System for detecting bruxism or other jaw disorders

Abstract

There is provided a system for diagnosing or predicting a risk of developing bruxism or other jaw disorder, comprising: a receiver for receiving audio data and video data of a subject; and a processor configured to identify one of audio data and video data indicative of a subject suffering from bruxism or other jaw disorder, or a risk of the subject developing bruxism or other jaw disorder, and in response thereto analyze the other one of the audio data and the video data to determine whether the subject has bruxism or other jaw disorder. To diagnose a subject suffering from bruxism or other jaw disorders or to predict the risk of the subject developing bruxism or other jaw disorders. Furthermore, there is provided a computer program adapted to implement a method for diagnosing or predicting the risk of developing bruxism or other jaw disorders when the program runs on a processor.

Description

Technical Field

[0001] The present invention relates to a system for detecting or diagnosing whether a subject suffers from bruxism or other jaw disorders, particularly in a non-invasive and user-friendly manner. The present invention also relates to a system for predicting whether a subject has a tendency or risk of developing bruxism or other jaw disorders, particularly in a non-invasive and user-friendly manner. Background Art

[0002] The jaws (maxilla and mandible) are components of the oral cavity. These bones are very important for the normal function of the oral cavity and are also related to the pathological conditions of the oral cavity. Bruxism is a condition in which a subject grinds, clenches, or grits their teeth. Temporomandibular joint disorder is another condition related to the jaws.

[0003] Bruxism can be classified into sleep bruxism and awake bruxism. Sleep bruxism is characterized by rhythmic or non-rhythmic muscle activity of the masticatory organs during sleep. Awake bruxism is characterized by repeated or continuous tooth contact and / or support or pushing / sliding of the mandible. The prevalence of bruxism varies by age group. In the adult population, the prevalence of awake bruxism is estimated to be approximately 22% to 30%, and sleep bruxism is approximately 1% to 15% of the population. It has been reported that in children and adolescents, the prevalence of bruxism is approximately 3% to 49%.

[0004] Bruxism is associated with numerous short-term and long-term adverse health effects. The short-term effects of bruxism include headache, limited mouth opening, facial myalgia (pain in the jaw and facial muscles), earache, and tightness or stiffness in the shoulders. Bruxism also affects sleep in the form of frequent disruptions. It is well known that the tooth grinding or knocking noise caused by bruxism can cause sleep interruption for bed partners. The oral manifestations of bruxism include excessive tooth mobility and gingival inflammation and recession. The long-term effects of bruxism include temporomandibular joint disorder (hereinafter referred to as TMJD, discussed further below), tooth wear, and fractures. TMJD is a group of more than 30 conditions that cause pain and dysfunction in the jaw joints and the muscles that control jaw movement. TMJ disorder also causes clicking or a rubbing sensation when the subject opens their mouth or chews.

[0005] If diagnosed and treated early, many bruxism-related problems can be avoided. For example, it has been observed that awake bruxism can be reduced by using appropriate reminder techniques.

[0006] In a particular example, the present invention relates to awake bruxism, in which a subject clenches their teeth or grinds their teeth without necessarily being aware of it. It is desirable to be able to diagnose such bruxism or predict whether a subject will develop such bruxism, for example, to be able to provide a timely warning to the user to stop grinding or clenching their teeth. More generally, it is desirable to have an effective method for detecting jaw disorders. Summary of the Invention

[0007] The present invention is defined by the claims.

[0008] According to an example of an aspect of the present invention, a system for diagnosing bruxism or other jaw disorders or predicting the risk of developing bruxism or other jaw disorders includes: a receiver configured to receive audio data and video data of a subject; and a processor configured to: identify or analyze one of the audio data and the video data indicative of the subject having bruxism or other jaw disorders or the risk of the subject developing bruxism or other jaw disorders, and in response thereto, analyze the other of the audio data and the video data to diagnose the subject having bruxism or other jaw disorders or predict the risk of the subject developing bruxism or other jaw disorders.

[0009] According to an example of an aspect of the present invention, a system for diagnosing bruxism or other jaw disorders is provided, the system including: a receiver configured to receive audio data and video data of a subject; and a processor configured to: identify or analyze one of the audio data and the video data indicative of the subject having bruxism or other jaw disorders, and in response thereto, analyze the other of the audio data and the video data to diagnose the subject having bruxism or other jaw disorders.

[0010] According to an example of an aspect of the present invention, a system for predicting the risk of developing bruxism or other jaw disorders is provided, the system including: a receiver configured to receive audio data and video data of a subject; and a processor configured to: identify or analyze one of the audio data and the video data indicative of the subject developing bruxism or other jaw disorders, and in response thereto, analyze the other of the audio data and the video data to predict the risk of the subject developing bruxism or other jaw disorders.

[0011] The system is designed to diagnose bruxism or other jaw disorders or predict the risk or trend of developing bruxism or other jaw disorders by analyzing the audio and video data of the subject. Thus, it can be performed remotely, enabling the subject to be analyzed at home. For example, it can be implemented as a component of a video conferencing system.

[0012] The use of audio and video analysis increases the specificity of the diagnosis of bruxism or other jaw disorders or the specificity of the risk of developing bruxism or other jaw disorders, and enables the effective use of resources, such as using processing power only when needed.

[0013] For example, the amount of data to be processed can be greatly reduced because at least some measurements are only performed when the maximum effect can be expected, since an appropriate analysis of one data stream is performed based on what is detected in another data stream (e.g., during yawning and sneezing, maximum mouth opening can occur - suddenly in the case of sneezing - which can be detected in a video stream, and then a cracking sound of the jaw joint can be detected in an audio stream).

[0014] By combining the analysis of video and audio data, more specific diagnoses or predictions can be made. Sound analysis can be used, for example, to detect sneezing, or can be used to perform general sound and speech analysis.

[0015] The processor is configured, for example, to identify or analyze video data indicating that a subject has bruxism or other jaw disorders or is at risk of developing bruxism or other jaw disorders by identifying an extended period of jaw closure when observing the movement of the user's lips; and in response, analyze audio data to determine whether the subject is speaking.

[0016] Just by observing the video, it is not clear whether the closed jaw is related to jaw clenching, or is simply the result of someone not speaking or actually speaking with the jaw closed but not clenched. Therefore, the additional specific audio analysis provides an additional solution for the diagnostic process or predicting the risk of developing bruxism or other jaw disorders.

[0017] The processor can then be configured (if speech is detected) to analyze the spectrum of the audio data to detect speech features characteristic of bruxism.

[0018] In another example, the processor can be configured to analyze or identify video data to detect yawning as an indication that a subject has bruxism or other jaw disorders or is at risk of developing bruxism or other jaw disorders; and in response, analyze audio data to detect cracking or clicking sounds.

[0019] These sound indications of TMJD itself can be caused by bruxism and are thus an example of another jaw disorder.

[0020] The processor can be configured to identify or analyze audio data indicating that a subject has bruxism or other jaw disorders or is at risk of developing bruxism or other jaw disorders by detecting the speech sound characteristics of speech with a fixed jaw position; and in response, analyze video data to determine whether the subject is speaking with the mouth closed.

[0021] For example, a closed mouth is identified when the upper and lower teeth are in contact with each other. As discussed below, a clenched mouth will additionally have jaw or cheek muscle contractions.

[0022] If the subject speaks with their mouth closed, the user has a higher probability of suffering from bruxism. In particular, during a bruxism episode, the subject will speak while clenching their jaw. The absence of jaw opening will be identified in the video data to confirm the audio analysis.

[0023] The processor can be configured to analyze video data to diagnose that the subject suffers from bruxism or other jaw disorders or predict the risk that the subject will develop bruxism or other jaw disorders by identifying repetitive lateral grinding movements of the jaw.

[0024] The processor can be configured to analyze video data to detect jaw clenching by monitoring facial skin and / or muscle movements and / or ear movements at the position of the joint of the jaw, thereby diagnosing that the subject suffers from bruxism or other jaw disorders or predicting the risk that the subject will develop bruxism or other jaw disorders.

[0025] Due to clenching, there can be pulsations of the cheek muscles (and even sometimes pulsations of the skin on the temples). For example, a fast Fourier transform analysis can be performed on the image to extract higher frequency content (>2Hz) from the video sequence.

[0026] The processor can be configured to analyze audio data by performing longitudinal voice analysis to diagnose that the subject suffers from bruxism or other jaw disorders or predict the risk that the subject will develop bruxism or other jaw disorders.

[0027] Sigmatism is an interference that copies consonants from the s and z sound groups. This condition, as well as some other characteristics of syllable pronunciation in continuous speech, are typical symptoms of bruxism. Using longitudinal voice signal analysis, changes related to these symptoms can be detected by comparing with historical data.

[0028] The processor can also be configured to analyze an early part of the video data to more accurately diagnose that the subject suffers from bruxism or other jaw disorders or more accurately predict the risk that the subject will develop bruxism or other jaw disorders. This can be performed when the analysis of the video data has been completed and now the early part of the video data is analyzed to perform the diagnosis more accurately.

[0029] For example, if jaw closure is monitored for an extended period while observing the movement of the user's lips, early analysis of the video stream can be used to check whether the bones at the back of the jaw have moved relative to each other by monitoring the video signal of the skin at the position of the joint of the jaw for a period of time (just) after the user closes their mouth. If so, the analysis of bruxism becomes more specific.

[0030] The processor can be configured to remotely activate the user's audio channel or remotely activate the user's video channel. Thus, the collection of appropriate data can be actively managed.

[0031] The receiver is configured to receive, for example, audio data and video data via a conference call. This provides a user-friendly way of analysis.

[0032] The present invention also provides a computer program which, when run on a processor, is adapted to implement a method comprising: receiving audio data and video data of a subject; identifying or analyzing one of the audio data and video data indicative of the subject suffering from bruxism or other jaw disorders or the risk of the subject developing bruxism or other jaw disorders, and in response thereto, analyzing the other of the audio data and video data to diagnose the subject as suffering from bruxism or other jaw disorders, or to predict the risk of the subject developing bruxism or other jaw disorders.

[0033] The method implemented by the computer program may comprise:

[0034] (i) identifying or analyzing video data indicative of the subject suffering from bruxism or other jaw disorders or the risk of developing bruxism or other jaw disorders by identifying an extended period of jaw closure when observing the movement of the user's lips; and

[0035] In response thereto, analyzing the audio data to determine whether the subject is speaking; or

[0036] (ii) analyzing the audio data to diagnose the subject as suffering from bruxism or other jaw disorders, or to predict the risk of the subject developing bruxism or other jaw disorders by detecting the voice sound characteristics of speech with a fixed jaw position; and

[0037] In response thereto, analyzing the video data to determine whether the subject is speaking with the mouth closed.

[0038] The method implemented by the computer program includes, for example: identifying or analyzing video data indicative of the subject suffering from bruxism or other jaw disorders or the risk of the subject developing bruxism or other jaw disorders by identifying an extended period of jaw closure when observing the movement of the user's lips; and in response thereto, analyzing the audio data to determine whether the subject is speaking.

[0039] The method implemented by the computer program includes, for example: analyzing the video data to detect yawning as an indication of the subject suffering from bruxism or other jaw disorders or the risk of the subject developing bruxism or other jaw disorders; and in response thereto, analyzing the audio data to detect popping or clicking sounds.

[0040] A method implemented by a computer program may include, for example: identifying or analyzing audio data indicative of a subject having bruxism or other jaw disorders, or a risk of the subject developing bruxism or other jaw disorders, by detecting voice sound characteristics of speech having a fixed jaw position; and in response, analyzing video data to determine whether the subject is speaking with their mouth closed.

[0041] After identifying or analyzing the video data to detect a subject having bruxism or other jaw disorders or a risk of the subject developing bruxism or other jaw disorders, the method may include analyzing an early portion of the video data to more accurately diagnose the subject as having bruxism or other jaw disorders, or more accurately predict the risk of the subject developing bruxism or other jaw disorders.

[0042] These and other aspects of the present invention will become apparent and be set forth with reference to the embodiments (one or more) described below. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] To better understand the present invention and to more clearly show how it may be implemented, reference will now be made, by way of example only, to the accompanying drawings, in which:

[0044] Figure 1 A system for detecting bruxism or other jaw disorders is shown;

[0045] Figure 2 An analysis method when audio analysis is performed first is shown; and

[0046] Figure 3 An analysis method when video analysis is performed first is shown. DETAILED DESCRIPTION

[0047] The present invention will be described with reference to the accompanying drawings.

[0048] It should be understood that the detailed description and specific examples, while indicating exemplary embodiments of the apparatus, systems, and methods, are intended for purposes of illustration only and are not intended to limit the scope of the present invention. These and other features, aspects, and advantages of the apparatus, systems, and methods of the present invention will become better understood from the following description, the appended claims, and the drawings. It should be understood that the drawings are merely schematic and are not drawn to scale. It should also be understood that in all the drawings, the same reference numerals are used to indicate the same or similar components.

[0049] The present invention provides a system for diagnosing bruxism or other jaw disorders or predicting the risk of developing bruxism or other jaw disorders, wherein audio data and video data of a subject are analyzed by a processor. One of the audio data and the video data is analyzed to detect potential bruxism or other jaw disorder events, and in response thereto, a specific analysis is performed on the other of the audio data and the video data to increase the confidence in the detection of bruxism or other jaw disorders. Thus, bruxism or other jaw disorders, or the risk of developing these disorders, are detected or diagnosed based on video and audio analysis, but data processing is reduced by performing only an initial analysis or identification of the video or audio to find candidate data samples for comprehensive analysis.

[0050] By performing the detection through automated audio- and video-based analysis, diagnosis can be performed remotely from the subject via a system for transmitting audio and video (such as a video conferencing system). The subject can simply use a mobile phone, tablet, laptop, or video conferencing system to access such a system.

[0051] Figure 1 A system 100 for diagnosing bruxism or other jaw disorders or predicting the risk of developing bruxism or other jaw disorders is shown.

[0052] In the following description, "bruxism" and, for example, "bruxism diagnosis" will be more generally referred to. This should be understood to more generally relate to bruxism or other jaw disorders, unless it is clear from the context that the discussion specifically relates to bruxism. These other jaw disorders can be related to bruxism; for example, TMJD can be caused by the above-mentioned bruxism. The term "jaw disorder" is intended to include any abnormal tooth-to-tooth contact load condition (e.g., jaw clenching, grinding, and thus having abnormal contact time or contact pressure). Some jaw disorders can also include abnormal jaw movement speed. Thus, the jaw disorders to be detected are essentially non-physiological.

[0053] This specific example utilizes a video conferencing system such that a remote practitioner performs a bruxism diagnosis or determines the risk of developing bruxism or other jaw disorders.

[0054] There is a user side, including a video conferencing system having a display 102 (including audio output), a microphone 104, and a camera 106. Audio and video data streams are thus generated and wirelessly transmitted to the practitioner side, where the analysis will be performed.

[0055] The practitioner side also includes a video conferencing system having a display 202 (including audio output), a microphone 204, and a camera 206. The audio and video data streams are received on the practitioner side. Of course, the video conferencing system allows for a two-way conversation between the user and the practitioner so that the practitioner can give instructions to the user.

[0056] However, it should be noted that the system of the present invention can be a stand-alone system, simply having a camera and a microphone for capturing images and sounds and directly providing the analysis results to the user. Then, the system can be implemented entirely by a single device, such as a mobile phone running an appropriate application.

[0057] In the example shown, the practitioner side has a receiver 210 for receiving the audio data and video data of the subject and a processor 212 for processing the audio data and video data to detect bruxism.

[0058] The processor identifies either the audio data or the video data that indicates that the subject has bruxism or other jaw disorders or the risk that the subject will develop bruxism or other jaw disorders. Thus, potential bruxism or jaw disorder events are identified. A potential bruxism or other jaw disorder event can be an event that has a disorder such as bruxism itself. However, conversely, it can be an event in which a specific further analysis will be able to reliably detect a disorder such as bruxism. For example, yawning itself does not indicate bruxism, but it provides a useful event for further analysis. Therefore, the term "potential bruxism or jaw disorder event" can be understood as an indicative event of bruxism or other jaw disorders or an event that requires further investigation because further investigation may be able to identify bruxism or other disorders (if they actually exist). Hereinafter, "potential bruxism or jaw disorder event" will be abbreviated as "potential bruxism event".

[0059] In response to detecting a potential bruxism event, a specific analysis of the other of the audio data and the video data is selected and performed. This analysis of the other data gives more confidence as to whether the potential bruxism event is indeed a bruxism event (and thus more generally a "bruxism or jaw disorder event"). In this analysis, it can be determined whether the subject has bruxism or another jaw disorder, or the risk of developing these disorders can be predicted.

[0060] Figure 2 An analysis method is shown when audio analysis is first performed as step 300. In step 302, it is determined whether there is a potential bruxism event, and if so, additional video analysis is performed in step 304. Otherwise, video analysis is not performed, and the method returns to audio analysis.

[0061] Figure 3 An analysis method is shown when video analysis is first performed as step 400. In step 402, it is determined whether there is a potential bruxism event, and if so, additional audio analysis is performed in step 404. Otherwise, audio analysis is not performed, and the method returns to video analysis.

[0062] Some examples of how to detect bruxism events or potential bruxism events will be described below. In some cases, the detection is only suitable for looking for potential bruxism events (such as yawning), while in other cases, the detection can be used first (to identify potential bruxism events) or second (to confirm potential bruxism events that have already been identified).

[0063] (i) Audio features indicating bruxism:

[0064] The audio signals generated during speech are a combination of vocal cord vibrations and airflows, all of which are modulated by the cavities created by the mouth and tongue. For this reason, humans are able to produce many types of audio signals represented by different audio spectra.

[0065] During a diurnal bruxism episode, the subject may talk while clenching or grinding the jaw. Such a restriction on jaw movement will result in a more limited range of the audio spectrum, as we are familiar with from the speech of ventriloquists.

[0066] Typical changes in the audio spectrum as a result of bruxism have been analyzed in the literature. For example, US2021 / 369189 discloses a bruxism detection and correction device that uses audio filters to analyze sounds to determine whether they are associated with bruxism events.

[0067] However, audio analysis alone may not be reliable enough. For example, it may not be possible to determine whether an audio signal is related to jaw clenching or is merely the result of someone speaking with a closed but unclenched jaw.

[0068] (ii) Video features indicating bruxism:

[0069] The video signals recorded during speech are a combination of jaw, lip, tooth, and tongue movements, particularly their relative positions. For this reason, humans produce many types of video signals to accompany the different audio spectra generated during speech.

[0070] During a diurnal bruxism episode, the subject may talk while clenching the jaw. Such a lack of jaw opening can be picked up in the video signal.

[0071] However, just by observing the video, it is also not possible to determine whether a closed jaw is related to jaw clenching or is merely the result of someone not speaking or actually speaking with a closed but unclenched jaw.

[0072] Another example of visual movements associated with bruxism is the lateral grinding movement of the jaw. These can be detected relatively easily from the video sequence.

[0073] Clenching of the jaw can also be detected. During jaw clenching, the bones at the back of the jaw move relative to each other, so monitoring the video signal of the skin at the location of the joint of the jaw will be characteristic of jaw clenching.

[0074] Due to clenching, there can also be pulsating cheek muscle movements (and sometimes even pulsating skin movements on the temples). To detect such conditions, FFT analysis of the image can be used to extract higher frequency content (>2Hz) from the video sequence.

[0075] Some specific combinations of the detection methods will now be outlined.

[0076] As Figure 2 shown, the first example is to use the audio stream to trigger a specific analysis of the video stream. The video stream analysis is only activated after a potential bruxism event is identified in the audio stream.

[0077] For example, if an audio with the characteristics of speech with a fixed jaw position for an extended period of time is detected, the video stream analysis is activated to determine whether the user is actually speaking with the mouth closed. If this is the case, the user has a higher chance of having diurnal bruxism.

[0078] In addition, if further analysis of the video stream (before or after speaking) indicates that the bones at the back of the jaw move relative to each other for a period of time (just) after the user closes the mouth, the analysis of bruxism becomes more specific. As described above, this can be achieved by monitoring the video signal of the skin at the location of the joint of the jaw.

[0079] As Figure 3 shown, the second example is to use the video stream to trigger a specific analysis of the audio stream. The audio stream analysis is only activated after a potential bruxism event is identified in the video stream. For example, if an extended period of jaw closure is monitored when observing the movement of the user's lips, audio analysis is performed to check whether the user is really speaking. If this is the case, the user has a higher chance of having diurnal bruxism. In addition, if a specific audio spectrum characteristic of bruxism is detected, the analysis of bruxism becomes more specific.

[0080] Yaw events (start, duration, end) can also be identified from the video data to trigger audio analysis. When a person yawns, the mouth usually opens to the maximum. Then the popping or clicking sounds of the temporomandibular joint (TMJ) can be measured, and temporomandibular joint disorder (TMJD) can be detected, which can accompany bruxism (and has been caused by bruxism).

[0081] The method of the present invention greatly reduces the amount of data to be processed, because a full measurement is only performed when the maximum effect can be applied or expected (for example, during yawning and sneezing, when the maximum mouth opening occurs, and the sounds related to TMJD can be measured at this time).

[0082] Another interesting option is to use the analysis of the video stream in order to trigger an earlier analysis of the video stream. In order to effectively utilize the processing resources, after identifying potential bruxism events in the video stream, an earlier analysis of the video stream can be performed.

[0083] An example was outlined above where a jaw closure with an extended period of moving lips can trigger an earlier analysis of the video stream to check whether the bones at the back of the jaw are moving relative to each other earlier. If this is the case, the analysis or prediction of the risk of developing bruxism becomes more specific.

[0084] Research has found that sigmatism (a disturbance where consonants are copied from the s and z sound groups) and certain characteristics of syllable pronunciation in continuous speech are typical symptoms of bruxism. Using longitudinal speech signal analysis, such changes can be detected by comparing with historical data.

[0085] Additional sensors can be used to make the determination of bruxism more accurate, such as ear pressure sensors. For example, pressure changes in the ear canal can indicate oral disorders such as bruxism. The measured outer ear pressure can convey information about typical movements involving the jaw bones, such as upward, downward, and left - right movements of the jaw. This information can then be further used to detect complex movements of the oral cavity, such as swallowing and yawning, which include different combinations of typical jaw bone movements. Based on the attributes of these movements, the detection of bruxism can be more accurate.

[0086] From the study of the drawings, the disclosure, and the appended claims, those skilled in the art can understand and implement variations of the disclosed embodiments when practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0087] Functions implemented by a processor can be implemented by a single processor or multiple separate processing units, which can together be considered to constitute a "processor". Such processing units can in some cases be remote from each other and communicate with each other in a wired or wireless manner.

[0088] The fact that certain measures are only cited in mutually different dependent claims does not indicate that a combination of these measures cannot be used advantageously.

[0089] A computer program can be stored / distributed on a suitable medium, such as an optical storage medium or a solid - state medium provided together with other hardware or as a component of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

[0090] If the term "adapted to" is used in a claim or the specification, it should be noted that the term "adapted to" is intended to be equivalent to the term "configured to". If the term "means" is used in a claim or the specification, it should be noted that the term "means" is intended to be equivalent to the term "system", and vice versa.

[0091] Any reference signs in the claims shall not be construed as limiting the scope.

Claims

1. A system (100) for diagnosing bruxism or other jaw disorders or predicting the risk of developing bruxism or other jaw disorders, comprising: A receiver (210) configured to receive audio data and video data of a subject; A processor (212) configured to: Identify one of the audio data and the video data indicative of the subject having bruxism or other jaw disorders or the risk of the subject developing bruxism or other jaw disorders, and in response thereto, Analyze the other of the audio data and the video data to diagnose the subject with bruxism or other jaw disorders, or predict the risk of the subject developing bruxism or other jaw disorders.

2. The system according to claim 1, wherein the processor is configured to: Identify the video data indicative of the subject having bruxism or other jaw disorders or the risk of the subject developing bruxism or other jaw disorders by identifying an extended period of jaw closure when observing the movement of the user's lips; and In response, analyze the audio data to determine whether the subject is speaking.

3. The system according to claim 2, wherein the processor is configured to: Analyze the spectrum of the audio data to detect features indicative of the subject having bruxism or other jaw disorders or the risk of the subject developing bruxism or other jaw disorders.

4. The system according to any one of claims 1 to 3, wherein the processor is configured to: Analyze the video data to detect yawning as an indication of the subject having bruxism or other jaw disorders or the risk of the subject developing bruxism or other jaw disorders; and In response, analyze the audio data to detect popping or clicking sounds.

5. The system according to claim 1, wherein the processor is configured to: Identify the audio data indicative of the subject having bruxism or other jaw disorders or the risk of the subject developing bruxism or other jaw disorders by detecting the voice sound characteristics of speech with a fixed jaw position; and In response, analyze the video data to determine whether the subject is speaking with the mouth closed.

6. The system according to any one of claims 1 to 5, wherein the processor is configured to analyze the video data to diagnose the subject with bruxism or other jaw disorders or predict the risk of the subject developing bruxism or other jaw disorders by identifying repetitive lateral grinding movements of the jaw.

7. The system according to any one of claims 1 to 6, wherein the processor is configured to analyze the video data to detect jaw clenching by monitoring facial skin and / or muscle movements and / or ear movements at the position of the joint of the jaw, thereby diagnosing the subject with bruxism or other jaw disorders or predicting the risk of the subject developing bruxism or other jaw disorders.

8. The system according to any one of claims 1 to 7, wherein the processor is configured to analyze the audio data by performing longitudinal voice analysis to diagnose that the subject has bruxism or other jaw disorders, or to predict the risk that the subject will develop bruxism or other jaw disorders.

9. The system according to any one of claims 1 to 8, wherein the processor is further configured to analyze an early portion of the video data to more accurately diagnose that the subject has bruxism or other jaw disorders, or to more accurately predict the risk that the subject will develop bruxism or other jaw disorders.

10. The system according to any one of claims 1 to 9, wherein the processor is configured to remotely activate the audio channel of the user or remotely activate the video channel of the user.

11. The system according to any one of claims 1 to 10, wherein the receiver is configured to receive the audio data and the video data via a conference call.

12. A computer program, which when run on a processor, is adapted to implement a method for diagnosing bruxism or other jaw disorders or predicting the risk of developing bruxism or other jaw disorders, the method comprising: receiving audio data and video data of a subject; identifying one of the audio data and the video data that indicates that the subject has bruxism or other jaw disorders or the risk that the subject will develop bruxism or other jaw disorders, and in response thereto, analyzing the other of the audio data and the video data to diagnose that the subject has bruxism or other jaw disorders, or to predict the risk that the subject will develop bruxism or other jaw disorders.

13. The computer program according to claim 12, wherein the method implemented by the computer program comprises: (i) identifying the video data that indicates that the subject has bruxism or other jaw disorders or the risk of developing bruxism or other jaw disorders by identifying an extended period of jaw closure when observing the movement of the user's lips; and in response, analyzing the audio data to determine whether the subject is speaking; or (ii) analyzing the audio data to diagnose that the subject has bruxism or other jaw disorders, or to predict the risk that the subject will develop bruxism or other jaw disorders by detecting the voice sound characteristics of speech with a fixed jaw position; and in response, analyzing the video data to determine whether the subject is speaking with the mouth closed.

14. The computer program according to claim 12 or 13, wherein the method implemented by the computer program comprises: analyzing the video data to detect yawning as an indication that the subject has bruxism or other jaw disorders or the risk that the subject will develop bruxism or other jaw disorders; and in response, analyzing the audio data to detect popping or clicking sounds.

15. The computer program according to any one of claims 12 to 14, wherein the method implemented by the computer program comprises analyzing an early portion of the video data to more accurately diagnose that the subject has bruxism or other jaw disorders, or more accurately predict the risk that the subject will develop bruxism or other jaw disorders.

Images