Method and apparatus for monitoring cardio-pulmonary health

Patent metadata

Field	Value
Publication number	US-2020113484-A1
Application number	US-201916546916-A
Country	US
Kind code	A1
Filing date	Aug 21, 2019
Priority date	May 30, 2012
Publication date	Apr 16, 2020
Grant date	—

Abstract

Disclosed is a cardio-pulmonary health monitoring apparatus. The apparatus comprises a contactless motion sensor configured to generate one or more movement signals representing bodily movement of a patient during a monitoring session; a processor; and a memory storing program instructions configured to cause the processor to carry out a method of processing the one or more movement signals. The method comprises extracting one or more sleep disordered breathing features from the one or more movement signals, and predicting whether a clinical event is likely to occur during a predetermined prediction horizon based on the one or more sleep disordered breathing features.

First claim

1 . A monitoring apparatus comprising:
a contactless motion sensor configured to generate one or more movement signals representing bodily movement of a patient during a monitoring session; a processor; and a memory storing program instructions configured to cause the processor to carry out a method of processing the one or more movement signals, the method comprising:
selecting one or more epochs of the one or more movement signals during which the patient was asleep and not performing gross bodily movements by extracting one or more waveform length values from one or more epochs of the one or more movement signals and identifying one or more epochs in which an extracted waveform length value is less than a threshold;
extracting one or more sleep disordered breathing (SDB) features from the one or more selected epochs of the one or more movement signals; and
predicting whether a clinical event is likely to occur during a predetermined prediction horizon based on the one or more SDB features.

2 . The monitoring apparatus of claim 1 , wherein the one or more waveform length values are extracted by measuring cumulative changes in amplitude of the one or more movement signals.

3 . The monitoring apparatus of claim 2 , wherein the one or more waveform length values are measured as:

w
i

=

∑

n
=
2

N





c
3



(
n
)

-

c
3



(

n
-
1

)



,

where w i is a waveform length value, i is an epoch, c 3 is a movement signal, and N is the number of samples in the epoch i of the movement signal c 3 .

4 . The monitoring apparatus of claim 2 , wherein the threshold is computed from one or more percentiles of the one or more waveform length values.

5 . The monitoring apparatus of claim 2 , wherein the threshold is an adaptive threshold that changes based on one or more percentiles of the one or more waveform length values.

6 . The monitoring apparatus of claim 1 , wherein the method further comprises sending an alert message to an external computing device dependent on the prediction.

7 . The monitoring apparatus of claim 1 , wherein the contactless motion sensor is a radio-frequency motion sensor configured to generate at least two movement signals based on respective transmitted radio-frequency signals that are in quadrature with each other.

8 . The monitoring apparatus of claim 7 , wherein the method comprises combining the two movement signals into a combined movement signal before the extracting.

9 . The monitoring apparatus of claim 7 , wherein the method comprises combining the SDB features extracted from each movement signal before the predicting.

10 . A monitoring apparatus comprising:
a contactless motion sensor configured to generate one or more movement signals representing bodily movement of a patient during a monitoring session; a processor; and a memory storing program instructions configured to cause the processor to carry out a method of processing the one or more movement signals, the method comprising:
selecting one or more sections of the one or more movement signals during which the patient was asleep and not performing gross bodily movements:
detecting one or more sleep disordered breathing (SDB) events in the one or more selected sections;
confirming one or more of the detected SDB events as valid SDB events; and
calculating one or more SDB features from the one or more confirmed SDB events, the one or more calculated SDB features being indicative of the severity of sleep-disordered breathing by the patient during the monitoring session.

11 . The monitoring apparatus of claim 10 , wherein at least one detected SDB event is confirmed as a valid SDB event, in part, by verifying that a respiratory effort envelope associated with the at least one detected SDB event dips below a threshold value for a time greater than a predetermined fraction of a modulation cycle length of the at least one detected SDB event.

12 . The monitoring apparatus of claim 11 , wherein the at least one detected SDB event is confirmed as a valid SDB event, in part, by verifying that one or more adjacent hyperpnea sections have a duration greater than a minimum value.

13 . The monitoring apparatus of claim 10 , wherein at least one detected SDB event is confirmed as a valid SDB event, in part, by computing at least one verification feature for the at least one detected SDB event and applying a rule-based inference engine to the at least one verification feature.

14 . The monitoring apparatus of claim 13 , wherein the at least one verification feature is a kurtosis of a section of a movement signal associated with the at least one detected SDB event.

15 . The monitoring apparatus of claim 13 , wherein the at least one verification feature is a waveform length value that is computed, in part, by measuring cumulative changes in amplitude of a section of a movement signal associated with the at least one detected SDB event.

16 . The monitoring apparatus of claim 13 , wherein the at least one verification feature is a degree of freedom of a section of a movement signal associated with the at least one detected SDB event.

17 . The monitoring apparatus of claim 13 , wherein the at least one verification feature is a mean value of a respiratory effort envelope associated with the at least one detected SDB event.

18 . The monitoring apparatus of claim 13 , wherein the at least one verification feature is an irregularity factor of a section of a movement signal associated with the at least one detected SDB event that is a ratio of a number of upward zero crossings and a number of peaks.

19 . The monitoring apparatus of claim 13 , wherein the at least one verification feature is a number of zero crossings of a section of a movement signal associated with the at least one detected SDB event.

20 . The monitoring apparatus of claim 13 , wherein the at least one verification feature is a phase locking value that is computed, in part, by determining an instantaneous phase difference between two halves of a section of a movement signal associated with the at least one detected SDB event.

21 . The monitoring apparatus of claim 13 , wherein

Assignees

• Resmed Sensor Tech Ltd

Inventors

• Schindhelm Klaus Henry
• Farrugia Steven Paul
• Colefax Michael Waclaw
• Javed Faizan
• Khushaba Rami
• Heneghan Conor
• De Chazal Philip
• Zaffaroni Alberto
• Fox Niall
• Celka Patrick
• O'Hare Emer
• Redmond Stephen James

Classifications

• G08B21/02

  Alarms for ensuring the safety of persons · CPC title

• A61B5/087

  Measuring breath flow · CPC title

• A61B5/0816

  Measuring devices for examining respiratory frequency (measuring frequency of electric signals G01R23/00) · CPC title

• A61B5/1126

  using a particular sensing technique · CPC title

• A61B5/1118

  Determining activity level · CPC title