JP2016197330A - Analysis system, and rehabilitation support system, method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent the reduction of motivation in rehabilitation.SOLUTION: A rehabilitation support system according to the invention comprises: past patient information storage means for storing, for a plurality of past patients, observation history information including observation information per prescribed unit, progress information that is associated with a recovery state and includes at least a time series element, and basic attribute information; subject patient information storage means for storing, for a subject patient, progress information and basic attribute information; next stage prediction means for predicting, on the basis of the progress information and basic attribute information pertaining to past patients and the subject patient, the number of prescribed units and the number of times action is performed as required for the subject patient to proceed to a next state; similar patient extraction means for extracting a past patient who most resembles the subject patient on the basis of the prediction result and the progress information and basic attribute information pertaining to past patients and the subject patient; and predicted observation information output means for predicting and outputting future observation information that pertains to the subject patient using observation history information that pertains to the extracted past patient.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a data analysis system, an analysis method, and an analysis program for data concerning an action or phenomenon of an individual accompanied by a gradual change (recovery, etc.) of ability and state including rehabilitation. The present invention also relates to a rehabilitation support system that supports rehabilitation, a rehabilitation support method, and a rehabilitation support program.

  There is a need for technology that supports and promotes patient recovery by maintaining and improving patient rehabilitation (rehabilitation).

  One factor that reduces patient motivation is that the patient cannot realize the rehabilitation effect. For example, even if a doctor provides information to the patient, “By continuing rehabilitation as it is, it will recover to the level at which daily life is possible,” and the patient does not know how much rehabilitation should be continued. Even if you continue, it is difficult to see the recovery state at first, and you cannot feel the effect.

  Therefore, it is important to first tell the patient how long rehabilitation is necessary. However, for example, if it takes a long period of time such as several months to complete rehabilitation, even if the doctor provides information to the patient about such a long rehabilitation period, the period until the rehabilitation is completed several months ahead for the patient. It is difficult to realize the recovery due to daily rehabilitation because it is too long or the change from the current state to the state where rehabilitation is completed is too large.

  As a technique related to the confirmation of the rehabilitation effect, for example, Patent Document 1 compares the rehabilitation execution data of the patient with the rehabilitation performance information of the past patient, and the degree of recovery of the patient (how much of the whole state The technology to display whether or not

  Further, for example, in Patent Document 2, a plurality of observation data including information on body movements when a person of the same case operates is analyzed, and a target value that is a body movement on the next reference date for each patient is analyzed. The technology to determine the is described. In addition, the technique described in Patent Document 2 is based on the average recovery for each period reference day obtained from past observation data that is close to the target patient and the case, sex, age, and severity of disability, in addition to the current recovery degree that can be seen from the patient's symptoms. By adding the degree, it is possible to set a target value suitable for each patient.

2013-161315 2001-000420 gazette

  In order to prevent the patient's motivation from decreasing, it is important to provide the patient with information on the rehabilitation effect in a shorter period than the period until completion of rehabilitation.

  In general, rehabilitation is divided into a plurality of stages according to the recovery state. Also, each stage often has clear criteria related to recovery status. In this way, by dividing the rehabilitation period into a plurality of stages in which clear criteria are set in advance, the patient can feel recovery when proceeding with the stages.

  However, even if the rehabilitation period is divided into multiple stages, it is still difficult to see how long it will take to proceed to the next stage. A similar problem arises that the effect cannot be realized. Therefore, it is desired to provide the patient with information such as the number of times and the number of days required to proceed from the present stage to the next stage, and information regarding the rehabilitation effect in a period shorter than the period until proceeding to the next stage.

  For example, if a patient can accurately and specifically present a prediction of recovery, such as how much recovery is expected on the next rehabilitation date or any day before proceeding to the next stage, the patient can be rehabilitated. It will be easier to realize the effect, and it will lead to the maintenance and improvement of motivation.

  The technique described in Patent Document 1 is a technique for specifically grasping the current recovery degree (rehabilitation effect) of a patient, such as being in the sixth stage among the ten stages, and the subsequent state It is not something to predict.

  In addition, if the technique of patent document 2 is utilized, the target value for every period reference day calculated | required for every patient can be shown as a prediction result of the said patient's recovery state of the said period reference day. However, the technique described in Patent Document 2 is intended to determine a target value, and is not intended to accurately predict the state of each patient's period reference date. For example, the technique described in Patent Document 2 does not consider the difference in recovery speed for each patient.

  The patient's recovery speed does not depend only on the diagnosis results such as the case, sex, age, severity of disability, etc. and the basic attributes of the patient. For example, the patient's recovery speed may vary depending on the invisible nature such as the patient's motivation and original physical ability.

  Therefore, simply extracting another patient group that is similar to the target patient's case, gender, age, and severity of disability, and using the extracted patient group results information, it is assumed that the error will be very large. Is done. Patent Document 2 also describes that the target value is corrected (balance correction) by multiplying the average recovery degree by a coefficient of 1 or more or 1 or less according to the condition or performance of the patient at the discretion of the doctor or trainer. ing. However, it is time-consuming to require the judgment of a doctor or trainer each time, and it is not clear what the doctor or trainer should make a correction on.

  Note that the above problems are not limited to rehabilitation, but are acts or events of individual items (individuals or individual items) that involve step-by-step changes in ability and state, and have continued for a relatively long period of time. The same applies to the motivation of persons (actors, observers, etc.) involved in acts or events that are difficult to grasp.

  Therefore, the present invention provides an analysis system, a rehabilitation support system, a method, and a program that can prevent a decrease in the motivation of a person involved in an act or event of an individual accompanied by a gradual change in ability or state, including rehabilitation. With the goal.

  The rehabilitation support system according to the present invention provides, for each of a plurality of past patients who have undergone rehabilitation having at least a stage determined based on the same standard as the rehabilitation performed by the target patient, for each rehabilitation of the patient or a predetermined period unit. Observation history information including observation information for each patient, progress information that is information relating to the recovery state of the patient and including at least a time-series element, and basic attribute information indicating the basic attribute of the patient Target patient information for storing past patient information storage means, progress information that is information related to the recovery state of the target patient and includes at least a time-series element, and basic attribute information indicating the basic attributes of the target patient Storage means, past multiple patient progress information and basic attribute information, and target patient progress information Based on the basic attribute information and the next stage prediction means for predicting the number of rehabilitations or the number of period units required for the target patient to proceed to the next stage, the prediction result by the next stage prediction means, and the progress of past multiple patients Similar patient extraction means for extracting a past patient most similar to the target patient based on the information and basic attribute information, and the progress information and basic attribute information of the target patient, and the extracted past patient observation state history information Is used to predict that the target patient will be observed at any implementation time included until the target patient proceeds to the next stage or at any time unit included before the target patient proceeds to the next stage. Prediction observation information output means for outputting observation information to be output.

  Further, the rehabilitation support method according to the present invention provides for each of a plurality of past patients who have undergone rehabilitation having at least a stage determined based on the same standard as the rehabilitation performed by the target patient, or for each predetermined rehabilitation of the patient. Observation history information including observation information for each period unit, progress information that is information related to the recovery state of the patient and includes at least a time-series element, and basic attribute information indicating the basic attributes of the patient A target for storing past patient information storage means for storing, progress information that is information relating to the recovery state of the target patient and includes at least a time-series element, and basic attribute information indicating the basic attributes of the target patient The information processing device that can access the patient information storage means is the past information and basic information of multiple patients. Based on the sex information, target patient progress information and basic attribute information, predict the number of rehabilitations or the number of time units required for the target patient to proceed to the next stage, and the prediction results and past multiple patient progress information Based on the basic attribute information and the progress information and basic attribute information of the target patient, the past patient most similar to the target patient is extracted, and the extracted past patient observation state history information is used to Expected to be observed from the target patient at any implementation time included until the patient progresses to the next stage or at any time unit included until the target patient progresses to the next stage Predictive observation information that is observation information is output.

  Further, the rehabilitation support program according to the present invention provides for each of a plurality of past patients who have undergone rehabilitation having at least a stage determined based on the same criteria as the rehabilitation performed by the target patient, or for each predetermined rehabilitation of the patient. Observation history information including observation information for each period unit, progress information that is information related to the recovery state of the patient and includes at least a time-series element, and basic attribute information indicating the basic attributes of the patient A target for storing past patient information storage means for storing, progress information that is information relating to the recovery state of the target patient and includes at least a time-series element, and basic attribute information indicating the basic attributes of the target patient A computer accessible to the patient information storage means is stored in the past with multiple patient progress information and Based on the basic attribute information, the progress information and basic attribute information of the target patient, the process of predicting the number of rehabilitations or the number of time units required for the target patient to proceed to the next stage, the prediction results, and the past multiple patients Based on the progress information and basic attribute information and the target patient's progress information and basic attribute information, use the process to extract the past patient most similar to the target patient, and use the extracted past patient observation history information Observed from the target patient at any implementation time included until the target patient progresses to the next stage or at any time unit included before the target patient progresses to the next stage. A process of outputting predicted observation information that is predicted observation information is executed.

  In addition, the analysis system according to the present invention is a data analysis system related to an action or phenomenon of an individual accompanied by a gradual change in ability or state, and is the same as the action or phenomenon of the object individual that is the object of analysis. For each of a plurality of past objects that have experienced an act or phenomenon having at least a stage determined by the standard, observation history information including observation information for each predetermined unit in the action or phenomenon of the individual object, and changes in the individual object Past individual information storage means for storing historical information that is information related to the ability or state to be performed and includes at least time-series elements, and basic attribute information indicating the basic attributes of the individual, and the target individual Is information related to the changing ability or state of the information, and includes at least time-series elements and time-lapse information, and basic attribute information indicating the basic attributes of the target object. It takes for the target individual to proceed to the next stage based on the target individual information storage means, the past information and basic attribute information of the plurality of past objects, and the progress information and basic attribute information of the target individual Based on the next stage prediction means for predicting the number of predetermined units, the prediction result by the next stage prediction means, the progress information and basic attribute information of a plurality of past objects, and the progress information and basic attribute information of the target object Using the similar individual extracting means for extracting the past individual most similar to the target individual and the observation state history information of the extracted past individual until the target individual proceeds to the next stage. Predicted observation information output means for outputting predicted observation information, which is observation information predicted to be observed from the target object when any predetermined unit included in between is provided.

  Further, the analysis method according to the present invention is a method for analyzing data on an action or phenomenon of an individual accompanied by a gradual change in ability or state, and is the same as the action or phenomenon of the object individual that is the object of analysis. For each of a plurality of past objects that have experienced an act or phenomenon having at least a stage determined by the standard, observation history information including observation information for each predetermined unit in the action or phenomenon of the individual object, and changes in the individual object Past personal information storage means for storing historical information that is information related to the ability or state to be performed and is information including at least a time-series element, and basic attribute information indicating the basic attributes of the individual; A target for storing progress information that is information related to the changing ability or state of the information and includes at least time series elements, and basic attribute information indicating the basic attributes of the target object The information processing apparatus that can access the object information storage means determines that the target object is the next stage based on the past information and basic attribute information of the plurality of objects and the progress information and basic attribute information of the target object. Predicting the number of predetermined units required to proceed to, and based on the prediction results, the progress information and basic attribute information of the past plural objects, and the progress information and basic attribute information of the target object, The most similar past individual is extracted, and the observation state history information of the extracted past individual is used, and at the time of any predetermined unit included until the target individual proceeds to the next stage Further, it is characterized in that predicted observation information which is observation information predicted to be observed from an individual object is output.

  The analysis program according to the present invention is a data analysis program related to an action or phenomenon of an individual accompanied by a gradual change in ability or state, and is the same as the action or phenomenon of an object that is the object of analysis. For each of a plurality of past objects that have experienced an act or phenomenon having at least a stage determined by the standard, observation history information including observation information for each predetermined unit in the action or phenomenon of the individual object, and changes in the individual object Past individual information storage means for storing historical information that is information related to the ability or state to be performed and includes at least time-series elements, and basic attribute information indicating the basic attributes of the individual, and the target individual Information related to the changing ability or state of the information, including at least time-series elements, progress information, and basic attribute information indicating the basic attributes of the target object, Based on the progress information and basic attribute information of a plurality of past objects and the progress information and basic attribute information of the target object, the target object is transferred to a computer accessible to the target object information storage means to be stored. Based on the process of predicting the number of predetermined units required to proceed to the stage, prediction results, past multiple pieces of progress information and basic attribute information, target piece of progress information and basic attribute information A process for extracting the past individual most similar to the individual, and any predetermined included in the period until the target individual proceeds to the next stage using the extracted past observation state history information A process of outputting predicted observation information, which is observation information predicted to be observed from the target object when the unit has elapsed, is executed.

  ADVANTAGE OF THE INVENTION According to this invention, the fall of the motivation of the person involved in the act or event of an individual with a step change of ability or a state including rehabilitation can be prevented.

It is a block diagram which shows the structural example of the analysis system of 1st Embodiment. It is explanatory drawing which shows the example of the information memorize | stored in the past individual information storage means. 3 is a block diagram showing an example of the configuration of next stage prediction means 101. FIG. It is a flowchart which shows an example of operation | movement of the analysis system of 1st Embodiment. It is a block diagram which shows the hardware structural example of the analyzer with which the rehabilitation assistance system of 2nd Embodiment is provided. It is a block diagram which shows the structural example of the analyzer with which the rehabilitation assistance system of 2nd Embodiment is provided. It is a flowchart which shows an example of operation | movement of the analyzer with which the rehabilitation assistance system of 2nd Embodiment is provided.

Embodiment 1. FIG.
Next, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a configuration example of an analysis system according to the first embodiment of the present invention. The analysis system of the present embodiment is a system for analyzing data relating to an action or phenomenon of an individual accompanied by a gradual change in ability or state, including rehabilitation. Examples of applicable acts or phenomena other than rehabilitation include, for example, exercises in the field of sports, experiments and observations of living organisms and any individual objects (individuals, liquids, gases) in the fields of biology and natural sciences, etc. Etc. Hereinafter, an action or phenomenon of an individual accompanied by a step change in ability or state, which is an object of analysis in the present embodiment, may be simply referred to as a target action or a target phenomenon.

  The analysis system 100 shown in FIG. 1 includes a past individual information storage unit 111, a target individual information storage unit 112, a next stage prediction unit 101, a similar individual extraction unit 102, and a predicted observation information output unit 103. Prepare.

  The past individual information storage means 111 is configured to determine, for each of a plurality of past items that have experienced an act or phenomenon having at least a stage determined based on the same criteria as the target action or target phenomenon of the target individual, Observation history information including observation information for each predetermined unit in the phenomenon, progress information that is information related to the ability or state of change of the individual object and includes at least time series elements, and basic attributes of the individual object And basic attribute information indicating.

  FIG. 2 is an explanatory diagram illustrating an example of information stored in the past individual information storage unit 111. The example shown in FIG. 2A is an example of basic attribute information stored in the past item information storage unit 111, and the example shown in FIG. 2B is stored in the past item information storage unit 111. It is an example of observation history information and progress information. FIG. 2B shows an example in which observation history information and progress information are stored together in one table.

  As shown in FIG. 2 (a), the past individual information storage means 111 associates, as basic attribute information, an individual ID for identifying an individual with each content of the basic attribute of the individual. May be stored. Further, as shown in FIG. 2B, the past individual information storage unit 111 includes, as observation history information and progress information, an individual ID for identifying an individual, and an individual action or target phenomenon of the individual. Observation information in a predetermined unit, observation information identification number ("data no" in the figure) of the individual, time information such as the date at that time, and the number of units as the number of the predetermined unit at that time, Information in which the stage at that time is associated may be stored. In this way, if at least the number of units at the time of observation information is acquired and the stage at that time is stored, the state of the stage in the target action or target phenomenon that the individual has passed (in each stage It is possible to know how many units are required, and which stage has been shifted from a certain stage. Hereinafter, in the present embodiment, in the case of progress information, it refers to information that associates the number of units when observation information is acquired with information on the stage of the target action or target phenomenon that the individual has passed. The stage information is an example of information related to the ability or state of the individual to change. The time series element in the progress information may be, for example, information indicating the progress of a change in the ability or state of an individual object. As an example, information related to the changing ability or state of an individual (information on actions and events during the response period, information on the current stage, etc.), information on time, and the number of actions performed (how many times ) Or the like. For example, in the case of rehabilitation, the above actions include actions related to medical treatment such as a diagnosis action, a rehabilitation action, and a diagnosis action.

  Here, the basic attribute of an individual may be a main attribute that the individual has. The basic attribute may be an attribute that the target object naturally has. For example, if the target object is a person, examples of basic attributes include gender, age or age. Further, if the target object is an object, the group to which the object belongs and the size, color, composition, etc. of the object can be mentioned. In addition, if the target item is a machine, the model, date of manufacture, and the like can be given.

  In addition, the predetermined unit in the target action or target phenomenon is a unit that is defined more finely than the stage of dividing the target action or target event and is used as a reference for progress. For example, the predetermined unit may be a unit related to a period such as one day or one hour in the case of an action or event that progresses with the passage of time of an individual, or any action performed on or performed by an individual May be a unit related to the number of actions such as once. In the case where a combination of a plurality of actions is counted as one action, a unit of 0.5 times can be considered. Other examples include units related to physical quantities applied to individual objects such as 1 gram or 1 cm. A combination of a unit related to time and other units (units for the number of actions and other physical quantities) may be used as the predetermined unit. With such a unit, it is possible to specify, for example, how many days after the act.

  In addition, the observation information is information that is observed from an individual object, and is not particularly limited as long as it is information related to the ability or state that changes in the target action or target phenomenon. The observation information may be, for example, information obtained by photographing a region including a changed part in an individual object. Note that the observation information is not limited to images and videos, and may be observable information such as numerical values obtained by observation.

  In addition, when the target action is rehabilitation of a person's physical movement, the observation information is preferably information indicating an objective recovery degree. As an example of such observation information, motion sequence information indicating a patient's physical motion can be cited. Here, the motion sequence information is information indicating continuous body movements. The motion sequence information may be, for example, a moving image of body movement, or information obtained by continuously arranging human skeleton information converted into joint position information after converting the moving image into still image data. May be.

  The target individual information storage unit 112 stores the past progress information of the target individual and the basic attribute information. The progress information and basic attribute information stored in the target individual information storage unit 112 may be in the same format as the progress information and basic attribute information stored in the past individual information storage unit 111. In this case, the target object information storage unit 112 stores observation history information including observation information in each predetermined unit of the target action or target phenomenon of the target individual as shown in FIG. You may remember.

  The next stage predicting means 101 determines the number of units required for the target individual to proceed to the next stage based on the progress information and basic attribute information of the past plural objects and the progress information and basic attribute information of the target individual. Predict.

  The similar individual extracting unit 102 includes a prediction result by the next stage predicting unit 101, past information and basic attribute information of a plurality of past items stored in the past individual information storing unit 111, and target individual information storing unit. Based on the progress information and basic attribute information of the target object stored in 112, the past individual most similar to the target object is extracted.

  For example, the similar individual extracting unit 102 extracts the past individual most similar to the target individual in terms of the number of units required from the stage where the target individual indicated by the basic attribute and the prediction result is now to the next stage. May be. Further, for example, when the similar individual extracting means 102 extracts, the speed of change (step transition) between the target individual and the past individual until the stage where the target individual is now (current stage) is further reached. Speed) and progression order of steps may be taken into account. In addition, for example, the similar individual extraction unit 102 takes into account the similarity of observation information between the target individual and the past individual when the current stage of the target individual is further extracted. Also good.

  The predicted observation information output means 103 uses the extracted observation state history information of the past individual, and when the target individual has elapsed until the target individual proceeds to the next stage, the target individual Predictive observation information which is observation information predicted to be observed from an object is output. Note that the predicted observation information output unit 103, for example, in generating predicted observation information at the time of the designated unit, includes the target included in the extracted past observation history information as the predicted observation information. The observation information observed during the same stage as the current stage of the individual object and observed when it corresponds to the designated unit time (hereinafter referred to as corresponding observation information) may be output as it is. Further, the predicted observation information output means 103 extracts, for example, the degree of change from the corresponding observation information when the latest observation information of the target patient is obtained, and the extracted degree of change is extracted from the target patient. Information reflected in the latest observation information may be generated and output.

  FIG. 3 is a block diagram showing a more detailed configuration example of the next stage prediction unit 101. As shown in FIG. 3, the next stage prediction unit 101 may include an attribute data generation unit 201, a prediction model learning unit 202, and a prediction unit 203.

  The attribute data generation means 201 is at least a piece of information relating to a given patient, including at least progress information and basic attribute information. The attribute data of the patient is attribute data of the patient and is represented by a vector comprising a plurality of predetermined elements. Generate attribute data.

  The predictive model learning unit 202 determines the number of rehabilitations or the number of period units required for an arbitrary patient to proceed to the next stage from the progress information and basic attribute information of an arbitrary patient based on the past information and basic attribute information of a plurality of patients. Is learned. The prediction model learning unit 202 also associates each attribute data of a plurality of past patients generated by the attribute data generating unit 201 with information on the number of rehabilitations or the number of period units that the patient has required at each stage. May be used as learning data to learn a prediction model.

  The predictive model learning means 202 is a step transition model in which a transition condition to another step is determined for each step as a predictive model, depending on the basic attributes of the patient and the transition speed to the previous step of the patient. A stage transition model may be learned.

  The prediction unit 203 uses the prediction model learned by the prediction model learning unit 202 to predict the number of rehabilitations or the number of period units required for the target patient to proceed to the next stage. Further, the prediction unit 203 calculates the number of rehabilitations or the number of period units required for the target patient to proceed to the next stage, which is obtained by inputting the target patient's attribute data generated by the attribute data generation unit 201 to the prediction model. It is good also as a prediction result.

  In the present embodiment, the past individual information storage unit 111 and the target individual information storage unit 112 are realized by a storage device, for example. Further, the next stage prediction unit 101, the similar item extraction unit 102, and the predicted observation information output unit 103 are realized by, for example, a processor that operates according to a program or an information processing apparatus including the processor.

  Next, the operation of this embodiment will be described. FIG. 4 is a flowchart showing an example of the operation of the analysis system of the present embodiment. In the example shown in FIG. 4, before the start of step S101, the past item information storage means 111 stores the basic attribute information, observation history information, and history of past items that have experienced the target action or event. It is assumed that at least information is stored, and at least the basic attribute information and the progress information of the target item are already stored in the target item information storage unit 112. Note that step S101 is started by, for example, a prediction instruction from the user.

  In the example illustrated in FIG. 4, first, the next stage prediction unit 101 determines that the target individual is the next based on the progress information and basic attribute information of a plurality of past objects and the progress information and basic attribute information of the target object. The number of predetermined units required to proceed to the step is predicted (step S101).

  Next, the similar individual extraction unit 102 determines the target individual based on the prediction result in step S101, the past plural pieces of progress information and basic attribute information, and the target individual progress information and basic attribute information. The past individual most similar to the object is extracted (step S102).

  Next, the predicted observation information output means 103 outputs the predicted observation information using the past observation state history information extracted in step S102 (step S103).

  As described above, according to the present embodiment, high-accuracy information is obtained for observation information at the elapse of any predetermined unit included in the target action or target phenomenon of the target object before proceeding to the next stage. Can be provided. Therefore, since the person involved in the target action or the target event can confirm such information, the effect in a shorter period can be realized, so that motivation can be maintained or improved.

  That is, the analysis system of this embodiment is not only a basic attribute, but also delimitation information that is a stage where the criteria are relatively clear, and information about the speed of change for each individual that has passed through such a stage (information including time-series elements) This is because the predicted observation information is output using the observation information of the similar individual that is preferably extracted using.

  Moreover, if the observation information of similar individual objects is used, information indicating a specific and integrated change can be easily obtained with high accuracy.

  In addition, when the target action in said embodiment is rehabilitation, the past individual information storage means 111 is the information regarding the medical treatment performed with respect to the said patient further about each past plural thing (plural patients). Certain clinical information may be stored. In addition, the target individual information storage unit 112 may store clinical information that is information related to medical care performed on the target individual (target patient). In such a case, the next stage prediction unit 101 further calculates the number of rehabilitations or the number of period units required for the target patient to proceed to the next stage based on the past clinical information of the plurality of patients and the clinical information of the target patient. It may be predicted.

Embodiment 2. FIG.
Next, a second embodiment of the present embodiment will be described with reference to the drawings. In the present embodiment, the above analysis system is applied to a rehabilitation support system.

  In addition, the rehabilitation support system of this embodiment has a function of predicting and displaying the operation sequence information of the next rehabilitation date of the target patient. Specifically, the analyzer provided in the rehabilitation support system is (1) necessary for further recovery from the day when the recovery state of the target patient first reaches the current recovery level of the target patient to the next recovery level. Has a function to predict the number of rehabilitation days. Furthermore, the analyzer (2) The above-mentioned prediction result and the medical practice performed on the patient from the onset of the injury or illness that caused the target patient to require rehabilitation until the first day when the current recovery level was reached Attribute data representing features such as information related to medical care (hereinafter referred to as clinical history information), such as medical prescriptions and diagnosed wound names, and patients who have completed similar rehabilitation in the past (hereinafter referred to as past patients) ), The number of rehabilitation days required to further recover from the day the target patient first reached the current level of recovery to the next level of recovery, and the injury or illness that caused each past patient to require rehabilitation treatment From the past patient group, the target patient's list of patients can be retrieved from the past patient group using the attribute data indicating the characteristics of the past patient's clinical history information, etc. It has a function of extracting a past patient kink and both embodiments days and attribute data are most similar. Further, the analysis device (3) displays the rehabilitation operation sequence information performed when the extracted past patient corresponds to the next rehabilitation implementation date of the target patient from the date when the current recovery level of the target patient is reached for the first time. Has a function to extract.

  Regarding (2) above, the clinical history information is the clinical history information from the day when the recovery level of the target patient was first reached to the level of recovery one stage before the date when the current recovery level was first reached. There may be. In addition, the number of days of rehabilitation for past patients is further increased until the first recovery level before the current recovery level of the target patient is reached (in this case, from the day when the recovery level of the previous stage is reached for the first time). The number of rehabilitation implementation days required for the above may be used. Similarly, the number of rehabilitation days required for the first time to reach each recovery level in the previous stage before reaching the current recovery level of the target patient may be used. Hereinafter, the current recovery level of the target patient may be referred to as the p-th recovery level, and the next recovery level may be referred to as the (p + 1) -th recovery level.

  FIG. 5 is a configuration diagram illustrating an example of a hardware configuration of an analysis apparatus included in the rehabilitation support system according to the present embodiment. The analysis apparatus 1 illustrated in FIG. 5 includes a CPU (Central Processing Unit) 1001, a memory 1002, an output device 1003, an input device 1004, and a network interface 1005.

  The memory 1002 is, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), an auxiliary storage device (such as a hard disk), or the like. The output device 1003 is a device that outputs information, such as a display device or a printer. The input device 1004 is a device that receives an input of a user operation, such as a keyboard and a mouse. The network interface 1005 is an interface connected to a network constituted by, for example, the Internet, a LAN (Local Area Network), a public line network, a wireless communication network, or a combination thereof.

  FIG. 6 is a block diagram illustrating a functional configuration example of the analysis apparatus included in the rehabilitation support system according to the present embodiment. As illustrated in FIG. 6, the analysis device 1 includes a rehabilitation frequency prediction unit 11, a similar patient extraction unit 15, a motion information extraction unit 16, and a prediction result output unit 17.

  In this case, each of the functional blocks of the analysis apparatus 1 is configured by a CPU 1001 that reads and executes a computer program stored in the memory 1002 and controls other units. The hardware configuration of the analyzer 1 and each functional block thereof is not limited to the above configuration.

  Next, information input to the analyzer 1 will be described.

  The analyzer 1 has first reached the p-th recovery level, which is the current recovery level, from the day when it first reached the p-1 recovery level, which is at least one stage before the current recovery level. Clinical history information up to a certain day is input. Note that the clinical history information may be clinical history information from the onset of the injury or illness that caused the need for rehabilitation treatment until the day when the p-th recovery level was reached for the first time. In that case, it is preferable that clinical history information is divided for each recovery level period. In the present embodiment, each recovery level period may be referred to as an i-th recovery level period using a subsequent recovery level index i (i = 1 to an integer corresponding to the number of steps). For example, in the case of the period from the onset of injury or illness that caused rehabilitation treatment to the first day when the first recovery level is reached, it is referred to as “first recovery level period”. For example, in the case of a period from the day when the p-1th recovery level is reached for the first time to the date when the pth recovery level is reached for the first time, it is referred to as a “pth recovery level period”.

  Moreover, the patient basic information showing age sex etc. is input into the analysis apparatus 1 regarding the target patient. Further, the analysis apparatus 1 receives the number of days that have elapsed since the day when the target patient first reached the p-th recovery level (hereinafter referred to as the number of days elapsed at the p-th level).

  The analysis apparatus 1 also includes, for each past patient, at least pth recovery level period clinical history information, patient basic information, and at least p + 1th recovery level period of each patient's physical exercise on each rehabilitation implementation date. The operation sequence information group representing the state and the number of days of rehabilitation during the p + 1th recovery level period may be input.

  The clinical history information of the target patient includes, for example, wound name history information that is a history of wound names diagnosed for the target patient during at least the p-th recovery level period of the target patient, and the target during the same period. A medical practice history that is a history of medical practice performed on a patient and pharmaceutical history information that is a history of pharmaceuticals prescribed or administered to the target patient during the same period may be included. Hereinafter, the clinical history information of the target patient may be referred to as target patient clinical history information.

  The past patient clinical history information includes wound name history information, which is a history of wound names diagnosed for the past patient during at least the p-th recovery level period of the past patient, and the past patient during the same period. The medical practice history that is the history of the medical practice performed on the patient and the pharmaceutical history information that is the history of the medicine prescribed or administered to the past patient during the same period may be included. Hereinafter, clinical history information of each past elephant patient may be referred to as past patient clinical history information.

  Here, the medical practice includes widespread clinical practice such as examination for diagnosis, treatment to cure wounds, surgery, rehabilitation, and the like. The wound name / history history information may be information in which the names of wounds and sickness diagnosed during the corresponding period are arranged in the order of case strings. The medical practice history may be information in which medical practices performed during the corresponding period are arranged in time series. The drug history information may be information in which drugs prescribed or administered during the corresponding period are arranged in time series.

  Here, it is assumed that the medical treatment history includes information that can specify the number of days of rehabilitation performed in each recovery level period passed by the patient. In addition, since the rehabilitation act is included in the medical care act, if the date and time when the rehabilit act was performed and the information of the recovery level of the patient at that time are stored in association with each other, the above-mentioned rehabilitation implementation days can be specified. Is possible. In addition, when the number of days elapsed at the p-th level can be specified from the medical treatment history of the target patient, the number of days elapsed at the p-th level may not be input separately.

  In addition, when the target patient has not reached any recovery level, that is, when the target patient is in the stage after the onset of injury or illness causing the rehabilitation treatment, the “pth recovery level period” described above. May be read as “the period from the onset of the injury or illness that caused the need for rehabilitation treatment until the date when the information affecting the recovery state satisfies a predetermined condition separately defined”.

  The patient basic information is information on basic attributes of the patient. The basic attributes of the patient are, for example, sex, age, height, weight, and the like. Hereinafter, the basic information of the target patient may be referred to as target patient basic information, and the basic information of the past patient may be referred to as target patient basic information.

  The operation sequence information group may be information that summarizes the operation sequence information of patients in rehabilitation, for example, for each past patient and for each rehabilitation implementation date during at least the p + 1th recovery level period. It is assumed that information on the rehabilitation implementation date is given to each operation sequence information. Hereinafter, the past patient motion sequence information group may be referred to as past patient motion sequence history information.

  In addition, the number of days of rehabilitation during the p + 1th recovery level period of the past patient was necessary to further recover to the next p + 1th recovery level from the day when the pth recovery level of the past patient was first reached. Rehabilitation days. In addition, when the said rehabilitation implementation days can be specified from the medical treatment history of a past patient, it is not necessary to input the said rehabilitation implementation days separately.

  Here, as an example of the recovery level, there is a stage based on an evaluation method based on a movement pattern of central nerve palsy. In this example, the stage information obtained by evaluating the recovery state in six stages from stage 1 (complete paralysis) to stage 6 (separate movement possible) can be used.

  The clinical history information corresponds to the progress information and clinical information of the first embodiment. The basic information corresponds to the basic attribute information of the first embodiment. Further, the operation sequence history information corresponds to the observation state history information of the first embodiment.

  Further, the rehabilitation frequency prediction unit 11 of the present embodiment corresponds to the next stage prediction unit 101 of the first embodiment. In addition, the attribute data generation unit 12 of the present embodiment corresponds to the attribute data generation unit 201 of the first embodiment. The prediction model learning unit 13 of this embodiment corresponds to the prediction model learning unit 202 of the first embodiment. The prediction unit 14 of this embodiment corresponds to the prediction unit 203 of the first embodiment. The similar patient extraction unit 15 of this embodiment corresponds to the similar individual extraction unit 102 of the first embodiment. The motion information extraction unit 16 and the prediction result output unit 17 of the present embodiment correspond to the predicted observation information output unit 103 of the first embodiment.

  Each functional block of the analyzer 1 may acquire information stored in advance in the memory 1002 as the input information described above. For example, each functional block may acquire information input from the input device 1004 or a portable storage medium (not shown) as the input information described above. Further, for example, each functional block may acquire the above-described input information from another device connected via the network interface 1005. Each functional block is configured to store the acquired input information in the memory 1002 and operate using the stored input information.

  Next, each functional block of the analyzer 1 will be described.

  The rehabilitation frequency predicting unit 11 of this example includes an attribute data generating unit 12, a predictive model learning unit 13, and a predicting unit 14, which are necessary during the (p + 1) th recovery level period of the target patient. Calculate the number of rehabilitation days.

  The attribute data generation unit 12 includes attribute data representing characteristics in the rehabilitation treatment of the target patient from the target patient clinical history information and the target patient basic information, and the rehabilitation treatment of each past patient from the past patient clinical history information and the target patient basic information. Create attribute data representing features.

  The prediction model learning unit 13 receives the attribute data of each past patient and the p + 1th recovery level period rehabilitation implementation days of each past patient as input from the patient attribute data during the p + 1th recovery level period of the patient. Learn the prediction model that calculates the number of rehabilitation implementation days.

  The prediction unit 14 predicts the number of rehabilitation implementation days required during the p + 1th recovery level period of the target patient by inputting the attribute data of the target patient into the learned prediction model.

  The similar patient extraction unit 15 uses the rehabilitation implementation days required during the predicted p + 1th recovery level period of the target patient and the attribute data of the target patient to calculate both the rehabilitation implementation days and the attribute data. The most similar patient is extracted from the past patient group.

  The motion information extraction unit 16 extracts motion sequence information in rehabilitation performed when the extracted past patient reaches the p-th recovery level for the first time and corresponds to the next rehabilitation implementation date of the target patient. .

  The prediction result output unit 17 displays the motion sequence information extracted by the motion information extraction unit 16 as a motion sequence prediction result on the next rehabilitation implementation date of the target patient.

  A more specific example of each functional block will be described later. Although not shown, the rehabilitation support system may include a database that stores information to be input to the analysis apparatus 1.

  Next, operation | movement of the analyzer 1 of this embodiment is demonstrated. FIG. 7 is a flowchart showing an example of the operation of the analyzer 1 of the present embodiment.

  In the example illustrated in FIG. 7, first, each functional block of the analysis apparatus 1 (for example, the rehabilitation frequency prediction unit 11, the similar patient extraction unit 15, the motion information extraction unit 16, and the prediction result output unit 17) is necessary. Input information is acquired (step S11). As already described, the input information includes the target patient basic information, the target patient clinical history information, the past patient basic information group, the past patient clinical history information group, the past patient motion sequence history information, and the target patient's The elapsed days at the p-th level and the number of days of rehabilitation during the p + 1th recovery level period of the past patient are included. The input information acquired in step S11 is stored in the memory 1002.

  Next, the attribute data generation unit 12 of the rehabilitation frequency prediction unit 11 creates attribute data representing the characteristics of the target patient in the rehabilitation treatment and attribute data representing the characteristics of the rehabilitation treatment of each past patient (step S12). .

  Next, the prediction model learning unit 13 learns the prediction model by inputting the attribute data of each past patient and the number of days of rehabilitation required during the p + 1th recovery level period of each past patient (step S13). ). Note that the processing up to step S12 only needs to be performed prior to the prediction in step S14.

  The prediction unit 14 predicts the number of rehabilitation implementation days required during the second recovery level period of the target patient by inputting the attribute data of the target patient to the learned prediction model (step S14).

  Next, the similar patient extraction unit 15 uses the prediction result of step S14 and the attribute data of the target patient to obtain the most in terms of the attribute data and the number of rehabilitation implementation days required during the (p + 1) th recovery level period. Similar patients are extracted from the past patient group (step S15).

  Next, the motion information extraction unit 16 obtains motion sequence information in rehabilitation performed when the extracted past patient corresponds to the next rehabilitation implementation date of the target patient from the day when the p-th recovery level is reached for the first time. Extract (step S16).

  The prediction result output unit 17 displays the motion sequence information extracted by the motion information extraction unit 16 as a motion sequence prediction result on the next rehabilitation implementation date of the target patient (step S17).

  Next, the operation of each functional block will be described in more detail.

[Attribute creation phase (step S12)]
For example, the attribute data generation unit 12 may create attribute data of the target patient and each past patient as follows. The attribute data generation unit 12 first reads target patient basic information, target patient clinical history information, past patient basic information, and past patient clinical history information from the memory 1002. Here, it is assumed that the total number of past patients is N (N is an integer of 1 or more). Further, the attribute data of the nth past patient among the past patients is represented as X_n (n = 1,..., N). The attribute data X_n is represented as a vector composed of a plurality of elements.

  For example, it is assumed that the number of elements of attribute data is seven. In this case, the attribute data generation unit 12 generates, for example, data represented as X_1 = (0, 0, 3, 2, 1, 0, 0) as the first patient's attribute data. This is because the value of the attribute item 1 is 0, the value of the attribute item 2 is 0, the value of the attribute item 3 is 3, the value of the attribute item 4 is 2, and the value of the attribute item 5 is n 1, the value of attribute item 6 is 0, and the value of attribute item 7 is 0. The created attribute data is stored in the memory 1002.

  The attribute data generation unit 12 also creates attribute data X ′ for the target patient and stores it in the memory 1002. Note that “′” in X ′ is a symbol indicating that the patient is a target patient, and X ′ is expressed as a vector composed of a plurality of elements, like X_n.

  Here, each element of attribute data of a past patient corresponds to an item included in past patient basic information or past patient clinical history information of the past patient, information calculated from the item, and the like. Similarly, each element of the attribute data of the target patient corresponds to an item included in the target patient basic information or target patient clinical history information, information calculated from the item, and the like. For example, it is assumed that items of basic information include gender, age, height, and weight. In such a case, as an element of attribute data, for example, an item indicating 1 if the gender is male, an item indicating 0 if the woman is female, an item indicating the numerical value of age, an item indicating the numerical value of height, An item indicating a numerical value may be included.

  In addition, one of the elements of attribute data of a past patient may be the number and the ratio of a specific injury / patient name of the past patient during a predetermined period indicated by the past patient clinical history information of the past patient. . Here, the predetermined period may be during the p-th recovery level period of the past patient, the entire period from the rehabilitation start to the p-th recovery level, each recovery level period, or at the rehabilitation start time. To the time point corresponding to the current state of the target patient in the p-th recovery level (such as after the lapse of ○ days from the day when the p-th recovery level is reached). For example, the number of cases may be the number of times that a specific wound name is included in a predetermined period of past patient clinical history information. Further, for example, the ratio of the number of cases may be represented by (number of times that a specific injury and disease name is included in a predetermined period of past patient clinical history information) / rehabilitation days. Here, the number of rehabilitation days may be the number of days in a predetermined period, or may be the number of rehabilitations performed in a predetermined period. In addition, the attribute data generation part 12 can also obtain | require the number of cases and its ratio with respect to all the periods quoted as an example of the predetermined period.

  Similarly, one of the elements of the attribute data of the target patient may be the number and ratio of specific injury names of the target patient during a predetermined period indicated by the target patient clinical history information.

  Further, one of the elements of the attribute data of a certain past patient may be the number or the ratio of specific medical practice names of the past patient during a predetermined period indicated by the past patient clinical history information of the past patient. Good.

  Similarly, one of the elements of the attribute data of the target patient may be the number and ratio of specific drug names of the target patient during a predetermined period indicated by the target patient clinical history information.

  Further, one of the elements of the attribute data of a certain past patient may be the number or the ratio of specific medical practice names of the past patient during a predetermined period indicated by the past patient clinical history information of the past patient. Good.

  Similarly, one of the elements of the attribute data of the target patient may be the number and ratio of specific drug names of the target patient during a predetermined period indicated by the target patient clinical history information.

  One element of attribute data of a past patient includes each recovery level period up to the p-th recovery level of the past patient and each recovery level period indicated by the past patient clinical history information of the past patient. It may be the number of rehabilitations required during.

  Similarly, one of the elements of the attribute data of the target patient includes each recovery level period up to the p-th recovery level of the target patient and each recovery level period indicated by the target patient clinical history information and the like. It may be the number of rehabilitations required.

  In this way, the attribute data generation unit 12 can provide information about each past patient and target patient, information described in each item in the target patient basic information, target patient clinical history information, past patient basic information, and past patient clinical history information. Then, attribute data is generated having statistical information such as the occurrence frequency of predetermined information calculated based on the information and the time / number of times taken for a predetermined action or state as elements.

[Prediction Model Learning Phase (Step S13)]
For example, the prediction model learning unit 13 may learn the prediction model as follows. That is, the prediction model learning unit 13 first reads the attribute data of each past patient and the number of days of rehabilitation required during the p + 1th recovery level period of each past patient from the memory 1002.

  Again, the attribute data of the past patient n is expressed as X_n (n = 1,..., N). The jth element of the past patient n is represented as X_nj (j = 1,..., M). M is the number of elements of attribute data. In addition, the number of rehabilitation days required during the p + 1th recovery level period of the past patient n is represented as Y_n.

  The prediction model is expressed by the following equation (1), for example.

Y_i = f (X_i) (1)

  Here, f () is a function that receives the attribute data X_i of an arbitrary patient i and outputs the number of rehabilitation days required for the patient i during the p + 1th recovery level period. Patient i includes past patients and target patients. Moreover, the value calculated | required with a prediction model is represented as Y_i. The prediction model learning unit 13 determines a function model f () for calculating Y_n = f (X_n), (n = 1,..., N) and learns its parameters.

  Below, the prediction model learning part 13 shows the example using the linear regression model which can output Y_i with respect to arbitrary X_i as a prediction model. The linear regression model is a model often applied to the problem of predicting Y_i from X_i. Hereinafter, the mathematical structure of linear regression will be described.

  Here, X is an M-dimensional explanatory variable corresponding to the attribute data. Y is a numerical value. Also, let W be an M-dimensional weight vector. In this case, the linear regression model is expressed by the following equation (2). The superscript T represents transposition of vectors.

Note that the portion of {W ^T X} in Equation (2) corresponds to f () in Equation (1). Assume that {X_n, Y_n} (n = 1,..., N) is given as learning data for N past patients. In this case, the prediction model learning unit 13 calculates the value of the parameter W in the model represented by Expression (2) by optimizing the objective function of the following Expression (3) using linear regression. However, X_n and Y_n are realized values of X and Y, respectively.

  Note that λ is a parameter for adjusting the balance between the likelihood (first term on the right side) and the penalty term (second term on the right side). || W || is the norm (length) of the vector W. Usually, the L1 norm or L2 norm is used. L (W) is a convex function related to W, and can be maximized by a method according to the gradient method.

The prediction model learning unit 13 obtains the value of the parameter W that maximizes L (W). Hereinafter, the value of W determined denoted as W _c. The prediction model learning unit 13 sets the obtained W _c as the parameter W of the model expressed by the equation (2). Further, the prediction model learning unit 13 stores the obtained W _c in the memory 1002.

[Prediction Phase (Step S14)]
For example, the prediction unit 14 may perform prediction as follows, for example. That is, the prediction unit 14 first information of the trained prediction model (the value of W _c is applied the formula (2) or the like), attribute data corresponding to the subject patient, from the memory 1002. The information of the prediction model, for example, may be a value of W _c. Here, the read attribute data of the target patient is X ′.

  Then, the prediction unit 14 uses the prediction model specified by the read information and the attribute data X ′ to calculate the rehabilitation implementation days Y ′ required for the target patient during the p + 1th recovery level period by the following formula: Calculate according to (4).

  Then, the prediction unit 14 stores the calculated Y ′ in the memory 1002. Here, Y ′ represents the number of rehabilitation implementation days that will be required to reach the next recovery state (p + 1th recovery level) from the current state (pth recovery level) of the subject patient. Y ′ may be converted to an integer by rounding off the decimal part.

[Similar Patient Extraction Phase (Step S15)]
The similar patient extraction unit 15 extracts past patients similar to the target patient as follows, for example. That is, the similar patient extraction unit 15 is required during the p + 1th recovery level period of the past patient and the rehabilitation implementation days and attribute data required during the p + 1th recovery level period of each past patient. A similarity may be obtained from the number of days of rehabilitation (that is, a prediction result) and a set of attribute data, and a past patient most similar to the most similar target patient may be extracted.

  Here, the similar patient extraction unit 15 firstly combines {X_n, Y_n} (n = 1,...) That is a combination of the number of days of rehabilitation Y_n and attribute data X_n required during the p + 1th recovery level period of each past patient. .., N) and the combination {X ′, Y ′} of the rehabilitation implementation days Y ′ and attribute data X ′ required during the p + 1th recovery level period of the target patient are read from the memory 1002.

Then, the similar patient extraction unit 15 calculates a combination having the highest similarity with {X ′, Y ′} from {X_n, Y_n} (n = 1,..., N), and the combination. N may be obtained, and the obtained value of n may be written in the memory 1002. Hereinafter, the value of n thus determined is expressed as _{n c.}

  Hereinafter, a method for calculating the similarity will be described in detail. First, the similar patient extraction unit 15 obtains X_n: X_nj (j = 1,..., M) and Y_n from the past patient data set {X_n, Y_n} (n = 1,..., N). V_n = [X_n1, X_n2,..., X_nM, Y_n] (n = 1,..., N) is generated from the vector data made up of a plurality of elements. Similarly, V ′ = [X′_1, X′_2,..., X′_M, Y ′] is generated from the target patient data set {X ′, Y ′}.

  Then, the similar patient extraction unit 15 calculates the similarity with V ′ for V_n (n = 1,..., N). Here, the calculated similarity is represented as S_n (n = 1,..., N). For example, the similar patient extraction unit 15 may obtain S_n as shown in the following formula (5).

Here, <A, B> represents an inner product of the vector A and the vector B. S_n obtained by Equation (5) takes a value between 0 and 1, and approaches S as the two vectors V ′ and V_n are equal in direction, indicating high similarity. Similar patient extractor 15, the value of n which showed the highest value S_n a n _c. In addition, when there are a plurality of patients having the same similarity S_n, each may be set as a similar patient n _c1 , n _c2,.

[Operation Information Extraction Phase (Step S16)]
The motion information extraction unit 16 extracts motion sequence information in the rehabilitation performed when the extracted past patient corresponds to the next rehabilitation implementation date of the target patient from the date when the p-th recovery level is reached for the first time. Operation information extracting unit 16, for example, the number of days plus one age in the p level of subject patient (hereinafter referred to as applicable days) is calculated, the extracted similar patients n _c, the recovery level of the p When the above-mentioned number of days has passed since the first arrival date, the operation sequence information of the rehabilitation performed at the time may be extracted. Instead of the number of days elapsed at the pth level of the target patient, the number of rehabilitations performed at the pth recovery level of the target patient (hereinafter referred to as the number of times performed at the pth level) and the number of days elapsed since the last implementation date are used. May be. In that case, the operation information extracting unit 16, the extracted similar patients n _c, after the regeneration carried many times in the p levels from the date of first reaches the recovery level of the p, last execution date of the subject patient The operation sequence information of the rehabilitation performed at the time when the number of days elapsed since the time elapses may be extracted.

  Here, the motion information extraction unit 16 first reads from the memory 1002 the elapsed days of the target patient at the p-th level. Here, the elapsed days at the p-th level of the target patient of the target patient is denoted as T.

Operation information extracting unit 16, extracted similar patients n _c is the past, when carrying out the rehabilitation first led from day T + 1 day after recovery levels of the p, extracts the operation sequence information.

[Prediction result display phase (step S17)]
The prediction result output unit 17 displays the motion sequence information extracted by the motion information extraction unit 16 as a prediction result of the motion sequence information on the next rehabilitation implementation date of the target patient. The display destination is, for example, the memory 1002, the output device 1003, or another device connected via the network interface 1005.

  In the above description, an example in which the prediction model learning unit 13 learns a linear regression model as a prediction model has been mainly described. Not only this but the prediction model learning part 13 makes a pair with the attribute data of a prediction object patient by using as a learning data a pair of the attribute data of an arbitrary patient and the performance value of a unit to be predicted such as the number of rehabilitation days and the number of rehabilitations. Other models for predicting the unit value may be learned.

  In each of the above embodiments, the functional blocks of the analysis system and the analysis apparatus have been mainly described as examples realized on the same computer apparatus. However, the analysis apparatus is not limited to this, and may be realized by being distributed on two or more physically separated apparatuses connected by wire or wirelessly.

  Further, in each of the above-described embodiments, the description has focused on an example in which each functional block of the analysis system and the analysis device is realized by a CPU that executes a computer program stored in a storage device or ROM. However, the present invention is not limited to this, and some, all, or a combination of each functional block may be realized by dedicated hardware.

  Further, in each of the above embodiments, the analysis method described with reference to each flowchart has been described. In the present invention, the operation of each functional block according to the analysis method may be stored in a storage device (storage medium) of the computer device as the computer program of the present invention. The computer program may be read and executed by the CPU of the computer apparatus. That is, as another aspect of the present invention, a program that causes at least one computer to execute the above-described method may be used, or a computer-readable recording medium that records such a program may be used. This recording medium includes a non-transitory tangible medium.

  This computer program includes a computer program that, when executed by a computer, causes the computer to perform its control method on the analyzer.

  A combination of the above two components and the expression of the present invention converted between a method, an apparatus, a system, a recording medium, a computer program, etc. is also effective as an aspect of the present invention.

  The various components of the present invention do not necessarily have to be independent of each other, and a plurality of components are formed as a single member, and a single component is formed of a plurality of members. It may be that a certain component is a part of another component, a part of a certain component overlaps with a part of another component, or the like.

  Moreover, although the several procedure is described in order in the method and computer program of this invention, the order of the description does not limit the order which performs a several procedure. For this reason, when implementing the method and computer program of this invention, the order of the several procedure can be changed in the range which does not have trouble in content.

  Furthermore, the plurality of procedures of the method and the computer program of the present invention are not limited to being executed at different timings. For this reason, another procedure may occur during the execution of a certain procedure, or some or all of the execution timing of a certain procedure and the execution timing of another procedure may overlap.

  While the present invention has been described with reference to the embodiments and examples, the present invention is not limited to the above embodiments and examples. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

  The present invention is not limited to rehabilitation, and can be suitably applied to the use of handling data relating to an action or phenomenon of an individual accompanied by a gradual change in ability or state in association with the state of change.

DESCRIPTION OF SYMBOLS 1 Analysis apparatus 11 Rehabilitation frequency prediction part 12 Attribute data generation part 13 Prediction model learning part 14 Prediction part 15 Similar patient extraction part 16 Motion information extraction part 17 Prediction result output part 100 Analysis system 101 Next stage prediction means 102 Similar object extraction means 103 Predictive observation information output means 111 Past individual information storage means 112 Target individual information storage means 201 Attribute data generation means 202 Prediction model learning means 203 Predictive means 1001 CPU
1002 Memory 1003 Output device 1004 Input device 1005 Network interface

Claims (12)

Observation history including observation information for each past rehabilitation of each patient or for each predetermined period for each of a plurality of past rehabilitations having at least a stage determined based on the same criteria as the rehabilitation performed by the target patient Past patient information storage means for storing information, progress information that is information related to the recovery state of the patient and includes at least a time-series element, and basic attribute information indicating the basic attributes of the patient;
Target patient information storage means for storing progress information that is information related to the recovery state of the target patient and includes at least a time-series element, and basic attribute information indicating the basic attributes of the target patient;
Based on the progress information and basic attribute information of a plurality of patients in the past, and the progress information and basic attribute information of the target patient, the number of rehabilitations or the number of period units required for the target patient to proceed to the next stage is predicted. Next-stage prediction means to perform,
The past patient most similar to the target patient based on the prediction result by the next-stage predicting means, the progress information and the basic attribute information of a plurality of past patients, and the progress information and the basic attribute information of the target patient Similar patient extraction means for extracting
Using the extracted past patient observation state history information, any implementation times included until the target patient proceeds to the next stage or any included until the target patient proceeds to the next stage A rehabilitation support system comprising: predicted observation information output means for outputting predicted observation information, which is observation information predicted to be observed from the target patient when the period unit of elapses. The rehabilitation support system according to claim 1, wherein the progress information includes information indicating a stage of rehabilitation performed by the patient in association with the number of rehabilitation implementation times or the information of the predetermined period unit. The next stage prediction means is
A prediction model that outputs the number of rehabilitations or the number of period units required for the arbitrary patient to proceed to the next stage from the historical information and basic attribute information of the arbitrary patient based on the historical information and basic attribute information of a plurality of patients in the past. A predictive model learning means for learning;
The rehabilitation according to claim 1, further comprising: a prediction unit that predicts the number of rehabilitations or the number of period units required until the target patient proceeds to the next stage using the prediction model learned by the prediction model learning unit Support system. The next stage predicting means is at least attribute information of the patient from the input information in a predetermined format including at least progress information and basic attribute information, and is represented by a vector composed of a plurality of predetermined elements. Including attribute data generation means for generating attribute data;
The predictive model learning means learns correspondence information between each attribute data of a plurality of past patients generated by the attribute data generating means and information on the number of rehabilitation times or the number of period units required by the patient at each stage. Learn the predictive model,
The prediction unit predicts the number of rehabilitations or the number of period units required for the target patient to proceed to the next stage, which is obtained by inputting the target patient attribute data generated by the attribute data generation unit to the prediction model. The rehabilitation support system according to claim 3. The past patient information storage means stores, for each of a plurality of past patients, clinical information that is information related to medical treatment performed on the patient,
The target patient information storage means stores clinical information, which is information related to medical care performed on the target patient, with respect to the target patient,
The next stage predicting means is based on the past patient progress information, basic attribute information and the clinical information and the target patient progress information, basic attribute information and the clinical information until the target patient proceeds to the next stage. The rehabilitation support system according to any one of claims 1 to 4, wherein the number of rehabilitation times or the number of period units is predicted. The target patient information storage means stores, for the target patient, observation history information including observation information for each rehabilitation operation so far or for each predetermined period unit,
The next stage predicting means determines that the target patient moves to the next stage based on at least the past patient's progress information, basic attribute information and observation history information, and the target patient's progress information, basic attribute information and observation history information. The rehabilitation support system according to any one of claims 1 to 5, wherein the number of rehabilitation times or the number of period units required to proceed is predicted. The predicted observation information output means is the observation information observed in the same stage as the current stage of the target patient, which is included in the extracted past history information of the patient as the predicted observation information, and is designated as the implementation time. The rehabilitation support system according to any one of claims 1 to 6, wherein observation information observed when a designated time unit has elapsed is output. An observation history including observation information for each of a plurality of past rehabilitations of the patient who have undergone rehabilitation having at least a stage determined based on the same criteria as the rehabilitation performed by the target patient, or for each predetermined period unit Past patient information storage means for storing information, progress information that is information related to the recovery state of the patient and includes at least time-series elements, and basic attribute information indicating the basic attributes of the patient, and a target Information that is accessible to target patient information storage means for storing progress information that is information related to the recovery state of the patient and that includes at least time-series elements, and basic attribute information indicating the basic attributes of the target patient The processing device
Based on the progress information and basic attribute information of a plurality of patients in the past, and the progress information and basic attribute information of the target patient, the number of rehabilitations or the number of period units required for the target patient to proceed to the next stage is predicted. And
Based on the prediction result, the progress information and the basic attribute information of a plurality of past patients, and the progress information and the basic attribute information of the target patient, a past patient most similar to the target patient is extracted,
Using the extracted past patient observation state history information, any implementation times included until the target patient proceeds to the next stage or any included until the target patient proceeds to the next stage A rehabilitation support method that outputs predictive observation information, which is observation information predicted to be observed from a target patient when a period unit of elapses. An observation history including observation information for each of a plurality of past rehabilitations of the patient who have undergone rehabilitation having at least a stage determined based on the same criteria as the rehabilitation performed by the target patient, or for each predetermined period unit Past patient information storage means for storing information, progress information that is information related to the recovery state of the patient and includes at least time-series elements, and basic attribute information indicating the basic attributes of the patient, and a target Computer capable of accessing target patient information storage means for storing progress information that is information related to a patient's recovery state and includes at least time-series elements, and basic attribute information indicating the basic attributes of the target patient In addition,
Based on the progress information and basic attribute information of a plurality of patients in the past, and the progress information and basic attribute information of the target patient, the number of rehabilitations or the number of period units required for the target patient to proceed to the next stage is predicted. Processing,
A process of extracting a past patient most similar to the target patient based on the prediction result, the progress information and the basic attribute information of a plurality of past patients, and the progress information and the basic attribute information of the target patient; Included in any implementation times included until the target patient proceeds to the next stage or until the target patient proceeds to the next stage using the extracted past observation history information of the patient A rehabilitation support program for executing a process of outputting predicted observation information which is observation information predicted to be observed from a target patient when an arbitrary unit of time has elapsed. A system for analyzing data about the actions or phenomena of an individual with a gradual change in ability or state,
For each of a plurality of past objects that have experienced an action or phenomenon having at least a stage determined based on the same criteria as the action or phenomenon of the object object that is the object to be analyzed, the action of the object or the Observation history information including observation information for each predetermined unit in the phenomenon, progress information that is information related to the ability or state of change of the individual object and includes at least time series elements, and basic attributes of the individual object Past individual information storage means for storing basic attribute information indicating
Target individual information storage for storing progress information that is information related to the ability or state of change of the target individual and includes at least time series elements, and basic attribute information indicating basic attributes of the target individual Means,
Based on the progress information and the basic attribute information of a plurality of past objects, and the progress information and the basic attribute information of the target object, the number of the predetermined units required for the target object to proceed to the next stage A next stage prediction means for predicting
Based on the prediction result by the next stage prediction means, the progress information and basic attribute information of a plurality of past objects, and the progress information and basic attribute information of the target object, the most similar to the target object Similar individual extraction means for extracting past individual items,
Using the observed past history information of the past individual object, it is predicted that the target object will be observed from the target object when any given unit included until it proceeds to the next stage. An analysis system comprising: predicted observation information output means for outputting predicted observation information that is observation information. A method of analyzing data about the behavior or phenomenon of an individual with a gradual change in ability or state,
For each of a plurality of past objects that have experienced an action or phenomenon having at least a stage determined based on the same criteria as the action or phenomenon of the object object that is the object to be analyzed, the action of the object or the Observation history information including observation information for each predetermined unit in the phenomenon, progress information that is information related to the ability or state of change of the individual object and includes at least time series elements, and basic attributes of the individual object Past attribute information storage means for storing basic attribute information indicating information, progress information that is information related to the ability or state of the object to change and includes at least a time-series element, and the target object An information processing apparatus capable of accessing the target item information storage means for storing basic attribute information indicating basic attributes of
Based on the progress information and the basic attribute information of a plurality of past objects, and the progress information and the basic attribute information of the target object, the number of the predetermined units required for the target object to proceed to the next stage Predict
Based on the prediction result, the progress information and basic attribute information of a plurality of past objects, and the progress information and basic attribute information of the target object, a past object most similar to the target object is determined. Extract and
Using the observed past history information of the past individual object, it is predicted that the target object will be observed from the target object when any given unit included until it proceeds to the next stage. An analysis method characterized by outputting predicted observation information that is observation information. A data analysis program for the actions or phenomena of an individual with a gradual change in ability or state,
For each of a plurality of past objects that have experienced an action or phenomenon having at least a stage determined based on the same criteria as the action or phenomenon of the object object that is the object to be analyzed, the action of the object or the Observation history information including observation information for each predetermined unit in the phenomenon, progress information that is information related to the ability or state of change of the individual object and includes at least time series elements, and basic attributes of the individual object Past personal information storage means for storing basic attribute information indicating, progress information that is information related to the ability or state of change of the target individual and includes at least a time-series element, and the target individual A computer accessible to the object information storage means for storing basic attribute information indicating basic attributes of
Based on the progress information and the basic attribute information of a plurality of past objects, and the progress information and the basic attribute information of the target object, the number of the predetermined units required for the target object to proceed to the next stage Process to predict,
Based on the prediction result, the progress information and basic attribute information of a plurality of past objects, and the progress information and basic attribute information of the target object, a past object most similar to the target object is determined. Processing to extract,
Using the observed past history information of the past individual object, it is predicted that the target object will be observed from the target object when any given unit included until it proceeds to the next stage. An analysis program for executing the process of outputting predicted observation information that is observation information.

Images