Information processing device

Abstract

In the present invention, an acquisition unit acquires, by inputting electrocardiogram data of a subject to a first trained model trained to output an onset risk of a specific disease of a person and the certainty degree of the onset risk with respect to an input of the electrocardiogram data of the person, the onset risk and the certainty degree outputted by the first trained model. When the certainty degree is equal to or greater than a prescribed value, a main determination unit determines the onset risk of the subject on the basis of the onset risk and the certainty degree outputted by the first trained model. When the certainty degree is less than the prescribed value, a sub-determination unit acquires the cardiac age of the subject, and determines the onset risk of the subject on the basis of the acquired cardiac age. An output unit outputs a determination result by the main determination unit when determination is performed by the main determination unit, and outputs a determination result by the sub-determination unit when determination is performed by the sub-determination unit.

Description

Information processing device

[0001] The present invention relates to an information processing device, an information processing method, and a recording medium for predicting the risk of developing a specific disease.

[0002] The risk of developing a particular disease is predicted by analyzing the measured electrocardiogram of the subject.

[0003] For example, Patent Document 1 discloses an apparatus that inputs electrocardiogram data of a subject into a machine-learned model using training electrocardiogram data from a patient with paroxysmal arrhythmia during a non-attack period when the patient is not experiencing paroxysmal arrhythmia, and outputs abnormality information from the model regarding whether or not the subject has paroxysmal arrhythmia.

[0004] Furthermore, Non-Patent Document 1 discloses a device that predicts new onset of atrial fibrillation in subjects who do not have atrial fibrillation, using a DNN (Deep Neural Network) that has been machine-learned using training electrocardiogram data at rest, gender, and age.

[0005] Japanese Patent Application Laid-Open No. 2022-37153

[0006] Sushravya Raghunath et al. "Deep Neural Networks Can Predict New-Onset Atrial Fibrillation From the 12-Lead ECG and Help Identify Those at Risk of Atrial Fibrillation-Related Stroke". Circulation. 2021;143:1287-1298. DOI: 10.1161 / CIRCULATIONAHA.120.047829.

[0007] When predicting the risk of developing a specific disease based on an electrocardiogram obtained from a subject, information about the subject's body is taken into consideration in addition to the electrocardiogram, as in Non-Patent Document 1. However, it has been difficult to improve accuracy with information that does not match the subject's actual physical condition.

[0008] An object of the present invention is to provide an information processing device that solves the above-mentioned problems.

[0009] An information processing device according to one embodiment of the present invention is configured to include: an acquisition unit that inputs electrocardiogram data of a subject into a first trained model that has been trained to output the person's risk of developing a specific disease and a certainty of the risk of developing the disease in response to input of the person's electrocardiogram data, and thereby acquires the risk of development and the certainty output by the first trained model; a main judgment unit that, if the certainty is equal to or greater than a predetermined value, determines the subject's risk of developing the disease based on the risk of development and the certainty output by the first trained model; a secondary judgment unit that, if the certainty is less than the predetermined value, acquires the subject's cardiac age and determines the subject's risk of developing the disease based on the acquired cardiac age; and an output unit that outputs the judgment result of the main judgment unit when the judgment is made by the main judgment unit, and outputs the judgment result of the secondary judgment unit when the judgment is made by the secondary judgment unit.

[0010] An information processing method according to another aspect of the present invention is configured to: input electrocardiogram data of a subject into a first trained model that has been trained to output the person's risk of developing a specific disease and a certainty of the risk of developing the disease in response to input of the person's electrocardiogram data, thereby obtaining the risk of development and the certainty output by the first trained model; if the certainty is greater than or equal to a predetermined value, determining the subject's risk of developing the disease based on the risk of development and the certainty output by the first trained model; if the certainty is less than the predetermined value, obtaining the subject's cardiac age and determining the subject's risk of developing the disease based on the obtained cardiac age; if the certainty is greater than or equal to the predetermined value, outputting a determination result based on the risk of development and the certainty output by the first trained model; and if the certainty is less than the predetermined value, outputting a determination result based on the cardiac age.

[0011] Furthermore, a computer-readable recording medium according to another aspect of the present invention is configured to record a program for causing a computer to perform the following processes: inputting electrocardiogram data of a subject into a first trained model, the first trained model having been trained to output the person's risk of developing a specific disease and a certainty of the risk of developing the disease in response to input of the person's electrocardiogram data, thereby acquiring the risk of development and the certainty output by the first trained model; determining the subject's risk of developing a specific disease based on the risk of development and the certainty output by the first trained model if the certainty is equal to or greater than a predetermined value; acquiring the subject's cardiac age if the certainty is less than a predetermined value, and determining the subject's risk of developing a specific disease based on the acquired cardiac age; and outputting a determination result based on the risk of development and the certainty output by the first trained model if the certainty is equal to or greater than a predetermined value, and outputting a determination result based on the cardiac age if the certainty is less than the predetermined value.

[0012] By having the above-described configuration, the present invention can improve the accuracy of predicting the risk of a subject developing a specific disease based on electrocardiogram data.

[0013] While the present invention has been described with reference to exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments and is not to be construed as limiting the scope of the invention.

[0014] 1 is a block diagram of an information processing device 10 according to a first embodiment of the present invention. The information processing device 10 has a function of predicting and outputting the risk of a subject developing a specific disease based on electrocardiogram data acquired from the subject.

[0015] The electrocardiogram data is data showing the measurement results of the subject's electrocardiogram. In this embodiment, it is assumed to be 12-lead electrocardiogram data, which is a test in which a total of 10 electrodes are attached to six locations on the chest, both wrists, and both ankles to record the electrical activity and changes of the heart. However, electrocardiogram data other than 12-lead electrocardiogram data may also be used. Furthermore, the electrocardiogram data may be raw data of the subject's electrocardiogram output by an electrocardiogram measurement device, or may be an electrocardiogram file converted into a predetermined format (e.g., an electrocardiogram image or PDF file).

[0016] In this embodiment, the specific disease is assumed to be atrial fibrillation. However, the specific disease is not limited to atrial fibrillation, and may be other cardiovascular diseases such as ventricular tachycardia, supraventricular tachycardia, atrial flutter, and ventricular fibrillation. In this embodiment, the risk of onset is defined as whether or not a subject who does not have a specific disease will newly develop the specific disease within a certain period of time (for example, within one year). Hereinafter, the presence of a risk of onset will be referred to as "positive," and the absence of a risk of onset will be referred to as "negative." However, the risk of onset is not limited to two types, such as positive and negative, and may be classified into three or more types based on the probability or degree of onset.

[0017] The information processing device 10 includes, as main functional units, a communication interface unit (hereinafter referred to as a communication I / F unit) 11, an operation input unit 12, a screen display unit 13, a storage unit 14, and an arithmetic processing unit 15.

[0018] The communication I / F unit 11 is made up of a dedicated data communication circuit and has the function of communicating data with various devices such as an electrocardiogram measuring device (not shown) and a medical professional terminal (not shown) connected via a wired or wireless connection. The operation input unit 12 is made up of operation input devices such as a keyboard and a mouse and has the function of detecting operator operations and outputting them to the arithmetic processing unit 15. The screen display unit 13 is made up of a screen display device such as an LCD (Liquid Crystal Display) or a PDP (Plasma Display Panel) and has the function of displaying various information such as a predicted onset risk on a screen in response to instructions from the arithmetic processing unit 15.

[0019] The storage unit 14 is made up of storage devices such as a hard disk and memory, and has the function of storing processing information and a program 141 required for various processes in the arithmetic processing unit 15. The program 141 is a program that is read into the arithmetic processing unit 15 and executed to realize various processing units, and is read in advance from an external device (not shown) or a storage medium (not shown) via a data input / output function such as the communication I / F unit 11 and stored in the storage unit 14. The main processing information stored in the storage unit 14 includes a specific disease trained model 142 and a cardiac age trained model 143.

[0020] The specific disease trained model 142 is a model trained to output a person's risk of developing a specific disease and a certainty of the risk in response to input of the person's electrocardiogram data. The certainty is a probability that indicates the reliability of the model's judgment result, with a higher certainty. In this embodiment, the certainty is greater than or equal to 0 and less than or equal to 1. The specific disease trained model 142 may output a certainty of either the presence or absence of a risk of developing the disease. Alternatively, the specific disease trained model 142 may output a certainty of the presence of a risk of developing the disease and a certainty of the absence of a risk of developing the disease, with the sum of both certainties being 1. The specific disease trained model 142 may be created by a computer different from the information processing device 10 and stored in the memory unit 14. Alternatively, the specific disease trained model 142 may be created in the information processing device 10 and stored in the memory unit 14.

[0021] The cardiac age trained model 143 is a model trained to output a cardiac age of a person in response to input of the person's electrocardiogram data. Cardiac age is an index representing the degree of aging of the heart, and by comparing it with chronological age (actual age), it is possible to know the degree of aging of the heart. The cardiac age trained model 143 may be created by a computer different from the information processing device 10 and stored in the storage unit 14. Alternatively, the cardiac age trained model 143 may be created in the information processing device 10 and stored in the storage unit 14.

[0022] For example, a DNN may be used for the specific disease trained model 142 and the cardiac age trained model 143. However, a model based on a support vector machine, a decision tree, a random forest, a logistic regression, or the like may also be used for these trained models.

[0023] The arithmetic processing unit 15 has a microprocessor such as a CPU (Central Processing Unit) and its peripheral circuits, and has a function of realizing various processing units by reading and executing a program 141 from the storage unit 14, thereby making the above hardware and the program 141 work together. The main processing units realized by the arithmetic processing unit 15 are an acquisition unit 151, a main determination unit 152, a sub-determination unit 153, and an output unit 154.

[0024] The acquisition unit 151 is configured to acquire electrocardiogram data of the subject. For example, the acquisition unit 151 may acquire the electrocardiogram data of the subject from an electrocardiogram measurement device (not shown) via the communication I / F unit 11. Alternatively, the acquisition unit 151 may acquire the electrocardiogram data of the subject via the communication I / F unit 11 from an electronic medical record (not shown) that records basic physical data such as the subject's age, sex, height, and weight, measurement data such as heart rate, body temperature, blood pressure, and electrocardiogram data, and medical condition data such as the subject's state of consciousness, current or past illnesses (pre-existing illnesses), and the circumstances at the time of the examination and the circumstances at the time of the test. Alternatively, if the electrocardiogram data of the subject has been stored in the storage unit 14 in advance, the acquisition unit 151 may acquire the electrocardiogram data of the subject from the storage unit 14.

[0025] The acquisition unit 151 is configured to input the acquired electrocardiogram data into the specific disease trained model 142 and acquire the person's risk of developing a specific disease and the certainty of the risk of developing the disease, which are output from the trained model. Note that the acquisition unit 151 may acquire the risk of development and the certainty calculated based on the subject's electrocardiogram data in a computer different from the information processing device 10.

[0026] When the certainty acquired by the acquisition unit 151 is equal to or greater than a threshold, the main determination unit 152 is configured to determine the subject's risk of developing a specific disease as positive or negative based on the onset risk and certainty acquired by the acquisition unit 151. The main determination unit 152 determines the onset risk with the higher certainty output by the specific disease trained model 142 as the subject's onset risk.

[0027] As described above, for example, the sum of the certainty factors for the risk of onset being "yes" and "no" is 1. The higher certainty factor is output as the judgment result. For example, if the certainty factor for "yes" is 0.9 and the certainty factor for "no" is 0.1, the risk of onset is judged to be "yes." If the certainty factor for "yes" is 0.1 and the certainty factor for "no" is 0.9, the risk of onset is judged to be "no." The maximum certainty factor for the risk of onset is 1, and the closer it is to 1, the higher the certainty factor of the judgment. Therefore, a positive result judged when the certainty factor for the risk of onset is equal to or greater than a threshold close to 1 can be said to be a clear positive or a strong positive. Similarly, a negative result judged when the certainty factor for the risk of onset is equal to or greater than a threshold close to 1 can be said to be a clear negative or a strong negative. The threshold can be set appropriately, for example, to a value equal to or greater than 0.5, depending on the usage scenario. Therefore, if the threshold is set to 0.6, a positive result greater than 0.5 but less than 0.6 can be said to be a low-certainty positive or a weak positive. A negative result greater than 0.5 but less than 0.6 can be considered a low confidence or weak negative, and is considered "questionable."

[0028] The main determination section 152 is configured to transmit the determination result to the output section 154 .

[0029] The information processing device 10 may also include a specific disease model learning unit 155. The specific disease model learning unit 155 has a function of creating the specific disease trained model 142. For example, the specific disease model learning unit 155 generates the specific disease trained model 142 by machine learning using a machine learning algorithm such as DNN, using electrocardiogram data acquired from various individuals similar to those in Patent Document 1 and Non-Patent Document 1 and information on whether or not the individuals have developed a specific disease as training data.

[0030] The secondary determination unit 153 is configured to obtain the cardiac age of the subject when the certainty acquired by the acquisition unit 151 is less than a threshold, and to determine the subject's onset risk as either positive or negative based on the obtained cardiac age. The cardiac age of the subject may be obtained by the acquisition unit 151. In this case, the acquisition unit 151 obtains the cardiac age upon receiving an instruction from the secondary determination unit 153.

[0031] When acquiring the cardiac age of the subject, the auxiliary determination unit 153 may acquire the cardiac age using the cardiac age learned model 143. Specifically, the auxiliary determination unit 153 inputs the electrocardiogram data acquired by the acquisition unit 151 into the cardiac age learned model 143, and acquires the predicted cardiac age output from the learned model.

[0032] The sub-determination unit 153 uses, for example, one of the following two determination methods.

[0033] <Determination Method 1> The sub-determination unit 153 makes a determination based on the result of comparing the cardiac age with a threshold. The threshold may be, for example, 65 years old. This is based on the finding that the incidence of atrial fibrillation is high in elderly people aged 65 or older. However, the threshold is not limited to 65 years old.

[0034] For example, the secondary determination unit 153 determines a positive result if the cardiac age is equal to or greater than a threshold, and determines a negative result if the cardiac age is less than the threshold. The reason for this is that a cardiac age less than the threshold is considered to indicate that the degree of cardiac aging is less advanced than that of a person of the threshold age, and a cardiac age equal to or greater than the threshold is considered to indicate that the degree of cardiac aging is more advanced than that of a person of the threshold age.

[0035] The secondary determination unit 153 may make the determination further using the onset risk acquired by the acquisition unit 151. That is, the secondary determination unit 153 may be configured to determine the onset risk of the subject as either positive or negative based on the acquired cardiac age and the onset risk output by the specific disease trained model 142. For example, the secondary determination unit 153 determines the onset risk of the subject as negative only when the onset risk output by the specific disease trained model 142 is negative and the cardiac age is less than a threshold, and determines the onset risk as positive in all other cases. By determining only subjects who are thought to have a reliably low risk of developing a disease as negative, it is possible to prevent subjects with a positive onset risk from being overlooked.

[0036] <Determination Method 2> The secondary determination unit 153 makes a determination based on the result of comparing the cardiac age with the subject's chronological age. The secondary determination unit 153 may receive the subject's chronological age input by an operator via the operation input unit 12, or may obtain the subject's chronological age via the communication I / F unit 11 from an electronic medical record (not shown) that records the subject's age, etc.

[0037] For example, the secondary determination unit 153 determines a positive result if the cardiac age is equal to or greater than the chronological age, and determines a negative result if the cardiac age is less than the chronological age. The reason for this is that a cardiac age less than the chronological age is considered to indicate that the degree of cardiac aging is less advanced than that of a person of the same chronological age, and a cardiac age equal to or greater than the chronological age is considered to indicate that the degree of cardiac aging is more advanced than that of a person of the same chronological age.

[0038] The secondary determination unit 153 may also make the determination using the onset risk acquired by the acquisition unit 151. That is, the secondary determination unit 153 may be configured to determine the subject's onset risk as either positive or negative based on the acquired cardiac age and the onset risk output by the specific disease trained model 142. For example, the secondary determination unit 153 determines the subject as negative only when the onset risk output by the specific disease trained model 142 is negative and the cardiac age is less than the chronological age, and determines the subject as positive in all other cases. As with determination method 1, by determining only subjects who are thought to have a reliably low risk of developing a disease as negative, it is possible to prevent subjects with a positive onset risk from being overlooked.

[0039] The sub-determination unit 153 is configured to transmit the result of the determination, either positive or negative, to the output unit 154 .

[0040] The information processing device 10 may also include a cardiac age model learning unit 156. The cardiac age model learning unit 156 has a function of creating the cardiac age trained model 143. For example, the cardiac age model learning unit 156 generates the cardiac age trained model 143 by machine learning using a machine learning algorithm such as DNN, using as training data electrocardiogram data of various people and the cardiac ages of the various people determined by medical professionals based on the results of cardiac ultrasound examinations of the various people.

[0041] The output unit 154 is configured to receive the determination results from the main determination unit 152 and the sub-determination unit 153, and to select the determination result by the main determination unit 152 when the main determination unit 152 determines whether the result is positive or negative, and to select the determination result by the sub-determination unit 153 when the sub-determination unit 153 determines whether the result is positive or negative. The output unit 154 is also configured to display the selected determination result on the screen display unit 13 and / or transmit it to an external device via the communication I / F unit 11.

[0042] Next, a description will be given of the operation of the information processing device 10. The operation of the information processing device 10 is roughly divided into a learning stage and an operation stage.

[0043] In the learning stage, the information processing device 10 creates a specific disease trained model 142 and a cardiac age trained model 143. The specific disease trained model 142 is created by a specific disease model learning unit 155. The specific disease model learning unit 155 generates the specific disease trained model 142 through machine learning using a machine learning algorithm such as DNN, using electrocardiogram data acquired from various people and the presence or absence of the specific disease of the people as training data. However, if the specific disease trained model 142 has already been created on a computer different from the information processing device 10, the process of creating the specific disease trained model 142 by the specific disease model learning unit 155 is omitted. Furthermore, the cardiac age trained model 143 is created by a cardiac age model learning unit 156. The cardiac age model learning unit 156 generates the cardiac age trained model 143 through machine learning using a machine learning algorithm such as DNN, using electrocardiogram data of various people and the cardiac ages of the various people determined by medical professionals based on the results of cardiac ultrasound examinations of the various people as training data. However, if the cardiac age learned model 143 has already been created by a computer different from the information processing device 10, the process of creating the cardiac age learned model 143 by the cardiac age model learning unit 156 is omitted.

[0044] In the operation stage, the information processing device 10 predicts and outputs the risk of developing a specific disease of a subject based on electrocardiogram data acquired from the subject, using the specific disease trained model 142 and the cardiac age trained model 143. The processing in the operation stage will be described below with reference to Fig. 2. Fig. 2 is a flowchart showing an example of the operation of the information processing device 10 in the operation stage.

[0045] First, the acquisition unit 151 acquires the subject's electrocardiogram data from an electrocardiogram measurement device (not shown) or the subject's electronic medical record (not shown) (step S1). Next, the acquisition unit 151 inputs the acquired electrocardiogram data into the specific disease trained model 142 and acquires the subject's risk of developing a specific disease and the certainty of that risk output from the trained model (step S2). Next, if the certainty acquired by the acquisition unit 151 is equal to or greater than a threshold (YES in step S3), the main determination unit 152 determines the subject's risk of developing a specific disease based on the acquired risk and the certainty of that risk (step S4). Then, the output unit 154 displays the determination result of the main determination unit 152 on the screen display unit 13 and / or transmits it to an external device via the communication I / F unit 11 (step S8). Then, the information processing device 10 terminates the process shown in FIG. 2.

[0046] On the other hand, if the confidence level acquired by the acquisition unit 151 is less than the threshold (NO in step S3), the auxiliary determination unit 153 acquires the subject's electrocardiogram data in the same manner as the main determination unit 152 (step S5). Next, the auxiliary determination unit 153 inputs the acquired electrocardiogram data into the cardiac age learned model 143 and acquires the predicted cardiac age output from the learned model (step S6). Next, the auxiliary determination unit 153 determines the subject's risk of developing heart disease based on the cardiac age using the aforementioned determination method 1 or determination method 2 (step S7). Then, the output unit 154 displays the determination result of the auxiliary determination unit 153 on the screen display unit 13 and / or transmits it to an external device via the communication I / F unit 11 (step S8). The process shown in FIG. 4 then ends.

[0047] As described above, the information processing device 10 predicts the risk of developing a specific disease by taking into account information that indicates the actual physical condition of the subject, such as cardiac age, in addition to electrocardiogram data. Therefore, the accuracy of predicting the risk of developing a specific disease of the subject can be improved compared to predictions based only on electrocardiogram data.

[0048] Furthermore, when the certainty of the subject's risk of developing a specific disease output from the specific disease trained model 142 is equal to or greater than a threshold, the information processing device 10 determines the subject's risk of developing a specific disease based on the risk of development and the certainty of the risk of development output from the specific disease trained model 142. This is because it takes into consideration that prediction accuracy is high when the certainty of the risk of development output from the specific disease trained model 142 is equal to or greater than a threshold. As a result, it is possible to prevent unnecessary determination based on cardiac age.

[0049] Furthermore, the information processing device 10 obtains the cardiac age of the subject based on the electrocardiogram data of the subject, which significantly reduces the burden on the subject and the necessary testing equipment compared to performing an ultrasound examination on the subject and obtaining the cardiac age of the subject determined by a medical professional based on the results of the examination.

[0050] Next, a modification of this embodiment will be described.

[0051] The secondary determination unit 153 may acquire the cardiac age of the subject by a method that does not use the cardiac age trained model 143. For example, if the cardiac age is recorded in the subject's electronic medical record, the secondary determination unit 153 may acquire the cardiac age of the subject from the electronic medical record. Alternatively, the secondary determination unit 153 may display several questions regarding the subject's physical condition on the screen display unit 13 and calculate the cardiac age of the subject by performing a predetermined calculation based on the answers to those questions. For example, the questions may include, but are not limited to, chronological age, gender, smoking status, height, weight, presence or absence of diabetes, rheumatoid arthritis, chronic kidney disease, or atrial fibrillation, presence or absence of cardiovascular disease in blood relatives, cholesterol level, and blood pressure.

[0052] If the judgment result output by the output unit 154 is positive, a service may be provided to the subject to guide them to optional tests or detailed tests (such as a 24-hour Holter electrocardiogram test).

[0053] Second Embodiment Next, an information processing device 20 according to a second embodiment of the present invention will be described. FIG.

[0054] Referring to FIG. 3, the information processing device 20 includes an acquisition unit 21, a main determination unit 22, a sub-determination unit 23, and an output unit 24.

[0055] The acquisition unit 21 is configured to input the subject's electrocardiogram data into a first trained model that has been trained to output the person's risk of developing a specific disease and a certainty of the risk of developing the disease in response to input of the person's electrocardiogram data, thereby acquiring the risk of development and the certainty output by the first trained model. The acquisition unit 21 can be configured, for example, similarly to the acquisition unit 151 in FIG. 1 , but is not limited thereto. The main determination unit 22 is configured to determine the subject's risk of development based on the risk of development and the certainty output by the first trained model when the certainty acquired by the acquisition unit 21 is equal to or greater than a predetermined value. The main determination unit 22 can be configured, for example, similarly to the main determination unit 152 in FIG. 1 , but is not limited thereto.

[0056] The auxiliary determination unit 23 is configured to obtain the cardiac age of the subject and determine the risk of onset of the disease of the subject based on the obtained cardiac age when the certainty factor obtained by the obtaining unit 21 is less than a predetermined value. The auxiliary determination unit 23 can be configured in the same manner as the auxiliary determination unit 153 in FIG. 1, for example, but is not limited to this.

[0057] The output unit 24 is configured to output the determination result of the main determination unit 22 when a determination is made by the main determination unit 22, and to output the determination result of the sub determination unit 23 when a determination is made by the sub determination unit 23. The output unit 24 can be configured similarly to the output unit 154 in Fig. 1, for example, but is not limited to this.

[0058] The information processing device 20 configured as described above operates as follows. First, the acquisition unit 21 inputs the subject's electrocardiogram data into a first trained model that has been trained to output the person's risk of developing a specific disease and a certainty factor for that risk in response to the input of the person's electrocardiogram data, thereby acquiring the risk of development and the certainty factor output by the first trained model. Next, if the certainty factor acquired by the acquisition unit 21 is equal to or greater than a predetermined value, the main determination unit 22 determines the subject's risk of development based on the risk and the certainty factor output by the first trained model. On the other hand, if the certainty factor acquired by the acquisition unit 21 is less than the predetermined value, the auxiliary determination unit 23 acquires the subject's cardiac age and determines the subject's risk of development based on the acquired cardiac age. Then, the output unit 24 outputs the determination result by the main determination unit 22 when the determination is made by the main determination unit 22, and outputs the determination result by the auxiliary determination unit 23 when the determination is made by the auxiliary determination unit 23.

[0059] The information processing device 20 configured and operated as described above can improve the accuracy of predicting the risk of a subject developing a specific disease compared to predictions based only on electrocardiogram data, because the risk of a specific disease is predicted by taking into account information that represents the subject's actual physical condition, such as cardiac age, in addition to electrocardiogram data.

[0060] Although the present invention has been described above with reference to the above-mentioned embodiments, the present invention is not limited to the above-mentioned embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0061] For example, the information processing device may use a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an MPU (Micro Processing Unit), an FPU (Floating Number Processing Unit), a PPU (Physics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, a microcontroller, or a combination thereof, instead of the above-mentioned CPU.

[0062] The present invention can be used for diagnostic support by electrocardiogram analysis aimed at early detection of cardiovascular diseases, including hidden atrial fibrillation.

[0063] REFERENCE SIGNS LIST 10, 20 Information processing device 11 Communication I / F unit 12 Operation input unit 13 Screen display unit 14 Memory unit 15 Arithmetic processing unit 21, 151 Acquisition unit 22, 152 Main judgment unit 23, 153 Sub-judgment unit 24, 154 Output unit 141 Program 142 Specific disease trained model 143 Cardiac age trained model 155 Specific disease model training unit 156 Cardiac age model training unit

Claims

1. an acquisition unit that inputs electrocardiogram data of a subject into a first trained model that has been trained to output a risk of developing a specific disease of the person and a certainty of the risk of developing the disease in response to input of the electrocardiogram data of the person, and thereby acquires the risk of development and the certainty output by the first trained model; a main determination unit that determines the onset risk of the subject based on the onset risk and the certainty output by the first trained model when the certainty is equal to or greater than a predetermined value; a sub-determination unit that acquires a cardiac age of the subject when the certainty factor is less than a predetermined value, and determines the risk of the subject developing the disease based on the acquired cardiac age; an output unit that outputs a determination result by the main determination unit when the determination is made by the main determination unit, and outputs a determination result by the sub determination unit when the determination is made by the sub determination unit; An information processing device comprising:

2. In acquiring the cardiac age, the auxiliary determination unit inputs the electrocardiogram data of the subject to a second trained model that is trained to output the cardiac age of the person in response to input of the electrocardiogram data of the person, thereby acquiring the cardiac age output by the second trained model. The information processing device according to claim 1 .

3. The second trained model is machine-trained using electrocardiogram data of various people and cardiac ages determined by medical professionals based on the results of cardiac ultrasound examinations of the various people as training data. The information processing device according to claim 2 .

4. the secondary determination unit, in acquiring the cardiac age, acquires a cardiac age determined by a medical professional based on a result of an ultrasound examination of the subject; The information processing device according to claim 1 .

5. the secondary determination unit acquires the chronological age of the subject, and makes the determination based on a result of comparing the cardiac age with the chronological age. The information processing device according to claim 1 .

6. The sub-determination unit If the cardiac age is less than the chronological age, the result is determined to be negative, and if the cardiac age is equal to or greater than the chronological age, the result is determined to be positive. The information processing device according to claim 5 .

7. the secondary determination unit makes the determination based on a result of comparing the cardiac age with a threshold value. The information processing device according to claim 1 .

8. The sub-determination unit If the cardiac age is less than the threshold, the result is determined to be negative, and if the cardiac age is equal to or greater than the threshold, the result is determined to be positive. The information processing device according to claim 7 .

9. By inputting the electrocardiogram data of a subject into a first trained model that has been trained to output the person's risk of developing a specific disease and a certainty of the risk of developing the disease in response to input of the person's electrocardiogram data, the risk of development and the certainty output by the first trained model are obtained; If the certainty is equal to or greater than a predetermined value, determining the onset risk of the subject based on the onset risk and the certainty output by the first trained model; If the confidence level is less than a predetermined value, the cardiac age of the subject is acquired, and the risk of the subject developing the disease is determined based on the acquired cardiac age; If the certainty is equal to or greater than a predetermined value, output the risk of onset output by the first trained model and a judgment result based on the certainty, and if the certainty is less than a predetermined value, output the judgment result based on the cardiac age. Information processing methods.

10. On the computer, a process of inputting electrocardiogram data of a subject into a first trained model that has been trained to output a risk of developing a specific disease of the person and a certainty of the risk of developing the disease in response to input of the electrocardiogram data of the person, thereby acquiring the risk of development and the certainty output by the first trained model; If the certainty is equal to or greater than a predetermined value, a process of determining the onset risk of the subject based on the onset risk and the certainty output by the first trained model; If the certainty is less than a predetermined value, a process of acquiring the cardiac age of the subject and determining the risk of the subject developing the disease based on the acquired cardiac age; a process of outputting a determination result based on the onset risk and the certainty output by the first trained model when the certainty is equal to or greater than a predetermined value, and outputting a determination result based on the cardiac age when the certainty is less than the predetermined value; A program to perform the following.