Medical information processing apparatus and method

Abstract

To support a medical worker to easily grasp the state of a subject.SOLUTION: A medical information processing apparatus includes an acquisition unit, a calculation unit, and a presentation unit. The acquisition unit acquires a plurality of pieces of biological information of different types for a subject. The calculation unit calculates a degree of abnormality of first biological information included in the plurality of pieces of biological information based on a correlation with second biological information other than the first biological information included in the plurality of pieces of biological information. The presentation unit presents, for each piece of second biological information, information indicating how much the correlation used to calculate the degree of abnormality deviates from the reference correlation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The embodiments disclosed in the present specification and drawings relate to a medical information processing device and a program. [Background technology]

[0002] Conventionally, there is known a technique for remotely monitoring the condition of a subject based on vital signs such as blood pressure, heart rate, etc. In such monitoring, the degree of abnormality of the subject data is calculated by comparing the data distribution of a normal case group with the subject data for each of various vital signs, and information based on the degree of abnormality is presented to a medical professional such as a doctor.

[0003] However, in clinical practice, it is rare to diagnose the condition of a subject based on the results of only one test item, and it is common to diagnose the condition of a subject by taking into account the relationship between multiple test items. Conventional technology can only determine whether or not there is an abnormality for each test item. Therefore, unless a doctor has extensive experience, he or she may not be able to understand the relationship between multiple test items and may not be able to correctly understand the condition of the subject. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6069042 Summary of the Invention [Problem to be solved by the invention]

[0005] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to assist medical professionals in easily understanding the condition of a subject. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described below can also be positioned as other problems. [Means for solving the problem]

[0006] A medical information processing apparatus according to an embodiment includes an acquisition unit, a calculation unit, and a presentation unit. The acquisition unit acquires multiple pieces of biological information of different types from a subject. The calculation unit calculates an abnormality level of first biological information included in the multiple pieces of biological information based on a correlation between the first biological information and second biological information other than the first biological information included in the multiple pieces of biological information. The presentation unit presents, for each piece of second biological information, information indicating how much the correlation used to calculate the abnormality level deviates from a reference correlation. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of a medical image processing apparatus according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a process for calculating a precision matrix according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a correlation between different types of vital data according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of normalization processing of vital data according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a process for calculating the degree of abnormality of each piece of vital data according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a process for calculating the degree of abnormality in the correlation between different types of vital data according to the embodiment. [Figure 7] FIG. 7 is a diagram for explaining an example of a process for generating finding information according to the embodiment. [Figure 8] FIG. 8 is a diagram for explaining an example of a process for generating cause information and intervention candidate information according to the embodiment. [Figure 9] FIG. 9 is a diagram for explaining an example of the process of generating cause information and intervention candidate information according to the embodiment. [Figure 10]FIG. 10 is a diagram illustrating an example of a process for presenting the degree of abnormality in the correlation between different types of vital data according to the embodiment. [Figure 11] FIG. 11 is a flowchart showing an example of processing performed by the medical image processing apparatus according to the embodiment. [Figure 12] FIG. 12 is a diagram for explaining an example of a process for presenting the degree of abnormality in the correlation between different types of vital data according to the first modification. [Figure 13] FIG. 13 is a diagram for explaining an example of a process for presenting the degree of abnormality in the correlation between different types of vital data according to the first modification. [Figure 14] FIG. 14 is a diagram for explaining an example of a process for presenting the degree of abnormality in the correlation between different types of vital data according to the first modification. DETAILED DESCRIPTION OF THE INVENTION

[0008] Fig. 1 is a block diagram showing an example of the configuration of a medical information processing device 100 according to an embodiment. Fig. 1 shows an example of a diagnosis support system 1 including the medical information processing device 100. For example, as shown in Fig. 1, the diagnosis support system 1 includes the medical information processing device 100, a subject device 200, and a doctor device 300, and each device is connected to each other via a network 400 so as to be able to communicate with each other.

[0009] In the diagnostic support system 1 shown in FIG. 1, a single subject device 200 and a single doctor device 300 are shown, but multiple subject devices 200 and multiple doctor devices 300 may be connected to the network 400.

[0010] 1 shows only the medical information processing device 100, the subject device 200, and the doctor device 300, but various other devices and systems may also be connected to the network 400. For example, the diagnosis support system 1 may also be a system in which a data storage device that stores various data on subjects is connected to the network 400.

[0011] The subject device 200 includes a vital data acquisition device 21 and a terminal device 22, and is operated by a subject (patient). The vital data acquisition device 21 and the terminal device 22 are connected to each other so that they can communicate with each other via short-range wireless communication or the like.

[0012] The vital data acquisition device 21 has various sensors, acquires vital data of the subject, and transmits it to the terminal device 22. For example, the vital data acquisition device 21 acquires vital data such as heart rate, pulse, blood pressure, electrocardiogram, respiratory condition, exercise status (number of steps, time, etc.), body temperature, and blood oxygen saturation, and transmits it to the terminal device 22.

[0013] The vital data acquisition device 21 is realized by, for example, a wearable device, a biosensor, a non-contact sensor, etc. The wearable device includes, for example, a wristwatch type, a pair of glasses type, a ring type, a shoe type, a pocket type, a pendant type, a diaper type, an electroencephalograph type, etc. The biosensor includes, for example, a simple blood glucose meter, an antigen-antibody test device (simple urine test device), etc. The non-contact sensor includes, for example, a millimeter-wave radar, etc.

[0014] Note that, depending on the type of vital data, vital data acquisition device 21 may change the timing of transmitting the vital data to terminal device 22. For example, vital data acquisition device 21 may transmit the measurement results to terminal device 22 in real time for data that can be measured continuously, such as heart rate.

[0015] Furthermore, for example, for vital signs that are difficult to measure in real time, such as blood pressure, the vital data acquisition device 21 may measure the subject's vital signs at a predetermined time and transmit the measurement results to the terminal device 22 each time the measurement results are output.

[0016] The terminal device 22 is a device operated by the subject. The terminal device 22 transmits the vital data of the subject received from the vital data acquisition device 21 to the medical information processing device 100. The terminal device 22 may display the various information received from the medical information processing device 100 on its own display or output it as audio information.

[0017] The terminal device 22 also accepts various operations via its own input interface. For example, the terminal device 22 can accept input operations from the subject regarding information on their own behavior, information on their psychological state, and the like, and transmit the information to the medical information processing device 100. The terminal device 22 can be realized by, for example, a PC, a tablet PC, a PDA, a mobile phone (smartphone, etc.), or the like.

[0018] In this embodiment, a case will be described in which the terminal device 22 transmits the vital data acquired by the vital data acquisition device 21 to the medical information processing device 100, but the embodiment is not limited to this. For example, the vital data acquisition device 21 may have a communication function with the medical information processing device 100, and the vital data acquisition device 21 may communicate with the medical information processing device 100.

[0019] The doctor's device 300 is composed of a terminal device 31 and is operated by a doctor who examines a subject. The doctor's device 300 may also be an apparatus that can be operated by medical professionals other than doctors. In this case, the information that can be viewed and the operations that can be performed may be determined according to the type of occupation of the medical professional.

[0020] The terminal device 31 is a device operated by a doctor. The terminal device 31 receives various information indicating the condition of the subject from the medical information processing device 100, and displays the various information received from the medical information processing device 100 on its own display or outputs it as audio information.

[0021] The terminal device 31 also accepts various operations via its own input interface. For example, the terminal device 31 accepts various operation inputs from a doctor and transmits them to the medical information processing device 100. The terminal device 31 is realized by, for example, a PC, a tablet PC, a PDA, a mobile phone (smartphone, etc.), etc.

[0022] The medical information processing device 100 is a device operated by an administrator of the diagnosis support system 1, and executes various processes to support doctors in diagnosing subjects. Specifically, the medical information processing device 100 presents information indicating abnormalities in the correlation between the vital data of the subjects based on multiple vital data acquired by the vital data acquisition device 21.

[0023] 1, the medical information processing device 100 includes a communication interface 11, an input interface 12, a display 13, a memory circuitry 14, and a processing circuitry 15. For example, the medical information processing device 100 is realized by a computer device such as a PC, a workstation, or a server.

[0024] The communication interface 11 controls the transmission and communication of various data sent and received between the medical information processing device 100 and each device connected via the network 400 .

[0025] Specifically, the communication interface 11 is connected to the processing circuit 15, and transmits data received from each device on the network 400 to the processing circuit 15, or transmits data received from the processing circuit 15 to each device on the network 400. For example, the communication interface 11 is realized by a network card, a network adapter, a NIC (Network Interface Controller), or the like.

[0026] The input interface 12 receives input operations of various instructions and information from an operator. Specifically, the input interface 12 is connected to the processing circuitry 15, converts the input operations received from the operator into electrical signals, and transmits the electrical signals to the processing circuitry 15.

[0027] For example, the input interface 12 may be realized by a trackball, a switch button, a mouse, a keyboard, a touchpad that performs input operations by touching the operation surface, a touchscreen that integrates a display screen and a touchpad, a non-contact input interface that uses an optical sensor, and a voice input interface.

[0028] In this specification, the input interface 12 is not limited to an interface having physical operation components such as a mouse, a keyboard, etc. For example, an example of the input interface 12 also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and transmits this electrical signal to a control circuit.

[0029] The display 13 displays various types of information and data. Specifically, the display 13 is connected to the processing circuit 15 and displays various types of information and data received from the processing circuit 15. For example, the display 13 is realized by a liquid crystal display, a CRT (Cathode Ray Tube) display, a touch panel, or the like.

[0030] The memory circuitry 14 stores various data, various programs, etc. For example, the memory circuitry 14 stores a generative model 141 and a clinical guideline 142. The generative model 141 and the clinical guideline 142 will be described later. Specifically, the memory circuitry 14 is connected to the processing circuitry 15, and stores data received from the processing circuitry 15, or reads out stored data and transmits it to the processing circuitry 15.

[0031] For example, the memory circuitry 14 is realized by a semiconductor memory element such as a read-only memory (ROM), a random access memory (RAM), or a flash memory, or a hard disk drive (HDD), a solid state drive (SSD), an optical disk, etc. The memory circuitry 14 may be realized by a cloud computer connected to the medical information processing device 100 via a network 400.

[0032] The processing circuitry 15 comprehensively controls the medical information processing device 100. Specifically, the processing circuitry 15 executes various processes to assist doctors in diagnosing subjects. For example, the processing circuitry 15 controls data exchange with devices on the network 400, data storage in the memory circuitry 14, various processes using data, and the like.

[0033] For example, as shown in FIG. 1, in this embodiment, the processing circuitry 15 executes an acquisition function 151, a calculation function 152, an analysis function 153, and a presentation function 154. Here, the acquisition function 151 is an example of an acquisition unit. The calculation function 152 is an example of a calculation unit. The analysis function 153 is an example of a first generation unit, a second generation unit, and a third generation unit. The presentation function 154 is an example of a presentation unit.

[0034] The acquisition function 151 acquires different types of vital data (measured values ​​of vital signs) for the subject. The vital data is an example of biological information. For example, the acquisition function 151 acquires the vital data periodically acquired by the vital data acquisition device 21 from the terminal device 22 of the subject device 200.

[0035] The calculation function 152 calculates the abnormality level of first vital data included in multiple vital data of different types based on the correlation with vital data other than the first vital data. The first vital data is an example of first biological information. Furthermore, the vital data other than the first vital data is an example of second biological information.

[0036] For example, the calculation function 152 calculates the degree of abnormality of each piece of vital data (first vital data) acquired by the acquisition function 151, and the degree of abnormality of the correlation between different types of vital data.

[0037] Specifically, the calculation function 152 collects different types of vital data from multiple subjects whose vital data are within normal ranges, and calculates the degree of abnormality of each vital data of the subject to be diagnosed based on the collected vital data.

[0038] As an example, the calculation function 152 calculates the degree of abnormality of each vital data item using the following equation (1).

[0039]

number

[0040] Here, Λ represents the precision matrix, x represents the normalized value of each vital data, and i and j represent the type of vital data. The precision matrix represents the direct dependency (correlation) between different types of vital data, and can be calculated using the following formula (2).

[0041]

number

[0042] Here, Σ represents a variance-covariance matrix, and includes information representing the variance of each vital data item and the correlation between vital data items.

[0043] In this embodiment, the calculation function 152 calculates Λ from multiple different types of vital data collected from multiple subjects whose vital data are each within a normal range. The calculation function 152 also derives correlations between different types of vital data from the calculation result of Λ.

[0044] Here, Fig. 2 is a diagram for explaining an example of the process of calculating the precision matrix. Fig. 2 shows an example in which Λ is calculated from data on body weight, body fat percentage, and systolic blood pressure collected from multiple subjects whose vital data are within the normal range.

[0045] 2 includes information representing the variability of each of the data for body weight, body fat percentage, and systolic blood pressure, the correlation between body weight and body fat percentage, the correlation between body weight and systolic blood pressure, and the correlation between body fat percentage and systolic blood pressure. Calculation function 152 derives the correlation between body weight, body fat percentage, and systolic blood pressure from the calculation result of Λ.

[0046] Here, Fig. 3 is a diagram illustrating an example of the correlation between different types of vital data. i,j <0 indicates a positive correlation, Λ i,j Since >0 indicates a negative correlation, the calculation function 152 can derive, from the calculation result of Λ in Figure 2, the following shown in Figure 3: "As weight increases, body fat percentage also increases (correlation a)," "As body fat percentage increases, systolic blood pressure also increases (correlation b)," and "There is no correlation between weight and systolic blood pressure (correlation c)."

[0047] Furthermore, the calculation function 152 performs a process of normalizing the measurement values ​​of each vital sign of the subject to calculate each vital data of the subject. For example, the calculation function 152 converts different types of vital data collected from multiple subjects into data with an average of 0 and a variance of 1. Note that the above is an example of a method for normalizing different types of vital data, and the normalization method is not limited to the above.

[0048] Here, Fig. 4 is a diagram illustrating an example of normalization processing of vital data. In the example of Fig. 4, the weight, body fat percentage, and systolic blood pressure of the subject are normalized. The upper part of Fig. 4 shows the weight, body fat percentage, and systolic blood pressure of the subject before normalization. In this case, the weight of the subject is 70 kg, the body fat percentage is 12%, and the systolic blood pressure is 90 mmHg.

[0049] In the example of Figure 4, the calculation function 152 normalizes the weight, body fat percentage, and systolic blood pressure of the target subject by converting multiple different types of vital data collected from multiple subjects into data with a mean of 0 and a variance of 1.

[0050] In the example of Fig. 4, the normalized values ​​of the weight, body fat percentage, and systolic blood pressure of the subject are weight 5, body fat percentage -2, and systolic blood pressure 0. In the example of Fig. 4, since 0 is the average, it can be seen that the subject is heavy in weight, has a low body fat percentage, and has average systolic blood pressure.

[0051] After normalizing each vital data of the target subject, the calculation function 152 calculates the degree of abnormality of each vital data by substituting the value of each normalized vital data of the target subject into the above-mentioned formula (1).

[0052] FIG. 5 is a diagram illustrating an example of a process for calculating the degree of abnormality of each vital data. As shown in equation (1), the value in the parentheses on the right side of equation (1) has the greatest influence on the calculation of the degree of abnormality of each vital data. This can also be said as the higher the absolute value of the value in the parentheses on the right side of equation (1), the higher the degree of abnormality of each vital data. For this reason, in the example of FIG. 5, for the sake of convenience, only the calculation of the value in the parentheses on the right side of equation (1) will be explained.

[0053] In the example of Figure 5, the value in the () on the right side of equation (1) can be calculated by finding Λx, which is the product of matrix x indicating normalized values ​​of the body weight, body fat percentage, and systolic blood pressure of the subject and precision matrix Λ. In the example of Figure 5, the Λx value for body weight is 10.5, the Λx value for body fat percentage is -13.0, and the Λx value for systolic blood pressure is 4.0. In the example of Figure 5, the large absolute values ​​of the Λx values ​​for body weight and body fat percentage indicate a high degree of abnormality in body weight and body fat percentage.

[0054] In this embodiment, after calculating the degree of abnormality of each vital data of the target subject, if there is an abnormality in at least one of the vital data, the calculation function 152 calculates the degree of abnormality in the correlation between different types of vital data. For example, if the calculated degree of abnormality of each vital data is equal to or greater than a threshold, the calculation function 152 calculates the degree of abnormality in the correlation between different types of vital data.

[0055] After calculating the degree of abnormality of each vital data of the target subject, the calculation function 152 may automatically calculate the degree of abnormality of the correlation between different types of vital data. Furthermore, the calculation function 152 may calculate the degree of abnormality of the correlation between different types of vital data when instructed by the user.

[0056] As an example, the calculation function 152 calculates the normalized value of each vital sign measurement value and the Λ i,j Based on the calculation results of (a) and (b), the degree of abnormality in the correlation between different types of vital data is calculated by quantifying the abnormality in the correlation between different types of vital data.

[0057] 6 is a diagram for explaining an example of a process for calculating the degree of abnormality of the correlation between different types of vital data. In the example of FIG. 6, the degree of abnormality of vital data i of a subject is expressed as {{1}}x i +《2》x j +《3》x k As shown in Figure 6, it can be said that the degree of abnormality of vital sign i is calculated using the correlation between vital sign i and vital sign j of the target subject, and the correlation between vital sign i and vital sign k of the target subject.

[0058] In the above formula, {2} x j +《3》x k In an ideal case (when there are no abnormalities in vital signs), i represents the term that makes 0. Therefore, 《2》 and 《3》 are 《1》 x i This can be said to represent the influence on

[0059] The stronger the correlation between vital j (or vital k) and vital i, the greater the value of 2 x j (or {3} x k ) is《1》x i Therefore, the effect on 《1》x i The influence on x i and x j (or x k ) can also be rephrased as the strength of correlation with

[0060] From this, for example, the calculation function 152 can calculate x i and x j The strength of correlation with x i and x k Considering the strength of correlation with i becomes 0) {2} x j +《3》x k And the actually calculated {2} x j +《3》x k By calculating the difference between these, it is possible to quantify abnormalities in the correlation between different types of vital data.

[0061] Specifically, the calculation function 152 can calculate the degree of abnormality in the correlation between different types of vital data using the following equation (3) or (4).

[0062]

number

[0063]

number

[0064] The above equation (3) is Λ i,j < 0, and x i If increases, x j Also, the above equation (4) shows that Λ i,j > 0, and x i If increases, x jindicates a decrease.

[0065] For example, Λ i,j < 0 and x i and x j There is a perfect positive correlation between i,j =-1), then x i and x j Since x is normalized, i and x j If there is no abnormality in the correlation between x i If x increases by 1, j should also increase by 1.

[0066] In such a case, the actual x i and x j The normalized value of the measurement is x i increased by 5, while x j is assumed to have increased by 4. In this case, x i and x j The abnormality of the correlation between |-1|×(5-4)=1.

[0067] Also, for example, Λ i,j < 0 and x i and x j and are almost unrelated (Λ i,j =-0.01), then x i x when increases by 1 j The increase in can be any value.

[0068] In such a case, the actual x i and x j The normalized value of the measurement is x i increased by 5, while x j is assumed to have increased by 2. In this case, x i and x j The abnormality of the correlation between |-0.01|×(5-2)=0.03.

[0069] Thus, x i and x j Even if the difference between x and x becomes large,i and x j If the correlation coefficient with is small, x i and x j The abnormality of the correlation between x and i and x j If the correlation coefficient with is large, x i and x j Even if the difference between x and i and x j The degree of abnormality in the correlation between

[0070] The above-described methods for calculating the degree of abnormality of each vital data and the method for calculating the degree of abnormality of the correlation between different types of vital data are merely examples, and the methods for calculating the degree of abnormality of each vital data and the method for calculating the degree of abnormality of the correlation between different types of vital data are not limited to these. Any method may be used as long as it is capable of calculating an index representing the degree of abnormality of each vital data and an index representing the degree of abnormality of the correlation between different types of vital data.

[0071] Continuing the explanation, returning to Fig. 1, the analysis function 153 analyzes the calculation results of the degree of abnormality of each vital data and the calculation results of the degree of abnormality of the correlation between different types of vital data.

[0072] For example, the analysis function 153 generates finding information representing findings derived from the degree of abnormality of each vital data and the degree of abnormality of the correlation between different types of vital data. As an example, the analysis function 153 generates the finding information based on the calculation process and results of the degree of abnormality of each vital data and the degree of abnormality of the correlation between different types of vital data, and a template representing the finding.

[0073] Here, Fig. 7 is a diagram for explaining an example of the generation process of finding information. In the example of Fig. 7, the fixed phrase FP is "(A) is (B), whereas (C) is (D)." For example, the fixed phrase FP is stored in the memory circuitry 14 or the like. In the example of Fig. 7, the analysis function 153 generates finding information by filling in the above (A) to (D) based on the calculation results of the abnormality degree of each vital data and the abnormality degree of the correlation between different types of vital data.

[0074] In the example of FIG. 7, the analysis function 153 derives that "the degree of abnormality in body weight and body fat percentage is high" from the calculated degree of abnormality in each of the body weight, body fat percentage, and systolic blood pressure of the subject.

[0075] In addition, the analysis function 153 derives the correlation between weight and body fat percentage, that is, "if weight increases, body fat percentage also increases," from the calculation result of Λ, which appears in the process of calculating the abnormality level of each vital data.

[0076] Furthermore, the analysis function 153 derives that the subject is "heavy-weight and low-body fat percentage" from the normalized measurements of the subject's weight, body fat percentage, and systolic blood pressure that appear in the process of calculating the degree of abnormality of each vital data.

[0077] The analysis function 153 fills in (A) to (D) of the template FP from the above information obtained by analyzing the calculation process and results of the abnormality of the correlation between different types of vital data, and generates the finding information, "(Body fat percentage) is (low) compared to (weight) being (heavy)."

[0078] It is also possible to add a sentence such as "(symptoms) were observed" to the template. In this case, the analysis function 153 may refer to the electronic medical record of the subject and fill in the blank, such as "(worsening of heart failure) was observed." This allows the analysis function 153 to generate finding information including information indicating the symptoms of the subject.

[0079] Furthermore, for example, the analysis function 153 generates, based on the generated finding information, cause information indicating the cause of an abnormality in the correlation between different types of vital data and intervention candidate information indicating candidates for intervention to reduce the abnormality in the correlation. As an example, the analysis function 153 generates the cause information and the intervention candidate information using the generation model 141 and the clinical guideline 142 stored in the memory circuitry 14.

[0080] Here, the generative model 141 of this embodiment is a model that generates cause information and intervention candidate information. For example, the generative model 141 is a large-scale language model (hereinafter also referred to as LLM (Large Language Model)).

[0081] LLM is an AI model in the field of natural language processing that has been pre-trained on a large corpus. For example, when a question or instruction is input as a sentence (prompt), the LLM is designed to generate and output a response that is in line with the meaning of the input sentence.

[0082] The clinical practice guidelines 142 represent guidelines summarizing information on the basis and procedures of medical practice such as disease prevention, diagnosis, treatment, and prognosis prediction. The clinical practice guidelines 142 may be stored in the storage circuitry 14 for each type of disease. The generative model 141 and the clinical practice guidelines 142 may be stored in an external server or the like different from the medical information processing device 100.

[0083] Here, the finding information, the cause information, and the intervention candidate information can be said to be information that supports a doctor in diagnosing a target subject. Therefore, in the following description, the finding information, the cause information, and the intervention candidate information will also be referred to as diagnostic support information.

[0084] An example of the process of generating cause information and intervention candidate information by the analysis function 153 will be described below with reference to Fig. 8 and Fig. 9. Fig. 8 and Fig. 9 are diagrams for explaining an example of the process of generating cause information and intervention candidate information.

[0085] As an example, the analysis function 153 extracts an input word ID1 that will be the basis of a sentence to be input to the generative model 141 from the generated finding information of the target subject, the electronic medical record of the target subject, etc. The analysis function 153 may also perform processing such as converting the expression of the word extracted as the input word ID1 into a general expression using a known natural language processing technique or the like.

[0086] In the example of Figure 8, the analysis function 153 extracts "heart failure", which indicates the disease from which the target subject is suffering, and "weight gain" and "decrease in body fat percentage", which indicate abnormalities in the vital data of the target subject, from the generated finding information, etc.

[0087] 8, the analysis function 153 refers to the clinical guidelines 142 and performs a keyword search, a vector search, etc. for the input word ID1 ("heart failure," "weight gain," and "reduction in body fat percentage"). Based on the search results, the analysis function 153 generates an input sentence to be input to the generative model 141 to generate cause information and intervention candidate information.

[0088] As described above, by searching the clinical guidelines 142 and generating sentences to be input to the generative model 141 based on the search results, it is possible to prevent the generative model 141 from generating cause information and intervention candidate information whose content deviates from the clinical guidelines 142.

[0089] The analysis function 153 inputs the generated input sentence into the generative model 141. The analysis function 153 generates the response sentence output from the generative model 141 as cause information and intervention candidate information.

[0090] In the example of Figure 8, the generative model 141 generates and outputs the output sentence OD, which reads, "The cause is thought to be a decrease in the left ventricular output, which has caused blood to stagnate in the body, resulting in edema. As a possible intervention, in the past, similar cases have been treated with intravenous injection (injecting a diuretic, which removes excess fluid from the body, into the vein)."

[0091] In the above case, the analysis function 153 generates cause information, based on the output sentence OD, such as "The cause is thought to be a decrease in the left ventricular output, which has caused blood to stagnate in the body, resulting in edema." Similarly, the analysis function 153 generates intervention candidate information, such as "In the past, similar cases have been treated with intravenous injections (intravenous injections of diuretics, which remove excess fluid from the body) as an intervention candidate."

[0092] In the example of Figure 8, the analysis function 153 extracts input word ID1, but as shown in Figure 9, input sentence ID2 may be generated based on the generated finding information of the target subject, the target subject's electronic medical record, etc.

[0093] In the above case, the analysis function 153 may refer to the clinical guidelines 142 and perform a keyword search, vector search, etc. for the input text ID2, or may input the generated input text ID2 directly into the generative model 141 without referring to the clinical guidelines 142.

[0094] Additionally, the analysis function 153 may generate cause information and candidate intervention information using only the clinical guidelines 142 .

[0095] For example, the analysis function 153 may perform a keyword search or vector search on the input word ID1, and may highlight a portion of the search results that can be estimated to represent the cause of the abnormality in the text data stored as the clinical guideline 142 and present it to a user such as a doctor. Similarly, the analysis function 153 may highlight a portion that can be estimated to represent a candidate for intervention to reduce the abnormality in a manner different from the above and present it to a user.

[0096] The presentation function 154 presents the degree of abnormality in the correlation between different types of vital data for each type of vital data other than the first vital data.

[0097] Here, the degree of abnormality in the correlation between different types of vital data can be said to represent the degree to which the correlation between different types of vital data derived based on each vital data of the target subject deviates from the reference correlation, which is the correlation between different types of vital data derived based on multiple vital data of different types collected from multiple subjects whose vital data are each within the normal range.

[0098] The calculation function 152 uses Λ to calculate the degree of abnormality of each vital data, and Λ contains information that indicates the correlation between different types of vital data. Furthermore, in the process of calculating the degree of abnormality of each vital data, the calculation function 152 performs a calculation in which Λ is multiplied by a normalized value of the measurement value of each vital sign of the subject.

[0099] Therefore, it can be said that the calculation function 152 calculates the degree of abnormality of each vital data by using the correlation between different types of vital data of the subject.

[0100] Therefore, the degree of abnormality in the correlation between different types of vital data can be said to be an example of information indicating how much the correlation used to calculate the degree of abnormality in the first biological information deviates from the standard correlation.

[0101] For example, when at least one of the abnormality levels of each vital data is above a threshold, the presentation function 154 presents the abnormality level of each vital data and the abnormality level of the correlation between different types of vital data to the user by displaying them as a vertical bar graph on a display or the like (display unit) of the terminal device 31 of the doctor's device 300.

[0102] Furthermore, for example, when at least one of the abnormalities of each vital data exceeds a threshold, the presentation function 154 notifies the user of a warning (alert) according to the disease the subject is suffering from and the type of vital data that exceeds the threshold.

[0103] As an example, when the degree of abnormality in the heart rate of a subject with heart failure exceeds a threshold, the presentation function 154 displays a warning message on the display unit of the terminal device 31 of the medical device 300 to warn the user that the subject's heart failure may have worsened.

[0104] The presentation function 154 may notify the user of a warning and may also notify the target subject of a similar warning via the terminal device 22 of the subject device 200 of the target subject.

[0105] FIG. 10 is a diagram illustrating an example of a process for presenting the degree of abnormality in the correlation between different types of vital data.

[0106] In the example of Figure 10, the screen 131 presenting the degree of abnormality of vital data has the following screen configuration: patient information display field PI, medical department display field CD, alert display field AL, date display field DF, selection range RS, outpatient icon IV (IV1, IV2), imaging test icon IT, doctor entry icon DN, remote measurement icon RM (RM1 to RM4), abnormality degree tab TB1, imaging test tab TB2, correlation abnormality tab TB3, abnormality degree graph SD1, selection box SL, vitals tab VT, correlation abnormality degree graph CD1, and diagnostic support information display field SI.

[0107] The patient information display field PI is a field that displays patient information about the subject. In the example of Fig. 10, the subject's name (Shinkou Taro), sex (male), date of birth (YYYY / MM / DD), and age (AA years old) are displayed.

[0108] The medical department display field CD is a display field that displays the medical department of the target subject. In the example of Fig. 10, "cardiology" is displayed. Note that if the target subject is visiting multiple medical departments, the user may be able to select a medical department by clicking the medical department display field CD, for example.

[0109] The alert display field AL is a display field that displays alerts. For example, the alert display field AL displays the content of the alert and the date and time when the most recent alert was issued (last execution date and time). In the example of FIG. 10, the alert display field AL displays that a "heart failure worsening alert" was most recently issued on YYYY / MM / DD HH:MM.

[0110] The date display field DF is a display field that displays the date on which a medical event related to the subject occurred or the date on which the medical event is scheduled to occur. The selection range RS represents the range of dates selected for viewing medical events. For example, information about medical events within the selection range RS is displayed at the bottom of the presentation screen 131.

[0111] The outpatient icons IV (IV1, IV2) are icons that indicate that outpatient treatment for the target subject has been performed or is scheduled to be performed. In the example of FIG. 10, the outpatient icon IV1 indicates that outpatient treatment for the target subject was performed on 1 / 26 (Wed). Furthermore, the outpatient icon IV2 indicates that outpatient treatment for the target subject was performed on 3 / 23 (Wed).

[0112] The imaging test icon IT is an icon that indicates that an imaging test has been performed or is scheduled to be performed on the target subject. In the example of Fig. 10, the imaging test icon IT indicates that an imaging test was performed on the target subject on 1 / 26 (Wed).

[0113] The doctor entry icon DN is an icon that indicates that a doctor has made some entry in the electronic medical record of the subject. In the example of Figure 10, the imaging examination icon IT indicates that a doctor has made some entry in the electronic medical record of the subject on Wednesday, January 26th.

[0114] The remote measurement icon RM is an icon indicating that vital data has been transmitted or will be transmitted from the subject device 200 of the target subject.

[0115] 10, the remote measurement icon RM1 indicates that vital data was transmitted from the subject device 200 of the target subject between January 26 (Wed) and February 9 (Wed). The remote measurement icon RM2 indicates that vital data was transmitted from the subject device 200 of the target subject between February 9 (Wed) and February 23 (Wed).

[0116] Further, the remote measurement icon RM3 indicates that vital data was transmitted from the subject device 200 of the target subject between Wednesday, February 23rd and Wednesday, March 9th. Further, the remote measurement icon RM3 indicates that vital data was transmitted from the subject device 200 of the target subject between Wednesday, March 9th and Wednesday, March 23rd.

[0117] The abnormality level tab TB1 is a tab for displaying information about the abnormality level of each vital data within the selected range RS. For example, when the user clicks on the abnormality level tab TB1, an abnormality level graph SD1 is displayed. The abnormality level graph SD1 will be described later.

[0118] The image examination tab TB2 is a tab for displaying the results of the image examination within the selected range RS.

[0119] The correlation anomaly tab TB3 is a tab for displaying information about the degree of anomaly between different types of vital data. For example, when the user clicks on the correlation anomaly tab TB2, a selection box SL, a vital tab VT, a correlation anomaly graph CD1, and a diagnostic support information display field SI are displayed. The selection box SL, the vital tab VT, the correlation anomaly graph CD1, and the diagnostic support information display field SI will be described later.

[0120] The abnormality level graph SD1 is a vertical bar graph showing the degree of abnormality of each vital data calculated by the calculation function 152. In the example of Fig. 10, the vertical axis shows the degree of abnormality of each vital data, and the horizontal axis shows the type of vital data. In the example of Fig. 10, the abnormality levels of body weight, body fat percentage, systolic blood pressure, diastolic blood pressure, and heart rate are shown as vertical bar graphs, indicating that the abnormality levels of body weight, body fat percentage, and heart rate are above a threshold.

[0121] The selection box SL is a selection box for selecting a type of vital data. For example, when the user clicks on the selection box SL, a list is displayed for selecting one of weight, body fat percentage, systolic blood pressure, diastolic blood pressure, and heart rate. Also, for example, when the user selects a type of vital data, a vital tab VT corresponding to the selected type of vital data is displayed.

[0122] The vitals tab VT is a tab for switching the type of vital data for which the degree of abnormality in correlation is to be displayed.

[0123] In the example of Fig. 10, a vital tab VT representing weight is displayed. For example, if the user selects body fat percentage by clicking the selection box SL in this state, a vital tab VT corresponding to the body fat percentage is additionally displayed, and the user can switch the type of vital data to be displayed between weight and body fat percentage.

[0124] The correlation abnormality degree graph CD1 is a vertical bar graph showing the degree of abnormality of the correlation between different types of vital data calculated by the calculation function 152. In the example of Fig. 10, the vertical axis represents the degree of abnormality of the correlation between the type of vital data corresponding to the vital tab VT and other types of vital data, and the horizontal axis represents the types of other vital data.

[0125] In addition, in the example of Figure 10, the degree of abnormality in the correlation between body weight and body fat percentage, the degree of abnormality in the correlation between body weight and systolic blood pressure, the degree of abnormality in the correlation between body weight and diastolic blood pressure, and the degree of abnormality in the correlation between body weight and heart rate are shown in vertical bar graphs, indicating that the degree of abnormality in the correlation between body weight and body fat percentage is above a threshold.

[0126] The diagnostic assistance information display field SI is a display field that displays the diagnostic assistance information generated by the analysis function 153.

[0127] In the example of Figure 10, the diagnostic support information display field SI displays the following as the finding information: "The patient's weight is high, but the body fat percentage is low." Also, the diagnostic support information display field SI displays the following as the cause information: "A decrease in cardiac output may have caused blood to stagnate, resulting in edema." Also, the diagnostic support information display field SI displays the following as the intervention candidate information: "Intravenous injections have been administered in similar cases in the past."

[0128] In this way, the medical information processing apparatus 100 according to this embodiment displays not only the degree of abnormality of each vital data item but also the degree of abnormality of the correlation between different types of vital data. This allows the user to easily understand the condition of the subject. Furthermore, the medical information processing apparatus 100 according to this embodiment also displays diagnostic support information. This makes it easier for the user to diagnose the subject and decide on a treatment method for the subject.

[0129] The processing circuitry 15 described above is realized by, for example, a processor. In this case, each of the processing functions described above is stored in the storage circuitry 14 in the form of a program executable by a computer. The processing circuitry 15 then reads and executes each program stored in the storage circuitry 14 to realize the function corresponding to each program. In other words, the processing circuitry 15 has each of the processing functions shown in FIG. 1 when each program is read.

[0130] The processing circuitry 15 may be configured by combining multiple independent processors, each of which executes a program to realize each processing function. The processing functions of the processing circuitry 15 may be realized by distributing or integrating them as appropriate across a single or multiple processing circuits. The processing functions of the processing circuitry 15 may also be realized by a combination of hardware and software, such as circuits.

[0131] Although the example in which the programs corresponding to the respective processing functions are stored in a single storage circuitry 14 has been described here, the embodiment is not limited to this. For example, the programs corresponding to the respective processing functions may be stored in a distributed manner in a plurality of storage circuits, and the processing circuitry 15 may read and execute each program from each storage circuit.

[0132] Some of the processing functions of the processing circuitry 15 may be realized by a cloud computer connected to the medical information processing device 100 via the network 400.

[0133] Next, a description will be given of processing executed by the medical information processing apparatus 100. Fig. 11 is a flowchart showing an example of processing executed by the medical information processing apparatus 100 according to the embodiment.

[0134] First, the acquiring function 151 acquires vital data of the target subject (step S101). For example, the acquiring function 151 acquires multiple different types of vital data periodically transmitted from the terminal device 22 of the subject device 200 of the target subject.

[0135] Next, the calculation function 152 calculates the degree of abnormality of each piece of vital data of the target subject (step S102). For example, the calculation function 152 calculates the degree of abnormality of each piece of vital data of different types acquired in step S101. The specific calculation method is as described above, and therefore will not be described again.

[0136] Next, the calculation function 152 determines whether any of the abnormality degrees of the vital data of the target subject is equal to or greater than a threshold value (step S103). For example, the calculation function 152 determines whether any of the abnormality degrees of the vital data calculated in step S102 is equal to or greater than a threshold value. If there is no abnormality degree equal to or greater than the threshold value (step S103: No), the process returns to step S101.

[0137] On the other hand, if any of the values ​​is equal to or greater than the threshold (step S103: Yes), the calculation function 152 calculates the degree of abnormality in the correlation between different types of vital data of the subject (step S104). The specific calculation method is as described above, and therefore will not be described here.

[0138] 11, the process of step S104 is described as a process after step S103, but the process of step S104 may be performed after step S102 and before step S103. In this case, the process of step S104 will be automatically performed after step S102, regardless of the calculation result of the degree of abnormality of each vital data of the target subject.

[0139] Next, the presentation function 154 notifies the user of a warning (step S105). For example, the presentation function 154 executes a process of issuing an alert to the user, the alert content depending on the type of vital data whose abnormality level is equal to or greater than a threshold, the disease that the target subject is suffering from, etc. The process of step S105 may be performed after the process of step S103 described above and before the process of step S104, or may be performed in parallel with the process of step S104.

[0140] Next, the analysis function 153 determines whether or not a user has issued an instruction to display medical information related to the medical treatment of the target subject (step S106). Generally, when the target subject for which a warning has been issued visits a medical institution, the user issues an instruction to display medical information for the examination of the target subject. If no instruction to display medical information has been issued (step S106: No), the process of step S106 is repeated.

[0141] On the other hand, if an instruction to display the medical information has been given (step S106: Yes), the analysis function 153 generates diagnostic assistance information (step S107). The specific generation method is as described above, and therefore will not be described again.

[0142] 11, the process of step S107 is described as a process after step S106, but the process of step S107 may be performed after the determination of Yes in step S103 and before the process of step S106. In this case, the process of step S107 may be performed before the process of step S105 or may be performed in parallel with the process of step S105.

[0143] Next, the presentation function 154 presents the abnormality level of the correlation between different types of vital data and the diagnostic assistance information to the user (step S108), and ends this process. For example, the presentation function 154 displays the presentation screen 131 shown in FIG. 10 on the display unit of the terminal device 31 of the doctor device 300.

[0144] As described above, the medical information processing device 100 according to this embodiment acquires multiple vital data of different types from a subject, calculates the degree of abnormality of a first vital data among the multiple vital data based on the correlation with other types of vital data than the first vital data, and presents the degree of abnormality of the correlation between different types of vital data for each type of vital data other than the first vital data, indicating how much the correlation used to calculate the degree of abnormality deviates from a reference correlation.

[0145] As a result, the medical information processing device 100 according to this embodiment can calculate an index that can identify abnormalities not only in a specific vital sign alone but also in consideration of the correlation between the specific vital sign and other vital signs. Furthermore, the medical information processing device 100 according to this embodiment can present to the user the degree to which the correlation between the specific vital sign derived from the vital sign data of the subject to be diagnosed and other vital signs deviates from a reference correlation (e.g., the correlation between the specific vital sign and other vital signs derived from the vital sign data of multiple subjects whose vital signs are within the normal range). By presenting such information, the user can more easily understand the condition of the subject, for example, compared to when the user is presented with information on whether or not a specific vital sign alone is abnormal. In other words, the medical information processing device 100 according to this embodiment can assist the user in easily understanding the condition of the subject.

[0146] In addition, the medical information processing device 100 according to this embodiment generates finding information representing findings based on the calculated degree of abnormality of each vital data, and displays the generated finding information together with the degree of abnormality of each vital data on the display unit or the like of the terminal device 31 of the doctor's device 300.

[0147] This allows, for example, even a user who is not an expert in the disease from which the target subject is suffering or a user with little experience to easily understand what abnormality has occurred in the target subject.

[0148] In addition, the medical information processing device 100 according to this embodiment generates cause information indicating the cause of an abnormality in each vital data, and displays the generated cause information on the display unit of the terminal device 31 of the doctor's device 300 together with the degree of abnormality in each vital data.

[0149] This allows, for example, even a user who is not an expert in the disease suffered by the target subject or a user with little experience to easily understand the cause of an abnormality that has occurred in the target subject.

[0150] In addition, the medical information processing device 100 according to this embodiment generates candidate intervention information representing candidates for intervention to reduce abnormalities occurring in the target subject, and displays the generated candidate intervention information on the display unit of the terminal device 31 of the medical device 300 together with the degree of abnormality of each vital data.

[0151] This makes it easier for a user who is not an expert in the disease suffered by the target subject or who has little experience to determine how to deal with a target subject in which an abnormality has occurred.

[0152] The above-described embodiment can be modified as needed by partially changing the configuration or function of each device included in the diagnosis support system 1. Therefore, the following describes modifications of the above-described embodiment as other embodiments. The following mainly describes differences from the above-described embodiment, and omits detailed descriptions of commonalities with the content already described. The modifications described below may be implemented individually or in appropriate combination.

[0153] (Variation 1) In the above-described embodiment, the presentation function 154 displays the degree of abnormality in the correlation between different types of vital data in a vertical bar graph. In this modified example, the degree of abnormality in the correlation between different types of vital data is displayed in a manner other than a vertical bar graph.

[0154] For example, the presentation function 154 may display the degree of abnormality in the correlation between different types of vital data in a horizontal bar graph. Fig. 12 is a diagram for explaining an example of a presentation process of the degree of abnormality in the correlation between different types of vital data according to Modification Example 1. Note that in Fig. 12, reference numerals are omitted for parts that are the same as those in Fig. 10.

[0155] In the example of FIG. 12, the presentation screen 131A has a screen configuration different from that of FIG. 10, in which an abnormality degree graph SD2 and a correlation abnormality degree graph CD2 are included.

[0156] The abnormality level graph SD2 is a horizontal bar graph showing the abnormality level of each vital data. In the example of Fig. 12, the horizontal axis represents the abnormality level of each vital data, and the vertical axis represents the type of vital data.

[0157] The correlation abnormality graph CD2 is a bar graph showing the degree of abnormality in the correlation between different types of vital data. In the example of Fig. 12, the horizontal axis represents the degree of abnormality in the correlation between the type of vital data corresponding to the vital tab VT (see Fig. 10) and other types of vital data, and the vertical axis represents the types of other vital data.

[0158] Furthermore, for example, the presentation function 154 may display the degree of abnormality in the correlation between different types of vital data in a radar chart (chart graph). Fig. 13 is a diagram for explaining an example of a presentation process of the degree of abnormality in the correlation between different types of vital data according to Modification Example 1. Note that in Fig. 13, reference numerals are omitted for parts that are the same as those in Fig. 10.

[0159] In the example of FIG. 13, the presentation screen 131B has a screen configuration different from that of FIG. 10, in which an anomaly degree graph SD3 and a correlated anomaly degree graph CD3 are included.

[0160] The abnormality degree graph SD3 is a chart graph that shows the degree of abnormality of each vital data. In the example of Fig. 13, the type of vital data is displayed on the outside of the abnormality degree graph SD3. The abnormality degree graph SD3 indicates that the degree of abnormality of each vital data increases as it moves further outward.

[0161] The correlation anomaly graph CD3 is a chart graph that shows the degree of anomaly in the correlation between different types of vital data. In the example of Fig. 13, other types of vital data are displayed outside the correlation anomaly graph CD3. The correlation anomaly graph CD3 indicates that the further outward the graph is, the higher the degree of anomaly in the correlation between the type of vital data corresponding to the vital tab VT (see Fig. 10) and the other types of vital data.

[0162] Furthermore, for example, the presentation function 154 may display the degree of abnormality in the correlation between different types of vital data in a line graph. Fig. 14 is a diagram for explaining an example of a presentation process of the degree of abnormality in the correlation between different types of vital data according to Modification Example 1. Note that in Fig. 14, reference numerals are omitted for parts that are the same as those in Fig. 10.

[0163] In the example of FIG. 14, the presentation screen 131C has a screen configuration different from that of FIG. 10, in which an abnormality degree graph SD4 and a correlation abnormality degree graph CD4 are included.

[0164] The abnormality level graph SD4 is a line graph showing the abnormality level of each vital data. In the example of Fig. 14, the vertical axis represents the abnormality level of each vital data, and the horizontal axis represents time (date).

[0165] The abnormality level graph SD4 also displays multiple line graphs. Each line graph represents a type of vital data. In the example of Fig. 14, the user can grasp the abnormality level of each vital data item over time.

[0166] The correlation abnormality graph CD4 is a line graph that shows the abnormality of the correlation between different types of vital data. In the example of Figure 14, the vertical axis represents the abnormality of the correlation between the type of vital data corresponding to the vital tab VT (see Figure 10) and other types of vital data. The horizontal axis represents time (date).

[0167] The correlation anomaly graph CD4 also displays multiple line graphs. Each line graph represents a different type of vital data. In the example of FIG. 14, the user can grasp the degree of anomaly in the correlation between different vital data over time.

[0168] 12 to 14 instead of the presentation screen 131 of Fig. 10, or may display any one of the presentation screens 131, 131A to 131C in accordance with a user instruction. Also, the presentation function 154 may present the degree of abnormality of each vital data and the degree of abnormality of the correlation between different types of vital data in a manner other than the above-mentioned presentation screens 131, 131A to 131C.

[0169] According to this modification, the degree of abnormality of each vital data of the target subject and the degree of abnormality of the correlation between different types of vital data of the target subject can be presented in a manner that is easy for the user to understand.

[0170] (Variation 2) In the above embodiment, the biometric information is vital data. In this modification, the biometric information includes information other than vital data.

[0171] For example, the biological information may include blood glucose measurements measured by a simple blood glucose meter, in which case the correlations between different types of biological information may be correlations between the blood glucose measurements and each vital data item.

[0172] As another example, the biological information may include measurement values ​​of various specimen tests (blood tests, urine tests, etc.) of the subject. In this case, the correlation between different types of biological information may be a correlation between the measurement values ​​of various specimen tests and each vital data, or a correlation between the measurement values ​​of different types of specimen tests.

[0173] According to this modification, the user can easily grasp abnormalities in the correlations between different types of biological information other than vital data.

[0174] In addition, in the above-described embodiment, an example has been described in which the acquisition unit, calculation unit, first generation unit, second generation unit, third generation unit, and presentation unit in this specification are realized by the acquisition function, calculation function, analysis function, and presentation function of a processing circuit, respectively, but the embodiment is not limited to this. For example, in addition to being realized by the acquisition function, calculation function, analysis function, and presentation function described in the embodiment, the acquisition unit, calculation unit, first generation unit, second generation unit, third generation unit, and presentation unit in this specification may also be realized by hardware only, software only, or a combination of hardware and software.

[0175] Furthermore, the term "processor" used in the description of the above-mentioned embodiments refers to circuits such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)).

[0176] Instead of storing the program in a memory circuit, the program may be directly embedded in the processor circuit. In this case, the processor realizes its function by reading and executing the program embedded in the circuit. Furthermore, each processor in this embodiment is not limited to being configured as a single circuit, but may be configured as a single processor by combining multiple independent circuits to realize its function.

[0177] Here, the assistance program executed by the processor is provided by being pre-installed in a ROM (Read Only Memory), a storage circuit, etc. Note that this assistance program may be provided by being recorded in a computer-readable, non-transitory storage medium such as a CD (Compact Disk)-ROM, a FD (Flexible Disk), a CD-R (Recordable), or a DVD (Digital Versatile Disk) in a format that can be installed or executed by these devices.

[0178] This assistance program may also be provided or distributed by being stored on a computer connected to a network such as the Internet and downloaded via the network. For example, this assistance program may be composed of modules including the above-mentioned processing functions. In actual hardware, a CPU reads and executes the medical image processing program from a storage medium such as a ROM, whereby each module is loaded into a main memory and generated on the main memory.

[0179] Furthermore, in the above-described embodiment and modified examples, the components of each device shown in the drawings are functional concepts and do not necessarily have to be physically configured as shown in the drawings. In other words, the specific form of distribution or integration of each device is not limited to that shown in the drawings, and all or part of them can be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc.

[0180] Furthermore, all or any part of the processing functions performed by each device may be realized by a CPU and a program analyzed and executed by the CPU, or may be realized as hardware using wired logic.

[0181] Furthermore, among the processes described in the above-mentioned embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method.In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified.

[0182] According to at least one of the embodiments described above, it is possible to assist medical personnel in easily understanding the condition of a subject.

[0183] Although several embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0184] 100 Medical information processing device 11 Communication Interface 12 Input Interface 13. Display 14 Memory circuit 15 Processing circuit 151 Acquisition Function 152 Calculation Function 153 Analysis function 154 Presentation function

Claims

1. an acquisition unit that acquires a plurality of different types of biological information about a subject; a calculation unit that calculates an abnormality level of first biological information included in the plurality of biological information based on a correlation between the first biological information and second biological information other than the first biological information included in the plurality of biological information; a presentation unit that presents information indicating how much the correlation used to calculate the degree of abnormality deviates from a reference correlation for each of the second biological information; A medical information processing device comprising:

2. A first generating unit that generates a finding for the abnormality degree is further provided, the presenting unit causes a display unit to display the findings together with the degree of abnormality. The medical information processing device according to claim 1 .

3. the first generating unit derives a state of the first biometric information for each type of the first biometric information and a state of the second biometric information for each type of the second biometric information based on the calculation result of the abnormality degree and the correlation used to calculate the abnormality degree, and generates the findings by filling in a template that represents the correlation between the first biometric information and the second biometric information and that can fill in the type of the first biometric information and the state of the first biometric information, and the type of the second biometric information and the state of the second biometric information. The medical information processing device according to claim 2 .

4. a second generating unit configured to generate information on a cause of the first biological information showing the degree of abnormality based on the calculation result of the degree of abnormality and the findings, the presentation unit causes the display unit to display information about the cause together with the degree of abnormality. The medical information processing device according to claim 2 .

5. a third generation unit that generates candidates for intervention to reduce the degree of abnormality based on the calculation result of the degree of abnormality and the findings, the presentation unit causes the display unit to display the intervention candidates; The medical information processing device according to claim 2 .

6. the presentation unit expresses information indicating how much the correlation used to calculate the degree of abnormality deviates from a reference correlation using at least one of a vertical bar graph, a horizontal bar graph, a radar chart, and a time-series line graph, and causes the information to be displayed on the display unit. The medical information processing device according to any one of claims 2 to 5.

7. On the computer, an acquiring step of acquiring a plurality of different types of biological information about a subject; a calculating step of calculating an abnormality level of first biological information included in the plurality of biological information based on a correlation between the first biological information and second biological information other than the first biological information included in the plurality of biological information; a presentation step of presenting information indicating how much the correlation used to calculate the degree of abnormality deviates from a reference correlation for each of the second biological information; A program that executes the following.

8. Further comprising a first generating step of generating a finding for the abnormality degree, the presenting step displays the findings together with the degree of abnormality on a display unit. The program according to claim 7.

9. The first generating step derives a state of the first biometric information for each type of the first biometric information and a state of the second biometric information for each type of the second biometric information based on the calculation result of the degree of abnormality and the correlation used to calculate the degree of abnormality, and generates the findings by filling in a template that represents the correlation between the first biometric information and the second biometric information and that can fill in the type of the first biometric information and the state of the first biometric information, and the type of the second biometric information and the state of the second biometric information. The program according to claim 8.

10. further comprising a second generating step of generating information on a cause of the first biological information showing the abnormality level, the presenting step causes the display unit to display information about the cause together with the degree of abnormality. The program according to claim 8.

11. further comprising a third generating step of generating candidates for intervention to reduce the degree of abnormality; the presenting step causes the display unit to display the intervention candidates; The program according to claim 8.

12. the presenting step represents information indicating how much the correlation used to calculate the degree of abnormality deviates from a reference correlation using at least one of a vertical bar graph, a horizontal bar graph, a radar chart, and a time-series line graph, and displays the information on the display unit; 12. The program according to any one of claims 8 to 11.

Images