Method and system for physiological parameter derivation from pulsating signals with reduced error

Patent metadata

Field	Value
Publication number	US-10172528-B2
Application number	US-201715467789-A
Country	US
Kind code	B2
Filing date	Mar 23, 2017
Priority date	May 31, 2016
Publication date	Jan 8, 2019
Grant date	Jan 8, 2019

Abstract

This disclosure relates generally to biomedical signal processing, and more particularly to method and system for physiological parameter derivation from pulsating signals with reduced error. In this method, pulsating signals are extracted, spurious perturbations in the extracted pulsating signals are removed for smoothening, local minima points in the smoothened pulsating signal are derived, systolic maxima point between two derived local minima are derived, most probable pulse duration and most probable peak-to-peak distance are derived, dicrotic minima is removed while ensuring that every dicrotic minima is preceded by a systolic maxima point and followed by a beat start point of said systolic maxima, diastolic peak is derived while ensuring that every dicrotic maxima is preceded by a diastolic notch followed by next beat start point of that maxima, and physiological parameters are derived from the derived local minima points, systolic maxima points, dicrotic notch and diastolic peak.

First claim

What is claimed is:

1. A processor-implemented method for deriving a plurality of physiological parameters from pulsating signals for monitoring cardiac health of a patient, said method comprising:
extracting, via one or more hardware processors, pulsating signals from the patient using a signal extraction module;
removing, via one or more hardware processors, spurious perturbations in the extracted pulsating signals using two different time window lengths for smoothening of said extracted pulsating signals, by using a smoothening module;
deriving, via one or more hardware processors, local minima points in the smoothened pulsating signals based on the discrete nature of said pulsating signals and strictly rising and falling edge of said pulsating signals and union of minima points derived from the smoothened pulsating signals with two different sizes using a minima derivation module;
deriving, via one or more hardware processors, systolic maxima point between two derived local minima based on the discrete nature of said pulsating signals, strictly rising and falling edge of said pulsating signals and union of maxima points derived from the smoothened pulsating signals with two different sizes using a maxima derivation module;
deriving, via one or more hardware processors, most probable pulse duration and most probable peak-to-peak distance using the derived local minima points and the derived systolic maxima points and based on the univariate nature of said pulsating signals by using a statistical learning module;
deriving, via one or more hardware processors, dicrotic minima based on the discrete nature of said pulsating signals, strictly rising and falling edge of said pulsating signals and union of the local minima points derived from two different smoothened pulsating signals with two different sizes ensuring that every dicrotic minima is preceded by a systolic maxima point and followed by a beat start point of said systolic maxima by using a dicrotic minima derivation module;
deriving, via one or more hardware processors, diastolic peak based on the discrete nature of said pulsating signals, strictly rising and falling edge of said pulsating signals and union of the systolic maxima points derived from two different smoothened pulsating signals with two different sizes ensuring that every dicrotic maxima is preceded by a diastolic notch and followed by next beat start point of that maxima by using a diastolic peak derivation module; and
deriving, via one or more hardware processors, physiological parameters from the derived local minima points, systolic maxima points, dicrotic notch and diastolic peak using a physiological parameter derivation module.

2. The method as claimed in claim 1 , wherein said pulsating signals are selected from photoplethysmogram (PPG) signals and arterial blood pressure (ABP) signals.

3. The method as claimed in claim 1 , wherein the signal extraction module consists of a mobile communication device or a wearable device.

4. The method as claimed in claim 1 , wherein the smoothening of the extracted pulsating signals is performed by taking union of two moving average windows.

5. The method as claimed in claim 1 , wherein the derivation of local minima points in the smoothened pulsating signals is a time window based process.

6. The method as claimed in claim 1 , wherein the derivation of best fit window is used as 300 milliseconds.

7. The method as claimed in claim 1 , wherein the derivation of systolic maxima between two derived local minima is a time window based process.

8. The method as claimed in claim 1 further consists of marking physiological abnormalities based on the derived physiological parameters.

9. The method as claimed in claim 8 , wherein said marking of physiological abnormalities is performed using a predefined set of rules.

10. The method as claimed in claim 9 , the predefined set of rules is used to classify between abnormalities arising out of physiological parameter disorder and anomaly outliers.

11. The method as claimed in claim 10 , the physiological parameter disorders are repetitive in nature.

12. A system for deriving a plurality of physiological parameters from pulsating signals for monitoring cardiac health of a patient; said system comprising:
a signal extraction module adapted for extracting pulsating signals from the patient;
a smoothening module adapted for removing spurious perturbations in the extracted pulsating signals using two different time window lengths for smoothening of said extracted pulsating signals;
a minima derivation module adapted for deriving local minima points in the smoothened pulsating signals based on the discrete nature of said pulsating signals and strictly rising and falling edge of said pulsating signals and union of minima points derived from the smoothened pulsating signals with two different sizes;
a maxima derivation module adapted for deriving systolic maxima point between two derived local minima based on the discrete nature of said pulsating signals, strictly rising and falling edge of said pulsating signals and union of maxima points derived from the smoothened pulsating signals with two different sizes;
a statistical learning module adapted for deriving most probable pulse duration and most probable peak-to-peak distance using the derived local minima points and the derived systolic maxima points and based on the univariate nature of said pulsating signals;
a dicrotic minima derivation module adapted for deriving dicrotic minima based on the discrete nature of said pulsating signals, strictly rising and falling edge of said pulsating signals and union of the local minima points derived from two different smoothened pulsating signals with two different sizes ensuring that every dicrotic minima is preceded by a systolic maxima point and followed by a beat start point of said systolic maxima;
a diastolic peak derivation module adapted for deriving diastolic peak based on the discrete nature of said pulsating signals, strictly rising and falling edge of said pulsating signals and union of the systolic maxima points derived from two different smoothened pulsating signals with two different sizes ensuring that every dicrotic maxima is preceded by a diastolic notch and followed by next beat start point of that maxima; and
a physiological parameter derivation module adapted for deriving physiological parameters from the derived local minima points, systolic maxima points, dicrotic notch and diastolic peak.

13. A computer program product for deriving a plurality of physiological parameters from pulsating signals for monitoring cardiac health of a patient, comprising:
extracting, via one or more hardware processors, pulsating signals from the patient using a signal extraction module;
removing, via one or more hardware processors, spurious perturbations in the extracted pulsating signals using two different time window lengths for smoothening of said extracted pulsating signals, by using a smoothening module;
deriving, via one or more hardware processors, local minima points in the smoothened pulsating signals based on the discrete nature of said pulsating signals and strictly rising and falling edge of said pulsating signals and union of minima points derived from the smoothened pulsating signals with two different sizes using a minima derivation module;
deriving, via one or more hardware processors, systolic maxima point between two derived local minima based on the discrete nature of said pulsating signals, strictly rising and falling edge of said pulsating signals and union of maxima points derived from the smoothened pulsating signals with two different

Assignees

• Tata Consultancy Services Ltd

Inventors

• Bandyopadhyay Soma
• Ukil Arijit
• Puri Chetanya
• Singh Rituraj
• Pal Arpan
• Murthy C A
• Mandana Kayapanda

Classifications

• A61B5/7203 Primary

  for noise prevention, reduction or removal · CPC title

• A61B5/024 Primary

  Measuring pulse rate or heart rate · CPC title

• A61B5/02108

  from analysis of pulse wave characteristics · CPC title

• A61B5/0245

  by using sensing means generating electric signals, {i.e. ECG signals} · CPC title

• A61B5/02416

  using photoplethysmograph signals, e.g. generated by infrared radiation (A61B5/14552 takes precedence) · CPC title