Wireless medical sensors and methods

Abstract

To provide medical sensors and related methods for measuring a real-time personal metric.SOLUTION: A medical sensor may comprise: an electronic device having a sensor comprising an accelerometer; and a bidirectional wireless communication system electrically connected to the electronic device for sending an output signal from the sensor to an external device and receiving commands from an external controller to the electronic device.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] Cross - Reference to Related Applications This application claims the benefit and priority of U.S. Provisional Patent Application No. 62 / 710,324, filed on February 16, 2018, U.S. Provisional Patent Application No. 62 / 631,692, filed on February 17, 2018, and U.S. Provisional Patent Application 62 / 753,203, filed on October 31, 2018, each of which is incorporated herein by reference in its entirety without contradiction.

[0002] Provided herein is a medical sensor, including, but not limited to, an on - board microphone and a feedback stimulus coupled to a mechanical - acoustic sensing electronic device, including a vibration motor, a speaker, or an LED indicator. A system and method are provided for an electronic device that uses a 3 - axis high - frequency accelerometer to sense mechanically - acoustic electrophysiological signals originating from the body. These devices are herein referred to as soft, flexible, wearable devices with advanced power - saving features and wireless communication capabilities, including being compatible with Bluetooth® - enabled systems. Within the system, there are signal - processing, signal - analysis, and machine - learning functions that provide a platform for multi - mode sensing of a wide range of physiological and environmental signals, including, but not limited to, voice, talk time, respiratory rate, heart rate, lung volume, swallowing function, body activity, sleep quality, movement, and feeding behavior. These systems and methods are adapted for use with additional sensors, including one or more of an on - board microphone, a pulse oximeter, an ECG, and an EMG, among others.

Background Art

[0003] Mechanical acoustic signals are known to contain essential information for clinical diagnosis and healthcare applications. In particular, mechanical waves propagating through body tissues and fluids resulting from natural physiological activities reveal characteristic traces of individual events such as the closure of heart valves, the contraction of skeletal muscles, the vibration of vocal cords, the respiratory cycle, scratching movements and sounds, as well as gastrointestinal motility.

[0004] The frequencies of these signals can range from fractions of 1 Hz (e.g., respiratory rate) to 2000 Hz (e.g., speech), and often have low amplitudes that exceed the auditory threshold. Physiological auscultation is typically performed using an analog or digital stethoscope in an individual procedure carried out during a clinical examination.

[0005] Alternative approaches rely on accelerometers within conventional rigid electronic device packages that are typically physically fixed to the body with straps so that the necessary mechanical coupling is obtained. Demonstrations of research results include phonocardiogram measurement (PCG, sounds from the heart), vibrocardiogram measurement (SCG, chest vibrations induced by the heartbeat), ballistocardiogram measurement (BCG, recoil movements associated with the response to cardiovascular pressure), and recording of sounds associated with breathing.

[0006] In the context of cardiovascular health, these measurements provide important insights that complement those inferred from electrocardiogram measurement (ECG). For example, structural defects within heart valves appear as mechanical acoustic responses and do not directly appear within the ECG trace.

[0007] Previously reported digital measurement methods are useful for laboratory research and clinical studies, but (i) their form factors (rigid designs and large sizes, e.g., 150 mm × 70 mm × 25 mm) limit the choice of wearing locations and compromise their usability as wearables, (ii) their bulky structures involve physical masses that suppress subtle movements associated with important physiological events through inertial effects, (iii) their mass densities and elastic moduli are different from those of the skin, thereby causing acoustic impedance mismatches with the skin, and (iv) they cannot capture, for example, ECG and PCG / SCG / BCG signals simultaneously, resulting in only a single operating mode, (iv) their methods for communication and data transmission to the user interface are performed via wires tethered to the device and the user interface machine, and (v) their power management is performed through wired connections. The devices and methods provided herein address these limitations in the technical field.

Prior Art Documents

Non-Patent Documents

[0008]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0009] Provided herein are methods and devices for providing a remote treatment type platform, where medical sensors attached to or embedded in a user provide useful information that caregivers, such as medical professionals, friends, or family, can act upon. These devices and methods are useful not only for diagnostic or treatment applications, but also for training and rehabilitation. This is reflected in devices and systems that perform two-way communication such that commands can be received by the medical sensors, where information is transmitted externally to the caregiver in response to an action and the user is instructed to perform appropriate actions, including swallowing, breathing, inhaling, and the like.

[0010] The devices and systems perform real-time output, such as useful information for novel clinical metrics, novel clinical markers, and beneficial endpoints, thereby improving the overall health and well-being of the user. These devices and systems are particularly suitable for utilizing off-site cloud storage and analytics that can conveniently, reliably, and easily trigger actions by clinicians or caregivers.

[0011] The special configuration of hardware, software, two-way information flow, and remote storage and analysis realizes a substantially improved platform for healthcare and welfare in a relatively unobtrusive mobile manner that is not bound by conventional clinical settings (e.g., restricted to hospitals or controlled environments). In particular, the software, which can be embedded in a chip or processor, may be installed on the devices described herein or be remote and provides greatly improved sensor performance and clinically useful information. Machine learning algorithms are particularly useful for further improving device performance.

Means for Solving the Problems

[0012] Specifically included herein are the appended claims and any other parts of the specification and drawings.

[0013] In one aspect, provided is a medical sensor, which comprises a) an electronic device having a sensor including an accelerometer, and b) a bi-directional wireless communication system electronically connected to the electronic device for transmitting an output signal from the sensor to an external device and receiving commands from an external controller to the electronic device.

[0014] The medical sensor may be wearable, tissue-mounted, implantable, or mechanically communicate with or directly to the subject's tissue. The medical sensor may comprise a wireless power supply system for powering the electronic device. The medical sensor may comprise a processor for providing a real-time metric. The processor may be mounted on the electronic device or positioned within an external device located at a distance from the medical sensor and wirelessly communicating with the wireless communication system. The processor may be part of a portable smart device.

[0015] The medical sensor may continuously monitor and generate real-time metrics, such as social metrics or clinical metrics. For example, clinical metrics may be selected from the group consisting of swallowing parameters, respiratory parameters, suction parameters, cough parameters, sneeze parameters, temperature, heart rate, sleep parameters, pulse oximetry, snoring parameters, body movement, scratching parameters, bowel movement parameters, neonatal subject diagnostic parameters, cerebral palsy diagnostic parameters, and any combination thereof. For example, social metrics may be selected from the group consisting of conversation time, word count, vocalization parameters, linguistic conversation parameters, interaction parameters, sleep quality, feeding behavior, physical activity parameters, and any combination thereof.

[0016] A medical sensor may include a processor configured to analyze an output signal. The processor may utilize machine learning to customize the analysis for each individual user of the medical sensor. The machine learning may include one or more supervised learning algorithms and / or unsupervised learning algorithms that are customizable for the user. The machine learning may improve sensor performance parameters and / or personalized user performance parameters used in diagnostic sensing or treatment applications.

[0017] The processor described herein may be configured to filter and analyze measured outputs from an electronic device to improve sensor performance parameters. The medical sensor may include a wireless power supply system for wirelessly powering the electronic device. The accelerometer may be a three-axis high-frequency accelerometer.

[0018] The electronic device described herein may include an extensible electrical interconnect, a microprocessor, an accelerometer, a stimulation device, a resistor, and a capacitor that are electronically communicating to sense vibrations or movements by the accelerometer and provide stimulation by the stimulation device to the user. The sensor may be configured to sense multiple or single physiological signals from a subject, and the threshold may be used to send back to the subject a trigger for a correction, stimulation, biofeedback, or enhancement signal.

[0019] The electronic device described herein may include a network comprising a plurality of sensors. For example, one sensor may be configured to sense the physiological signal from the subject, and one sensor may be configured to provide a feedback signal to the subject.

[0020] The threshold may be personalized for the subject. The stimulation device may include one or more of a vibration motor, electrodes, a light emitter, a thermal actuator, or an audio notification.

[0021] The medical sensor described herein may further comprise a flexible encapsulation layer surrounding the flexible substrate and the electronic device. The encapsulation layer may include a lower encapsulation layer and an upper encapsulation layer, as well as a strain isolation layer, which is supported by the lower encapsulation layer, and the flexible substrate is supported by the strain isolation layer. There may be an air pocket between the electronic device and the upper encapsulation layer. The medical sensor may be configured such that there is no air pocket between the electronic device and the lower layer of the device that is close to or in contact with the tissue surface of the subject.

[0022] The medical sensor may have a device mass of less than 1 g, less than 500 mg, less than 400 mg, or optionally less than 200 mg, and a device thickness of less than 10 cm, less than 6 mm, less than 5 mm, or optionally less than 3 mm.

[0023] The medical sensor described herein may be configured for a therapeutic swallowing application, a social interaction meter, a stroke rehabilitation device, or a respiratory therapy device. The medical sensor may be configured to be worn by a user and used in a therapeutic swallowing application, and the output signal is a signal for one or more swallowing parameters selected from the group consisting of swallowing frequency, swallowing count, and swallowing energy. The medical sensor may further comprise a stimulation device that provides a tactile signal to the user to participate in safe swallowing. Safe swallowing may be determined by sensing the beginning of inspiration and expiration of the user's respiratory cycle. One or more machine learning algorithms may be used in a feedback loop for optimizing the tactile signal timing.

[0024] The medical sensors described herein may be configured to be worn by a user and used as a social interaction meter, and the output signal may be a signal for one or more social parameters selected from the group consisting of conversation time, number of words (rate of fluency), vocalization parameters, linguistic conversation parameters, or interaction parameters. The medical sensor may be configured to be worn on the user's suprasternal notch. The medical sensor may be a sensor for use with one or more additional user well-being parameters selected from the group consisting of sleep quality, eating behavior, and physical activity, and the social and well-being parameters of the medical sensor may be combined to provide a social interaction metric.

[0025] The medical sensor may further comprise a stimulation device that provides a tactile signal to the user to engage in a social interaction event. The medical sensor may be configured to be worn by a user and used in a stroke rehabilitation device, and the output signal may be a signal for social parameters and / or swallowing parameters. The medical sensor may be a sensor for use with one or more additional stroke rehabilitation parameters selected from the group consisting of walking, falling, and physical activity. The medical sensor may comprise a stimulation device that provides a tactile signal to the user to engage in a safe swallowing event.

[0026] The medical device may be configured to be worn by a user and used in a respiratory therapy device, and the output signal may be a signal for inhalation and / or exhalation, i.e., effort, duration, or airflow through the throat. The medical device may comprise a stimulation device that provides a tactile signal to the user to engage in respiratory training.

[0027] The medical device described herein may comprise an external sensor operably connected to an electronic device. The external sensor may comprise a microphone and / or a mouthpiece.

[0028] The medical sensors described herein may be capable of reproducing an avatar, i.e., a video representation, of a subject's position and movement over time.

[0029] In one aspect, provided is a method of measuring real-time personal metrics using any of the medical sensors described herein.

[0030] In one aspect, provided is a method of measuring real-time personal metrics, the method comprising: a) attaching or implanting subcutaneously any of the devices of the above claim to the user's skin surface; b) detecting signals generated by the user with the sensor; c) analyzing the filtered signals to thereby classify the filtered signals; and d) providing real-time metrics to the user or a third party based on the classified filtered signals.

[0031] The method described may include filtering the detected signals before the analyzing step. The steps provided may include one or more of providing a tactile stimulus to the user, storing or displaying clinical metrics, and / or storing or displaying social metrics. The step of providing may further include storing the real-time metrics on a remote server for subsequent analysis to generate an action by a clinician or caregiver. This action may include sending a command to the medical sensor.

[0032] The real-time metrics may be health-related mental, physical, or social metrics. The step of analyzing may include the use of a machine learning algorithm. The machine learning algorithm may include a supervised learning algorithm, and each algorithm is independently trained to provide personalized real-time metrics specific to an individual user.

[0033] Personalized real-time individual metrics can be metrics for therapeutic or diagnostic applications. The therapeutic or diagnostic applications can be selected from the group consisting of safe swallowing, respiratory therapy, cerebral palsy diagnosis or treatment, and neonatal diagnosis or treatment.

[0034] The real-time individual metrics can be for medical applications selected from the group consisting of sleep medicine, dermatology, respiratory medicine, social interaction assessment, speech therapy, dysphagia, stroke rehabilitation, nutrition, obesity treatment, fetal monitoring, neonatal monitoring, cerebral palsy diagnosis, pregnant woman monitoring, bowel function, diagnosis or treatment of sleep disorders, sleep therapy, trauma, prevention of trauma falls or hyperextension of joints or limbs, prevention of trauma during sleep, small firearm / ballistic-related injuries, and cardiac output monitoring treatment.

[0035] In one aspect, provided is a medical sensor comprising an electronic device having a sensor with an accelerometer and a wireless communication system electronically connected to the electronic device.

[0036] The wireless communication system can be a bidirectional wireless communication system. The wireless communication system can be a system for transmitting an output signal from the sensor to an external device. The wireless communication system can be a system for receiving commands from an external controller to the electronic device.

[0037] The medical sensor described herein can be wearable or implantable. The medical sensor can comprise a wireless power supply system for powering the electronic device. The medical sensor can comprise a processor for providing real-time metrics. The processor can be mounted on the electronic device or positioned within an external device that is located at a distance from the medical sensor and wirelessly communicates with the wireless communication system. The processor can be part of a portable smart device.

[0038] The medical sensors described herein can continuously monitor and generate real-time metrics. The real-time metrics can be social metrics or clinical metrics. Clinical metrics can be selected from the group consisting of swallowing parameters, respiratory parameters, suction parameters, cough parameters, sneeze parameters, temperature, heart rate, sleep parameters, pulse oxygen concentration, snoring parameters, body movement, scratching parameters, bowel movement parameters, and any combination thereof.

[0039] Social metrics can be selected from the group consisting of conversation time, number of words, vocalization parameters, linguistic conversation parameters, interaction parameters, sleep quality, eating behavior, physical activity parameters, and any combination thereof.

[0040] The medical sensors described herein can include a processor configured to analyze the output signal. The processor may utilize machine learning to customize the analysis for each individual user of the medical sensor. Machine learning can include one or more supervised learning algorithms and / or unsupervised learning algorithms that are customizable for the user. Machine learning can improve sensor performance parameters and / or personalized user performance parameters used in diagnostic or therapeutic applications.

[0041] The described sensor may be provided on or near the suprasternal notch of the subject. The described sensor may be provided on or near the mastoid process of the subject. The described sensor may be provided on or near the neck of the subject. The described sensor may be provided on or near the lateral neck of the subject. The described sensor may be provided under or near the chin of the subject. The described sensor may be provided on or near the jaw line of the subject. The described sensor may be provided on or near the clavicle of the subject. The described sensor may be provided on or near the bony prominence of the subject. The described sensor may be provided behind the ear of the subject.

[0042] The described electronic device may comprise one or more three-axis high-frequency accelerometers. The described electronic device may comprise a mechanical acoustic sensor. The described electronic device may comprise one or more of an on-board microphone, an ECG, a pulse oximeter, a vibration motor, a flow sensor, and a pressure sensor.

[0043] The described electronic device may be a flexible device and / or an extensible device. The described electronic device may have a multi-layer floating device architecture. The described electronic device may be at least partially supported by an elastomeric substrate, a superstrate, or both. The described electronic device may be at least partially supported by a silicone elastomer that provides strain isolation.

[0044] The described electronic device may be at least partially encapsulated by a moisture-resistant enclosure. The described electronic device may further include an air pocket.

[0045] The wireless communication system described in this specification may be a Bluetooth communication module. The wireless communication system described in this specification may be powered by a wireless rechargeable system. The wireless rechargeable system may include one or more of a rechargeable battery, an induction coil, a full-wave rectifier, a regulator, a charging IC, and a PNP transistor.

[0046] The medical sensor described in this specification may include a gyroscope, such as a three-axis gyroscope. The medical sensor described in this specification may include a magnetometer, for example, to measure the electric field generated by a patient's respiration. The described medical sensor may be worn near the patient's suprasternal notch.

[0047] In one aspect, provided is a device that includes an electronic device having a sensor with an accelerometer, and a bi-directional wireless communication system electronically connected to the electronic device for transmitting an output signal from the sensor to an external device and receiving commands from an external controller to the electronic device, wherein the sensor senses multiple or single physiological signals from a subject that provide a basis for one or more corrections, stimulations, biofeedback, or reinforcement signals provided to the subject.

[0048] The correction, stimulation, biofeedback, or reinforcement signal may be provided by one or more actuators. The one or more actuators may be thermal, optical, electro-tactile, auditory, visual, tactile, or chemical actuators operably connected to the subject. The device may include a processor for performing feedback control of the one or more corrections, stimulations, biofeedback, or reinforcement signals provided to the subject.

[0049] Multiple or single physiological signals may provide the input for the feedback control. The feedback control may include a threshold processing step for triggering the one or more correction, stimulation, biofeedback, or reinforcement signals provided to the subject. The threshold processing step may be achieved by dynamic threshold processing.

[0050] In one aspect, provided is a device, which is an electronic device having a multi-mode sensor system comprising a plurality of sensors, wherein the sensors comprise an accelerometer and at least one sensor other than the accelerometer, and an electronic device, and a bi-directional wireless communication system electronically connected to the electronic device for transmitting an output signal from the sensors to an external device and receiving commands from the external controller to the electronic device.

[0051] The sensor system may comprise one or more sensors selected from the group consisting of optical sensors, electronic sensors, thermal sensors, magnetic sensors, optical sensors, chemical sensors, electrochemical sensors, fluid sensors, or any combination thereof. The sensor system may comprise one or more sensors selected from the group consisting of pressure sensors, electrophysiological sensors, thermocouples, heart rate sensors, pulse oxygen concentration sensors, ultrasonic sensors, or any combination thereof.

[0052] In one aspect, provided is a device, which comprises an electronic device having a sensor comprising an accelerometer, and one or more actuators operably connected to the sensor, wherein the sensor senses multiple or single physiological signals from the subject that provide the basis for one or more correction, stimulation, biofeedback, or reinforcement signals applied to the subject by the one or more actuators.

[0053] The one or more correction, stimulation, biofeedback, or reinforcement signals may be one or more optical signals, electronic signals, thermal signals, magnetic signals, chemical signals, electrochemical signals, fluid signals, visual signals, mechanical signals, or any combination thereof.

[0054] One or more actuators may be selected from the group consisting of a thermal actuator, an optical actuator, an electro-tactile actuator, an auditory actuator, a visual actuator, a tactile actuator, a mechanical actuator, or a chemical actuator that is operably connected to the subject. The one or more actuators may be one or more stimulators. The one or more actuators may be a heating device, a light emitter, a vibration element, a piezoelectric element, a sound generating element, a tactile element, or any combination thereof.

[0055] The processor may be operably connected to the electronic device and the one or more actuators, and the processor performs feedback control of the one or more corrections, stimulations, biofeedback, or reinforcement signals provided to the subject. A plurality or a single physiological signal may provide the input for the feedback control.

[0056] The feedback control may include a threshold processing step for triggering the one or more corrections, stimulations, biofeedback, or reinforcement signals provided to the subject. The threshold processing step may be achieved by dynamic threshold processing.

[0057] The described device may comprise a bidirectional wireless communication system that is electronically connected to an electronic device for transmitting an output signal from a sensor to an external device and receiving a command from an external controller to the electronic device. Correction, stimulation, biofeedback, or reinforcement signals may be provided to the subject for training or treatment. The training or treatment may be for respiratory or swallowing training.

[0058] The described device can continuously monitor and generate real-time metrics. The real-time metrics can be social metrics or clinical metrics. Clinical metrics can be selected from the group consisting of swallowing parameters, respiratory parameters, suction parameters, cough parameters, sneeze parameters, temperature, heart rate, sleep parameters, pulse oxygen concentration, snoring parameters, body movement, scratching parameters, bowel movement parameters, neonatal subject diagnosis parameters, cerebral palsy diagnosis parameters, and any combination thereof. Social metrics can be selected from the group consisting of conversation time, number of words, vocalization parameters, linguistic conversation parameters, interaction parameters, quality of sleep, eating behavior, physical activity parameters, and any combination thereof.

[0059] The described device can comprise a gyroscope, such as a 3-axis gyroscope. The described device can comprise a magnetometer.

[0060] In one aspect, provided is a method of diagnosis using any of the devices or sensors described herein.

[0061] In one aspect, provided is a method of training a subject using any of the devices or sensors described herein.

[0062] In addition, the provided sensor configurations can be used in combination to provide more accurate measurements or metrics. For example, an accelerometer can be used in combination with a mechanical acoustic sensor for measuring a user's scratching. The scratching motion can be detected by the accelerometer, but other common motions (e.g., waving a hand, typing) can be difficult to distinguish from scratching. Incorporating an acoustic sensor near the skin enables secondary classification and improves data collection.

[0063] Differential measurements of discrete regions of a patient's body can also be useful in improving data collection and data accuracy. In some cases, a single device may be positioned on a biological boundary to measure two different regions, and in some cases, multiple devices may be used. For example, placing a device on the suprasternal notch enables acceleration measurements of both the chest and neck. During breathing, the degree of movement in the chest is high while the neck is relatively stationary. This allows for more robust measurements and evaluations using the devices described herein.

[0064] Without wishing to be bound by any particular theory, there may be an explanation of the underlying principles and understandings associated with the devices and methods disclosed herein. Regardless of the ultimate correctness of the explanations or hypotheses regarding the machines, one embodiment of the invention may still be operable and useful. BRIEF DESCRIPTION OF THE DRAWINGS

[0065]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Figure 24

Figure 25

Figure 26

Figure 27

Figure 28

Figure 29

Figure 30A

Figure 30B

Figure 30C

Figure 30D

Figure 31A

Figure 31B

Figure 32A

Figure 32B

Figure 32C

Figure 32D

Figure 33

Figure 33C

Figure 33D

Figure 34

Figure 35A

Figure 35B

Figure 35C

Figure 35D

Figure 36

Figure 37

Figure 38

Figure 39

Figure 40

Figure 41

Figure 42

Figure 43

Figure 43C

Figure 43D

Figure 43E

Figure 44A

Figure 44B

Figure 45A

Figure 45B

Figure 45C

Figure 45D

Figure 45E

Figure 46A

Figure 46B

Figure 46C

Figure 46D

Figure 47A

Figure 47B

Figure 47C

Figure 47D

Figure 47E

Figure 47F

Figure 47G

Figure 47H

Figure 48

Figure 49A

Figure 49B

Figure 50A

Figure 50B

Figure 51A

Figure 51B

Figure 52

Figure 53A

Figure 53B

Figure 54A

Figure 54B

Figure 55A

Figure 55B

Figure 56

[0066] In general, the terms and phrases used herein have meanings recognized in the art, which can be found by referring to standard textbooks, periodical literature, and context known to those skilled in the art. The following definitions are provided to clarify specific uses in the context of the present invention.

[0067] "Mechanical acoustics" refers to any sound, vibration, or movement by the user that can be detected by an accelerometer. Thus, the accelerometer is preferably a high-frequency three-axis accelerometer capable of detecting a wide range of mechanical acoustic signals. Examples include breathing, swallowing, organ (lung, heart) movement, exercise (scratching, gymnastics, movement), conversation, bowel activity, cough, sneeze, and the like.

[0068] "Bidirectional wireless communication system" refers to the on-board components of a sensor that enable the ability to transmit and receive signals. In this way, the output can be provided to an external device, including a cloud-based device, a personal portable device, or a caregiver computer system. Similarly, a command can be transmitted to the sensor by an external controller, which may or may not be compatible with the external device. Machine learning algorithms may be used to improve signal analysis, and then a command signal can be transmitted to a medical sensor, including a stimulation device for a medical sensor that provides a tactile signal to a user of a medical device useful for treatment. More generally, these systems can be incorporated into a processor, such as a microprocessor, that is either on-board the electronic device of the medical sensor or physically separated from that electronic device.

[0069] As used herein, "real-time metric" is used in a broad sense to refer to any output that is useful in healthcare and welfare. This may refer to social metrics that are useful in understanding the social welfare of a user. This may refer to clinical metrics that are useful in understanding or training biological functions such as breathing and / or swallowing.

[0070] "Customized machine learning" refers to the analysis of the output from sensors that have been tailored to individual users. Such systems recognize the individual variations between users based on criteria including medical conditions (stroke vs. dementia), weight, baseline fluency, resting respiratory rate, basal heart rate, etc. In particular, by tailoring the analysis to individual users, the output of the sensors and what is done downstream by caregivers is significantly improved. This is generally referred to herein as an improvement in "sensor performance parameters". Exemplary parameters include, for example, accuracy, repeatability, fidelity, and classification accuracy.

[0071] "Proximate to" refers to the location in close proximity to another element and / or the placement of a subject such as a human subject. For example, in one embodiment, proximate means within 10 cm of the placement on another element and / or subject, optionally within 5 cm for some applications, and optionally within 1 cm for some applications.

[0072] In some embodiments, the inventors' sensor system is wearable and is tissue-mounted or implantable or mechanically communicates with or directly mechanically communicates with the subject's tissue. As used herein, mechanical communication enables the sensors of the present invention to gain deeper insights while reducing motion artifacts compared to accelerometers that are strapped to the body (wrist or chest) in some embodiments and to have a shape-conforming flexibility that enhances the sensing ability and can directly or indirectly contact the skin or other tissue in a direct manner (e.g., without gaps).

[0073] Various embodiments of the technology of the present invention relate to sensing and physical feedback interfaces, generally including "mechanophonic" sensing. More specifically, some embodiments of the technology of the present invention relate to systems and methods for mechanophonic sensing electronic devices configured for use in respiratory diagnosis, digestive diagnosis, social interaction diagnosis, skin inflammation diagnosis, cardiovascular diagnosis, and human machine interface (HMI).

[0074] Physiological mechanophonic signals, which often have frequencies and intensities that exceed values associated with the audible range, can provide highly clinically useful information. Conventional packages of stethoscopes and digital accelerometers can capture some relevant data, but neither is suitable for use in a continuous wearable mode in a typical non-static environment, and both have drawbacks related to mechanical conversion or signals through the skin.

[0075] Various embodiments of the technology of the present invention include an extensible class of devices with soft form fit, which maximize detectable signals, enable multi-mode operation such as electrophysiological recording and neurocognitive interaction, and can be used on almost any part of the body, particularly devices configured to perform mechanophonic recording from the skin.

[0076] Experimental and computational studies have highlighted the important role of low effective elastic modulus and low areal mass density for effective operation in this type of measurement mode on the skin. Demonstrations involving vibrational cardiac measurements and heart murmur detection in a series of heart patients have exemplified the usefulness in advanced clinical diagnosis. Monitoring of pump thrombosis in assistive artificial hearts provides an example of the characterization of mechanical implants. Tracking the swallowing trends of healthy subjects with respect to the respiratory cycle leads to a new understanding of natural body behavior. Measuring movement, listening to the sounds of the respiratory, circulatory, and digestive systems, and even typical movements such as scratching with a single device simultaneously provide a completely new dimension to pathological diagnosis. Speech recognition and human-machine interface are representatives of additional proven applications. These and other possibilities suggest extensive use for soft skin-integrated digital technologies capable of capturing acoustic signals from the human body. A physical feedback system integrated with the sensor adds additional therapeutic functions to the device.

[0077] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the technology of the present invention. However, it will be apparent to one skilled in the art that embodiments of the technology of the present invention may be practiced without some of these specific details. For convenience, embodiments of the technology of the present invention are described with respect to cardiovascular diagnosis, respiration and swallowing correlation, and scratching intensity detection, but the technology of the present invention also provides many other applications in a wide variety of potential technical fields.

[0078] The technology introduced in this specification can be embodied as dedicated hardware (e.g., circuitry), as programmable circuitry appropriately programmed by software and / or firmware, or as a combination of dedicated and programmable circuitry. Accordingly, embodiments can include a machine-readable medium storing instructions that can be used to program a computer (or other electronic device) to execute a process. The machine-readable medium can include, but is not limited to, floppy disks, optical disks, compact disk read-only memory (CD-ROM), magneto-optical disks, ROM, random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic or optical cards, flash memory, or other types of media / machine-readable media suitable for storing electronic instructions.

[0079] "In some embodiments", "according to some embodiments", "in the illustrated embodiments", "in other embodiments", and similar phrases generally mean that the particular feature, structure, or characteristic following the phrase is included in at least one implementation of the technology of the present invention and may be included in multiple implementations. In addition, such phrases do not necessarily refer to the same embodiment or different embodiments.

[0080] FIG. 1 illustrates an exploded view of an example of a medical device 10, such as an epidermal mechanacoustic electrophysiological measurement device, according to some embodiments of the technology of the present invention.

[0081] In this exemplary embodiment, the epidermal mechanacoustic electrophysiological measurement device includes a lower elastomer shell 20, a silicone strain isolation layer 30, an extensible interconnect 40, an electronic device 50 such as a microprocessor, a vibration motor, a resistor, a capacitor, and the like, and an upper elastomer shell 60.

[0082] Figure 2 shows an example of a wearable (e.g., epidermally mounted) electromechanical acoustical electrophysiological measurement device according to some embodiments of the technology of the present invention. This exemplary assembly includes the exemplary epidermally mounted electromechanical acoustical electrophysiological measurement device of FIG. 1, along with a stimulation device such as a vibration motor.

[0083] The technology of the present invention utilizes the most advanced concepts in flexible and stretchable electronics to enable soft form-conformable integration with the skin without the need to be wired to a device, providing different types of electromechanical acoustical electrophysiological sensing platforms. This technology enables accurate recording of physiological vital signals in a way that avoids many of the limitations of prior art (e.g., heavy and bulky packages) due to the freedom of the application environment. The electromechanical acoustical modality includes a miniaturized low-power accelerometer with high sensitivity (16384 LSB / g) and a wide frequency band (1600 Hz), where the functional limitations can be enhanced. The soft strain isolation packaging assembly shows other exemplary features of these stretchable systems, along with electronics for electrophysiological recording and an active feedback system. Exemplary embodiments of the technology of the present invention have a mass of 300 mg (or less than 600 mg, or between 100 mg and 500 mg), a thickness of 4 mm (or between about 3 mm and 5 mm), and an effective modulus of elasticity of 100 kPa (in the x and y directions) (or between about 50 kPa and 200 kPa), which correspond to values on the lower order than previously reported. In this way, any of the medical devices provided herein can be described as having form-conformability, including form-conformability to the user's skin. Such physical device parameters are not overly form-incompatible and can be worn over long periods of time.

[0084] Exemplary embodiments of the technology of the present invention provide a substantially wireless form factor capable of transferring, communicating, and powering wirelessly, capturing signals associated with breathing, swallowing, and vocalization, in a format that can contact substantially any region of the body, including the curved portion of the neck, resulting in a qualitative improvement in measurement capabilities and wearability. The following description and figures illustrate the characteristics of this technology, demonstrating its usefulness in a wide range of examples, from customizable applications from human studies on patients to personal health monitoring / training devices.

[0085] Certain data shows simultaneous recordings of walking, breathing, heart activity, respiratory cycle, and swallowing. Also, the vibroacoustic sounds of a ventricular assist device (VAD) (i.e., a device used to enhance failing myocardial function, which is often exacerbated by device thrombosis) are captured and can be used to detect pump thrombosis or device malfunction.

[0086] In addition, there are applications of speech recognition and classification for human-machine interfaces in a mode that captures laryngeal vibrations without interference from ambient noise. Basic research on the biocompatibility of the skin contact surface and the mechanical properties and fundamental aspects of the contact surface bonding provides additional insights into the operation of the technology of the present invention.

[0087] Also, the function of the device that interacts with the patient through the stimulation function integrated in the sensor enables this device to be a therapeutic device. By providing a wireless form factor and devices for personal and even clinical use, large amounts of data are collected. Through machine learning, the device can utilize the stimulation not only as an output based on a scheduled time point but also as an input for the study of mechanical acoustic signals related to physiological responses.

[0088] Figure 3 shows a device cross-section of an example of a medical device, including a wearable epidermal mechanophono-electrophysiological measurement / therapy device according to some embodiments of the technology of the present invention that includes thickness and modulus of elasticity information.

[0089] Referring to Figure 4, each layer of an exemplary epidermal mechanophono-electrophysiological measurement / therapy device will be described in further detail. The lower elastomer shell includes a 100 μm layer of Sylgard having a modulus of elasticity of 100 kPa. The silicone gel layer between the device and the shell includes a 50 μm layer of Sylgard gel having a modulus of elasticity of 5 kPa. The stretchable interconnect includes a bilayer of meandering copper traces 18 μm thick, encapsulated between two 12 μm layers of polyimide (PI) each having a modulus of elasticity of 2.5 GPa. The electronic device is adhered to the stretchable interconnect and then covered with an upper elastomer shell, and includes a 100 μm layer of Sylgard that includes an air pocket between the electronics and the upper elastomer shell.

[0090] The manufacturing process involves five parts: (i) production of a flexible PCB (fPCB) device platform, (ii) chip bonding onto the fPCB device platform, (iii) casting the upper and lower elastomer shells from a mold, (iv) layering the Sylgard gel, and (v) bonding the upper elastomer shell and the lower elastomer shell.

[0091] Next, the processing process will be described in more detail. (i) In a photolithography and metal etching process, or a laser cutting process, a pattern of interconnects is defined in the copper. A spin coating and curing process generates a uniform layer of PI on the resulting pattern. Photolithography and reactive ion etching (RIE, Nordson MARCH) define the upper, middle, and lower layers of the PI in a geometry that matches the geometry of the interconnects. (ii) In a chip bonding process, the electronic components necessary to operate the device are assembled. (iii) A pair of concave and convex molds for each of the upper and lower elastomer shells defines the shape of the outer structure of the device. (iv) The concave region within the lower shell contains a layer of Sylgard gel for both the purpose of adhesion and strain insulation of the device platform. (v) By bonding the curved thin upper elastomer membrane shell to the flat lower elastomer shell, the electronic components are packaged together with air pockets.

[0092] Figure 5 illustrates a sensing circuit diagram of an example of an epidermal mechanophono-electrophysiological measurement / therapy device according to some embodiments of the technology of the present invention.

[0093] The sensing circuit includes a mechanophone sensor (BMI160, Bosch), a coin motor, and a Bluetooth-compatible microcontroller (nRF52, Nordic Semiconductor). The sensor has a frequency band (1600 Hz) that lies between various target respiratory, cardiac, scratching, and vocal cord movement and sounds. Additional sensors within the platform may include, but are not limited to, an on-board microphone, an ECG, a pulse oximeter, a vibration motor, a flow sensor, and a pressure sensor.

[0094] Figure 6 illustrates a charging circuit diagram of an example of an epidermal mechanophono-electrophysiological measurement / therapy device according to some embodiments of the technology of the present invention.

[0095] The wireless charging circuit includes an induction coil, a full-wave rectifier (HSMS-2818, Broadcom), a regulator (LP2985-N, Texas Instruments), a charging IC (BQ2057, Texas Instruments), and a PNP transistor (BF550, SIEMENS).

[0096] The device can also be coupled to external components, such as an external mouthpiece for measuring lung volume. The mouthpiece houses a diaphragm. Its deflection is associated with a specific pressure. The amount of deflection of the membrane using the device defines the amount of air volume transferred during the exhalation period.

[0097] For healthy adults, the first heart sound (S1) and the second heart sound (S2) have acoustic frequencies of 10 to 180 Hz and 50 to 250 Hz, respectively. The vibration frequency of the human vocal cords is in the range of 90 to 2000 Hz. The average fundamental frequency is approximately 116 Hz (male, average age 19.5 years), approximately 217 Hz (female, average age 19.5 years), and approximately 226 Hz (children, 9 to 11 years) during conversation. To enable the detection of heart operation and speech, the cut-off frequency of the low-pass filter is 500 Hz. A high-pass filter (cut-off frequency, 15 Hz) removes movement artifacts.

[0098] The low-frequency respiratory cycle (0.1 - 0.5 Hz), the cardiac cycle (0.5 - 3 Hz), and the snoring signal (3 - 500 Hz) have their respective unique frequency bands. By passing these specific frequency bands for each of these biomarkers, the filter removes high-frequency noise and low-frequency movement artifacts.

[0099] Apart from the frequency band of the present invention, many other mechanical and acoustic biosignals are measured from the raw data (e.g., scratching movement (1 - 10 Hz), scratching sound (15 - 150 Hz)).

[0100] Figures 8 to 10 show examples of epidermal mechanophono-electrophysiological measurements of vocal cords (e.g., conversation) and swallowing by some processing algorithms of the technology of the present invention including signal filtering and automatic analysis.

[0101] Without limitation, signal processing algorithms including Shannon energy conversion, moving average smoothing, Savitsky-Golay smoothing, and automatic thresholding set up faster analysis of large amounts of data.

[0102] General signal processing involves seven parts: (i) collection of raw data, (ii) filtering of data, (iii) normalization of filtered data, (iv) energy conversion of data, (v) smoothing of data and creation of an envelope, (vi) threshold setting, (vii) masking of data.

[0103] Next, signal processing will be described in more detail. (i) By capturing raw acceleration signals without using an analog filter, a plurality of signals that overlap each other are provided. (ii) By filtering the data in various bands of the frequency spectrum, the raw signal is segmented into multiple layers of signals specific to different biomarkers. (iii) Normalization of each filtered data enables proper comparison of each signal. (iv) By converting the normalized filtered signal, the signal is simplified to all positive values. When observing signals higher than the DC frequency region, the signal fluctuates across the zero reference line. Without limitation, for information related to the duration of conversation, cough, or swallowing, true measurement is possible by energy interpretation of the signal. (v) Smoothing the data includes the normalized filtered signal and represents the measured signal in a simpler way. (vi) By using a histogram or an automatic threshold setting algorithm, specific activities can be determined and classified. (vii) Using the picked threshold, the number of samples associated with the activity is determined by the mask.

[0104] The wavelet transform method simply extracts signals related to specific activities such as conversation, laughter, coughing, or swallowing. Using the scale and time information from the transform, it classifies specific characteristics of swallowing in a particular type of diet amount, as well as the types of communication and interaction.

[0105] Supervised machine learning of labeled signals involves two parts: (i) labeling the activities to the signals by timestamping the data at the time when an event occurred, (ii) accompanied by a multi-class classification method including, but not limited to, the random forest method.

[0106] Such classification generates classifications for specific incidents of the breathing pattern (inhalation, exhalation), swallowing specific types of food (fluids, solids), and for the human-machine interface for vocal cord vibration recognition.

[0107] Next, the human interface is described in more detail. The coin cell learns the breathing cycle and swallowing incident trends of healthy individuals and is activated to give an appropriate signal for the swallowing time based on the breathing cycle for people with swallowing difficulties. Also, it measures the movement and frequency of the vocal cords and learns the characters and words associated with specific vibrations.

[0108] Unsupervised learning is utilized in subjective studies including a social meter. This includes dimensionality reduction methods such as Latent Dirichlet to obtain predictors. Then, the clustering method includes, but is not limited to, k-mode, and DBSCAN classifies specific groups of people who share similar behavior of the signals.

[0109] Reinforcement learning seeks the correlation of the clinical outcomes of the treatment given by the device's user interface. The implementation of reinforcement learning is carried out towards the end of the set of classification and preliminary studies.

[0110] FIG. 5 illustrates a sensing circuit diagram of an example of an epidermal mechanoacoustic electrophysiological measurement / therapy device according to some embodiments of the technology of the present invention.

[0111] The system may employ any of a variety of bidirectional communication systems, including those compliant with the Bluetooth® standard, to connect to any standard smartphone (FIG. 19), tablet, or laptop. This is a secure user interface for both consumers and researchers. This data measurement is HIPAA-compliant for data transfer and cloud storage—we already use Box® as a HIPAA-compliant storage platform for our wireless sensors. Further signal analysis operations can enable the classification of other relevant behaviors for individuals with AD, such as personal hygiene activities (brushing teeth), housework, or driving. This signal processing and further machine learning based on the sensor output can be deployed on either the device itself, the smartphone, or a cloud-based system.

[0112] The on-board memory provides maximum freedom in a wireless environment even when there is no user interface machine linked to the device for data streaming or storage.

[0113] Beyond the use of conventional adhesives, we propose a novel skin device interface incorporating an adhesive that can withstand continuous wear for up to two weeks. Instead of requiring the user to adhere and fully remove the sensor to the skin, particularly skin on the neck that is prone to damage, our device can be attached and detached using a magnet. Other coupling mechanisms may involve buttons, clasps, hooks, and loop connections. The adhesives that adhere to the skin vary by type (e.g., acrylic, hydrogel, etc.) and can be optimized for the desired length of skin adhesion (FIG. 7).

[0114] Wireless functionality:

[0115] Communication with a user interface machine that displays, stores, and analyzes data is generally known. Here, in contrast, we present sensor technology that has an on-board processor, data storage, and communicates with a user interface via a wireless protocol such as Bluetooth® or, in some embodiments, an ultra-wideband or narrowband communication protocol that can optionally perform secure transmission. In this way, the device can be utilized in a natural setting without the need for an external power source.

[0116] The device can also be powered by inductive coupling and perform data communication and / or data transfer via a Near Field Communication (NFC) protocol. When the user is utilizing the device within an enclosed environment such as a bed during sleep or in a hospital environment, power and data transmission can be performed via an inductive coil that resonates at 13.56 MHz. This enables continuous measurements without the need for an on-board battery or an external power source.

[0117] The wireless battery charging platform enables the use of a fully encapsulated device that isolates the electronic device from the surroundings, protecting it from substances that would otherwise damage the sensor. The encapsulation layer is made from a thin film of a polymer or elastomer such as silicone elastomer (Silbione RTV 4420). Such an encapsulation layer is significantly less permeable compared to polydimethylsiloxane and Ecoflex as described in the prior art.

[0118] Advanced signal processing

[0119] Digital Filter Processing: Digital filters of both types, (finite impulse response) FIR and infinite impulse response (IIR), are used as appropriate. When a specific time window is automatically selected within a region with a high signal-to-noise ratio, a specific frequency band is selected to reduce the effects of artifacts and noise and maximize the signal of interest.

[0120] Algorithms for Signal-Specific Analysis: One method involves processing the filtered signal in the time domain. When the signal of interest is filtered in an appropriate frequency band, specific events of interest (e.g., conversation vs. cough vs. scratch) are more appropriately revealed from the raw output of the acoustic mechanical sensor. By using the energy information generated from the acceleration of the sensor, information such as the duration of discrete events or the number or frequency of events is more appropriately calculated. Another processing technique of our system uses power frequency spectrum analysis, where the power distribution of each frequency component is evaluated. This enables the derivation of additional information from the raw signal (e.g., pitch from audio).

[0121] Machine Learning

[0122] Supervised Learning: Supervised machine learning of labeled signals involves two parts: (i) labeling the activity to the signal by timestamping the data at the time when the event occurred, and (ii) involving a multi-class classification method including, but not limited to, the random forest method. Such classification generates classifications for specific incidents of breathing patterns (inhalation, exhalation), swallowing specific types of food (fluids, solids), and for human-machine interfaces for vocal cord vibration recognition.

[0123] For example, by using the scale and time information from the conversion, we can classify specific characteristics of swallowing related to the food content eaten (e.g., thin liquids like water, thick liquids, soft foods, or normal foods) through supervised machine learning. This process does not require the same degree of time or frequency ambiguity as the fast Fourier transform.

[0124] Next, the human interface will be described in more detail. The coin cell is activated to give an appropriate swallowing time cue based on the respiratory cycle for people who have lost the ability to learn the trends of the respiratory cycle and swallowing incidents of healthy individuals and measure the time to swallow along with breathing. Also, the sensor measures the movement and frequency of the vocal cords and learns the characters and words associated with each specific signal.

[0125] Unsupervised learning: This is performed without labeled signal input. In the case of the wearable social interaction meter, we adopt unsupervised learning. This includes dimensionality reduction methods such as Latent Dirichlet to obtain features related to quantifying social interaction. This includes features of voice (tone, pitch), physical activity, sleep quality, and conversation time. Then, clustering methods (e.g., k-mode and DBSCAN) classify specific groups of signals into categories.

[0126] Reinforcement learning: This involves the sensor system learning the effect of tactile stimuli on swallowing and then measuring the actual swallowing events along with breathing. This enables the system to perform automatic adjustment and calibration to ensure that the measured swallowing events correspond to the ideal timing within the respiratory cycle.

[0127] Personalized "body" biomarkers

[0128] By combining high-fidelity sensing, signal processing, and machine learning, it becomes possible to create novel metrics that can serve as physical biomarkers for health and well-being. For example, the ability to quantify spontaneous swallowing during the day has already been shown to be an independent measure of swallowing dysfunction. Thus, the sensors provided herein can be used to calculate a score of swallowing function that is sensitive to small but clinically meaningful changes in the patient's natural environment.

[0129] The timing of swallowing in relation to the respiratory cycle (inhalation, exhalation) is important in avoiding problems such as aspiration, which can lead to choking or pneumonia. The ability to time swallowing is largely under involuntary control that leads to coordinated efforts between breathing and swallowing. However, in diseases such as stroke or head / neck cancer where radiation is administered, this coordination is lost. Then, our sensors may also be able to quantify swallowing events in the context of the respiratory cycle and provide a measure of "safe swallowing". The social interaction score can also be created via signal processing and machine learning to create an overall score of social activities. This can be used as a threshold to involve caregivers or loved ones in enhancing daily social interactions when the baseline threshold is not met. These are examples of how novel metrics can be derived from the sensor system to enable patient behavior changes or clinician and caregiver interventions.

[0130] Therapeutic wearable sensors

[0131] The present disclosure has advanced features presented for sensor systems useful for therapeutic purposes. Conventional research has focused only on diagnostic applications.

[0132] Two examples of therapeutic uses are described herein. First, the timing of safe swallowing makes it possible to prevent dangerous events such as aspiration, which can lead to choking, pneumonia, or even death. Our sensor can be converted into a therapeutic swallow primer that triggers user swallowing based on sensing the start of inhalation and exhalation of the respiratory cycle. This makes it possible for the sensor to trigger swallowing during a safer part of the respiratory cycle (typically in mid- to late-exhalation). Additionally, machine learning algorithms can be used to optimize the timing of the trigger within the feedback loop. For example, the sensor can track both the respiratory rate and swallowing behavior. A trigger is issued that is timed to lead to a swallowing event within an ideal respiratory timing window. In this embodiment, to trigger swallowing, we propose a vibration motor that provides direct tactile feedback. Other trigger mechanisms can include visual notifications (e.g., light-emitting diodes), electrical impulses (e.g., electrodes), and temperature notifications (e.g., thermistors). In some embodiments, for example, the system provides one or more parameters detected by a sensor as a basis for input to a feedback loop with a signal generation device component that provides one or more signals to a subject (e.g., a patient), such as a vibration signal (e.g., an electromechanical motor), as well as an electrical signal, a thermal signal (e.g., a heating device), a visual signal (LED or full graphic user interface), an audio signal (e.g., an audible sound), and / or a chemical signal (elution of a skin-perceivable compound such as menthol or capsaicin). In such embodiments, the feedback loop is executed for a specified time interval based on measurements by the sensor, and the one or more signals are provided to the subject periodically or repeatedly based on the sensed parameters. The feedback approach can be implemented using machine learning, for example, to provide an individualized response based on measured parameters specific to a given subject.

[0133] In one embodiment, somatic perception is achieved by an enclosed sensing / stimulation circuit that is enabled through real-time processing, and the feedback loop may be of the tactile, electro-tactile, thermal, visual, audio, chemical, etc. variety. In one embodiment, the sensor can also operate within a network, and its anatomically separated sensing functions allow for more information, and with one sensor, measure (e.g., on the suprasternal notch), but trigger feedback with a sensor elsewhere that is relatively hidden (e.g., the chest).

[0134] A second treatment modality is for the sensor to operate as a wearable respiratory therapy system. In conditions such as chronic obstructive pulmonary disease (COPD), dyspnea or shortness of breath is a common symptom that has a major impact on quality of life. Respiratory therapy is a commonly deployed method of training subjects to control their breathing (both timing and respiratory effort), increase lung aeration, and improve respiratory muscle strength recovery. Our sensor can be used to track inspiratory and expiratory effort and duration. Based on these measurements, tactile feedback (or visual feedback via an LED) can potentially train the user to extend or shorten inhalation or exhalation to maximize airflow. Respiratory organ inhalation effort can be triggered similarly. For example, when a specific inhalation effort is achieved, a threshold is passed and tactile vibration is triggered. This tactile feedback can also be triggered after a specific length of time has reached for the inhalation effort. Thus, the sensor can track airflow through the larynx and use this as a way to perform somatic respiratory training. In another embodiment, the sensor itself can be fitted with an external mouthpiece (Figs. 11 - 13), operate as a wireless spirometer during a training session, and then be returned to the larynx for normal sensing.

[0135] Another treatment modality involves evaluating the patient with respect to positioning the subject's body, or a part thereof, to prevent injury and / or support a given treatment outcome, and optionally treating, using the sensor system of the present invention. Physical injury can occur when the limbs move and shift to significant deformation points. This can occur by way of example, for instance, injuring a limb (e.g., the shoulder) which then has to be placed in a relatively fixed state or restricted to a safe range of movement, e.g., to support healing or treatment. During sleep or daily activities, the subject may inadvertently move this limb to a position of deformation that would cause injury. In these embodiments, the sensors of the present invention are used as a sentinel system to evaluate the position within the space of the limb and provide a notification (any of tactile, sound, visual, heat, chemical, electrical, etc.) to alert the user and / or caregiver.

[0136] Medical Use Case

[0137] Sleep Medicine: A wireless sleep tracker capable of measuring time to sleep, wake-up time after sleep onset, sleep duration, respiratory rate, heart rate, pulse oxygen concentration, inspiratory time, expiratory time, snoring time, respiratory effort, and body movement. Skin close coupling over the suprasternal notch enables capturing respiratory rate and heart rate given proximity to the carotid artery and trachea. As an example, a sleep medicine application can go beyond simply measuring vital signs of sleep or provide metrics of sleep quality. The sensor system of the present invention also supports applications for improving sleep. Examples of applications in this aspect include the following. 1. During sleep, the sensor can detect that the subject has changed vital signs (abnormal vital signs) which can include an increase or decrease in heart rate, cessation of respiratory rate, decrease in pulse oxygen concentration, or a combination of snoring (abnormal breathing sounds). This then triggers a feedback mechanism such as vibration, audio, visual, electrical, or heat that causes the individual to shift position or become aware / wake up. 2. In the case of an injury or postoperative situation, excessive movement or range of motion can lead to deterioration of the injury, especially during unconscious periods such as sleep. The acoustic mechanical sensor can detect a limb in space, either alone or within a network of multiple spatially separated sensors, and trigger a feedback mechanism (e.g., vibration, audio, visual, etc.) to notify the user to return to a safe position or avoid deterioration of the injury. 3. When it is difficult to quantify symptoms (e.g., pain and itching), the quality of sleep is a surrogate marker for the severity of these symptoms. The sensor can thus be used to indirectly assess symptoms (e.g., pain or discomfort) by measuring the quality of sleep. Another novel feature of this aspect of the invention is to use the sensor over time to repeat sleep positions and / or movements. This enables the use of an accelerometer on the sensor to reconstruct movement and body position. This enables direct video feedback to be sent to the user and visually associate a body position with vital signs or respiratory sounds (e.g., snoring). Figure 41 presents exemplary sensor data for using the inventor's multimode sensor for sleep therapy, for example, for determining the correlation between body position and vital signs and / or respiratory sounds.

[0138] In one embodiment, the sensor can evaluate the position in space relative to a particular limb or body configuration prone to injury (e.g., the postoperative tendon plate), and if a dangerous range of motion or position is sensed, this triggers a biofeedback signal to warn the user or cause the user to change that position to avoid sleeping on the injured arm side. The sensor system of the present invention also helps, for example, to monitor treatments related to snoring, and the detection of snoring provides vibration biofeedback that triggers a change in position.

[0139] In one embodiment, the sensor is used to repeat a video and / or visual representation of the position of a subject in space. Advantages of this aspect of the invention included that it also reduced privacy issues and data storage.

[0140] Dermatology: The ability to capture scratching behavior and distinguish it from the movement of other limbs through combining mechanical signal processing and acoustic signal processing.

[0141] Respiratory medicine: Chronic obstructive pulmonary disease (COPD) is a chronic condition characterized by recurrent lung symptoms. Our sensor can quantify important markers indicating COPD exacerbation, including cough, expectoration, wheezing, the volume of air changed during forced pulmonary exhalation, respiratory rate, heart rate, and pulse oxygen concentration. Asthma and idiopathic pulmonary fibrosis can be similarly evaluated on the same scale.

[0142] Quantification of social interaction metrics, acoustic and linguistic features of single-speaker and multi-speaker tasks: Measuring vocal conversations and vocal signals as components of social interaction is complex and requires sensors that can capture a wide range of acoustic and linguistic parameters, as well as the acoustic characteristics of the speaking environment. The sensor can quantify key parameters of social interaction related to the incoming acoustic signal, including conversation time and number of words. The recorded signal can be used to extract additional data, including vocalization features (e.g., F0, spectral peak, voice onset time, temporal features of speech), as well as linguistic conversation markers (e.g., pauses, hesitations). When worn by individual interlocutors, the sensor can capture linguistic features spanning multiple interlocutors from separately recorded signals, facilitating the analysis of interactive social interaction. By attaching to the skin along the suprasternal notch, it becomes possible to accurately quantify true user conversation time regardless of ambient conditions. Furthermore, social interaction is a complex multi-factor complex. The present disclosure enables quantification of important physical parameters (e.g., sleep quality, eating behavior, physical activity) that can potentially be combined into novel metrics for social interaction.

[0143] The sensor system of the present invention can be used to create and monitor social interaction scores and metrics, for example, using an approach based on sensor signals, feedback analysis, and / or signal transmission to a subject. Figure 40 shows a portable electronic device (e.g., a smartphone) that communicates with a sensor and is at least partly based on a validated scale and questionnaire (used in combination with psychosocial health parameters (e.g., conversation time (minutes / day), voice biomarkers (tone, pitch), interaction partners (#), GPS location information (from the smartphone)) and physical health parameters (e.g., number of steps, sleep quality, eating behavior, etc.) derived from sensor signals and / or measured characteristics), including those based on psychometric surveys, to create social interaction scores and metrics. In some embodiments, the sensor output and survey on the smartphone app are weighted to generate a social interaction score representing the subject.

[0144] The ability to monitor a wide range of acoustic and linguistic features in an ecologically valid ambient environment is important in identifying individuals at increased risk of mood disorders, individuals at risk of social isolation that can lead to an increased risk of cognitive decline, and individuals at risk of other disorders marked by early changes in speech, voice, and speech quantity / quality (e.g., among others, changes in fluidity in Alzheimer's dementia, prodromal symptoms of Huntington's disease, multiple sclerosis, and early language changes in Parkinson's disease).

[0145] Acquired neurocognitive and neuro-linguistic disorders (e.g., aphasia, cognitive communication disorders associated with neurodegenerative disorders with or without dementia, traumatic brain injury, right brain injury), acquired motor speech and fluency disorders, neurodevelopmental disorders, and childhood language disorders. The device can also be used in clinical applications when recording the volume and quality of conversations in hearing therapy / auditory rehabilitation applications. The device can also be used to monitor vocal usage patterns in users specializing in vocalization and people with medical conditions related to vocalization.

[0146] The sensor system and method of the present invention are also useful for the treatment of diseases associated with loss of muscle or nerve function, such as amyotrophic lateral sclerosis, Lambert-Eaton myasthenic syndrome, myasthenia gravis, Duchenne muscular dystrophy, etc. The sensor can be used to evaluate the functional performance of a subject, for example, by evaluating physical activity, respiratory performance, or swallowing performance in these situations.

[0147] As described above, if vocal recovery can be quantified in a wearable format that is not affected by ambient noise conditions, it will hold high value in evaluating the nature of and treatment outcomes for a number of disorders associated with dysphonia, speech disorders, language disorders, non-verbal disorders, and cognitive communication disorders. Further applications include quantifying the frequency and severity of stuttering in individuals suffering from fluency and fluency-related disorders. By attaching to the skin along the suprasternal notch, this function can be used while minimizing the stigma associated with wearing the device. Recording large amounts of data from an ecologically valid environment is important in improving clinical assessment, monitoring, and intervention options for a number of disorders.

[0148] Dysphagia and swallowing problems: Dysphagia (swallowing disorder) remains a problem across a number of medical conditions including, but not limited to, head / neck cancer, stroke, scleroderma, and dementia. From previous research findings, it has been found that the frequency of spontaneous swallowing is an independent marker of dysphagia severity. Furthermore, in hospitalized patients, the ability to determine the safety and efficiency of swallowing function is extremely important in identifying patients at risk of aspiration, optimizing nutrition, and improving diet to prevent aspiration, facilitating timely discharge, and avoiding readmission related to aspiration pneumonia. The sensor can potentially act as a screening tool to detect abnormal movements associated with dysphagia and / or potentially guide diet-related recommendations. Improvement of dysphagia through therapeutic intervention can also be tracked with the sensor. This application may be applicable to a wide range of ages from neonates to the elderly.

[0149] Stroke rehabilitation: As described, the sensor provides unique capabilities to assess speech and swallowing function, both important parameters in stroke recovery. Beyond this, the sensor can also measure walking, falls, and physical activity as a comprehensive stroke rehabilitation sensor.

[0150] Nutrition / Obesity: The preferred deployment of the sensor is via skin close coupling to the suprasternal notch. This enables quantification of swallowing and swallowing counts. As food passes through, a unique sensor signature is generated, allowing us to predict meal times and eating behavior. The mechanism of swallowing varies based on the density of the food or liquid bolus being ingested. Thus, our sensor can detect liquid versus solid ingestion. Further, our sensor can evaluate swallowing signals that can distinguish between ingestion of solid food, denser semi-liquid foods (e.g., peanut butter), or thin liquids (e.g., water). This can be useful for food intake tracking for weight loss. Other applications include evaluating food intake in individuals with eating disorders (e.g., anorexia or bulimia). Further applications include evaluating the meal time behavior of individuals who have undergone gastric bypass surgery, and the sensor can issue a warning if the individual has consumed too much food or liquid post-surgery.

[0151] Pregnant Woman / Fetal Monitoring: Currently, ECHO Doppler is the most common modality for capturing the fetal heart rate of pregnant women. However, this modality is limited in that it can be difficult to capture the fetal heart rate from obese patients. Further, the Doppler signal is frequently lost as the fetus descends during labor. Previous studies have demonstrated the potential value of mechanical acoustic sensing for fetal heart rate monitoring. Our wearable sensor system is highly convenient for this application.

[0152] Post-Surgical Surgical Monitoring of Intestinal Function: Stethoscopes are commonly used to evaluate the recovery of intestinal function after abdominal surgery. Intestinal obstruction, or failure of intestinal function recovery, is a common cause of hospitalization or delayed discharge. A sensor that can quantify the recovery of intestinal function through acoustic signal measurement would be useful in this context.

[0153] Cardiology: The stethoscope is the standard of care for diagnosis and disease monitoring. The sensors presented here show that they can continuously capture data and information derived from the stethoscope. This includes continuous assessment of abnormal heart sounds. In some cases, such as congenital heart defects, the presence of a heart murmur is extremely important for the health of the subject. The sensor system of the present invention may be for performing continuous acoustic measurements of heart function. Abnormal sounds also reflect heart valve diseases. Thus, the sensors herein can be used to track the stability or worsening of valve diseases such as aortic valve stenosis, mitral valve stenosis, mitral valve regurgitation, tricuspid valve stenosis or regurgitation, or pulmonary valve stenosis or regurgitation.

[0154] There is still no captureable non-invasive method for assessing cardiac output and left ventricular function that is specific to cardiology. Echocardiography in heart disease patients is non-invasive but requires specialized training and does not help with continuous wearable use. Non-invasive methods for continuously tracking cardiac output have high clinical value for a number of situations including congestive heart failure. Embodiments of the sensor system of the present invention can provide measures of both heart rate and stroke volume (the amount of blood pumped per beat). Cardiac output is the product of heart rate and stroke volume. This can be accomplished, for example, by evaluating the delay time between peaks with respect to heart rate. Then, the decay of the accelerometer amplitude represents the intensity of each heartbeat by measuring the displacement of the skin with each beat.

[0155] Figure 42 presents exemplary data for the use of the sensor system of the present invention for monitoring advanced physical performance metrics against cardiac output. As shown in the figure, after intense physical activity, the sensor picks up an elevated heart rate but also an elevated jolt. When the user returns to baseline, the heart rate and amplitude normalize. This is an example showing how the amplitude can be used to evaluate and correlate the amount of blood pumped with each heartbeat.

[0156] Another embodiment is in the military. Injuries due to firearms or explosions lead to the propagation of mechanical waves from the point of impact. The sensor can be used to assess the severity of such impacts as a means of non-invasively evaluating the user's gunshot impact or proximity to a blast. The sensor can also be used to assess the likelihood of injury to vital organs (e.g., placed over the heart or lungs). The sensor may be deployed directly on the user (e.g., police officer, soldier), on clothing, or on a bulletproof vest.

[0157] External modification: Any of the medical devices provided herein may have one or more external modifications, including providing access to new diagnostic and treatment functions. For example, the addition of an external mouthpiece enables the controlled release of an airflow from the user that can be measured by a sensing element (e.g., an accelerometer or microphone) within the sensor system. This enables the quantification of the airflow (volume over time) without the need for expensive equipment such as a spirometer. Critical parameters such as forced expiratory volume in one second (FEV1) can then be collected at home and the data can be transmitted and stored wirelessly. Changes in airflow parameters such as FEV1 can then be combined with other parameters such as wheezing, cough frequency, and expectoration, thereby enabling the creation of a novel metric for disease that can serve as an early warning system for deterioration.

[0158] Therapeutic Application: In respiratory diseases such as chronic obstructive pulmonary disease (COPD) or asthma, respiratory training is an important component in reducing shortness of breath (dyspnea). This includes teaching breathing techniques such as pursed-lip breathing (PLB). This involves exhaling air through tightly pursed lips and inhaling through the nose with the mouth closed. The lengths of inhalation and exhalation are also adjusted to suit the patient's individual respiratory state. The lengths of exhalation and inhalation can be adjusted according to the user's comfort. A sensor can then be deployed in a treatment modality that differentiates between mouth breathing and nasal breathing based on vibrations in the throat or changes in the airflow. The sensor can also time the lengths of inhalation and exhalation. A respiratory therapist can also set, for example, an ideal time length, and the sensor can provide tactile feedback to the patient or user when the ideal inhalation or exhalation time length is reached. Overall, the sensor can act as a "wearable" respiratory therapist that reinforces effective breathing patterns as well as techniques to improve breathing and patient symptoms, and can prevent the exacerbation of respiratory diseases. In further research, it is also possible to combine this with continuous pulse oxygen concentration.

[0159] Alzheimer's Dementia:

[0160] Alzheimer's disease (AD) affects 5.4 million Americans, with annual expenditures reaching $236 billion and a total of 18.1 billion hours of care by loved ones. First, the decline in social interaction or loneliness is an important facilitator of cognitive decline and directly increases the risk of depression in patients with AD. Second, high-quality social interaction is associated with a reduced risk of dementia in old age, providing a non-pharmacological strategy to reduce the incidence and mortality of AD. Third, changes in social interaction and conversation are potential biomarkers for the early identification of AD and disease exacerbation. The main barrier to promoting the use of social interaction in AD patients was the lack of tools that could comprehensively evaluate the quantity and quality of social interaction in the real-world environment. Rating scales for social interaction (self-report / proxy report) are subject to reporting bias and lack sensitivity. Smartphones have limitations in sensing accuracy, there is variation in sensor performance among manufacturers, they cannot measure important parameters (e.g., meal-time behavior), and voice fidelity decreases in noisy ambient environments. Devices for measuring social interaction have been reported in the literature, but these systems are bulky, heavy, not continuously usable, and lack the comprehensive sensing capabilities necessary to adequately capture the entire spectrum of parameters in social interaction. Furthermore, these systems have not been rigorously validated in the older generation with low technological literacy.

[0161] To advance the care of patients suffering from AD, there is a need for non-invasive remote monitoring technology acceptable to wearers that can track a wide range of parameters related to social interactions spanning the mental, social, and physical health domains. To address this, we propose the development of a first integrated wearable sensor capable of continuously measuring critical parameters of social interaction within a network environment that minimizes user stigma through an optimized wearable form factor. The current prototype incorporates a high-frequency 3-axis accelerometer capable of measuring speech, physiological parameters (e.g., heart rate, heart rate variability), sleep quality, meal-time activity, and physical activity (e.g., step count) in an ecologically valid environment through additional signal analytics. The sensor is completely enclosed in medical-grade silicone less than 4 mm thick, and the bending and modulus of elasticity parameters are several orders of magnitude lower compared to previously reported technologies. The sensor adhered to the suprasternal notch with a low-irritation adhesive enables a discreet skin-to-skin connection and allows us to collect mechanical acoustic signals that are invisible from wristband-based sensors and smartphones in our technology. This includes the ability to measure respiratory rate, heart rate, swallowing rate, and conversation time with an accuracy not achievable by other technologies. We propose the development of a fully integrated social interaction sensor with additional features, rationally designed using inputs from AD patients and their caregivers, and validated against clinically standard devices with more advanced signal processing capabilities. The estimated cost per sensor is less than $25, and the total addressable annual market size is $288 million per year. Goal 1 is to add an integrated microphone to our existing wearable flexible sensor platform that already has a high-frequency 3-axis accelerometer capable of continuous communication via Bluetooth®. The success criteria are the successful completion of bench tests showing high-fidelity audio capture from the full range of inputs from 38 dB (whisper) to 128 dB (concert), and the successful wireless data transfer to a HIPAA-secure database. A user interface is provided to researchers to enable more advanced analytics.Additional parameters such as pitch, tone, under-talking time, over-talking time, and number of turns of the conversation partner can be extracted.

[0162] The development of the first true wearable social interaction sensor capable of continuous, multimodal, and real-world sensing is an important innovation for those including the AD research community as an observation tool and patients and their caregivers as an intervention tool. By accurately, reliably, and separately capturing a number of parameters related to social interaction, we can detect social isolation in individuals suffering from AD, promote further participation, and provide subtle feedback that reduces loneliness with our sensor.

[0163] Alzheimer's disease (AD) affects 5.4 million Americans and is the sixth leading cause of death, increasing 71% from 2000 to 2013. Annual expenditures reach $236 billion, and a total of 18.1 billion hours of care are provided by loved ones. There are limited therapies (behavioral and pharmaceutical) for AD, and many candidates have failed in late-stage clinical trials. Advances in next-generation AD therapies rely on high-quality clinical measurement tools to detect novel, ecologically valid, and sensitive biophysical markers of cognitive decline. As the search for new therapies continues, alternative strategies are needed soon to modify the course of the disease by addressing the contributing factors and outcomes of social interactions associated with AD. Central to these strategies is the recognition that loneliness and social isolation are significant threats to the health of older adults, leading to self-harm, self-neglect, cognitive impairment, physical disability, and increased mortality. Addressing modifiable risk factors, particularly social isolation, is a major policy goal for public health agencies and governments to reduce the enormous burden of AD. In numerous rigorous studies, the protective effect of high-quality social interactions has been demonstrated in mitigating the harmful effects of AD and optimizing healthy aging (mental, physical, and social). Difficulties in dialogue, such as interruptions in the exchange of messages between conversational partners, or increased time to convey and understand messages, emerge early in AD, resulting in increased social isolation, which in turn accelerates cognitive decline and significantly increases the burden on caregivers in AD. In addition, since the natural course of AD is characterized by periods of disease stability and emphasized by periods of rapid functional decline, measuring changes in social interactions longitudinally facilitates a deeper understanding of the natural progression of AD. Behaviors of dialogue and social interaction extracted from real-world communication are promising next-generation biophysical markers of cognitive change and treatment outcomes. Despite their significant clinical importance, changes in dialogue ability and social interaction in the real-world context are not easily evaluated in clinical visits. Clinicians must rely on patient and proxy reports, which are vulnerable to inaccuracies and reporting bias.Developing reliable, non-invasive, user-acceptable wearable technologies for collecting dialogue and social interaction data would be highly beneficial for the field. Currently, there are no commercially available technologies that can measure a wide range of relevant parameters regarding social interaction in form factors that enable long-term real-world use for individuals with AD. Thus, any of the devices and methods provided herein may be used in AD assessment, diagnosis, and treatment.

[0164] Parameters of importance to social interaction (physical, mental, and social): Social interaction is a complex construct. Previous studies have linked social interaction to cognitive function, mental health, sleep quality, physical activity, social activity, eating behavior, and language use in dementia. Thus, assessment of social interaction requires tools that can collect multiple behaviors within a natural environment.

[0165] (1) Physical function: Physical activity, sleep quality, and mobility areas are all related to social interaction.

[0166] (2) Vocal characteristics: Speech rate, conversation time, voice pitch, tone, pauses, intensity, comprehensibility, and rhythm, which reflect aspects of mood and even sources of conversation breakdown.

[0167] (3) Meal-time behavior: Eating frequency, overeating, or anorexia, using swallowing frequency counts.

[0168] (4) Dialogue and language behavior from people with dementia and their conversational partners: Number of alternations, duration of alternations, talking too much (when one partner talks more than the other), conversation breakdown and repair, topic maintenance, and word-finding difficulty.

[0169] Evaluating the collection of adult social interactions typically involves psychometric surveys of self-report and proxy-report (e.g., Friendship Scale, Yale Physical Activity Scale, SF-36). However, this method of data collection is often biased, insensitive, and frequently difficult to use with individuals with cognitive and language impairments. Furthermore, psychometric survey tools alone do not reflect changes in conversational ability, which are often at the root of social interaction changes in aging and dementia. Therefore, survey tools are best considered in conjunction with an objective measure of conversational changes in real-world settings. Smartphones with custom mobile apps have been previously considered for this purpose. Older adults have been shown to be the least likely to use smartphones and have low technological literacy. However, smartphones have several advantages, including wide availability, on-board sensors (e.g., accelerometers, microphones), and wireless communication capabilities. Previous studies have shown that data collected on smartphones (text messages and phone use) correlate with traditional psychometric mood assessments, but the overall accuracy of these smartphone-based measures remains poor (<66%). There is strong evidence that voice, conversation, and language features are sensitive markers of changes in mood, cognitive language, and social interaction, but smartphone recordings are of insufficient quality for clinical monitoring of these behaviors, particularly in real-world situations with high ambient noise. Furthermore, smartphone-based accelerometers for monitoring physical activity and sleep have accuracy issues. Many available smartphone platforms have different hardware specifications and cannot normalize data inputs. Commercially available systems worn on the wrist (e.g., FitBit®) are mostly limited to tracking steps and therefore do not capture range-of-motion data. Remote data recording systems such as LENA provide more advanced signal processing, but they have only been tested in parent-child social interactions, are limited to voice collection, and have not demonstrated the ability to capture important speech features in AD.For example, measuring "overtalking" time is a major cause of interrupting conversations and eliciting negative attitudes shown by healthy conversation partners, and is important in the context of AD. The most advanced systems reported in the literature for social interaction include both an accelerometer and a microphone within a device attached by a strap. However, the systems are bulky and cannot be worn daily, causing the problem of user stigma and requiring quiet ambient conditions for operation. Furthermore, these systems cannot collect relevant physiological parameters (e.g., heart rate, heart rate variability, respiratory rate) for social interaction. Since mealtime behavior is related to changes in mental health and social interaction, a number of groups have reported sensors worn on the wrist and neck for measuring hand movement and chewing / swallowing behavior, but have only reported moderate accuracy. These eating behavior sensors lack the ability to collect other relevant parameters such as speech, physical activity, or physiological metrics. There is an immediate need for a technology that can provide an objective, comprehensive, and unobtrusive measurement that captures a wide range of parameters important for social interaction in individuals with AD.

[0170] Recent advances in materials science and mechanical structural principles have enabled a new class of stretchable, bendable, and soft electronic devices. These systems match the elastic modulus of the skin, bond to any curved surface of the body, and enable mechanically invisible use for up to two weeks. Similar to temporary tattoos, the close bond with the skin enables physiological measurements with data fidelity comparable to FDA-approved medical devices. In particular, mechanical acoustic signals have high clinical relevance. The propagation of mechanical waves through the body, measurable through the skin, reflects various physiological processes including the opening and closing of heart valves in the chest, the vibration of vocal cords in the neck, and swallowing. Therefore, wearable sensors closely connected to the skin are key in sensing these biosignals and realizing a wide range of sensing possibilities. This is in contrast to external accelerometers incorporated into smartphones and wrist-based traditional "wearables" that are limited to measuring only basic physical activity metrics (e.g., step count). What is described is the use of high-frequency accelerometers bonded to the skin to sense a wide range of parameters related to the assessment of social interactions.

[0171] We present a novel mechanoacoustic sensing platform (Figure 19) that incorporates state-of-the-art concepts into a stretchable electronic device adhered to the suprasternal notch, capable of continuously measuring, storing, and analyzing important parameters of social interaction in a distributed network. The mechanoacoustic system incorporates filamentous serpentine copper traces (3 μm) placed between polyimide encapsulation layers that connect small chip components. The central sensing unit can be a high-frequency 3-axis accelerometer capable of capturing high-frequency signals up to 1600 Hz (e.g., speech) from low-frequency signals of fractions of 1 Hz (e.g., step count, respiratory rate), all operating at ultra-low power consumption. This ability to sample high-frequency signals is in stark contrast to most commercially available accelerometer-based sensors (e.g., Actigraphy / FitBit®) that operate only in the low-frequency band. The resulting device has a mass of 213.6 g, a thickness of 4 mm, effective elastic moduli of 31.8 kPa (x-axis) and 31.1 kPa (y-axis), and bending rigidities of 1.02 μNm (x-axis) and 0.94 μNm (y-axis), corresponding to values several orders of magnitude lower than previously reported values and enabling long-term wear. The entire system floats within an ultra-low elastic modulus elastomer core (Silbione RT Gel). Another thin layer of ultra-low elastic modulus silicone (Ecoflex) acts as a shell that reduces the contact stress on the skin surface, maximizing user comfort and water protection.

[0172] This platform provides a system that employs a high-frequency accelerometer closely fitted to the skin enabled for use by a low-elasticity structure allowing multimode operation and robust adhesion. The system can communicate with a smartphone using Bluetooth®, where the smartphone mainly acts as a visual display and additional data storage unit. The current system can also interact with the sensors of a smartphone, including a microphone, in an additional manner if required.

[0173] Software and signal analytics for novel data collection related to social interaction: Provided is a series of signal processing functions with a band-pass filter for bioacoustic machines within a selected range within the bandwidth of an accelerometer, which enables multimodal sensing of a number of biomarkers from step count and respiration (low band of the spectrum) to swallowing (mid-band of the spectrum), and speech (high band of the spectrum). Close skin coupling enables highly sensitive measurements with a high signal-to-noise ratio. This enables the sensor to measure both subtle mechanical activities and acoustic biosignals below the threshold for audible levels by conventional microphones. We demonstrate that we can detect words (left, right, up, down) by using our acoustic machine sensor to distinguish its time-frequency characteristics from vocal cord vibrations related to the creation of each word. This ability can then be used by the sensor to control a computer game (e.g., Pac-Man). In the case of calculating conversation time, the bioacoustic signal is filtered with an eighth-order Butterworth filter. The filtered signal then passes through a root mean square threshold. The energy of the signal is then interrogated with a 50 millisecond window that enables the determination of conversation time and number of words. A short-time Fourier transform defines the spectrogram of the data. The results are averaged using principal component analysis and dimensionally reduced to form a feature vector. Finally, the feature vector is classified using linear discriminant analysis. We demonstrate the functionality of a system that can identify specific interlocutors and quantify conversation time in a group of three stroke survivors with aphasia and one speech therapist (Figure 21).

[0174] Another important advantage is that it can synchronously combine the collection of acoustic and mechanical signals to enable the capture of conversation time specific to the wearer in both noisy and quiet ambient conditions. Compared with the microphone of a smartphone (iPhone (registered trademark) 6, Apple, Cupertino), it demonstrates that the performance difference of our sensors in quiet and noisy ambient conditions is minimal. This overcomes the fundamental limitations of other technologies that struggle to capture true user call time in noisy ambient conditions. Also, the unique ID applied to each sensor enables the identification of the number of conversation partners.

[0175] Beyond acoustic signals, the sensors have the ability to utilize additional analytics to measure other parameters related to social interaction through the close connection of the skin. As previously reported in research adopting signal processing strategies from electrocardiograms and acoustic signals obtained from stethoscopes, we use Shannon energy calculations to induce a higher contrast for prominent mechanical acoustic signatures in the time domain from signal noise. Subsequently, a Savitzky-Golay smoothing function is applied to form an envelope over the transient energy data. Examples of the system's advantages include the measurement of respiratory rate transmitted through the neck and the pulsation of arterial blood through the external carotid artery, and measurements such as heart rate, heart rate variability, and respiratory rate are related to the assessment of sleep quality (Figs. 26 - 27). The sensors also have the ability to measure simpler sleep quality metrics such as duration, restlessness, and onset of sleep. Furthermore, our system has demonstrated that it can calculate the swallowing count, which provides direct insight into meal-time behavior and can provide a proxy marker for overeating or anorexia (Fig. 10), and even meal times. Finally, the sensors can determine the number of daily steps as a measure of physical activity comparable to existing commercial systems.

[0176] Form factor - reducing the burden and stigma on caregivers and wearers: The flexible sensor platform maximizes user comfort during neck movement, conversation, and swallowing. Highly visible neck-worn sensors (necklaces and circumferential neck sensors) are another limitation compared to other published solutions. 79% of respondents expressed significant discomfort and concerns regarding daily wearing of neck-worn sensors. Therefore, highly wearable sensors that can capture the necessary parameters must minimize potential stigma for people with AD and their interlocutors. Previous qualitative research on user acceptance of wearables in AD has emphasized the importance of low device maintenance, ensured data security, and individualization of wearing. The deployment of sensors at the suprasternal notch using medical-grade adhesives is an important advantage in terms of user acceptability in that it can capture relevant signals transmitted from the speech system while being largely covered by a buttoned shirt. The sensors are also encapsulated in silicone that matches the user's skin tone. Finally, the sensors support fully wireless charging and waterproof use, allowing the device to be placed in place and take a bath. Regarding the selection of adhesives to maximize the comfort of the wearer, we have extensive experience in identifying the optimal adhesive that can be adjusted based on the desired duration of use (from 1 day to 2 weeks). When the vulnerability of mature skin is high, we currently employ a mild acrylic polymer matrix adhesive (STRATGEL®, Nitto Denko) that acts without causing significant skin irritation or redness even when used daily for a long time (more than 2 weeks) in healthy adults. That is, the important advantages of wearable acoustic mechanical sensors for social interaction compared to existing systems and previously reported studies are as follows.

[0177] Multi - mode function: The sensor has already demonstrated that it can collect the maximum number of valuable parameters for evaluating social interaction in one technical platform that can be made usable through skin - close coupling. The parameters include conversation time, number of interaction partners, swallowing count, respiratory rate, heart rate, sleep quality, and physical activity. Additional parameters are compatible with the devices and methods provided in this specification.

[0178] Real - world continuous sensing function: The sensor can measure sound only when mechanical vibrations are sensed on the user's throat, which enables highly specific recording of true user conversation time regardless of noisy or quiet ambient environments. This allows for deployment in the real world outside of a controlled clinical environment.

[0179] Low - burden and unobtrusive form factor: The sensor passive - ly collects data without requiring user adjustment. Wireless charging limits the user's burden and smoothes adhesion. Deployment on the suprasternal notch enables high - fidelity signal capture without the stigma of a highly visible neck - mounted system.

[0180] Advanced signal analytics: Various signal - processing techniques can be employed to derive additional meaningful metrics for social interaction.

[0181] Hardware can be employed within a flexible wearable platform. Currently, the central microprocessor comes with a 2.4 GHz 32-bit CPU and 64 kB RAM and has up to eight analog channel inputs. A commercially available microphone may be used to determine the ideal specifications. Specifically, the MP23AB01DH (STMicroelectronics) series provides a thin microphone MEMS system (3.6 mm × 2.5 mm × 1 mm) that does not further increase the wearable form factor. Furthermore, the system has low power consumption (250 μA), a low sensitivity of 38 dB, and a high signal-to-noise ratio (65 dB). The microphone operates in synchronization with a 3-axis accelerometer and can collect external voice signals. The capacity of the current lithium-ion battery is 12 mAh. Therefore, we expect that adding an external microphone will not significantly affect the battery life. To determine success, the performance and auditory clarity of the microphone are being tested with standardized blocks (60 seconds) of voice text that increase the decibel (10) levels from 38 dB (whisper) to 128 dB (concert).

[0182] Expansion of Software and Signal Analysis - Bluetooth® can be used to connect to a standard smartphone, tablet, or laptop. The user interface can display raw signals and data storage. The sensors can be used as observation tools for social interaction, including using a secure user interface focused on researchers. This includes software protocols that enable HIPAA-compliant data transfer and cloud storage, although we already use Box® as a HIPAA-compliant storage platform for our wireless sensors. Signal processing (Savitzky Golay filtering, Butterworth filtering, Shannon energy envelope technique) enables the derivation of many important metrics of social interaction, although additional signal processing functions derive additional, more advanced metrics. For example, paraverbal features such as the pitch, tone, and voice reaction time of users during interaction are correlated with depression in all people, including those with dementia. Hesitation and talking too much are additional metrics of interest. We propose an approach from multiple aspects, including using hidden Markov model approaches, open access speech processing algorithms (e.g., COVAREP) 58, and wavelet analysis. In particular, we are convinced that wavelet analysis is the most promising strategy, assuming the established theory of previous research in which mother wavelets for specific metrics of interest are classified from raw input acoustic machine signals. The user interface enables researchers to freely manipulate raw data in various ways and deploy various signal processing strategies and toolboxes of interest. Furthermore, signal analysis enables the classification of other related behaviors for individuals with AD, such as personal hygiene activities (brushing teeth), housework, or driving.

[0183] Wearable medical devices worldwide will grow by 20% over the next decade, exceeding $3 billion, while the elderly population, despite having greater needs, does not receive adequate services and is critical. The platform provided herein is applicable to a wide range of dementia indications, as well as additional sensing applications (e.g., sleep or swallowing disorder sensors). Dementia, including AD, is a devastating condition. Increasing meaningful social interaction serves as both an immediate strategy for reducing cognitive decline and prevalence in AD while simultaneously providing a potential preventive strategy in the elderly. The wearable medical sensors provided herein have the opportunity to become an important clinical outcome tool for AD researchers by providing the first technology capable of comprehensively assessing social interaction in a natural environment. Further, the sensors can directly assist the individual and their caregiver, and on days when a person with AD has not been spoken to or meaningfully engaged, the sensors provided herein can notify the appropriate person and reduce the loneliness of that day.

[0184] Example 1: Exemplary Epidermal Device Using Mechanophonic Sensing and Actuation Functionality

[0185] An exemplary device using mechanophonic sensing and actuation functionality was fabricated and tested with respect to overall functionality and mechanical characteristics.

[0186] (B) of FIG. 43 presents an exploded view of the mechanical acoustic device of the present invention for epidermal sensing and actuation functions. As shown, the mechanical acoustic sensor is encapsulated within a silicone elastomer substrate and a superstrate (e.g., overlay) component, and includes a silicone gel layer that provides an overall multi-layer floating device architecture. As shown, the multi-layer device includes an IC component, a power source (e.g., a battery), contacts, and interconnect components (e.g., flexible serpentine interconnects and contact pads) in a trace, and an intermediate layer (e.g., a polyimide layer). The multi-layer architecture and device components are arranged and configured to enable effective integration with the subject's tissue (e.g., epidermis), as well as the ability to undergo deformation without delamination and / or failure. (A) of FIG. 43 shows the deployment of the device to the subject's body proximate the lateral neck, for example, for a speech and / or swallowing monitoring application. FIG. 43E presents an image showing the ability of the device to deform without failure, for example, via extensional and torsional deformations. FIG. 43D presents a series of schematic diagrams illustrating the ability of the device to incorporate serpentine interconnects such that it can accommodate extensional and torsional deformations without inducing a sufficiently high level of strain that would result in significant device degradation or failure. FIG. 43C presents a schematic diagram showing one embodiment of a bidirectional wireless communication for transmitting the output signal from the sensor to an external device and receiving commands from an external controller to the electronic device. The schematic also shows one embodiment of the power supplied by wireless charging of a battery, such as a lithium ion battery, to provide power to a 2.4 GHz Bluetooth wireless communication component, for example.

[0187] Figure 30A is a schematic diagram illustrating a potential wearing arrangement on a subject's body (schematically shown by the overlapping boxes). Figure 30B is a photograph and schematic diagram illustrating device placement on a subject's body including positions near the side of the neck and near the suprasternal notch. Figures 30C and 30D are diagrams presenting exemplary signals for the X, Y, and Z dimensions corresponding to a subject's activities including holding breath, sitting and talking, leaning, walking, and jumping up.

[0188] Figure 31A is a flowchart corresponding to a signal processing approach for the analysis of triaxial accelerometer output. Figure 31B is a diagram presenting an exemplary signal corresponding to a subject's activity.

[0189] Figure 32A is a diagram presenting exemplary data of respiratory rate GS vs. MA corresponding to a range of subjects. Figure 32B is a diagram presenting exemplary data of heart rate GS vs. MA corresponding to a subject. Figure 32C is a diagram presenting exemplary data of conversation time GS vs. MA corresponding to a range of subjects. Figure 32D is a diagram presenting exemplary data of swallowing frequency GS vs. MA corresponding to a range of subjects.

[0190] Figures 33(A) and 33(B) are diagrams presenting exemplary signals corresponding to a subject's activities including various configurations of vertical movement of the face and head. Figure 33C is a plot of rotation angle vs. time (minutes). Figure 33D is a plot of heart rate (BPM) vs. time (minutes).

[0191] Example 2: Wearable Sensors for Early Triage of High-Risk Newborns for CP

[0192] This example demonstrates the utility of the flexible wearable sensor device of the present invention for diagnostic applications, including early triage of high-risk neonatal subjects for cerebral palsy (CP). Predicting the ultimate neurological function in high-risk neonates is difficult, and research has demonstrated that the absence of smooth movement predicts the development of CP (see, for example, BMJ 2018:360:K207). The assessment of CP in neonatal subjects is typically performed by general movement assessment (GMA), which corresponds to, for example, a 5-minute video assessment of a supine infant using a standardized rubric.

[0193] In some embodiments, networked sensors provide added value. Deeper insights into abnormal movements can be obtained if the movements of the limbs can be evaluated in temporal synchronization via a network of sensors attached to the body. This enables a visual reproduction of the movements, which can provide video data such as GMA for future analysis. The advantages here include a reduction in the required data storage volume, anonymization of the subjects, and the ability to operate under low illumination conditions (e.g., at night or during sleep).

[0194] GMA is the current gold standard with the best available evidence for positive and negative predictive rates, but implementing GMA requires specialized training that may not be feasible for broader screening. 3D computer vision and motion trackers are also potentially useful for GMA, but they have the disadvantages of being very expensive, requiring significant computational power, and a large training set.

[0195] The sensor of the present invention provides an alternative approach that can accurately monitor and analyze the movements of neonatal subjects in real time, thus supporting applications for providing clinically relevant predictive information for the diagnosis of CP.

[0196] Figure 34(A) is a schematic diagram illustrating a research-grade wearable sensor of the present invention that incorporates a three-axis accelerometer, a gyroscope, and an EMG detector into a multilayer flexible device format. Figure 34(B) is a schematic diagram showing a plurality of wearable sensors (five in total) provided on different regions for a neonatal subject including the limbs and torso. In one embodiment, the sensors are provided on the neonatal subject's body during a one-hour clinical visit. Figure 34(C) is a diagram presenting accelerometer and gyroscope data obtained from the sensors.

[0197] Figure 35A is a schematic diagram of the sensor of this embodiment showing the EMG and accelerometer modules as well as the Bluetooth communication module. Figures 35B, 35C, and 35D are diagrams presenting examples of data obtained from the sensors including acceleration, reconstructed 3D motion, and EMG.

[0198] Figure 36 is a schematic flowchart of a method of using the sensors described herein to identify neonatal subjects at risk for CP. As shown, the miniaturized flexible accelerometer records spontaneous movements. A neurologist annotates the duration of the spontaneous movements and whether they are normal from the video recording. The data is uploaded to a server via Bluetooth, and a machine learning classifier is trained to detect the presence of abnormal movements based on the ground truth labels provided by a clinician. The model is tested periodically and updated / re-refined.

[0199] Figure 37 is an image of the miniaturized flexible accelerometers attached to the limbs and torso of a neonatal subject.

[0200] Figure 38 is a diagram presenting an example of data analytics useful for analyzing the output of the sensors of an example of the present invention, for example, for clinical diagnostic applications.

[0201] Figure 39 is a plot showing the difference in motion data between infants at risk of CP and infants with typical development, using 20 different features extracted from the motion data of 12-week-old infants.

[0202] Figure 40 presents the results of a study on wearable sensors for children with cerebral palsy (under 24 months) compared to age-matched controls, namely, the development of a new early detection tool.

[0203] Example 3: Mechanical Acoustic Sensing Summary

[0204] In conventional multimode biosensing, multiple rigid sensors need to be worn at designated locations and reserved times on multiple measurement sites. A device with soft shape conformity using MEMS accelerometers revolutionizes this tradition. This is suitable for use in a continuous wearable operation mode when recording mechanical acoustic signals derived from human physiological activities. The advantage of a device with multiplexed sensing functions is that it can continuously detect subtle vibrations of the skin on the order of about 5×10 -3 m·s -2 to about 20 m·s -2Establish a new opportunity area to continuously record the large inertial amplitude of the body and the high-fidelity signals on the epidermis in the range from static gravity to the voice band of 800 Hz. The minimum spatial and temporal constraints of devices operating beyond the clinical environment will expand the advantages of mechanisms different from ordinary electronic devices. Therefore, we develop a system-level wireless flexible mechanical acoustic device for recording multiple physiological information from the suprasternal notch at a single position. From this unique arrangement, the triaxial accelerometer simultaneously acquires walking motion, anatomical orientation, swallowing, breathing, heart activity, vocal cord vibration, and other mechanical acoustic signals that fit within the bandwidth of sensor capacitance, which are superimposed on a single stream of data. Multiple rationalizations of the algorithm analyze this high-density information into meaningful physiological information. The recording continues for 48 hours. We have also demonstrated in many field studies the ability of the device to measure essential vital signals (heart rate, respiratory rate, energy intensity) as well as unconventional biomarkers (conversation time, swallowing count, etc.) from healthy normal people. We verify these results against the golden rule and demonstrate clinical consensus and applications in clinical sleep studies.

[0205] First The human body continuously generates a number of mechanical acoustic (MA) signals that attenuate at the interface between the skin and the air (1-5). These signals contain important information about the physiological activities of the body and often have intensities and frequencies that exceed the range related to the audible range. These signals include, but are not limited to, vocal cord vibrations (about 100 Hz), heart activity (about 10 Hz), walking (about 1 Hz), breathing (about 0.1 Hz), and anatomical orientation (about 0 Hz). Conventional health monitoring tools are limited to clinical environments, and thus the mode of recording continuous physiological activities is rather discrete. In addition, the physical condition in the clinical setting has a causal relationship from an unnatural environment and can output distorted physiological information that does not reflect the natural state of the subject (5). By continuously recording physiological events in the daily environment over a long period, more realistic information about the subject will be obtained. However, it is difficult for conventional electronic devices such as stethoscopes and accelerometers to have both continuous measurement and high-fidelity signal recording (6). A good mechanical coupling of conventional electronic devices to the skin is usually interrupted during natural body movements, resulting in signal distortion. Recent advances in flexible electronics (1, 7-11) have enabled high-fidelity measurement of physiological data from the epidermis. Similarly, an epidermal mechanical acoustic sensor can acquire high-fidelity physiological information because it has a flexible structure with a low mass density (1). This epidermal mechanical acoustic sensor utilizes an accelerometer that is seamlessly coupled to the skin by a flexible substrate (1). As a result, it is sensitive to movements related to the skin and the body but less sensitive to ambient noise. With a soft shape-conforming form factor, the device can achieve a continuous wearable mode without imposing a burden on the skin from mechanical mismatching and the induced stress. However, still, the wires that conduct power and communication to the device reduce these advantages of mechanical isolation from the surroundings. A continuous wearable operation mode freed from spatial and movement constraints is not possible with a wired configuration.

[0206] Near-field communication (NFC) provides a solution for wireless data and power transmission to wearable sensors through inductive coupling of a 13.56 MHz device antenna and a transmitter antenna (12, 13). The system has the advantage of operating without a battery, but the problem of limited operating range depending on the geometry and power of the antenna persists. Bluetooth is another wireless communication mode that enables communication in the meter-scale range using a battery (14). Thus, by maintaining a connection with a portable hosting device such as a mobile phone, the device can operate without being restricted by space. However, the Bluetooth platform requires relatively large electronic components compared to other ICs and passive components. As a result, after conventional solid elastomer encapsulation, the entire device becomes rigid.

[0207] Described herein is a soft and stretchable wireless mechanoacoustic sensing platform that provides solutions to these challenges and enables continuous monitoring of multi-mode physiological information with high fidelity through Bluetooth Low Energy protocol, rechargeable lithium-ion battery, and air pocket encapsulation that bypasses the effects of rigid and relatively large electronic components. As a result, a system-level continuous diagnostic soft electronic device with enhanced robustness and no spatial and temporal constraints is obtained, which, in turn, does not permeate water or other foreign substances. Careful consideration of the measurement site provides a single stream of data with rich physiological information. The suprasternal notch is the location of the notch between the collarbones. Since the neck bridges the circulatory and respiratory systems between the head and the body, there are signals with various intensities and frequencies coupled to those physiological systems. The algorithm analyzes a single data into multiple physiological information by considering the specific characteristics of each signal and related events.

[0208] Results Device Design and Circuit Considerations The ultra-thin and flexible form factor of the wireless mechanoacoustic sensor enables the measurement of mechanical signals from the suprasternal notch with high signal fidelity. Figure 43(A) emphasizes the shape-conformability structure of the device that can deform naturally even when the neck is moved significantly. This design incorporates an extensible flexible interconnect, a strain isolation layer, and a soft encapsulation, enabling the circuit, which features wireless communication and highly robust power supply, to accommodate large mechanical deformations.

[0209] Figure 43(B) presents the overall structure of the system. The electronic platform is a flexible printed circuit board (fPCB) made of double-sided copper with polyimide as the insulating layer sandwiching the copper layers. The fPCB utilizes annealed rolled copper with a fatigue limit 6.5 times that of conventional electrodeposited copper films (16).

[0210] We designed the electronics centered around three main components for MA signal acquisition and wireless operation, which are a three-axis digital accelerometer sensor (BMI160, Bosch) that measures vibrations with a wide range (±2g), high resolution (16 bits), and a sampling frequency of 1600 Hz, a microcontroller (nRF52832, Nordic Semiconductor) that acquires data and communicates wirelessly with the user interface via Bluetooth Low Energy (BLE), and a wireless charging circuit that inductively charges a 45 mAh lithium-ion battery (Figure 43E). The BLE communication protocol operates over a distance range of approximately 2 m.

[0211] Adopting commercially available IC components and batteries has advantages in terms of robustness and production yield. However, their rigid and bulky structures may suppress the overall flexibility of the device. To solve this problem, we use meandering interconnects to mechanically decouple small flexible PCB islands (1 cm × 1 cm) where electronic components related to the microcontroller and charging circuit are densely arranged, as shown in Fig. 43(B). By densely allocating IC components, the sensor secures 71% of the total area for flexible interconnects for deformation absorption and for the edges of the device. The interconnect is compressed by only 10% of its original length in the non-active state (Fig. 43C). The pre-buckling structure increases the deformation ability of the device by nullifying the initial 10% tensile elongation (Fig. 48). From the simulation results, it can be seen that the pre-buckled meandering structure with a 270° arc angle has a 42% tensile strain 40% higher than the previously reported design (12) and recovers a twist with a 90° twist angle (Fig. 43D). From the simulation, the device may be subjected to 40% compression and 160° bending before yielding (Fig. 55).

[0212] We apply a 0.4 mm thick viscoelastic silicone gel with an ultra-low elastic modulus of 6 kPa under the flexible PCB for strain insulation. This insulation layer decouples the rigid electronic device islands other than the accelerometer from the large in-plane deformation of the substrate with a maximum strain of 40% (Fig. 56). Fig. 56 shows the relationship between strain insulation with gels of various thicknesses and the stress on the skin.

[0213] The wireless device is encapsulated by a silicone elastomer membrane for use in daily activities. As a result, the device is impervious to water or other foreign objects. A thin film (300 mm) made of silicone (Ecoflex Smooth-on) with a low elasticity of 60 kPa and a high elasticity of 500 MPa encapsulates the electronic device without physically contacting them (see SI for details). This design aims to minimize the curing effect from encapsulation. The thin film encapsulation with a hollow core has a lower moment of inertia of 68 mm compared to a solid silicone encapsulation of 450 mm 3 . The absence of mechanical interaction between the electronic component and the encapsulant provides additional robustness to the electronic device. Also, the hollow core allows the meandering interconnect to deform in a self-standing manner, increasing the extensibility further compared to a meandering section restricted to in-plane deformation. The low mass density of the device and the high sensitivity of the acceleration sensor are also due to the hollow encapsulation. Due to the above-mentioned mechanical engineering and materials engineering, the device is mechanically robust as shown in Fig. 43E and functions even with large deformations. 3

[0214] In-situ biosignal measurement The soft and shape-conforming unconstrained contact of the device with the epidermis enables the measurement of subtle vibrations of the skin on the order of about 5×10 2 g / √Hz (Fig. 48) from low to high frequencies (0 - 800 Hz) of large inertial amplitudes of the body of about 2g. When worn at the suprasternal notch that bridges the circulatory and respiratory systems between the head and the torso, a single device simultaneously captures not only gravity but also mechanical movements and acoustic vibrations resulting from the subject's core body movements, heart noise, breathing, speech, and swallowing. Fig. 44A presents 60-second 3-axis acceleration data of a sample obtained from a healthy normal subject, showing a series of bioactivities such as sitting, talking, drinking water, leaning, walking, and jumping. -4

[0215] ​​Acceleration signals derived from different physiological functions exhibit different characteristics in both the time domain and the frequency domain, conveying a wealth of information about the associated biological activities. We focus on z-axis acceleration data that emphasizes the normal direction movement and vibration with respect to the skin surface. Respiratory activity, which appears as low-frequency chest wall movement, induces changes in the magnitude of the gravitational projection of all axes. The subject held their breath at the marked point for about 10 seconds, causing a plateau in the acceleration signal. Quasi-static three-dimensional acceleration provides measurements of the gravitational vector indicating the body direction. Figure 44B shows the detailed characteristics of individual physiological events. The upper, middle, and lower segments show the zoomed-in time series, time-frequency spectrogram, and sample spectrum of representative high-frequency (>10 Hz) events, respectively. In frequency analysis, a 0.1-second Hann window with a 0.98-second overlap is applied. Heart activity - systole and diastole (6) - generates paired pulses with a peak amplitude of about 0.05 g, and the power is concentrated in the 20 - 50 Hz band. The conversation signal is characterized by high-quality harmonics of the fundamental frequency in the range of 85 to 255 Hz for a typical adult. The swallowing event starts with slow (about 0.1 second) vocal cord and laryngeal mechanics during the pharyngeal phase and ends with a high-frequency ring-down of water during the esophageal phase [citation]. Walking or jumping movements induce impact forces with large amplitudes (about 1 g) over a wide frequency range up to about 100 Hz.

[0216] Single-device MA measurements stream the superimposed information from multiple signal sources. As shown in Figure 44, we set up an offline data processing flow that utilizes characteristic features to extract biomarkers, namely, energy consumption (EE), heart rate (HR), respiratory rate (RR), swallowing count (SC), and conversation time (TT), which can play important roles in clinical and healthcare applications (Figure 45A).

[0217] For all filter processing processes, a fourth-order Butterworth infinite impulse response (IIR) discrete-time filter was used, followed by a non-causal zero-phase filter processing approach. We estimated the EE in a 2-second, 50% overlap time window as the sum of the band-limited root mean square (BLRMS) over the full-axis low frequencies (1 - 10 Hz) [Liu2011]. We used a threshold of 0.05g 2 = s + 5δs to classify active versus inactive states during daily activities, where s ≈ 0.012g and δs ≈ 0.008g are the characteristic mean and standard deviation of the EE measurements for the subject.

[0218] Heart rate analysis begins by passing the z-axis acceleration data through a band-pass filter (f 1 = 20 Hz, f 2 = 50 Hz) to suppress noise outside the frequency range of interest. We zeroed the signal within the time window when excessive movement was detected (EE > 0.05g 2 ) given a minimum peak height of 0.005g and a minimum peak distance of 0.33 s (≈180 BPM), and identified the heart pulse as the local maximum within the time series of the band-pass signal (Figure 45B). This algorithm excludes peak intervals longer than 1.2 s (≈50 BPM). Applying the mean over a 5-s time window to the peak-to-peak intervals gives an estimated moving HR.

[0219] Respiration measurements are sensitive to movement artifacts due to overlap within their frequency region (0.1 - 1 Hz). We developed a noise subtraction algorithm that utilizes time-synchronized 3-axis acceleration measurements. That is, given the inherent device wearing position and orientation (Figure 43(A) - Figure 43(B)), both the z-axis and x-axis measurements are sensitive to chest wall movement, while the y-axis acceleration is mainly associated with core body movement. We applied continuous wavelet transform and cross-wavelet transform to extract the common mode s xz between the z-axis measurement and the x-axis measurement, and then the differential mode s xz between s (xz)y' and the y-axis measurement (Note S1). Band-pass (f1 = 0.1Hz, f 2 The number N of zero-crossing nodes of the (Hz) signal (N = 1 Hz) is used to count the number of inspirations and expirations per minute and estimate RR as N / 2 breaths per minute (BPM) (Figure 45C, see SI for details).

[0220] A speech signal is characterized by a fundamental frequency F as the maximum value of the power spectral density within the range of the human voice. 0 Swallowing events are distinguishable by the presence of the second harmonic of the sigma-sigma (Figure 45D). Swallowing events, on the other hand, are characterized by both low-frequency mechanical motion (0.1-5 Hz) and high-frequency (>100 Hz) acoustic ring-down. After zeroing out speech and loud motion signals, the algorithm simultaneously detects high- and low-frequency signals above its silence-time threshold as swallowing events (Figure 45E, GMMHMM model).

[0221] We test the process flow in two field study schemes: exercise and eating. In the exercise scheme, each subject cycles or rests on an elliptical trainer aiming to span a range of heart rates from 50 BPM to 180 BPM. The algorithm outputs heart rate and compares it to the polar monitor recording every 5 seconds (Figure 50). Subjects manually count the number of respiratory cycles per minute while active. In the eating scheme, each subject speaks and swallows periodically for 5 minutes according to a given speaking time and swallow count. In this scheme, each subject performs five 5-minute tests. Within each minute of the nth test, the subject speaks for n×10 seconds and then swallows for (n+k)×10 seconds, where k=1,...,6-n.

[0222] Figure 46 shows the Bland - Altman analysis for HR, RR, TT, and SC. The solid and dashed lines mark the mean value of the difference and 1.96 times the standard deviation between the mechanical acoustic measurement and the reference standard, respectively. HR has a mean difference of - 3.12 BPM and a standard deviation of 5.43 BPM. RR has a mean difference of 0.25 BPM and a standard deviation of 2.53 BPM. TT has a mean difference of - 2.00 s / min and a standard deviation of 2.17 s / min. SC has a mean difference of - 0.65 counts / 5 min and a standard deviation of 2.68 counts / 5 min. The one - sample Kolmogorov - Smirnov test cannot reject the null hypothesis that the difference data is from a standard normal distribution against the alternative hypothesis that the difference data is not from a standard normal distribution at a 5% significance level for all test parameters.

[0223] Sleep study By applying it to sleep studies, the usefulness of devices and adaptive algorithms in advanced clinical diagnosis is demonstrated. Figure 47A shows a subject wearing one mechanical acoustic device on the suprasternal notch along with the gold - standard sleep polysomnography sensor ensemble including electrocardiogram (EKG), pressure transducer airflow (PTAF), abdominal strain gauge, thoracic strain gauge, thermistor, electroencephalogram (EEG), and electro - oculogram recording (EOG). In addition to detecting HR and RR, taking advantage of the absence of excessive movement during sleep, the mechanical acoustic sensor monitors the body orientation by measuring only gravity during calm periods. We demonstrate the detection of body orientation using 3 - axis acceleration data as shown in Figure 52.

[0224] Figures 47C - 47E compare the HR, RR, and body orientation measurements from the gold - standard device and the mechanical acoustic device throughout an approximately 7 - hour sleep test for male subjects. Figure 47C compares the HR analyzed from the 60 - second, 50% overlapping time - window band - pass (1 - 50 Hz) EKG signal versus the band - pass (20 - 50 Hz) mechanical acoustic z - axis signal. Figure 47D shows the band - pass filter (f 1 = 0.1 Hz, f 2The RR analyzed from the PTAF signal and the device z-axis signal of a 120-second, 50% overlapping time window to which a frequency of 0.8 Hz was applied is shown. The golden ratio body orientation is investigated by visual inspection. The device captures the body orientation by measuring the quasi-static gravity projection within the device frame associated with the core body frame (see SI for details). Figure 47E shows that when the zero degree is defined as the supine position and the positive direction is defined as the right direction, the device captures the general tendency of the body orientation as the rotation angle φ around the vertical axis. In addition to the supine, prone, left lateral, and right lateral positions, the MA signal reconstructs additional details associated with the relative rotation of the head with respect to the core body. Figure 47F shows the inference of the sleep stage from machine learning the accelerometer data compared with the clinical examination sleep stage. We apply a Gaussian mixture hidden Markov model (GMMHMM) to the Mel-frequency cepstral coefficient (MFCC) features that cluster the five sleep stages from wakefulness to rapid eye movement (REM).

[0225] In addition to conventional sleep studies, we analyze the correlations of HR, RR, and body orientation. Figure 47G shows the cumulative distribution functions of the HR and RR statistics in four classes of body orientation (supine position: -45° < φ < 45°, left: -135° < φ < -45°, right: 45° < φ < 135°, prone position: φ > 135° or φ < -135°). The data are obtained from MA measurements of one male subject over seven nights. We utilize an in-house use case for large-scale statistics on 10 subjects (Figure 51). The results show that HR and RR are significantly higher when the subject sleeps in a position close to the prone position.

[0226] Discussion Materials and Methods Flexible electronics platform: Cut the board outline and circuit design with a UV laser cutter (LPKF U4) together with a meandering interconnect. The cut circuit board is made from a double-sided copper sheet with a thin copper-clad laminate (12 μm) and a copper film (12 μm) adhered to a polyimide (PI) film (25 μm) (FLP 7421).

[0227] CO 2 Using a laser cutter (VLS3.50), cut an FR-4 (0.381 mm, McMaster Carr 1331T37) substrate (FIG 43B) having the shape of two islands ((B) in FIG 43) as a reinforcing material to enhance robustness. The substrate is adhered to the back surface of the circuit board, and the circuit board is bent along the designated bending lines and adhered to the other side of the FR-4 substrate using an adhesive (Loctite Tak Pak 444). This forms a two-layer component island with a small area. Fix the components to the circuit board with solder paste (Chip Quik TS391LT).

[0228] Strain insulation: CO 2 Using a laser cutter (VLS3.50), cut an FR-4 board shadow mask and screen-print a layer of silicone gel (Silbione RT Gel 4717 A / B, Bluestar Silicone, E = 5 kPa) on the lower encapsulating elastomer layer. The gel is cured on a hot plate at 100 °C for 5 minutes.

[0229] Encapsulation: Using a 3-axis milling machine (Roland MDX 540), cut an aluminum mold according to the 3D encapsulation mold design from CAD software (ProE Creo 3.0). Cast a base silicone elastomer film and a capping silicone elastomer film (Ecoflex, 00-30, Smooth-on) separately from two pairs of aluminum molds. Each pair of molds has a concave mold design and a convex mold design, forming a hollow space within the encapsulant. The Ecoflex poured into the mold is cured in an oven at 70 °C for 7 minutes. After depositing a silicone gel (strain insulation layer) on the cast lower elastomer, the electronics are coupled to the substrate by the silicone gel, which is the strain insulation layer. Then, use the uncured Ecoflex as an adhesive to adhere the capping film to the substrate.

[0230] Supplementary information Suppression of Motion Artifacts in Respiratory Analysis Based on Wavelet Coherence: Let \(n = 1, 2,\cdots, N\), the wavelet cross-spectrum of two time series \(x\) n and \(y\) n is as follows. \(C\) xy (s, n)= \(C\) * x (s, n) \(C\) y (s, n), (S.1) where \(C\) y (s, n) and \(C\) y (s, n) represent the continuous wavelet transforms (CWT) of \(x\) and \(y\) at scale \(s\) and position \(n\). * represents the complex conjugate.

[0231]

Equation

[0232] For a specific application in suppressing motion artifacts occurring within the frequency range of the respiratory cycle, the Morlet wavelet is used in the calculation. We selected a sampling period \(\Delta t = 20\) seconds to cover all the time scales of interest. The minimum scale for the Morlet wavelet is \(s\) 0 = 2\(\Delta t\). The CWT discretizes the scale by 16 voices per octave. The number of octaves is the nearest integer less than or equal to \(\log\) 2 \(N - 1\), which is 10 in this case. We perform a moving average filter to smooth the CWT coefficients over 16 scales. We use the built-in MATLAB® functions 'cwt' and'smoothCFS' to perform the continuous wavelet transform and the smoothing operation respectively.

[0233] Gaussian mixture hidden Markov model (HMM): For the robust and flexible classification problem regarding time-series signals, an effective method is to utilize a probabilistic approach that can infer random patterns using probabilities. In this study of mechanical acoustic biosignals, a Gaussian mixture hidden Markov model was introduced. This model is constructed to describe unobserved states related to the events of interest having discrete probabilities linked by a Markov chain. We apply this algorithm to swallowing detection and sleep stage identification.

[0234] To consider the hyperparameters of the probability model, we manually select the number of states as n = 5. Regarding the approach of feature extraction, we use the Mel-frequency cepstral coefficients (MFCC). MFCC integrates the low-frequency power spectral density in a narrow band, while for high-frequency components, it integrates in a wide band (it is necessary to specify the bandwidth about f). The MFCC coefficients take the form of the power of each band. We chose to handle a total of 15 bands, which has been shown to give a good balance between the complexity of the system and the functional representation ability for signals sampled at a frequency of about 1 - 2 kHz. In swallowing detection, significant features resulting from swallowing activities appear in the lower-order MFCCs and attenuate as the order increases. In contrast, speech consists of harmonic components and shows a unique pattern in the higher-order MFCCs.

[0235] Description of Incorporation by Reference and Modifications All references throughout this application, such as patent documents, patent application publications, and non-patent literature or other materials including issued or granted patents or equivalent documents, are hereby incorporated by reference in their entirety as if each reference were individually incorporated by reference to the extent that each reference is not at least partially inconsistent with the disclosure of this application (for example, references that are partially inconsistent are incorporated by reference except for the partially inconsistent portions of the reference).

[0236] The terms and expressions used in this specification are used as terms of explanation and not of limitation, and there is no intention in the use of such terms and expressions to exclude equivalents of the features shown and described or portions thereof, it being understood that various modifications are possible within the scope of the invention as claimed. Accordingly, although the invention has been particularly shown by preferred embodiments, exemplary embodiments, and optional features, those skilled in the art can also resort, as a last resort, to modifications and changes of the concepts disclosed herein, and it should be understood that such modifications and changes are considered to be within the scope of the invention as defined by the appended claims. The specific embodiments presented herein are examples of useful embodiments of the invention, and it will be apparent to those skilled in the art that the invention can be practiced using numerous variations of the devices, device components, and method steps described herein. As will be apparent to those skilled in the art, the methods and devices useful for the methods of the invention can include numerous optional components and processing elements and steps.

[0237] If groups of alternatives are disclosed herein, it is understood that all individual components of those groups and subgroups are disclosed separately. When Markush groups or other groups are used herein, it is intended that the group and all individual members of all possible combinations and subcombinations thereof be individually included in the disclosure.

[0238] All combinations or assemblages of components described or exemplified herein can be used to practice the invention, unless otherwise indicated.

[0239] In this specification, when ranges are given, such as thickness, size, modulus of elasticity, mass, temperature range, time range, or composition or concentration range, all intermediate ranges and sub-ranges, as well as all individual values included in the given range, are intended to be included in this disclosure. It will be understood that sub-ranges or ranges or individual values within ranges included in the description of this specification may be excluded from the claims of the present invention.

[0240] All patents and publications referred to in this specification are indicative of the level of those skilled in the art in the technical field to which the present invention pertains. The references cited in this specification are hereby incorporated by reference in their entirety to show the state of the art as of the date of publication or filing, and this information is intended to be used in this specification, if necessary, to exclude specific embodiments in the prior art. For example, when a composition is claimed, it should be understood that compounds known in the art and available prior to the applicant's invention, including those presented in the references cited in this specification, are not intended to be included in the composition claims of this specification.

[0241] As used herein, the term "comprising" is synonymous with "including", "containing", or "characterized by", and is inclusive or open-ended and does not exclude additional, unrecited elements or method steps. "Consisting of" as used herein excludes elements, steps, or ingredients not specified in the claims. "Consisting essentially of" as used herein does not exclude materials or steps that do not substantially affect the basic and novel characteristics of the claims. In each case herein, "comprising", "consisting essentially of", and "consisting of" may be replaced by either of the other two expressions. The invention as properly illustrated and described herein may be practiced without one or more elements or one or more limitations not specifically disclosed herein.

[0242] One of ordinary skill in the art will appreciate that starting materials, biomaterials, reagents, synthetic methods, purification methods, analytical methods, assay methods, and biological methods other than those specifically exemplified can be used in the practice of the invention without undue experimentation. All functional equivalents known in the art for such materials and methods are intended to be included in the invention. The terms and expressions used are used as terms of description and not of limitation, and there is no intention in the use of such terms and expressions to exclude equivalents of the features shown and described or portions thereof, it being understood that various modifications are possible within the scope of the invention as claimed. Accordingly, although the invention has been particularly shown and described with reference to preferred embodiments and optional features, one of ordinary skill in the art may also resort to modifications and variations of the concepts disclosed herein as a last resort, and such modifications and variations are considered to be within the scope of the invention as defined by the appended claims.

Description of the Reference Numerals

[0243] 20 Lower elastomer shell 30 Silicone strain isolation layer 40 Stretchable interconnect 50 Electronic device 60 Upper elastomer shell

Claims

1. a. an electronic device having a sensor comprising an accelerometer; b. a two-way wireless communication system electronically connected to the electronic device for transmitting output signals from the sensor to an external device and for receiving commands for the electronic device from an external controller; A medical sensor comprising:

2. 10. The medical sensor of claim 1, which is wearable, tissue-mounted or implantable, or in mechanical communication with or direct mechanical communication with tissue of a subject.

3. The medical sensor according to claim 1 or 2, further comprising a wireless power supply system for supplying power to the electronic device.

4. The medical sensor of any one of claims 1 to 3, further comprising a processor for providing real-time metrics.

5. 5. The medical sensor of claim 4, wherein the processor is located on-board the electronic device or in an external device located at a distance from the medical sensor and in wireless communication with the wireless communication system.

6. The medical sensor of claim 5, wherein the processor is part of a portable smart device.

7. 7. The medical sensor of any one of claims 1 to 6, which continuously monitors and generates real-time metrics.

8. The medical sensor of claim 7 , wherein the real-time metric is a social metric or a clinical metric.

9. 9. The medical sensor of claim 8, wherein the clinical metric is selected from the group consisting of swallowing parameters, breathing parameters, aspiration parameters, coughing parameters, sneezing parameters, temperature, heart rate, sleep parameters, pulse oximetry, snoring parameters, body movement, scratching parameters, bowel movement parameters, neonatal subject diagnostic parameters, cerebral palsy diagnostic parameters, and any combination thereof.

10. 9. The medical sensor of claim 8, wherein the social metric is selected from the group consisting of conversation time, word count, vocalization parameters, linguistic discourse parameters, dialogue parameters, sleep quality, eating behavior, physical activity parameters, and any combination thereof.

11. The medical sensor of any one of claims 1 to 10, further comprising a processor configured to analyze the output signal.

12. The medical sensor of claim 11 , wherein the processor utilizes machine learning to customize the analysis for each individual user of the medical sensor.

13. The medical sensor of claim 12 , wherein the machine learning comprises one or more supervised and / or unsupervised learning algorithms customizable for the user.

14. 14. The medical sensor of claim 12 or 13, wherein the machine learning improves sensor performance parameters and / or personalized user performance parameters for use in diagnostic sensing or therapeutic applications.

15. 15. The medical sensor of any one of claims 11 to 14, wherein the processor is configured to filter and analyze measured output from the electronic device to improve sensor performance parameters.

16. The medical sensor according to claim 1 , further comprising a wireless power supply system for wirelessly powering the electronic device.

17. 17. The medical sensor of claim 1, wherein the accelerometer is a three-axis high frequency accelerometer.

18. 18. The medical sensor of any one of claims 1 to 17, wherein the electronic device further comprises a stretchable electrical interconnect, a microprocessor, an accelerometer, a stimulator, a resistor and a capacitor in electronic communication for sensing vibration or motion by the accelerometer and providing stimulation to a user by a stimulator.

19. 20. The medical sensor of claim 18, wherein the sensor senses multiple or single physiological signals from a subject and a threshold is used to send a trigger for a correction, stimulation, biofeedback, or reinforcement signal back to the subject.

20. 20. The medical sensor of claim 18, wherein the electronic device comprises a network comprising a plurality of sensors.

21. 21. The medical sensor of claim 20, wherein at least one of the sensors is for sensing the physiological signal from the subject, and at least one of the sensors is for providing a feedback signal to the subject.

22. The medical sensor of claim 18 , wherein the threshold is personalized for the subject.

23. 20. The medical sensor of claim 18, wherein the stimulator comprises one or more of a vibration motor, an electrode, a light emitter, a thermal actuator, or an audio notification.

24. 24. The medical sensor of any one of claims 1 to 23, further comprising a flexible encapsulation layer surrounding a flexible substrate and said electronic device.

25. 24. The medical sensor of claim 1, wherein the encapsulation layer includes a lower encapsulation layer and an upper encapsulation layer, and a strain insulating layer, the strain insulating layer being supported by the lower encapsulation layer, and the flexible substrate being supported by the strain insulating layer.

26. 26. The medical sensor of claim 25, further comprising an air pocket between the electronic device and the upper encapsulation layer.

27. 26. The medical sensor of claim 25, wherein there are no air pockets between the electronic device and an underlying layer of the device that is near or in contact with a tissue surface of a subject.

28. 28. The medical sensor of any one of claims 1 to 27, having a device mass of less than 400 mg and a device thickness of less than 6 mm.

29. 29. The medical sensor of any one of claims 1 to 28 configured for a therapeutic swallowing application, a social interaction meter, a stroke rehabilitation device, or a respiratory therapy device.

30. 30. The medical sensor of claim 29, configured to be worn by a user and for use in therapeutic swallowing applications, wherein the output signal is a signal for one or more swallowing parameters selected from the group consisting of swallow frequency, swallow count, and swallow energy.

31. 31. The medical sensor of claim 30, further comprising a stimulator that provides a tactile signal to a user to engage in safe swallowing.

32. 32. The medical sensor of claim 31, wherein the safe swallowing is determined by sensing the onset of inspiration and expiration of a user's respiratory cycle.

33. 23. The medical sensor of claim 21 or 22, wherein one or more machine learning algorithms are used in a feedback loop for optimization of the tactile signal timing.

34. 30. The medical sensor of claim 29, configured to be worn by a user and used as a social interaction meter, wherein the output signal is a signal for one or more social parameters selected from the group consisting of conversation time, word count (fluency rate), vocalization parameters, linguistic discourse parameters, or dialogue parameters.

35. 35. The medical sensor of claim 34, configured to be attached to the suprasternal notch of the user.

36. 36. The medical sensor of claim 34 or 35, for use with one or more additional user welfare parameters selected from the group consisting of sleep quality, eating behavior, and physical activity, wherein the social and welfare parameters of the medical sensor are combined to provide a social interaction metric.

37. 37. The medical sensor of any one of claims 34 to 36, further comprising a stimulator that provides a tactile signal to a user to engage in a social interaction event.

38. 30. The medical sensor of claim 29, configured to be worn by a user and for use in a stroke rehabilitation device, and wherein the output signal is a signal for a social parameter and / or a swallowing parameter.

39. 40. The medical sensor of claim 38 for use with one or more additional stroke rehabilitation parameters selected from the group consisting of gait, falls, and physical activity.

40. 40. The medical sensor of claim 38 or 39, further comprising a stimulator that provides a tactile signal to a user to engage in a safe swallowing event.

41. 30. The medical sensor of claim 29, configured to be worn by a user and for use in a respiratory treatment device, wherein the output signal is a signal for inspiration and / or expiration, i.e., effort, duration, or airflow through the throat.

42. 42. The medical sensor of claim 41, further comprising a stimulator that provides a tactile signal to a user to engage in breathing exercises.

43. 43. The medical sensor of any one of claims 1 to 42, further comprising an external sensor operatively connected to the electronic device.

44. 44. The medical sensor of claim 43, wherein the external sensor comprises a microphone and / or a mouthpiece.

45. 45. The medical sensor of any one of claims 1 to 44, wherein the sensor is capable of recreating an avatar or animated representation of the subject's body posture and movements over time.

46. A method for measuring real-time personal metrics using any of the above medical sensors.

47. 1. A method for measuring real-time personal metrics, comprising: a. attaching any of the devices according to any one of claims 1 to 45 to a user's skin surface or implanting it subcutaneously; b. detecting a signal generated by the user with the sensor; c. analyzing the filtered signal thereby classifying the filtered signal; and d. providing real-time metrics to the user or a third party based on the classified filtered signals.

48. 48. The method of claim 47, further comprising the step of filtering the detected signal prior to the analyzing step.

49. The providing step includes: providing a tactile stimulus to the user; storing or displaying the clinical metrics; and / or Storing or displaying social metrics 48. The method of claim 47, comprising one or more of:

50. 50. The method of any one of claims 47 to 49, wherein the providing step further comprises storing the real-time metrics on a remote server for subsequent analysis to generate clinician or caregiver action.

51. 51. The method of claim 50, wherein the action includes sending a command to the medical sensor.

52. 48. The method of claim 47, wherein the real-time metric is a health-related mental metric, a physical metric, or a social metric.

53. 48. The method of claim 47, wherein the analyzing step includes using a machine learning algorithm.

54. 54. The method of claim 53, wherein the machine learning algorithms include independent supervised learning algorithms, each independently trained to provide personalized real-time metrics specific to an individual user.

55. 55. The method of claim 54, wherein the personalized real-time personal metrics are for therapeutic or diagnostic applications.

56. The therapeutic or diagnostic application comprises: a. Safe swallowing, b. Respiratory treatment, Cerebral palsy diagnosis or treatment, and d. Neonatal diagnosis or treatment 56. The method of claim 55, selected from the group consisting of:

57. The real-time personal metric may include: a. Sleep medicine, b. Dermatology, c.Respiratory medicine, d. Social interaction assessment; e. Speech therapy, f. Swallowing disorder g. Stroke rehabilitation, h. Nutrition, i. Obesity treatment, j. Fetal monitoring, k. Neonatal monitoring, l. Cerebral palsy diagnosis, m. Pregnancy monitoring, n.Intestinal function, o. diagnosing or treating sleep disorders; p.Sleep therapy, q.Trauma, r. Prevention of injuries due to falls or hyperextension of joints or limbs, s. Prevention of trauma during sleep, t. Small arms / ballistic related injuries; and u. Cardiac output monitoring treatment 57. The method of any one of claims 54 to 56, for a medical application selected from the group consisting of:

58. a. an electronic device having a sensor comprising an accelerometer; b. a wireless communication system electronically connected to the electronic device; A medical sensor comprising:

59. 59. The medical sensor of claim 58, wherein the wireless communication system is a two-way wireless communication system.

60. 60. The medical sensor of claim 58 or 59, wherein the wireless communication system is for transmitting an output signal from the sensor to an external device.

61. 61. The medical sensor of any one of claims 58 to 60, wherein the wireless communication system is for receiving commands from an external controller to the electronic device.

62. 62. The medical sensor of any one of claims 58 to 61, which is wearable or implantable.

63. 63. The medical sensor of any one of claims 58 to 62, further comprising a wireless power system for powering the electronic device.

64. 64. The medical sensor of any one of claims 58 to 63, further comprising a processor for providing real-time metrics.

65. 65. The medical sensor of any one of claims 58 to 64, wherein the processor is on-board the electronic device or positioned within an external device located at a distance from the medical sensor and in wireless communication with the wireless communication system.

66. 66. The medical sensor of any one of claims 58 to 65, wherein the processor is part of a portable smart device.

67. 67. The medical sensor of any one of claims 58 to 66, which continuously monitors and generates real-time metrics.

68. 68. The medical sensor of claim 67, wherein the real-time metric is a social metric or a clinical metric.

69. 69. The medical sensor of claim 68, wherein the clinical metric is selected from the group consisting of swallowing parameters, breathing parameters, aspiration parameters, coughing parameters, sneezing parameters, temperature, heart rate, sleep parameters, pulse oximetry, snoring parameters, body movement, scratching parameters, bowel movement parameters, and any combination thereof.

70. 70. The medical sensor of claim 69, wherein the social metrics are selected from the group consisting of conversation time, word count, vocalization parameters, linguistic discourse parameters, dialogue parameters, sleep quality, eating behavior, physical activity parameters, and any combination thereof.

71. 71. The medical sensor of any one of claims 58 to 70, further comprising a processor configured to analyze the output signal.

72. 72. The medical sensor of claim 71, wherein the processor utilizes machine learning to customize the analysis for each individual user of the medical sensor.

73. 73. The medical sensor of claim 72, wherein the machine learning comprises one or more supervised and / or unsupervised learning algorithms customizable for the user.

74. 73. The medical sensor of claim 71 or 72, wherein the machine learning improves sensor performance parameters and / or personalized user performance parameters for use in diagnostic sensing or therapeutic applications.

75. 75. A medical sensor or method according to any preceding claim, wherein the sensor is positioned at or near the suprasternal notch of the subject.

76. 76. A medical sensor or method according to any preceding claim, wherein the sensor is provided on or near the mastoid process of the subject.

77. 77. A medical sensor or method according to any one of the preceding claims, wherein the sensor is placed at or near the neck of a subject.

78. 78. A medical sensor or method according to any one of the preceding claims, wherein the sensor is placed at or near the lateral neck of the subject.

79. 79. A medical sensor or method according to any one of the preceding claims, wherein the sensor is placed under the subject's mandible.

80. 80. A medical sensor or method according to any one of the preceding claims, wherein the sensor is placed at or near the subject's jaw line.

81. 81. A medical sensor or method according to any one of the preceding claims, wherein the sensor is provided at or near the clavicle of the subject.

82. 82. A medical sensor or method according to any one of the preceding claims, wherein the sensor is provided on or near a bony prominence of the subject.

83. 83. A medical sensor or method according to any preceding claim, wherein the sensor is placed behind the subject's ear.

84. 84. The medical sensor or method of any one of claims 1 to 83, wherein the electronic device comprises one or more three-axis high frequency accelerometers.

85. 85. The medical sensor or method of any one of claims 1 to 84, wherein the electronic device comprises a mechanical acoustic sensor.

86. 86. The medical sensor or method of any one of claims 1 to 85, wherein the electronic device further comprises one or more of an on-board microphone, an ECG, a pulse oximeter, a vibration motor, a flow sensor, and a pressure sensor.

87. 87. The medical sensor or method of any one of claims 1 to 86, wherein the electronic device is a flexible device.

88. 88. The medical sensor or method of any one of claims 1 to 87, wherein the electronic device is an extensible device.

89. 89. The medical sensor or method of any one of claims 1 to 88, wherein the electronic device has a multi-layer floating device architecture.

90. 90. The medical sensor or method of any one of claims 1 to 89, wherein the electronic device is at least partially supported by an elastomeric substrate, a superstrate, or both.

91. 91. The medical sensor or method of any one of claims 1 to 90, wherein the electronic device is at least partially supported by a silicone elastomer that provides strain isolation.

92. 92. The medical sensor or method of any one of claims 1 to 91, wherein the electronic device is at least partially encapsulated by a moisture resistant enclosure.

93. 93. The medical sensor or method of any one of claims 1 to 92, wherein the electronic device further comprises an air pocket.

94. 94. The medical sensor or method of any one of claims 1 to 93, wherein the bidirectional wireless communication system is a Bluetooth communication module.

95. 95. The medical sensor or method of any one of claims 1 to 94, wherein the bidirectional wireless communication system is powered by a wireless rechargeable system.

96. 96. The medical sensor or method of any one of claims 1 to 95, wherein the wireless rechargeable system comprises one or more of a rechargeable battery, an induction coil, a full wave rectifier, a regulator, a charging IC, and a PNP transistor.

97. 97. The medical sensor or method of any one of claims 1 to 96, further comprising a gyroscope.

98. 98. The medical sensor or method of claim 97, wherein the gyroscope is a high frequency three-axis gyroscope.

99. 99. The medical sensor or method of any one of claims 1 to 98, further comprising a magnetometer.

100. 100. A medical sensor or method according to any preceding claim, wherein the medical sensor is attached to the patient near the suprasternal notch.

101. A device, comprising: a. an electronic device having a sensor comprising an accelerometer; b. a two-way wireless communication system electronically connected to the electronic device for transmitting output signals from the sensor to an external device and for receiving commands for the electronic device from an external controller; The sensor is a device that senses multiple or single physiological signals from the subject that provide the basis for one or more corrective, stimulating, biofeedback, or reinforcement signals provided to the subject.

102. 102. The device of claim 101, wherein the correction, stimulation, biofeedback, or reinforcement signals are provided by one or more actuators.

103. 103. The device of claim 101 or 102, wherein the one or more actuators are thermal, optical, electrotactile, auditory, visual, tactile, or chemical actuators operably connected to the subject.

104. 104. A device according to any one of claims 101 to 103, wherein a processor provides feedback control of the one or more corrective, stimulation, biofeedback or reinforcement signals provided to the subject.

105. 105. A device according to any one of claims 101 to 104, wherein the multiple or single physiological signal provides an input for the feedback control.

106. 106. The device of claim 105, wherein the feedback control includes a threshold processing step for triggering the one or more corrective, stimulating, biofeedback, or reinforcement signals provided to the subject.

107. 107. The device of claim 106, wherein said thresholding step is accomplished by dynamic thresholding.

108. A device, comprising: a. an electronic device having a multi-modal sensor system comprising a plurality of sensors, the sensors comprising an accelerometer and at least one sensor that is not an accelerometer; b. a two-way wireless communication system electronically connected to said electronic device for transmitting output signals from said sensor to an external device and for receiving commands to said electronic device from an external controller.

109. 109. The device of claim 108, wherein the sensor system comprises one or more sensors selected from the group consisting of optical sensors, electronic sensors, thermal sensors, magnetic sensors, optical sensors, chemical sensors, electrochemical sensors, fluid sensors, or any combination thereof.

110. 110. The device of claim 108 or 109, wherein the sensor system comprises one or more sensors selected from the group consisting of a pressure sensor, an electrophysiological sensor, a thermocouple, a heart rate sensor, a pulse oximetry sensor, an ultrasonic sensor, or any combination thereof.

111. A device, comprising: a. an electronic device having a sensor comprising an accelerometer; b. one or more actuators operatively connected to the sensor; The sensor is a device that senses multiple or single physiological signals from the subject that provide the basis for one or more corrective, stimulating, biofeedback, or reinforcement signals provided to the subject by the one or more actuators.

112. The device of claim 111, wherein the one or more corrective, stimulating, biofeedback, or enhancing signals are one or more optical signals, electronic signals, thermal signals, magnetic signals, chemical signals, electrochemical signals, fluid signals, visual signals, mechanical signals, or any combination thereof.

113. 113. The device of claim 111 or 112, wherein the one or more actuators are selected from the group consisting of a thermal actuator, an optical actuator, an electrotactile actuator, an auditory actuator, a visual actuator, a tactile actuator, a mechanical actuator, or a chemical actuator operably connected to the subject.

114. 114. A device according to any one of claims 111 to 113, wherein the one or more actuators are one or more stimulators.

115. 115. A device according to any one of claims 111 to 114, wherein the one or more actuators are a heating device, a light emitter, a vibration element, a piezoelectric element, a sound generating element, a tactile element, or any combination thereof.

116. 116. A device as described in any one of claims 111 to 115, wherein a processor is operatively connected to the electronic device and the one or more actuators, the processor providing feedback control of the one or more corrective, stimulation, biofeedback, or reinforcement signals provided to the subject.

117. 117. The device of claim 116, wherein the multiple or single physiological signal provides an input for the feedback control.

118. 118. The device of claim 117, wherein the feedback control includes a threshold processing step for triggering the one or more corrective, stimulating, biofeedback, or reinforcement signals provided to the subject.

119. 119. The device of claim 118, wherein said thresholding step is accomplished by dynamic thresholding.

120. 120. A device as described in any one of claims 111 to 119, further comprising a two-way wireless communication system electronically connected to the electronic device for transmitting output signals from the sensor to an external device and for receiving commands to the electronic device from an external controller.

121. 121. A device according to any one of claims 111 to 120, wherein the one or more corrective, stimulating, biofeedback or reinforcement signals are provided to the subject for training or treatment.

122. 122. The device of claim 121, wherein the training or treatment is for breathing or swallowing training.

123. 123. A device according to any one of claims 101 to 122, configured to continuously monitor and generate real-time metrics.

124. 124. The device of claim 123, wherein the real-time metric is a social metric or a clinical metric.

125. The device of claim 124, wherein the clinical metrics are selected from the group consisting of swallowing parameters, breathing parameters, aspiration parameters, coughing parameters, sneezing parameters, temperature, heart rate, sleep parameters, pulse oximetry, snoring parameters, body movement, scratching parameters, bowel movement parameters, neonatal subject diagnostic parameters, cerebral palsy diagnostic parameters, and any combination thereof.

126. 126. The device of claim 125, wherein the social metrics are selected from the group consisting of conversation time, word count, vocalization parameters, linguistic discourse parameters, dialogue parameters, sleep quality, eating behavior, physical activity parameters, and any combination thereof.

127. 127. A device according to any one of claims 111 to 126, further comprising a gyroscope.

128. 128. The device of claim 127, wherein the gyroscope is a high frequency three-axis gyroscope.

129. 129. The device of any one of claims 111 to 128, further comprising a magnetometer.

130. 130. A method of performing a therapy using a device or sensor according to any one of claims 111 to 129.

131. 131. A method of performing diagnosis using a device or sensor according to any one of claims 111 to 130.

132. 132. A method of training a subject using a device or sensor according to any one of claims 111 to 131.

Images