System and method for characterizing an upper airway using speech characteristics

Patent metadata

Field	Value
Publication number	US-10182787-B2
Application number	US-201214352336-A
Country	US
Kind code	B2
Filing date	Oct 11, 2012
Priority date	Oct 20, 2011
Publication date	Jan 22, 2019
Grant date	Jan 22, 2019

Abstract

The present invention relates to systems and methods for characterizing at least one anatomical parameter of an upper airway of a patient by analysing spectral properties of an utterance, comprising: a mechanical coupler comprising means for restricting the jaw position of the patient; means for recording an utterance; and processing means for determining at least one anatomical parameter of the upper airway from the recorded utterance and comparing the recorded utterance to a threshold value. In addition the present invention relates to the use of the above mentioned systems as a diagnostics tool for assessing obstructive sleep apnea.

First claim

The invention claimed is:

1. A system for characterizing at least one anatomical parameter of an upper airway of a patient based on an utterance in the form of a complete unit of speech in spoken language generated by the patient and delivering a respiratory drug to the patient, comprising:
a mechanical coupler structured to fix a position of a jaw and teeth of the patient and cause a mouth of the patient to have a predetermined diameter while the patient is generating the generated utterance and transmit an audible sound signal comprising the generated utterance;
a sound recording unit structured to receive the audible sound signal from the mechanical coupler and generate a recording of the audible sound signal;
a respiratory drug delivery apparatus structured to deliver the respiratory drug through the upper airway of the patient; and
a computing device structured and configured to: (i) receive the recording of the audible sound signal, determine whether the generated utterance is correct as matching a predetermined utterance to be performed based on the recording of the audible sound signal, and responsive to determining that the generated utterance is correct, determine a cross-section of the upper airway of the patient based on the recording of the audible signal by extracting and analyzing spectral properties of the generated utterance from the recording of the audible signal, (ii) detect a point of time when the cross-section is maximal during the generated utterance, and (iii) cause the drug delivery apparatus to generate an aerosol responsive to the point of time being detected.

2. A method for characterizing at least one anatomical parameter of an upper airway of a patient based on an utterance in the form of a complete unit of speech in spoken language generated by the patient, comprising the steps of:
fixing a position of a jaw and teeth of the patient and causing a mouth of the patient to have a predetermined diameter while the patient is generating the generated utterance by inserting a mechanical coupler coupled to a sound recording unit into a mouth of the patient, wherein the mechanical coupler is structured to transmit an audible sound signal comprising the generated utterance;
generating a recording the audible sound signal using the sound recording unit;
receiving the recording of the audible sound signal, and determining whether the generated utterance is correct as matching a predetermined utterance to be performed based on the recording of the audible sound signal;
responsive to determining that the generated utterance is correct, determining said at least one anatomical parameter of the upper airway based on the recording of the audible signal by extracting and analyzing spectral properties of the generated utterance from the recording of the audible signal; and
using the determined at least one anatomical parameter of the upper airway to assess obstructive sleep apnea;
wherein said at least one anatomical parameter is a cross-section of said upper airway and wherein said method further comprises the steps of detecting a point of time when the cross-section is maximal during the generated utterance, and causing an aerosol of a respiratory drug to be generated responsive to the point of time being detected.

3. The method according to claim 2 , further comprising the step of providing real-time feedback.

4. The method according to claim 2 , further comprising detecting a body position of the patient and in response thereto instructing the patient through a user interface to change the patient's body position.

5. The method according to claim 2 , further comprising the step of storing the spectral properties of the recorded utterance in a database.

6. A method for characterizing at least one anatomical parameter of an upper airway of a patient based on an utterance in the form of a complete unit of speech in spoken language generated by the patient, comprising the steps of:
fixing a position of a jaw and teeth of the patient and causing a mouth of the patient to have a predetermined diameter while the patient is generating the generated utterance by inserting a mechanical coupler coupled to a sound recording unit into a mouth of the patient, wherein the mechanical coupler is structured to transmit an audible sound signal comprising the generated utterance;
generating a recording of the audible sound signal using the sound recording unit;
receiving the recording of the audible sound signal, and determining whether the generated utterance is correct as matching a predetermined utterance to be performed based on the recording of the audible sound signal; and
responsive to determining that the generated utterance is correct, determining said at least one anatomical parameter of the upper airway based on the recording of the audible signal by extracting and analyzing spectral properties of the generated utterance from the recording of the audible signal;
wherein said at least one anatomical parameter is a cross-section of said upper airway and wherein said method further comprises the steps of detecting a point of time when the cross-section is maximal during the generated utterance, and causing an aerosol of a respiratory drug to be generated responsive to the point of time being detected.

7. The method according to claim 6 , further comprising the step of delivering the aerosol to the upper airway of the patient.

Assignees

• Koninklijke Philips Nv

Inventors

• De Waele Stijn
• Winter Stefan
• Geerlings Alexander Cornelis

Classifications

• A61B5/486

  Biofeedback (using electroencephalography [EEG] A61B5/375) · CPC title

• A61B7/003 Primary

  Detecting lung or respiration noise · CPC title

• A61B5/4803

  Speech analysis specially adapted for diagnostic purposes · CPC title

• A61B5/4818

  Sleep apnoea · CPC title

• A61B5/7282

  Event detection, e.g. detecting unique waveforms indicative of a medical condition (cough events A61B5/0823; seizures A61B5/4094; sleep apnoea A61B5/4818) · CPC title