Classifications

• • G—PHYSICS
  • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
  • G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
  • G16Z99/00—Subject matter not provided for in other main groups of this subclass
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B7/00—Instruments for auscultation
  • A61B7/003—Detecting lung or respiration noise
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/08—Measuring devices for evaluating the respiratory organs
  • A61B5/0826—Detecting or evaluating apnoea events
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
  • A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
  • A61B5/1075—Measuring physical dimensions, e.g. size of the entire body or parts thereof for measuring dimensions by non-invasive methods, e.g. for determining thickness of tissue layer
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/48—Other medical applications
  • A61B5/4803—Speech analysis specially adapted for diagnostic purposes
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/48—Other medical applications
  • A61B5/4806—Sleep evaluation
  • A61B5/4818—Sleep apnoea
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/48—Other medical applications
  • A61B5/4836—Diagnosis combined with treatment in closed-loop systems or methods
  • A61B5/4839—Diagnosis combined with treatment in closed-loop systems or methods combined with drug delivery
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/70—Means for positioning the patient in relation to the detecting, measuring or recording means
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
  • A61B5/7271—Specific aspects of physiological measurement analysis
  • A61B5/7282—Event detection, e.g. detecting unique waveforms indicative of a medical condition
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/74—Details of notification to user or communication with user or patient; User input means
  • A61B5/7475—User input or interface means, e.g. keyboard, pointing device, joystick
  • A61B5/749—Voice-controlled interfaces
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B7/00—Instruments for auscultation
  • A61B7/02—Stethoscopes
  • A61B7/04—Electric stethoscopes
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
  • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
  • A61B2562/0204—Acoustic sensors
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/48—Other medical applications
  • A61B5/486—Biofeedback
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
  • A61B5/7235—Details of waveform analysis
  • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
  • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
  • A61M15/00—Inhalators
• • G—PHYSICS
  • G10—MUSICAL INSTRUMENTS; ACOUSTICS
  • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
  • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
  • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
  • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
  • G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
• • G—PHYSICS
  • G10—MUSICAL INSTRUMENTS; ACOUSTICS
  • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
  • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
  • G10L25/75—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 for modelling vocal tract parameters

Definitions

• the present invention relates to a system and method for characterizing an upper airway using speech characteristics.
• OSA Obstructive Sleep Apnoea
• apnoea a disease whereby the upper airway is obstructed many times per night to such an extent that the patient is unable to breathe (apnoea) or has a reduced breathing capacity (hyponea).
• Diagnosis of OSA can be done in a sleep lab by monitoring a patient during an overnight measurement. If the total of number of apnoea' s and hyponeas exceeds a certain limit, the OSA diagnosis is assigned.
• an acoustic pharyngometer can be used to actively extract geometric parameters of the upper airway by sending an acoustic signal into the throat and processing the reflections of the latter.
• test/retest validity and the accuracy of an acoustic pharyngometry measurement performed by devices known in the art is not that high.
• CA2585824 discloses a method for screening OSA, namely to derive flow information from breathing sounds in the ear, and combine them with the level of snoring. However, the method disclosed in CA '824 can only be used to detect apnoea as they happen.
• a first aspect of the invention relates to systems for characterizing at least one anatomical parameter of an upper airway of a patient by analyzing spectral properties of an utterance, the system comprising:
• a mechanical coupler comprising means for restricting the jaw position of the patient
• 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.
• the characterization can be performed autonomously.
• the system and method according to the present invention functions independently: once the operation is started, it continues until the operation is terminated, without manual intervention, but possibly under the control of a controller.
• the system according to embodiments of the present invention can autonomously check whether that a user has preformed the required utterance.
• the processing means provides real-time feedback.
• the system further comprises means for speech recognition for controlling correctness of the recorded utterance.
• system further comprises means for delivering at least one respiratory drug through the upper airway of the patient.
• the at least one anatomical parameter is the cross-section of the upper airway and wherein the system further comprises means for determining at least one point of time when the cross-section is maximal during an utterance. In yet another embodiment the system further comprises means for delivering at least one respiratory drug through said upper airway of the patient at said at least one point of time when said cross-section of the upper airway is maximal. In one embodiment of the present invention the respiratory drug delivering means comprises a timing mechanism.
• a second aspect of the invention relates to the use of the above mentioned systems as a diagnostics tool for assessing obstructive sleep apnea.
• a further aspect of the invention relates to methods for assessing at least one anatomical parameter of an upper airway of a patient by analyzing spectral properties of an utterance, comprising the steps of:
• the method further comprises the step of providing real-time feedback.
• the method further comprises the step of adapting the patient's body position.
• the method further comprises the step of storing the spectral properties of the recorded utterance in a database.
• the threshold value is determined by means of speech recognition.
• the invention according to embodiments of the invention further includes a method wherein the at least one anatomical parameter is the cross-section of said upper airway and wherein said method further comprises the step of determine at least one point of time when the cross-section is maximal when executing an utterance.
• Embodiments of the invention include a method further comprising the step of delivering at least one respiratory drug in the upper airway of the patient.
• the teachings of the present invention permit the design of improved methods and systems for guiding a user in performing accurate and reliable measurements for characterizing an upper airway.
• Fig. la is a schematic representation of the approximated articulatory model of the vocal tract.
• Fig lb is a schematic illustration of the approximated articulatory model using a concatenation of four lossless cylindrical acoustic tubes.
• Fig. 2 is a schematic representation of the system according to an embodiment of the present invention.
• Fig. 3 illustrates a representative output of an acoustic pharyngometry measurement.
• Fig. 4a and Fig. 4b illustrate a real time estimation of upper airway tract based on uttered sounds using a system according to an embodiment of the present invention.
• first, second, third and the like in the description and in the claims are used for distinguishing between similar elements and not necessarily for describing a sequence, either temporally, spatially, in ranking or in any other manner. It is to be understood that the terms so used are interchangeable under appropriate circumstances and that the embodiments of the invention described herein are capable of operation in other sequences than described or illustrated herein. Moreover, the terms top, bottom, over, under and the like in the description and the claims are used for descriptive purposes and not necessarily for describing relative positions. It is to be understood that the terms so used are interchangeable under appropriate circumstances and that the embodiments of the invention described herein are capable of operation in other orientations than described or illustrated herein.
• an element described herein of an apparatus embodiment is an example of a means for carrying out the function performed by the element for the purpose of carrying out the invention.
• utterance used herein relates to a complete unit of speech in spoken language. It is generally but not always bounded by silence. It can be represented and delineated in written language in many ways. It is obvious that utterances do not exist in written language, only their representations do.
• real-time relates to hardware or software systems that are subject to a "real-time constraint", for instance operational deadlines from event to system response.
• real-time programs preferably execute within strict constraints on response time.
• a non-real-time system is one for which there is no deadline, even if fast response or high performance is desired or preferred.
• the need of real-time software is often addressed in the context of real-time operating systems, and synchronous programming languages, which provide frameworks on which to build real-time application software.
• Real-time computations can be said to have failed if they are not completed before their deadline, whereby their deadline is relative to an event. A real-time deadline must be met, regardless of the system load.
• articulator or "speech organ” relates to organs which can produce the many sounds or utterances needed for language. Organs used include the lips, teeth, tongue, alveolar ridge, hard palate, velum (soft palate), uvula and glottis. Speech organs or articulators can be of two types: passive articulators and active articulators. Passive articulators remain static during the articulation of sound, such as upper lips, teeth, alveolar ridge, hard palate, soft palate, uvula, and pharynx wall, whereas active articulators move relative to these passive articulators to produce various speech sounds, in different manners. The most important active articulators are the tongue, the lower lip and glottis.
• Aerodynamic energy refers to the airflow through the vocal tract. Its potential form is air pressure; its kinetic form is the actual dynamic airflow. The acoustic energy is variation in the air pressure that can be represented as sound waves.
• Air cavities are containers of air molecules of specific volumes and masses. The main air cavities present in the articulatory system are the supraglottal cavity and the subglottal cavity. They are so- named because the glottis, the openable space between the vocal folds internal to the larynx, separates the two cavities.
• the supraglottal cavity or the orinasal cavity is divided into an oral subcavity (the cavity from the glottis to the lips excluding the nasal cavity) and a nasal subcavity (the cavity from the velopharyngeal port, which can be closed by raising the velum to the nostrils).
• the subglottal cavity consists of the trachea and the lungs.
• the atmosphere external to the articulatory stem may also be consisted an air cavity whose potential connecting points with respect to the body are the nostrils and the lips.
• the pitch must be set independently from the vowel quality and if the same vowel can be spoken on different voice qualities, the voice quality must be set independently from the vowel quality.
• the vowel quality seems to depend mostly on tongue position: front-back and open-close, but vowel quality can also be affected by the position of other articulators, the jaw, lips and velum.
• Fig. la An elementary segment (1, 2, 3, 4, 5, 6, 7, 8, 9 or 10 in Fig. la) of the upper airway is represented by a cylindrical tube of a specific length and cross-section area.
• lb shows a schematic illustration of the approximated articulatory model using a concatenation of four lossless cylindrical acoustic tubes, each of length li and cross-section area A.
• the upper airway can be viewed as an acoustic tube of varying cross-sectional area terminated by the vocal cords on one end and by the lip opening at the other.
• Another model which can be used is the source-filter model of sound production in the upper airway.
• This model of sound production assumes a source of sound and a filter that shapes that sound, organised so that the source and the filter are independent. This independence allows one to measure and quantify the source separately from the filter.
• the source of sound is the regular vibration of the vocal folds in the larynx and the filter is the whole vocal tract tube between the larynx and the lips.
• the source-filter model can also be applied to fricative sounds, whereby the source of sound is the turbulence generated by passing air through a constriction, and the filter is the vocal tract tube anterior to the constriction.
• articulators that contribute to the spectral shaping of an utterance can be described and visualized in real-time for instance by applying a method disclosed by D. Hill et al in Proceedings of AVIOS '95, the 14th Annual International Voice Technologies Applications Conference of the American Voice I/O Society, San Jose September 11 -14 1995, AVIOS: San Jose, pp. 27-44.
• the articulators which influence the cross-section of an airway are determined. More specifically, the geometry of an upper airway is preferably determined using the above mentioned models.
• the present invention can also be applied using natural inhaled/exhaled breathing noise and not only utterance, for instance during sleep or prior to drug inhalation.
• the invention according to an embodiment relates to a system 10 for characterizing at least one anatomical parameter of an upper airway of a patient, for instance a throat or a vocal tract, by analysing spectral properties of an utterance
• the invention provides in one embodiment a system for characterizing at least one anatomical parameter of an upper airway of a patient by analysing spectral properties of an utterance, the system comprising:
• a mechanical coupler 1 comprising a mouthpiece 1 1 which restricts the jaw position and which can be anatomically fitted according to the utterance the patient is supposed to perform;
• a sound recording unit 2 for recording an utterance, for instance a microphone or the mechanical coupler used as a free-floating microphone; and a computing device preferably comprising a non-transitory memory adapted to determine at least one anatomical parameter of the upper airway from the recorded utterance and comparing the recorded utterance to a threshold value.
• the system according to an embodiment of the invention is illustrated in Fig. 2.
• the system comprises a mechanical coupler 1 which is used to transmit a generated audible sound signal, for instance a vocal utterance or a non-vocal utterance, like for instance natural inhaled/exhaled breathing noise, from the to be examined cavity into the system 10.
• a generated audible sound signal for instance a vocal utterance or a non-vocal utterance, like for instance natural inhaled/exhaled breathing noise
• both vocal and non- vocal utterances can be generated, however vocal utterances may provide less information on the lower airway system as compared to non- vocal utterances.
• the mechanical coupler 1 enables the restriction of the jaw position.
• the latter is in one embodiment of the invention enabled by using different mouthpieces 11 which can be anatomically fitted according to the utterance the patient is supposed to perform.
• the mouthpiece 11 can ensure, for example, that the teeth and jaws are in a certain position and that the opening of
• the mouthpiece 11 can restrict the position of the tongue as well.
• the opening of the mouth has a very specific diameter leading that the variability in the utterances is reduced and thus enhancing the precision of the measurement.
• the mechanical coupler 1 can further comprise a probe 12.
• the mechanical coupler 1 and ,in one embodiment of the invention, the probe 12 can comprise means for recording an utterance, for instance by using a sound recording unit 2 for recording the utterances.
• the mechanical coupler 1 and the probe 12 can have a tubular shape but different shapes can be applied as well.
• the sound recording unit 2 is integrated with the tube formed by the coupler 1 and the probe 12. This can be enabled for instance by integrating a snoring microphone in an OptiVent Inline Spacer both developed by Philips Respironics. The setup illustrated in Fig.
• the sound recording unit 2 is in one embodiment of the invention connected to a processing means 5.
• the processing means 5 can determine the anatomical parameters of the upper airway from the recorded utterances or inhaled/exhaled breathing noise and compare the determined anatomical parameters to a threshold value.
• the processing means 5 can provide feedback in real-time as a result of processing the obtained data in real-time.
• the processing means 5 can be a computing device comprising in one embodiment of the invention a non-transitory memory. More specifically a personal computer, a laptop, a tablet computer, a smart phone, a mobile phone, a watch or any electronic visual displays which can comprise a touchscreen can be used. In another embodiment of the present invention the processing means 5 can be executed by a single operation for instance with respect to a predetermined button, and hence can be executed by an exceedingly simple operation. All processing means 5 which are known to a person skilled in the art can be used, as well as any software which could enable the characterization of the necessary anatomical parameters can also applied.
• the system according to embodiments of the present invention can further comprise means to instruct and control a patient's body position.
• the upper airway geometry at different body positions e.g. lying down and standing
• the means to instruct and control a patient's body position can for instance be enabled by adding a 3D accelerometer to the system as illustrated in Fig. 2, which gives the orientation of the system and can be used to instruct and control the patient via the user interface (e.g. the patient could be asked to first do a measurement in standing and then in lying position).
• the processing means 5 can also be connected to a database 4 (locally or remotely) and for instance a loudspeaker, a display or both 6 which can be used as means to provide the feedback to a user.
• the display comprises an interface to instruct and provide feedback to the test subject, whereby the usability of the interface is very easy to use by the test subject.
• the user interface comprises at least one screen, whereby one screen can be a main screen whereas another screen can be used to select a particular parameter, for instance a compression.
• many of the functionality's that are important for a good result which can be done autonomously by the device are done by the system itself. An example of this is the determination of the frame rate which is done by determining the number of images in the sequence and the length of the speech fragment and calculating the frame rate using these numbers.
• the database 4 in one embodiment of the invention contains a predefined sequence of utterances that a user can perform.
• the database 4 can contain a set of sequences, from which an operator can choose.
• the processing means 5 can for instance be integrated or installed on a mobile device, for instance a mobile phone.
• a screen or speaker of the mobile phone can be used as means to provide feedback to a user and accordingly an integrated microphone which is standard on a mobile phone can be used as a sound recording unit.
• the mechanical coupler 1 can be a cover that one can attach to the cell phone whereby said cover comprises a tube in front of the microphone.
• the tube can be used as means to fix the mount of a user in a predefined way in relation to the integrated microphone.
• the invention can provide real-time feedback for optimal administration and delivery of respiratory drugs.
• Knowledge of the upper airway anatomy can improve the proportion of the administered drugs that have to be delivered to a desired location.
• Drug delivery systems known in the art are not efficient since only about 25% of the administered drug is delivered where it should be, by obtaining real-time feedback on the upper airways one can model the flow of the particles through these upper airways.
• Knowledge of the upper airway anatomy can improve the proportion of the administered drug that should be delivered to the desired location.
• respiratory drug delivery the problem is getting the drug "beyond the throat". Once beyond the throat there are various systemic routes for the drug to reach the targeted alveoli. More drugs delivered "beyond the throat" means a shorter treatment time which is a real differentiator.
• the means for delivering at least one respiratory drug through the airway of a patient can for instance be an aerosol device, the I-neb AAD system by Philips Respironics which is a fast aerosol generating system can be used.
• an aerosol device the I-neb AAD system by Philips Respironics which is a fast aerosol generating system can be used.
• the exact dose of the respiratory drugs can be calculated and visualized by applying a flow modelling and based on this the particle delivery is modelled for instance by applying CFD tools like for instance Star CD and Star CCM+ manufactured by CD-adapco. More specifically the particle delivery and the timing of the aerosol generation can be optimized and in this way the drug delivery can be personalized but restricted by the medication prescription.
• the cross- section of the upper airway is determined by the processing means 5 and in addition a point in time when the cross-section is maximal during an utterance can be determined. This point of time when the cross-section of the upper airway is maximal, can be used for the timing of the aerosol generation, which then can be optimized for drug delivery, thus providing a system tuning approach.
• a mechanical coupler restricting the jaw position for instance by applying a stepped-mouthpiece (K. Nikander et al in "Manipulation of upper airway volume using a stepped mouthpiece" ERS, September 2010) can be used as a way to force the upper airways to open up. Feedback to the patient on the way his/hers upper airway is opened up is beneficial to this goal. In addition it may support adherence and compliance.
• Advantageously embodiments of the present invention enable the amount of drug delivery to be more controllable, consistent and repeatable over the various therapy sessions.
• a method can comprise one of the following steps: the system tells the patient which utterance to perform, which the system records.
• a processing means 5 performs can check on the correctness of the recorded utterance, for example by means of speech recognition to determine whether the correct utterance has been performed.
• speech recognition models known in the art can be used to enable the latter, for instance by applying a vector Taylor series approach for environment-independent recognition, or by using a parallel model combination (PMC) scheme, or hidden Markov models. If the utterance was not correct, the system can ask the patient to repeat it. In a next step the system can repeat the previous steps until all predefined utterances have been performed correctly by the patient.
• the processing means can then extract and analyse the features important for OSA diagnosis.
• An example of a method which can be used is disclosed by Robb et al in Vocal tract resonance characteristics of adults with obstructive sleep apnoea in Acta Otolaryngology, 1997. 117(5): p. 760-3.
• the following steps can be applied: spectral properties of the utterances can be analysed, resulting in a determination of the anatomical parameters of the upper airway, for instance dimensions of the throat between the vocal chords and the mouth.
• the derived dimensions can be used as an indicator for OSA.
• the dimensions can be linked to other measurements for which the predictive power has already been established, for instance measurement data of an acoustic pharyngometry measurement as illustrated in Fig. 3.
• Figure 3 taken from Jung et al. shows the representative output of an acoustic pharyngometry measurement, having the parameter area on the Y-axis and the parameter distance on the X-axis.
• the values can also be linked to the presence of OSA in a trial that is run specifically for derivation of a detector based on speech features.
• Another method to derive the cross-sectional dimensions from the lips to the glottis is by applying a speech- coding by for instance Linear Predictive Coding (LPC).
• LPC Linear Predictive Coding
• This method can also be used for obtaining a real-time estimate of the instantaneous throat geometry for optimizing respiratory drug delivery in terms of more efficient deposition and shorter treatment times as illustrated in Fig. 4a and 4b.
• Embodiments of the present invention provide feedback to the patient while he/she holds its throat open by uttering sounds, e.g. exhaling. In a subsequent inhale, while keeping the throat fixated, the drug delivery can take place. Direct feedback can improve adherence and compliance.
• the determined values can be compared to predefined thresholds or used by a more sophisticated classifier to give a probability that the patient is suffering from OSA as illustrated in Figs. 4a and 4b.
• the result can be given to an operator.
• An example of a classifier is for instance the naive Bayesian classifier known in the art.
• the classifier can also include physiological measures such as BMI and neck circumference to increase screening performance.
• the present invention can additional be applied for OSA phenotyping.
• the throat dimensions obtained from the processing means can help to identify different types of OSA, providing an indication for the most successful treatment (CPAP, surgery).
• An alternative embodiment of the present invention is a system comprising a training mode.
• the training mode can be applied to two groups of patients, one group diagnosed with OSA and another group diagnosed non-OSA. When the two groups are examined, reference data can be obtained which can then be used in future measurements.
• the processor then autonomously can train the implemented classifier to be used for future tests.
• the system is not only used for a one-time measurement but used in repeating check-ups.
• a patient's results can be stored in a database (locally or remotely, not necessarily identical with the previously mentioned database).
• the next time the patient receives a check-up the system can be used to record another measurement. This can then be compared to the previous results of this patient. This decreases the importance of absolute numbers obtained during a one-time measurement and enables the observation and evaluation of a trend.
• the system can be equipped with a state-of-the-art speaker-recognition module. It autonomously can assign new measurements to previous measurements by identifying the speaker based on the performed utterances.

Landscapes

• Health & Medical Sciences (AREA)
• Life Sciences & Earth Sciences (AREA)
• Engineering & Computer Science (AREA)
• Veterinary Medicine (AREA)
• Surgery (AREA)
• Physics & Mathematics (AREA)
• Biomedical Technology (AREA)
• Heart & Thoracic Surgery (AREA)
• Medical Informatics (AREA)
• Molecular Biology (AREA)
• Public Health (AREA)
• Animal Behavior & Ethology (AREA)
• General Health & Medical Sciences (AREA)
• Biophysics (AREA)
• Pathology (AREA)
• Physiology (AREA)
• Pulmonology (AREA)
• Acoustics & Sound (AREA)
• Bioinformatics & Cheminformatics (AREA)
• Pharmacology & Pharmacy (AREA)
• Medicinal Chemistry (AREA)
• Chemical & Material Sciences (AREA)
• Dentistry (AREA)
• Oral & Maxillofacial Surgery (AREA)
• Audiology, Speech & Language Pathology (AREA)
• Artificial Intelligence (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Psychiatry (AREA)
• Signal Processing (AREA)
• Biodiversity & Conservation Biology (AREA)
• Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Priority Applications (9)

Applications Claiming Priority (2)

Related Child Applications (2)

Publications (1)

Family

ID=47324215

Family Applications (1)

Country Status (9)

Cited By (7)

Families Citing this family (10)

Citations (6)

Family Cites Families (18)

• 2012
  • 2012-10-11 BR BR112014009233A patent/BR112014009233A8/pt not_active Application Discontinuation
  • 2012-10-11 MX MX2014004534A patent/MX352472B/es active IP Right Grant
  • 2012-10-11 JP JP2014536371A patent/JP2014532448A/ja active Pending
  • 2012-10-11 RU RU2014120177A patent/RU2623129C2/ru active
  • 2012-10-11 EP EP12798375.7A patent/EP2744408B1/en active Active
  • 2012-10-11 CN CN201280051551.XA patent/CN103889324B/zh active Active
  • 2012-10-11 WO PCT/IB2012/055501 patent/WO2013057637A1/en not_active Ceased
  • 2012-10-11 US US14/352,336 patent/US10182787B2/en active Active
  • 2012-10-11 IN IN2660CHN2014 patent/IN2014CN02660A/en unknown

Patent Citations (6)

Non-Patent Citations (4)

Also Published As

Similar Documents

Legal Events