KR20230108115A - Machine learning-based urinary disorder diagnosis and diaper dermatitis diagnosis system - Google Patents

Abstract

A machine learning-based urinary disorder diagnosis and diaper dermatitis diagnosis system of the present invention comprises: a smart diaper that fills between the user's legs, catches urine, and generates a second electrical signal when urinating; a terminal that transmits a first electrical signal to the smart diaper and receives a second electrical signal from the smart diaper, generates a urine generation signal based on the transmitted second electrical signal, and transmits the generated urine generation signal and the transmitted second electrical signal to the server; and a server that receives Urine-related data from at least one terminal and determines urination disorder or diaper dermatitis based on the urination-related data wherein the urination-related data includes urination start resistance value (Rs), urination end resistance value (Re), duration of one urination (Rh), total number of urinations during the day (Utd), the total number of urinations (Und) from 9 PM to 7 AM and the total urination time per week (W). The present invention is to induce needed care according to the occurrence posibilities of urinary disorder and diaper dermatitis.

Description

Machine learning-based urinary disorder diagnosis and diaper dermatitis diagnosis system}

The present invention relates to a system for diagnosing dysuria and diaper dermatitis through analysis of urination patterns using machine learning.

Urination control disorders, including urinary incontinence, are common diseases that more than half of the elderly living in long-term care institutions suffer from.

In order to prevent this, it is necessary to frequently check and replace the patient's diaper, which interferes with sufficient rest and sleep of the patient and guardian, which is a factor that lowers the quality of life. In addition, in an acute medical institution, inconvenience such as having to weigh a diaper every time to measure the amount of urine of a patient occurs.

Korean Patent Publication No. 1020060068819 (published on Jun. 21, 2006); A diaper that notifies you of urination

The present invention has the advantage of inducing appropriate management according to the probability of occurrence of dysuria and diaper dermatitis by calculating the probability of occurrence of dysuria and diaper dermatitis.

The machine learning-based urination disorder diagnosis and diaper dermatitis diagnosis system of the present invention is a smart diaper that is filled between the user's legs, receives urine, and generates a second electrical signal during urination, and transmits a first electrical signal to the smart diaper, A terminal that receives the second electrical signal from the smart diaper, generates a urine generation signal based on the transmitted second electrical signal, and transmits the generated urine generation signal and the transmitted second electrical signal to the server. , and urination-related data from at least one terminal - the urination-related data includes a urination start resistance value (Rs), a urination end resistance value (Re), a one-time urination duration (Rh), and the total number of urinations per day (Utd). , including the total number of urination (Und) from 9:00 pm to 7:00 am of the day and the total urination time (W) per week-received, and a server that determines dysuria or diaper dermatitis based on the urination-related data can include

In addition, the server may calculate the occurrence probability of dysuria or diaper dermatitis by a machine learning algorithm.

In addition, the server may calculate the probability of occurrence of urinary incontinence by the following equation (1).

(Re-Rs)/Rh = Cr1 Equation (1)

(Where, Cr1 is the probability of occurrence of urinary incontinence, Re is the resistance to end urination, Rs is the resistance to start urination, and Rh is the duration of urination once)

In addition, the server may calculate the probability of enuresis by the following Equation (2).

Und/Utd = Cr2 Equation (2)

Here, Cr2 is the probability of nocturnal enuresis, Und is the total number of urinations from 9:00 pm to 7:00 am during the day, and Utd is the total number of urinations during the day)

In addition, the server may calculate the probability of occurrence of oliguria by the following equation (3).

Utd/Utad = Cr3 Equation (3)

(Where, Cr3 is the probability of occurrence of oliguria, the Utd is the total number of urinations per day of users, and the average total number of urinations per day of all users of Utad)

In addition, the server may calculate the probability of occurrence of oliguria by the following equation (4).

It/W = Cr4 Equation (4)

(Where, Cr4 is the probability of occurrence of diaper dermatitis, It is the total accumulated incontinence time for one day, and W is the total urination time per week)

The present invention has the advantage of inducing appropriate management according to the urination disorder by calculating the probability of urination disorder occurrence in the elderly residing in a long-term care institution through machine learning.

In addition, the present invention has the advantage of improving the quality of life by increasing the diaper replacement frequency of the elderly with a high probability of dermatitis by calculating the probability of occurrence of diaper dermatitis based on machine learning.

In addition, the present invention has the advantage of reducing the burden of frequently checking and replacing the patient's diaper.

1 shows that the smart diaper and the terminal of the present invention are separated.
Figure 2 shows that the terminal is mounted on the smart diaper of the present invention.
3 is a block diagram of a system for diagnosing dysuria and diaper dermatitis through urination pattern analysis using machine learning according to the present invention.
4 is a block diagram of a terminal of the present invention.
5 is a block diagram of a server of the present invention.
6 shows the probability of occurrence of urinary incontinence according to Equation (1) of the present invention.
7 shows the probability of nocturnal enuresis according to Equation (2) of the present invention.
8 shows the probability of occurrence of oliguria according to Equation (3) of the present invention.
9 shows the probability of occurrence of diaper dermatitis (IAD) according to Equation (4) of the present invention.
10 shows the body of the present invention.

A system for diagnosing dysuria and diaper dermatitis through urination pattern analysis using machine learning according to an embodiment of the present invention includes a smart diaper 100, a terminal 200, and a server 300.

<Smart diaper (100)>

The smart diaper 100 according to an embodiment of the present invention may include a diaper portion 110, a pattern portion 120, and a first connection terminal 130.

1. Diaper unit 110

The diaper unit 110 may include a body 111 and a waist belt 112 as a mechanism that is filled between the user's legs and collects urine.

The body 111 is disposed to face the user's excretory organ that excretes urine. The body 111 has a length extending from the user's buttocks through between the legs to the stomach.

The waist belt 112 extends from the side of one end of the body 111 and has a length extending from the user's hip through the user's waist to the user's stomach.

The body 111 may include a surface layer 111a where urine first arrives, a diffusion layer 111b for diffusing urine, an absorbent layer for absorbing and storing urine, and a waterproof layer 111e for preventing leakage of urine to the outside. .

The surface layer 111a is formed of a hydrophilic fiber material and receives the wearer's urine and transfers it to the diffusion layer 111b.

The diffusion layer 111b is made of a hydrophobic material and diffuses the urine transferred from the water supply layer to the absorption layer.

The absorption layer may include an upper layer 111c made of a hydrophilic material and a lower layer 111d made of a cellulose material. The upper layer 111c absorbs a certain amount of urine. The lower layer 111d traps the remaining urine that could not be absorbed by the upper layer 111c to prevent the reverse leakage of urine. Here, the reverse leakage means that urine flows backward from the absorbent layer to the water layer when pressure is applied to the incontinence pants due to a change in the wearer's posture or coughing.

The waterproof layer 111e is a portion that meets the inside of the panty portion and may be a back sheet made of a waterproof material to prevent urine absorbed in the urine absorption layer from being discharged to the outside. The back sheet may have minute through holes through which moisture in a vapor state is discharged while moisture in a liquid state is not discharged.

2. Pattern part 120

The pattern part 120 may be formed on an inner surface of the waterproof layer 111e or an outer surface of the waterproof layer 111e.

The pattern part 120 may be formed so that the first pattern 121 and the second pattern 122 face each other at regular intervals. The first pattern 121 and the second pattern 122 may be in the form of parallel lines or may include a plurality of branches extending from the parallel lines.

At the end of the pattern unit 120, a plurality of agents for transmitting electrical signals from the terminal 200 to the pattern unit 120 and transmitting electrical signals generated from the pattern unit 120 to the terminal 200. One connection terminal 130 may be formed.

3. First connection terminal (130)

The first connection terminal 130 may be formed of a metal material to receive and transmit electrical signals. In addition, an even number of 2, 4, 6, etc. is formed and connected to the first pattern 121 and the second pattern 122, respectively. Two first connection terminals 130 are formed so that one first connection terminal 130 is connected to the first pattern 121 and the other first connection terminal 130 is connected to the second pattern 122. Connected.

In addition, the first connection terminal 130 may be detachably connected to the second connection terminal 210 formed in the terminal 200 to be described later.

A protrusion is formed in the first connection terminal 130 and a concave portion is formed in a position corresponding to the protrusion in the second connection terminal 210 so that the protrusion fits into the concave portion and is connected thereto. In addition, when the protruding portion is separated from the concave portion, the second connecting terminal 210 is removed from the first connecting terminal 130 . The first connection terminals 130 and the second connection terminals 210 have the same number, and are formed at corresponding positions so that the protrusions and the concave parts are aligned.

Conversely, a protrusion is formed in the second connection terminal 210 and a concave portion is formed in a position corresponding to the protrusion in the first connection terminal 130 so that the protrusion fits into the concave portion and can be connected. In addition, when the protruding portion is separated from the concave portion, the second connecting terminal 210 is removed from the first connecting terminal 130 .

Alternatively, the first connection terminal 130 and the second connection terminal 210 are formed of a metal material having magnetism, so that the first connection terminal 130 and the second connection terminal 210 interact with each other by magnetic force. may be connected.

The first connection terminal 130 and the second connection terminal 210 are formed of a metal material capable of transmitting and receiving electrical signals.

<Terminal 200>

The terminal 200 may be mounted on an outer surface of the waist belt 112 of the diaper.

The terminal 200 may include a second connection terminal 210, a battery 220, a determination unit 230, and a first communication unit 240.

The terminal 200 may be mounted under or above the belly button of the wearer. Preferably, it can be mounted below the navel to prevent wearing discomfort.

1. Second connection terminal (210)

As described above, the second connection terminal 210 is formed to be detachable from the first connection terminal 130 . The second connection terminals 210 are formed equal to the number of the first connection terminals 130, transmit a first electrical signal to the first connection terminals 130, and the first connection terminals 130 Receives a second electrical signal from

2. Battery (220)

The terminal 200 may contain a battery 220 providing driving power for managing urinary incontinence. The battery 220 may be disposable or used in both charging methods.

3. Judging unit 230

The determination unit 230 may generate an electricity generation signal for supplying an electrical signal to the pattern unit 120 and transmit it to the battery 220 . When the battery 220 receives the electricity generation signal, it can generate a preset first electrical signal and transmit it to the pattern part 120 .

The first electrical signal is transferred to the first connection terminal 130 via the second connection terminal 210 . The first electrical signal transmitted to the first connection terminal 130 is transmitted to the first pattern 121 part 120 .

When the urine collecting part is not stained with urine, the resistance value is high and the permittivity is small between the first pattern 121 part 120 and the second pattern 122 part 120, so that the first pattern 121 ) The first electrical signal transmitted to the unit 120 cannot be transmitted to the second pattern 122 unit 120.

Conversely, when the urine collection part is soiled with urine, the resistance value between the first pattern 121 part 120 and the second pattern 122 part 120 decreases and the permittivity increases, and the first pattern 121 part 120 decreases. The first electrical signal transmitted to the (121) unit 120 is transmitted to the second pattern 122 unit 120.

When receiving the first electrical signal, the second pattern 122 unit 120 outputs a second electrical signal and transfers it to the first connection terminal 130 . The second electrical signal transmitted to the first connection terminal 130 may be transmitted to the determination unit 230 via the second connection terminal 210 .

The determination unit 230 may determine that urine has occurred when the second electrical signal is received.

In addition, the determination unit 230 may generate a urine generation signal based on the second electrical signal, and transmit the urine generation signal and the second electrical signal to the communication unit.

4, Department of Communications

When the communication unit receives the urine generation signal from the determination unit 230, it may transmit the urine generation signal and the second electrical signal to the portable terminal or server 300.

<Server 300>

The server 300 according to an embodiment of the present invention includes an input unit 310, a big data unit 320, and a calculation unit 330.

The input unit 310 receives a urination start resistance value (Rs), a urination end resistance value (Re), a urination duration time (Rh), a total number of urinations per day (Utd), and 9:00 PM during the day from a plurality of terminals. The total number of urinations (Und) and the total urination time (W) in units of a week from 7:00 am to 7:00 am are received, and the values thus received are transmitted to the big data unit 320.

The big data unit 320 outputs, from the input unit 310, the urination start resistance value (Rs), the urination end resistance value (Re), the urination time (Rh), the total number of urinations per day (Utd), and the total number of urinations per day (Utd) per day. The number of urination (Und) and the urination time per week are received and input.

Here, the urination start resistance value (Rs), the urination end resistance value (Re), the duration of one urination (Rh), the total number of urinations during the day (Utd), and the 9:00 pm part of the day stored in the big data unit 320 The data of the total number of urination (Und) and the total urination time (W) in units of a week from 20:00 to 7:00 AM are referred to as urination-related data.

The calculation unit 330 extracts statistical characteristics and dysuria patterns for the urination-related data through equations to be described later. Each feature extracted in this way is provided as data for a machine learning algorithm for deriving the probability of dysuria.

(1) Statistical characteristics related to urinary incontinence

Among the urination-related data, the daily unit of urination start resistance value (Rs), urination end resistance value (Re), and one-time urination duration (Rh) are used. Statistical characteristics representing urinary incontinence use Equation (1).

(Re-Rs)/Rh = Cr1 Equation (1)

Here, Cr1 is the probability of occurrence of urinary incontinence, Re is the resistance to end urination, Rs is the resistance to start urination, and Rh is the duration of urination once.

6 shows the probability of occurrence of urinary incontinence according to Equation (1).

(2) Statistical characteristics related to enuresis

Among the urination-related data, the total number of urinations per day (Utd) and the total number of urinations from 9:00 PM to 7:00 AM (Und) are used. Statistical characteristics representing enuresis use Equation (2)

Und/Utd = Cr2 Equation (2)

Here, Cr2 is the probability of nocturnal enuresis, Und is the total number of urinations from 9:00 pm to 7:00 am during the day, and Utd is the total number of urinations during the day.

7 shows the probability of nocturnal enuresis according to Equation (2).

(3) oliguria-related statistical characteristics

Among the urination-related data, the total number of urinations per day (Utd) is used. The big data unit 320 receives the total number of times of urination (Utd) of a plurality of users for a day from a plurality of terminals. The calculation unit 330 receives the total number of times of urination (Utd) of a plurality of users during the day and calculates the average total number of times of urination (Utad) of all users during the day based on this.

Statistical characteristics related to oliguria are derived using Equation (3) based on the calculated average total number of urination (Utad) of all users during the day and the total number of urination (Utd) of all users during the day.

Utd/Utad = Cr3 Equation (3)

Here, Cr3 is the probability of occurrence of oliguria, Utd is the total number of urinations per day of users, and the average total number of urinations per day of all users of Utad.

8 shows the probability of occurrence of oliguria according to Equation (3).

(4) Statistical characteristics related to diaper dermatitis (IAD)

The calculation unit 330 calculates the incontinence duration on a daily basis based on the urination start resistance value (Rs), the urination end resistance value (Re), and the urination duration time (Rh). When the difference between the urination start resistance value (Rs) and the urination end resistance value (Re) is within a predetermined range, it is determined as incontinence, and the incontinence time per urination is calculated by calculating the urination start time and the urination end time. The total incontinence time calculated by accumulating the incontinence time per one time during the day is set as It. Also, the calculation unit 330 may calculate the total urination time calculated on a weekly basis. The total urination time per week calculated in this way is set as W.

Statistical characteristics related to diaper dermatitis (IAD) are derived using Equation (4) based on the total voiding time per week (W) and total incontinence time accumulated during the day (It).

It/W = Cr4 Equation (4)

9 shows the probability of occurrence of diaper dermatitis (IAD) according to Equation (4).

Here, Cr4 is the probability of occurrence of diaper dermatitis, It is the total incontinence time accumulated for one day, and W is the total urination time per week.

The server 300 may express dysuria and diaper dermatitis occurrence probability together. For example, the server 300 may be expressed as (incontinence 60%, IAD occurrence probability 45%), (oliguria 70%, IAD occurrence probability 57%), and the like.

The calculated probability of dysuria and diaper dermatitis occurring may be displayed on a display connected to the server 300 .

Claims (2)

A smart diaper that is filled between the user's legs, receives urine, and generates a second electrical signal during urination;
The first electrical signal is transmitted to the smart diaper, the second electrical signal is received from the smart diaper, a urine generation signal is generated based on the transmitted second electrical signal, and the generated urine generation signal and the transmission a terminal that transmits the second electrical signal to the server; and
Urination-related data from at least one terminal - the urination-related data includes a urination start resistance value (Rs), a urination end resistance value (Re), a urination duration per urination (Rh), the total number of urinations per day (Utd), a day including the total number of urination (Und) from 9:00 pm to 7:00 am and the total urination time (W) per week - received, including a server that determines dysuria or diaper dermatitis based on the urination-related data but
The server calculates the probability of occurrence of dysuria or diaper dermatitis by a machine learning algorithm, machine learning-based dysuria diagnosis and diaper dermatitis diagnosis system The method of claim 1, wherein the server
Calculate the probability of occurrence of urinary incontinence by the following equation (1),
The probability of enuresis occurring is calculated by the following equation (2),
The probability of occurrence of oliguria is calculated by the following equation (3),
A machine learning-based dysuria diagnosis and diaper dermatitis diagnosis system, characterized in that the probability of occurrence of oliguria is calculated by the following equation (4).
(Re-Rs)/Rh = Cr1 Equation (1)
(Where, Cr1 is the probability of occurrence of urinary incontinence, Re is the resistance to end urination, Rs is the resistance to start urination, and Rh is the duration of urination once)
Und/Utd = Cr2 Equation (2)
Here, Cr2 is the probability of nocturnal enuresis, Und is the total number of urinations from 9:00 pm to 7:00 am during the day, and Utd is the total number of urinations during the day)
Utd/Utad = Cr3 Equation (3)
(Where, Cr3 is the probability of occurrence of oliguria, the Utd is the total number of urinations per day of users, and the average total number of urinations per day of all users of Utad)
It/W = Cr4 Equation (4)
(Where, Cr4 is the probability of occurrence of diaper dermatitis, It is the total accumulated incontinence time for one day, and W is the total urination time per week)