA; BOOTH, BRIAN J.; USTA, FATMA; TAJI, BAHAREH; GLOAG, DAVID; TELENKOV, SERGEY A.; CASTELINO, ROBIN F.
To: AUSCULSCIENCES, INC.
Reel/Frame 069164/0903 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 10, 2024
From: VERNALIS, MARINA; BOOTH, BRIAN J.; USTA, FATMA; TAJI, BAHAREH; GLOAG, DAVID; TELENKOV, SERGEY A.; CASTELINO, ROBIN F.
To: AUSCULSCIENCES, INC.
Reel/Frame 067951/0868 →
Continuity (13)
Continuation 17509018 · Oct 24, 2021
Continuation PCTUS2021044854 · Aug 5, 2021
Continuation In Part PCTUS2020029970 · Apr 24, 2020
Continuation In Part 16854894 · Apr 21, 2020
Continuation In Part PCTUS2018056956 · Oct 22, 2018
Provisional Application 63062424 · Aug 6, 2020
Provisional Application 63061770 · Aug 5, 2020
Provisional Application 62838270 · Apr 24, 2019
Provisional Application 62838296 · Apr 24, 2019
Provisional Application 62575390 · Oct 21, 2017
Provisional Application 62575399 · Oct 21, 2017
Provisional Application 62575397 · Oct 21, 2017
Related Publication 20240366178A1 · Nov 7, 2024
References Cited (160)
US 4378022A · Suobank · 1983 [cited by applicant]
US 4548204A · Groch et al. · 1985 [cited by applicant]
US 4594731A · Lewkowicz · 1986 [cited by applicant]
US 4628939A · Little · 1986 [cited by applicant]
US 4905706A · Duff et al. · 1990 [cited by applicant]
US 5109863A · Semmlow et al. · 1992 [cited by applicant]
US 5117833A · Albert · 1992 [cited by applicant]
US 5289824A · Mills et al. · 1994 [cited by applicant]
US 6048319A · Hudgins et al. · 2000 [cited by applicant]
US 6050950A · Mohler · 2000 [cited by applicant]
US 6053872A · Mohler · 2000 [cited by applicant]
US 6572560B1 · Watrous et al. · 2003 [cited by applicant]
US 6629937B2 · Watrous · 2003 [cited by applicant]
US 7096060B2 · Arand et al. · 2006 [cited by applicant]
US 7115102B2 · Abbruscato · 2006 [cited by applicant]
US 7190994B2 · Mohler et al. · 2007 [cited by applicant]
US 7462153B2 · Bostian et al. · 2008 [cited by applicant]
US 7527597B2 · Sandler et al. · 2009 [cited by applicant]
US 7753856B2 · Dziubinski · 2010 [cited by applicant]
US 7909772B2 · Popev et al. · 2011 [cited by applicant]
US 8419651B2 · Owsley et al. · 2013 [cited by applicant]
US 8449471B2 · Tran · 2013 [cited by applicant]
US 8475396B2 · Jones et al. · 2013 [cited by applicant]
US 8684943B2 · Schmidt et al. · 2014 [cited by applicant]
US 8690789B2 · Watrous · 2014 [cited by applicant]
US 8715206B2 · Telfort et al. · 2014 [cited by applicant]
US 8755535B2 · Telfort et al. · 2014 [cited by applicant]
US 8771204B2 · Telfort et al. · 2014 [cited by applicant]
US 8821415B2 · Al-Ali et al. · 2014 [cited by applicant]
US 8827919B2 · Siejko et al. · 2014 [cited by applicant]
US 8870791B2 · Sabatino · 2014 [cited by applicant]
US 8870792B2 · Al-Ali et al. · 2014 [cited by applicant]
US 8920343B2 · Sabatino · 2014 [cited by applicant]
US 8968195B2 · Tran · 2015 [cited by applicant]
US 9050007B1 · Brockway et al. · 2015 [cited by applicant]
US 9125564B2 · Schmidt et al. · 2015 [cited by applicant]
US 9125574B2 · Zia et al. · 2015 [cited by applicant]
US 9198634B2 · Pretorius et al. · 2015 [cited by applicant]
US 9215980B2 · Tran et al. · 2015 [cited by applicant]
US 9226726B1 · Semmlow · 2016 [cited by applicant]
US 9237870B2 · Mittal · 2016 [cited by applicant]
US 9364193B2 · Patangay et al. · 2016 [cited by applicant]
US 9386961B2 · Al-Ali et al. · 2016 [cited by applicant]
US 9408549B2 · Brockway et al. · 2016 [cited by applicant]
US 9636029B1 · Narasimhan et al. · 2017 [cited by applicant]
US 9724016B1 · Al-Ali et al. · 2017 [cited by applicant]
US 9801542B2 · Tran et al. · 2017 [cited by applicant]
US 9848800B1 · Lee et al. · 2017 [cited by applicant]
US 9848848B2 · Emmanouilidou et al. · 2017 [cited by applicant]
US 9955887B2 · Hughes et al. · 2018 [cited by applicant]
US 9955939B2 · Sezan et al. · 2018 [cited by applicant]
US 9999359B2 · Thakur et al. · 2018 [cited by applicant]
US 10098559B2 · Hughes et al. · 2018 [cited by applicant]
US 10441181B1 · Telfort et al. · 2019 [cited by applicant]
US 10463340B2 · Telfort et al. · 2019 [cited by applicant]
US 11045144B2 · Zhou et al. · 2021 [cited by applicant]
US 11045163B2 · Laska et al. · 2021 [cited by applicant]
US 11191486B2 · Griffin et al. · 2021 [cited by applicant]
US 11284827B2 · Telenkov · 2022 [cited by examiner]
US 11896380B2 · Telenkov et al. · 2024 [cited by applicant]
US 20040260188A1 · Syed et al. · 2004 [cited by applicant]
US 20040267148A1 · Arand et al. · 2004 [cited by applicant]
US 20060064037A1 · Shalon et al. · 2006 [cited by applicant]
US 20060161064A1 · Watrous et al. · 2006 [cited by applicant]
US 20070055151A1 · Shertukde et al. · 2007 [cited by applicant]
US 20070191725A1 · Nelson · 2007 [cited by applicant]
US 20090043218A1 · Warner et al. · 2009 [cited by applicant]
US 20100087746A1 · Radzievsky et al. · 2010 [cited by applicant]
US 20100145210A1 · Graff et al. · 2010 [cited by applicant]
US 20110066041A1 · Pandia et al. · 2011 [cited by applicant]
US 20110066042A1 · Pandia et al. · 2011 [cited by applicant]
US 20110098583A1 · Pandia et al. · 2011 [cited by applicant]
US 20110125060A1 · Telfort et al. · 2011 [cited by applicant]
US 20110208009A1 · Fu et al. · 2011 [cited by applicant]
US 20120130263A1 · Pretorius et al. · 2012 [cited by applicant]
US 20130109989A1 · Busse et al. · 2013 [cited by applicant]
US 20140276229A1 · Ikeda · 2014 [cited by applicant]
US 20150018702A1 · Galloway et al. · 2015 [cited by applicant]
US 20150038856A1 · Houlton et al. · 2015 [cited by applicant]
US 20150057512A1 · Kapoor · 2015 [cited by applicant]
US 20160120434A1 · Park et al. · 2016 [cited by applicant]
US 20160242665A1 · Galloway · 2016 [cited by applicant]
US 20170079594A1 · Telfort et al. · 2017 [cited by applicant]
US 20180020987A1 · Schmidt et al. · 2018 [cited by applicant]
US 20180317876A1 · Emmanouilidou et al. · 2018 [cited by applicant]
US 20190059748A1 · Kaiser et al. · 2019 [cited by applicant]
US 20190117162A1 · Zhou et al. · 2019 [cited by applicant]
US 20190117165A1 · Zeng et al. · 2019 [cited by applicant]
US 20190117184A1 · Laska et al. · 2019 [cited by applicant]
US 20190175072A1 · Schmidt et al. · 2019 [cited by applicant]
US 20190298269A1 · Atashbar et al. · 2019 [cited by applicant]
US 20200015773A9 · Sabatino · 2020 [cited by applicant]
US 20200046241A1 · Lam et al. · 2020 [cited by applicant]
US 20200245889A1 · Telenkov et al. · 2020 [cited by applicant]
US 20200253509A1 · Al-Ali et al. · 2020 [cited by applicant]
US 20210298684A1 · Zeng et al. · 2021 [cited by applicant]
US 20210298685A1 · Zeng et al. · 2021 [cited by applicant]
US 20220061797A1 · Vernalis · 2022 [cited by examiner]
CA 3025748A1 · 2017 [cited by applicant]
EP 2710959A1 · 2014 [cited by applicant]
IN 202141027484A · 2021 [cited by applicant]
WO 2006078954A1 · 2006 [cited by applicant]
WO 2008036911A2 · 2008 [cited by applicant]
WO 2011015935A1 · 2011 [cited by applicant]
WO 2019079829A1 · 2019 [cited by applicant]
WO 2020219991A1 · 2020 [cited by applicant]
WO 2022032041A1 · 2022 [cited by applicant]
US 8,740,816 B2, 06/2014, Telfort et al. (withdrawn) [cited by applicant]
Weissler et al., “Systolic Time Intervals in Heart Failure in Man,” Circulation, Vo. 37, No. 2, Feb. 1968, pp. 149-159. [cited by applicant]
Miller et al., “Spectral Analysis of Arterial Bruits (Phonoangiography): Experimental Validation,” 61 Circulation (3) pp. 515-520 (Mar. 1980). [cited by applicant]
Luisada et al., “Assessment of Left Ventricular Function by Noninvasive Methods,” 32 Adv. Cardiol, pp. 111-141 (1985). [cited by applicant]
Abe et al., “Measurement of Left Atrial Systolic Time Intervals in Hypertensive patients Using Doppler Echocardiography: Relation to Fourth Heart Sound and Left Ventricular Wall Thickness,” 11 JACC (4) pp. 800-805 (Apr.… [cited by applicant]
Daubechies, Ingrid, “Orthonormal Bases of Compactly Supported Wavelets,” Communications on Pure and Applied Mathematics, vol. XLI, 909-996 (1988). [cited by applicant]
Rangayyan et al., “Phonocardiogram Signal Analysis: A Review,” 15 CRC Critical Reviews in Biomedical Engineering(3) pp. 211-237 (1988). [cited by applicant]
Donnerstein, Richard L., “Continuous Spectral Analysis of Heart Murmurs for Evaluating Stenotic Cardiac Lesions,” 64 American J, Cardiology pp. 625-630 (Sep. 1989). [cited by applicant]
Mallat, Stephane G., A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell., 11(7), 674-693 (1989). [cited by applicant]
Hamilton et al., “Compression of the Ambulatory ECG by Average Beat Subtraction and Residual Differencing,” IEEE Transactions on Biomedical Engineering, vol. 38, No. 3, pp. 253-259 (Mar. 1991). [cited by applicant]
Khadra et al., “The Wavelet Transform and its Applications to Phonocardiogram Signal Analysis,” 16 Med. Inform. (3), pp. 271-277 (1991). [cited by applicant]
Thakor et al., “Applications of Adaptive Filtering to ECG Analysis: Noise Cancellation and Arrhythmia Detection,” 38 IEEE Transaction on Biomedical Engineering (8) pp. 785-794 (Aug. 1991). [cited by applicant]
Glower, et al., “Mechanical Correlates of the Third Heart Sound,” 19 JACC (2) pp. 450-457 (Feb. 1992). [cited by applicant]
Wikerhauser, Mladen Victor, Lectures on Wavelet Packet Algorithms, http://citeseerx.ist.psu.edu, Apr. 1992. [cited by applicant]
MathWorks, “Envelope Detection”, MathWorks Help Center, MATLAB & Simulink, Internet document, 6 pp., downloaded on Apr. 15, 2019, https://www.mathworks.com/help/dsp/ug/envelope-detection.html. [cited by applicant]
Weston, Jason, “Support Vector Machine (and Statistical Learning Theory) Tutorial”, NEC Labs America, Internet Document: http://www.cs.columbia.edu/~kathy/cs4701/documents/jason_svm_tutorial.pdf, downloaded on Apr. 17, … [cited by applicant]
Wikipedia, “Softmax Function”, Internet Document, 7 pp., https://en.wikipedia.org/wiki/Softmax_function, downloaded on Apr. 17, 2019. [cited by applicant]
Wikipedia, “Convolution Neural Network”, Internet Document, 22 pp., https://en.wikipedia.org/wiki/Convolutional_neural_network as of Apr. 22, 2019 per https://web.archive.org/web/20190422083506/https://en.wikipedia.org/… [cited by applicant]
Giordano et al., “A Novel Method for Measuring the Timing of Heart Sound Components through Digital Phonocardiography,” Sensors 2019, 19, 1868; Publication [online]. Apr. 19, 2019 [retrieved Jul. 6, 2020]. Retrieved fro… [cited by applicant]
Tan, Andrew, “Principal Components of Electrocardiograms”, Internet Document, Medium, Nov. 29, 2016, 8 pp., https://medium.com/@andrewtan_36013/principal-components-of-electrocardiograms-14874b3a96b1. [cited by applicant]
Schmidt, Samuel, Detection of Coronary Artery Disease with an Electric Stethoscope, PHD Thesis, Aalborg University, Aalborg, Denmark, 2011, 49 pp. [cited by applicant]
Bogaert et al., Clinical cardiac MRI, Springer Science & Business Media, 2012, p. 517. [cited by applicant]
Bogaert et al., Clinical cardiac MRI, Springer Science & Business Media, 2012, p. 17. [cited by applicant]
Zhu et al., “An R-peak detection method based on peaks of Shannon enegy envelope : Abstract”,Science Direct, Biomedical Signal Processing and Control, vol. 8, Issue 5, Sep. 2013, pp. 466-474, https://doi.org/10.1016/j.b… [cited by applicant]
Mohamed et al., “An Approach for ECG Feature Extraction using Daubechies 4 (DB4) Wavelet”, International Journal of Computer Applications (0975-8887), vol. 96—No. 12, Jun. 2014. [cited by applicant]
Sharma et al., “Study and Design of a Shannon-Energy-Envelope based Phonocardiogram Peak Spacing Analysis for Estimating Arrhythmic Heart-Beat”, International Journal of Scientific and Research Publications, vol. 4, Iss… [cited by applicant]
Jeong-Seon Park et al: “R Peak Detection Method Using Wavelet Transform and Modified Shannon Energy Envelope”, Journal of Healthcare Engineering, vol. 2017, Jul. 5, 2017 (Jul. 5, 2017), pp. 1-14, XP055546974, Brentwood … [cited by applicant]
Ray, Sunil, “Understanding Support Vector Machine (SVM) algorithm from examples (along with code)”, Sep. 13, 2017, 6 pp., from https://www.analyticsvidhya.com/blog/2017/09/understaing-support-vector-machine-example-code… [cited by applicant]
Healio-Learn the Heart, “Heart Sounds Topic Review,” Cardiology Review: Topic Reviews, Downloaded on Oct. 18, 2018, 14 pp., https://www.healio.com/cardiology/learn-the-heart/cardiology-review/topic-reviews/heart-sounds. [cited by applicant]
MathWorks, “Code for Shannon energy envelope?”, MATLAB Answers, MATLAB Central, Internet document, 3 pp., Jan. 17, 2019, https://www.mathworks.com/matlabcentral/answers/440144-code-for-shannon-energy-envelope/. [cited by applicant]
European Patent Office International Search Report and Written Opinion of International Searching Authority in International Application No. PCT/US2018/056956, Feb. 1, 2019, 9 pp. [cited by applicant]
USPTO, International Preliminary Report On Patentability in International Application No. PCT/US2018/056956, Nov. 26, 2019, 86 pp. [cited by applicant]
USPTO, Examiner's search strategy and results, Written Opinion of the ISA, International Search Report, and Transmittal in International Application No. PCT/US2020/029970, Oct. 1, 2020, 23 pp. [cited by applicant]
USPTO, International Search Report and Written Opinion of the ISA and Transmittal thereof, Examiner's search strategy and results in International Application No. in International Application No. PCT/US2021/044854, USPT… [cited by applicant]
Wood et al., “Time-Frequency Transforms: A New Approach to First Heart Sound Frequency Dynamics,” IEEE Transaction on Biomedical Engineering, vol. 39, No. 7, pp. 730-740 (Jul. 1992). [cited by applicant]
Akay et al., “Noninvasive Characterization of the Sound Pattern Caused by Coronary Artery Stenosis Using FTF/FAEST Zero Tracking Filters: Normal/Abnormal Study,” 21 Annals of Biomedical Engineering, pp. 175-182 (1993). [cited by applicant]
Akay et al., “Noninvasive Acoustical Detection of Coronary Artery Disease: A Comparative Study of Signal Processing Methods,” 40 IEEE Transaction on Biomedical Engineering (6) pp. 571-578 (Jun. 1993). [cited by applicant]
Akay et al., “Acoustical Detection of Coronary Occlusions Using Neural Networks,” 15 J. Biomed. Eng pp. 469-473 (1993). [cited by applicant]
Akay et al., “Application of Adaptive FTF/FAEST Zero Tracking Filters to Noninvasive Characterization of the Sound Pattern Caused by Coronary Artery Stenosis Before and After Angioplasty,” 21 Annals of Biomedical Engine… [cited by applicant]
Perini et al., “Body Position Affects the Power Spectrum of Heart Rate Variability During Dynamic Exercise,” 66 Eur. J. Appl. Physiol. , pp. 207-213 (1993). [cited by applicant]
Graps, Amara, “An Introduction to Wavelets,” IEEE Computational Science and Engineering, Summer 1995, vol. 2, No. 2, 1995, pp. 1-18. [cited by applicant]
Saito et al., “Local discriminant bases and their applications,” J. Math. Imaging and Vision, 5, 337-358 (1995). [cited by applicant]
Saito et al., “On Local Feature Extraction for Signal Classification,” ICIAM, 1995, https://www.math.ucdavis.edu/~saito/publications/saito_iciam95.pdf. [cited by applicant]
Zhou et al, “A Novel Technique for Muscle Onset Detection Using Surface EMG Signals without Removal of ECG Artifacts,” US National Library of Medicine, National Institutes of Health, HHS Public Access, https://www.ncbi.… [cited by applicant]
Richman et al, “Physiological Time-Series Analysis Using Approximate Entropy and Sample Entropy,” Am J Physiol Heart Circ Physiol., 278: H2039-H2049, 2000. [cited by applicant]
Santos et al., “Detection of First and Second Cardiac Sounds Based on Time Frequency Analysis,” 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Oct. 25-28, 2001, Istanbul, T… [cited by applicant]
Erne, Paul, “Beyond auscultation—acoustic cardiography in the diagnosis and assessment of cardiac disease,” Swiss Med. Wkly 2008, 128 (31-32), pp. 439-452. [cited by applicant]
Kessler et al., “Wavelet Notes”, University of Iowa, https://arxiv.org/pdf/nucl-th/0305025.pdf, Feb. 5, 2008. [cited by applicant]
Wasilewski, Filip, “Wavelet Daubechies 4 (db4) Properties,” Pywavelets, Internet Document: http://wavelets.pybytes.com/wavelet/db4/, 2008-2019. [cited by applicant]
Bogaert et al., Clinical cardiac MRI, Springer Science & Business Media, 2009, pp. 10-11. [cited by applicant]
Inovise Medical Inc, “Audicor 200S”, 2009, 2 pp. brochure downloaded from www.audiocore.com on Sep. 14, 2020. [cited by applicant]
Xinpei Wang et al: “Detection of the First and Second Heart Sound Using Heart Sound Energy”, 2009 2nd International Conference on Biomedical Engineering and Informatics : BMEI 2009 ; Tianjin, China, Oct. 17-19, 2009, Ja… [cited by applicant]
Zuber et al., “Acoustic cardiography to improve detection of coronary artery disease with stress testing,” World Journal of Cardiology, vol. 2, Issue 5, May 26, 2010, pp. 118-124. [cited by applicant]