Search

EP-4734839-A1 - METHOD AND APPARATUS FOR SENSOR TIGHTNESS DETECTION

EP4734839A1EP 4734839 A1EP4734839 A1EP 4734839A1EP-4734839-A1

Abstract

A system determines tightness of a wearable device (100). The system may include at least one processor configured to receive a photoplethysmography (PPG) signal from a wearable device. The at least one processor may determine a tightness measure from the PPG signal, such as from a segment of the PPG signal. The at least one processor may determine the tightness of the wearable device based on the tightness measure.

Inventors

  • MASSIE, Frederik Roger Anne
  • VITS, Steven Elsa Louis
  • SHOULDICE, REDMOND

Assignees

  • ResMed Sensor Technologies Limited

Dates

Publication Date
20260506
Application Date
20240628

Claims (20)

  1. 1. A system for determining tightness of a wearable device, comprising: at least one processor configured to: receive a photoplethysmography (PPG) signal from a wearable device; and determine a tightness measure from the PPG signal, the tightness measure indicating the tightness of the wearable device.
  2. 2. The system of claim 1, wherein the tightness measure is determined from a detected segment of the PPG signal.
  3. 3. The system of claim 2 wherein the detected segment comprises any of a detected peak and/or a detected trough.
  4. 4. The system of any one of claims 2 to 3, wherein the tightness measure is associated with an area formed between a computed curve and the detected segment of the PPG signal.
  5. 5. The system of claim 4, wherein the computed curve intersects the detected segment at two end points of the detected segment.
  6. 6. The system of any one of claims 4 to 5, wherein the tightness measure is determined based on: a first parameter associated with a distance measure between the computed curve and the detected segment; and a second parameter indicating presence of a concave characteristic in the detected segment.
  7. 7. The system of claim 6, wherein the at least one processor is configured to: determine the first parameter and the second parameter for each detected segment of the PPG signal, determine a moving median of the determined first and second parameters; and determine the tightness measure based on the moving median.
  8. 8. The system of any one of claims 6 to 7, wherein the at least one processor is configured to determine the first parameter by: calculating a plurality of distances between a plurality of sample points on the computed curve and corresponding sample points on the detected segment; and determining the first parameter by calculating an average of 50% of smallest distances of the plurality of distances.
  9. 9. The system of any one of claims 6 to 8, wherein the at least one processor is configured to determine the second parameter by: calculating a plurality of second derivatives for a plurality of sample points on a curve between a trough and a peak in the detected segment, the trough preceding the peak; and determining the second parameter by determining a percentage of the calculated plurality of second derivatives that have a negative value.
  10. 10. The system of any one of claims 1 to 9, wherein the at least one processor is configured to determine validity of the PPG signal based on the tightness measure.
  11. 11. The system of claim 10, wherein the at least one processor is configured to determine the validity of the PPG signal based on the tightness measure and low perfusion detection.
  12. 12. The system of any one of claims 1 to 11, wherein the at least one processor is configured to: compare the tightness measure to a threshold; and determine that the PPG signal is valid when the tightness measure is less than or equal to the threshold.
  13. 13. The system of any one of claims 1 to 12, wherein the at least one processor is configured to: identify a period of time in the PPG signal during which the tightness measure exceeds a threshold; and derive a peripheral arterial tonometry signal from the PPG signal, outside of the identified period of time, to detect an occurrence of a sleep-related event.
  14. 14. The system of any one of claims 1 to 13, wherein the at least one processor is configured to: determine whether the PPG signal is valid by comparing the tightness measure to a first threshold; and after determining that the PPG signal is valid, determine whether to exclude any period of time from the PPG signal for deriving a peripheral arterial tonometry signal to detect an occurrence of a sleep-related event by comparing the tightness measure corresponding to the period of time to a second threshold, wherein the second threshold is lower than the first threshold.
  15. 15. The system of claim 14, wherein the at least one processor is configured to determine that the PPG signal is valid when the tightness measure is less than or equal to the first threshold.
  16. 16. The system of any one of claims 14 to 15, wherein the at least one processor is configured to exclude the period of time from the PPG signal for deriving the peripheral arterial tonometry signal when the tightness measure exceeds the second threshold.
  17. 17. The system of any one of claims 1 to 16, wherein the detected segment is a segment of the PPG signal between two adjacent troughs.
  18. 18. The system of any one of claims 1 to 17, wherein the PPG signal is measured at a finger.
  19. 19. The system of any one of claims 1 to 18, wherein the wearable device includes a PPG sensor configured to generate the PPG signal.
  20. 20. The system of claim 19, wherein the PPG sensor includes an infrared sensor and/or a red- light sensor.

Description

METHOD AND APPARATUS FOR SENSOR TIGHTNESS DETECTION 1 CROSS REFERENCE TO RELATED APPLICATIONS [0001] This application claims the benefit of United States Provisional Patent Application No. 63/511,309, filed 30 June 2023, the entire content of which is incorporated herein by reference. 2 BACKGROUND OF THE TECHNOLOGY 2.1 FIELD OF THE TECHNOLOGY [0002] The present technology relates to determining tightness of fit of a wearable device worn by a user or a tight application of the wearable device to the user. In particular, the present technology relates to detecting inappropriate tightness of the wearable device based on signal measurement such as with respect to light measurement of photoplethysmography (PPG) sensors. 2.2 DESCRIPTION OF THE RELATED ART [0003] Wearable devices, such as such as smartwatches, activity trackers and finger probes, can help assess physiological parameters and/or conditions of users. For instance, wearable PPG devices can monitor pulse rate (PR), oxygen saturation (SpO2), peripheral arterial tone, blood pressure and/or blood vessel stiffness, and may be implemented for detection of sleep related events of the users. [0004] It is important for the user to wear the PPG device with a suitable fit that is not too tight and not too loose, as the contact pressure between the PPG device and the user may negatively affect PPG signal quality. Excessive contact pressure, as in the case of overtightness, may block bloodstream and lower perfusion of peripheral arteries, causing artery stiffness and venous blood pooling. As a result, excessive contact pressure may distort PPG waveforms, lower AC signal amplitudes in the PPG waveforms, and reduce the signal to noise ratio, which, in turn, may reduce measurement accuracy (such as of SpCh measurements), and may, for example, delay screening or diagnoses. [0005] On the other hand, insufficient contact pressure, as in the case of over-looseness, may result in an inadequate contact. The distance or angle between the PPG device and the user’s skin may scatter light, which, in turn, may reduce signal accuracy. The further away the PPG device from the user’s skin, the more signal noise may be introduced into the measurements. [0006] Both reflective and transmissive PPG devices may be affected by the contact pressure. For instance, in the case of the reflective PPG device, the contact pressure may affect the PPG waveform morphology. In the case of the transmissive PPG device, excessive contact pressure may alter the measured blood samples because of severe blood flow restriction. [0007] The optimum contact pressure varies markedly among individuals due to differences in skin elasticity and blood-vessel compliance. Despite numerous attempts, no generally accepted standards for clinical or fundamental PPG measurements to account or mitigate for unsuitable contact pressure have been adopted. [0008] In view of the foregoing, there is a need to develop a solution that automates detection of fit or tightness of the wearable device, and which may be used to timely inform the user of when and/or how to adjust the fit or tightness of the sensing device. Further, to improve the overall accuracy of the physiological condition evaluation, there is a need to identify, filter and/or eliminate PPG signals that are affected by inappropriate tightness of the wearable device. 3 BRIEF SUMMARY OF THE TECHNOLOGY [0009] The present technology is directed towards systems and methods for determining tightness of a wearable device, such as determining inappropriate fit or tightness of the wearable device. [0010] A first aspect of the present technology relates to a system for determining tightness of a wearable device. [0011] A second aspect of the present technology relates to a method for determining tightness of a wearable device. [0012] Some implementations of the present technology may include a system for determining tightness of a wearable device. The system, may include at least one processor. The at least one processor may be configured to receive a photoplethysmography (PPG) signal from a wearable device. The at least one processor may be configured to determine a tightness measure from the PPG signal, the tightness measure indicating the tightness of the wearable device. [0013] In some implementations, the tightness measure may be determined from a detected segment of the PPG signal. The detected segment may include any of a detected peak and/or a detected trough. The tightness measure may be associated with an area formed between a computed curve and the detected segment of the PPG signal. The computed curve may intersect the detected segment at two end points of the detected segment. The tightness measure may be determined based on a first parameter associated with a distance measure between the computed curve and the detected segment. The tightness measure may be determined based on a second parameter indicating presence of a concave characteristic in the detecte