WO2018030340A1

WO2018030340A1 - Care plan creation assistance system, storage medium, care plan creation assistance method, and care plan creation assistance program

Info

Publication number: WO2018030340A1
Application number: PCT/JP2017/028587
Authority: WO
Inventors: 茂雄岡本; 竜哉関根; 瑛子篠澤; 浜田　宏一
Original assignee: セントケア・ホールディング株式会社
Priority date: 2016-08-08
Filing date: 2017-08-07
Publication date: 2018-02-15
Also published as: JP7145261B2; CN109564780A; CN109564780B; JPWO2018030340A1; JP7004655B2; JP2021099867A

Abstract

This care plan creation assistance system comprises: a care plan output unit which, using a care plan output model, acquires for each care plan a probability with respect to an input of a care recipient's situation that a level of required care will improve, and outputs the care plan with the higher acquired probability; an assessment unit which assesses whether the level of required care has improved after care has been carried out upon the care recipient using the outputted care plan; a probability computation unit which, using the result of the assessment which has been performed by the assessment unit, computes anew the probability that the level of required care will be improved by the outputted care plan; and a process change unit which changes the care plan output assistance model such that the probability which is acquired for the care plan which has been outputted with respect to the input of the care recipient's situation approaches the computed probability. This care plan creation assistance system assists with the creation of a care plan by outputting, in accordance with each individual care recipient's situation, a care plan for which an improvement in a level of required care may be expected.

Description

Care plan creation support system, storage medium, care plan creation support method, and care plan creation support program

The present invention relates to a care plan creation support system, a storage medium, a care plan creation support method, and a care plan creation support program.

A care plan for a supporter who needs care or assistance from another person in daily life, including bathing, excretion, and meals, or a care recipient (hereinafter collectively referred to as “caregiver”) is called a care plan. The care plan includes a service plan schedule that defines specific contents of the care service and the date and time when the care service is provided.

The care plan is usually prepared by taking care benefits determined by the care manager according to the degree of care required that is certified based on the situation of the care recipient. When a person who wishes to receive certification for the degree of care required applies for certification for long-term care, the nursing care insurer who has received the application causes the authorized investigator of the accredited research organization to investigate the physical condition of the applicant. The survey is performed by selecting a preset item from two or more options that matches the applicant's situation, or inputting an item in text. This survey result is input to a computer or the like and used for primary determination of the degree of care required by a predetermined calculation method. The long-term care insurer causes the long-term care certification examination committee, which is the installation organization, to certify the applicant's degree of long-term care based on the above primary determination, other special instructions for the care recipient, and the opinion of the attending physician. Thus, the upper limit of the nursing care benefit to the care recipient is determined according to the degree of nursing care required.

After the upper limit of nursing care benefits is determined, the care manager creates a care plan suitable for the care recipient in consideration of the above nursing benefits. At this time, the care manager or the person entrusted with the care manager newly evaluates the condition of the care recipient at the time of preparing the care plan (hereinafter also simply referred to as “assessment”). Thereafter, the care manager creates the care plan based on the current status of the cared person (hereinafter, also simply referred to as “assessment result”).

Patent Documents 1 to 6 include assessments for the purpose of streamlining care plan creation and homogenizing care plans that are provided by suppressing the deterioration of the quality of care plans due to the ability of care managers. A method for supporting the creation of a care plan from the results and a system for implementing the method have been proposed.

By the way, the number of care recipients is increasing due to the recent declining birthrate and aging population. In addition, since there are very few cases where the degree of care required is improved by nursing, the number of care recipients with a high degree of care required is increasing as the number of care recipients increases. Some of the funds required for long-term care benefits are covered by long-term care benefit costs, which are a type of social security costs. However, the higher the degree of care required, the higher the long-term care benefit costs. Therefore, care benefit costs are increasing year by year due to an increase in the number of care recipients and an increase in the number of care recipients with a high degree of care required. For example, the population of so-called elderly people over the age of 65 in Japan is about 36.5 million (population of 3.3) in 2015, compared to about 34 million in 2015 (1 in 3.7). The number of nursing care benefits is expected to be 21 trillion yen in 2025, compared to 10.1 trillion yen in 2015.

Also, the increase in the number of care recipients and the increase in the number of care recipients that require a high degree of care will have a significant social impact. For example, problems such as so-called nursing care leave, which are forced to leave work for the care of close relatives, have also become apparent, and these problems can reduce the quality of life of care recipients and those involved in caregivers. Or reduce the workforce, which can cause social losses.

JP 11-149499 A Japanese Unexamined Patent Publication No. 2000-3404 JP 2000-3391 A JP 2001-101279 A JP 2006-146410 A JP 2010-205263 A

As mentioned above, the financial and social burdens are increasing due to the increase in the number of care recipients, and it is necessary to suppress these burdens. In particular, since the amount of nursing care benefits and the amount of social burden increase as the degree of care required increases, it is desirable to suppress an increase in the number of care recipients with a high degree of care required. However, an effective method for reducing the number of care recipients with high care needs has not yet been established.

For example, if the care plan is devised to improve the level of care recipients, the increase in the number of care recipients with high levels of care can be suppressed. However, there are only a few examples of care plans that have improved the level of care required, and even if these examples are applied to other care recipients in different situations, improvement of the level of care required is also expected. It is not always possible.

Also, in order to implement the above-mentioned care plan, it is thought that it is important to make care plans more efficient and to make the created care plans more uniform. On the other hand, Patent Documents 1 to 6 describe that the purpose of improving the efficiency of care plan creation and homogenization of the created care plan can be achieved by having the computer assist the creation of the care plan. (Hereinafter, a system that supports the creation of a care plan is also simply referred to as a “care plan creation support system.” The care plan creation support system is a system that can output information useful for the creation of a care plan by a care manager. Well, it may have only a function of outputting only the care service to be included in the care plan, or may have a function of simultaneously outputting a service plan schedule defining the date and time for providing the care service. . However, these documents do not consider the creation of a care plan that can improve the degree of care required.

The present invention has been made in view of the above-mentioned problems, and by generating a recommended care plan that can be expected to improve the degree of care required according to the situation of each individual care recipient, creation of a care plan The purpose is to provide a care plan creation support system capable of supporting the above. The present invention also provides a storage medium that can be used in the system, a care plan creation support method that can be implemented using the system, and a care plan creation support program that can execute the method. And its purpose.

One embodiment of the present invention for solving the above problem is that a care receiver uses a care plan output model that outputs, for each care plan, the probability that the degree of care required improves with respect to the input of the status of the care recipient. For each care plan, a probability that the degree of care required of the care recipient is improved is input for each care plan, and a care plan with a higher probability is output as a recommended care plan. A care plan output unit; a determination unit that determines whether or not the degree of care required of the cared person after the cared person has been cared for using the output care plan; and the determination Using the result of the determination by the unit, a probability calculation unit for newly calculating a probability that the degree of care required of the cared person is improved when care is performed according to the output care plan and the situation of the cared person Said output care for input Probability of being acquired for orchids, closer to the calculated probability, and the process-changing section for changing the care plan output assistance model relates care plan creation support system comprising a.

Another embodiment of the present invention for solving the above-described problem is a storage medium connectable to the care plan creation support system, the information for identifying the care recipient, the subject of the care recipient. The situation of the caregiver, the care plan used for the cared person, and the degree of care required of the cared person after the care is performed using the care plan, or the care is performed using the care plan. The present invention relates to a storage medium for storing a record associated with a change in the degree of care required as a result of the change.

In addition, another embodiment of the present invention for solving the above-described problems uses a care plan output model that outputs, for each care plan, the probability that the degree of care required improves with respect to the input of the situation of the care recipient. A care plan in which the probability of improvement in the degree of care required of the care receiver is obtained for each care plan with respect to the input of the care recipient status of the care recipient, and a care plan with a higher probability of acquisition is recommended. Using the results of the determination, the step of outputting as, the step of determining whether or not the degree of care required of the care receiver after providing the output care plan to the care receiver has improved, The step of newly calculating the probability that the degree of care required of the cared person will be improved by providing the output care plan and the probability of obtaining the output care plan for the input of the status of the cared person , The calculated accuracy So as to approach, the step of changing the care plan output assistance model relates care plan preparation supporting method comprising.

Further, another embodiment of the present invention for solving the above-described problem is a care plan output model for outputting, for each care plan, the probability that the degree of care required improves with respect to the input of the status of the care recipient. For each care plan, the probability of improvement in the degree of care required of the care recipient is obtained for each care plan with respect to the input of the care recipient status of the care recipient, and a care plan with a higher probability of acquisition is recommended. A process of outputting as a care plan to be performed, a process of determining whether or not the degree of care required of the care receiver after providing the output care plan to the care receiver has improved, and a result of the determination A process for newly calculating a probability that the degree of care required of the care recipient is improved by providing the output care plan, and the output care plan in response to the input of the situation of the care recipient Acquired Rate is closer to the calculated probability, and the process for changing the care plan output assistance model relates care plan creation support program for execution.

The present invention provides a care plan creation support system that can support the creation of a care plan by outputting a recommended care plan that can be expected to improve the degree of care required according to the situation of each individual care recipient. Is done. The present invention also provides a storage medium that can be used in the system, a care plan creation support method that can be implemented using the system, and a care plan creation support program that can execute the method. The

FIG. 1 is a block diagram showing an example of the configuration of a care plan creation support system according to an embodiment of the present invention. FIG. 2 is a flowchart illustrating an example of processing by the care plan creation support system. FIG. 3 is a flowchart showing specific processing included in the care plan output (step S100). FIG. 4 is a schematic diagram illustrating the configuration of the intermediate unit according to the first embodiment. FIG. 5 is a flowchart showing specific processes included in the learning process (step S200). FIG. 6 is a flowchart showing the configuration of a care plan creation support system according to another embodiment of the present invention. FIG. 7 is a block diagram showing a configuration of a care plan creation support system according to still another embodiment of the present invention. FIG. 8 is a block diagram showing a configuration of a care plan creation support system according to still another embodiment of the present invention.

[First Embodiment]
FIG. 1 is a block diagram illustrating an example of a configuration of a care plan creation support system 100 according to an embodiment of the present invention. The care plan creation support system 100 according to the present embodiment includes a care plan output unit 110 that functions as a processing unit, a determination unit 120, a probability calculation unit 130, a process change unit 140, a storage unit 150 that functions as a storage medium, and a display. Unit 160 and an input unit 170.

Although not shown, the care plan creation support system 100 includes, for example, a CPU (Central Processing Unit) as a processor, a storage medium such as a ROM (Read Only Memory) storing a control program, and a RAM (Random Access Memory). A working memory and a communication circuit are provided. In this case, the function of each processing unit described above is realized by the CPU executing a control program (corresponding to the “care plan creation support program” of the present invention). At least a part of a program for executing processing by the care plan output unit, the determination unit, the probability calculation unit, and the processing change unit is stored in a server, but as in a fourth embodiment to be described later At least a part of the program may be stored in a cloud server.

When the care plan output unit 110 provides care to the cared person using a preset care plan (hereinafter also simply referred to as “provided the care plan”), the degree of care required of the cared person is determined. It is a processing unit that acquires the improvement probability for each care plan set in advance and outputs the care plan having the higher acquired probability as a recommended care plan. For example, the care plan output unit 110 inputs the care recipient status of the care recipient to a probabilistic inference model (hereinafter simply referred to as “care plan output support model”), so that care is set in advance. A probability that the degree of care required of the care receiver is improved when the plan is provided is acquired. Note that the probabilistic inference model is an inference value (in this embodiment, the degree of care required is improved in this embodiment) by performing a predetermined operation on the input value. This is an inference model that outputs a probability of Thereafter, the care plan output unit 110 refers to the probability that the degree of care required that is output for each care plan is improved, for example, by selecting a care plan that has a higher probability that the degree of care required improves, It is a processing unit that outputs a care plan recommended for the care recipient.

The determination unit 120 is a processing unit that determines whether the current level of care required of the care recipient has improved over the previous level of care required of the care recipient. For example, the determination unit 120 determines whether or not the care-required level of the cared person has improved after the cared person has been cared for using the care plan output from the care plan output unit 110. Note that the determination unit 120 may determine whether or not the care-required level of the cared person has improved after the cared person has been cared for using a care plan created separately by the care manager.

The probability calculation unit 130 uses the result of determination by the determination unit 120 to receive a caregiver when care is performed according to the preset care plan (in particular, the care plan output by the care plan output 110). It is a processing part which newly calculates the probability that the degree of care required will improve. For example, the probability calculation unit 130 includes the total number of records having the same care plan and the care plan used for care among the records stored in the storage unit 150, and the degree of care required included in the record. The number of records determined to be improved is calculated, the ratio of the number of records determined to have improved the degree of care required to the total number of records is calculated, and the calculated ratio It is assumed that the degree of care required of the person will improve.

The process change unit 140 includes a care plan created from the past situation of the care recipient and the past situation of the care recipient and provided to the care recipient in the past, and a result of determination by the determination unit 120. Is a processing unit that changes the care plan output support model using the combination of and as teacher data. Specifically, the processing change unit 140 has a combination of the situation of the care recipient and the care plan that has the same probability of being acquired for a care plan when the care recipient status is input to the care plan output unit 110. The care plan output support model is changed so as to approach the probability calculated by the probability calculation unit 130.

Details of processing by these processing units will be described later.

The care plan creation support system 100 is characterized in that the care plan output support model is changed by a learning process. According to the learning process, it is possible to change the care plan output support model so that features included in past data can be mechanically extracted and similar results are output for inputs having similar features. It is. Therefore, it is determined whether the degree of care required has improved for each care plan provided for the situation of a care recipient, and these data (care recipient status, care plan, and each care plan The care plan output support model is changed so that a care plan with a high probability of improving the degree of care required can be output even in situations with similar characteristics by performing the learning process using the above determination result) it can. As a result, the care plan creation support system 100 has a higher probability that even after individual caregivers having various situations will improve after the care is required according to the characteristics of the situation of the care recipient. Can be output as a recommended care plan. In addition, by preparing a large number of such data and repeating the above learning process, the accuracy of outputting a care plan with a higher probability of improving the degree of care required for the situation of any care recipient will increase. .

The storage unit 150 is a storage medium that can be written and read.

The storage unit 150 can be a storage medium such as a database. In the storage unit 150, care recipient information, date or date and time, the situation of the care recipient, a care plan, the degree of care required of the care recipient, and care required after care has been performed using the care plan. A record in which the degree or change in the degree of care required as a result of providing the care plan is associated is stored. A unique record number may be given to the record.

The above date or date is the date or date when the care recipient was assessed.

The care recipient information is information for uniquely identifying a care recipient who can receive care, and may include an ID number unique to the care recipient, the name, gender and date of birth of the care recipient. .

The situation of the care recipient can be the assessment result obtained by the care manager or the person entrusted with the care to the care recipient. Moreover, as the situation of the care recipient, the contents described in the doctor's opinion such as the survey result on the service usage status, the survey result on the special notes, the disease name, etc. may be used.

The care plan is a care plan prepared by the care manager based on the situation of the care recipient and provided to the care recipient.

The degree of care required of the care recipient is the degree of care required of the care recipient certified by the Care Certification Committee when the care plan was created.

The degree of long-term care required after care has been performed using the above care plan is that the care recipient needs to be re-certified by the Care Certification Committee after providing the care plan to the same care recipient. Degree.

The change in the degree of care required is data that can be tabulated and is determined by determination by the determination unit 120. For example, “1” is recorded for a record that includes a care plan that is determined to have improved the degree of care required, and “0” is stored for a record that includes a care plan that has not been improved for the level of care required. Is granted.

The storage unit 150 stores in advance the number of records that can be calculated by the probability calculation unit 130 at the time of initial setting.

The display unit 160 is a display device such as a smartphone, a PC, or a TV carried by the care manager, and displays a recommended care plan according to a display control signal input from the care plan output unit 110. The display unit 160 can be used by the care manager who has viewed the displayed care plan to create a care plan provided to the care recipient.

The input unit 170 includes various operation keys such as a numeric keypad and a start key, an audio reception unit, or a video reception unit such as a camera, receives various input operations by a user, generates input data, and generates the generated input Data is output to the care plan output unit 110 and the determination unit 120. The input unit 170 is a variety of signal receiving devices configured to receive input data electrically output from other media such as a reception connector and output the input data to the care plan output unit 110 and the determination unit 120. May be. The input data output from the input unit 170 is output to the care plan output unit 110 to be used for the output of the care plan, and is also output to the determination unit 120 for output of the care plan by the probability calculation unit 130 and the processing change unit 140. Used to change support model.

FIG. 2 is a flowchart showing an example of processing by the care plan creation support system 100. The care plan creation support system 100 receives data related to the situation of the care recipient and outputs a recommended care plan for the care recipient based on a predetermined probabilistic inference model (step S100). Then, the care plan creation support system 100 performs a learning process for changing the probabilistic reasoning model so that a care plan with a higher probability of improving the degree of care required of the care recipient can be output (step S200).

FIG. 2 shows a mode in which the learning process (step S200) is performed after the care plan output (step S100), but the care plan output (step S100) is performed after the learning process (step S200). Alternatively, the care plan output (step S100) and the learning process (step S200) may be performed simultaneously in parallel.

Hereinafter, input data used for processing by the care plan creation support system 100 will be described, and then more specific processing included in care plan output (step S100) and learning processing (step S200) will be described.

(Input data)
The input data is information related to the assessment performed on the cared person in order to create a new care plan. The information on the cared person, the date or date of the assessment performed on the cared person, the cared person And the degree of care required of the care recipient at the date or date of the assessment. The care receiver information included in the input data and the care receiver information stored in the storage unit 150 are preferably composed of only the same items, but the determination unit 120 can determine the same care recipient. As long as there are some, only some items may overlap.

The situation of the care recipient is the one that best suits the situation of the care recipient from two or more choices of "Yes (Y)" or "No (N)" for multiple survey items. Can be the result of selecting. The types of the plurality of survey items and options are not particularly limited, and can be arbitrarily determined. For example, survey items and options defined for use in certification of the degree of care required can be used. The survey for accreditation of the degree of care required includes general surveys and basic surveys, either or both of which may be used, and basic survey items and options (74 items as of July 2015) You may use only. At this time, when the certification standard for the degree of care required is changed, it is preferable that the survey items and options can be changed accordingly. In addition, as for the situation of the care recipient, the contents of the result of the general survey and the opinion of the attending physician may be input as text.

For example, the survey items used to determine the level of care required as of July 2015 include “paralysis of left upper limb (selection from“ Yes ”and“ No ”)” and “turn over (“ Do not grab ”),“ Items related to the caregiver's physical function / living behavior, such as “Can be grasped by something” and “Cannot do”), “Movement (“ Not assisted ”,“ Need to watch, ”etc.),“ One Items related to the caregiver's life function, such as “Departmental assistance is required” and “All assistance is required”), “Communication of intention” (“Study subject can communicate intention to others”, “Occasionally The choice of “can communicate”, “can hardly communicate” and “can't communicate”) and “speak birth date and age (selection from“ capable ”and“ impossible ”) Items involved, “Stolen things etc. Items related to mental / behavioral disorders of care recipients, such as “become damaging (choose from“ No ”,“ Occasionally ”and“ Yes ”),“ Management of money (“Unreleased”, “One” Select from “partially released” and “all released”) or “daily decision-making” (“can be done in special cases”), “can be done except in special cases”, “daily” Related to adaptation to social life, such as “selection from“ difficult ”and“ impossible ”), and medical treatment received in the past 14 days, such as“ dialysis (selection from “with” and “without”) It consists of 74 items such as items. These items may be used as they are, or some items may be selected and used, and other items may be arbitrarily registered and used.

It should be noted that the number of items in the situation of the care recipient can be 5 or more and 20 or less, and further 5 or more and 15 or less from the viewpoint of saving the input effort. The situation of the cared person at this time is preferably composed of survey items used during the evaluation (monitoring) of the daily life action (ADL) and the instrumental daily life action (IADL) performed on the cared person. As the survey items used in the evaluation of the ADL, the evaluation items used in the evaluation methods such as the Barcel index, the performance status defined by the Eastern Cooperative Oncology Group (ECOG), and the functional independence evaluation table (FIM) should be used. Can do.

(Step S100: Output of care plan)
In the output of the care plan (step S100), the care plan output unit 110 inputs the input status of the care recipient into the care plan output support model, and acquires the probability that the degree of care required improves for each care plan. To do. Thereafter, the care plan output unit 110 outputs a care plan recommended to the care recipient from the probability that the degree of care required output for each care plan is improved, and displays the care plan on the display unit 160.

The above care plan includes at least nursing care services. The care service is a specific content of the care service provided to the care recipient. The care service may be selected from those that can be provided by a care provider. The care plan may include a service plan schedule that defines the date and time for providing the care service in addition to the specific content of the care service.

FIG. 3 is a flowchart showing specific processing included in the care plan output (step S100).

First, the care plan output unit 110 inputs the status of the care recipient into the care plan output support model, and acquires the probability that the degree of care required improves for each care plan (step S310). Thereafter, the care plan output unit 110 outputs one or a plurality of care plans that have a high probability of improving the degree of care required as recommended care plans (step S320). For example, the care plan output unit 110 outputs a care plan with a high output probability (for example, a care plan with the highest probability or a care plan corresponding to the 10th output unit with the probability) as a recommended care plan. To do.

Thereafter, the care plan output unit 110 outputs the output care plan as a display control signal to the display unit 160, and displays the care plan on the display unit 160 (step S330). At this time, when the care plan is changed as in a third embodiment to be described later, the process returns to step S310, and the care plan output unit 110 causes the display unit 160 to display the modified care plan.

Finally, the care plan output unit 110 newly records in the storage unit 150 the care receiver information, date or date / time, the care receiver status and the level of care required, and the output or changed care plan included in the input data. (Step S340).

The care plan output support model described above is a probabilistic inference model that outputs a predetermined inference value for each type of care plan set in advance with respect to the input of the status of the care recipient. It is configured to be changeable. The inference value is a probability that the degree of care required of the cared person is improved when each care plan is provided to the cared person having the input status. The care plan output support model includes, for example, a neural network, a Boltzmann machine, and a decision tree.

Hereinafter, the configuration of the care plan output support model when the care plan output support model includes a neural network will be exemplified.

The neural network (hereinafter also simply referred to as “plan output network”) includes an input layer composed of a plurality of input units, one or a plurality of intermediate layers each composed of a plurality of intermediate units, and an output composed of a plurality of output units. Has a layer. The plan output network is a multi-layer neural network having N layers having a plurality of intermediate layers from the input layer side to the output layer side, and the intermediate unit of each intermediate layer is the middle of the previous layer. Information received from one or more intermediate units (or input units) included in the layer is output to one or more intermediate units (or output units) included in the intermediate layer of the next layer. The number (N) of layers included in the plan output network may be three or more, and can be arbitrarily determined according to the number of assessment items. For example, the number (N) of the layers may be 3 or more and 25 or less, preferably 5 or more and 20 or less, and more preferably 8 or more and 16 or less.

The input layer (N = 1) has the same number of the input units as the survey items included in the situation of the care recipient. The input unit corresponds to one of the plurality of survey items and outputs an input value corresponding to each option of the survey item as it is to one or a plurality of intermediate units.

The intermediate layers (N = k (1 <k <N)) each have an arbitrary number of the intermediate units. The intermediate unit receives an output from one or a plurality of intermediate units (or one or a plurality of input units included in the input layer) of the intermediate layer of the previous layer, and receives any or a plurality of the intermediate layers of the next layer Output to the intermediate unit (or the output unit of the output layer). The intermediate layer may be a fully connected layer in which the intermediate unit included in the intermediate layer is combined with all the intermediate units (or input units) in the previous layer, or the intermediate unit included in the intermediate layer is the intermediate unit in the previous layer. It may be a convolutional layer that combines only with a part of (or the input unit).

At this time, as shown in FIG. 4, the intermediate unit Z in the k-th layer receives the outputs w1, w2, w3, and w4 from the intermediate unit (four in the figure) in the k-1th layer. Thereafter, as shown in the equation (1), the intermediate unit Z obtains a value u1 obtained by further adding a predetermined bias b to a sum of values obtained by multiplying each output by a predetermined weight y1, y2, y3, and y4. calculate. Note that the weight and bias can be changed by the process changing unit 140.
u1 = w1 * y1 + w2 * y2 + w3 * y3 + w4 * y4 + b (1)

The intermediate unit further outputs a value z1 obtained by applying a predetermined activation function f to u1 to the intermediate unit (or output unit) of the (k + 1) th layer. The type of the activation function f is not particularly limited, and a sigmoid function, a logistic function, a normalized linear function (Rectified Linear Unit: ReLU), a softmax function, and the like can be used. Among these, the activation function f of the intermediate unit is preferably ReLu from the viewpoint of increasing the output accuracy and increasing the processing speed.

The output layer (N = N) has the same number of output units as the number of preset care plans that can be output. Each output unit receives the output from one or a plurality of (N-1) th intermediate units, and the value obtained by performing the same processing as that of the intermediate unit is the value of the cared person input to the input layer. Output as an inference value for the situation (probability of improving the degree of care required). At this time, the activation function f of the output unit has a sum of inference values output from all the output units of 1, and the output inference values can be used as they are in a probability distribution. Function is preferred.

At this time, each of the output units is associated with a care plan that can be output by a preset care plan output unit 110 on a one-to-one basis. Then, the inference value output by each of the output units is regarded as a probability that the degree of care required of the cared person having the above situation is improved when each care plan is provided. Therefore, the care plan output unit 110 can select and output a care plan corresponding to an output unit having a larger inference value as a care plan recommended for a care recipient having the above situation.

The weights and biases of each unit in the intermediate layer and output layer are set as teacher data based on a combination of a past care recipient status and a care plan selected by the care manager for the care recipient at the time of initial setting. It is preferable to set in advance by a learning process by the process changing unit 140.

(Step S200: Learning process)
In the learning process (step S200), the determination unit 120, the probability calculation unit 130, and the process change unit 140 change the above-described care plan output support model through the learning process. Specifically, the determination unit 120 determines whether or not the degree of care required included in the input data has improved from the past degree of care required of the same care recipient registered in the storage unit 150. Thereafter, the probability calculation unit 130 determines, for any combination of the care recipient status and the care plan included in the storage unit 150, from the determination result, to the care recipient having the care recipient status that constitutes the combination. On the other hand, the probability that the degree of care required improves when the care plan is provided is calculated. Thereafter, the process changing unit 140 changes the care plan output support model using the situation and care plan of the cared person constituting the combination and the probability that the degree of care required for the combination is improved as teacher data. For example, when the process changer 140 inputs the care recipient status to the neural network, the inference value output from each output unit provides a care plan corresponding to the output unit. The weight and bias values of each intermediate unit and output unit are changed so as to approach the value calculated as the probability that the degree of care improves.

In addition, the past care-required degree, the past care recipient status and the past care plan, which will be described later, are the date or date of the input data among the records of the same care recipient registered in the storage unit 150. The degree of care required, the status of the care recipient, and the care plan included in the record at the time of going back to the past for a predetermined period from Specifically, it is included in a record in which the date or date registered in the assessment date or date included in the record is a point in time that is a predetermined period after the assessment date or date included in the input data. The items are the above-mentioned degree of care required, the past care plan, and the past care recipient status. The predetermined period can be a period from the creation of a care plan to the re-creation of a care plan, for example, six months.

FIG. 5 is a flowchart showing specific processing included in the learning processing (step S200). The determination unit 120 compares the care receiver information included in the input data with the care receiver information registered in the storage unit 150, and the record of the care receiver same as the input data is registered in the storage unit 150. It is determined whether or not (step S510).

As a result of the determination, when records of the same cared person are registered (step S510: YES), the determination unit 120 performs the above after care is performed using a past care plan for the cared person. A change in the degree of care required of the care recipient (whether or not the degree of care required has been improved) is evaluated (step S520). Specifically, the determination unit 120 is included in the care recipient's degree of care required (current care requirement level) included in the input data and in the past records of the same care recipient registered in the storage unit 150. It is determined whether or not the current level of care required has improved (becomes lower) than the past level of need for care. In addition, when the record of the same care receiver is not registered (step S510: NO), the input data cannot be used for the learning process, so the process in FIG. 5 ends.

As of July 2016, the level of long-term care required in Japan consists of 7 levels: Need 1 Need, Need 2 Need 1, Need 1 Need 2, Need 3 Need 4, Need 4 Need 5 and Need 5, Need For Care The degree of care required is low, and the latter is judged to be high. Therefore, when the degree of care required shifts from the latter classification to the former classification, for example, the degree of care required in the past for a care recipient is “care required 3”, but the degree of care required included in the input data is “required care required”. When it is “care 2”, it is determined that the degree of care required of the care recipient has improved.

This determination result is based on the item “change in the degree of care required” in the record of the same care recipient included in the storage unit 150 and including the past care recipient status and the past care plan used for the evaluation. Is registered as a value of “” (step S530).

Thereafter, the probability calculation unit 130 counts the number of records in which the value of the item “change in the degree of care required” is newly registered in the storage unit 150 (step S540). As a result, when it is determined that a predetermined number or more of data has been newly registered (step S540: YES), the probability calculation unit 130 obtains a probability that the degree of care required of the care recipient is improved (step S550). For example, the probability calculation unit 130 includes the total number of records having the same care plan and the care plan used for care among the records stored in the storage medium 150, and the degree of care required included in the record. The number of records determined to have improved is obtained, and the ratio of the number of records determined to have improved the degree of care required to the total number of records is calculated. If it is not determined that a predetermined number or more of data has been newly registered (step S540: NO), the processing in FIG. 5 ends.

Thereafter, the process changing unit 140 performs a learning process to change the care plan output support model (step S560).

For example, the processing change unit 140 may cause the inference value output from the output unit corresponding to the care plan to be the obtained ratio when the care receiver status is input to the above-described plan output network. , Change the above plan output network.

Specifically, the process changing unit 140 obtains a difference (error) between the inferred value output by the plan output network when the care recipient status is input and the calculated ratio. Next, the process changing unit 140 reduces the weights and biases of any of the intermediate units and output units of the plan output network (in the above-described example of FIG. 4, y1, y2, y3) so that the error is reduced. , Y4 and b) change one or more values.

The method of changing the evaluation network and the plan output network is not particularly limited, and a known method such as a gradient descent method using an error back propagation method can be used. In addition, the type of error function used to represent the error in the gradient descent method is not particularly limited, and publicly known expressions such as a square error and a cross entropy expression can be used.

With such a configuration, the care plan output by the care plan output unit 110 through the process including the execution of the care plan output support model including the plan output network has a high probability that the degree of care required of the care recipient is improved. It will be a thing. In particular, by inputting a large number of input data and performing a large number of learning processes, the above-described combination having a high probability of improving the degree of care required is configured for a cared person having any cared person's situation. A care plan can be selected and provided to the care recipient.

Also, by making the computer support the creation of the care plan, the purpose of improving the efficiency of the care plan creation and homogenizing the created care plan can be achieved.

One of the factors that hindered the improvement of the quality of the created care plan in the conventional care plan creation method is whether there is liveliness of the care recipient who was provided with the care plan included in the care plan. It is mentioned that the quality of selection of the care plan was evaluated based on the judgment criteria that are easily changed depending on the subjectivity of the observer. On the other hand, if the care plan is evaluated according to an evaluation criterion that can objectively determine whether or not the degree of care required is improved, the subjectivity of the observer that affects the evaluation of the care plan can be eliminated as much as possible. .

In addition, when the care plan output support model is configured to include a multi-layer neural network as in this embodiment, when a specific care plan is provided among the survey items included in the status of the care recipient input The care plan output support model can be changed so that the probability that the specific care plan is output will be higher when an item having a characteristic that the degree of care required is likely to be improved is input. . Therefore, even when a situation of a similar cared person having a survey item having the above characteristics is input, since the specific care plan is output with high probability, the care plan output unit 110 is not included in the teacher data. It is possible to output a care plan with a high probability that the degree of care required will improve even for the situation of a care recipient (or the number of data is small).

[Second Embodiment]
FIG. 6 is a flowchart showing a specific process included in the learning process (step S200) in another embodiment of the present invention. This embodiment is different from the first embodiment in that a care plan evaluation model which is a probabilistic inference model different from the care plan output support model is used for changing the care plan output support model by the learning process. Since other processes and the system configuration are the same as those in the first embodiment, a duplicate description is omitted.

The care plan evaluation model is a probabilistic inference model that outputs the probability of improvement in the level of care required by the implementation of the care plan for the input of the combination of the situation of the care recipient and the care plan, and is changed by the learning process It is configured to be possible. The care plan evaluation model includes, for example, a neural network, a Boltzmann machine, and a decision tree.

Hereinafter, the configuration in the case where the care plan evaluation model includes a neural network (hereinafter also simply referred to as “evaluation network”) will be exemplified. At this time, the care plan evaluation model has an input layer composed of a plurality of input units, one or a plurality of intermediate layers each composed of a plurality of intermediate units, and an output layer composed of one output unit. The evaluation network is a multi-layer neural network having N layers having a plurality of intermediate layers from the input layer side to the output layer side, and each intermediate layer has an intermediate unit of the previous layer. The information received from one or more intermediate units (or input units) included in is output to one or more intermediate units (or output units) included in the next intermediate layer. The number (N) of layers that the evaluation network has may be three or more, and can be arbitrarily determined according to the number of combinations of the situation of the care recipient and the care plan. For example, the number (N) of the layers may be 3 or more and 25 or less, preferably 5 or more and 20 or less, and more preferably 8 or more and 16 or less.

The evaluation network, except that the input items to the input layer are a combination of the situation of the care recipient and the care plan, and the inference value output from the output layer is the probability that the degree of care required will improve for the above combination, It can be set as the structure similar to the plan output network mentioned above.

At this time, the probability calculation unit 130 determines that a sufficient amount of data has been newly registered in the storage unit 150 in step S540 described above (step S540: YES), and then records among the records stored in the storage medium 150. , Find the total number of records with the same care plan and care plan used for care, and the number of records included in the above records that have been determined that the level of care required has been improved. Then, the ratio of the number of records determined that the degree of care required has been improved is calculated (step S550). Thereafter, the process changing unit 140 changes the evaluation network so that the ratio is output when the combination is input to the care plan evaluation model (step S570).

Specifically, the process change unit 140 obtains a difference (error) between the probability that the degree of care required output by the evaluation network improves when the combination is input and the calculated ratio. Next, the process changing unit 140 changes one or more values of the weight and bias of each of the intermediate units and output units of the evaluation network so that the error is reduced.

Thereafter, the processing change unit 140 performs the same processing as in the first embodiment, and the inference value output by each output unit when the situation of the care recipient is input to the plan output network is the situation of the care recipient. Then, the plan output network is changed so that the degree of care required output from the evaluation network is improved when the combination with the care plan corresponding to the output unit is input (step S560-2).

With this configuration, the probability that the degree of care required with higher accuracy than the “ratio of records with improved degree of care required” in Embodiment 1 is the target output when changing the care plan output support model Can be used as a value. Therefore, it is possible to make the recommended care plan output from the care plan output support model more likely to improve the degree of care required.

Note that, with such a configuration, it is possible to predict the prognosis of the care recipient using only the output from the evaluation network.

[Third Embodiment]
FIG. 7 is a block diagram showing a configuration of a care plan creation support system according to still another embodiment of the present invention. The care plan creation support system 700 according to the present embodiment includes a care plan change unit 710 that changes the care plan displayed on the display unit 160.

The care plan changing unit 710 includes various operation keys such as a numeric keypad and a start key, an audio receiving unit, or a video receiving unit such as a camera, and accepts various input operations by the care manager for changing the output care plan. The generated input data is transmitted to the care plan output unit 110. The care plan output unit 110 receives input data and changes the output care plan. 7 shows an example in which the care plan changing unit 710 is configured separately from the display unit 160. For example, the display unit 160 is configured such that the operation part is integrally formed on the display screen, such as a touch panel. Or may be configured to be connected to a hard key such as a button or a key and function as the care plan changing unit 710 at the same time.

The changed care plan is registered in the storage unit 150 in the same manner as in the first embodiment and the second embodiment.

At the same time, the display unit 160 may be connected to a care provider's server and display information such as availability of the care service included in the output care plan and availability information. With such a configuration, the care manager can change the care plan from the display unit 160 when it is determined that reservation of the displayed care service cannot be made.

Further, the care plan changing unit 710 may be configured to connect to a care provider's server and to arrange care service by input from the touch panel or the hard key.

[Fourth Embodiment]
FIG. 8 is a block diagram showing a configuration of a care plan creation support system according to still another embodiment of the present invention. The care plan creation support system 800 according to the present embodiment includes a cloud server 810 that is a virtualization server that cooperates with various devices via the Internet. The cloud server 810 includes a program for executing processing by the care plan output unit 110, the determination unit 120, the probability calculation unit 130, and the process change unit 140 described above, and data stored in a storage medium such as the storage unit 150, and the like. A part or all of is saved.

The cloud server 810 is owned, managed, and operated by a management company that operates a nursing care business or a contractor that is commissioned by the management company (hereinafter also simply referred to as “management company etc. 830”). The operating company or the like 830 accesses the cloud server 810 from one or more processing units 835 such as a PC that can be connected to the cloud server 810, and causes the processing unit 835 to execute the above-described processing.

At this time, the input unit 170 may be a device (for example, a smartphone, a PC, a TV, or the like) that can be connected to the Internet held by a group 820 such as an assessment operator who performs an assessment of the care recipient. Input data input from the device as the input unit 170 is transmitted from the device to the cloud server 810. At this time, it is preferable that the input unit 170 is configured to automatically delete personal information such as the name, date of birth, and status of the care receiver after transmission.

At this time, the display unit 160 may be a device (for example, a smartphone, a PC, a TV, or the like) that can be connected to the Internet held by the group 840 such as a care manager who creates a care plan. The care plan output by the care plan output unit 110 is transmitted to the device as the display unit 160 and displayed. When the group 840 corrects the care plan from the display unit 160, the corrected data is transmitted to the cloud server 810.

Note that the group 820 and the group 840 may be the same company or individual.

Note that each of the above-described embodiments is merely an example of implementation in carrying out the present invention, and the technical scope of the present invention should not be construed in a limited manner. That is, the present invention can be implemented in various forms without departing from the gist or the main features thereof.

For example, in each of the above-described embodiments, data with a change in the level of care required by one step and data with a change in two or more levels are similarly treated as data with an improved level of care required. The degree of improvement may be weighted according to how many times the degree of care has been improved and used in the learning process.

In the above embodiments, the storage unit 150 is described as a component incorporated in the care plan creation support system. However, the storage unit 150 is configured independently of the care plan creation support system, and the care plan creation support system is configured. May be configured to be able to refer to data for performing each of the processes described above. Also at this time, in the fourth embodiment, the storage unit 150 may be stored in a cloud server.

Further, in each of the above embodiments, the determination result by the determination unit 120 is registered in the storage unit 150, and the probability calculation unit 130 newly calculates the probability that the degree of care required improves using the registered determination result. However, the degree of care required in the past and the degree of care required included in the input data are registered in the storage unit 150, and the determination unit 120 compares the above two levels of care required registered in the storage unit 150 and You may determine the change of a nursing care degree. Also at this time, a change in the degree of care required as a result of care being performed using the care plan may be separately registered in the storage unit 150.

In the third embodiment, a plurality of care plans are output as recommended care plans from the care plan output unit 110, and one care plan selected by the care manager is input from the care plan change unit 710. The care plan selected and input may be registered in the storage unit 150.

In each of the above-described embodiments, the display unit 160 is described as a smartphone or tablet PC that can be carried by the care manager. However, the care manager is displayed on the screen as a desktop PC or the like provided in an office or the like. A care plan may be created while checking the care plan. Note that the output unit 160 may not only display the care plan on the screen, but may also be a mode in which the care plan is read out as speech.

This application claims priority based on Japanese Patent Application No. 2016-155859 filed on August 8, 2016, and the contents described in the claims, specification and drawings of this application are Incorporated into the application.

According to the care plan creation support system of the present invention, it is possible to output a care plan having a high probability of improving the degree of care required according to the situation of each individual care recipient, and to improve the output accuracy by learning processing. be able to. Therefore, if the care plan produced using the care plan creation support system of the present invention is provided to the care recipient, an improvement in the degree of care required of the care recipient can be expected. If the level of care required of the cared person is improved, it is expected that the care benefit cost will be reduced and the turnover of the caregiver will be reduced, and the financial and social burden due to the increase in the cared person can be expected.

100, 700, 800 Care plan creation support system 110 Care plan output unit 120 Judgment unit 130 Probability calculation unit 140 Processing change unit 150 Storage unit 160 Display unit 170 Input unit 710 Care plan change unit 810 Cloud server 820 Group 830 Operating company etc. 835 Processing Unit 840 Group

Claims

Using the care plan output model that outputs, for each care plan, the probability that the degree of care required improves with respect to the input of the status of the care recipient, the degree of care required of the care recipient for the input of the status of the care recipient A care plan output unit that obtains a probability of improvement for each care plan, and outputs the care plan with the higher probability acquired as a recommended care plan;
A determination unit that determines whether or not the degree of care required of the cared person after the cared person has been cared for using the output care plan; and
Using the result of determination by the determination unit, a probability calculation unit that newly calculates a probability that the degree of care required of the care recipient improves when care is performed according to the output care plan, and the care recipient A process changing unit that changes the care plan output support model so that a probability acquired for the output care plan with respect to an input of a situation approaches the calculated probability;
Care plan creation support system with
The care plan output support model includes a neural network,
The care plan creation support system according to claim 1.
The situation of the cared person is a result of selecting an option that matches the situation of the cared person with respect to a survey item set for use in authorization of the degree of care required. Care plan creation support system.
A care plan changing unit capable of changing the output from the care plan output unit;
The care plan creation support system according to any one of claims 1 to 3.
In the determination unit, the care-required level of the care receiver newly input after care is performed using the care plan is improved from the care-required level of the care receiver before the care is performed. The care plan creation support system according to any one of claims 1 to 4, wherein the care plan creation support system determines whether or not.
At least a part of a program for executing processing by the care plan output unit, the determination unit, the probability calculation unit, and the processing change unit is stored in a server,
The care plan creation support system according to any one of claims 1 to 5.
At least a part of a program for executing processing by the care plan output unit, the determination unit, the probability calculation unit, and the processing change unit is stored in a cloud server,
The care plan creation support system according to claim 6.
A storage medium connectable to the care plan creation support system according to claim 1,
Information for identifying the care recipient, the status of the care recipient of the care recipient, the care plan used for the care recipient, and the care recipient after the care has been performed using the care plan Storing a record associated with a caregiver's need for care or a change in the need for care as a result of care being performed using the care plan,
Storage medium.
Using the care plan output model that outputs, for each care plan, the probability that the degree of care required will improve with respect to the input of the status of the care recipient, the care recipient for the input of the status of the care receiver of the care recipient Obtaining a probability that the degree of care required for each care plan is improved for each care plan, and outputting the care plan with the higher probability acquired as a recommended care plan; and
A step of determining whether or not the degree of care required of the cared person after providing the output care plan to the cared person has improved;
Using the result of the determination, the step of newly calculating a probability that the degree of care required of the care recipient is improved by providing the output care plan and the output for the input of the situation of the care recipient Changing the care plan output support model so that the probability acquired for the care plan approaches the calculated probability;
Care plan creation support method including.
On the computer,
Using the care plan output model that outputs, for each care plan, the probability that the degree of care required will improve with respect to the input of the status of the care recipient, the care recipient for the input of the status of the care receiver of the care recipient Processing for obtaining the probability of improvement in the degree of care required for each care plan, and outputting the acquired care plan with a higher probability as a recommended care plan,
A process of determining whether or not the degree of care required of the cared person after providing the output care plan to the cared person has improved;
Using the result of the determination, a process for newly calculating the probability that the degree of care required of the care recipient is improved by providing the output care plan;
A process of changing the care plan output support model so that a probability acquired for the output care plan with respect to the input of the care recipient status approaches the calculated probability;
Care plan creation support program to execute