JP2015228202A - Determination system, determination method, and determination program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a determination system, a determination method, and a determination program capable of objectively grasping an effect of a medicine without imposing a strain on a subject.SOLUTION: The determination system is provided with: a correct information extraction unit that extracts, from digital information that includes a log of the subject who shows a sign of improvement of a symptom, correct information indicating a feature of the log relating to the improvement of the symptom; an evaluation unit that evaluates, on the basis of correct information included in other digital information that includes a log of other subject, a degree of improvement of a symptom of the other subject; and an effect estimation unit that estimates the effect of the medicine relative to the symptom according to an evaluation result obtained by the evaluation unit.

Description

  The present invention relates to a determination system, a determination method, and a determination program.

  Conventionally, one or more (eg, 2, 3, 4, 5, 6, 7, 8, or more) overexpressed miR, underexpressed miR, mRNA, gene mutation, protein, ligand, peptide, snoRNA, or Biomarkers specific to schizophrenia are known that can include any combination of these and can be used to create a biosignature specific to schizophrenia. For example, as shown in FIG. 47 of Patent Document 1, a technique is known in which diagnosis is performed by adding a biomarker to a predetermined mental illness or the like.

Special table 2013-526852 gazette

  In the prior art described in Patent Document 1, the effect of a drug can be grasped only subjectively. Moreover, in the said prior art, since a biomarker is used for the patient of the predetermined disease who is a test subject, objectivity can be ensured, but a physical and psychological burden may be put on a patient.

  Therefore, an object of the present invention is to provide a determination system, a determination method, and a determination program that can objectively grasp the effect of a medicine without imposing a burden on a subject.

  A determination system according to one aspect of the present invention is a determination system that evaluates the effect of a drug on a subject or determines a symptom in order to achieve the above-described object, and records the progress of a subject who has an indication of symptom improvement. The correct information extracting unit that extracts the correct information indicating the characteristics of the progress record related to the improvement of the symptom from the digital information including, and other information based on the correct answer information included in the other digital information including the progress record of other subjects An evaluation unit that evaluates the degree of improvement of the symptom of the subject, and an effect estimation unit that estimates the effect of the drug on the symptom according to the evaluation result of the evaluation unit.

  In the determination system according to one aspect of the present invention, the feature information extraction unit includes a feature of a progress record related to the absence of a sign of symptom improvement from digital information including a subject's progress record without a symptom improvement sign. It is also possible to extract incorrect answer information indicating.

  In the determination system according to one aspect of the present invention, digital information of a subject who has a sign of symptom improvement is stored in advance in a predetermined storage device, and the correct information extraction unit corrects the correct information from the stored digital information. Information can also be extracted.

  The determination system according to an aspect of the present invention may further include an output unit that outputs an estimation result of the effect estimation unit and / or recommendation information of the drug.

  In the determination system according to one aspect of the present invention, the digital information may include care record information, nursing record information, and / or medical record information.

  In addition, a determination method according to one embodiment of the present invention is a determination method in a determination system for evaluating the effect of a drug on a subject or determining a symptom in order to achieve the above object, and there is an indication of symptom improvement. The correct information extraction stage that extracts the correct information indicating the characteristics of the progress record related to the improvement of symptoms from the digital information including the subject's progress record, and the correct information included in the other digital information including the progress record of other subjects Based on the evaluation stage for evaluating the degree of improvement of the symptoms of other subjects, and the effect estimation stage for estimating the effect of the drug on the symptoms according to the evaluation result in the classification stage.

  In addition, a determination program according to one embodiment of the present invention is a determination program for a determination system for evaluating the effect of a drug on a subject or determining a symptom in order to achieve the above object. Included in the correct information extraction function that extracts the correct information indicating the characteristics of the progress record related to symptom improvement from the digital information including the progress record of the subject with the sign of, and other digital information including the progress record of other subjects Based on the correct answer information, an evaluation function that evaluates the degree of improvement of the symptoms of other subjects and an effect estimation function that estimates the effect of the drug on the symptoms according to the evaluation result in the evaluation function are realized.

  According to the determination system, the determination method, and the determination program according to the present invention, it is possible to provide a determination system, a determination method, and a determination program that can objectively grasp the effect of the medicine without imposing a burden on the subject.

It is a functional block diagram of the judgment system concerning this embodiment. It is a flowchart of the process in the judgment system which concerns on this Embodiment. It is another flow figure of processing in a judgment system concerning this embodiment. It is a hardware block diagram of the judgment program which concerns on this Embodiment. It is a figure which shows the change before and behind medicine administration. It is a figure of the example of application of the judgment system concerning this embodiment. It is a figure which a doctor recommends the timing of administration of a chemical | medical agent. It is a figure of the other example of application of the judgment system concerning this embodiment. It is a figure of the output by the output part which concerns on this Embodiment.

[Embodiment]
(Outline of judgment system 1)
The determination system 1 according to the present embodiment is a system that automatically evaluates, determines, or estimates the effect of a drug administered to a patient with a predetermined disease as a subject from the progress record of the patient. Specifically, the judgment system 1 uses the progress records of a small number of subjects who suffer from a predetermined disease and have shown signs of symptom improvement by administration of the drug, and whether the symptoms of other subjects have been improved by the drug. (Ie, whether the drug is effective against the disease associated with the condition), whether to administer the drug to other subjects, and / or symptoms of other subjects This is a system that automatically determines the degree of recovery.

  That is, the determination system 1 extracts digital information including a progress record of a subject who has shown signs of symptom improvement due to administration of a drug from a user terminal or server that stores information related to the progress record. Based on the extracted digital information, the determination system 1 is characterized based on characteristic information that characterizes the improvement of symptoms (this characteristic information can be prepared in advance or can be automatically prepared for each execution of processing). The presence or absence of the drug effect is determined for the subject indicated by the extracted digital information. In the present embodiment, the predetermined disease is a mental illness mainly causing a disorder in cognitive function such as schizophrenia, autism, Alzheimer's disease, or dementia, but is not limited to these examples. .

  A subject suffering from a mental illness such as schizophrenia may change the behavior (for example, the content of speech) before and after the improvement due to the improvement of the symptoms. The behavior is recorded by a doctor, a nurse, and / or a caregiver. The determination system 1 is based on data (for example, text data, audio data, image data, video data, etc.) included in a record of a subject whose symptom improvement has been recognized by a doctor or the like. It is automatically judged whether there is a sign that the symptom is improved by the drug. That is, for example, the determination system 1 objectively determines the presence or absence of the effect of the drug on the symptom improvement based on words uttered by the subject.

The progress record includes, for example, care records, nursing records (including information on the course of nursing the patient, etc., including incident reports, occurrence reports, etc.), medical records (for example, medical records by doctors (electronic medical records). Including email) and / or combinations thereof, as well as freely described items included therein. In addition, the progress record may be described by text, image, sound, moving image, and / or a combination thereof. The digital information includes, for example, care record information indicating a care record, nursing record information indicating a nursing record, or medical record information indicating a medical record. Moreover, a chemical | medical agent is a chemical | medical agent used for mental disorders, such as schizophrenia, for example. As an example of the drug, vitamin B _{6 and the} like can be mentioned.

  Furthermore, in this embodiment, the server is one or more servers, and may be configured to include a plurality of servers. For example, the server includes a server capable of storing digital information such as a mail server, a file server, or a document management server. Further, the user terminal is one or more user terminals, and can be configured to include a plurality of user terminals. For example, the user terminal includes a personal computer, a notebook computer, a tablet PC, or a mobile communication terminal such as a mobile phone.

(Details of the judgment system 1)
FIG. 1 shows an example of a functional configuration block of the determination system according to the present embodiment.

  The determination system 1 has an information storage unit 10 that stores digital information including a progress record of a medical condition of a patient as a subject, a digital information acquisition unit 12 that acquires digital information from the information storage unit 10, and improvement in symptoms is recognized. A correct answer identifying unit 14 for identifying the digital information of the subject, a correct information extracting unit 16 for extracting correct information as feature information that is information related to the improvement of the symptom from the digital information of the subject in which the improvement of the symptom is recognized, and The evaluation unit 18 that evaluates the digital information based on the correct answer information, the effect estimation unit 20 that estimates the effect of the drug according to the evaluation result of the evaluation unit 18, the estimation result of the effect estimation unit 20, and / or the drug And an output unit 22 for outputting recommendation information.

  The output unit 22 is a display device such as a display that can display digital information, correct information, and / or estimation results of the effect estimation unit 20 and recommendation information, and / or a printer that outputs the digital information to a predetermined medium. Output device. Further, the output unit 22 can output the information to be output by recording the information on a recording medium such as a magnetic recording medium or an optical recording medium.

(Information storage unit 10)
The information storage unit 10 stores digital information including a progress record of the subject's symptoms in association with a subject identifier that uniquely identifies the subject. The digital information stored in the information storage unit 10 is updated as needed in accordance with the change in the progress record. The information storage unit 10 stores digital information of a plurality of subjects. The information storage unit 10 can store a plurality of digital information of a file (eg, a text file, a document file, an electronic medical record, and / or an electronic mail) including data representing a progress record. The information storage unit 10 supplies the stored digital information to the digital information acquisition unit 12 in response to an action from the digital information acquisition unit 12. The information storage unit 10 may be connected to other components of the determination system 1 through a communication network such as the Internet or a wired or wireless network such as a LAN so as to be able to communicate with each other.

(Digital information acquisition unit 12, correct answer identification unit 14)
The digital information acquisition unit 12 acquires digital information from the information storage unit 10 in real time or at an arbitrary timing. And the correct answer identification part 14 identifies whether the test subject's progress record contained in the digital information which the digital information acquisition part 12 acquired is the content with a symptom improvement. For example, when a progress record including content with symptom improvement is included in the digital information, the correct answer identifying unit 14 associates the correct answer identifier with the digital information. On the other hand, the correct answer identifying unit 14 associates an incorrect answer identifier with the digital information when the digital information includes a progress record including content in which improvement of symptoms is not recognized.

  For example, the correct answer identifying unit 14 associates a correct answer identifier or an incorrect answer identifier with digital information in accordance with an instruction from a person who is qualified to diagnose a subject such as a doctor. In this case, the correct answer identifying unit 14 associates the qualified person identifier that uniquely identifies the qualified person with the digital information. The correct answer identifying unit 14 supplies information about the digital information associated with the qualified person identifier to the correct information extracting unit 16. The timing of associating the correct answer identifier or the incorrect answer identifier with the digital information in the correct answer identifying unit 14 may be arbitrary.

  In addition, the correct answer identifying unit 14 can automatically associate a correct answer identifier or an incorrect answer identifier with digital information. In this case, the correct answer identifying unit 14 stores, for example, weighting information indicating a weight previously associated with a predetermined morpheme (for example, a keyword) in accordance with the relationship between the morpheme and content with symptom improvement. A weighting information storage unit can be included. Then, the correct answer identifying unit 14 acquires weighting information corresponding to each of a plurality of morphemes obtained by morphological analysis of text data included in the digital information from the weighting information storage unit. The correct answer identifying unit 14 substitutes the weight corresponding to the acquired weighting information into a predetermined calculation formula, and calculates the weight of the digital information. Then, for example, the correct answer identifying unit 14 associates a correct identifier with digital information having a weight exceeding a predetermined criterion, and associates an incorrect identifier with digital information having a weight equal to or less than the reference.

(Correct answer information extraction unit 16)
The correct answer information extraction unit 16 extracts correct answer information from digital information including a progress record including the effect of a drug of a subject who has a sign of improvement in symptoms. The correct answer information may be, for example, a morpheme that appears in a progress record when there is a sign of improvement for a predetermined disease, and in particular, a predetermined ratio (for example, the number of the morpheme included in the progress record) The morpheme may appear in the progress record exceeding the ratio obtained by dividing by the total number of all morphemes included in the progress record.

  The correct information extraction unit 16 can also adjust the method of extracting correct information based on a plurality of digital information. For example, the correct answer information extraction unit 16 uses a plurality of pieces of digital information associated with correct answer identifiers, and the correct answer identifier is determined based on the number of correct information included in each piece of digital information and the number of digital information used. The most probable value of correct information included in the digital information to be associated is calculated. The most probable value is, for example, an average value of the number of pieces of correct answer information included in the digital information. And the correct information extraction part 16 extracts correct information from the digital information containing the correct information more than this average value.

  In addition, the correct answer information extraction unit 16 serves as feature information indicating the characteristics of a progress record related to the absence of a sign of symptom improvement from digital information including the progress record of a subject who has no sign of symptom improvement. Incorrect answer information can also be extracted. The incorrect answer information is, for example, a morpheme that appears in the progress record when no sign of improvement is recognized for a predetermined disease, and that appears in the progress record beyond a predetermined ratio. Further, the correct information extraction unit 16 prepares in advance, as teacher data, digital information of a subject who has a sign of improvement in symptoms and / or digital information of a subject who has no sign of improvement of symptoms (for example, a predetermined storage device) The correct answer information and / or incorrect answer information may be extracted from the teacher data. The correct answer information extraction unit 16 supplies the extracted correct answer information and / or incorrect answer information to the evaluation unit 18.

(Evaluation part 18)
The evaluation unit 18 evaluates the digital information based on the correct answer information. For example, the evaluation unit 18 evaluates the sign of improvement in the symptoms of the other subject based on the correct information included in the other digital information including the progress record of the other subject. More specifically, the evaluation unit 18 includes keywords appearing in the digital information (for example, morphemes included in the electronic medical record, partial voices extracted from voice data recording conversations between doctors and patients), and the like. The above degree can be evaluated by calculating a score from the following expression based on the weighting of the keyword. Here, the score quantifies the strength of the connection between digital information (for example, data such as nursing records and electronic medical records) and a predetermined case (for example, the effect of a drug administered to a patient). This is the value that was evaluated.

  Specifically, the evaluation unit 18 generates a keyword vector indicating whether or not a predetermined keyword is included in the digital information. The keyword vector indicates whether or not a predetermined keyword associated with the element is included in the digital information when each element of the keyword vector takes a value of “0” or “1”. Is a vector. For example, in a case where the digital information includes the keyword “good way”, the evaluation unit 18 changes the element corresponding to the “good way” in the keyword vector from “0” to “1”. Then, the evaluation unit 18 calculates the inner product of the keyword vector (vertical vector) and the weight vector (vertical vector using the weight for each keyword as an element) as in the following formula, thereby calculating the score of the digital information. S is calculated.

ここで、ｓはキーワードベクトルを表し、Ｗは重みベクトルを表す。なお、Ｔは行列・ベクトルを転置する（行と列とを入れ替える）ことを表す。

Here, s represents a keyword vector, and W represents a weight vector. T represents transposing a matrix / vector (replaces rows and columns).

  Alternatively, the evaluation unit 18 may calculate the score S according to the following formula.

ここで、ｍ_ｊは、ｊ番目のキーワードの出現頻度を表し、ｗ_ｉは、ｉ番目のキーワードの重みを表す。なお、評価部１８は、デジタル情報に含まれる第１キーワードが評価された結果（第１キーワードの重み）と、当該デジタル情報に含まれる第２キーワードが評価された結果（第２キーワードの重み）とに基づいて（すなわち、共起を考慮して）、スコアＳを算出してよい。また、評価部１８は、デジタル情報ごとに１つのスコアを算出するだけでなく、当該デジタル情報に含まれる部分データ（例えば、センテンス、段落、部分音声、動画に含まれるフレーム）ごとにスコアを算出することもできる。この場合、評価部１８は、部分データごとに算出されたスコアの最大値、平均値、及び／又は合計値を、当該デジタル情報のスコアとしてよい。

Here, m _j represents the appearance frequency of the j-th keyword, and w _i represents the weight of the i-th keyword. The evaluation unit 18 evaluates the first keyword included in the digital information (weight of the first keyword) and the result of evaluation of the second keyword included in the digital information (weight of the second keyword). The score S may be calculated based on (ie, considering co-occurrence). The evaluation unit 18 not only calculates one score for each digital information, but also calculates a score for each partial data included in the digital information (for example, a sentence, a paragraph, a partial sound, and a frame included in a moving image). You can also In this case, the evaluation unit 18 may use the maximum value, average value, and / or total value of the scores calculated for each partial data as the score of the digital information.

  Note that the correct answer identifying unit 14 can associate the correct answer identifier or the incorrect answer identifier with the digital information based on the score calculated by the evaluation unit 18. Further, the correct answer identifying unit 14 can learn the weighting of each keyword based on the result of associating the correct answer identifier or the incorrect answer identifier, and can increase or decrease the number of keywords used for identification based on the learning result. . The weighting of each keyword can be determined based on the amount of information transmitted in a specific morpheme that the keyword has. Weighting can be learned, for example, by the following formula every time the association processing is repeated, and the accuracy can be improved.

  The evaluation unit 18 supplies information indicating the evaluation result to the effect estimation unit 20.

(Effect estimation unit 20)
The effect estimation unit 20 estimates the effect on the symptom of the drug according to the evaluation result of the evaluation unit 18. Here, the effect includes, for example, the effect of the drug on the subject, signs of improvement in the subject's symptoms, necessity of medication, and / or the degree of recovery of the subject's symptoms. For example, the effect estimation unit 20 estimates that there is an effect on digital information of a subject who has a sign of improvement in symptoms, and estimates that there is no effect on digital information of a subject who has no sign of improvement. More specifically, for example, when the score calculated by the evaluation unit 18 exceeds a predetermined threshold (when a predetermined condition is met), the effect estimation unit 20 estimates that the above effect has been obtained, and exceeds it. If not, it can be estimated that the above effect was not achieved. Or the effect estimation part 20 can also output the score itself calculated by the evaluation part 18 as an estimation result.

  Moreover, the effect estimation part 20 can also produce | generate the recommendation information of the said chemical | medical agent which shows the necessity of administering a chemical | medical agent with respect to a test subject according to an evaluation result. For example, the effect estimation unit 20 generates recommendation information indicating that a predetermined drug should be administered to a subject who has no signs of improvement in symptoms. Furthermore, the effect estimation part 20 can also estimate the recovery degree of a test subject's symptom according to an evaluation result. The effect estimation unit 20 supplies information indicating the estimation result and / or recommendation information to the output unit 22.

(Output unit 22)
The output unit 22 outputs information indicating the estimation result received from the effect estimation unit 20 and / or recommendation information to the outside. The output unit 22 outputs, for example, an estimation result and / or recommendation information using text, sound, and / or an image. The output unit 22 can also supply an estimation result and / or recommendation information or the like to a predetermined information processing apparatus located at a location away from the determination system 1. For example, when the determination system 1 is installed in a remote area such as a non-medical village, the output unit 22 of the determination system 1 supplies the above information to a hospital or the like where the doctor exists. Thereby, even if there is no doctor in the place where the system is present, the determination system 1 can remotely instruct a pharmacist or nurse who stays at the place. Further, the output unit 22 can output a value of a clinical global impression scale (CGI). Further, a value of a clinical benefit response (CBR) rate (for example, a score calculated by the evaluation unit 18) may be output. The above-mentioned clinical general impression scale or CBR value may be changed according to the predetermined disease described above. By using the value of CBR by the determination system 1, the objectivity of the output result can be improved.

(Outline of judgment method)
FIG. 2 shows an example of the flow of processing in the determination system according to the embodiment of the present invention.

  First, the digital information acquisition unit 12 acquires digital information including a progress record of the first subject from the information storage unit 10. Then, the correct answer identifying unit 14 associates the digital information of the first subject with information indicating the presence / absence of information indicating symptoms of improvement (that is, correct answer identifier or incorrect answer identifier) (step 10). S ”). Next, the correct answer information extraction unit 16 extracts correct answer information characteristic of a sign that there is a symptom improvement from the digital information associated with the correct answer identifier (correct answer information extraction step: S15). In addition, the correct answer information extraction unit 16 can also extract incorrect answer information characteristic of a sign that improvement in symptoms is not recognized from digital information associated with an incorrect answer identifier (S15).

  And the evaluation part 18 acquires the digital information of a 2nd test subject via the digital information acquisition part 12 (S20). The evaluation unit 18 compares the acquired digital information of the second subject with the correct information extracted by the correct information extraction unit 16 (S25). The evaluation unit 18 evaluates the degree of improvement of the symptoms of the second subject based on the comparison result (evaluation stage: S30). The evaluation unit 18 supplies the digital information of the subject who has signs of improvement to the effect estimation unit 20.

  The effect estimation unit 20 associates the digital information received from the evaluation unit 18 with estimation result information indicating an estimation result indicating that there is a drug effect and / or recommendation information (effect estimation step: S35). Moreover, the effect estimation part 20 can also generate | occur | produce the timing information which shows the dosing timing of the chemical | medical agent with respect to a test subject. The effect estimation unit 20 supplies information indicating the estimation result to the output unit 22. The output unit 22 outputs an estimation result, recommendation information, and / or timing information that can be perceived by a user such as an intention (S40).

  The determination system 1 can also execute the following processing. First, the digital information acquisition unit 12 acquires a predetermined number of digital information from the information storage unit 10. The correct answer identifying unit 14 associates correct answer information or incorrect answer information with each of all or a part of the data included in the extracted digital information based on a predetermined criterion. Next, the evaluation unit 18 evaluates the relevance between the data (mainly, data in which correct answer information or incorrect answer information is not yet associated) and correct information or incorrect answer information. For example, the evaluation unit 18 scores each piece of data using a keyword in which weighting information corresponding to the degree of relevance with correct answer information or incorrect answer information is associated in advance. For example, the evaluation unit 18 associates a higher score with an increase in the relationship between correct answer information or incorrect answer information and data. The evaluation unit 18 scores each of the plurality of data using this weighting information.

  Then, the evaluation unit 18 determines whether or not the relevance evaluation result satisfies a predetermined criterion (for example, a value calculated by an exponential function using a score associated with data as a variable (hereinafter, “ If there is a case where “rank” exceeds a predetermined rank), the correct answer information or the incorrect answer information is related to the extracted data when the predetermined criteria are satisfied. to decide. Further, the evaluation unit 18 re-extracts a predetermined number of data from the digital information whose relevance is evaluated, and re-evaluates the relevance between the extracted data and the correct answer information or incorrect answer information. The evaluation unit 18 changes the above-described predetermined standard according to the re-evaluation result. The evaluation unit 18 repeats the data extraction, the evaluation of the relevance between the data and the correct answer information or the incorrect answer information, and the determination as to whether or not the evaluation result satisfies a predetermined standard. It is possible to improve the extraction accuracy of data having relevance.

  FIG. 3 shows another example of the flow of processing in the determination system according to the embodiment of the present invention. In the flow of FIG. 3, substantially the same processing as the flow described in FIG. 2 is executed. Therefore, a detailed description is omitted except for differences.

  The evaluation unit 18 associates correct information or incorrect information with the acquired digital information of the second subject (S27). Specifically, the evaluation unit 18 associates correct information or incorrect information with digital information in accordance with an instruction from an expert such as a doctor. In addition, the evaluation process in the evaluation unit 18 is not limited to the order in the present embodiment. For example, the evaluation process may be performed before or after administration of the drug, or after a predetermined time has elapsed after administration, and / or continuously. Can do.

  FIG. 4 shows an example of the hardware configuration of the determination program according to the embodiment of the present invention.

  The determination system 1 according to the present embodiment includes a CPU 1500, a graphic controller 1520, a random access memory (RAM), a memory 1530 such as a read-only memory (ROM) and / or a flash ROM, and a storage device that stores data. 1540, a read / write device 1545 that reads data from and / or writes data to a recording medium, an input device 1560 that inputs data, a communication interface 1550 that transmits / receives data to / from an external communication device, and a CPU 1500 A chipset 1510 that connects the graphic controller 1520, the memory 1530, the storage device 1540, the read / write device 1545, the input device 1560, and the communication interface 1550 so that they can communicate with each other; Provided.

  The chip set 1510 includes a memory 1530, a CPU 1500 that accesses the memory 1530 and executes predetermined processing, and a graphic controller 1520 that controls display on an external display device. Perform data passing. The CPU 1500 operates based on a program stored in the memory 1530 and controls each component. The graphic controller 1520 displays an image on a predetermined display device based on the image data temporarily stored on the buffer provided in the memory 1530.

  The chip set 1510 connects a storage device 1540, a read / write device 1545, and a communication interface 1550. The storage device 1540 stores programs and data used by the CPU 1500 of the determination system 1. The storage device 1540 is, for example, a flash memory. The read / write device 1545 reads the program and / or data from the storage medium storing the program and / or data, and stores the read program and / or data in the storage device 1540. For example, the read / write device 1545 acquires a predetermined program from a server on the Internet via the communication interface 1550 and stores the acquired program in the storage device 1540.

  The communication interface 1550 executes data transmission / reception with an external device via a communication network. Further, when the communication network is disconnected, the communication interface 1550 can execute data transmission / reception with an external device without going through the communication network. An input device 1560 such as a keyboard, a tablet, or a mouse is connected to the chip set 1510 via a predetermined interface.

  The determination program for the determination system 1 stored in the storage device 1540 is provided to the storage device 1540 via a communication network such as the Internet or a recording medium such as a magnetic recording medium or an optical recording medium. Then, the determination program for the determination system 1 stored in the storage device 1540 is executed by the CPU 1500.

  The determination program executed by the determination system 1 according to the present embodiment works on the CPU 1500 to change the determination system 1 into the information storage unit 10, the digital information acquisition unit 12, and the correct answer identification unit 14 described in FIGS. , The correct answer information extraction unit 16, the evaluation unit 18, the effect estimation unit 20, and the output unit 22.

(Application example of the judgment system 1)
FIG. 5 shows changes before and after drug administration.

  In FIG. 5, the score is shown in association with the trial execution code, the doctor code or the nurse code, and the flag before and after administration. The trial execution code is a code for identifying a treatment using a predetermined drug or the like, and the doctor code or the nurse code is a code for uniquely identifying the doctor or the nurse. The pre- and post-drug flags are flags indicating whether or not a drug has been dosed. “0” indicates that no drug is being dispensed and “1” indicates that a drug has been dispensed. The score is a score calculated by the correct answer identifying unit 14 of the determination system 1 according to the present embodiment. By outputting the content shown in FIG. 5 by the output unit 22, it is possible to compare scores before and after administration of a predetermined medicine. And a doctor, a nurse, etc. can objectively grasp | ascertain whether the predetermined | prescribed patient had the effect of the chemical | medical agent and the grade of the effect of a chemical | medical agent by comparing this score. For example, when the post-administration score is larger than the pre-administration score, it can be determined that there is an effect of the drug, and that the greater the increase in the score, the higher the effect of the drug (or the tendency to recover from a predetermined disease).

  FIG. 6 shows an application example of the determination system according to the present embodiment.

  The determination system 1 can use the nurse robot 24 as the output unit 22. For example, when receiving the recommendation information from the effect estimation unit 20, the nurse robot 24 outputs the content of the recommendation information 200 in a perceptible manner to the nurse or the like. As an example, the nurse robot 24 outputs the recommendation information 200 by voice.

  FIG. 7 shows an example in which a doctor recommends the timing of drug administration.

  The doctor 9 can recommend 202 the timing of administration of a predetermined medicine by adding the output result of the determination system 1 to the result of actually examining the patient. By using the determination system 1, objectivity can be added to the determination of the doctor 9.

  FIG. 8 shows another application example of the determination system according to the present embodiment.

  The determination system 1 can be applied to remote treatment. For example, the nurse 30 owns the tablet personal computer 3. The tablet PC 3 acquires the information output by the output unit 22 from the server 7 of the determination system 1 installed in the remote hospital 5 (for example, via a communication network such as the Internet or a mobile phone network). To do. And the tablet personal computer 3 outputs the information received from the output part 22 so that the nurse 30 can perceive. The nurse 30 performs a predetermined operation according to the information output from the tablet personal computer 3.

  FIG. 9 shows an example of output by the output unit according to the present embodiment.

  The output unit 22 can display a graphic on the meter on a predetermined display and indicate whether or not the subject's symptom shows a sign of improvement by the height of the meter. For example, the output unit 22 can display a meter on a predetermined display, and can display an arrow that moves clockwise according to the improvement of the subject's symptom on the meter.

(Effect of embodiment)
The determination system 1 according to the present embodiment analyzes the digital information having a progress record including the content issued by the subject, thereby estimating the effect of the drug administered to the subject, the timing of administration of the drug, and the disease The extent of recovery can be estimated. Therefore, the determination system 1 can contribute to the adjustment of the dosage of the medicine and the determination of the dosage timing based on the remarks of the subject. And since the judgment system 1 can judge the effect with respect to the test subject of a chemical | medical agent based on the information contained in a progress record, by using the judgment result by the judgment system 1 with comments, such as a doctor, objectivity is attached to a comment, such as a doctor. Can be provided. Moreover, since the determination system 1 performs a process based on the conversation between the subject and the doctor, the burden on the subject is not imposed.

[Example applied to data other than text]
The determination system 1 can also analyze data other than text. For example, when the determination system 1 analyzes speech, (1) by recognizing the speech, the content of the conversation included in the speech may be converted into characters (text), and the text may be analyzed (2 ) Audio data may be analyzed as it is.

  In the case of (1) above, the determination system 1 converts speech into text by using an arbitrary speech recognition algorithm (for example, a recognition method using a hidden Markov model), and is similar to the processing described above. Processing is performed on the text. Thereby, the determination system 1 can analyze the voice.

  In the case of (2) above, the determination system 1 extracts a partial sound (data element) included in the sound. For example, when the voice “symptom is improved” is obtained, the determination system 1 extracts partial sounds “symptom” and “improvement” from the voice, and based on the evaluation result of the partial voice, unclassified It is possible to evaluate the relationship between the voice (unknown data) and the classification information (predetermined case). In this case, the determination system 1 can classify the sound using a time series data classification algorithm (for example, a hidden Markov model, a Kalman filter, a neural network, or the like). Thereby, the determination system 1 can analyze the voice.

  Alternatively, the determination system 1 can also analyze the video (moving image). In this case, the determination system 1 can identify a person included in the frame image by extracting a frame image included in the video and using an arbitrary face recognition technique. In addition, the determination system 1 uses an arbitrary motion recognition technique (for example, a pattern matching technique may be applied), thereby allowing a partial video included in the video (of all frame images included in the video to be included). The motion (motion) of the person can be extracted from the image including a part of the image. Then, the determination system 1 can evaluate the relationship between the unclassified video (unknown data) and the classification information (predetermined case) based on the person and / or motion. Thereby, the determination system 1 can analyze the video.

  While the embodiments and examples of the present invention have been described above, the embodiments and examples described above do not limit the invention according to the claims. In addition, it should be noted that not all the combinations of features described in the embodiments and examples are essential to the means for solving the problems of the invention. Furthermore, the technical elements of the above-described embodiments and examples may be applied independently, or may be applied by being divided into a plurality of parts such as program parts and hardware parts. .

DESCRIPTION OF SYMBOLS 1 Judgment system 3 Tablet PC 5 Hospital 7 Server 9 Doctor 10 Information storage part 12 Digital information acquisition part 14 Correct answer identification part 16 Correct answer extraction part 18 Evaluation part 20 Effect estimation part 22 Output part 24 Nurse robot 30 Nurse 200 Recommendation information 202 Recommendation 1500 CPU
1510 chip set 1520 graphic controller 1530 memory 1540 storage device 1545 read / write device 1550 communication interface 1560 input device

Claims (7)

A judgment system for evaluating the effect of a drug on a subject or judging a symptom,
A correct information extraction unit for extracting correct information indicating characteristics of the progress record related to improvement of the symptom from digital information including a progress record of a subject who has a sign of improvement of the symptom; and
Based on the correct information included in other digital information including the progress records of other subjects, an evaluation unit that evaluates the degree of improvement of symptoms of the other subjects,
A determination system comprising: an effect estimation unit that estimates an effect of the drug on the symptom according to an evaluation result of the evaluation unit.   The correct answer information extraction unit extracts incorrect information indicating characteristics of the progress record related to absence of an indication of improvement of symptoms from digital information including a progress record of a subject having no indication of improvement of symptoms. Item 2. The determination system according to Item 1. The digital information of the subject who has signs of improvement of the symptoms is stored in advance in a predetermined storage device,
The determination system according to claim 1, wherein the correct information extraction unit extracts the correct information from the digital information stored in advance. The determination system according to any one of claims 1 to 3, further comprising an output unit that outputs an estimation result of the effect estimation unit and / or recommendation information of a drug.   The determination system according to claim 1, wherein the digital information includes care record information, nursing record information, and / or medical record information. A judgment method in a judgment system for evaluating the effect of a drug on a subject or judging a symptom,
A correct information extraction stage for extracting correct information indicating characteristics of the progress record related to improvement of the symptom from digital information including a progress record of a subject who has a sign of improvement of the symptom; and
Based on the correct information included in other digital information including the progress record of other subjects, an evaluation stage for evaluating the degree of improvement of symptoms of the other subjects,
A determination method including an effect estimation step of estimating an effect of the drug on the symptom according to an evaluation result in the evaluation step. A judgment program for a judgment system for evaluating the effect of a drug on a subject or judging a symptom,
On the computer,
Correct information extraction function for extracting correct information indicating characteristics of the progress record related to improvement of the symptom from digital information including a progress record of a subject who has a sign of improvement of the symptom; and
Based on the correct information included in other digital information including the progress record of other subjects, an evaluation function that evaluates the degree of improvement of symptoms of the other subjects,
A determination program for realizing an effect estimation function for estimating an effect of the drug on the symptom according to an evaluation result in the evaluation function.

Images