Digital urination diary management method and system

Abstract

To provide a method and a system (apparatus) for managing a digital voiding diary.SOLUTION: A method for managing a digital voiding diary is implemented by at least one processor. The method may include the steps of: receiving a plurality of optical datasets associated with a specific user detected by a plurality of photodiodes within a medical device at each of a plurality of time points, the plurality of photodiodes being configured to detect light intensity associated with light radiated to the skin located above the bladder of the specific user; estimating the bladder urine volume for each of the plurality of time points on the basis of the plurality of optical datasets; and recording the estimated bladder urine volume of the specific user for each of the plurality of time points.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] (Cross - reference to related applications) This application claims priority based on Korean Patent Application No. 10 - 2023 - 0158122, filed on November 15, 2023, the content of which is incorporated herein by reference.

[0002] The present disclosure relates to a digital urination log management method and system, and specifically, to a digital urination log management method and system based on estimated intra - bladder urine volume and physiological measurement information.

Background Art

[0003] With the advent of an aging society, urinary disorders are prevalent in 60% of people over 40 years old. In particular, in order to prescribe medications for patients with urinary disorders such as overactive bladder, underactive bladder, benign prostatic hyperplasia, nocturia, recurrent cystitis, urinary incontinence, etc., patients are required to create a urination log over a period of 72 hours.

[0004] A urination log can be hand - written by a patient to record the number of urinations and urine volume for each time period of urination over 72 hours. Specifically, the patient must record the urination time and urine volume even when waking up or during sleep (including the case of waking up to urinate during sleep) within 72 hours starting 3 days before visiting the hospital. Then, the patient revisits the hospital, and based on this, the doctor can analyze the total daily urine volume, the average number of daily urinations, the average number of nocturia episodes, the average ratio of nocturnal urine volume, and the functional bladder capacity to diagnose the patient's urinary disorder. Creating a urination log can support an accurate assessment of symptoms and the diagnosis of urinary disorders at the start of treatment for urinary disorders. Since changes during the treatment of urinary disorders can be objectively confirmed, the urination log is highly regarded for the evaluation of treatment response and prognosis.

[0005] However, despite its importance, it is difficult for patients to manually record urination time and volume in a voiding diary while away from home. Patients may experience significant stress in creating a voiding diary within a 72-hour period, even when they have come to the hospital for treatment of frequent urination or urgency. Patients who come to the hospital for nocturia (or urination during sleep) may miss sleep if they have to measure the amount of urine with a urination cup each time they urinate during the night and manually record it in their voiding diary. Creating a voiding diary, which is essential for accurate diagnosis or initiating treatment for voiding disorders, can instead cause patients difficulty and stress. This difficulty and stress in creating a voiding diary may lead patients to interrupt or inaccurately complete the diary. This difficulty and stress may be particularly exacerbated for patients with voiding disorders, who are predominantly elderly.

[0006] Therefore, physicians who diagnose / prescribe based on voiding diaries may face the problem of low reliability of data from handwritten voiding diaries over a 72-hour period. Furthermore, physicians may lack the time to fully analyze the results of voiding diaries within their clinical environment. [Overview of the Initiative] [Problems that the invention aims to solve]

[0007] This disclosure provides a digital urination diary management method and system (device) to solve the aforementioned problems. [Means for solving the problem]

[0008] This disclosure can be embodied in a variety of ways, including methods, apparatus (systems), and / or computer programs stored on computer-readable storage media, and computer-readable storage media on which computer programs are stored.

[0009] According to one embodiment of the present disclosure, a digital urination diary management method performed by at least one processor may include the steps of: receiving a plurality of optical data sets associated with a specific user detected by a plurality of photodiodes in a medical device at each of a plurality of time points, wherein the plurality of photodiodes are configured to detect light intensity associated with light irradiated onto the skin located over the bladder of the specific user; estimating the amount of urine in the bladder for each of the plurality of time points based on the plurality of optical data sets; and recording the amount of urine in the bladder of the specific user for each of the estimated plurality of time points.

[0010] According to one embodiment of the present disclosure, the method may further include the step of outputting the total daily urination volume of a particular user based on the bladder volume of that particular user for each of a plurality of recorded time points.

[0011] According to one embodiment of the present disclosure, the method may further include the steps of displaying the amount of urine a particular user urinates while awake, along with a first visual object, based on the amount of urine a particular user urinates in their bladder at each of several recorded time points, along with a second visual object, based on the amount of urine a particular user urinates while asleep, along with a second visual object.

[0012] According to one embodiment of the present disclosure, the method may further include the step of outputting the average daily total urination volume and the average number of urinations per day of a particular user, based on the bladder volume of the particular user for each of a plurality of recorded time points.

[0013] According to one embodiment of the present disclosure, the method may further include the step of outputting the number of times a particular user urinates during sleep on a given day, or the percentage of the amount of urine urinated during sleep on a given day, based on the amount of urine in the particular user's bladder for each of a set of recorded time points.

[0014] According to one embodiment of the present disclosure, the method may further include the steps of estimating the functional bladder volume of a particular user based on the amount of urine in the user's bladder for each of a plurality of recorded time points, and outputting the estimated functional bladder volume of the particular user.

[0015] According to one embodiment of the present disclosure, the step of estimating urine volume includes the steps of estimating a set of optical characteristic values ​​for at least a part of a particular user's body based on a set of optical datasets, and estimating the bladder urine volume for each of a set of time points using a urine volume estimation model based on the estimated set of optical characteristic values, wherein the urine volume estimation model is a deep learning-based model or a machine learning-based model trained on a set of training datasets, and the set of training datasets may include a pair of the actual urine volume of a particular user and a set of optical characteristic values ​​associated with the actual urine volume.

[0016] According to one embodiment of the present disclosure, the training datasets include a first training dataset and a second training dataset, the first training dataset including a first actual urine volume of a specific user and a pair of first training optical characteristic values ​​associated with the first actual urine volume, and the second training dataset including a second actual urine volume of a specific user and a pair of second training optical characteristic values ​​associated with the second actual urine volume, the second actual urine volume may be greater than the first actual urine volume.

[0017] A computer program stored on a computer-readable recording medium can be provided to execute a method according to one embodiment of the present disclosure on a computer.

[0018] According to one embodiment of the present disclosure, a user terminal includes a communication unit, a memory, and at least one processor connected to the memory and configured to execute at least one computer-readable program contained in the memory, wherein at least one program receives at least one optical data set associated with a specific user detected by a plurality of photodiodes in a medical device at each of a plurality of time points, wherein the plurality of photodiodes are configured to detect light intensity associated with light irradiated onto the skin located over the bladder of the specific user, and may include commands for estimating the amount of urine in the bladder for each of the plurality of time points based on the plurality of optical data sets, and for recording the amount of urine in the bladder of the specific user for each of the estimated plurality of time points. [Effects of the Invention]

[0019] According to some embodiments of this disclosure, physiological information can be provided to users without the support of medical professionals or other experts. Furthermore, the ease of use enhances user convenience and increases accessibility to consumers for personalized applications.

[0020] According to some embodiments of this disclosure, system parameters for multiple photodiodes included in a medical device can be uniformly corrected. After generating calibration parameters once, the medical device may not require additional calibration. In other words, calibration using a phantom becomes unnecessary, improving user convenience.

[0021] According to some embodiments of this disclosure, user convenience can be enhanced by providing rapid calculation and high accuracy.

[0022] According to some embodiments of the present disclosure, physiological information regarding a plurality of regions can be provided using a plurality of light sources and a plurality of photodiodes. Physiological information can be provided not only for a local region of the body but also for a wide range of parts of the body. Further, by providing physiological information regarding a plurality of regions, the state of organs contained in the body (e.g., the amount of urine stored in the bladder, the position of the bladder, etc.) can be specifically grasped.

[0023] According to some embodiments of the present disclosure, in the case of a patient who does not feel the urge to urinate, etc., physiological information regarding their own bladder and / or the amount of urine in the bladder can be received in real time or periodically. The patient can use the provided information to monitor the amount of urine stored in their own bladder and urinate at an appropriate time.

[0024] According to some embodiments of the present disclosure, the urine volume estimation model can be provided for users by learning learning obesity information. Further, the urine volume estimation model uses a machine learning model or a deep learning model for which app development support is relatively good, so the invention according to the present disclosure can be easy for mobile app development for wearable devices. Also, the machine learning model or the deep learning model is easy to retrain, and the invention according to the present disclosure can perform bladder urine volume estimation for individuals. Further, the urine volume estimation model is easy to maintain and improve, and is excellent in model scalability and model versatility.

[0025] According to some embodiments of the present disclosure, when the amount of the learning dataset is not large, a plurality of additional learning datasets are generated by a teacher model to perform data augmentation. By the urine volume prediction model learning more data through data augmentation, an automated bladder urine volume prediction method designed based on medical knowledge and diagnosis can be implemented.

[0026] According to some embodiments of the present disclosure, a user can be easily guided on how to link a user terminal with a medical device. Subsequently, the user can use the medical device linked with the user terminal. Also, information regarding the user can be input to optimize the medical device, an artificial intelligence model for individuals, etc. for the user.

[0027] According to some embodiments of the present disclosure, the invention according to the present disclosure can provide a digitized urination log to patients and doctors by digitizing the urination log. Specifically, by accurately and quickly calculating the urination time and urination volume, when a patient wears a medical device, the urination time and urination volume can be automatically recorded. That is, since the patient does not have to measure with a urination cup and write the urination log by hand, high user accessibility can be provided.

[0028] According to some embodiments of the present disclosure, the digital urination log management method can reduce the analysis time of medical staff by providing an automatic analysis function for the diagnosis of urinary disorders, thereby enhancing the accessibility of the needy. Also, the invention according to the present disclosure can provide data automatically analyzed regarding the average total urination volume per day, the average number of urination times per day, the number of nocturia times by date, the average number of nocturia times per day, the ratio of nocturia volume by date, the average ratio of nocturia volume by date, the average nocturia volume by date, the functional bladder volume, etc., enabling doctors to perform accurate and rapid diagnosis / prescription for patients.

[0029] The effects of the present disclosure are not limited to this, and other effects not mentioned should be clearly understood by those with ordinary knowledge in the technical field to which the present disclosure belongs (referred to as "ordinary technicians") from the description of the claims.

Brief Description of the Drawings

[0030] Embodiments of the present disclosure and the like are described based on the following attached drawings. Here, similar reference numerals indicate similar elements, but are not limited thereto. [Figure 1] It is a schematic diagram showing an example of a medical device for estimating physiological information according to an embodiment of the present disclosure. [Figure 2] This is a schematic diagram showing an information processing system, a medical device, and a configuration connected to enable communication between multiple user terminals according to one embodiment of the present disclosure. [Figure 3] This is a block diagram showing the internal configuration of a user terminal and information processing system according to one embodiment of the present disclosure. [Figure 4] This figure shows an example of a manner in which diffuse light is detected using the first to third photodiodes according to one embodiment of the present disclosure. [Figure 5] This figure shows an example of the process for estimating physiological information according to one embodiment of the present disclosure. [Figure 6] This figure shows an example of generating calibration parameters using a calibration box according to one embodiment of the present disclosure. [Figure 7] This graph shows an example of the process for generating calibration parameters according to one embodiment of the present disclosure. [Figure 8] This figure shows an example of applying calibration parameters according to one embodiment of the present disclosure. [Figure 9] This figure shows an example of the learning process of an initial optical characteristic value estimation model according to one embodiment of the present disclosure. [Figure 10] This figure shows an example of a medical device according to one embodiment of the present disclosure. [Figure 11] This figure shows an example of estimating physiological information based on multiple optical data according to one embodiment of the present disclosure. [Figure 12] This figure shows an example of estimating physiological information based on multiple light scattering coefficient data maps according to one embodiment of the present disclosure. [Figure 13] This is a block diagram showing an example of a method for estimating bladder volume according to one embodiment of the present disclosure. [Figure 14] This graph shows an example of training data related to one embodiment of the present disclosure. [Figure 15] This block diagram shows an example of a urine volume estimation model according to one embodiment of the present disclosure. [Figure 16]This graph shows several examples of a urine volume estimation model according to one embodiment of the present disclosure. [Figure 17] This figure shows an example of an interface for managing a digital urination diary according to one embodiment of the present disclosure. [Figure 18] This figure shows an example of a urination diary according to one embodiment of the present disclosure. [Figure 19] This figure shows an example of a urination diary according to one embodiment of the present disclosure. [Figure 20] This is a flowchart illustrating a digital urination diary management method according to one embodiment of the present disclosure. [Modes for carrying out the invention]

[0031] The specific details for implementing this disclosure will be described below in detail based on the attached drawings. However, in the following explanation, specific descriptions of publicly known functions and configurations will be omitted if there is a risk of unnecessarily obscuring the gist of this disclosure.

[0032] In the attached drawings, identical or corresponding components are assigned the same reference numerals. Furthermore, in the following descriptions of embodiments, redundant descriptions of identical or corresponding components may be omitted. However, the omission of a description of a component should not be interpreted as meaning that such a component is not included in a particular embodiment.

[0033] The advantages and features of the embodiments disclosed, and the methods for achieving them, will become clear with reference to the embodiments described below, based on the accompanying drawings. However, this disclosure is not limited to the embodiments disclosed below and may be embodied in a variety of different forms. These embodiments are provided only to complete the disclosure and to enable a person of the ordinary skill to accurately recognize the category of the invention.

[0034] This disclosure provides a brief explanation of the terminology used and a detailed description of the embodiments of the disclosure. The terminology used in this disclosure has been selected to the greatest extent possible from commonly used terms, taking into account the function of the disclosure; however, this may change due to the intent of engineers in the relevant field, case law, the emergence of new technologies, etc. In certain cases, the applicant may have arbitrarily selected terms; the meanings of these terms will be described in detail in the description of the invention. Therefore, the terminology used in this disclosure should be defined not merely as simple term names, but based on the meaning of the term and the overall content of this disclosure.

[0035] In this disclosure, unless explicitly specified in the context, a singular expression may include multiple expressions, and a plural expression may include a singular expression. Throughout the specification, where a part "includes" a component, this does not exclude other components, unless otherwise stated, and may further include other components.

[0036] Furthermore, the terms “module” or “part” as used in this specification refer to software or hardware components, and a “module” or “part” performs a certain role. However, the meaning of “module” or “part” is not limited to software or hardware. A “module” or “part” may be configured to reside on an addressable storage medium, or to regenerate one or more processors. Thus, as an example, a “module” or “part” may include components such as software components, object-oriented software components, class components, task components, as well as at least one of processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. Components and “modules” or “parts” may be combined with a smaller number of components and “modules” or “parts” to provide internal functionality, or further separated into additional components and “modules” or “parts.”

[0037] According to one embodiment of the present disclosure, a “module” or “part” may be embodied in a processor and memory. “Processor” should be broadly interpreted to include general-purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, and the like. In some environments, “processor” may also refer to application-specific semiconductors (ASICs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), and the like. “Processor” may also refer to combinations of processing devices, such as a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors coupled with a DSP core, or any other such combination. “Memory” should also be broadly interpreted to include any electronic component capable of storing electronic information. The term "memory" can also refer to various types of processor-readable media, such as RAM (Random Access Memory), ROM (Read Only Memory), NVRAM (Non-Volatile Random Access Memory), PROM (Programmable Read-Only Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic or optical data storage devices, and registers. When a processor can read / receive information from or record information into memory, the memory is said to be in electronic communication with the processor. Memory integrated into a processor is in electronic communication with the processor.

[0038] Furthermore, terms such as 1st, 2nd, A, B, (a), (b), etc., used in the following examples are used solely to distinguish one component from another, and do not limit the nature, order, or procedure of that component.

[0039] Furthermore, in the following embodiments, if one component is "connected," "joined," or "connected" to another component, it must be understood that while they may be directly connected or linked to each other, other components may also be "connected," "joined," or "connected" to each other.

[0040] In this disclosure, “each of the A's” may refer to each of all the components included in the A's, or to each of some of the components included in the A's.

[0041] Furthermore, the use of "comprises" or "comprising" in the following examples does not preclude the existence or addition of one or more other components, steps, operations, and / or elements mentioned.

[0042] In this disclosure, "diffuse reflectance" can refer to the ratio of the light intensity of a light source to the light intensity of diffused light measured at a specific distance from the light source. Here, diffused light can refer to the light diffused from an object to which light is irradiated. For example, when light is irradiated onto a body, the diffuse reflectance can refer to the ratio of the light intensity of the light source to the light intensity of diffused light measured at a specific distance from the light source. Specifically, diffuse reflectance can be expressed as shown in the following equation 1.

[0043]

number

[0044] In this disclosure, “system parameters” may refer to coefficients associated with photodetection of a photodiode. System parameters may include proportionality coefficients and intercept coefficients. The proportionality coefficients and intercept coefficients of system parameters can be understood from the following description.

[0045] If the optical data detected by the photodiode is a voltage value, it can be expressed as shown in equation 2 below.

[0046]

number

[0047] Hereinafter, various embodiments of this disclosure will be described in detail based on the attached drawings.

[0048] Figure 1 is a schematic diagram showing an example of a medical device 100 for estimating physiological information according to one embodiment of the present disclosure. As shown in the figure, the medical device 100 may include a communication unit for sending and receiving data with a user terminal 120. The medical device 100 may also include a plurality of photodiodes 112_1 to 112_20 and a plurality of light source groups 114_1 to 114_4. The medical device 100 can acquire light data related to the body using the plurality of photodiodes 112_1 to 112_20 and the plurality of light source groups 114_1 to 114_4. The user terminal 120 receives the light data related to the body and can estimate the user's physiological information based on the received light data. Figure 1 shows the medical device 100 including 20 photodiodes 112_1 to 112_20 and 4 light source groups 114_1 to 114_4, but is not limited to this. That is, the number of photodiodes and light source groups included in the medical device 100 can be changed as needed.

[0049] In one embodiment, a plurality of photodiodes 112_1 to 112_20 and a plurality of light source groups 114_1 to 114_4 may be arranged on one surface of the medical device 100. In this case, the medical device 100 can be attached to the body so that the surface faces the body. For example, the medical device 100 can be attached to the body so that the surface faces the area where the bladder is located.

[0050] In one embodiment, each of the multiple light source groups 114_1 to 114_4 may include six light sources having different wavelengths, but is not limited thereto. For example, the first light source group 114_1 may include the first to sixth light sources. The second light source group 114_2 may include the seventh to twelfth light sources. The third light source group 114_3 may include the thirteenth to eighteenth light sources. The fourth light source group 114_4 may include the nineteenth to twenty-fourth light sources. Each of the first to twenty-fourth light sources may be an LD (Laser Diode), an LED (Light-Emitting Diode), or an OLED (Organic Light-Emitting Diode). Furthermore, each of the first to twenty-fourth light sources may emit continuous wave light.

[0051] In one embodiment, the multiple light sources included in each of the multiple light source groups 114_1 to 114_4 can be configured to emit light of different wavelengths from each other. For example, each of the first to sixth light sources included in the first light source group 114_1 can emit light of different wavelengths from each other. Also, each of the seventh to twelfth light sources included in the second light source group 114_2 can emit light of different wavelengths from each other. Also, each of the thirteenth to eighteenth light sources included in the third light source group 114_3 can emit light of different wavelengths from each other. Also, each of the nineteenth to twenty-fourth light sources included in the fourth light source group 114_4 can emit light of different wavelengths from each other.

[0052] Here, light sources from different light source groups can emit light of the same wavelength. For example, the first, seventh, thirteenth, and ninth light sources can emit light of the same wavelength. Similarly, the second, eighth, fourteenth, and twenty-first light sources can emit light of the same wavelength. Also, the third, ninth, fifteenth, and twenty-first light sources can emit light of the same wavelength. Furthermore, the fourth, tenth, sixteenth, and twenty-second light sources can emit light of the same wavelength. Also, the fifth, eleventh, seventeenth, and twenty-third light sources can emit light of the same wavelength. Also, the sixth, twelfth, eighteenth, and twenty-fourth light sources can emit light of the same wavelength.

[0053] In one embodiment, multiple photodiodes 112_1 to 112_20 can detect light and generate optical data. Specifically, multiple photodiodes 112_1 to 112_20 can detect the light intensity of diffused light, which is light diffused from the body. In addition, multiple photodiodes 112_1 to 112_20 can detect diffused light associated with light sources irradiated by light sources included in multiple light source groups 114_1 to 114_4. Furthermore, each photodiode can detect diffused light and measure a voltage value corresponding to the light intensity of the diffused light. At this time, with one light source turned on, one photodiode can detect diffused light.

[0054] In one embodiment, the user terminal 120 can transmit an optical data detection request to the medical device 100. In response to the optical data detection request, the medical device 100 can activate a plurality of light source groups 114_1 to 114_4 and detect a plurality of photodiodes 112_1 to 112_20. The process for activating the plurality of light source groups 114_1 to 114_4 and detecting the plurality of photodiodes 112_1 to 112_20 will be described in detail later with reference to Figure 10. Alternatively, the medical device 100 may periodically detect optical data and transfer it to the user terminal 120 without receiving an optical data detection request from the user terminal 120.

[0055] In one embodiment, the medical device 100 can transmit multiple optical data detected via multiple photodiodes 112_1 to 112_20 to a user terminal 120. A processor included in the user terminal 120 can estimate physiological information based on the multiple optical data. Here, the physiological information may include information on water (H2O), fat, oxygenated hemoglobin (HbO2), deoxygenated hemoglobin (HHb), bladder monitoring information (notification of urination time, notification of catheterization time, bladder urine volume, etc.). A method for estimating physiological information based on multiple optical data will be described in detail later with reference to Figures 4 to 12. Alternatively, the medical device 100 may directly estimate physiological information based on the optical data without transferring the optical data to the user terminal 120.

[0056] With this configuration, physiological information can be estimated based on optical data acquired from the medical device 100. Additionally, the estimated physiological information can be provided to the user via the user terminal 120. Thus, the invention described herein can provide physiological information to the user without the support of a specialist such as a doctor. Furthermore, the invention described herein enhances user convenience through its simple usage method and increases accessibility to consumers for personal use.

[0057] Figure 2 is a schematic diagram showing a configuration in which an information processing system 230, a medical device 240, and a plurality of user terminals 210_1, 210_2, and 210_3 are connected to enable communication between them, according to one embodiment of the present disclosure. As shown in the figure, the plurality of user terminals 210_1, 210_2, and 210_3 can be connected via a network 220 to the information processing system 230 and the medical device 240, which can provide physiological information estimation services and / or digital voiding diary management services. Here, the plurality of user terminals 210_1, 210_2, and 210_3 may include terminals of users to whom physiological information estimation services and / or digital voiding diary management services are provided.

[0058] According to one embodiment, the information processing system 230 may include computer-executable programs (e.g., downloadable applications) related to the provision of physiological information estimation services, the provision of digital urination diary management services, etc., one or more server devices and / or databases capable of storing, providing, and executing data, and one or more distributed computing devices and / or distributed databases for a cloud computing service infrastructure.

[0059] The physiological information estimation service and / or digital voiding diary management service provided by the information processing system 230 can be provided to users via physiological information estimation service applications installed on each of the multiple user terminals 210_1, 210_2, and 210_3. For example, the information processing system 230 can provide information related to physiological information estimation and / or digital voiding diary management received from user terminals 210_1, 210_2, 210_3 and / or medical device 240, or perform corresponding processing, via the physiological information estimation service application and the digital voiding diary management service application. As an example, the digital voiding diary management service provided by the information processing system 230 can also be accessed from the web. Furthermore, the digital voiding diary management service provided by the information processing system 230 can be extended to include PHR (Personal Health Record), EMR (Electronic Medical Record), EHR (Electronic Health Record), etc.

[0060] According to one embodiment, the information processing system 230 can estimate physiological information based on optical data. Here, the optical data may be data measured by a medical device 240. The information processing system 230 can receive optical data directly from the medical device 240 or receive optical data via user terminals 210_1, 210_2, and 210_3. The information processing system 230 can provide the physiological information estimation results to user terminals 210_1, 210_2, 210_3 and / or the medical device 240.

[0061] According to one embodiment, the information processing system 230 can estimate the amount of urine in the bladder for each of several time points based on a plurality of optical datasets. Here, the plurality of optical datasets may be data measured by the medical device 240. The information processing system 230 can receive the plurality of optical datasets directly from the medical device 240, or it can receive the optical datasets via user terminals 210_1, 210_2, and 210_3. The information processing system 230 can also record the amount of urine in the bladder of a specific user for each of the estimated time points. At this time, the information processing system 230 can provide the recorded amount of urine in the bladder of a specific user to user terminals 210_1, 210_2, 210_3 and / or the medical device 240.

[0062] Multiple user terminals 210_1, 210_2, and 210_3 can communicate with the information processing system 230 and the medical device 240 via the network 220. The network 220 can be configured to enable communication between the multiple user terminals 210_1, 210_2, and 210_3, the information processing system 230, and the medical device 240. Depending on the installation environment, the network 220 may consist of a wired network such as Ethernet (registered trademark), PLC (Power Line Communication), telephone line communication equipment, and RS-serial communication, a mobile communication network, a wireless network such as WLAN (Wireless LAN), Wi-Fi (registered trademark), Bluetooth (registered trademark), and ZigBee (registered trademark), or a combination thereof. The communication method is not limited and may include not only communication methods that utilize communication networks that can include the network 220 (e.g., mobile communication networks, wired internet, wireless internet, broadcasting networks, satellite networks, etc.), but also short-range wireless communication between user terminals 210_1, 210_2, and 210_3.

[0063] In Figure 2, a mobile phone terminal 210_1, a tablet terminal 210_2, and a PC terminal 210_3 are shown as examples of user terminals, but the user terminals 210_1, 210_2, and 210_3 can be any computing device capable of wired and / or wireless communication, and on which a physiological information estimation service application or a web browser can be installed and run. For example, user terminals can include AI speakers, smartphones, mobile phones, navigation systems, desktop computers, laptop computers, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, game consoles, wearable devices, IoT (Internet of Things) devices, VR (virtual reality) devices, AR (augmented reality) devices, set-top boxes, and the like. Furthermore, while Figure 2 shows a configuration in which three user terminals 210_1, 210_2, and 210_3 communicate with the information processing system 230 and the medical device 240 via the network 220, the configuration is not limited to this, and a different number of user terminals may be configured to communicate with the information processing system 230 and the medical device 240 via the network 220.

[0064] Figure 3 is a block diagram showing the internal configuration of a user terminal and an information processing system according to one embodiment of the present disclosure. The user terminal 210 can refer to any computing device capable of wired / wireless communication, capable of running physiological information estimation service applications, digital urination diary management service applications, etc., and can include, for example, the mobile phone terminal 210_1, tablet terminal 210_2, and PC terminal 210_3 shown in Figure 2. As shown in the figure, the user terminal 210 can include a memory 312, a processor 314, a communication module 316, and an input / output interface 318. Similarly, the information processing system 230 can include a memory 332, a processor 334, a communication module 336, and an input / output interface 338. As shown in Figure 3, the user terminal 210 and the information processing system 230 can be configured to communicate information and / or data via the network 220 using their respective communication modules 316, 336. Furthermore, the input / output device 320 may be configured to input information and / or data to the user terminal 210 or output information and / or data generated from the user terminal 210 via the input / output interface 318.

[0065] The memories 312 and 332 may include any non-temporary computer-readable recording medium. According to one embodiment, the memories 312 and 332 may include permanent mass storage devices such as ROM (read-only memory), disk drives, SSDs (solid-state drives), and flash memory. In other examples, permanent mass storage devices such as ROM, SSDs, flash memory, and disk drives may be included in the user terminal 210 or information processing system 230 as separate permanent storage devices distinct from the memory. The memories 312 and 332 may also store an operating system and at least one program code (for example, code for a physiological information estimation service application or a digital urination diary management service application installed and driven on the user terminal 210).

[0066] Such software components can be loaded from a computer-readable recording medium separate from memories 312 and 332. Such a separate computer-readable recording medium may include a recording medium directly connectable to the user terminal 210 and the information processing system 230, but may also include computer-readable recording media such as flexible drives, disks, tapes, DVD / CD-ROM drives, and memory cards. As another example, software components may be loaded into memories 312 and 332 via communication modules 316 and 336, rather than via a computer-readable recording medium. For example, at least one program may be loaded into memories 312 and 332 based on a computer program installed by a file provided via the network 220 by a developer or a file distribution system that distributes application installation files.

[0067] Processors 314 and 334 can be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to processors 314 and 334 by memory 312 and 332 or by communication modules 316 and 336. For example, processors 314 and 334 can be configured to execute instructions received by program code stored in a recording device such as memory 312 and 332.

[0068] Communication modules 316 and 336 can provide configurations and functions for the user terminal 210 and the information processing system 230 to communicate with each other via the network 220, and can also provide configurations and functions for the user terminal 210 and / or the information processing system 230 to communicate with other user terminals or other systems (e.g., another cloud system). For example, requests or data (e.g., optical data, multiple optical data sets, physiological information estimation requests, urination diaries, urination analysis results, etc.) generated by program code stored in a recording device such as memory 312 by the processor 314 of the user terminal 210 can be transmitted to the information processing system 230 via the network 220 under the control of the communication module 316. Conversely, control signals and commands provided under the control of the processor 334 of the information processing system 230 can be received by the user terminal 210 via the communication module 336 and the network 220 through the communication module 316 of the user terminal 210.

[0069] The input / output interface 318 may be a means for interfacing with the input / output device 320. For example, the input device may include devices such as a camera including an audio sensor and / or image sensor, a keyboard, a microphone, or a mouse, and the output device may include devices such as a display, a speaker, or a haptic feedback device. In another example, the input / output interface 318 may be a means for interfacing with a device that integrates a configuration or function for performing input and output in one, such as a touchscreen. For example, when the processor 314 of the user terminal 210 processes instructions of a computer program loaded into memory 312, a service screen, etc., configured using information and / or data provided by the information processing system 230 or other user terminals, may be displayed on the display via the input / output interface 318. In Figure 3, the input / output device 320 is shown not to be included in the user terminal 210, but it is not limited to this and may be configured integrally with the user terminal 210. Furthermore, the input / output interface 338 of the information processing system 230 may be connected to the information processing system 230 or may be a means for interface with input and output devices (not shown) that the information processing system 230 may include. In Figure 3, the input / output interfaces 318 and 338 are shown as elements configured separately from the processors 314 and 334, but the system is not limited to this, and the input / output interfaces 318 and 338 may be configured to be included in the processors 314 and 334.

[0070] The user terminal 210 and the information processing system 230 may include more components than those shown in Figure 3. However, it is not necessary to explicitly show most of the conventional components. According to one embodiment, the user terminal 210 can be implemented to include at least a portion of the aforementioned input / output device 320. The user terminal 210 may also further include other components such as a transceiver, a GPS (Global Positioning system) module, a camera, various sensors, and a database. For example, if the user terminal 210 is a smartphone, it may include components that are generally found in smartphones, and the user terminal 210 can be implemented to further include a variety of components such as an accelerometer, gyroscope, image sensor, proximity sensor, touch sensor, illuminance sensor, camera module, various physical buttons, buttons using a touch panel, input / output ports, and a vibrator for vibration.

[0071] When programs for physiological information estimation service applications or digital urination diary management service applications are running, the processor 314 can receive text, images, videos, audio and / or actions, etc., input or selected by input devices such as a touchscreen, keyboard, camera including an audio sensor and / or image sensor, and microphone, which are connected to the input / output interface 318. The processor 314 can store the received text, images, videos, audio and / or actions, etc., in the memory 312 or provide them to the information processing system 230 via the communication module 316 and the network 220.

[0072] The processor 314 of the user terminal 210 can be configured to manage, process, and / or store information and / or data received from the input / output device 320, other user terminals, the information processing system 230, and / or multiple external systems. The information and / or data processed by the processor 314 can be provided to the information processing system 230 via the communication module 316 and the network 220. The processor 314 of the user terminal 210 can transfer and output information and / or data to the input / output device 320 via the input / output interface 318. For example, the processor 314 can display the received information and / or data on the screen of the user terminal 210.

[0073] The processor 334 of the information processing system 230 can be configured to manage, process, and / or store information and / or data received from multiple user terminals 210 and / or multiple external systems. The information and / or data processed by the processor 334 can be provided to the user terminals 210 via the communication module 336 and the network 220.

[0074] JPEG0007863360000003.jpg96151

[0075] In one embodiment, the light source 420 may be one of the first to twenty-fourth light sources of the medical device 100 shown in Figure 1. The first to third photodiodes 430_1, 430_2, and 430_3 may be part of a plurality of photodiodes 112_1 to 112_20 of the medical device 100 shown in Figure 1. That is, from the description of the example of the light source 420, the first photodiode 430_1, the second photodiode 430_2, and the third photodiode 430_3, the process of calculating the normalized diffuse reflectance based on the light data detected by the plurality of photodiodes can be understood.

[0076] JPEG0007863360000004.jpg127151

[0077] In one embodiment, the measured voltage value can be corrected using calibration parameters. The corrected voltage value can be expressed as shown in the following equation 3.

[0078]

number

[0079] In one embodiment, the system parameters can differ for each photodiode. Specifically, the proportionality constants of the system parameters for each photodiode can differ from one another due to manufacturing process errors and the influence of connected circuit devices. As shown in Equation 3, the system parameters of each photodiode can be corrected to be identical using calibration parameters.

[0080] Normalized diffuse reflectance can represent the relative relationship of the diffuse reflectances of other photodiodes based on the diffuse reflectance of a specific photodiode. Here, normalized diffuse reflectance can be calculated based on a corrected voltage value. Specifically, normalized diffuse reflectance can be understood by the following equation 4. In this case, equation 4 can be derived from equations 1, 2, and 3.

[0081]

number

[0082] JPEG0007863360000007.jpg54151

[0083] Figure 4 illustrates in detail the process of calculating the normalized diffuse reflectance for the light source 420 and the first to third photodiodes 430_1, 430_2, and 430_3. The method for estimating physiological information based on the normalized diffuse reflectance for the light source 420 and the first to third photodiodes 430_1, 430_2, and 430_3 will be described in detail later with reference to Figure 5.

[0084] Figure 5 shows an example of the process for estimating physiological information according to one embodiment of the present disclosure. The first optical data 510_1 may be data generated by the first photodiode. The second optical data 510_2 may be data generated by the second photodiode. The third optical data 510_3 may be data generated by the third photodiode. When measuring the voltage value corresponding to the light intensity detected by each photodiode, the multiple optical data 510_1, 510_2, and 510_3 may be the measured voltage values. For example, the first optical data 510_1 may be the measured voltage value of the first photodiode described in Figure 4. Similarly, the second optical data 510_2 may be the measured voltage value of the second photodiode described in Figure 4. Also, the third optical data 510_3 may be the measured voltage value of the third photodiode described in Figure 4.

[0085] In one embodiment, the correction unit 520 can calculate multiple corrected optical data 522_1, 522_2, and 522_3 using the calibration parameter 512 based on multiple optical data 510_1, 510_2, and 510_3. Specifically, each of the multiple corrected optical data 522_1, 522_2, and 522_3 can be calculated by correcting each of the multiple optical data 510_1, 510_2, and 510_3. For example, the corrected first optical data 522_1 may be the corrected voltage value of the first photodiode described above in Figure 4. Similarly, the corrected second optical data 522_2 may be the corrected voltage value of the second photodiode described above in Figure 4. Furthermore, the corrected third optical data 522_3 may be the corrected voltage value of the third photodiode described above in Figure 4. The process by which the optical data is corrected using the calibration parameter 512 can be understood from the content described above in Figure 4.

[0086] In one embodiment, the diffuse reflectance calculation unit 530 can calculate multiple normalized diffuse reflectances 532_1 and 532_2 based on multiple corrected optical data 522_1, 522_2, and 522_3. For example, the normalized diffuse reflectance 532_1 of the second photodiode can be calculated based on the corrected first optical data 522_1 and the corrected second optical data 522_2. Similarly, the normalized diffuse reflectance 532_2 of the third photodiode can be calculated based on the corrected first optical data 522_1 and the corrected third optical data 522_3. The process of calculating the normalized diffuse reflectance can be understood from the above-described content in Figure 4.

[0087] In one embodiment, the absorption coefficient and reduced scattering coefficient can be estimated based on multiple normalized diffuse reflectances 532_1 and 532_2. Here, the absorption coefficient may be an optical coefficient of the biological tissue used to analyze the physiological components of the biological tissue, depending on the degree to which light of each wavelength is absorbed by the biological tissue. The reduced scattering coefficient may be an optical coefficient that indicates the structural properties of the biological tissue. For example, adipose tissue in obese patients with large fat cells exhibits relatively little light scattering, while adipose tissue in normal-weight patients with small fat cells exhibits relatively good light scattering. As shown in the figure, an initial optical property estimation model 540 and / or a numerical solver 550 can be used to estimate the absorption coefficient and reduced scattering coefficient.

[0088] In one embodiment, the initial optical characteristic value estimation model 540 can estimate the initial optical characteristic value for a specific region based on multiple normalized diffuse reflectances 532_1 and 532_2. Here, the specific region may be a body part associated with the second and third photodiodes. The initial optical characteristic value may include the initial light scattering coefficient 542 and the initial light absorption coefficient 544. For example, the initial optical characteristic value estimation model 540 may be an artificial neural network model (e.g., a deep learning-based model) that has learned multiple optical characteristic values ​​and normalized theoretical diffuse reflectances associated with multiple optical characteristic values. The learning process of the initial optical characteristic value estimation model 540 will be described in detail based on Figure 9.

[0089] In one embodiment, the numerical solver 550 can estimate the final optical characteristic value based on the initial optical characteristic value. In this case, the final optical characteristic value may include the final optical scattering coefficient 554 and the final optical absorption coefficient 556. For example, the numerical solver 550 can utilize the Levenberg-Marquardt algorithm. Specifically, the numerical solver 550 can take the initial optical characteristic value and several normalized diffuse reflectances 532_1 and 532_2 as initial inputs and estimate the final optical characteristic value based on the diffuse reflectance theoretical formula 552.

[0090] Here, the theoretical equation 552 for diffuse reflectance is as shown in equation 5 below.

[0091]

number

[0092] In one embodiment, the numerical solver 550 is input with initial optical characteristic values ​​for a specific region and multiple normalized diffuse reflectances 532_1 and 532_2 as initial values, and can estimate the final optical characteristic values ​​for the specific region based on the diffuse reflectance theoretical formula 552. Specifically, the initial light scattering coefficient 542 for the specific region, the initial light absorption coefficient 544 for the specific region, the normalized diffuse reflectance 532_1 of the second photodiode, and the normalized diffuse reflectance 532_2 of the third photodiode are input to the numerical solver 550 as a set, and the final light scattering coefficient 554 and the final light absorption coefficient 556 for the specific region can be estimated.

[0093] In one embodiment, the physiological information estimation unit 560 can estimate physiological information 564 for a specific region based on the final optical characteristic value. Specifically, the physiological information 564 can be estimated based on the extinction coefficient 562, the final light scattering coefficient 554, and the final light absorption coefficient 556. For example, the extinction coefficient 562 can be represented by an extinction coefficient matrix as shown in Table 1 below.

[0094] [Table 1]

[0095] JPEG0007863360000010.jpg58151

[0096] In one embodiment, a pseudo inverse matrix of the extinction coefficient matrix can be calculated as shown in Table 1. Using the inverse matrix of the extinction coefficient matrix, physiological information 564 based on the light absorption coefficients for each wavelength can be calculated. Specifically, we will examine the process of calculating physiological information using the following equation 6, which is obtained by multiplying the light absorption coefficients for each wavelength by the inverse matrix of the extinction coefficient matrix.

[0097]

number

[0098] JPEG0007863360000012.jpg67155

[0099] Figure 5 shows an example of estimating physiological information 564 using light emitted from a single light source, but it is not limited to this. For example, the body can be illuminated with light from a group of light sources having different wavelengths, and a group of photodiodes can detect the intensity of the diffused light. Specifically, a group of light sources including a light source emitting light of a first wavelength, a light source emitting light of a second wavelength, a light source emitting light of a third wavelength, a light source emitting light of a fourth wavelength, a light source emitting light of a fifth wavelength, and a light source emitting light of a sixth wavelength can be used. In this case, based on multiple light data associated with the six wavelengths of light, six final light absorption coefficients 556 for a specific region can be estimated. Subsequently, based on the six final light absorption coefficients 556 for the specific region, the oxygenated hemoglobin content, deoxygenated hemoglobin content, water content, and fat content for the specific region can be estimated using the inverse matrix of the absorption coefficient matrix.

[0100] In summary, based on three optical data points, one optical absorption coefficient for a specific region can be estimated. If six different wavelengths of light are used, six optical absorption coefficients for a specific region can be estimated based on three optical data points associated with each wavelength, and based on these six optical absorption coefficients, four pieces of content information for that region (oxygenated hemoglobin content, deoxygenated hemoglobin content, water content, and fat content) can be estimated.

[0101] Figure 5 shows an example of estimating physiological information 564 using optical data detected by three photodiodes, but it is not limited to this. For example, more than three photodiodes (e.g., 20) can be used. In this case, it is possible to estimate physiological information 564 for multiple regions.

[0102] The method described in Figures 4 and 5 allows us to understand the physiological information estimation process for an example of the medical device 100 shown in Figure 1. The flow of the optical data structure for the example of the medical device 100 shown in Figure 1 will be described in detail later based on Figures 10 to 12.

[0103] Figure 6 shows an example of generating calibration parameters using a calibration box 610 according to one embodiment of the present disclosure. In one embodiment, a plurality of photodiode apertures 612_1 to 612_20 and a plurality of light source group apertures 614_1 to 614_4 may be formed on one surface of the calibration box 610. Each of the plurality of photodiode apertures 612_1 to 612_20 can correspond to the position of each of the plurality of photodiodes 112_1 to 112_20 included in the medical device 100 shown in Figure 1. Similarly, each of the plurality of light source group apertures 614_1 to 614_4 can correspond to the position of each of the plurality of light source groups 114_1 to 114_4 included in the medical device 100 shown in Figure 1. In this case, the medical device 100 can be placed in the calibration box 610 such that one side of the medical device 100, which has multiple photodiodes 112_1 to 112_20 and multiple light source groups 114_1 to 114_4 arranged on it, faces one side of the calibration box 610, which has multiple openings 612_1 to 612_20 and 614_1 to 614_4 formed on it.

[0104] The calibration box 610 shown has 20 photodiode apertures 612_1 to 612_20 and 4 light source group apertures 614_1 to 614_4, but is not limited to this configuration. In other words, the number of apertures formed in the calibration box 610 can be changed depending on the number of photodiodes and light source groups included in the medical device 100 shown in Figure 1.

[0105] In one embodiment, the calibration box 610 may include a standard reflector inside. The standard reflector can diffuse (and / or reflect, hereafter referred to as "diffuse") the irradiated light. Optical information about the standard reflector (e.g., diffuse reflectance at different wavelengths) may be predefined.

[0106] In one embodiment, a Look Up Table (LUT) can be generated using the calibration box 610 before generating calibration parameters. In this case, the LUT can include relative relationship information regarding the light intensity of diffused light between multiple photodiode apertures 612_1 to 612_20. Specifically, the LUT can include information regarding the ratio of light intensity of diffused light reaching each photodiode aperture.

[0107] As an example, the information included in the LUT can be generated as follows: The first light source can be positioned in the first light source group aperture 614_1. Then, a specific photodiode can be positioned in the first photodiode aperture 612_1. Here, in order to eliminate the influence of the intercept coefficient of the system parameters on the specific photodiode, an offset may be set such that when no light is detected on the specific photodiode, the measured voltage value of the specific photodiode becomes 0.

[0108] JPEG0007863360000013.jpg96151

[0109] JPEG0007863360000014.jpg64151

[0110] [Table 2]

[0111] JPEG0007863360000016.jpg51151

[0112] In one embodiment, the LUT can store information on the ratio of diffuse light intensity by position for each wavelength of irradiated light in the form of a table. In this case, the LUT can store the information in separate tables: one associated with a first wavelength (e.g., a first light source) and another associated with a second wavelength (e.g., a second light source). For example, if six different wavelengths of light (e.g., a first to a sixth light source) are used, six tables can be generated for each of the six wavelengths, and 20 pieces of diffuse light intensity ratio information can be generated per table.

[0113] As can be seen from equation 1 above, the light intensity of diffused light reaching each photodiode can be proportional to the light intensity of the light source. Furthermore, using the information contained in the LUT, the light intensity of diffused light reaching other photodiodes can be proportional to the light intensity of diffused light reaching a specific photodiode. In summary, the light intensity information of diffused light reaching each photodiode can be generated by correcting the light intensity information of the light source using the information contained in the LUT. An example of the process of correcting the light intensity information of the light source using the information contained in the LUT will be described in detail later with reference to Figure 7.

[0114] In one embodiment, calibration parameters can be generated based on light intensity information of a light source corrected using a LUT. Specifically, calibration parameters can be generated for each of a plurality of photodiodes. Here, the calibration parameters may include a proportionality coefficient and an intercept coefficient.

[0115] The process of generating calibration parameters will be explained based on the multiple photodiodes 112_1 to 112_20 and multiple light source groups 114_1 to 114_4 shown in Figure 1. The medical device 100 can be positioned in the calibration box 610 such that one side of the medical device 100, on which the multiple photodiodes 112_1 to 112_20 and multiple light source groups 114_1 to 114_4 are arranged, faces one side of the calibration box 610, on which the multiple openings 612_1 to 612_20 and 614_1 to 614_4 are formed.

[0116] The first detection process may include a step in which the first photodiode detects diffused light while the standard reflecting object is illuminated by the first light source. In this case, the first light source included in the first group of light sources may be preferred for illumination, but is not limited to this, and one of the second to twenty-fourth light sources may be preferred for illumination. The first detection process may also include a step in which the second photodiode 112_2 detects diffused light while the standard reflecting object is illuminated by the first light source. In other words, the first detection process may include a step in which all of the photodiodes 112_1 to 112_20 detect diffused light while the object is illuminated by the first light source. Here, the light intensity of the first light source may remain constant during the first detection process. The second detection process is the same as the first detection process except that the light intensity of the first light source is changed during the first detection process. Similarly, a third detection process to the nth detection process can be performed sequentially by changing the light intensity of the first light source. Such a detection process can be performed dozens of times. For example, the light intensity of the first light source can be continuously increased or decreased as the detection process progresses.

[0117] Through a continuous detection process, a measurement graph based on the light intensity of the light source can be generated for each photodiode. At this time, using LUT information, a measurement graph based on the light intensity of diffused light can be generated for each photodiode. Subsequently, a trend line can be generated for each photodiode based on the measurement graph based on the light intensity of diffused light. Then, calibration parameters can be generated based on the equation of the generated trend line. The process of generating the trend line is shown in detail in Figure 7, and the process of generating calibration parameters based on the trend line equation is shown in detail in Figure 8.

[0118] Figure 7 is a graph showing an example of the process for generating calibration parameters according to one embodiment of the present disclosure. For the sake of explanation, Figure 7 will focus on the two photodiodes shown in Figure 1, namely the first photodiode 112_1 and the third photodiode 112_3.

[0119] JPEG0007863360000017.jpg74151

[0120] As shown above in Figure 6, the light intensity of diffused light reaching a specific photodiode can be expressed in proportion to the light intensity of the light source. For example, in the first detection process, if the light intensity of the light source is 16 mW, the relative value of the light intensity of diffused light reaching the third photodiode 112_3 may be 8 a.u.

[0121] JPEG0007863360000018.jpg83151

[0122] The second graph, 720, is a graph of measured values ​​based on the light intensity of diffused light obtained through the first to fifth detection processes. In the illustrated example, the light intensity of the light source may decrease as the detection process progresses. As a result, the light intensity of diffused light reaching the third photodiode 112_3 may also decrease in proportion to the light intensity of the light source. Similarly, the light intensity of diffused light reaching the first photodiode 112_1 may also decrease in proportion to the light intensity of diffused light reaching the third photodiode 112_3.

[0123] JPEG0007863360000019.jpg64151

[0124] Similar to the explanation of the trend lines for the first and third photodiodes described above, trend lines for multiple photodiodes can be generated. Subsequently, calibration parameters for multiple photodiodes can be generated based on the equations of the generated trend lines. The specific process for generating the calibration parameters will be described in detail later with reference to Figure 8.

[0125] Figure 8 shows an example of applying calibration parameters according to one embodiment of the present disclosure. The first graph 810 is a graph showing the trend lines 812, 814, 816, and 818 of multiple photodiodes before using the calibration parameters. The x-axis is the light intensity of diffused light, and the y-axis is the measured voltage value. Using the first graph 810, the calibration parameters can be generated by the following equation 7.

[0126]

number

[0127] JPEG0007863360000021.jpg51151

[0128] JPEG0007863360000022.jpg77151

[0129] JPEG0007863360000023.jpg51151

[0130] In one example, when using light of six different wavelengths, each photodiode can generate six trend lines associated with each wavelength of light. In this case, one proportionality coefficient for the calibration parameters can be generated for each of the six trend lines, for a total of six. Furthermore, the proportionality coefficient and intercept coefficient for the calibration parameters can be generated separately for each photodiode. That is, when six different wavelengths of light and 20 photodiodes are used, 120 proportionality coefficients and 20 intercept coefficients for the calibration parameters can be generated.

[0131] JPEG0007863360000024.jpg80151

[0132] This configuration allows for the uniform correction of system parameters for multiple photodiodes included in the medical device. Furthermore, as shown in Figure 5, a normalized diffuse reflectance can be calculated based on the uniformly corrected system parameters, and physiological information can be estimated based on the normalized diffuse reflectance. Thus, the medical device according to the present invention may not require additional calibration after the generation of calibration parameters is completed once. In other words, the present invention can improve user convenience by eliminating the need to perform calibration using a phantom.

[0133] JPEG0007863360000025.jpg64151

[0134] In one embodiment, the normalized theoretical diffuse reflectance calculation unit 920 can calculate a first normalized theoretical diffuse reflectance 922_1 and a second normalized theoretical diffuse reflectance 922_2 based on an arbitrary light scattering coefficient 912 and an arbitrary light absorption coefficient 914. Specifically, the normalized theoretical diffuse reflectance calculation unit 920 can calculate a normalized theoretical diffuse reflectance from an arbitrary light scattering coefficient and an arbitrary light absorption coefficient using a diffuse reflectance theoretical formula. The diffuse reflectance theoretical formula can be expressed as shown in equation 5 above.

[0135] The normalized theoretical diffuse reflectance calculation unit 920 can calculate a pair of normalized theoretical diffuse reflectances based on a pair of optical characteristic values. For example, the pair of optical characteristic values ​​can include an arbitrary light scattering coefficient 912 and an arbitrary light absorption coefficient 914. The pair of normalized theoretical diffuse reflectances can include a first normalized theoretical diffuse reflectance 922_1 and a second normalized theoretical diffuse reflectance 922_2. In this case, one training data set can include a pair of optical characteristic values ​​and a pair of normalized theoretical diffuse reflectances.

[0136] In one embodiment, the process for calculating the normalized theoretical diffuse reflectance may be the same as the following process. As shown in Figure 5, the theoretical diffuse reflectance formula may be an equation relating to the light scattering coefficient, the light absorption coefficient, and the distance between the light source and the photodiode. That is, a first theoretical diffuse reflectance can be calculated based on an arbitrary light scattering coefficient 912, an arbitrary light absorption coefficient 914, and a first distance between the light source and the first photodiode. Similarly, a second theoretical diffuse reflectance can be calculated based on an arbitrary light scattering coefficient 912, an arbitrary light absorption coefficient 914, and a second distance between the light source and the second photodiode. Furthermore, a third theoretical diffuse reflectance can be calculated based on an arbitrary light scattering coefficient 912, an arbitrary light absorption coefficient 914, and a third distance between the light source and the third photodiode. Here, the first normalized theoretical diffuse reflectance 922_1 may be the value obtained by dividing the second theoretical diffuse reflectance by the first theoretical diffuse reflectance. Furthermore, the second normalized theoretical diffuse reflectance 922_2 may be the value obtained by dividing the third theoretical diffuse reflectance by the first theoretical diffuse reflectance. In this case, information regarding the first distance, the second distance, and the third distance can be pre-inputted into the normalized theoretical diffuse reflectance calculation unit 920.

[0137] Multiple arbitrary light scattering coefficients 912 and light absorption coefficients 914 can be generated. Based on each of the multiple pairs of optical characteristic coefficients, multiple normalized theoretical diffuse reflectance pairs can be generated. Based on the multiple optical characteristic coefficients and the multiple pairs of normalized theoretical diffuse reflectances corresponding to the optical characteristic coefficient pairs, a first set of training data can be generated. As an example, the first set of training data may include 20,000,000 pairs of optical characteristic coefficients and normalized theoretical diffuse reflectance pairs.

[0138] In one embodiment, the first initial optical characteristic value estimation model 930_1 may be a deep learning-based model or a machine learning-based model trained using a first set of training data. Here, the machine learning-based model may be one of KNN (K-Nearest Neighbors), GB (Gradient Boost), or ANN (Artificial Neural Network). The first initial optical characteristic value estimation model 930_1, trained on the first set of training data, can estimate the initial optical characteristic values ​​(light scattering coefficient and light absorption coefficient) based on the normalized diffuse reflectance of the second photodiode and the normalized diffuse reflectance of the third photodiode.

[0139] In one embodiment, the fourth to sixth distances may be the distances between the light source and the fourth to sixth photodiodes, respectively. Information regarding the fourth, fifth, and sixth distances may be pre-inputted into the normalized theoretical diffuse reflectance calculation unit 920. In this case, the fourth, fifth, and sixth distances may differ from the first, second, and third distances, respectively. In this case, the fourth theoretical diffuse reflectance can be calculated based on an arbitrary light scattering coefficient 912, an arbitrary light absorption coefficient 914, and the fourth distance between the light source and the fourth photodiode. Furthermore, the fifth theoretical diffuse reflectance can be calculated based on an arbitrary light scattering coefficient 912, an arbitrary light absorption coefficient 914, and the fifth distance between the light source and the fifth photodiode. Additionally, the sixth theoretical diffuse reflectance can be calculated based on an arbitrary light scattering coefficient 912, an arbitrary light absorption coefficient 914, and the sixth distance between the light source and the sixth photodiode. Here, the third normalized theoretical diffuse reflectance may be the value obtained by dividing the fifth theoretical diffuse reflectance by the fourth theoretical diffuse reflectance. Furthermore, the fourth normalized theoretical diffuse reflectance 922_2 may be the value obtained by dividing the sixth theoretical diffuse reflectance by the fourth theoretical diffuse reflectance. Multiple training data generated by repeating this process may constitute the second set of training data. The second initial optical characteristic value estimation model 930_2 can be trained based on the second set of training data.

[0140] By repeating the above process for distances 7 through 9, a third set of training data can be generated. At this point, the third initial optical characteristic value estimation model 930_3 can be trained based on the third set of training data. By repeating the above process for distances 10 through 12, a fourth set of training data can be generated. At this point, the fourth initial optical characteristic value estimation model 930_4 can be trained based on the fourth set of training data. Figure 9 shows the generation of four initial optical characteristic value estimation models 930_1 to 930_4, but is not limited to this; any number of initial optical characteristic value estimation models can be generated depending on the number of photodiodes and the arrangement of the photodiodes and light source.

[0141] When estimating initial optical characteristic values ​​based on normalized diffuse reflectance for the first, second, and third distances, the first initial optical characteristic value estimation model 930_1 is used. Similarly, when estimating initial optical characteristic values ​​based on normalized diffuse reflectance for the fourth, fifth, and sixth distances, the second initial optical characteristic value estimation model 930_2 is used. When estimating initial optical characteristic values ​​based on normalized diffuse reflectance for the seventh, eighth, and ninth distances, the third initial optical characteristic value estimation model 930_3 is used. Similarly, when estimating initial optical characteristic values ​​based on normalized diffuse reflectance for the tenth, eleventh, and twelfth distances, the fourth initial optical characteristic value estimation model 930_4 is used.

[0142] When the aforementioned numerical solver is used to estimate the final light scattering coefficient and final light absorption coefficient by inputting an arbitrary light scattering coefficient 912 and an arbitrary light absorption coefficient 914 as initial values, it has the disadvantage of requiring a long calculation time and having low accuracy. When the initial light characteristic value estimation model 930 of the present invention is used to estimate the initial light scattering coefficient and initial light absorption coefficient, and then the final light scattering coefficient and final light absorption coefficient are estimated using the numerical solver, the calculation time is reduced and the accuracy can be improved. Thus, the present invention has the advantage of providing rapid calculation and high accuracy, thereby improving user convenience.

[0143] Figure 10 shows an example of a medical device according to one embodiment of the present disclosure. As shown in the figure, a plurality of photodiodes and a plurality of light source groups 1012, 1014, 1022, and 1024 may be arranged on one side of the medical device. The illustrated example may be identical to the medical device shown in Figure 1. The first light source group 1012 may include six light sources. The six light sources can emit light of different wavelengths from each other. The second to fourth light source groups 1014, 1022, and 1024 may also each include six light sources configured to emit light of different wavelengths from each other.

[0144] In one embodiment, the medical device may be a device that has undergone calibration. For example, calibration of the medical device may be performed during the manufacturing process. Furthermore, the medical device is used while attached to the body. The process by which a medical device attached to the body detects optical data will be described in detail later.

[0145] In one embodiment, the first state 1010 can represent a detection relationship between the first light source group 1012 and the third light source group 1014 and the first set of photodiodes 1016. In the first measurement process, with the first light source included in the first light source group 1012 emitting light, each of the first set of photodiodes 1016 can detect diffused light. At this time, the light intensity of the first light source may be constant during the first measurement process. After the first measurement process is completed, the first set of photodiodes 1016 can detect optical data (12 measurement voltage values) associated with the first light source. Each of the second to sixth measurement processes is the same as the first measurement process, except that the second to sixth light sources included in the first light source group 1012 are used instead of the first light source in the first measurement process. Similarly, the 13th to 18th measurement processes can be performed in relation to the 13th to 18th light sources included in the third light source group 1014.

[0146] In one embodiment, the second state 1020 can represent the detection relationship between the second light source group 1022 and the fourth light source group 1024 and the second set of photodiodes 1026. In the seventh measurement process, with the seventh light source included in the second light source group 1022 emitting light, each of the second set of photodiodes 1026 can detect diffused light. At this time, the light intensity of the seventh light source may be constant during the seventh measurement process. After the seventh measurement process is completed, the second set of photodiodes 1026 can detect optical data (12 measurement voltage values) associated with the seventh light source. Each of the eighth to twelfth measurement processes is the same as the seventh measurement process, except that the eighth to twelfth light sources included in the second light source group 1022 are used instead of the seventh light source in the seventh measurement process. Similarly, the 19th to 24th measurement processes can be performed in relation to the 19th to 24th light sources included in the fourth light source group 1024.

[0147] The process of estimating physiological information based on the optical data obtained through measurement processes 1 to 24 will be described in detail later with reference to Figures 11 and 12. The physiological information estimated based on the optical data may include information on the oxygenated hemoglobin content, the deoxygenated hemoglobin content, the water content, the fat content, and the bladder urine volume.

[0148] Figure 11 shows an example of estimating physiological information based on multiple optical data according to one embodiment of the present disclosure. In Figure 11, the optical data (measured voltage values) detected by the first measurement process, the thirteenth measurement process, the seventh measurement process, and the nineteenth measurement process, which are associated with the first wavelength (i.e., the first light source, the seventh light source, the thirteenth light source, and the nineteenth light source), will be explained in detail. Here, the measured voltage value can mean the voltage value corrected using calibration parameters. Optical data associated with the second to sixth wavelengths can be processed in the same manner as the optical data associated with the first wavelength.

[0149] JPEG0007863360000026.jpg54151

[0150] As shown above in Figure 4, the normalized diffuse reflectance can be calculated by dividing the voltage value of each photodiode by the reference photodiode voltage value. As shown in the figure, in the optical data associated with the first and thirteenth light sources, the fifth and fifteenth photodiodes closest to the first and thirteenth light sources can be selected as reference photodiodes. For example, in the first row for multiple photodiodes associated with the first light source, the fifth photodiode can be selected as the reference photodiode, and in the second row, the fifteenth photodiode can be selected as the reference photodiode. As shown in the figure, in the optical data associated with the seventh and ninth light sources, the sixth and sixteenth photodiodes closest to the seventh and ninth light sources can be selected as reference photodiodes. For example, in the first row for multiple photodiodes associated with the seventh light source, the sixth photodiode can be selected as the reference photodiode, and in the second row, the sixteenth photodiode can be selected as the reference photodiode.

[0151] JPEG0007863360000027.jpg45151

[0152] As shown in the figure, the normalized diffuse reflectance 1122 of the first photodiode with respect to the seventh light source can be generated based on the measured voltage value 1112 of the first photodiode with respect to the seventh light source and the measured voltage value 1114 of the sixth photodiode with respect to the seventh light source, where the sixth photodiode may be a reference photodiode. Furthermore, the normalized diffuse reflectance 1128 of the seventh photodiode with respect to the thirteenth light source can be generated based on the measured voltage value 1116 of the fifth photodiode with respect to the thirteenth light source and the measured voltage value 1118 of the seventh photodiode with respect to the thirteenth light source, where the fifth photodiode may be a reference photodiode.

[0153] In one embodiment, the normalized diffuse reflectance data map 1120 may have fewer data points than the measurement voltage data map 1110. Specifically, the normalized diffuse reflectance for a specific reference photodiode is not calculated. For example, the normalized diffuse reflectance for the measurement voltage value 1116 of the fifth photodiode for the thirteenth light source is not calculated. Here, the fifth photodiode may be a reference photodiode. In the illustrated example, if the measurement voltage data map 1110 has 48 (4 × 12) data points and there are 8 measurement voltage values ​​corresponding to the reference photodiode, the number of normalized diffuse reflectance data points may be 40.

[0154] The light scattering coefficient can be associated with a specific region, where the light scattering coefficient may be the final light scattering coefficient. For example, the first region may be a body part associated with the first and second photodiodes. Similarly, the nth region may be a body part associated with the nth and n+1th photodiodes.

[0155] JPEG0007863360000028.jpg42151

[0156] As an example, the light scattering coefficient of the nth region for the yth light source can be estimated based on the normalized diffuse reflectance of the nth photodiode for the yth light source and the normalized diffuse reflectance of the (n+1)th photodiode for the y light source. For example, the light scattering coefficient 1132 of the first region for the seventh light source can be estimated based on the normalized diffuse reflectance 1122 of the first photodiode for the seventh light source and the normalized diffuse reflectance 1124 of the second photodiode for the seventh light source. Another example is the light scattering coefficient 1134 of the sixth region for the thirteenth light source, which can be estimated based on the normalized diffuse reflectance 1126 of the sixth photodiode for the thirteenth light source and the normalized diffuse reflectance 1128 of the seventh photodiode for the thirteenth light source.

[0157] Similarly, the light absorption coefficient data map can be calculated based on a normalized diffuse reflectance data map 1120, where the light absorption coefficient may be the final light absorption coefficient. Since the light absorption coefficient is part of the physiological information, the light absorption coefficient data map is used as physiological information.

[0158] In one embodiment, the light scattering coefficient data map 1130 may have fewer data points than the normalized diffuse reflectance data map 1120. Specifically, one light scattering coefficient can be estimated based on two normalized diffuse reflectances. For example, if the normalized diffuse reflectance data map 1120 has 40 (4 × 10) data points, the light scattering coefficient data map 1130 may have 32 (4 × 8) data points. Similarly, the light absorption coefficient data map may also have fewer data points than the normalized diffuse reflectance data map 1120.

[0159] After the first to 24th measurement processes are performed based on the above, a light scattering coefficient data map and a light absorption coefficient data map can be calculated for the multiple detected light data. In one embodiment, the light scattering coefficient data map and the light absorption coefficient data map can be generated separately for each wavelength. For example, after performing the second, eighth, fourteenth, and 20th measurement processes associated with a second wavelength, a light scattering coefficient data map and a light absorption coefficient data map for the second wavelength can be calculated for the multiple detected light data. Similarly, after performing multiple measurement processes associated with the nth wavelength, a light scattering coefficient data map and a light absorption coefficient data map for the nth wavelength can be calculated for the multiple detected light data. The process of calculating a physiological information data map based on multiple light scattering coefficient data maps will be described in detail later with reference to Figure 12.

[0160] Figure 12 shows an example of estimating physiological information based on multiple light scattering coefficient data maps according to one embodiment of the present disclosure. The multiple light scattering coefficient data maps 1210 may include wavelength-specific light scattering coefficient data maps. In one embodiment, the light scattering coefficient data map 1212_1 for a first wavelength may include all light scattering coefficients estimated based on multiple optical data detected by performing multiple measurement processes associated with the first wavelength. Similarly, each of the light scattering coefficient data maps 1212_2 to 1212_6 for second to sixth wavelengths is similar to the light scattering coefficient data map 1212_1 for the first wavelength, except that instead of the first wavelength, multiple measurement processes are performed associated with each of the second to sixth wavelengths, and the data is based on multiple optical data detected. Here, the light scattering coefficient can mean the final light scattering coefficient. In the illustrated example, the light scattering coefficient of the x-th region with respect to the y-th light source can be represented by x and y.

[0161] In one embodiment, a physiological information data map can be calculated based on multiple light scattering coefficient data maps 1210. Specifically, physiological information can be estimated based on multiple light scattering coefficients for a specific region for light sources associated with different wavelengths. The method for estimating physiological information based on light scattering coefficients can be found in the description in Figure 5.

[0162] For example, physiological information about the x-th region can be estimated based on the light scattering coefficients of [(x, y), (x, y+1), (x, y+2), (x, y+3), (x, y+4), (x, y+5)]. Here, (x, y) may be the light scattering coefficient of the x-th region for the y-th light source, as included in the light scattering coefficient data map 1212_1 for the first wavelength. Specifically, physiological information about the eighth region (e.g., oxygenated hemoglobin content, deoxygenated hemoglobin content, water content, fat content, etc.) can be estimated based on the light scattering coefficients of the eighth region for the first light source, the second light source, the third light source, the fourth light source, the fifth light source, and the sixth light source. Here, each of the first to sixth light sources can emit light of each of the first to sixth wavelengths.

[0163] In one embodiment, the multiple physiological information data maps may include a first physiological information data map 1220, a second physiological information data map 1230, a third physiological information data map 1240, and a fourth physiological information data map 1250. Here, each of the first to fourth physiological information data maps 1220, 1230, 1240, and 1250 may be one of an oxygenated hemoglobin (HbO2) data map, a deoxygenated hemoglobin (HHb) data map, a water (H2O) data map, and a fat (Fat) data map.

[0164] In one embodiment, the multiple physiological information data maps 1220, 1230, 1240, and 1250 can have fewer data points than the multiple light scattering coefficient data map 1210. Specifically, four pieces of physiological information can be estimated based on six data points contained in the multiple physiological information data maps. For example, if each of the multiple light scattering coefficient data maps 1210 contains 32 (4 × 8) data points, then the multiple light scattering coefficient data maps 1210 can contain 192 (4 × 8 × 6) data points. In this case, the multiple physiological information data maps 1220, 1230, 1240, and 1250 can contain 128 (4 × 8 × 4) data points.

[0165] By using multiple light sources and multiple photodiodes, physiological information concerning multiple regions can be provided. The invention described herein can provide physiological information not only for localized areas of the body but also for a wide range of body parts. Furthermore, by providing physiological information concerning multiple regions, the state of organs contained within the body (for example, the amount of urine stored in the bladder, the location of the bladder, etc.) can be specifically understood. In the case of patients who do not feel the urge to urinate, the invention described herein can be used to receive physiological information about their bladder in real time or periodically. Based on the information provided, patients can monitor the amount of urine stored in their bladder and urinate at the appropriate time.

[0166] Figure 13 is a block diagram showing an example of a method for estimating bladder volume according to one embodiment of the present disclosure. In the following description based on Figures 13 to 16, "measurement cycle" can refer to a series of processes for detecting an optical dataset using a medical device (e.g., medical device 100 described based on Figure 1) placed on the skin located on the bladder of a specific user. That is, the measurement cycle may include the first to 24 measurement processes shown in Figure 10. The detailed process of the measurement cycle can be understood from the above description based on Figures 1 and 10.

[0167] In one embodiment, the processor can receive an optical dataset 1302 associated with a specific user by performing a measurement cycle. For example, the optical dataset 1302 may include the measurement voltage data map 1110 shown in Figure 11. For example, the optical dataset 1302 may include 48 optical data points for each of six wavelengths.

[0168] In one embodiment, the optical characteristic value set estimation unit 1310 can estimate an optical characteristic value set for at least a part of a specific user's body based on the optical data set 1302. Here, the processor is the optical characteristic value set estimation unit 1310. For example, the optical characteristic value set estimation unit 1310 can calculate a normalized diffuse reflectance set for multiple photodiodes based on the optical data set 1302. Furthermore, the optical characteristic value set estimation unit 1310 can estimate an optical characteristic value set 1312 associated with at least a part of the body based on the normalized diffuse reflectance set. The series of processes performed by the optical characteristic value set estimation unit 1310 can be understood from the explanation based on Figures 4 to 12.

[0169] For example, the optical characteristic value set 1312 may include the final light scattering coefficient 554 and the final light absorption coefficient 556, as described with reference to Figure 5. For example, the optical characteristic value set 1312 may include the light scattering coefficient data map 1130 and the light absorption coefficient data map, as described with reference to Figure 11. For example, the optical characteristic value set 1312 may include 32 pairs of light scattering coefficients and light absorption coefficients for each of the six wavelengths.

[0170] In one embodiment, the urine volume estimation model 1320 can estimate the bladder urine volume 1322 of a specific user based on the optical characteristic value set 1312. In this case, the urine volume estimation model 1320 may be a deep learning-based model or a machine learning-based model that has been trained on multiple training datasets. For example, the machine learning-based model may be an ANN (Artificial Neural Network), KNN (K-Nearest Neighbors), GB (Gradient Boost), a Linear regression model, a Random Forest model, or an Ada Boost model. The training dataset may also include pairs of actual urine volume and optical characteristic value sets associated with the actual urine volume. The process of acquiring the training dataset and the process by which the urine volume estimation model 1320 learns from multiple training datasets will be described in detail based on Figures 14 and 15.

[0171] In another embodiment, the urine volume estimation model 1320 can estimate the user's bladder urine volume 1322 based on the optical characteristic value set 1312 and obesity information 1314. Here, the urine volume estimation model 1320 may be a deep learning-based model or a machine learning-based model that has learned multiple training datasets and training obesity information. In this case, the obesity information may include information about body fat in the area surrounding the bladder. For example, the obesity information may include body mass index (BMI; Body Max Index), obesity measured by the abdominal obesity measurement method, obesity measured by the standard weight method, body fat index, abdominal fat thickness measured using ultrasound, etc. As another example, the obesity information may include the optical absorption coefficient mentioned above. With this configuration, the urine volume estimation model 1320 can accurately estimate urine volume even in the case of obese users by learning the obesity information 1314.

[0172] In one embodiment, the processor can calculate a physiological information set based on the optical characteristic value set 1312. The process for calculating the physiological information set can be understood from the explanation based on Figure 12. Here, the physiological information set can correspond to the optical characteristic value set 1312. For example, the physiological information set can include optical absorption coefficient data included in the optical absorption coefficient data map. Also, the physiological information set can include multiple physiological information data maps 1220, 1230, 1240, and 1250 calculated based on the multiple optical scattering coefficient data maps 1210 described above, based on Figure 12. In this case, the processor can estimate urine volume 1322 using the optical characteristic value set 1312 and the physiological information set corresponding to the optical characteristic value set 1312. However, since the physiological information set can be calculated based on the optical characteristic value set 1312, the explanation will be based on the optical characteristic value set 1312.

[0173] For users with a high amount of fat around the skin where the bladder is located, the optical data included in the optical dataset 1302 may show little change despite an increase or decrease in bladder urine volume. In one embodiment, if the amount of change in the optical data included in the optical dataset 1302 is minimal despite an increase or decrease in bladder urine volume, the processor can output a result associated with inability to estimate urine volume. For example, the processor can output a result associated with inability to estimate urine volume if the obesity information 1314 is above a predetermined obesity threshold.

[0174] In one embodiment, if the estimated urine volume 1322 is greater than or equal to a predetermined threshold value, the processor can output a message related to a urination recommendation. For example, the threshold value can correspond to the average amount of urine in the bladder at which a person feels the urge to urinate. Specifically, the processor can output visual, auditory, and tactile information via the user terminal / medical device as a message related to a urination recommendation. For example, the user terminal / medical device can output a pop-up window or vibration / sound notification recommending urination. With this configuration, a patient wearing the medical device can urinate at the appropriate time by being provided with a message related to a urination recommendation.

[0175] The measurement cycle can be performed in real time or periodically. The invention according to this disclosure can provide the patient with an estimated urine volume 1322 based on an optical data set 1302 detected by the measurement cycle. The patient may be provided with bladder urine volume in real time or periodically. That is, the patient can monitor the amount of urine stored in their bladder with the provided information and urinate at the appropriate time.

[0176] Figure 14 is a graph showing an example of training data according to one embodiment of the present disclosure. In one embodiment, the processor can receive an optical dataset associated with the nth measurement by the nth measurement cycle (where n is 1, 2, 3, 4 or more). The processor can estimate the optical characteristic value of the nth measurement based on the optical dataset of the nth measurement. In this case, the nth actual urine volume may be a value directly measured from the bladder urine volume of a particular user at the time the nth measurement cycle was performed. For example, the actual urine volume can be obtained through processes such as bladder irrigation, urodynamic study (UDS), or clean intermittent catheterization (CIC).

[0177] As an example, the actual urine volume can be obtained through a bladder irrigation process. Specifically, the bladder irrigation process may include draining the urine from a specific user's bladder using a Foley catheter. At this time, the amount of urine in the specific user's bladder can be specifically confirmed using an ultrasonic bladder volume device (RU scanner, Residual Urine Scanner). Subsequently, the bladder irrigation process may involve injecting sterile saline solution into the specific user's bladder. At this point, the actual urine volume can correspond to the volume of sterile saline solution injected. For example, if all the urine in the specific user's bladder has been drained, the first actual urine volume may be approximately 0 ml. Subsequently, if 100 ml of sterile saline solution is injected into the specific user's bladder, the second actual urine volume may be 100 ml.

[0178] As another example, actual urine volume can be obtained through a urodynamic examination process. Specifically, the urodynamic examination process may include a bladder lavage process using a Foley catheter for UDS instead of a standard Foley catheter. Actual urine volume can be obtained through the bladder lavage process included in the urodynamic examination process. Furthermore, the urodynamic examination process can acquire a variety of measurement data, such as internal bladder pressure, bladder muscle activity, and the state of the urethra-bladder connection. As an example, the training dataset may include this measurement data.

[0179] Another example is that actual urine volume can be obtained through the self-catheterization process. Specifically, the self-catheterization process may involve using a self-catheterization catheter to drain urine from the bladder. At this time, the amount of urine drained using the self-catheterization catheter can be measured (for example, by measuring the amount of urine drained using a catheterization cup). In this case, the actual urine volume can be calculated using the amount of urine drained. For example, through the self-catheterization process, all the urine in the bladder may be drained in two stages. 200 ml of urine may be drained in the first stage, and 150 ml of urine may be drained in the second stage. In this case, the first actual urine volume may be 350 ml, the second actual urine volume 150 ml, and the third actual urine volume 0 ml.

[0180] For example, multiple actual urine volumes can be obtained. For instance, a first actual urine volume corresponding to the minimum bladder volume of a specific user can be obtained. Furthermore, a second actual urine volume (X) corresponding to the minimum bladder volume of that specific user can be obtained (where X is 2, 3, or more). If X is 3 or greater, the second to X-1 actual urine volumes can be obtained as values ​​between the first actual urine volume and the X actual urine volume.

[0181] The graph in Figure 14 may have time on the x-axis and the bladder volume of a specific user on the y-axis. Referring to Figure 14, the actual urine volume contained in each of the first training data 1410, second training data 1420, third training data 1430, and fourth training data 1440 may be displayed. Specifically, the first training data 1410 may include the first actual urine volume at the time the first measurement cycle was performed. Similarly, the nth training data may include the nth actual urine volume at the time the nth measurement cycle was performed. Additionally, the nth training data may include pairs of the nth actual urine volume and the nth measurement optical characteristic value. Figure 14 shows only the first to fourth training data 1440, but is not limited to these. For example, multiple training data can be obtained by more than four or fewer measurement cycles.

[0182] The minimum urine volume of a specific user's bladder can correspond to the amount of urine when all of the urine in the bladder has been emptied. For example, the minimum urine volume of a specific user's bladder may be approximately 0 ml. Also, the maximum urine volume of a specific user's bladder can correspond to the maximum capacity of the bladder. For example, the maximum urine volume of a specific user's bladder may be approximately 400 ml to 500 ml. The minimum and maximum urine volumes of a specific user's bladder can differ from user to user. Referring to Figure 14, the first actual urine volume corresponds to the minimum urine volume of a specific user's bladder, and the third actual urine volume corresponds to the maximum urine volume of a specific user's bladder.

[0183] In one embodiment, the teacher model can be generated by learning from multiple training datasets. For example, the teacher model can be a linear regression model, a random forest model, or the like. The teacher model can also take additional training urine volume data as input to estimate an additional training optical characteristic value set.

[0184] For example, the nth training model may be a training model trained on the (n+1)th training dataset and the nth training dataset. Here, the additional training urine volume for the nth estimation can be any value selected between the (n+1)th actual urine volume and the nth actual urine volume. Here, the nth estimation can mean the process of estimating multiple sets of additional training optical characteristic values ​​for the nth estimation using the nth training model, based on multiple additional training urine volumes for the nth estimation between the (n+1)th actual urine volume and the nth actual urine volume. For example, the multiple additional training urine volumes for the nth estimation can be values ​​selected at a constant interval between the (n+1)th actual urine volume and the nth actual urine volume. For example, if the (n+1)th actual urine volume is 400 ml and the nth actual urine volume is 100 ml, then the first additional training urine volume for the nth estimation may be 200 ml and the second additional training urine volume for the nth estimation may be 300 ml.

[0185] For example, the first estimation may include a process of estimating a first additional training optical characteristic value set based on a second actual urine volume and a first additional training urine volume between the first actual urine volumes. Similarly, the first estimation may include a process of estimating a kth additional training optical characteristic value set based on a kth additional training urine volume between the second actual urine volume and the first actual urine volume (where k is 1, 2, 3, or more). In this case, the first additional training dataset of the first estimation may include a first additional training urine volume and a first additional training optical characteristic value set. Similarly, the kth additional training dataset of the first estimation may include a kth additional training urine volume and a kth additional training optical characteristic value set.

[0186] Referring to the graph in Figure 14, the amount of urine used for additional training included in each of the first additional training dataset 1412_1, the second additional training dataset 1412_2, and the third additional training dataset 1412_3 of the first estimation can be displayed. Specifically, the amount of urine used for additional training from the first additional training dataset 1412_1 to the third additional training dataset 1412_3 of the first estimation can be displayed between the first actual urine volume and the second actual urine volume. As an example, each time point for the first additional training dataset 1412_1 to the third additional training dataset 1412_3 of the first estimation can correspond to a method in which the amount of urine used for additional training is selected between the second actual urine volume and the first actual urine volume. For example, if multiple additional training urine volumes are selected as values ​​at regular intervals between the second actual urine volume and the first actual urine volume, then each time point for the first additional training dataset 1412_1 to the third additional training dataset 1412_3 of the first estimation can be selected as values ​​at regular intervals between the second actual urine volume measurement time and the first actual urine volume measurement time. For example, if the second actual urine volume is 400 ml, the time point corresponding to the first training data 1410 is 0 seconds, the first actual urine volume is 0 ml, the time point corresponding to the second training data 1420 is 4000 seconds, the first estimated additional training urine volume is 100 ml, the second estimated additional training urine volume is 200 ml, and the third estimated additional training urine volume is 300 ml, then the time point corresponding to the first estimated first additional training dataset 1412_1 is 1,000 seconds, the time point corresponding to the second estimated additional training dataset 1412_2 is 2,000 seconds, and the time point corresponding to the third estimated additional training dataset 1412_3 is 3,000 seconds.

[0187] Based on the above explanation regarding the first estimation between the second training data 1420 and the first training data 1410, the second estimation between the third training data 1430 and the second training data 1420, and the third estimation between the fourth training data 1440 and the third training data 1430 can be understood similarly.

[0188] Figure 14 shows, but is not limited to, three additional training datasets 1412_1 to 1412_3 for the first estimation. For example, if the number of urine volumes for additional training is selected to be more than 3 or less than 3, the additional training datasets may also be generated to be more than 3 or less than 3. Also, Figure 14 shows a model in which four measurement cycles are performed, but is not limited to this. For example, measurements may be performed more than or less than 4 times. Another example is that multiple measurements may be performed within 72 hours.

[0189] In one embodiment, if the measurement cycle is performed twice, two training datasets can be obtained. For example, the first urine volume included in the first training dataset corresponds to the minimum urine volume of a specific user's bladder, and the second urine volume included in the second training dataset corresponds to the maximum urine volume of a specific user's bladder. In this case, by minimizing data collection from the user, inconvenience to the user is minimized, and a personalized urine volume prediction model can be generated.

[0190] In other embodiments, if the measurement cycle is performed multiple times (e.g., three or more times), multiple training datasets can be obtained. In this case, multiple teacher models can be generated based on the multiple training datasets, and multiple additional training datasets can be generated based on the multiple teacher models. The urine volume prediction model can improve the accuracy of bladder urine volume estimation by learning from multiple training datasets and multiple additional training datasets.

[0191] Figure 15 is a block diagram showing an example of a urine volume estimation model 1550 according to one embodiment of the present disclosure. In one embodiment, the urine volume estimation model 1550 can learn from multiple training datasets 1512 and 1514. Here, the nth training dataset can include a pair of the nth actual urine volume and an nth set of optical characteristic values. That is, the multiple training datasets 1512 and 1514 can include multiple actual urine volumes 1512 and multiple sets of optical characteristic values ​​1514. The method for obtaining multiple training datasets can be understood from the multiple training data 1410, 1420, 1430, and 1440 described above based on Figure 14.

[0192] In one embodiment, the urine volume estimation model 1550 can further train one or more additional training datasets 1532, 1534. Here, the kth additional training dataset can include pairs of the kth additional training urine volume and the kth additional training optical characteristic value set. That is, multiple additional training datasets 1532, 1534 can include multiple additional training urine volumes 1532 and multiple additional training optical characteristic value sets 1534. The method for obtaining multiple additional training datasets can be understood from the multiple additional training datasets 1412_1~1412_3, 1422_1, 1422_2, 1432_1~1432_4 described above, based on Figure 14. Figure 15 shows multiple pairs of additional training urine volumes and additional training optical characteristic value sets, but is not limited to this; there may be only one pair of additional training urine volumes and additional training optical characteristic value sets.

[0193] In one embodiment, the urine volume estimation model 1550 can be trained by applying weights 1520 to multiple training datasets 1512 and 1514. Specifically, the weights 1520 may be information for the urine volume estimation model 1550 to adjust the training weights of multiple additional training datasets 1532 and 1534 and multiple training datasets 1512 and 1514. For example, the weights 1520 may be predetermined before the urine volume estimation model 1550 is trained on data. Additionally or alternatively, the weights 1520 may be applied to multiple additional training datasets and adjusted during the training process of the urine volume estimation model 1550.

[0194] In one embodiment, the urine volume estimation model 1550 can further learn obesity information 1540 for learning. In this case, the obesity information 1540 for learning may be obesity information of bodies that are the subjects of multiple actual urine volume measurements 1512. Figure 15 shows a single set of obesity information 1540 for learning, but is not limited to this. For example, if multiple actual urine volume measurements 1512 are performed on multiple bodies, the urine volume estimation model 1550 can learn multiple sets of obesity information for learning.

[0195] The urine volume estimation model 1550 can learn by applying a weighted value 1520 to multiple training datasets 1512 and 1514, thereby giving more weight to multiple actual urine volumes 1512. This allows the urine volume estimation model 1550 to accurately estimate urine volume. Furthermore, by learning with training obesity information 1540, the urine volume estimation model 1550 can be provided to individual users. Moreover, since the urine volume estimation model 1550 utilizes machine learning models or deep learning models, which have relatively good app development support, the invention of this disclosure can be easily used in the development of mobile applications for wearable devices. Furthermore, machine learning models or deep learning models are easy to retrain, and the invention of this disclosure can perform personalized estimation of bladder urine volume. In addition, the urine volume estimation model 1550 is easy to maintain and improve, and has excellent model extensibility and versatility.

[0196] Figure 16 is a graph showing several examples of a urine volume estimation model according to one embodiment of the present disclosure. Referring to Figure 16, the urine volume estimation graph 1600 can display the urine volume estimation results of multiple urine volume estimation models. Specifically, the urine volume estimation graph 1600 can display the first graph 1640, the second graph 1650, and the third graph 1660. In Figure 16, the third graph 1660 may be displayed as a dotted line graph. The urine volume estimation graph 1600 can also display the first actual urine volume included in the first training dataset 1610 and the second actual urine volume included in the second training dataset 1630. Furthermore, the urine volume estimation graph 1600 can display the first comparative actual urine volume included in the first comparison dataset 1622, the second comparative actual urine volume included in the second comparison dataset 1624, and the third comparative actual urine volume included in the third comparison dataset 1626. The urine volume estimation graph 1600 can display an index on the x-axis and bladder urine volume (actual urine volume and / or estimated urine volume) on the y-axis. In this case, the index can be an indicator to represent the passage of time. For example, the index at the time when the first measurement cycle is performed can be indicated as 0, and the index at the time when the second measurement cycle is performed can be indicated as 4.

[0197] In one embodiment, the first training dataset 1610 may include pairs of a first actual urine volume and a first set of optical characteristic values. The second training dataset 1630 may include pairs of a second actual urine volume and a second set of optical characteristic values. In one embodiment, the first comparison dataset 1622 may include pairs of a first comparative actual urine volume and a first comparative set of optical characteristic values. Similarly, the second comparison dataset 1624 may include pairs of a second comparative actual urine volume and a second set of comparative optical characteristic values, and the third comparison dataset 1626 may include pairs of a third comparative actual urine volume and a third set of comparative optical characteristic values. Here, the multiple training datasets 1610, 1630 and the multiple comparison datasets 1622, 1624, 1626 may be obtained by performing a measurement cycle. For example, multiple training datasets 1610, 1630 and multiple comparison datasets 1622, 1624, 1626 may have been obtained from a specific user who had a medical device (e.g., medical device 100 shown in Figure 1) attached to the skin located over the bladder.

[0198] For example, the first actual urine volume may be the actual urine volume in a specific user's bladder at the time the first measurement is performed. The second actual urine volume may be the actual urine volume in a specific user's bladder at the time the second measurement is performed. Referring to Figure 16, the first actual urine volume may be approximately 100 ml, and the second actual urine volume may be approximately 300 ml. The method for measuring the actual urine volume can be understood from the above description based on Figure 14.

[0199] Similarly, the method for measuring the first to third comparative actual urine volumes is the same as the method for measuring the first and second actual urine volumes. In this case, the first to third comparative actual urine volumes may be actual urine volumes not used in training the urine volume learning model. Also, the first to third comparative optical characteristic value sets may be optical characteristic value sets not used in training the urine volume learning model.

[0200] As an example, the first to third comparative urine volumes may be selected between the first and second urine volumes. For instance, the first to third comparative urine volumes may be selected to have the same interval between the first and second urine volumes. Referring to Figure 16, if the first urine volume is 100 ml and the second urine volume is 300 ml, then the first comparative urine volume may be 150 ml, the second comparative urine volume 200 ml, and the third comparative urine volume 250 ml. In Figure 16, three comparative urine volumes are selected, but more or fewer than three comparative urine volumes may also be selected.

[0201] In Figure 16, the "comparative measurement cycle" can refer to a measurement cycle used to estimate the comparative optical characteristic value set. In this case, the index at the time the first comparative measurement cycle is performed can be indicated as 1, the index at the time the second comparative measurement cycle is performed can be indicated as 2, and the index at the time the third comparative measurement cycle is performed can be indicated as 3. For example, the nth comparative measurement cycle may be performed at the time when the nth comparative actual urine volume is measured. Furthermore, the nth comparative optical characteristic value set can be estimated based on the nth comparative optical data set detected by the nth comparative measurement cycle.

[0202] In one embodiment, the first urine volume estimation model may be a model trained on the first training dataset 1610 and the second training dataset 1630. For example, an ANN model may be used for the first urine volume estimation model. The first graph 1640 can display the urine volume estimation results of the first urine volume estimation model. The training model may also be a model trained on the first training dataset 1610 and the second training dataset 1630. For example, a Random Forest model or a Linear Regression model may be used for the training model. The second graph 1650 can display the urine volume estimation results of the training model. The second urine volume estimation model may also be a model trained on the first training dataset 1610, the second training dataset 1630, and multiple additional training datasets. In this case, the multiple additional training datasets may be generated by the training model. For example, an ANN model may be used for the second urine volume estimation model. The third graph 1660 can display the urine volume estimation results of the second urine volume estimation model.

[0203] Comparing the urine volume estimation results of the first urine volume estimation model, the second urine volume estimation model, and the training model, the results can be represented as shown in Table 3. Referring to Figure 16, the urine volume estimation graph 1600 may represent Table 3.

[0204] [Table 3]

[0205] In Table 3, the urine volume estimation model can include a first urine volume estimation model, a second urine volume estimation model, and a training model. The urine volume estimation model can estimate urine volume by inputting a set of optical characteristic values ​​(or a set of comparative optical characteristic values) corresponding to each index. For example, the first urine volume estimation model can generate a urine volume estimation result corresponding to approximately 39.1 ml when the first set of comparative optical characteristic values ​​is input. In this case, the estimation error of the first urine volume estimation model may be 110.9 ml, which is obtained by subtracting the estimation result of the first urine volume estimation model, 39.1 ml, from the first comparative actual urine volume, 150 ml. Similarly, the second urine volume estimation model can generate a urine volume estimation result corresponding to approximately 115.6 ml when the first set of comparative optical characteristic values ​​is input. In this case, the estimation error of the second urine volume estimation model may be 34.4 ml, which is obtained by subtracting the estimation result of the first urine volume estimation model, 115.6 ml, from the first comparative actual urine volume, 150 ml. Table 3 or Urine Volume Estimation Graph 1600 confirms that the second urine volume estimation model, which was trained on multiple training datasets and multiple additional training datasets, has a smaller urine volume estimation error than the first urine volume estimation model, which was trained on multiple training datasets.

[0206] If the amount of training dataset is insufficient, the supervising model generates multiple additional training datasets, thus performing data augmentation. By learning more data through data augmentation, the urine volume prediction model can realize an automated bladder urine volume prediction method designed based on medical knowledge and diagnosis.

[0207] Figure 17 shows an example of an interface for managing a digital urination diary according to one embodiment of the present disclosure. In one embodiment, a medical device (for example, medical device 100 shown in Figure 1) is used by a specific user to manage a digital urination diary. Before using the medical device, the specific user can link their user terminal with the medical device. In addition, the user terminal can receive the specific user's personal information in order to provide information optimized for the specific user. Subsequently, an artificial intelligence model (for example, a urine volume prediction model) for the specific user can be generated based on the information obtained from the linked medical device.

[0208] In one embodiment, the first interface 1710 can display messages guiding a specific user regarding information about the linkage between the medical device and the user terminal. For example, the first interface 1710 can display a guide on how to link the medical device and the user terminal. For instance, once the linkage between the medical device and the user terminal is complete, the user can proceed to the next step.

[0209] In one embodiment, the second interface 1720 can display a message requesting input for information of a specific user. Specifically, the second interface 1720 can display a message requesting information of a specific user necessary to create a urination diary. For example, the second interface 1720 can display a message requesting input for personal information of a specific user (e.g., name, gender, age, weight, height, obesity information, etc.). The user can input their personal information through the second interface 1720.

[0210] In one embodiment, the third interface 1730 can display messages guiding the user through the process after the input of information for a specific user is complete. For example, the third interface 1730 can display a message indicating that the input of information for a specific user is complete. Additionally or alternatively, the third interface 1730 can display a summary of the input information.

[0211] In one embodiment, the fourth interface 1740 can display messages related to the generation of an artificial intelligence model for a specific user. For example, the fourth interface 1740 may include an input object 1742. When input is received for the input object 1742, a medical device linked to a user terminal can receive multiple optical datasets for the specific user. Subsequently, by learning from the multiple received optical datasets, an artificial intelligence model for the specific user can be generated. At this time, the artificial intelligence model can also learn personal information about the specific user.

[0212] This configuration allows users to easily receive guidance on how to connect their user terminal with the medical device. The user then uses the medical device connected to their user terminal. Furthermore, information about the user can be input to optimize the medical device and the user-specific artificial intelligence model for that user.

[0213] Figure 18 shows an example of a voiding diary according to one embodiment of the present disclosure. The processor can output information related to the amount of urine voided by a specific user as a voiding diary. The amount of urine voided can be calculated based on the estimated urine volume (for example, the urine volume 1322 shown in Figure 13). Specifically, the processor can receive multiple optical data related to a specific user, measured from multiple photodiodes in the medical device at multiple time points. The processor can also estimate the amount of urine in the bladder for each of the multiple time points based on the multiple optical data sets. Subsequently, the processor can record the amount of urine in the bladder of the specific user for the estimated multiple time points. The specific process for estimating the amount of urine in the bladder for each of the multiple time points can be understood from the content described above in Figures 13 to 16. At this time, the amount of urine voided can be calculated based on the amount of urine in the bladder of the specific user for the recorded multiple time points.

[0214] In one embodiment, the amount of urine in a specific user's bladder at a first time point and the amount of urine in a specific user's bladder at a second time point can be recorded. In this case, the amount of urine excreted can be calculated based on the difference between the amount of urine at the first time point and the amount of urine at the second time point. For example, the amount of urine excreted calculated based on the amount of urine at the second time point and the amount of urine at the first time point can be recorded as the amount of urine excreted at the second time point.

[0215] Urine volume can be divided into urination during sleep and urination while awake. For example, urination during sleep is the amount of urine a specific user urinates at the time they are asleep, and may be calculated based on the amount of urine in the bladder recorded at that time. Similarly, urination while awake is the amount of urine a specific user urinates at the time they are awake, and may be calculated based on the amount of urine in the bladder recorded at that time.

[0216] Referring to Figure 18, the first interface 1810 can display at least a portion of the urination diary. Here, the first interface 1810 can display the amount of urine urinated while awake, along with the first visual object 1812. The first interface 1810 can also display the amount of urine urinated while sleeping, along with the second visual object 1814.

[0217] In one embodiment, the processor can receive or estimate information regarding a specific user's sleep / wake-up times. For example, the user can input sleep / wake-up information via a user terminal. In another example, the processor can estimate sleep / wake-up information based on an optical dataset (e.g., optical dataset 1302 shown in Figure 13). In yet another example, the processor can estimate sleep / wake-up information based on information generated by sensors included in a medical device (e.g., motion sensing sensors or gyroscopes). In yet another example, the processor can estimate sleep / wake-up information based on time information, etc.

[0218] The processor can calculate the total daily urination volume based on the urination volume at multiple points in time, where each point in time may include information about the year, month, day, hour, minute, and second. Specifically, the total daily urination volume can be calculated based on the urination volume at any of the multiple points in time that fall on the same date. Referring to Figure 18, the first interface 1810 can display the total urination volume by date via the third visual object 1816.

[0219] In one embodiment, the processor can calculate the amount of urine excreted for periodic time points. In this case, the processor periodically receives multiple optical data sets detected by multiple photodiodes in the medical device, and calculates the amount of urine excreted for periodic time points based on the received optical data sets. Here, the period for calculating the amount of urine excreted can be predetermined.

[0220] As an example, the processor can calculate the amount of urine excreted for each urination time of a specific user. In this case, the processor can determine the time of urination based on sensors or optical data sets included in the medical device. Alternatively, the processor can receive input of the time of urination via a user terminal. Referring to Figure 18, the first interface 1810 can display the first input object 1818. The processor can receive the optical data set by receiving input to the first input object 1818. Subsequently, the processor can calculate the amount of urine excreted at the time the input to the first input object 1818 was received, based on the received optical data set. In this case, the time the input to the first input object 1818 was received corresponds to the time of urination.

[0221] The processor can output information related to a specific user's urine volume in various ways as a urination diary. Referring to Figure 18, the second interface 1820 can display information related to urine volume for a specific date. Here, the processor can switch from the first interface 1810 to the second interface 1820 by receiving input to the second input object 1822. The second interface 1820 can display at least a portion of the urination diary for the time when the specific user is awake on a specific date, together with the fourth visual object 1824. The second interface 1820 can also display the total urine volume and number of urinations for the time when the specific user is awake on a specific date via the fifth visual object 1826. Furthermore, the second interface 1820 can display the total urine volume and number of urinations for the time when the specific user is asleep on a specific date via the sixth visual object 1828.

[0222] Creating a voiding diary may be essential for the diagnosis and prescription of voiding disorders such as overactive bladder, underactive bladder, benign prostatic hyperplasia, nocturia, recurrent cystitis, and urinary incontinence. The invention disclosed herein provides patients and doctors with a digitized voiding diary by digitizing the diary. Specifically, accurate and rapid calculation of the time and volume of urination can be performed, and if the patient is wearing the medical device, the time and volume of urination can be automatically recorded. In other words, the patient does not have to measure with a voiding cup and handwrite the diary, thus providing high user accessibility.

[0223] Figure 19 shows an example of a voiding diary according to one embodiment of the present disclosure. The processor can calculate at least a portion of the voiding diary based on the recorded urine volume (for example, the urine volume 1322 shown in Figure 13). Specifically, the processor can calculate voiding analysis results by analyzing the voiding records. For example, the processor can calculate the average total daily urine volume, the average number of urinations per day, the number of nighttime urinations per day, the average number of nighttime urinations per day, the percentage of nighttime urine volume per day, the average percentage of nighttime urine volume per day, the average nighttime urine volume per day, and functional bladder volume as voiding analysis results. Here, functional bladder volume can mean the maximum voiding volume of a particular user's bladder. For example, functional bladder volume can mean the maximum voiding volume in the created voiding diary.

[0224] In one embodiment, the processor can output voiding analysis results. Referring to Figure 19, the first interface 1910 can display the voiding analysis results. The first interface 1910 can display the average total daily voiding volume together with the first visual object 1912. The first interface 1910 can display the average number of urinations per day together with the second visual object 1914. The first interface 1910 can display the average number of urinations during sleep per day together with the third visual object 1916. The first interface 1910 can display the average percentage of voiding volume during sleep together with the fourth visual object 1918. The first interface 1910 can display the functional bladder volume together with the fifth visual object 1919.

[0225] The second interface 1920 can display the amount of urine excreted on a daily basis. For example, the processor can record the amount of urine in a particular user's bladder at multiple points in time within a certain period (e.g., 72 hours). In this case, the second interface 1920 can display the amount of urine excreted on a daily basis within that period as a bar graph.

[0226] The third interface 1930 can display the percentage of sleep urination by day. For example, the processor can calculate the percentage of sleep urination by day based on the total sleep urination by day and the nocturia (frequent nighttime urination) by day. In this case, the third interface 1930 can display the calculated percentage of sleep urination by day as a bar graph.

[0227] With this configuration, the digital voiding diary management method can reduce the analysis time for medical staff by providing an automated analysis function for diagnosing voiding disorders, thereby increasing accessibility for users. Furthermore, the invention disclosed herein provides automatically analyzed data regarding the average total daily voiding volume, the average number of urinations per day, the number of urinations during sleep per day by date, the average number of urinations during sleep per day, the percentage of urination volume during sleep per day, the average percentage of urination volume during sleep per day, the average urination volume during sleep per day, and functional bladder volume, enabling doctors to perform accurate and rapid diagnoses and prescriptions for patients.

[0228] Figure 20 is a flowchart illustrating a digital urination diary management method 2000 according to one embodiment of the present disclosure. The method 2000 can be performed by a control unit (or at least one processor) of a medical device, a user terminal and / or at least one processor of an information processing system. The method 2000 is initiated by a step (S2010) in which the processor receives, at multiple time points, multiple optical datasets associated with a specific user detected by multiple photodiodes in the medical device.

[0229] In one embodiment, the processor can estimate the amount of urine in the bladder for each of several time points based on multiple optical datasets (S2020). Specifically, the processor can estimate multiple sets of optical characteristic values ​​for at least a part of a particular user's body based on multiple optical datasets. Furthermore, based on the estimated sets of optical characteristic values, the processor can estimate the amount of urine in the bladder for each of several time points using a urine volume estimation model. Here, the urine volume estimation model is a deep learning-based model or a machine learning-based model trained on multiple training datasets, and the multiple training datasets may include pairs of the actual urine volume of a particular user and sets of optical characteristic values ​​associated with the actual urine volume.

[0230] In one embodiment, the training datasets include a first training dataset and a second training dataset, the first training dataset including a first actual urine volume of a specific user and a pair of first training optical characteristic values ​​associated with the first actual urine volume, and the second training dataset including a second actual urine volume of a specific user and a pair of second training optical characteristic values ​​associated with the second actual urine volume, the second actual urine volume may be greater than the first actual urine volume.

[0231] In one embodiment, the processor can record the bladder volume of a specific user for each of several estimated time points (S2030). The processor can also output the total daily urination volume of the specific user based on the recorded bladder volume of the specific user for each of the several recorded time points.

[0232] In one embodiment, the processor can display the amount of urine a particular user urinates while awake, along with a first visual object, based on the amount of urine in the user's bladder at each of several recorded time points. It can also display the amount of urine a particular user urinates while sleeping, along with a second visual object, based on the amount of urine in the user's bladder at each of several recorded time points.

[0233] In one embodiment, the processor can output the average total daily urine volume and the average number of times a day a particular user urinates, based on the bladder volume of that particular user for each of several recorded time points.

[0234] In one embodiment, the processor can output the number of times a particular user urinates during sleep on a given day or the percentage of the amount of urine urinated during sleep on a given day, based on the amount of urine in the bladder of that particular user for each of several recorded time points.

[0235] In one embodiment, the processor can estimate the functional bladder volume of a specific user based on the amount of urine in the user's bladder at each of several recorded time points. The processor can also output the estimated functional bladder volume of the specific user.

[0236] The methods described above may be provided as computer programs stored on a computer-readable recording medium for execution on a computer. The medium may be used to continuously store computer-executable programs or to temporarily store them for execution or download. The medium may also be a variety of recording or storage means in the form of a single or multiple hardware combination, and is not limited to a medium directly connected to a computer system, but may be distributed over a network. Examples of mediums include magnetic media such as hard disks, flexible disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical mediums such as floppy disks, and ROMs, RAMs, flash memories, etc., configured to store program instructions. Other examples of mediums include recording or storage media managed by app stores that distribute applications and other sites and servers that supply or distribute various software.

[0237] The methods, operations, or techniques described herein can be implemented by a variety of means. For example, such techniques can be implemented in hardware, firmware, software, or a combination thereof. A person of ordinary skill would understand that the various exemplary logical blocks, modules, circuits, and algorithmic steps described herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate these mutual substitutability between hardware and software, various exemplary components, blocks, modules, circuits, and steps have been generally described in terms of their functional aspects. Whether such functions are implemented as hardware or software depends on the design requirements attached to the specific application and the overall system. A person of ordinary skill may implement the functions described in a variety of ways for each specific application, but such implementations should not be construed as exceeding the scope of this disclosure.

[0238] In hardware implementation, the processing units used to perform the techniques may be implemented in one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, other electronic units designed to perform the functions described herein, computers, or combinations thereof.

[0239] Accordingly, the diverse exemplary logic blocks, modules, and circuits described herein may also be embodied or performed by any combination of general-purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gates and transistor logic, discrete hardware components, or any combination designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but alternatively, a processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be embodied by a combination of computing devices, such as a DSP and a microprocessor, multiple microprocessors, one or more microprocessors associated with a DSP core, or any other combination of configurations.

[0240] In the embodiment of firmware and / or software, the technique can be embodied in instructions stored on a computer-readable medium such as RAM (random access memory), ROM (read-only memory), NVRAM (non-volatile random access memory), PROM (programmable read-only memory), EPROM (erasable programmable read-only memory), EEPROM (electrically erasable PROM), flash memory, CD (compact disc), or magnetic or optical data storage devices. The instructions may be executable by one or more processors, which can perform specific modes of the functions described herein.

[0241] When embodied in software, the technique may be stored on or transferred via a computer-readable medium as one or more instructions or code. A computer-readable medium includes any medium that facilitates the transfer of a computer program from one location to another, and includes both computer storage media and communication media. The storage medium may be any available medium accessible by a computer. As an unrestricted example, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium accessible by a computer that can be used to transfer or store desired program code in the form of instructions or data structures. Furthermore, any connection may appropriately refer to a computer-readable medium.

[0242] For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, lead wire, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, lead wire, digital subscriber line, or wireless technologies such as infrared, radio, and microwave are included within the definition of a medium. The terms "disk" and "disc" used in this application include CDs, laser discs, optical discs, DVDs (digital versatile discs), flexible discs, and Blu-ray discs, where a disk typically reproduces data magnetically, while a disc reproduces data optically using a laser. The aforementioned combinations, etc., must also be included within the scope of computer-readable media, etc.

[0243] Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, portable disks, CD-ROMs, or any other known form of storage medium. An exemplary storage medium may be linked to the processor so that the processor reads information from or writes information to the storage medium. Alternatively, the storage medium may be integrated into the processor. The processor and storage medium may reside within an ASIC. The ASIC may reside within a user terminal. Alternatively, the processor and storage medium may exist as separate components within the user terminal.

[0244] While the embodiments described above are described as utilizing aspects of the subject matter currently disclosed in one or more standalone computer systems, the disclosure is not limited to such embodiments and can be embodied in any computing environment, such as networks or distributed computing environments. Furthermore, aspects of the subject matter in this disclosure can be embodied in multiple processing chips or devices, and storage may be similarly affected across multiple devices. Such devices may include PCs, network servers, and portable devices.

[0245] While this disclosure has been described in part by some embodiments, various modifications and alterations are possible without departing from the disclosure as understood by a person of the ordinary skill in the art to which the invention of this disclosure pertains. Such modifications and alterations should be understood to fall within the scope of the claims appended to this specification. [Explanation of Symbols]

[0246] 100 Medical Devices 112_1 First photodiode 112_2 Second photodiode 112_20 The 20th photodiode 114_1 First Light Source Group 114_2 Second Light Source Group 114_3 Third Light Source Group 114_4 The fourth group of light sources 120 user terminals

Claims

1. In a digital urination diary management method performed by at least one processor, The process involves receiving three or more optical data sets associated with a specific user, detected by three or more photodiodes within the medical device at multiple time points, wherein the three or more photodiodes are configured to detect light intensity associated with light irradiated onto the skin located above the specific user's bladder. The steps include correcting the three or more optical datasets using calibration parameters that make the system parameters of each photodiode the same, based on the three or more optical datasets, A step of estimating the amount of urine in the bladder for each of the multiple time points based on the three or more corrected optical datasets, The step includes recording the amount of urine in the bladder of the particular user for each of the estimated multiple time points, The step of estimating the amount of urine in the bladder includes the step of calculating a plurality of normalized diffuse reflectances based on the three or more corrected optical datasets, The steps include: estimating the light absorption coefficient and light scattering coefficient for at least a part of the body of the specific user based on the multiple normalized diffuse reflectances calculated above; A method for managing a voiding diary, comprising estimating the amount of urine in the bladder for each of the multiple time points based on the estimated light absorption coefficient and light scattering coefficient, using a urine volume estimation model.

2. The voiding diary management method according to claim 1, further comprising the step of outputting the total daily voiding volume of the specific user based on the bladder volume of the specific user for each of the multiple recorded time points.

3. The steps include displaying the amount of urine the specific user urinates while awake, based on the amount of urine in the specific user's bladder for each of the recorded multiple time points, together with a first visual object, A method for managing a urination diary according to claim 1, further comprising the step of displaying the amount of urine a particular user urinates during sleep, together with a second visual object, based on the amount of urine in the particular user's bladder for each of the multiple recorded time points.

4. The urination diary management method according to claim 1, further comprising the step of outputting the average daily total urination volume and the average daily number of urinations of the specific user based on the bladder volume of the specific user for each of the multiple recorded time points.

5. The urination diary management method according to claim 1, further comprising the step of outputting the number of times the specific user urinates during sleep on a given day, or the percentage of the amount of urine urinated during sleep on a given day, based on the amount of urine in the specific user's bladder for each of the multiple recorded time points.

6. A step of estimating the functional bladder volume of the specific user based on the amount of urine in the bladder of the specific user for each of the multiple recorded time points, A method for managing a urination diary according to claim 1, further comprising the step of outputting the estimated functional bladder volume of the specific user.

7. The urine volume estimation model is a deep learning-based model or a machine learning-based model trained on multiple training datasets, The urination diary management method according to claim 1, wherein the plurality of training datasets include pairs of the actual urine volume of a specific user and sets of optical characteristic values ​​associated with the actual urine volume.

8. The plurality of training datasets include a first training dataset and a second training dataset, The first training dataset includes a pair of the first actual urine volume of the specific user and a first set of training optical characteristic values ​​associated with the first actual urine volume. The second training dataset includes a second actual urine volume of the specific user and a pair of second training optical characteristic values ​​associated with the second actual urine volume. The method for managing a urination diary according to claim 7, wherein the second actual urine volume is greater than the first actual urine volume.

9. A computer program stored on a computer-readable recording medium for performing the method according to any one of claims 1 to 8 on a computer.

10. A user terminal, Communications Department and, Memory and The system includes at least one processor connected to the memory and configured to execute at least one computer-readable program contained in the memory, The aforementioned at least one program, The process involves receiving three or more optical data sets associated with a specific user, detected by three or more photodiodes within the medical device at multiple time points, wherein the three or more photodiodes are configured to detect light intensity associated with light irradiated onto the skin located above the specific user's bladder. The steps include correcting the three or more optical datasets using calibration parameters that make the system parameters of each photodiode the same, based on the three or more optical datasets, A step of estimating the amount of urine in the bladder for each of the multiple time points based on the three or more corrected optical datasets, The command includes the step of recording the amount of urine in the bladder of the particular user for each of the estimated multiple time points, The step of estimating the amount of urine in the bladder includes the step of calculating a plurality of normalized diffuse reflectances based on the three or more corrected optical datasets, The steps include: estimating the light absorption coefficient and light scattering coefficient for at least a part of the body of the specific user based on the multiple normalized diffuse reflectances calculated above; A user terminal that estimates the amount of urine in the bladder for each of the multiple time points based on the estimated light absorption coefficient and light scattering coefficient, using a urine volume estimation model.

Images