System and method for detecting defecation event

Abstract

To provide a system and a method for easily and accurately detecting a defecation event and acquiring defecation event data.SOLUTION: A system 100 and a method facilitate detection and recording of a defecation event of a target such as a participant of a clinical test for treating a digestive system disease such as an irritable bowel syndrome (IBS), an inflammatory bowel disease (IBD), and chronic coprostasis. The system 100 and the method can be used by individual patients for detecting and recording a defecation event, and resultant data can be checked in detail by a medical treatment provider at the time of evaluating health and / or treatment of the gastrointestinal of the patient.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to systems and methods for automatically detecting a bowel movement event in a subject, and more particularly, to systems and methods for detecting a bowel movement event by detecting one or more actions associated with such an event. [Background technology]

[0002] Accurately obtaining bowel event data (e.g., the frequency and / or timing of such events) is typically required for the diagnosis, evaluation, treatment, and / or management of various gastrointestinal disorders, such as irritable bowel syndrome (IBS), inflammatory bowel disease (IBD), and chronic constipation. However, obtaining such data can be cumbersome and typically relies on patient memory, which can be subject to inaccuracies. Summary of the Invention

[0003] The present disclosure provides systems and methods for easily and accurately detecting bowel movements and acquiring bowel movement event data that do not have to rely on patient memory.

[0004] According to one embodiment of the present disclosure, a system for detecting a bowel movement event in a subject includes a wearable device configured to be carried on the subject's torso. The wearable device is operable in a sleep mode and an active mode. The wearable device includes a wake-up sensor configured to detect a first stimulus and a mechanomyogram (MMG) sensor configured to detect abdominal muscle movement signals in the subject. A processor is operably coupled to the wake-up sensor and the MMG sensor. The processor reconfigures the wearable device from the sleep mode to the active mode based on the first stimulus detected by the wake-up sensor. In the active mode, the wearable device is configured in communication with the processor to determine the occurrence of a bowel movement event in the subject based on the abdominal muscle movement signals detected by the MMG sensor.

[0005] In some embodiments, the subject's abdominal muscle movement signal is the second stimulus, and the system further includes a third sensor operably coupled to the processor and configured to detect the third stimulus, In the active mode, the processor is configured to determine the occurrence of a bowel movement event in the subject based on the abdominal muscle movement signal detected by the mechanomyogram sensor and the third stimulus detected by the third sensor.

[0006] In some embodiments, the third sensor includes a gas sensor disposed within the wearable device and configured to detect flatus.

[0007] In some embodiments, the third sensor is an audio sensor configured to detect toilet flush sounds. In some embodiments, the audio sensor may also be configured to detect sounds caused by or associated with clothing movement, such as the friction of removing lower body clothing.

[0008] In some embodiments, the third sensor is an electromyography electrode configured to sense electrical muscle signals of the subject.

[0009] In some embodiments, the third sensor is an inertial measurement unit configured to detect changes in the posture of the subject.

[0010] In some embodiments, the wearable device further comprises a patch configured to be carried on the torso of the subject, the patch carrying the wake-up sensor and the mechanomyogram sensor.

[0011] In some embodiments, the patch further carries a processor.

[0012] In some embodiments, the wearable device further comprises a belt configured to extend around a torso of the subject, the belt carrying the wake-up sensor and the mechanomyogram sensor.

[0013] In some embodiments, the belt further carries a processor.

[0014] In some embodiments, the wake-up sensor includes one of an optical sensor and a resistive force sensor configured to detect when the subject removes lower body clothing.

[0015] In some embodiments, the wearable device further comprises a health sensor configured to detect a health stimulus associated with the health of the subject.

[0016] In some embodiments, the health sensor includes a blood sensor configured to detect blood in the subject's stool.

[0017] In some embodiments, the blood sensor includes a solid-state vapor detection sensor configured to sense one or more volatile organic compounds.

[0018] According to another embodiment of the present disclosure, a system for detecting a defecation event in a subject includes a wearable device configured to be carried on a torso of the subject. The wearable device includes a mechanomyogram sensor configured to detect abdominal muscle movement signals in the subject and a gas sensor configured to detect flatus. A processor is operably coupled to the mechanomyogram sensor and the gas sensor. The processor is configured to determine the occurrence of a defecation event in the subject based on the abdominal muscle movement signals detected by the mechanomyogram sensor and the flatus detected by the gas sensor.

[0019] In some embodiments, the processor is configured to determine the occurrence of a defecation event in the subject based on a sequence of events including one of the abdominal muscle movement signal detected by the mechanomyogram sensor and the flatus detected by the gas sensor preceding the other of the abdominal muscle movement signal detected by the mechanomyogram sensor and the flatus detected by the gas sensor.

[0020] In some embodiments, the wearable device further comprises a base carrying the mechanomyogram sensor, the gas sensor, and the processor.

[0021] According to yet another embodiment of the present disclosure, a system for detecting a defecation event in a subject includes a wearable device configured to be carried on the subject's torso and under lower body garments worn by the subject. The wearable device includes an optical sensor configured to detect increased light when the subject removes the lower body garment. A processor is operably coupled to the optical sensor, the processor configured to determine the occurrence of a defecation event based at least in part on the increased light detected by the optical sensor.

[0022] In some embodiments, the wearable device is operable in an active mode and a sleep mode, and the processor reconfigures the wearable device from the sleep mode to the active mode when it determines, in response to increased light detected by the optical sensor, that the subject has removed lower body clothing.

[0023] In some embodiments, the optical sensor is a first sensor configured to detect light as the first stimulus. The wearable device further includes a second sensor configured to detect a second stimulus when the wearable device is in the active mode. The second stimulus is different from the first stimulus. A processor is operably coupled to the second sensor, and the processor is configured to determine the occurrence of a bowel movement event in the subject based on a signal received from the second sensor.

[0024] In some embodiments, the optical sensor is a first sensor configured to detect light as the first stimulus. The wearable device further includes a second sensor configured to detect a second stimulus when the wearable device is in the active mode. The second stimulus is different from the first stimulus. A processor is operably coupled to the second sensor, and the processor is configured to determine the occurrence of a bowel movement event in the subject based on signals received from the first sensor and the second sensor.

[0025] In some embodiments, the second sensor is a mechanomyogram sensor.

[0026] In some embodiments, the wearable device further comprises a patch configured to be carried on the torso of the subject, the patch carrying the optical sensor and the processor.

[0027] In some embodiments, the wearable device further comprises a belt configured to extend around a torso of the subject, the belt carrying the optical sensor and the processor.

[0028] According to yet another embodiment of the present disclosure, a method for detecting a bowel movement event in a subject includes detecting increased light when the subject removes lower body clothing with an optical sensor of a wearable device carried on the subject's torso, detecting abdominal muscle movement signals of the subject with a mechanomyogram sensor of the wearable device, and determining the occurrence of a bowel movement event based at least in part on the increased light detected when the subject removes lower body clothing and the detected abdominal muscle movement signals of the subject.

[0029] In some embodiments, the method further includes detecting flatus by a gas sensor of the wearable device, and determining that a defecation event has occurred is based at least in part on the detected flatus.

[0030] In some embodiments, the method further includes detecting, by an inertial measurement unit of the wearable device, a sitting movement by the subject prior to detecting the abdominal movement signal of the subject, and determining that a defecation event has occurred is based at least in part on the detected sitting movement.

[0031] In some embodiments, the method further includes detecting, by an inertial measurement unit of the wearable device, a standing up movement by the subject after detecting the flatus, and determining that a defecation event has occurred is based at least in part on the detected standing up movement.

[0032] In some embodiments, the method further comprises detecting multiple bowel movement events in the subject over a period of time.

[0033] In some embodiments, detecting each of the plurality of bowel movement events of the subject includes detecting abdominal muscle movement signals of the subject with a mechanomyogram sensor of the wearable device; detecting increased light when the subject removes lower body clothing with an optical sensor; and determining the occurrence of each of the plurality of bowel movement events based at least in part on the subject's detected abdominal muscle movement signals and the increased light detected when the subject removes lower body clothing.

[0034] In some embodiments, detecting increased light by an optical sensor when a subject removes lower body clothing precedes detecting abdominal muscle movement signals of the subject by a mechanomyogram sensor.

[0035] In some embodiments, detecting a subject's abdominal muscle movement signals with a mechanomyogram sensor precedes detecting increased light with an optical sensor when the subject removes lower body clothing.

[0036] In some embodiments, the method further includes reconfiguring the wearable device from a sleep mode to an active mode based on the increased light detected when the subject removes lower body clothing, wherein in the sleep mode the mechanomyogram sensor is inactive and in the active mode the mechanomyogram sensor is configured to detect abdominal muscle movement signals of the subject.

[0037] According to yet another embodiment of the present disclosure, a system for training one or more processors to detect a bowel movement event in a subject includes a first wearable device configured to be carried on a body of the subject. The first wearable device includes a first bowel movement event sensor configured to detect one or more first stimuli. The system further includes a second wearable device configured to be carried on the body of the subject. The second wearable device includes a second bowel movement event sensor configured to detect one or more second stimuli. The system further includes one or more processors operably coupled to the first bowel movement event sensor and the second bowel movement event sensor and configured to determine the occurrence of a detected bowel movement event in the subject based on the one or more second stimuli and associate a first stimulus detected by the first bowel movement event sensor within a predetermined time period of the detected bowel movement event with the bowel movement event in the subject.

[0038] In some embodiments, the one or more processors are further configured to train a machine learning algorithm for detecting a bowel movement event in the subject using data indicative of a first stimulus sensed by a first bowel movement event sensor associated with the subject's bowel movement event.

[0039] In some embodiments, the first wearable device further includes a wake-up sensor configured to detect one or more wake-up stimuli. The first wearable device is configured to transition from a sleep mode to an active mode, in which the first wearable device is configured to detect a bowel movement event of the subject via the first bowel movement event sensor, when the wake-up sensor detects a wake-up stimulus associated with the bowel movement event of the subject. The one or more processors are further configured to associate the wake-up stimulus detected by the wake-up sensor within a second predetermined period of the detected bowel movement event with the bowel movement event of the subject.

[0040] In some embodiments, the one or more processors comprise a first processor operably coupled to the first bowel movement event sensor and a second processor operably coupled to the second bowel movement event sensor, wherein the first processor and the second processor are operably coupled to each other.

[0041] In some embodiments, the one or more processors comprise a single processor operably coupled to the first bowel movement event sensor and the second bowel movement event sensor.

[0042] In some embodiments, the first wearable device includes a smart watch.

[0043] In some embodiments, the second wearable device includes a patch configured to be carried on the torso of the subject.

[0044] In some embodiments, the first wearable device includes at least one of the one or more processors.

[0045] In some embodiments, at least one of the one or more processors is in wireless communication with the first wearable device.

[0046] In some embodiments, the first stimulus and the second stimulus are different types of stimuli.

[0047] In some embodiments, the first stimulus and the second stimulus are the same type of stimulus.

[0048] According to another embodiment of the present disclosure, a method for training one or more processors operably coupled to a first wearable device to detect a bowel movement event of a subject includes detecting one or more first stimuli by a first bowel movement event sensor carried by the first wearable device; detecting one or more second stimuli by a second bowel movement event sensor carried by a second wearable device; determining, by the one or more processors, the occurrence of the detected bowel movement event of the subject based on the second stimuli; and associating, by the one or more processors, the first stimuli detected by the first bowel movement event sensor within a predetermined period of the detected bowel movement event to the subject's bowel movement event.

[0049] In some embodiments, the method further includes training, by the one or more processors, a machine learning algorithm for detecting a bowel movement event in the subject using data indicative of a first stimulus sensed by a first bowel movement event sensor associated with the subject's bowel movement event.

[0050] In some embodiments, the first wearable device further comprises a wake-up sensor configured to detect one or more wake-up stimuli, and the first wearable device is configured to transition from a sleep mode to an active mode, in which the first wearable device is configured to detect a bowel movement event of the subject via the first bowel movement event sensor, when the wake-up sensor detects a wake-up stimulus associated with the bowel movement event of the subject. The method further includes associating, by the one or more processors, the wake-up stimulus detected by the wake-up sensor within a second predetermined period of the detected bowel movement event with the bowel movement event of the subject. The second predetermined period may be the same as or different from the predetermined period.

[0051] According to another embodiment of the present disclosure, a system for training one or more processors to detect a bowel movement event in a subject includes a wearable device configured to be carried on a body of the subject. The wearable device includes a bowel movement event sensor configured to detect one or more stimuli. The system further includes a mobile device configured to receive user input from the subject indicating a bowel movement time at which the bowel movement event occurred. The system further includes one or more processors operably coupled to the bowel movement event sensor and the mobile device and configured to associate a stimulus detected by the bowel movement event sensor within a predetermined time period of the bowel movement time with the bowel movement event in the subject.

[0052] In some embodiments, the one or more processors are further configured to train a machine learning algorithm for detecting a bowel movement event in the subject using data indicative of a first stimulus sensed by a first bowel movement event sensor associated with the subject's bowel movement event.

[0053] In some embodiments, the wearable device further comprises a wake-up sensor configured to detect one or more wake-up stimuli, and the wearable device is configured to transition from a sleep mode to an active mode in which the wearable device is configured to detect a bowel movement event of the subject via the bowel movement event sensor when the wake-up sensor detects a wake-up stimulus associated with the bowel movement event of the subject. The one or more processors are further configured to associate the wake-up stimulus detected by the wake-up sensor with the bowel movement event of the subject within a second predetermined period of the detected bowel movement event. The second predetermined period may be the same as or different from the predetermined period.

[0054] According to yet another embodiment of the present disclosure, a method for training one or more processors operably coupled to a wearable device to detect a bowel movement event in a subject includes detecting one or more stimuli with a bowel movement event sensor carried by the wearable device. The method further includes receiving a user input via the subject's mobile device indicating a bowel movement time at which the bowel movement event occurred. The method further includes associating, by the one or more processors, the stimuli detected by the bowel movement event sensor within a predetermined period of the bowel movement time with the subject's bowel movement event.

[0055] In some embodiments, the method further includes training, by the one or more processors, a machine learning algorithm for detecting a bowel movement event in the subject using data indicative of a first stimulus sensed by a first bowel movement event sensor associated with the subject's bowel movement event.

[0056] In some embodiments, the wearable device further comprises a wake-up sensor configured to detect one or more wake-up stimuli, and the wearable device is configured to transition from the sleep mode to the active mode when the wake-up sensor detects a wake-up stimulus associated with the subject's bowel movement event, and the method further includes associating, by the one or more processors, the wake-up stimulus detected by the wake-up sensor within a second predetermined period of the detected bowel movement event with the subject's bowel movement event. [Brief explanation of the drawings]

[0057] The above and other advantages and objects of the present invention, and the manner in which they are achieved, will become more apparent, and the invention itself will be better understood, by reference to the following description of an embodiment of the invention taken in conjunction with the accompanying drawings. [Figure 1] FIG. 1 is a schematic diagram of a system for detecting a bowel movement event in a subject, according to one embodiment of the present disclosure. [Figure 2]FIG. 10 is a perspective view of a wearable device for detecting a bowel movement event in a subject according to another embodiment of the present disclosure. [Figure 3] FIG. 3 is a bottom view of the wearable device of FIG. 2. [Figure 4A] FIG. 10 is a front perspective view of a wearable device for detecting a bowel movement event in a subject according to another embodiment of the present disclosure. [Figure 4B] FIG. 10 is a rear perspective view of a wearable device for detecting a bowel movement event in a subject according to another embodiment of the present disclosure. [Figure 5] FIG. 10 is a perspective view of a wearable device for detecting a bowel movement event in a subject according to yet another embodiment of the present disclosure. [Figure 6] FIG. 10 is a perspective view of a wearable device for detecting a bowel movement event in a subject according to a further embodiment of the present disclosure. [Figure 7] FIG. 7 is a plan view of the wearable device of FIG. 6. [Figure 8] FIG. 7 is a bottom view of the wearable device of FIG. 6. [Figure 9] FIG. 1 is a flow diagram of a method for detecting a bowel movement event in a subject, according to one embodiment of the present disclosure. [Figure 10] 10 illustrates operations associated with another method for detecting a bowel movement event in a subject, according to one embodiment of the present disclosure. [Figure 11] 10 illustrates operations associated with another method for detecting a bowel movement event in a subject, according to one embodiment of the present disclosure. [Figure 12] 10 illustrates operations associated with another method for detecting a bowel movement event in a subject, according to one embodiment of the present disclosure. [Figure 13] 10 illustrates operations associated with another method for detecting a bowel movement event in a subject, according to one embodiment of the present disclosure. [Figure 14] 10 illustrates operations associated with another method for detecting a bowel movement event in a subject, according to one embodiment of the present disclosure. [Figure 15] 10 illustrates operations associated with another method for detecting a bowel movement event in a subject, according to one embodiment of the present disclosure. [Figure 16] 10 illustrates operations associated with another method for detecting a bowel movement event in a subject, according to one embodiment of the present disclosure. [Figure 17] FIG. 1 is a flow diagram of a method for training a first wearable device to detect a bowel movement event by using a second wearable device, according to one embodiment of the present disclosure. [Figure 18] FIG. 1 is a flow diagram of a method for training a wearable device to detect bowel movement events using manual user input received via a subject's mobile device, according to one embodiment of the present disclosure.

[0058] Corresponding reference characters indicate corresponding parts throughout the several views. Although the drawings represent embodiments of the present invention, the drawings are not necessarily to scale and certain features may be exaggerated or omitted in some of the drawings to better illustrate and explain the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0059] Systems and methods according to embodiments of the present disclosure facilitate detecting bowel movement events in a subject by detecting one or more stimuli associated with the event. The subject may be a participant in a clinical trial for the treatment of gastrointestinal disorders such as irritable bowel syndrome (IBS), inflammatory bowel disease (IBD), and chronic constipation. Alternatively, systems and methods according to embodiments of the present disclosure may be used by individual patients to detect and record bowel movement events, and the resulting data may be reviewed by a healthcare provider when evaluating the patient's gastrointestinal health and / or treatment.

[0060] Referring now to FIG. 1 , a system 100 for detecting a bowel movement event in a subject is schematically illustrated, according to one embodiment of the present disclosure. Generally, the system 100 includes a wearable device 102 configured to be worn by, attached to, or otherwise carried by the subject. The wearable device 102 detects one or more stimuli indicative of a bowel movement event in the subject. The wearable device 102 is operably coupled (illustratively, via wireless communication—as used herein, the term “operably coupled” includes wired and wireless data communication, whether direct or indirect, via one or more intervening devices or components, and such data communication may be continuous or intermittent) to one or more remote devices 104, and the wearable device 102 transmits data regarding the bowel movement event to the remote devices 104. The remote devices 104 can analyze, display, or otherwise provide the data regarding the bowel movement event to one or more users, such as a clinical trial administrator, a healthcare provider, or the subject themselves. These aspects are described in further detail below.

[0061] 1 , wearable device 102 includes a base 106 configured to be attached to or otherwise carried by a subject. Base 106 carries an electronics assembly 108 that facilitates detecting and recording a subject's bowel movement events. In the illustrated embodiment, electronics assembly 108 includes one or more wake-up sensors 110 that detect a "wake-up" stimulus that precedes a bowel movement event. Wake-up sensors 110 are operatively coupled (illustratively via wired communication) to a processor 112. When wake-up sensors 110 detect the one or more wake-up stimuli, processor 112 reconfigures device 102 from a sleep mode to an active mode. In the sleep mode, one or more components of electronics assembly 108 may operate in a lower power consumption state (e.g., operate at a lower clock rate, a lower voltage, or both) or may be inactive or "off." In some embodiments, in the sleep mode, the processor 112 may be in a state where signals output from the sensors are ignored, not processed, or not stored. In the active mode, one or more components of the electronics assembly 108 may operate in a higher power consumption state (e.g., operating at a higher clock rate, a higher voltage, or both) or may be active or "on." Illustratively, such components may include one or more bowel movement event sensors 114 that detect stimuli during a bowel movement event. In some embodiments, in the active mode, the processor 112 may be in a state where signals output from the sensors are processed and / or stored. In other words, the wake-up sensor 110 may wake the device 102 for a potential bowel movement event, and the bowel movement event sensor 114 may then be used to confirm the occurrence of a bowel movement event.

[0062] The wake-up sensor 110 can take various forms. For example, the wake-up sensor 110 may include one or more optical sensors and / or one or more resistive force sensors that detect when a subject removes lower-body clothing. More specifically, the optical sensors detect increased light when a subject removes lower-body clothing, and the resistive force sensors detect a lack of contact force applied by the lower-body clothing. As another example, the wake-up sensor 110 may include one or more audio sensors that detect one or more corresponding sounds when a subject removes lower-body clothing. As yet another example, the wake-up sensor 110 may include one or more accelerometers and / or inertial measurement units (IMUs) that detect changes in the user's posture, for example, associated with sitting or standing. The wake-up stimulus detected by the wake-up sensor and that causes the electronic assembly 108 to switch from an inactive state to an active state may include a single detected stimulus, for example, increased light, removal of contact force from a resistive force sensor, and / or a sound associated with removing clothing. Alternatively or additionally, the wake-up stimulus may include multiple stimuli (e.g., any of the stimuli described above) sensed in a particular sequence or grouped closely in time. Particular embodiments of wearable devices including such wake-up sensors are described in further detail below.

[0063] Similarly, the defecation event sensor 114 can take a variety of forms. For example, the defecation event sensor 114 may include one or more electromyogram (EMG) electrodes for detecting electrical signals of the subject's abdominal muscles, which can indicate contraction of those muscles during a defecation event, such as a Valsalva maneuver. As another example, the defecation event sensor 114 may include one or more electrocardiogram (ECG) electrodes and / or one or more photoplethysmography (PPG) sensors for detecting electrical signals of the subject's heart, which can indicate a decrease and subsequent increase in heart rate during a Valsalva maneuver. As another example, the defecation event sensor 114 may include one or more mechanomyogram (MMG) sensors for detecting low-frequency vibrations of the subject's abdominal muscles, which can indicate contraction of those muscles during a defecation event. As another example, the defecation event sensor 114 may include one or more inertial measurement units (IMUs) for detecting changes in the subject's posture, more specifically, a change to a sitting posture before a defecation event and / or a change to a standing posture after a defecation event. As another example, the defecation event sensor 114 may include one or more audio sensors for detecting sounds emanating from the subject's bowels, toilet flushing sounds, and / or sounds associated with flatus. As another example, the defecation event sensor 114 may include one or more gas sensors configured to detect flatus. As another example, the defecation event sensor 114 may include one or more temperature sensors for detecting changes in bowel temperature that may occur before or during a defecation event. As another example, the defecation event sensor 114 may include one or more optical sensors and / or one or more resistive force sensors for detecting when the subject removes lower-body clothing. Particular embodiments of wearable devices including such defecation event sensors are described in further detail below.

[0064] Continuing with reference to FIG. 1 , in the illustrated embodiment, electronics assembly 108 further includes one or more health sensors 115 that detect stimuli associated with the subject's health. Health sensor 115 can take a variety of forms. For example, health sensor 115 may be a blood sensor that detects blood in the subject's stool, which may be indicative of one or more gastrointestinal disorders. More specifically, the blood sensor may be a solid-state vapor detection sensor that detects one or more volatile organic compounds (VOCs) that produce a "metallic odor" (e.g., hexanal, heptanal, octanal, nonanal, decanal, and / or 1-octen-3-one, which are formed by the reaction of ions in the blood with lipids in the stool). In some embodiments, health sensor 115 may normally be in a sleep mode, and health sensor 115 may be reconfigured to an active mode when one or more of bowel movement event sensors 114 detects a bowel movement event. Alternatively, the health sensor 115 may normally be in a sleep mode, and the health sensor 115 may be reconfigured to an active mode when one or more of the wake-up sensors 110 detect one or more wake-up stimuli.

[0065] 1, processor 112 may be any device or component capable of executing stored software and / or firmware code that, when executed by processor 112, causes wearable device 102 to perform the functions described herein. Processor 112 may be, for example, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), hardwired logic, a combination thereof, etc.

[0066] The processor 112 is operatively coupled (illustratively via wired communication) to memory 116 for storing data related to the fault event and / or the subject's health. Such data may include, for example, bowel movement event time, event length, wake-up sensors 110 and / or bowel movement event sensors 114 that detected the event, wake-up sensors 110 and / or bowel movement event sensors 114 that did not detect the event, data received from health sensors 115, etc. The memory 116 may be any suitable computer-readable medium accessible by the processor 112. The memory 116 may be a single storage device or multiple storage devices, may be located internal or external to the processor 112, and may include both volatile and non-volatile media. Memory 116 may be, for example, random-access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), flash memory, a magnetic storage device, optical disk storage, or any other suitable medium capable of storing data and accessible by processor 112.

[0067] The processor 112 is also operatively coupled (illustratively via wired communication) to a power source 118 to provide power to various components of the electronics assembly 108, including the wake-up sensor 110, the bowel movement event sensor 114, and the health sensor 115. The power source 118 may be, for example, one or more rechargeable batteries, one or more inductive / wireless power receivers, etc.

[0068] 1 , processor 112 is also operatively coupled (illustratively via wired communication) to user interface 122. User interface 122 operates to receive one or more user inputs (e.g., to manually confirm the occurrence of a bowel movement event) and / or to display data, information, and / or prompts generated by system 100. User interface 122 may include at least one input device for receiving user input. User interface 122 may include a graphical user interface (GUI) having a touchscreen display operable to display data and receive user input. Alternatively, user interface 122 may include a non-touchscreen display, a keyboard, a keypad, a microphone, a speaker, a combination thereof, etc.

[0069] The processor 112 is further operatively coupled to a transmitter 120 (illustratively via wired communication) for wirelessly transmitting information, such as bowel movement event information and / or subject health data stored by the memory 116, to the remote device 104. The transmitter 120 may be, for example, a Bluetooth transmitter, an IEEE 802.11 transmitter, a cellular communication transmitter, a short-range communication transmitter, or the like. The transmitter 120 may be continuously or intermittently coupled to the remote device 104. A transceiver (not shown) may be used in place of the transmitter 120 to facilitate providing information from the remote device 104 to the wearable device 102. Such information may include, for example, software updates.

[0070] The remote device 104 may be, for example, a mobile device such as a smartphone, smartwatch, or tablet device, a personal computer, a remote computer, or a database, etc. In a clinical trial setting, the remote device 104 may be capable of analyzing bowel event data and / or subject health data received from various wearable devices 102 and evaluating the effectiveness of one or more treatments provided to subjects using the wearable devices 102. In other settings, the remote device 104 may include or be operably coupled to one or more displays for providing bowel event data and / or subject health data to a user, such as a healthcare provider or a subject, using the wearable device 102.

[0071] System 100, and more particularly wearable device 102, can be modified in various ways. For example, transmitter 120 may be coupled to remote device 104 via wired communication, or processor 112 may be operably coupled to one or more of the other components of electronics assembly 108 via wireless communication. Similarly, in some embodiments, wearable device 102 may lack processor 112, and sensors 110, 114, 115 may instead be operably coupled to a processor of remote device 104, such as a processor of a smartphone. In some embodiments, wearable device 102 may not include user interface 122 and may instead rely on wireless communication with remote device 104 to convey information to and / or receive instructions from a user. As a further example, in some embodiments, there may be two or more wearable devices 102, each operably coupled to a remote device 104. For example, there may be a first wearable device 102 in the form of a smartwatch and a second wearable device 102 in the form of a patch configured to be carried on the torso of a subject, and both wearable devices are operably coupled to a remote device 104 (e.g., a smartphone). In such an embodiment, all wearable devices may include similar sensors 110, 114, and / or 115, or the wearable devices may include different sensors 110, 114, and / or 115. As a specific example, the first wearable device 102 in the form of a smartwatch may include an audio sensor and an accelerometer / motion sensor that function as a bowel movement event sensor, while the second wearable device 102 in the form of a torso patch may include other types of bowel movement event sensors (e.g., a gas sensor, a mechanomyogram sensor, and / or an electromyogram sensor). Because all wearable devices are operably coupled to the remote device 104, the remote device 104 can use input from all operably coupled wearable devices to detect a bowel movement event.

[0072] 2 and 3, a wearable device 202 according to one embodiment of the present disclosure is shown. The wearable device 202 is a more specific embodiment of the wearable device 102 described above. As such, the wearable device 202 includes some of the same components and operates in the same manner as the wearable device 102 described above. The wearable device 202 also operably couples to one or more remote devices 104, as described above. The wearable device 202 includes a base or housing 206 configured to be removably worn by a subject. More specifically, the base 206 is a patch that can be adhesively secured to the subject's torso. A patient-facing side 222 of the base 206 can be adhesively secured to the subject. The patient-facing side 222 of the base 206 also includes one or more bowel movement event sensors 214, more specifically, a plurality of electromyography electrodes 224 for sensing the subject's abdominal muscle electrical signals. The base 206 also carries one or more wake-up sensors 210, more specifically, an elongated optical sensor 226 positioned under the lower body garment and configured to detect when the subject removes the lower body garment. The base 206 carries a processor 212 and a power source 218 therein. In some embodiments, the base 206 can carry additional sensors, such as an inertial measurement unit, a gas sensor, a mechanomyogram sensor, or any of the other sensors contemplated herein.

[0073] 4A and 4B, a wearable device 302 according to another embodiment of the present disclosure is shown. The wearable device 302 is another, more specific embodiment of the wearable device 102 described above. As such, the wearable device 302 includes some of the same components and operates in the same manner as the wearable device 102 described above. The wearable device 302 also operably couples to one or more remote devices 104, as described above. The wearable device 302 includes a base 306 configured to be removably worn by a subject. More specifically, the base 306 is a patch that can be adhesively secured to the subject's torso. A patient-facing side 322 of the base 306 can be adhesively secured to the subject. The patient-facing side 322 of the base 306 also includes one or more defecation event sensors 314, more specifically, a plurality of electromyography (EMG) electrodes 324 for detecting the subject's abdominal muscle electrical signals and a mechanomyography (MG) sensor 325 ( FIG. 4B ) for detecting the subject's abdominal muscle movement signals. The opposite side 328 of the base 306 removably carries a hub 330 ( FIG. 4A ) that operably couples to the defecation event sensors 314. The hub 330 carries a processor (not shown), memory (not shown), and a power source (not shown). The hub 330 may be detached from the base 306 to facilitate recharging of the power source. The hub 330 also carries the user interface 320 ( FIG. 4A ), more specifically, one or more lights 332 and a speaker 334 for providing information to the subject. In some embodiments, the base 306 may carry additional sensors, such as an optical sensor, an audio sensor, an inertial measurement unit, a gas sensor, or any of the other sensors discussed herein.

[0074] Referring to FIG. 5 , a wearable device 402 according to yet another embodiment of the present disclosure is shown. The wearable device 402 is yet another, more specific embodiment of the wearable device 102 described above. Accordingly, the wearable device 402 includes some of the same components and operates in the same manner as the wearable device 102 described above. The wearable device 402 also operably couples to one or more remote devices 104, as described above. The wearable device 402 includes a base 406 configured to be removably worn by a subject. More specifically, the base 406 is a belt that can extend around and be secured to the subject's torso. A patient-facing side 422 of the base 406 also includes one or more bowel movement event sensors 414, more specifically, a plurality of electromyography electrodes 424, an inertial measurement unit 436, and a mechanomyography sensor 438. In some embodiments, the base 406 may carry additional sensors, such as optical sensors, audio sensors, or any of the other sensors discussed herein.

[0075] 6-8, a wearable device 502 according to yet another embodiment of the present disclosure is shown. The wearable device 502 is yet another, more specific embodiment of the wearable device 102 described above. As such, the wearable device 502 includes some of the same components and operates in the same manner as the wearable device 102 described above. The wearable device 502 also operably couples to one or more remote devices 104, as described above. The wearable device 502 includes a base or housing 506 configured to be removably worn by a subject. More specifically, the base 506 carries a patch 540 (FIG. 6) that can be adhesively secured to the subject's torso. The base 506 also carries one or more bowel movement event sensors 514 (FIG. 8). More specifically, the base 506 carries a mechanomyogram sensor 524 for detecting abdominal muscle movement signals of the subject and a temperature sensor 542 for detecting intestinal temperature changes. The base 506 carries a processor 512 (FIG. 8) and a battery (not shown) therein. The base 506 also carries a user interface 520 (FIG. 7). The user interface 520 includes a first input 544 operable to reconfigure the device 502 from a sleep mode to an active mode. The user interface 520 further includes a second input 546 operable to reconfigure the device 502 from an active mode to a sleep mode. In some embodiments, the base 506 may carry additional sensors, such as an optical sensor, an inertial measurement unit, an audio sensor, a gas sensor, an electromyogram sensor, or any of the other sensors discussed herein.

[0076] Systems according to embodiments of the present disclosure can determine the occurrence of a defecation event in various manners. For example, in some embodiments, the system can determine the occurrence of a defecation event when at least a certain number of defecation event sensors 114 detect a corresponding stimulus (as a more specific example, when a majority of the defecation event sensors 114 detect a corresponding stimulus). In other embodiments, the system can determine the occurrence of a defecation event when all of the defecation event sensors 114 detect a corresponding stimulus. In some embodiments, the system can use machine learning to improve the accuracy of determining the occurrence of a defecation event for a particular subject. More specifically, some systems can recognize that one or more particular stimuli are consistently detected before or during a defecation event for a particular subject, and the system can weight the information received from the corresponding sensors more heavily when determining the occurrence of a defecation event. In some embodiments, the system can determine the occurrence of a defecation event when the defecation event sensors 114 detect a corresponding stimuli according to a particular sequence or algorithm. Similarly, in some embodiments, the system can reconfigure the device from sleep mode to active mode when the wake-up sensor 110 detects a corresponding stimuli according to a particular sequence or algorithm.

[0077] 9 , a method 600 for detecting a defecation event in a subject is shown, according to one embodiment of the present disclosure. Prior to commencing method 600, a wearable device, such as any of the wearable devices contemplated herein, is attached to the subject's torso. Method 600 begins, at block 602, by detecting increased light with an optical sensor in the wearable device when the subject removes lower body clothing. Method 600 continues, at block 604, by detecting abdominal muscle movement signals with a mechanomyogram sensor in the wearable device. Method 600 concludes, at block 606, by determining the occurrence of a defecation event based at least in part on the subject's detected abdominal muscle movement signals and the increased light detected when the subject removes lower body clothing.

[0078] Method 600 may be modified in various ways and / or may include various additional operations. For example, method 600 may further include reconfiguring the wearable device from a sleep mode, in which the mechanomyogram sensor is inactive, to an active mode, in which the mechanomyogram sensor is configured to detect abdominal muscle movement signals from the subject based on increased light detected when the subject removes lower body clothing. As another example, method 600 may further include detecting flatus with a gas sensor of the wearable device, and determining that a defecation event has occurred may be based at least in part on the detected flatus. As yet another example, method 600 may further include detecting a standing movement by the subject after detecting flatus with an inertial measurement unit of the wearable device, and determining that a defecation event has occurred may be based at least in part on the detected standing movement. As yet another example, method 600 may further include detecting, by an inertial measurement unit of the wearable device, a sitting motion by the subject prior to detecting the abdominal muscle movement signal of the subject, and determining that a bowel movement event has occurred may be based at least in part on the detected sitting motion. As another example, method 600 may be repeated to determine multiple bowel movement events over a period of time, such as multiple days, weeks, months, or years. As an alternative example, detecting an abdominal muscle movement signal in block 604 may precede detecting increased light in block 602.

[0079] 10-16 illustrate operations associated with another method for detecting a bowel movement event in a subject according to one embodiment of the present disclosure. Prior to commencing the method, a wearable device 702, such as any of the wearable devices contemplated herein, is attached to the torso of the subject S. As shown in FIG. 10, the method begins by (A) detecting abdominal muscle movement signals of the subject S with a mechanomyogram sensor (not shown) of the wearable device 702, (B) detecting temperature changes in the subject's bowel with a temperature sensor (not shown) of the wearable device 702, and / or (C) detecting sounds emanating from the subject's bowel with an audio sensor (not shown) of the wearable device 702. As shown in FIG. 11, the method continues by detecting increased light when the subject S removes lower-body clothing with an optical sensor (not shown) of the wearable device 702. As shown in FIG. 12, the method then includes detecting a sitting movement of the subject S with an inertial measurement unit (not shown) of the wearable device 702. As shown in Figure 13, the method continues by detecting abdominal muscle movement signals of subject S via a mechanomyogram sensor (not shown) of the wearable device 702. As shown in Figure 14, the method then includes detecting flatus via a gas sensor (not shown) of the wearable device 702. As shown in Figure 15, the method continues by detecting a standing movement of subject S via an inertial measurement unit (not shown) of the wearable device 702. As shown in Figure 16, the method then includes (A) detecting a hand movement to flush the toilet via an inertial measurement unit (not shown) of a remote device, illustratively a smartwatch 704 worn by subject S, and / or (B) detecting a toilet flush sound via an audio sensor (not shown) of the remote device. The method concludes by determining the occurrence of a bowel movement event based at least in part on one or more of the previously detected stimuli.The methods for detecting a defecation event presented in Figures 10-16 may be modified by omitting one or more of the previously presented steps, adding additional steps between some of the previously presented steps, and / or rearranging the order of the presented steps. For example, in some embodiments, the method may not include detecting bowel temperature changes and / or sounds emanating from the subject's bowel (as shown in Figure 10), but instead may begin with detecting increased light when subject S removes lower body clothing (as shown in Figure 11). In some embodiments, the method may omit detecting flatus (as shown in Figure 14). In still other embodiments, the method may omit detecting posture changes with an inertial measurement unit (as shown in Figures 13 and 15). Any sequence of all or any subset of the presented steps may be used to determine the occurrence of a defecation event.

[0080] The sensitivity and specificity of the systems and methods described herein for detecting a bowel movement event in a subject may be improved using machine learning techniques. Referring to FIG. 17 , a method 800 for training one or more processors to detect a bowel movement event is shown, according to an embodiment of the present disclosure. Prior to commencing method 800, a first wearable device, such as a smartwatch or any of the wearable devices contemplated herein, and a second wearable device, such as any of the wearable devices contemplated herein, may be provided to a subject for attachment to the subject's body. Both wearable devices may take the form of a wearable device 102 described herein (see, e.g., FIG. 1 ). The first wearable device may include a first bowel movement event sensor 114 configured to detect one or more first stimuli, and the second wearable device may include a second bowel movement event sensor 114 configured to detect one or more second stimuli. The first wearable device and the second wearable device are operably coupled to one or more processors in any of the manners contemplated herein, either wirelessly or through a wired connection. In some embodiments, the one or more processors may comprise a first processor operably coupled to the first wearable device (e.g., embedded within or in wireless communication with the first wearable device) and a second processor operably coupled to the second wearable device (e.g., embedded within or in wireless communication with the second wearable device). In such embodiments, the first processor may be operably coupled to the second processor such that the two processors can function together to implement method 800. In some embodiments, the one or more processors may consist of a single processor operably coupled to both the first wearable device and the second wearable device. This single processor may reside on the first wearable device, on the second wearable device, or on a remote device 104 (e.g., a smartphone) operably coupled to both wearable devices.

[0081] Method 800 begins at block 802 by detecting one or more first defecation stimuli by one or more first defecation event sensors carried by a first wearable device. Method 800 continues at block 804 by detecting one or more second stimuli associated with one or more deficiency events in the subject by one or more second defecation event sensors carried by a second wearable device. The stimuli detected (by both the first defecation event sensor and the second defecation event sensor) may be any of the stimuli contemplated herein. In some embodiments, the first defecation stimulus and the second defecation stimulus may be different types of stimuli. For example, the second defecation event sensor may be an EMG electrode and / or an MMG sensor, the second stimulus may be an abdominal muscle electrical signal and / or an abdominal muscle movement signal of the subject, the first defecation event sensor may be an inertial measurement unit, and the first stimulus may be movement of the subject. In other embodiments, the first defecation stimulus and the second defecation stimulus may be the same type of stimulus. Method 800 continues at block 806 by determining, by one or more processors, the occurrence of a detected defecation event in the subject based on the second stimulus. This determination may be accomplished through any of the methods discussed herein. Method 800 continues at block 808 by associating, by one or more processors, a first stimulus detected by the first defecation event sensor within a predetermined period of the detected defecation event (e.g., within 60, 120, 180, and / or 240 seconds before and / or after the detected defecation event) with the subject's defecation event. The one or more processors can then use data indicative of the first stimulus detected by the first defecation event sensor associated with the subject's defecation event to train a machine learning algorithm for detecting the subject's defecation event.

[0082] Method 800 may be useful for training a machine learning algorithm implemented on one or more processors to detect a bowel movement event of a subject using a first stimulus sensed by a first bowel movement event sensor. In particular, method 800 may be useful in situations where a second bowel movement event sensor is initially capable of detecting a bowel movement event with greater sensitivity and / or specificity than the first bowel movement event sensor, but where it is ultimately desirable to detect a bowel movement event using only or primarily the first bowel movement event sensor.

[0083] As an illustrative and non-limiting example, the second wearable device may be a patch configured to be secured to the subject's torso, as described herein. The patch may include an MMG sensor, an EMG sensor, an ECG sensor, an optical sensor, a gas sensor, and / or other sensors as described herein. The first wearable device may be a smartwatch configured to be worn on the subject's wrist. The smartwatch may include additional or different sensors, such as an accelerometer / inertial measurement unit (IMU) and / or an audio sensor. The second wearable device may initially be capable of detecting bowel movements with greater specificity and sensitivity than the first wearable device, but may be more cumbersome and / or inconvenient for the subject to wear over an extended period of time. Thus, it may be desirable to eventually train one or more processors to use only the first wearable device (i.e., the smartwatch) to detect bowel movements without the assistance of the second wearable device. To achieve this training, the second wearable device, upon detecting a bowel movement event using the techniques described herein, may instruct one or more processors to associate recent (e.g., within 60 or 120 seconds before or after the detected bowel movement event) motion and / or audio signals recorded by the smartwatch with the bowel movement. In this way, the second wearable device provides ground truth labels that enable the smartwatch to distinguish motion and / or audio signals associated with bowel movements from motion and / or audio signals not associated with bowel movements. Over time, as the wearable patch trains the one or more processors, the processors can use the stimuli sensed by the smartwatch to predict and / or detect bowel movements with increasing accuracy. Eventually, once the smartwatch (or mobile device) is fully trained, the subject may stop wearing the wearable patch and rely solely on the smartwatch to detect bowel movements.

[0084] Training the machine learning algorithm in the one or more processors can be accomplished using any known machine learning technique. For example, the one or more processors may use a neural network having multiple layers of nodes to predict or detect a defect event based on a stimulus sensed by a first defecation event sensor. The sensitivity and specificity of such a neural network can be improved by adjusting the weights associated with such layers of nodes using ground truth data providing examples of first stimuli associated with defecation events and examples of first stimuli not associated with defecation events. Such ground truth data can be provided by a second defecation event sensor on a second wearable device, as described herein. The weights in the neural network can be adjusted using an iterative training procedure that compares predicted outputs based on a particular first stimulus with ground truth labels provided by the second wearable device indicating whether such first stimulus is associated with a defecation event. If the neural network's predictions do not match the ground truth labels, the weights can be adjusted according to a loss function to improve the agreement between the network's predictions and the ground truth labels. In this manner, by providing a ground truth label indicating whether a particular first stimulus is associated with a defecation event, the weights of the neural network can be adjusted to improve the network's detection of a defecation event based solely on the first stimulus.

[0085] Method 800 may be modified in various ways and / or may include various additional operations. For example, one or more processors may be trained to determine the occurrence of a defecation event when one or more defecation event sensors of the first wearable device detect corresponding stimuli according to a particular sequence or algorithm. As another example, the first wearable device may further include a wake-up sensor configured to detect one or more wake-up stimuli. The first wearable device may be further configured to transition from a sleep mode to an active mode in which the first wearable device is configured to detect a defecation event of interest via the first defecation event sensor when the wake-up sensor detects a wake-up stimulus associated with the defecation event of interest. Method 800 may be modified by having the one or more processors associate a wake-up stimulus detected by the wake-up sensor within a second predetermined period of the detected defecation event (e.g., within 60, 120, 180, and / or 240 seconds before and / or after the detected defecation event) with the defecation event. The second predetermined period may be the same as the predetermined period or may be different from the predetermined period. In this manner, the one or more processors can be trained not only to detect bowel movement events with greater sensitivity and specificity, but also to wake up from a sleep mode to an active mode to detect such bowel movement events with greater accuracy. This may help to conserve power used by the one or more processors and / or the first wearable device.

[0086] 18 , another method 900 for training one or more processors to detect a defecation event is shown, according to one embodiment of the present disclosure. Prior to commencing method 900, a wearable device, such as any of the wearable devices contemplated herein, may be provided to a subject for attachment to the subject's body. The wearable device may take the form of wearable device 102 described herein (see, e.g., FIG. 1 ) and may include a defecation event sensor 114 configured to detect one or more stimuli. The wearable device, and the defecation event sensor provided therein, may be operably coupled to one or more processors. The one or more processors may be provided on the wearable device or may communicate wirelessly with the wearable device. For example, the one or more processors may reside on a remote device 104 (e.g., a smartphone).

[0087] Method 900 begins at block 902 by detecting one or more stimuli by a bowel movement event sensor of the wearable device. Method 900 continues at block 904 by receiving user input via the subject's mobile device (e.g., remote device 104) indicating a bowel movement time at which a bowel movement event occurred. The user input may include manual input from the subject (e.g., activation of a physical button and / or a virtual button on a touchscreen, voice input) that a bowel movement event occurred at the time the user provided the input. Alternatively, or additionally, the user input may include manual input from the subject indicating that a bowel movement event occurred at a particular time in the past. Alternatively, or additionally, the user input may include manual input from the subject indicating that a bowel movement event is about to occur (e.g., the subject is about to defecate).

[0088] Method 900 continues at block 906 by associating, by the one or more processors, a stimulus detected by a defecation event sensor within a predetermined period of time (e.g., within 60, 120, 180, and / or 240 seconds before and / or after the defecation time) received from the subject with a defecation event. The one or more processors can then use data indicative of a first stimulus detected by a first defecation event sensor associated with the subject's defecation event to train a machine learning algorithm for detecting a defecation event in the subject. In this manner, the machine learning algorithm implemented by the one or more processors for detecting a defecation event based on the stimulus detected by the defecation event sensor can be trained using ground truth data manually provided by the subject. Such training may be implemented using any of the techniques described herein.

[0089] While this invention has been shown and described as having a preferred design, the invention may be modified within the spirit and scope of this disclosure. This application is therefore intended to cover any variations, uses, or adaptations of the invention using its general principles. Further, this application is intended to cover such departures from the disclosure as come within known or customary practice in the art to which this invention pertains.

Claims

1. 1. A system for detecting a bowel movement event in a subject, the system comprising: a wearable device configured to be carried on the subject's torso, the wearable device being operable in a sleep mode and an active mode, the wearable device comprising: a wake-up sensor configured to detect a first stimulus; a mechanomyogram sensor configured to detect abdominal muscle movement signals of the subject; and a processor operably coupled to the wake-up sensor and the mechanomyogram sensor, the processor configured to switch the wearable device from the sleep mode to the active mode based on the first stimulus detected by the wake-up sensor, and in the active mode, the wearable device configured to communicate with the processor to determine the occurrence of a bowel movement event in the subject based on an abdominal muscle movement signal detected by the mechanomyogram sensor.

2. 2. The system of claim 1, wherein the abdominal muscle movement signal of the subject is a second stimulus, the system further comprising a third sensor operably coupled to the processor and configured to detect a third stimulus, and in the active mode, the processor is configured to determine the occurrence of a bowel movement event in the subject based on the abdominal muscle movement signal detected by the mechanomyogram sensor and the third stimulus detected by the third sensor.

3. 3. The system of claim 2, wherein the third sensor comprises a gas sensor disposed within the wearable device and configured to detect flatus.

4. The system of claim 2 , wherein the third sensor is an audio sensor configured to detect toilet flush sounds.

5. The system of claim 2 , wherein the third sensor is an electromyography electrode configured to sense electrical muscle signals of the subject.

6. The system of claim 2 , wherein the third sensor is an inertial measurement unit configured to sense changes in the subject's attitude.

7. 7. The system of claim 1, wherein the wearable device further comprises a patch configured to be carried on the torso of the subject, the patch carrying the wake-up sensor and the mechanomyogram sensor.

8. The system of claim 7 , wherein the patch further carries the processor.

9. 7. The system of claim 1, wherein the wearable device further comprises a belt configured to extend around the torso of the subject, the belt carrying the wake-up sensor and the mechanomyogram sensor.

10. The system of claim 9 , wherein the belt further carries the processor.

11. The system of any one of claims 1 to 10, wherein the wake-up sensor comprises one of an optical sensor and a resistive force sensor configured to detect when the subject removes lower body clothing.

12. The system of any one of claims 1 to 11, wherein the wearable device further comprises a health sensor configured to detect a health stimulus associated with the subject's health.

13. 13. The system of claim 12, wherein the health sensor comprises a blood sensor configured to detect blood in the subject's stool.

14. 14. The system of claim 13, wherein the blood sensor comprises a solid-state vapor detection sensor configured to sense one or more volatile organic compounds.

15. 1. A system for detecting a bowel movement event in a subject, the system comprising: a wearable device configured to be carried on the subject's torso, the wearable device comprising: a mechanomyogram sensor configured to detect abdominal muscle movement signals of the subject; a gas sensor configured to detect flatus; and a processor operably coupled to the mechanomyogram sensor and the gas sensor, the processor configured to determine the occurrence of a defecation event in the subject based on abdominal muscle movement signals detected by the mechanomyogram sensor and flatus detected by the gas sensor.

16. 16. The system of claim 15, wherein the processor is configured to determine the occurrence of a defecation event in the subject based on a sequence of events including one of the abdominal movement signal detected by the mechanomyogram sensor and the flatus detected by the gas sensor preceding the other of the abdominal movement signal detected by the mechanomyogram sensor and the flatus detected by the gas sensor.

17. 17. The system of claim 15 or 16, wherein the wearable device further comprises a base carrying the mechanomyogram sensor, the gas sensor, and the processor.

18. 1. A system for detecting a bowel movement event in a subject, the system comprising:

1. A wearable device configured to be carried on the subject's torso and beneath lower body clothing worn by the subject, the wearable device comprising: a wearable device comprising an optical sensor configured to detect increased light when the subject removes the lower body garment; and a processor operably coupled to the optical sensor, the processor configured to determine the occurrence of a defecation event based at least in part on the increased light detected by the optical sensor.

19. 20. The system of claim 18, wherein the wearable device is operable in an active mode and a sleep mode, and the processor is configured to switch the wearable device from the sleep mode to the active mode when the processor determines in response to the increased light detected by the optical sensor that the subject has removed the lower body garment.

20. 20. The system of claim 19, wherein the optical sensor is a first sensor configured to detect light as a first stimulus, the wearable device further comprising a second sensor configured to detect a second stimulus when the wearable device is in the active mode, the second stimulus being different from the first stimulus, the processor is operably coupled to the second sensor, and the processor is configured to determine the occurrence of a bowel movement event in the subject based on a signal received from the second sensor.

21. 20. The system of claim 19, wherein the optical sensor is a first sensor configured to detect light as a first stimulus, the wearable device further comprising a second sensor configured to detect a second stimulus when the wearable device is in the active mode, the second stimulus being different from the first stimulus, the processor is operably coupled to the second sensor, and the processor is configured to determine the occurrence of a bowel movement event in the subject based on signals received from the first sensor and the second sensor.

22. 22. The system of claim 20 or 21, wherein the second sensor is a mechanomyogram sensor.

23. 23. The system of any one of claims 18 to 22, wherein the wearable device further comprises a patch configured to be carried on the torso of the subject, the patch carrying the optical sensor and the processor.

24. 23. The system of any one of claims 18 to 22, wherein the wearable device further comprises a belt configured to extend around the torso of the subject, the belt carrying the optical sensor and the processor.

25. 1. A method for detecting a defecation event in a subject, the method comprising: detecting, with an optical sensor of a wearable device carried on the torso of the subject, increased light when the subject removes lower body clothing; detecting abdominal muscle movement signals of the subject with a mechanomyogram sensor of the wearable device; determining the occurrence of the defecation event based at least in part on the increased light detected when the subject removes the lower body garment and the abdominal movement signal detected of the subject.

26. 26. The method of claim 25, further comprising detecting flatus by a gas sensor of the wearable device, wherein the determination that the defecation event has occurred is based at least in part on the detected flatus.

27. 27. The method of claim 25 or 26, further comprising detecting a sitting motion by the subject by an inertial measurement unit of the wearable device before detecting the abdominal movement signal of the subject, and wherein the determination that the defecation event has occurred is based at least in part on the detected sitting motion.

28. 28. The method of any one of claims 25 to 27, further comprising detecting, by an inertial measurement unit of the wearable device, a standing up movement by the subject after detecting the flatus, and wherein the determination that the defecation event has occurred is based at least in part on the detected standing up movement.

29. 29. The method of any one of claims 25 to 28, further comprising detecting multiple bowel movement events in the subject over a period of time.

30. Detecting each of the plurality of bowel movement events in the subject comprises: detecting abdominal muscle movement signals of the subject with the mechanomyogram sensor of the wearable device; detecting, with the optical sensor, increased light when the subject removes lower body clothing; and determining the occurrence of each of the plurality of defecation events based at least in part on the detected abdominal movement signal of the subject and the increased light detected when the subject removes the lower body garment.

31. 31. The method of any one of claims 25 to 30, wherein detecting the increased light by the optical sensor when the subject removes the lower body garment precedes detecting the abdominal muscle movement signal of the subject by the mechanomyogram sensor.

32. 31. The method of any one of claims 25 to 30, wherein detecting the abdominal muscle movement signal of the subject with the mechanomyogram sensor precedes detecting the increased light with the optical sensor when the subject removes the lower body garment.

33. 31. The method of claim 25, further comprising reconfiguring the wearable device from a sleep mode to an active mode based on the increased light detected when the subject removes the lower body garment, wherein in the sleep mode the mechanomyogram sensor is inactive and in the active mode the mechanomyogram sensor is configured to detect the abdominal muscle movement signals of the subject.

34. 1. A system for training one or more processors to detect a defecation event in a subject, the system comprising: a first wearable device configured to be carried on a body of the subject, the first wearable device comprising a first bowel movement event sensor configured to detect one or more first stimuli; a second wearable device configured to be carried on the body of the subject, the second wearable device comprising a second bowel movement event sensor configured to detect one or more second stimuli; and one or more processors operably coupled to the first bowel movement event sensor and the second bowel movement event sensor, and configured to determine the occurrence of a detected bowel movement event of the subject based on the one or more second stimuli, and to associate a first stimulus sensed by the first bowel movement event sensor within a predetermined period of the detected bowel movement event with the bowel movement event of the subject.

35. 35. The system of claim 34, wherein the one or more processors are further configured to train a machine learning algorithm for detecting a bowel movement event in the subject using data indicative of a first stimulus sensed by the first bowel movement event sensor that is associated with a bowel movement event in the subject.

36. the first wearable device further comprising a wake-up sensor configured to detect one or more wake-up stimuli; the first wearable device is configured to transition from a sleep mode to an active mode, in which the first wearable device is configured to detect a bowel movement event of the subject via the first bowel movement event sensor, when the wake-up sensor detects a wake-up stimulus associated with a bowel movement event of the subject; 36. The system of claim 34 or 35, wherein the one or more processors are further configured to associate a wake-up stimulus sensed by the wake-up sensor within a second predetermined period of the detected bowel movement event with the subject's bowel movement event.

37. 37. The system of any one of claims 34 to 36, wherein the one or more processors comprise a first processor operably coupled to the first bowel movement event sensor and a second processor operably coupled to the second bowel movement event sensor, the first processor and the second processor being operably coupled to each other.

38. 37. The system of any one of claims 34 to 36, wherein the one or more processors comprise a single processor operatively coupled to the first bowel movement event sensor and the second bowel movement event sensor.

39. The system of any one of claims 34 to 38, wherein the first wearable device comprises a smart watch.

40. 40. The system of any one of claims 34 to 39, wherein the second wearable device comprises a patch configured to be carried on the subject's torso.

41. The system of any one of claims 34 to 40, wherein the first wearable device comprises at least one of the one or more processors.

42. The system of any one of claims 34 to 40, wherein at least one of the one or more processors is in wireless communication with the first wearable device.

43. 43. The system of any one of claims 34 to 42, wherein the first stimulus and the second stimulus are different types of stimuli.

44. 43. The system of any one of claims 34 to 42, wherein the first stimulus and the second stimulus are the same type of stimulus.

45. 1. A method for training one or more processors operably coupled to a first wearable device to detect a bowel movement event in a subject, the method comprising: detecting one or more first stimuli by a first bowel movement event sensor carried by the first wearable device; sensing one or more second stimuli by a second bowel movement event sensor carried by a second wearable device; determining, by the one or more processors, the occurrence of a detected defecation event in the subject based on the second stimulus; and and associating, by the one or more processors, a first stimulus sensed by the first bowel movement event sensor within a predetermined period of the detected bowel movement event with the subject's bowel movement event.

46. 46. ​​The method of claim 45, further comprising training, by the one or more processors, a machine learning algorithm for detecting a defecation event in the subject using data indicative of a first stimulus sensed by the first defecation event sensor associated with the defecation event in the subject.

47. The first wearable device further comprises a wake-up sensor configured to detect one or more wake-up stimuli, and the first wearable device is configured to transition from a sleep mode to an active mode, in which the first wearable device is configured to detect a bowel movement event of the subject via the first bowel movement event sensor, when the wake-up sensor detects a wake-up stimulus associated with a bowel movement event of the subject, and the method includes:

46. ​​The method of claim 45, further comprising associating, by the one or more processors, a wake-up stimulus sensed by the wake-up sensor within a second predetermined period of the detected bowel movement event with the subject's bowel movement event.

48. 48. The method of any one of claims 45 to 47, wherein the one or more processors comprise a first processor operably coupled to the first bowel movement event sensor and a second processor operably coupled to the second bowel movement event sensor, the first processor and the second processor being operably coupled to each other.

49. 49. The method of any one of claims 45 to 48, wherein the one or more processors comprise a single processor operatively coupled to the first bowel movement event sensor and the second bowel movement event sensor.

50. The method of any one of claims 45 to 48, wherein the first wearable device comprises a smartwatch.

51. 51. The method of any one of claims 45 to 50, wherein the second wearable device comprises a patch configured to be carried on the subject's torso.

52. 52. The method of any one of claims 45 to 51, wherein the first wearable device comprises at least one of the one or more processors.

53. 52. The method of any one of claims 45 to 51, wherein at least one of the one or more processors is in wireless communication with the first wearable device.

54. 53. The method of any one of claims 45 to 52, wherein the first stimulus and the second stimulus are different types of stimuli.

55. 53. The method of any one of claims 45 to 52, wherein the first stimulus and the second stimulus are the same type of stimulus.

56. 1. A system for training one or more processors to detect a defecation event in a subject, the system comprising: a wearable device configured to be carried on a body of the subject, the wearable device comprising a bowel movement event sensor configured to detect one or more stimuli; a mobile device configured to receive user input from the subject indicating a bowel movement time when a bowel movement event occurred; one or more processors operably coupled to the bowel movement event sensor and the mobile device, the processors configured to associate a stimulus detected by the bowel movement event sensor within a predetermined time period of the bowel movement with a bowel movement event of the subject.

57. 57. The system of claim 56, wherein the one or more processors are further configured to train a machine learning algorithm for detecting a bowel movement event in the subject using data indicative of a first stimulus sensed by the first bowel movement event sensor associated with the subject's bowel movement event.

58. the wearable device further comprises a wake-up sensor configured to detect one or more wake-up stimuli; the wearable device is configured to transition from a sleep mode to an active mode, in which the wearable device is configured to detect a bowel movement event of the subject via the bowel movement event sensor, when the wake-up sensor detects a wake-up stimulus associated with a bowel movement event of the subject; 58. The system of claim 56 or 57, wherein the one or more processors are further configured to associate a wake-up stimulus detected by the wake-up sensor within a second predetermined period of the detected bowel movement event with the subject's bowel movement event.

59. The system of any one of claims 56 to 58, wherein the mobile device comprises at least one of the one or more processors.

60. 60. The system of any one of claims 56 to 59, wherein the wearable device comprises at least one of the one or more processors.

61. 61. The system of any one of claims 56 to 60, wherein the wearable device comprises at least one of a smart watch and a patch configured to be carried on the subject's torso.

62. 1. A method for training one or more processors operably coupled to a wearable device to detect a bowel movement event in a subject, the method comprising: detecting one or more stimuli with a bowel movement event sensor carried by the wearable device; receiving a user input via the subject's mobile device indicating a bowel movement time when a bowel movement event occurred; and associating, by the one or more processors, a stimulus detected by the bowel movement event sensor within a predetermined time period of the bowel movement with a bowel movement event of the subject.

63. 63. The method of claim 62, further comprising training, by the one or more processors, a machine learning algorithm for detecting a bowel movement event in the subject using data indicative of a first stimulus sensed by the first bowel movement event sensor associated with the subject's bowel movement event.

64. The wearable device further comprises a wake-up sensor configured to detect one or more wake-up stimuli, and the wearable device is configured to transition from a sleep mode to an active mode when the wake-up sensor detects a wake-up stimulus associated with a bowel movement event of the subject, and the method includes:

64. The method of claim 62 or 63, further comprising associating, by the one or more processors, a wake-up stimulus detected by the wake-up sensor within a second predetermined period of the detected bowel movement event with the subject's bowel movement event.

65. The method of any one of claims 62 to 64, wherein the mobile device comprises at least one of the one or more processors.

66. 66. The method of any one of claims 62 to 65, wherein the wearable device comprises at least one of the one or more processors.

67. 67. The method of any one of claims 62 to 66, wherein the wearable device comprises at least one of a smartwatch and a patch configured to be carried on the subject's torso.

Images