Electrocardiogram evaluation device, electrocardiogram evaluation method, and program

Abstract

An electrocardiogram evaluation device (1X) mainly comprises an acquisition means (30X), a selection means (31X), and an evaluation means (33X). The acquisition means (30X) acquires electrocardiogram data pertaining to an electrocardiogram of a subject. The selection means (31X) selects, from the electrocardiogram data, induction data on induction corresponding to a disease to be examined. The evaluation means (33X) evaluates an electrocardiogram pertaining to the disease on the basis of the induction data.

Description

Technical Field

[0001] The present disclosure relates to the technical field of an electrocardiogram evaluation apparatus, an electrocardiogram evaluation method, and a storage medium for evaluating an electrocardiogram regarding the presence or absence of a disease.

Background Art

[0002] Conventionally, an apparatus for determining the presence or absence of an abnormality by analyzing a measured electrocardiogram of a subject has been known. For example, Patent Document 1 discloses an electrocardiogram analysis apparatus that analyzes an electrocardiogram waveform measured from a subject in light of a predetermined arrhythmia criterion and outputs an alarm or the like when an arrhythmia is detected.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When performing an evaluation regarding the presence or absence of a disease based on an electrocardiogram, there is a risk that the accuracy may decrease by using data of leads not related to the target disease.

[0005] In view of the above problems, one object of the present disclosure is to provide an electrocardiogram evaluation apparatus, an electrocardiogram evaluation method, and a storage medium capable of accurately performing an evaluation of an electrocardiogram of a subject regarding a target disease.

Means for Solving the Problems

[0006] One aspect of the electrocardiogram evaluation apparatus is acquisition means for acquiring electrocardiogram data regarding an electrocardiogram of a subject; selection means for selecting a lead corresponding to a disease to be examined from all the leads of the electrocardiogram; Individual evaluation means for determining an individual evaluation, which is an evaluation for each lead, based on the electrocardiogram data corresponding to the selected lead for each lead, A means for determining an overall evaluation that combines the individual evaluations for each of the aforementioned inductions, This is an electrocardiogram evaluation device that has [a specific feature / ability].

[0007] One aspect of an electrocardiogram evaluation method is: Computers We obtain electrocardiogram data related to the subject's electrocardiogram, From all leads of the aforementioned electrocardiogram, select the lead corresponding to the disease being examined. Based on the electrocardiogram data corresponding to the selected lead for each lead, an individual evaluation, which is an evaluation for each lead, is determined. A comprehensive evaluation is determined by combining the individual evaluations for each of the aforementioned inductions. This is an electrocardiogram evaluation method.

[0008] One aspect of the program is: We obtain electrocardiogram data related to the subject's electrocardiogram, From all leads of the aforementioned electrocardiogram, select the lead corresponding to the disease being examined. Based on the electrocardiogram data corresponding to the selected lead for each lead, an individual evaluation, which is an evaluation for each lead, is determined. A comprehensive evaluation is determined by combining the individual evaluations for each of the aforementioned inductions. It is a program that instructs a computer to perform a process. [Effects of the Invention]

[0009] One example of the effects of the present invention is that it becomes possible to accurately evaluate the electrocardiogram of a subject with respect to the target disease. [Brief explanation of the drawing]

[0010] [Figure 1] An example of the hardware configuration of an electrocardiogram evaluation device is shown. [Figure 2] This is a functional block diagram of an electrocardiogram evaluation device. [Figure 3] This outlines the processing flow when the target disease is atrial fibrillation. [Figure 4] This is an example of an electrocardiogram evaluation screen. [Figure 5] This is an example of a flowchart showing an overview of the processes performed by the electrocardiogram evaluation device in the first embodiment. [Figure 6] This is a functional block of the electrocardiogram evaluation device in the second embodiment. [Figure 7] It is an enlarged view of the waveform of the induction data. [Figure 8] It is an example of a flowchart showing the outline of the process executed by the electrocardiogram evaluation device in the second embodiment. [Figure 9] It is a block diagram of the electrocardiogram evaluation device in the third embodiment. [Figure 10] It is an example of a flowchart showing the processing procedure of the electrocardiogram evaluation device in the third embodiment.

Mode for Carrying Out the Invention

[0011] Hereinafter, embodiments of an electrocardiogram evaluation device, an electrocardiogram evaluation method, and a storage medium will be described with reference to the drawings.

[0012] <First Embodiment> (1) System Configuration FIG. 1 shows an example of the hardware configuration of the electrocardiogram evaluation device 1. The electrocardiogram evaluation device 1 analyzes an electrocardiogram measured from a subject and evaluates the electrocardiogram regarding a disease to be diagnosed (also referred to as "target disease"). The electrocardiogram evaluation device 1 mainly includes an interface 11, a memory 12, a processor 13, an input unit 14, and an output unit 15. These elements are connected via a data bus 19. The target disease is mainly a circulatory disease and may be any disease detectable by electrocardiogram analysis.

[0013] The interface 11 performs an interface operation between the electrocardiogram evaluation device 1 and an external device. In this case, the interface 11 is a communication interface such as a network adapter for communicating with an external device, which is a device separate from the electrocardiogram evaluation device 1, by wire or wirelessly, or a hardware interface compliant with USB (Universal Serial Bus), SATA (Serial AT Attachment), etc.

[0014] In this embodiment, interface 11 receives electrocardiogram data, which is data relating to the subject's electrocardiogram, from an external device and supplies the electrocardiogram data to processor 13. In this case, the external device may be an electrocardiogram measuring device that measures an electrocardiogram from the electrocardiogram signals of electrodes attached to the subject, or it may be a device that stores the measurement results output by the electrocardiogram measuring device. Furthermore, the electrocardiogram data is data that shows the measurement results relating to the subject's electrocardiogram, and in this embodiment, it is data from a 12-lead electrocardiogram, which is an examination in which a total of 10 electrodes are attached to 6 locations on the chest and both wrists and both ankles to record the electrical activity and changes of the heart. The electrocardiogram data may be raw data of the subject's electrocardiogram output by the electrocardiogram measuring device, or it may be an electrocardiogram file converted to a predetermined format (e.g., an electrocardiogram image or a PDF file).

[0015] Memory 12 consists of various volatile memories used as working memory, such as RAM (Random Access Memory) and ROM (Read Only Memory), and non-volatile memory that stores information necessary for processing the electrocardiogram evaluation device 1. Memory 12 may also include external storage devices such as hard disks connected to or built into the electrocardiogram evaluation device 1, or it may include storage media such as removable flash memory. Memory 12 stores programs for the electrocardiogram evaluation device 1 to perform each of the processes in this embodiment.

[0016] Furthermore, the memory 12 functionally includes a model storage unit 21. The model storage unit 21 stores parameters for a model that outputs an evaluation result indicating the presence or absence of a target disease based on lead data representing each lead of a 12-lead electrocardiogram. The model is, for example, a machine learning model such as a neural network or a support vector machine, which is pre-trained to output an evaluation result indicating the presence or absence of a target disease when lead data is input, and the trained parameters are stored in the model storage unit 21. When the model is composed of a neural network, the model storage unit 21 stores various parameters such as the layer structure, the neuron structure of each layer, the number and size of filters in each layer, and the weights of each element of each filter.

[0017] The model may be a model learned separately for each induction. In this case, the model storage unit 21 stores the model parameters for each induction. Similarly, the model may be a model learned separately for each target disease. In this case, the model storage unit 21 stores the model parameters corresponding to each of the diseases that could be the target disease.

[0018] The processor 13 executes predetermined processes by running programs and other data stored in memory 12. The processor 13 is a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a TPU (Tensor Processing Unit), or other type of processor. The processor 13 may be composed of multiple processors. The processor 13 is an example of a computer.

[0019] The input unit 14 generates an input signal. The input unit 14 is, for example, a button, touch panel, remote controller, or voice input device. The output unit 15 displays information and / or outputs sound based on the control of the processor 13. The output unit 15 is, for example, a display, projector, or speaker. The output unit 15 is an example of a display device.

[0020] Note that the configuration of the electrocardiogram evaluation device 1 shown in Figure 1 is an example, and various modifications may be made. For example, instead of being supplied from an external device, the electrocardiogram data may be pre-stored in the memory 12. In another example, at least one of the input unit 14 or the output unit 15 may be an external device connected to the electrocardiogram evaluation device 1 by an interface 11 or the like. In yet another example, at least some of the information stored in the memory 12 may be stored in an external device connected to the electrocardiogram evaluation device 1. In this case, the external device may be configured as one or more server devices.

[0021] (3) Functional Blocks Figure 2 is a functional block diagram of the electrocardiogram evaluation device 1. Functionally, the processor 13 of the electrocardiogram evaluation device 1 includes an acquisition unit 30, a selection unit 31, an individual evaluation unit 32, an overall evaluation unit 33, and an output control unit 34. In this diagram, blocks that exchange data are connected by solid lines, but the combination of blocks that exchange data is not limited to Figure 2. The same applies to the diagrams of other functional blocks described later.

[0022] The acquisition unit 30 acquires electrocardiogram data from an external device via the interface 11. If the electrocardiogram data is raw data of a 12-lead electrocardiogram that has not been quantized, or image data (including PDF files) representing signal waveforms, the acquisition unit 30 converts it into lead data, which is time-series data that has been quantized (including sampling and encoding) for each lead. In this case, the acquisition unit 30 may perform the above-mentioned conversion process based on any digital conversion method or image recognition method. The acquisition unit 30 may also generate lead data as measurement data for a predetermined time period extracted from the electrocardiogram data. The predetermined time period may be, for example, a time width that matches the input format of the model used. The acquisition unit 30 then supplies 12 lead data corresponding to the 12 leads to the selection unit 31.

[0023] The selection unit 31 selects lead data from the 12 lead data points for the 12 leads to be used to determine the presence or absence of the target disease, and supplies the selected lead data to the individual evaluation unit 32. In this case, for example, if the target disease is atrial fibrillation, the selection unit 31 selects lead data corresponding to leads I, II, and V1. Since leads I, II, and V1 each correspond to axes in the three-dimensional space of the heart, using these three leads allows for spatial capture of the electrical activity of the heart, making it possible to accurately determine the presence or absence of atrial fibrillation. In another example, if the target disease is cardiac hypertrophy, the selection unit 31 selects lead data corresponding to at least leads V5 and V6. In yet another example, if the target disease is angina pectoris, the selection unit 31 selects lead data corresponding to at least leads II, V5, and V6.

[0024] When evaluating a disease specified by the input unit 14 or the like, the selection unit 31 determines which leads should be used to evaluate the electrocardiogram for the specified target disease and selects the lead data corresponding to the determined leads. In this case, for example, the memory 12 stores table information showing the correspondence between diseases that can be target diseases and the leads to be used when each disease becomes a target disease. "Diseases that can be target diseases" include diseases that are diagnosed based on electrocardiograms. The selection unit 31 then refers to this table information and determines which leads to be used to evaluate the electrocardiogram for the target disease. In this way, the selection unit 31 selects lead data according to the target disease using a rule-based method.

[0025] The individual evaluation unit 32 uses the lead data selected by the selection unit 31 to perform an individual electrocardiogram evaluation (also called "individual evaluation") for each selected lead, and supplies individual evaluation information representing the individual evaluation of each lead to the overall evaluation unit 33. In this case, the individual evaluation unit 32 inputs the lead data into a model constructed by referring to parameters stored in the model storage unit 21, and obtains the evaluation result regarding the presence or absence of the target disease (normal or abnormal) output by the model as the individual evaluation. If a model has been pre-trained for each target disease and / or lead type, the individual evaluation unit 32 selects a model according to the target disease and lead type.

[0026] The overall evaluation unit 33 performs an overall evaluation of the electrocardiogram related to the target disease (also called "overall evaluation") based on the individual evaluations for each lead calculated by the individual evaluation unit 32, and supplies overall evaluation information representing the overall evaluation to the output control unit 34.

[0027] For example, the overall evaluation unit 33 performs a majority vote on the individual evaluations (evaluations representing normal or abnormal) for each lead indicated by the individual evaluation information, and determines the evaluation with the most votes as the overall evaluation. Hereafter, the method of determining the overall evaluation by majority vote will also be called the "majority voting method." In another example, weights are set in advance for each lead, and the overall evaluation unit 33 calculates an overall score representing the probability of the target disease existing based on the weights for each lead and the individual evaluations for each lead. This overall score is calculated such that, for example, the higher the probability of the target disease existing, the higher the score. For example, the overall evaluation unit 33 calculates the product of the confidence level of being normal and the weight for each lead, and calculates the sum of the above products for each lead as the overall score. The confidence level mentioned above may be the confidence level representing the likelihood of each class (here, normal or abnormal) output when the model is a neural network, or it may be a value obtained by binarizing the output of the model. The overall evaluation unit 33 then determines an overall evaluation indicating normality (i.e., the absence of the target disease) if the overall score is above a predetermined threshold, and determines an overall evaluation indicating abnormality (i.e., the presence of the target disease) if the overall score is below the threshold. The threshold is, for example, stored in memory 12 beforehand. Alternatively, the overall score may be calculated such that a higher score indicates a lower probability of the presence of the target disease. Hereafter, the method of determining the overall evaluation based on weighting and the overall score will also be referred to as the "scoring method".

[0028] The output control unit 34 controls the output unit 15 based on the overall evaluation information supplied from the overall evaluation unit 33. In this case, for example, the output control unit 34 displays the overall evaluation (i.e., the evaluation of the presence or absence of the target disease) indicated by the overall evaluation information, along with the electrocardiogram data acquired by the acquisition unit 30, on the output unit 15. In this case, the output control unit 34 may further display the waveform of each lead data selected by the selection unit 31 and clearly indicate the aforementioned waveform section (also called the "section of interest") that was emphasized in the calculation of the individual evaluation by the model. In other words, the output control unit 34 may display the waveform of each selected lead data in a manner that clearly indicates the section of interest. An example of this display will be explained with reference to Figure 4. The output control unit 34 functions as a "display control means".

[0029] Here, we will describe specific examples of what the acquisition unit 30, selection unit 31, individual evaluation unit 32, and overall evaluation unit 33 do. Figure 3 shows the processing flow when the target disease is atrial fibrillation.

[0030] First, the acquisition unit 30 acquires lead data corresponding to the 12 leads. The upper part of Figure 3 shows, as a representative example, waveforms based on lead data for leads I, II, III, aVR, and V1. Then, the selection unit 31 selects lead data for leads I, II, and V1 from these 12 lead data, as shown in the middle part of Figure 3, which are effective in evaluating the presence or absence of atrial fibrillation, the target disease. The individual evaluation unit 32 then inputs the lead data for leads I, II, and V1 into the model to acquire individual evaluations. Here, the individual evaluation unit 32 generates individual evaluation information indicating that the individual evaluation based on the lead data for lead I is "normal," the individual evaluation based on the lead data for lead II is "abnormal," and the individual evaluation based on the lead data for lead V1 is "normal," and supplies this information to the overall evaluation unit 33. The overall evaluation unit 33 then performs a majority vote on the individual evaluations based on the individual evaluation information and determines the evaluation that receives the majority, "normal," as the overall evaluation. The overall evaluation unit 33 may determine the overall evaluation according to a scoring system instead of a majority vote system.

[0031] Figure 4 shows an example of an electrocardiogram evaluation screen displayed on the output unit 15 by the output control unit 34. The output control unit 34 generates a display signal based on various information supplied from other processing units and supplies this display signal to the output unit 15, thereby displaying the electrocardiogram evaluation screen on the output unit 15.

[0032] In this case, the output control unit 34 displays the overall evaluation based on the overall evaluation information generated by the overall evaluation unit 33, and also displays the waveform of the lead data selected by the selection unit 31. Furthermore, the output control unit 34 clearly indicates the sections of interest that were emphasized in the calculation of the individual evaluation by the model on the waveform. Here, the output control unit 34 highlights the above-mentioned sections of interest with a dashed line frame. As a result, the output control unit 34 can present the locations in the electrocardiogram that serve as the basis for the evaluation, thereby effectively supporting the examiner's final diagnosis.

[0033] Here, we will provide a supplementary explanation of a specific example of how to determine the interval of interest. For example, if the model is a convolutional neural network, the electrocardiogram evaluation device 1 may add an attention mechanism to the model so that the output data before the full connection is input, and identify the interval in which the coefficient output by the attention mechanism is greater than or equal to a predetermined value as the interval of interest.

[0034] The components of the acquisition unit 30, selection unit 31, individual evaluation unit 32, overall evaluation unit 33, and output control unit 34 can be implemented, for example, by the processor 13 executing a program. Alternatively, the necessary programs may be recorded on any non-volatile storage medium and installed as needed to implement each component. At least some of these components are not limited to being implemented by software programs, but may also be implemented by a combination of hardware, firmware, and software. Furthermore, at least some of these components may be implemented by, for example, an FPGA (Field-Programmable Gate Array) or a microcontroller, which can be programmed by the user. This may be implemented using an integrated circuit. In this case, the program composed of the above-mentioned components may be implemented using this integrated circuit. Furthermore, at least a portion of each component may be composed of an ASSP (Application Specific Standard Produce), an ASIC (Application Specific Integrated Circuit), or a quantum processor (quantum computer control chip). Thus, each component may be implemented using various hardware. The same applies to other embodiments described later. Moreover, each of these components may be implemented through the collaboration of multiple computers, for example, using cloud computing technology.

[0035] (4) Processing flow Figure 5 is an example of a flowchart showing an overview of the processes performed by the electrocardiogram evaluation device 1 in the first embodiment.

[0036] First, the electrocardiogram evaluation device 1 acquires lead data for each lead based on the electrocardiogram data supplied from an external device (step S11). In this case, the electrocardiogram evaluation device 1, for example, performs a digitization process on the acquired electrocardiogram data to generate lead data, which is time-series numerical data.

[0037] Then, the electrocardiogram evaluation device 1 selects lead data according to the target disease (step S12). In this case, for example, the electrocardiogram evaluation device 1 recognizes the target disease based on the input information from the input unit 14 or the setting information stored in the memory 12, and selects lead data related to the target disease in a rule-based manner.

[0038] Next, the electrocardiogram evaluation device 1 determines an individual evaluation for each lead based on the selected lead data (step S13). In this case, the electrocardiogram evaluation device 1 inputs each of the selected lead data into a model constructed by referring to the model storage unit 21, thereby obtaining an individual evaluation from the model that shows the presence or absence of the target disease for each lead.

[0039] Then, the electrocardiogram evaluation device 1 determines the overall electrocardiogram evaluation for the target disease based on the individual evaluation calculated in step S13 (step S14). Note that the individual evaluation corresponds to a provisional evaluation of the electrocardiogram, and the overall evaluation corresponds to the final electrocardiogram evaluation determined by the electrocardiogram evaluation device 1.

[0040] Then, the electrocardiogram evaluation device 1 outputs overall evaluation information representing the overall evaluation (step S15). In this case, instead of outputting the overall evaluation information to the output unit 15, or in addition to doing so, the electrocardiogram evaluation device 1 may store the overall evaluation information in the memory 12 or transmit it to an external device.

[0041] <Second Embodiment> Figure 6 shows the functional blocks of the electrocardiogram evaluation device 1 in the second embodiment. The electrocardiogram evaluation device 1 in the second embodiment differs from the electrocardiogram evaluation device 1 in the first embodiment in that it further performs a process of extracting data used to determine the evaluation of the electrocardiogram from the selected lead data based on the subject's attribute information. Hereafter, components identical to those in the first embodiment will be denoted by the same reference numerals as appropriate, and their descriptions will be omitted.

[0042] In addition to selecting lead data related to the target disease, the selection unit 31A extracts data used to determine the evaluation of the electrocardiogram (also called "evaluation target data") from the selected lead data, based on the subject's attribute information and attribute / mode correspondence information pre-stored in the attribute / mode correspondence information storage unit 22. The evaluation target data is the data that will be input into the model.

[0043] In the process of extracting data to be evaluated, the selection unit 31A selectively executes one of three waveform selection modes (continuous waveform mode M1, single waveform mode M2, and partial waveform mode M3). Here, continuous waveform mode M1 is a mode in which data of a continuous waveform (four waveforms in the example of Figure 3) (i.e., the entire induction data) is determined as data to be evaluated, similar to the first embodiment. Single waveform mode M2 ​​is a mode in which induction data for one waveform is determined as data to be evaluated, and partial waveform mode M3 is a mode in which induction data corresponding to a partial waveform smaller than one waveform is determined as data to be evaluated. Continuous waveform mode M1 is an example of the "first mode", single waveform mode M2 ​​is an example of the "second mode", and partial waveform mode M3 is an example of the "third mode".

[0044] Here, the subject attribute information refers to information indicating arbitrary attributes of the subject that are affected in the electrocardiogram examination, such as age, sex, and medical history. The selection unit 31A may receive the subject attribute information from an external device that manages the subject attribute information via the interface 11, generate it based on the output of the input unit 14 based on user operation, or obtain it from the memory 12 which has previously stored the attribute information.

[0045] Attribute-mode correspondence information is information that associates the expected attributes of the subject with the waveform selection mode appropriate for those attributes. Attribute-mode correspondence information is generated in advance based on the results of a previously performed electrocardiogram examination, etc., and is stored in the attribute-mode correspondence information storage unit 22.

[0046] Figure 7 is a magnified view of a waveform of some guidance data. In this example, the guidance data contains two waveforms, one of which is enclosed by a dashed frame. As shown, each waveform contains P-wave, Q-wave, R-wave, S-wave, T-wave, U-wave, etc., and the positions of these waves can be detected through signal processing.

[0047] In the continuous waveform mode M1, the selection unit 31A determines the induction data itself, which represents a continuous waveform, as the evaluation target data. In the single waveform mode M2, the selection unit 31A determines the data representing one waveform extracted from the induction data as the evaluation target data. In the partial waveform mode M3, the selection unit 31A determines the data representing a partial waveform extracted from the induction data as the evaluation target data. For example, the evaluation target data in partial waveform mode M3 may be data representing the interval from wave P to wave Q (PQ interval), the interval from wave Q to wave T (QT interval), or any other interval between any two waves, or it may be data representing an interval cut out from only an individual wave (for example, the P wave interval, the R wave interval).

[0048] In the single-waveform mode M2, the selection unit 31A may extract evaluation target data corresponding to any one waveform from among the multiple waveforms included in the target induction data, or it may extract evaluation target data corresponding to each of the multiple waveforms. In the latter case, for example, the individual evaluation unit 32 determines the individual evaluation for the target induction data based on the evaluation result of the model obtained by inputting the evaluation target data corresponding to each of the multiple waveforms into the model. In this case, the individual evaluation unit 32 may determine the individual evaluation based on, for example, a majority vote. Similarly in the partial-waveform mode M3, the selection unit 31A extracts data corresponding to a partial waveform of at least one waveform as evaluation target data. When evaluation target data corresponding to each of the multiple partial waveforms has been generated, the individual evaluation unit 32 determines the individual evaluation for the target induction data based on the evaluation result of the model obtained by inputting each of these evaluation target data into the model.

[0049] Note that the models used in continuous waveform mode M1, single waveform mode M2, and partial waveform mode M3 may be different. In this case, the learned parameters of the models used in continuous waveform mode M1, single waveform mode M2, and partial waveform mode M3 are pre-stored in the model storage unit 21.

[0050] The selection unit 31A then selects the waveform selection mode that corresponds to the attribute indicated by the received subject attribute information in the attribute-mode correspondence information. The selection unit 31A then supplies the evaluation target data extracted from each lead data based on the selected waveform selection mode to the individual evaluation unit 32. In addition, the record corresponding to partial waveform mode M3 in the attribute-mode correspondence information further contains information that identifies the section of the partial waveform to be extracted as evaluation target data (for example, PQ section, QT section, section of an arbitrary wave, etc.). Therefore, even when partial waveform mode M3 is selected, the selection unit 31A can extract the evaluation target data based on the attribute-mode correspondence information. In this way, the selection unit 31A accurately extracts the evaluation target data necessary for evaluation based on the subject's attribute information.

[0051] Figure 8 is an example of a flowchart showing an overview of the processes performed by the electrocardiogram evaluation device 1 in the second embodiment.

[0052] First, the electrocardiogram evaluation device 1 acquires lead data for each lead based on the electrocardiogram data supplied from an external device (step S21). Then, the electrocardiogram evaluation device 1 selects the lead data according to the target disease (step S22).

[0053] Next, the electrocardiogram evaluation device 1 determines the waveform selection mode based on the subject's attributes (step S23). In this case, the electrocardiogram evaluation device 1 determines the waveform selection mode according to the subject's attributes based on the subject's attribute information supplied from the external device and the attribute / mode correspondence information stored in the attribute / mode correspondence information storage unit 22. If a waveform selection mode corresponding to the subject's attributes is not recorded in the attribute / mode correspondence information, the electrocardiogram evaluation device 1 sets the waveform selection mode to, for example, continuous waveform mode M1.

[0054] Then, the electrocardiogram evaluation device 1 determines an individual evaluation for each lead based on the selected lead data and the determined waveform selection mode (step S24). In this case, the electrocardiogram evaluation device 1 inputs data obtained by cutting out the interval determined by the waveform selection mode from the selected lead data into the model constructed by referring to the model storage unit 21 as the data to be evaluated. Then, based on the evaluation results obtained from the model, the electrocardiogram evaluation device 1 determines an individual evaluation that shows the presence or absence of the target disease for each lead.

[0055] Then, the electrocardiogram evaluation device 1 determines the overall electrocardiogram evaluation for the target disease based on the individual evaluation calculated in step S24 (step S25). Then, the electrocardiogram evaluation device 1 outputs overall evaluation information representing the overall evaluation (step S26).

[0056] The electrocardiogram evaluation device 1 according to the second embodiment can generate individual evaluations that show the presence or absence of the target disease with greater accuracy by determining an appropriate waveform selection mode according to the attributes of the subject, and can output accurate evaluation results regarding the target disease.

[0057] <Third Embodiment> Figure 9 is a block diagram of the electrocardiogram evaluation device 1X in the third embodiment. The electrocardiogram evaluation device 1X mainly comprises an acquisition means 30X, a selection means 31X, and an evaluation means 33X. The electrocardiogram evaluation device 1X may be composed of multiple devices.

[0058] The acquisition means 30X acquires electrocardiogram data relating to the subject's electrocardiogram. The acquisition means 30X can be, for example, the acquisition unit 30 in the first or second embodiment. The selection means 31X selects lead data corresponding to the disease to be examined from the electrocardiogram data. The selection means 31X can be, for example, the selection unit 31 in the first embodiment, or the selection unit 31A in the second embodiment. The evaluation means 33X evaluates the electrocardiogram relating to the disease based on the selected lead data. The evaluation means 33X can be, for example, the individual evaluation unit 32 and the overall evaluation unit 33 in the first or second embodiment.

[0059] Figure 10 is an example flowchart showing the processing procedure performed by the electrocardiogram evaluation device 1X in the third embodiment. The acquisition means 30X acquires electrocardiogram data relating to the subject's electrocardiogram (step S41). The selection means 31X selects lead data corresponding to the disease to be examined from the electrocardiogram data (step S42). Then, the evaluation means 33X performs an evaluation of the electrocardiogram relating to the disease based on the selected lead data (step S43).

[0060] According to the third embodiment, the electrocardiogram evaluation device 1X can accurately perform an evaluation of the electrocardiogram related to the target disease using lead data related to the disease being examined.

[0061] In each of the embodiments described above, the program is transmitted via various types of non-transitory computer-readable media. Programs can be stored using a transient computer-readable medium and supplied to a computer, such as a processor. Transitory computer-readable mediums include various types of tangible storage media. Examples of transient computer-readable mediums include magnetic storage media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical storage media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memory (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). Programs may also be supplied to a computer by various types of transient computer-readable mediums. Examples of transient computer-readable mediums include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable mediums can supply programs to a computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels.

[0062] In addition, some or all of the above embodiments (including modifications, the same applies hereinafter) may also be described as follows, but are not limited to the following.

[0063] [Note 1] A means for acquiring electrocardiogram data related to the electrocardiogram of a subject, A selection means for selecting lead data corresponding to the disease to be examined from the electrocardiogram data, An evaluation means for performing an evaluation of the electrocardiogram related to the disease based on the selected lead data, An electrocardiogram evaluation device having the following features. [Note 2] The evaluation means is Individual evaluation means for determining an individual evaluation, which is an evaluation for each of the aforementioned guidance data, based on the guidance data for each guidance, A means for determining an overall evaluation that combines the individual evaluations for each of the aforementioned inductions, An electrocardiogram evaluation device as described in Appendix 1, having the following features. [Note 3] The overall evaluation determination means is an electrocardiogram evaluation device as described in Appendix 2, which determines the overall evaluation based on a majority vote of the individual evaluations. [Note 4] The electrocardiogram evaluation device described in Appendix 2, wherein the overall evaluation determination means calculates a score based on the weight set for each lead and the individual evaluation, and determines the overall evaluation based on the score. [Note 5] An electrocardiogram evaluation device according to any one of the appendices 1 to 4, further comprising display control means for displaying waveforms based on the lead data on a display device in a manner that clearly indicates the section of interest in the waveform that was the focus of attention in the evaluation. [Note 6] The electrocardiogram evaluation device according to any one of the appendices 1 to 5, wherein the selection means selects the lead data corresponding to lead I, lead II, and lead V1 when the disease is atrial fibrillation. [Note 7] The aforementioned selection means is, A first mode in which the entirety of the aforementioned guidance data is extracted as evaluation target data, which is the data used to determine the evaluation in the selected guidance data, A second mode in which data corresponding to the unit waveform of the induction data is extracted as the data to be evaluated, A third mode in which data corresponding to a partial waveform of the aforementioned induction data is extracted as the data to be evaluated, An electrocardiogram evaluation device described in any one of the appendices 1 to 6, which performs one of the following actions. [Note 8] The electrocardiogram evaluation device according to any one of the appendices 1 to 7, wherein the selection means extracts evaluation target data, which is data used to determine the evaluation, from the selected lead data based on the attribute information of the subject. [Note 9] Computers We obtain electrocardiogram data related to the subject's electrocardiogram, From the electrocardiogram data mentioned above, select the lead data corresponding to the disease to be examined. Based on the selected lead data, the electrocardiogram is evaluated in relation to the disease. Electrocardiogram evaluation methods. [Note 10] We obtain electrocardiogram data related to the subject's electrocardiogram, From the electrocardiogram data mentioned above, select the lead data corresponding to the disease to be examined. A storage medium containing a program that causes a computer to perform a process of evaluating the electrocardiogram related to the disease based on the selected lead data.

[0064] Although the present invention has been described above with reference to embodiments, the present invention is not limited to the above embodiments. Various modifications to the structure and details of the present invention can be made that are understandable to those skilled in the art within the scope of the present invention. That is, the present invention naturally includes the full disclosure, including the claims, and various modifications and alterations that those skilled in the art could make in accordance with the technical idea. Furthermore, each disclosure of the above-mentioned patent documents and other references is incorporated herein by reference. [Explanation of symbols]

[0065] 1. 1X electrocardiogram evaluation device 11 Interfaces 12 memory 13 processors 14 Input section 15 Output section 21 Model Memory Unit 22 Attribute / Mode Compatible Information Storage Unit

Claims

1. A means for acquiring electrocardiogram data related to the electrocardiogram of a subject, A selection means for selecting the lead corresponding to the disease to be examined from among all leads of the electrocardiogram, Individual evaluation means for determining an individual evaluation, which is an evaluation for each lead, based on the electrocardiogram data corresponding to the selected lead for each lead, A means for determining an overall evaluation that combines the individual evaluations for each of the aforementioned inductions, An electrocardiogram evaluation device having the following features.

2. Acquisition means for acquiring electrocardiogram data relating to the electrocardiogram of a subject, A selection means for selecting the lead corresponding to the disease to be examined from among all leads of the electrocardiogram, The system includes an evaluation means for performing an evaluation of the electrocardiogram related to the disease based on the electrocardiogram data corresponding to the selected lead, The selection means selects leads I, II, and V1 if the disease is atrial fibrillation. Electrocardiogram evaluation device.

3. Acquisition means for acquiring electrocardiogram data relating to the electrocardiogram of a subject, A selection means for selecting the lead corresponding to the disease to be examined from among all leads of the electrocardiogram, The system includes an evaluation means for performing an evaluation of the electrocardiogram related to the disease based on the electrocardiogram data corresponding to the selected lead, The aforementioned selection means is, A first mode in which the entire electrocardiogram data corresponding to the selected lead is extracted as evaluation target data, which is the data used to determine the evaluation in the electrocardiogram data corresponding to the selected lead, A second mode in which data corresponding to the unit waveform of the electrocardiogram data corresponding to the selected lead is extracted as the data to be evaluated, A third mode in which data corresponding to a partial waveform of the electrocardiogram data corresponding to the selected lead is extracted as the data to be evaluated, An electrocardiogram evaluation device that performs one of the following actions.

4. Acquisition means for acquiring electrocardiogram data relating to the electrocardiogram of a subject, A selection means for selecting the lead corresponding to the disease to be examined from among all leads of the electrocardiogram, The system includes an evaluation means for performing an evaluation of the electrocardiogram related to the disease based on the electrocardiogram data corresponding to the selected lead, The selection means is an electrocardiogram evaluation device that extracts evaluation target data, which is data used to determine the evaluation, from the electrocardiogram data corresponding to the selected lead, based on the attribute information of the subject.

5. The electrocardiogram evaluation apparatus according to claim 1, wherein the overall evaluation determination means determines the overall evaluation based on a majority vote of the individual evaluations.

6. The electrocardiogram evaluation device according to claim 1, wherein the overall evaluation determination means calculates a score based on the weight set for each lead and the individual evaluation, and determines the overall evaluation based on the score.

7. The invention further comprises a display control means for displaying the evaluation results and the acquired electrocardiogram data on a display device, An electrocardiogram evaluation device according to any one of claims 1 to 6.

8. The display control means performs display control to display on the display device the waveform based on the electrocardiogram data corresponding to the selected lead in a manner that clearly indicates the section of interest in the waveform that was the focus of attention in the evaluation. The electrocardiogram evaluation device according to claim 7.

9. The acquisition means acquires the electrocardiogram data from an external device via an interface. An electrocardiogram evaluation device according to any one of claims 1 to 8.

10. Computers We obtain electrocardiogram data related to the subject's electrocardiogram, From all leads of the aforementioned electrocardiogram, select the lead corresponding to the disease being examined. Based on the electrocardiogram data corresponding to the selected lead for each lead, an individual evaluation, which is an evaluation for each lead, is determined. An electrocardiogram evaluation method for determining an overall evaluation by combining the individual evaluations for each lead.

11. We obtain electrocardiogram data related to the subject's electrocardiogram, From all leads of the aforementioned electrocardiogram, select the lead corresponding to the disease being examined. Based on the electrocardiogram data corresponding to the selected lead for each lead, an individual evaluation, which is an evaluation for each lead, is determined. A program that causes a computer to perform a process to determine an overall evaluation by combining the individual evaluations for each of the aforementioned guidances.

Images