Analysis of bodily emissions

Abstract

To provide an apparatus for use with an output device regarding urine and feces of a subject that are emitted in a toilet bowl.SOLUTION: At least one computer processor is configured to: receive one or more urine-related parameters; determine that a subject is suffering from dehydration on the basis of at least some of the one or more urine-related parameters; receive one or more feces images; determine one or more feces-related parameters by performing computer vision analyses on the one or more feces images, the one or more feces-related parameters including at least one of texture or color of the feces, the computer vision analyses including at least one of detection of an area of interest, execution of form change, and execution of image segmentation using GrabCut; and perform output to an output device according to at least partially the above-mentioned processing.SELECTED DRAWING: Figure 1

Description

Detailed Description of the Invention

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Patent Application No. 63 / 006,130, by Kapp-Barnea, entitled "Detecting and classifying dehydration," filed April 7, 2020, which is incorporated herein by reference.

[0002] Field of the Invention Some applications of the present invention relate generally to the analysis of bodily exudates, and more particularly to devices and methods for detecting and classifying dehydration by analyzing bodily exudates such as urine and feces.

[0003] 〔background〕 Dehydration is widespread among the elderly, resulting in significant costs to both individuals and health care systems. The elderly are particularly vulnerable for a variety of reasons, including age-related changes in total body water content, impaired thirst perception, renal concentrating capacity, vasopressin efficacy, and medication-related subclinical thirst. Functional limitations, low voiding frequency, and urinary incontinence are very common among elderly patients, which may further increase vulnerability to dehydration. The effects of dehydration include confusion, disorientation, nausea, dizziness, general malaise, weakness, infections, coronary artery disease, impaired or delayed wound healing, and death. Symptoms of dehydration are often diverse and sometimes nonspecific. Precious and critical time is therefore lost in hospital diagnosis. This delay often results in a worsening of the condition.

[0004] Dehydration can be defined as a clinically significant decrease in an individual's optimal total body water (TBW) volume. Dehydration can occur with or without electrolyte loss. (See, for example, RF Kushner, DA Schoeller, "Estimation of total body water by bioelectrical impedance analysis," The American Journal of Clinical Nutrition, Vol. 44, No. 3, pp. 417-424, September 1986; and Weinberg AD1, Minaker KLJAMA, "Dehydration Evaluation and management in older adults," Council on Scientific Affairs, American Medical Association, 15;274(19):1552-6, November 1995.) There are three different forms of dehydration. Isotonic dehydration is due to the balanced loss of water and sodium. For example, fasting for longer than a given period of time can cause isotonic dehydration. Similarly, vomiting and diarrhea can cause isotonic dehydration because of the large amount of water and electrolytes in the stomach contents. Hypertonic dehydration, the most common type of dehydration, is caused by a greater loss of water than sodium. It is characterized by hypernatremia (e.g., serum sodium levels above 145 mmol / L) and hyperosmolarity (e.g., serum osmolality above 300 mmol / kg). Fever is probably the most common cause of hypertonic dehydration because of the limited ability to increase oral water intake and the frequent loss of water through the lungs and skin. Hypotonic dehydration occurs when sodium loss exceeds water loss. Serum sodium is decreased (e.g., less than 135 mmol / L) and serum osmolality is low (e.g., less than 280 mmol / kg). This type of dehydration is primarily caused by the overuse of diuretics, which causes excessive sodium loss.

[0005] [Overview of the embodiment] According to some applications of the present invention, one or more sensors coupled to the toilet detect one or more urine-related parameters associated with urine of the subject without requiring any action to be performed by any person after discharge of the urine into the toilet. Typically, the one or more sensors coupled to the toilet are further configured to detect one or more feces-related parameters associated with feces of the subject without requiring any action to be performed by any person after discharge of the feces into the toilet. A computer processor receives the one or more urine-related parameters and the one or more feces-related parameters. Based at least in part on the one or more urine-related parameters, the computer processor determines that the subject suffers from dehydration. Based at least in part on the one or more feces-related parameters, the computer processor classifies the dehydration as a given type of dehydration, such as, for example, isotonic dehydration, hypertonic dehydration, and hypotonic dehydration. Typically, an output is generated at least in part in response thereto.

[0006] In some applications, the computer processor is configured to derive a specific gravity of the subject's urine and determine that the subject is dehydrated based at least in part on the specific gravity of the subject's urine. In some such applications, the one or more sensors are configured to detect a signal indicative of absorption of cyan-green light by the subject's urine, and the computer processor is configured to derive the specific gravity of the subject's urine based at least in part on the signal. In some applications, the sensor is configured to detect a signal indicative of absorption of light in a wavelength band of 480-520 nm by the subject's urine, and the computer processor is configured to derive the specific gravity of the subject's urine based at least in part on the signal.

[0007] In some applications, the computer processor is configured to receive one or more of the urine-related parameters and derive parameters indicative of foaming and / or cloudiness of the subject's urine, estimate a concentration of albumin in the subject's urine based at least in part on the derived parameters, and generate an output on the output device in response to the estimated concentration of albumin in the subject's urine.

[0008] In some applications, the computer processor is configured to receive one or more of the urine-related parameters and derive a concentration of at least one hemoglobin derivative molecule in the subject's urine based at least in part on the one or more urine-related parameters. Typically, the at least one hemoglobin derivative molecule includes bilirubin, oxidized urobilinogen, and / or urobilin. The computer processor typically generates an output at least in part in response to the derived concentration of the at least one hemoglobin derivative molecule. In some such applications, the illumination component illuminates the subject's urine with light in a wavelength band within a range of 440-480 nm, and the sensor detects a signal indicative of light emitted by the subject's urine in a wavelength range of 505-535 nm in response to the illumination of the subject's urine. Typically, the computer processor determines a concentration of oxidized urobilin in the subject's urine at least in part in response to the signal. Alternatively or additionally, the sensor is configured to detect a signal indicative of absorption of light by the subject's urine within a wavelength band of 480-520 nm, and the computer processor is at least partially responsive to the signal to determine a concentration of oxidized urobilinogen in the subject's urine. Still alternatively or additionally, the sensor detects a plurality of signals indicative of absorption of light by the subject's urine within a first wavelength band of 390-420 nm and a second wavelength band of 445-475 nm. Typically, the computer processor is at least partially responsive to a plurality of the signals to determine a concentration of bilirubin in the subject's urine.

[0009] In some applications, one or more lighting components coupled to the toilet bowl are configured to illuminate the subject's urine with light in a wavelength band within a range of 300-520 nm. The sensor is configured to detect an intensity of light in a wavelength band within a range of 530-560 nm emitted by the urine in response to illuminating the urine. The computer processor derives a level of cellulose in the subject's urine based at least in part on the intensity of the detected light, and generates an output in response to the derived level of cellulose in the subject's urine. In some such applications, the computer processor is configured to detect that the subject has hematuria based on signals detected by the one or more sensors, and the computer processor is configured to activate the lighting component to illuminate the subject's urine with light in a wavelength band within a range of 300-520 nm in response to detecting that the subject has hematuria. Typically, the computer processor determines that the suspected cause of the subject's hematuria is a biofilm-based pathogen in the subject's urinary tract based on the derived level of cellulose in the subject's urine.

[0010] Thus, in accordance with some applications of the present invention, an apparatus for use with an output device with respect to urine and feces of a subject discharged into a toilet bowl, comprising: one or more sensors coupled to the toilet bowl, the one or more sensors configured to detect one or more urine-related parameters associated with urine of the subject without requiring any action to be performed by any person after discharge of the urine into the toilet bowl, and one or more feces-related parameters associated with feces of the subject without requiring any action to be performed by any person after discharge of the feces into the toilet bowl; An apparatus is provided comprising: at least one computer processor configured to receive one or more of the urine-related parameters; receive one or more of the fecal-related parameters; determine that the subject is suffering from dehydration based at least in part on the one or more urine-related parameters; classify the dehydration as a given type of dehydration selected from the group consisting of isotonic dehydration, hypertonic dehydration and hypotonic dehydration based at least in part on the one or more fecal-related parameters; and generate an output on the output device at least in part in response thereto.

[0011] In some applications, the at least one computer processor is configured to detect the one or more urine related parameters associated with the subject's urine by detecting a urine color. In some applications, the at least one computer processor is configured to detect the one or more urine related parameters associated with the subject's urine by detecting a urine volume. In some applications, the at least one computer processor is configured to detect the one or more urine related parameters associated with the subject's urine by detecting a urination duration.

[0012] In some applications, at least one of the computer processors is configured to detect one or more stool-related parameters associated with the subject's stool by detecting one or more stool-related parameters selected from the group consisting of shape, size, texture, and color.

[0013] In some applications, at least one computer processor is configured to detect one or more of the urine-related parameters associated with the subject's urine by detecting a urination frequency of the subject. In some applications, at least one computer processor is configured to detect a urination frequency of the subject by automatically detecting which person is urinating at a given time.

[0014] In some applications, at least one computer processor is configured to detect one or more stool-related parameters associated with the subject's stool by performing a computer vision analysis on the image of the stool. In some applications, at least one computer processor is configured to perform a computer vision analysis on the image of the stool by performing one or more steps selected from the group consisting of masking, contrast enhancement, image edge detection, region of interest detection, applying morphological changes, and performing segmentation.

[0015] In some applications, the at least one computer processor is configured to derive a specific gravity of the subject's urine and determine that the subject is dehydrated based at least in part on the specific gravity of the subject's urine. In some applications, the one or more sensors are configured to detect a signal indicative of absorption of cyan-green light by the subject's urine, and the at least one computer processor is configured to derive the specific gravity of the subject's urine based at least in part on the signal. In some applications, the one or more sensors are configured to detect a signal indicative of absorption of light in a wavelength band of 480-520 nm by the subject's urine, and the at least one computer processor is configured to derive the specific gravity of the subject's urine based at least in part on the signal.

[0016] In accordance with some applications of the present invention, a method for use with respect to urine and feces of a subject discharged into a toilet bowl, comprising the steps of: detecting, using one or more sensors coupled to the toilet bowl, one or more urine-related parameters associated with the urine of the subject after discharge of the urine into the toilet bowl without requiring any action to be taken by any person; and detecting, using one or more sensors coupled to the toilet bowl, one or more feces-related parameters associated with the feces of the subject after discharge of the feces into the toilet bowl without requiring any action to be taken by any person. and using a computer processor, receiving one or more of the urine-related parameters, receiving one or more of the fecal-related parameters, determining that the subject is suffering from dehydration based at least in part on the one or more urine-related parameters, classifying the dehydration as a given type of dehydration selected from the group consisting of isotonic dehydration, hypertonic dehydration and hypotonic dehydration based at least in part on the one or more fecal-related parameters, and generating an output on an output device at least in part in response thereto.

[0017] In some applications, detecting one or more urine related parameters associated with the subject's urine includes detecting a urine color. In some applications, detecting one or more urine related parameters associated with the subject's urine includes detecting a urine volume. In some applications, detecting one or more urine related parameters associated with the subject's urine includes detecting a urination duration.

[0018] In some applications, detecting one or more stool-related parameters associated with the subject's stool includes detecting one or more stool-related parameters selected from the group consisting of shape, size, texture, and color.

[0019] In some applications, detecting one or more urine-related parameters associated with the subject's urine includes detecting a urination frequency of the subject. In some applications, detecting a urination frequency of the subject includes automatically detecting which person is urinating at a given time.

[0020] In some applications, detecting one or more stool-related parameters associated with the subject's stool includes performing a computer vision analysis on an image of the stool. In some applications, performing a computer vision analysis on the image of the stool includes performing one or more steps selected from the group consisting of masking, contrast enhancement, image edge detection, region of interest detection, applying morphological changes, and performing segmentation.

[0021] In some applications, determining that the subject is dehydrated includes deriving a specific gravity of the subject's urine and determining that the subject is dehydrated based at least in part on the specific gravity of the subject's urine. In some applications, deriving a specific gravity of the subject's urine includes detecting a signal indicative of absorption of cyan-green light by the subject's urine and deriving the specific gravity of the subject's urine based at least in part on the signal. In some applications, deriving a specific gravity of the subject's urine includes detecting a signal indicative of absorption of light in a wavelength band of 480-520 nm by the subject's urine and deriving the specific gravity of the subject's urine based at least in part on the signal.

[0022] In accordance with some applications of the present invention, there is further provided an apparatus for use with an output device with respect to urine of a subject discharged into a toilet bowl, the apparatus comprising: one or more sensors coupled to the toilet bowl, the one or more sensors configured to detect one or more urine-related parameters associated with the subject's urine without requiring any action to be taken by any person after the urine is discharged into the toilet bowl; and at least one computer processor configured to receive the one or more urine-related parameters, derive a concentration of at least one hemoglobin derivative molecule in the subject's urine selected from the group consisting of bilirubin, oxidized urobilinogen, and urobilin based at least in part on the one or more urine-related parameters, and generate an output on the output device at least in part in response to the derived concentration of at least one hemoglobin derivative molecule.

[0023] In some applications, the device further includes an illumination component configured to illuminate the subject's urine with light in a wavelength band within a range of 440 to 480 nm, the one or more sensors configured to detect a signal indicative of light emitted by the subject's urine of a wavelength within a range of 505 to 535 nm in response to the illumination of the subject's urine, and at least one of the computer processors configured to determine a concentration of oxidized urobilin in the subject's urine, at least in part, in response to the signal.

[0024] In some applications, the one or more sensors are configured to detect a signal indicative of absorption of light within a wavelength band of 480 to 520 nm by the subject's urine, and at least one of the computer processors is configured, at least in part, to determine a concentration of oxidized urobilinogen in the subject's urine in response to the signal.

[0025] In some applications, the one or more sensors are configured to detect a plurality of signals indicative of absorption of light by the subject's urine within a first wavelength band of 390-420 nm and a second wavelength band of 445-475 nm, and the at least one computer processor is configured to determine a concentration of bilirubin in the subject's urine at least in part responsive to the plurality of signals. In some applications, the at least one computer processor is configured to determine a ratio of light absorption by the subject's urine in each of the first and second wavelength bands relative to one another, and to determine a concentration of bilirubin in the subject's urine based on the ratio.

[0026] In accordance with some applications of the present invention, there is further provided an apparatus for use with an output device with respect to urine of a subject discharged into a toilet bowl, the apparatus comprising: one or more sensors coupled to the toilet bowl, the one or more sensors configured to detect one or more urine-related parameters associated with the subject's urine without requiring any action to be taken by any person after discharge of the urine into the toilet bowl; and at least one computer processor configured to receive the one or more urine-related parameters, derive parameters indicative of foaming and / or cloudiness of the subject's urine, estimate a concentration of albumin in the subject's urine based at least in part on the derived parameters, and generate an output on the output device in response to the estimated concentration of albumin in the subject's urine.

[0027] In accordance with some applications of the present invention, there is further provided an apparatus for use with an output device with respect to a subject's urine discharged into a toilet bowl, the apparatus comprising: one or more lighting components coupled to the toilet bowl and configured to illuminate the subject's urine with light in a wavelength band within a range of 300-520 nm; one or more sensors coupled to the toilet bowl and configured to detect an intensity of light in a wavelength band within a range of 530-560 nm emitted by the urine in response to illuminating the urine; and at least one computer processor configured to derive a level of cellulose in the subject's urine based at least in part on the intensity of detected light, and generate an output on the output device in response to the derived level of cellulose in the subject's urine.

[0028] In some applications, the computer processor is configured to detect that the subject has hematuria based on signals detected by one or more of the sensors, and in response to detecting that the subject has hematuria, the computer processor is configured to drive the illumination component to illuminate the subject's urine with light in a wavelength band within a range of 300-520 nm. In some applications, the computer processor is configured to determine that a suspected cause of the subject's hematuria is a biofilm-based pathogen in the subject's urinary tract based on the derived level of cellulose in the subject's urine.

[0029] The present invention will be more fully understood from the following detailed description of the embodiments thereof when taken in conjunction with the drawings, in which: BRIEF DESCRIPTION OF THE DRAWINGS

[0030] FIG. 1 is a schematic diagram of an apparatus for analyzing bodily exudates, according to some applications of the present invention.

[0031] 2A-2E show representative images of some computer vision analysis steps performed on images of feces in a toilet bowl, according to some applications of the present invention.

[0032] FIG. 3 is a ROC curve illustrating the sensitivity and specificity of a classifier for detecting urine specific gravity based on blue light absorption by urine, according to some applications of the present invention.

[0033] FIG. 4 is a ROC curve illustrating the sensitivity and specificity of a classifier utilizing the sensor module described herein for detecting the presence of blood in a subject's urine, according to some applications of the present invention.

[0034] Detailed Description of the Embodiments Reference is now made to FIG. 1. FIG. 1 is a schematic diagram of a device 20 for analyzing bodily waste, according to some applications of the present invention. As shown, the device 20 includes a sensor module 22, typically disposed in a toilet bowl 23. In some applications (not shown), the sensor module (and / or additional components of the device) are integral with the toilet bowl. The sensor module includes one or more sensors 24. Typically, the one or more sensors are configured to detect one or more urine-related parameters (such as urination frequency, urine volume, urine color and / or urine consistency) and detect one or more feces-related parameters (such as feces shape, size, texture, etc.). In some applications, the one or more sensors detect at least some of the aforementioned parameters while the bodily waste is being discharged into the toilet bowl by the subject. Alternatively or additionally, the one or more sensors detect at least some of the aforementioned parameters when the bodily waste is placed into the toilet bowl after discharge by the subject. In some applications, the sensor includes an imaging component, such as an RGB camera, a spectral camera, and / or a hyperspectral camera. Alternatively or additionally, the one or more sensors may include one or more optical sensors configured to receive light from the bodily exudate. In some applications, the sensor module includes one or more lighting components 25. According to the respective application, such lighting components include lighting components (e.g., LEDs and / or lasers) configured to illuminate the bodily exudate in a given spectral band and / or a broadband light source. In some applications, the broadband light source is used in combination with one or more bandpass filters (which may be used to filter the emitted and / or detected light).

[0035] Typically, the computer processor receives one or more urine-related parameters from the one or more sensors as well as one or more fecal-related parameters from the one or more sensors. Depending on the respective application, the computer processor performing the analysis described herein is the computer processor 28 disposed in the housing 30 (which typically also houses the sensor module) or is a different computer processor in communication with the sensor module. Typically, based at least in part on the one or more urine-related parameters, the computer processor determines that the subject suffers from dehydration. For example, the one or more urine-related parameters detected by the one or more sensors may include urine color, urine volume (which may be measured by detecting the height h of urine in the toilet bowl), urination duration (which may be measured by detecting the time over which the height h of urine in the toilet bowl rises), and / or urination frequency. Typically, to detect the urination frequency of a particular subject, the sensor module is configured to receive an input from the subject indicating that the subject is currently using the toilet bowl, or the sensor module is configured to automatically detect which subjects are urinating in the toilet bowl at a given time.

[0036] In some applications, based at least in part on one or more stool-related parameters (such as stool shape, size, texture, color, etc.), the computer processor classifies the dehydration as a given type of dehydration, such as isotonic dehydration, hypertonic dehydration, or hypotonic dehydration. For example, the one or more sensors may include one or more cameras. In such applications, the computer processor typically receives one or more images of the stool and analyzes the images to determine spatial and / or textural and / or color parameters of the stool. In some applications, images captured at different wavelengths are analyzed. For example, the stool may be illuminated at different wavelengths of light at different times, and images may be acquired while the stool is illuminated under each illumination wavelength. Alternatively or additionally, images may be acquired using filters, cameras, and / or other imaging or light detection devices configured to acquire images at various wavelengths (e.g., spectrometers, spectral cameras, hyperspectral cameras, etc.). In some applications, analysis of the fecal images is performed using computer vision analysis algorithms that perform segmentation and / or texture classification. Alternatively or additionally, image analysis is performed using deep neural networks trained for this task.

[0037] By way of illustration and not by way of limitation, some representative examples of steps that may be included in a computer vision analysis algorithm are as follows: masking, for example to exclude peripheral areas away from feces; contrast enhancement, to highlight image areas where feces are located; image edge detection to detect the edges of feces; detection of regions of interest, e.g., using Gaussian mixture models; Performing morphological changes for noise cleaning; Performing segmentation using GrabCut.

[0038] Reference is now made to Figures 2A, 2B, 2C, 2D and 2E, which show representative images of some of the computer vision analysis steps described above that are performed on images of feces in a toilet bowl, in accordance with some applications of the present invention.

[0039] 2A is an example of contrast enhancement performed on an image of a subject's stool: the left frame shows the stool image before enhancement, and the right frame shows the enhanced image.

[0040] Figure 2B is an example of edge detection performed on an image of a subject's stool: the left frame shows the image of the stool before the edge detection algorithm is applied, and the right frame shows the output of the edge detection algorithm.

[0041] 2C is an example of region of interest detection performed on images of a subject's stool using a Gaussian mixture model. A sequence of images shows respective clusters identified as regions of interest within the images. Typically, each of the regions of interest is then subjected to further analysis to detect parameters associated with the subject's stool.

[0042] Figure 2D shows the various stages of the noise cleaning algorithm applied to an image of a subject's stool, whereby morphological changes are applied to the image to clean noise from the image.

[0043] 2E is an example of the GrabCut image segmentation algorithm applied to an image of a subject's stool. The left frame shows the image of the stool before the GrabCut image segmentation algorithm is applied, and the right frame shows the output of the GrabCut image segmentation algorithm.

[0044] Typically, the computer processor 28 generates an output on an output device (e.g., a user interface device 32, described below) based on the detection and classification of dehydration. For example, the computer processor may generate an output indicating that the subject is suffering from a given type of dehydration and / or may generate an output indicating a recommended course of action for the subject based on the type of dehydration. In this regard, it is noted that for a patient suffering from dehydration, different courses of action are typically recommended depending on the type of dehydration.

[0045] In Figure 1, a subject's urine 27 and feces 26 are shown disposed in a toilet bowl contemporaneously with one another. However, it should be noted that the scope of the present application includes analyzing the subject's feces at a time separate from analyzing the subject's urine. For example, the subject may first be determined to be suffering from dehydration by analyzing the subject's urine. Subsequently, when the subject has a bowel movement, the subject's feces may be analyzed to classify the subject's dehydration as a given type of dehydration, as described above.

[0046] For some applications, the devices and methods described herein are practiced in conjunction with the devices and methods described in US 10,575,830 to Attar and / or US 2019 / 0195802 to Attar, both of which are incorporated herein by reference.

[0047] In some applications, the apparatus 20 includes a power source (e.g., a battery pack) located outside the toilet bowl and within the housing 30. Alternatively or additionally, the sensor module is connected to a utility power source (not shown). Typically, the power source and the sensor module 22 are wired (as shown) or wirelessly connected (not shown). Depending on the respective application, a computer processor that performs the above-mentioned analysis is located within the toilet bowl (e.g., computer processor 28 is located within the housing 30 (which typically also houses the sensor module)) or is located remotely. For example, as shown, the sensor module may wirelessly communicate with a user interface device 32 that includes a computer processor. Such user interface devices may include, but are not limited to, a telephone 34, a tablet computer 36, a laptop computer 38, or different types of personal computing devices. Typically, the user interface device operates as both an input device and an output device through which a user interacts with the sensor module 22. The sensor module may transmit data to a user interface device, and a computer processor of the user interface device may execute a program configured to analyze the received data.

[0048] In some applications, the sensor module 22 and / or the user interface device communicate with a remote server. For example, the device may communicate with a doctor or insurance company through a communication network without intervention from the subject. The doctor or insurance company may evaluate the results and determine whether further testing or intervention is appropriate for the subject. In some applications, data associated with the received sensor signal is stored in a memory. For example, the memory may be located in the toilet bowl (e.g., in the sensor unit), in the housing 30, or remotely. The subject may periodically submit the stored data to a facility, such as a health care facility (e.g., a doctor's office or pharmacy) or an insurance company, and a computer processor at the facility may then perform the above-described analysis on batches of data associated with multiple bodily exudates of the subject acquired over a period of time.

[0049] It should be noted that the devices and methods described herein include screening tests that do not require the subject to physically touch the bodily waste. Moreover, typically, the subject only needs to periodically touch any part of the dedicated sensing device, for example, to install the device or to replace or recharge the device's battery. (Note that the subject may operate a user interface device, but this is typically a device (such as a phone) that the subject operates even when the sensing device is not in use.) Furthermore, typically, the devices and methods described herein do not require the subject to add anything to the toilet bowl after discharging the bodily waste into the toilet bowl to facilitate analysis of the waste and / or determination that the subject is suffering from dehydration and classification of said dehydration. In some applications, the subject does not need to perform any action after installing the device in the toilet bowl. The test is automatic and processed by the device. Therefore, unless an abnormality is detected, monitoring the subject's waste is seamless to the subject and does not require compliance by the subject.

[0050] Typically, after a subject expels a bodily waste into a toilet bowl (typically, once a subject has completed expelling the bodily waste, the bodily waste is at least partially disposed within the water in the toilet bowl), the bodily waste is imaged by receiving reflected and / or transmitted light from the toilet bowl without requiring any action to be taken by any person after expulsion. In some applications, the bodily waste is analyzed while it is being expelled into the toilet bowl.

[0051] In some applications, for each excretion of the subject, in the event of a positive signal, the apparatus reports the findings to the subject via an output device, such as via user interface device 32. In some applications, the output device includes an output component (e.g., a light (e.g., LED) or a screen, etc.) integrated within apparatus 20.

[0052] The sensor module 22 is typically disposed within the toilet bowl. Furthermore, the sensor module typically includes an imaging component. The imaging component includes one or more optical sensors. The one or more optical sensors are configured to receive light from bodily waste discharged by the subject and are disposed within the toilet bowl. Typically, the sensor module is housed within a water-resistant housing. Furthermore, typically, a face of the sensor module below which the imaging component is mounted is covered by a transparent, water-resistant cover. Note that FIG. 1 illustrates the sensor module disposed above the water level in the toilet bowl. However, in some applications, at least a portion of the sensor module (e.g., the entire sensor module) is submerged in the water in the toilet bowl.

[0053] In some applications, the sensor module includes a subject sensor. The subject sensor is configured to detect when the subject is on or near the toilet bowl and / or whether the subject has defecate and / or urinated in the toilet bowl. For example, the subject sensor may include a motion sensor configured to sense the movement of feces, urine, the subject, or water in the toilet bowl. Alternatively or additionally, the subject sensor may include a light sensor configured to detect when a light in the toilet is switched on or when the subject is sitting on the toilet bowl. In some applications, the light sensor used to detect light from bodily waste is also used for the functions described above. In some such applications, the sensor module is configured to be in standby mode most of the time (so that the sensor module uses less power). The sensor module is switched on in response to detecting that the subject is on or near the toilet bowl and / or in response to detecting that the subject has defecate and / or urinated in the toilet bowl. Typically, an imaging component of the sensor module acquires images in response to detecting that a subject is on or near the toilet bowl and / or that the subject has defecate and / or urinate into the toilet bowl. In some applications, the sensor module is manually switched on by the subject.

[0054] In some applications, the computer processor 28 is configured to detect one or more additional components and / or parameters of the subject's urine based on the data obtained by the sensor module 22. Some such applications are described below.

[0055] (Urine specific gravity) Urine specific gravity is a measure of the concentration of solutes in urine. Urine specific gravity is a measure of the ratio of urine density compared to the density of water, providing information about the kidney's ability to concentrate urine. Typically, healthy adult urine has a specific gravity in the range of 1.010 to 1.030. Increased specific gravity (known as hypertonic urine) may be associated with dehydration, diarrhea, vomiting, excessive sweating, urinary tract / bladder infections, diabetes mellitus, renal artery stenosis, hepatorenal syndrome, reduced blood flow to the kidney (especially as a result of heart failure) and / or excess antidiuretic hormone. Decreased specific gravity (known as hypotonic urine) may be associated with renal failure, pyelonephritis, diabetes insipidus, acute tubular necrosis, interstitial nephritis and excessive fluid intake (e.g., psychogenic polydipsia).

[0056] In some applications, the sensor module is configured to generate a signal indicative of absorption of light by the subject's urine, and the computer processor is configured to derive a specific gravity of the subject's urine based on the signal. Typically, the computer processor derives a specific gravity of the subject's urine based on the sensor signal indicative of absorption of cyan-green light (e.g., light in a wavelength band of 480-520 nm) by the subject's urine. In some applications, the computer processor generates an output in response to the derived specific gravity. For example, the computer processor may generate an output on the user interface device 32 indicating that the subject is suffering from dehydration and / or may generate an output on the user interface device 32 indicating a recommended course of action for the subject. In some applications, the computer processor is configured to detect that the subject is suffering from dehydration based on the specific gravity of the subject's urine, and is configured to categorize the dehydration using the techniques described above.

[0057] Reference is now made to FIG. 3, which is an ROC curve showing the sensitivity and specificity of a classifier for detecting urine specific gravity based on urine blue light absorption, according to some applications of the present invention. The results shown in FIG. 3 are for a classifier using a specific gravity of 1.025 as the classification point (i.e., a specific gravity less than 1.025 is considered to indicate either isotonic or hypotonic urine, and a specific gravity greater than 1.025 is considered to indicate hypertonic urine). The results of this classifier were compared to those obtained using Multistix® 10SG reagent strips manufactured by Siemens (Germany). The classifier provided a sensitivity of 81% and a specificity of 80.0%, with an area under the curve ("AUC") of 82%, indicating that this is a reliable classifier for determining specific gravity.

[0058] (hematuria) Blood in human urine (known as hematuria) is a warning sign of a variety of serious conditions of the urinary tract, some of which may be life-threatening. Hematuria could be due to, for example, a urinary tract infection, a kidney infection, bladder or kidney stones, prostate enlargement, kidney disease, viral or streptococcal infections, or bladder and kidney cancer. In some applications, the computer processor analyzes the signal from the sensor module to determine that the subject is suffering from hematuria. In some such applications, the computer processor uses techniques described in US 10,575,830 by Attar, which is incorporated herein by reference.

[0059] Reference is now made to Figure 4, which is an ROC curve showing the sensitivity and specificity of a classifier utilizing the sensor module described herein for detecting the presence of blood in a subject's urine, according to some applications of the present invention. The classifier yielded a sensitivity of 80.5% and a specificity of 80.8%, with an AUC of over 88%, as compared to the results of a hemoglobin immunoassay performed using a QuikRead go wrCRP+Hb instrument manufactured by Aidian (Espoo, Finland). This indicates that the sensor described herein may be used to reliably detect the presence of blood in a subject's urine.

[0060] (bilirubin, oxidized urobilinogen and urobilin) Bilirubin, urobilin and urobilinogen are all derivative molecules of hemoglobin metabolism in the liver. Urobilinogen is a colorless by-product of bilirubin reduction. Urobilinogen levels are elevated in liver disease (e.g., hepatitis). When urobilinogen is exposed to air, it is oxidized to urobilin, which gives urine its yellow color.

[0061] Bilirubin has a distinct absorption spectrum, (a) exhibiting a valley in a wavelength band in the range of 390-420 nm (e.g., about 400-410 nm), and (b) exhibiting a peak in a wavelength band in the range of 445-475 nm (e.g., about 455-465 nm). Thus, in some applications of the present invention, the sensor module is configured to detect light absorption in each of the wavelength bands, and the computer processor is configured to responsively determine a concentration of bilirubin in the subject's urine. In some such applications, the computer processor determines a ratio of light absorption in each of the wavelength bands relative to one another, and determines a concentration of bilirubin in the subject's urine based on the ratio. In some applications, the computer processor is configured to generate an output in response to the detected bilirubin concentration. For example, in response to a high concentration of bilirubin, the computer processor may generate an output on a user interface device indicating that the subject should seek medical attention.

[0062] Oxidized urobilinogen has a distinct absorption spectrum exhibiting a peak in the absorption spectrum in a wavelength band within a range of 480-520 nm (e.g., about 500-about 515 nm). Thus, in some applications of the present invention, the sensor module is configured to detect light absorption in the wavelength band, and the computer processor is configured to responsively determine a concentration of oxidized urobilinogen in the subject's urine. In some applications, the computer processor is configured to generate an output in response to the detected concentration of oxidized urobilinogen. For example, in response to a high concentration of oxidized urobilinogen, the computer processor may generate an output on a user interface device indicating that the subject should seek medical attention.

[0063] Further, it has been demonstrated that pre-illumination of urobilin at a wavelength of about 460 nm (e.g., 440-480 nm) causes the urobilin to emit (by autofluorescence) light at a wavelength of about 520 nm. Thus, in accordance with some applications of the present invention, the subject's urine is illuminated with illumination in a wavelength band in the range of 440-480 nm (e.g., using illumination component 25 shown in FIG. 1). A computer processor then analyzes the sensor signal to determine the intensity of light emitted by the urine at a wavelength of about 520 nm (e.g., a wavelength band in the range of 505-535 nm or a wavelength band in the range of 515-525 nm) in response to illuminating the urine. Typically, the computer processor is configured to responsively determine a concentration of oxidized urobilin in the subject's urine.

[0064] (Proteins (e.g., albumin)) Proteins (e.g., albumin) are normally abundant in blood. When there is a problem with the kidneys, proteins may leak into the urine. A large amount of protein in the urine may be an indication of kidney disease. Although proteins in urine tend not to have an optical signature, it has been observed that the presence of proteins in a subject's urine can cause urinary foaming. This is because proteins have a soap-like effect that reduces the surface tension of the urine. As a result of urine discharge, electrostatic forces occur between molecules in the liquid and the surface, and air bubbles form as a result of the dispersion of air in the urine. In some applications, the computer processor is configured to detect a sensor signal indicative of foaming and / or cloudiness of the subject's urine and / or indicative of an amount of foaming and / or cloudiness of the urine, and is configured to determine, at least in part, that there is an excess of protein in the subject's urine in response thereto. Alternatively or additionally, the computer processor is configured to estimate a concentration of protein in the subject's urine in response to the foaming and / or cloudiness of the subject's urine and / or the amount of foaming and / or cloudiness of the urine. In some such applications, the computer processor is configured to estimate urine turbidity by detecting the opacity of the urine. In some applications, the computer processor is configured to measure the height of a foam layer above the urine and, in response, determine that an excess of protein is present in the subject's urine and / or estimate a concentration of protein in the subject's urine. In some applications, the computer processor is configured to generate an output in response to detecting an excess of protein in the subject's urine and / or based on the estimated concentration of protein in the subject's urine. For example, in response to detecting an excess of protein in the subject's urine and / or based on the estimated concentration of protein in the subject's urine, the computer processor may generate an output on a user interface device indicating that the subject should seek medical attention.

[0065] (Biofilm-based pathogens) It has been suggested that a cause of recurrent urinary tract infections (UTIs) is a pathogenic biofilm (e.g., Escherichia coli (UPEC) and the like) formed within the urinary tract. Typically, in such cases, cellulose is present within the extracellular matrix of the biofilm within the urinary tract. Furthermore, it has been demonstrated that pre-illumination of cellulose with broadband illumination in a wavelength range of 300-520 nm causes the cellulose to emit light (by autofluorescence) at a wavelength of approximately 545 nm. Thus, in accordance with some applications of the present invention, a subject's urine is illuminated with broadband illumination in a wavelength range of 300-520 nm (e.g., using illumination component 25 shown in FIG. 1). A computer processor then analyzes the sensor signal to determine the intensity of light emitted by the urine at a wavelength of approximately 545 nm (e.g., a wavelength range of 530-560 nm or a wavelength range of 540-550 nm) in response to the illumination of the urine.

[0066] In some applications, the computer processor is configured to derive a level of cellulose in the subject's urine based at least in part on the detected intensity of the light. As described above, in some applications, the computer processor is configured to detect hematuria by analyzing the sensor signal. In some applications, in response to detecting hematuria (e.g., using the techniques described above), the computer processor is configured to (a) activate the illumination component 25 to illuminate the subject's urine with broadband illumination in a wavelength band within a range of 300-520 nm, and (b) in response to illuminating the urine, determine an intensity of light emitted by the urine at a wavelength of about 545 nm (e.g., a wavelength of 530-560 nm, or a wavelength of 540-550 nm). Based on the detected intensity of light (and the derived concentration of cellulose in the urine), the computer processor is configured to perform a differential diagnosis to determine whether a suspected cause of the hematuria is a biofilm-based pathogen in the subject's urinary tract. In some such applications, the computer processor generates an output in response to the differential diagnosis. For example, the computer processor may generate an output on a user interface device indicating that the subject should seek medical attention.

[0067] The applications of the invention described herein may take the form of a computer program product accessible from a computer usable or computer readable medium (e.g., a non-transitory computer readable medium). The computer program product provides program code for use by or in connection with a computer or any instruction execution system, such as a computer processor in the user interface device 32, a computer processor 28 located in the housing 30, or a remote cloud-based computer processor. For purposes of this specification, a computer usable or computer readable medium may be any apparatus that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, instruction execution apparatus, or instruction execution device. The medium may be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device), or may be a propagation medium. Typically, the computer usable or computer readable medium is a non-transitory computer usable or computer readable medium.

[0068] Examples of computer-readable media include semiconductor or solid-state memory, magnetic tape, removable computer diskettes, random access memory (RAM), read-only memory (ROM), rigid magnetic disks, and optical disks. Current examples of optical disks include compact disk-read-only memory (CD-ROM), compact disk-read / write (CD-R / W), and DVD. In some applications, cloud storage is used.

[0069] A data processing system suitable for storing and / or executing program code will include at least one processor (e.g., a computer processor in the user interface device 32, a computer processor 28 located within the housing 30, or a remote cloud-based computer processor) coupled directly or indirectly to memory elements (e.g., a memory in the user interface device 32) through a system bus. The memory elements may include local memory used during actual execution of the program code, mass storage, and cache memory that provides temporary storage of at least some of the program code so as to reduce the number of times the code needs to be retrieved from mass storage during execution. The system may read the instructions of the present invention on the program storage device and follow these instructions to perform the methodology of the present invention embodiments.

[0070] Network adapters may be coupled to the processor such that the processor may become coupled to other processors, remote printers, or storage devices through intervening private or public networks. Modems, cable modems, and Ethernet cards are just a few of the types of network adapters currently available.

[0071] Computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including, for example, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages, such as the programming language C or a similar programming language.

[0072] It will be understood that the algorithms described herein may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing device to produce a machine, such that the instructions executed via a processor of the computer (e.g., the computer processor of the user interface device 32, the computer processor 28 located in the housing 30, or a remote cloud-based computer processor) or other programmable data processing device create means for implementing the functions / behaviors specified in the algorithms described in this application. These computer program instructions may also be stored in a computer readable medium (e.g., a non-transitory computer readable medium). The computer readable medium may instruct the computer or other programmable data processing device to function in a particular manner, such that an article of manufacture including instruction means for implementing the functions / behaviors specified in the algorithms is produced by the instructions stored in the computer readable medium. Also, computer program instructions may be loaded onto a computer or other programmable data processing apparatus, causing the computer or other programmable apparatus to perform a series of operational steps to generate a computer-implemented process, such that the instructions, executed on the computer or other programmable apparatus, provide a process for implementing the functions / behavior specified in the algorithms described in this application.

[0073] Typically, the computer processors described herein are hardware devices that are programmed with computer program instructions to create a dedicated computer. For example, when programmed to execute the algorithms described herein, the computer processor typically functions as a dedicated bodily waste analysis computer processor. Typically, the operations described herein performed by the computer processor cause the physical state of the memory, which is an actual physical item, to be transformed to have a different magnetic polarity, charge, etc., depending on the memory technology used.

[0074] It will be appreciated by those skilled in the art that the present invention is not limited to what has been particularly shown and described above, but rather, the scope of the present invention includes both combinations and subcombinations of the various features described above, as well as variations and modifications of the present invention that would occur to one skilled in the art upon reading the foregoing description and that are not present in the prior art. [Brief description of the drawings]

[0075] [Figure 1] 1 is a schematic diagram of an apparatus for analyzing bodily wastes, according to some applications of the present invention. [Figure 2A] 1 shows representative images of some computer vision analysis steps performed on images of feces in a toilet bowl, according to some applications of the present invention. [Figure 2B] 1 shows representative images of some computer vision analysis steps performed on images of feces in a toilet bowl, according to some applications of the present invention. [Figure 2C] 1 shows representative images of some computer vision analysis steps performed on images of feces in a toilet bowl, according to some applications of the present invention. [Figure 2D] 1 shows representative images of some computer vision analysis steps performed on images of feces in a toilet bowl, according to some applications of the present invention. [Figure 2E]1 shows representative images of some computer vision analysis steps performed on images of feces in a toilet bowl, according to some applications of the present invention. [Diagram 3] 1 is a ROC curve illustrating the sensitivity and specificity of a classifier for detecting urine specific gravity based on blue light absorption by urine, according to some applications of the present invention. [Figure 4] 1 is a ROC curve illustrating the sensitivity and specificity of a classifier utilizing a sensor module described herein for detecting the presence of blood in a subject's urine, according to some applications of the present invention.

Claims

1. 1. An apparatus for use with an output device with respect to urine and feces of a subject discharged into a toilet bowl, comprising: one or more sensors coupled to the toilet bowl; at least one computer processor; The sensor includes: detecting one or more urine-related parameters related to the subject's urine after discharge of the urine into the toilet bowl without requiring any action to be taken by any person; configured to acquire one or more fecal images of the subject after expulsion of the feces into the toilet bowl without requiring any action to be performed by any person; The computer processor includes: receiving the one or more urine-related parameters from the one or more sensors and determining whether the subject is suffering from dehydration based at least in part on the one or more urine-related parameters; receiving the one or more fecal images from the one or more sensors and performing computer vision analysis on the one or more fecal images to determine one or more fecal-related parameters; the one or more stool-related parameters include at least one of a texture and a color of the stool; The computer vision analysis includes at least one of detecting a region of interest, applying a morphological transformation, and performing image segmentation using GrabCut; An apparatus configured to provide output to the output device in response at least in part to the steps above.

2. 10. The apparatus of claim 1, wherein the at least one computer processor is configured to detect the one or more urine-related parameters of the subject's urine by detecting a urine color.

3. The apparatus of claim 1 , wherein the at least one computer processor is configured to detect the one or more urine-related parameters of the subject's urine by detecting a urine volume.

4. 2. The apparatus of claim 1, wherein the at least one computer processor is configured to detect the one or more urine-related parameters of the subject's urine by detecting a urination duration.

5. The apparatus of claim 1 , wherein the one or more stool-related parameters further comprise at least one of a shape and a size of the stool.

6. 6. The apparatus of claim 1 , wherein the at least one computer processor is configured to detect the one or more urine-related parameters relating to the subject's urine by detecting a urination frequency of the subject.

7. 7. The apparatus of claim 6, wherein the at least one computer processor is configured to detect urination frequency of the subject by automatically detecting which person is urinating at a given time.

8. The apparatus of claim 1 , wherein the computer vision analysis further comprises at least one of masking, contrast enhancement, and image edge detection.

9. 6. The apparatus of claim 1, wherein the at least one computer processor is configured to derive a specific gravity of the subject's urine and determine that the subject is suffering from dehydration based at least in part on the specific gravity of the subject's urine.

10. the one or more sensors are configured to detect a signal indicative of absorption of cyan-green light by the subject's urine; 10. The apparatus of claim 9, wherein the at least one computer processor is configured to derive the specific gravity of the subject's urine based at least in part on the signal.

11. the one or more sensors are configured to detect a signal indicative of absorption of light within a wavelength band of 480-520 nm by the subject's urine; 10. The apparatus of claim 9, wherein the at least one computer processor is configured to derive the specific gravity of the subject's urine based at least in part on the signal.

Images