Method for predicting a biological event

Abstract

Based on one embodiment of the present disclosure, a method for predicting a bio event is disclosed. Specifically, according to the present disclosure, a computing device acquires biometric information of a patient and utilizes a pre-trained artificial neural network model to generate a first output indicating an expected occurrence time of the bio event based on the biometric information.

Description

Technical Field

[0001] The present invention relates to a method for predicting a biological event. Specifically, the present invention relates to a method for predicting the occurrence time of a biological event, such as an event related to a disease predetermined to have a fatal impact on the health state of a patient, based on the biological information of the patient by utilizing an artificial neural network model.

Background Art

[0002] A method of predicting a potential biological event of a patient, such as cardiac arrest, from the biological information of the patient including body temperature, blood pressure, respiratory rate, heart rate, electrocardiogram, etc., performing intensive monitoring, and taking necessary measures in advance has been used in the medical field.

[0003] Particularly recently, a method for predicting a biological event of a patient using a deep learning model, which is one of the techniques of machine learning, has been studied. A machine learning model that performs such a function operates by receiving a plurality of inputs using a recurrent neural network (RNN), long short-term memory (LSTM), etc., and generating one output value.

[0004] However, the conventional method for predicting a biological event of a patient using a deep learning model remains at providing very limited information, such as the possibility of a biological event such as cardiac arrest occurring in a patient within a certain period of time. In this case, when there are multiple patients who may experience various types of biological events, it is impossible to know which patient is in a more urgent state, and it is also difficult to take necessary measures according to the severity of the disease condition.

[0005] Therefore, there is a need in the industry for a method for predicting biological events in order to take measures necessary for patients with more serious medical conditions.

[0006] Korean Patent Publication KR2022-0040515A discloses a cardiac arrest risk prediction system using an electrocardiogram based on machine learning.

Summary of the Invention

Problems to be Solved by the Invention

[0007] The present disclosure has been devised in response to the above-described background art, and an artificial neural network model generates a first output related to the predicted occurrence time of a biological event based on the input of a patient's biological information, thereby predicting the biological event.

[0008] However, the technical problems to be solved by the present disclosure are not limited to the above-described technical problems, and various technical problems may be included within the scope obvious to a person skilled in the art from the following description.

Means for Solving the Problems

[0009] Based on an embodiment of the present disclosure for solving the above-described problems, a method executed by a computing device for predicting a biological event in a medical field is disclosed. The method may include obtaining biological information of a patient and generating a first output indicating a predicted occurrence time of the biological event based on the biological information by utilizing an artificial neural network model.

[0010] In one embodiment, the biological event may include an event related to a disease predetermined to affect the health state of the patient.

[0011] In one embodiment, the method may further include generating a second output representing the possibility of a biological event occurring within a predetermined time by utilizing the artificial neural network model.

[0012] In one embodiment, the first output may include a value corresponding to the length of the remaining time from the time when the biological information is obtained to the time when the biological event is predicted to occur.

[0013] In one embodiment, the method further includes providing, to a user, comprehensive prediction information related to a biological event based on the first output and the second output, where the comprehensive prediction information can include information capable of determining the priority of each patient among all patients.

[0014] In one embodiment, the comprehensive prediction information can include information filtered by comparing the second output with a predetermined threshold, and information related to the priority of a patient determined based on the result of the filtering and the magnitude of the first output.

[0015] Based on one embodiment of the present disclosure for solving the above-described problems, a method executed by a computing device for predicting a biological event is disclosed. The method includes obtaining biological information of a patient, and generating prediction information related to a biological event based on the biological information by utilizing an artificial neural network model, where the artificial neural network model can be a model learned by multi-task learning based on a first task of predicting the expected occurrence time of a biological event and a second task of predicting the possibility of occurrence of a biological event.

[0016] In one embodiment, the artificial neural network model can be learned based on two or more different learning data sets.

[0017] In one embodiment, the two or more different learning data sets can include first learning data that is biological information with information related to the occurrence time of a patient's biological event set as a label.

[0018] In one embodiment, the two or more different learning data sets can include second learning data that is biological information with binary information related to whether a biological event occurs within a predetermined time set as a label.

[0019] Based on an embodiment of the present disclosure for realizing the above problems, a computer program stored in a computer-readable storage medium including instructions for causing a computing device to execute an operation of predicting a biological event is disclosed. The above operation may include an operation of acquiring biological information of a patient and an operation of generating a first output indicating an expected occurrence time of a biological event based on the biological information by utilizing an artificial neural network model.

[0020] Based on an embodiment of the present disclosure for realizing the above problems, a computing device for predicting a biological event is disclosed. The computing device includes at least one processor and a memory, and the one or more processors can: acquire biological information of a patient, utilize an artificial neural network model, and generate a first output indicating an expected occurrence time of a biological event based on the biological information.

Advantages of the Invention

[0021] The present disclosure can provide biological event prediction information useful for treating patients in whom a biological event has occurred or has not yet occurred. For example, the present disclosure can generate a plurality of different types of prediction information related to a biological event based on the biological information of a patient, and based on the generated plurality of prediction information, it is possible to optimize the treatment for a patient in whom a biological event has occurred or has not yet occurred.

[0022] However, the technical problems to be solved by the present disclosure are not limited to the above-mentioned technical problems, and various technical problems may be included within the scope obvious to those skilled in the art from the following description.

Brief Description of the Drawings

[0023] The following drawings, which are attached for use in the description of embodiments of the present disclosure, are merely a part of the embodiments of the present disclosure, and for those of ordinary skill in the art to which the present disclosure pertains (hereinafter referred to as "ordinary technicians"), it is possible to obtain other drawings based on these drawings without the effort of conceiving a new invention.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

DETAILED DESCRIPTION OF THE INVENTION

[0024] The present disclosure discloses a method for predicting a biological event based on a first output indicating an expected occurrence time of a biological event and a second output indicating a possibility of occurrence of a biological event based on biological information of a patient by utilizing an artificial neural network model.

[0025] Various embodiments will be described below with reference to the drawings. Various explanations are presented in this specification to facilitate understanding of the present disclosure. However, it is obvious that such embodiments can be implemented even without such specific explanations.

[0026] As used herein, terms such as "component", "module", "system", etc. refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or the execution of software. For example, a component can be, but is not limited to, a processing procedure (procedure) executed on a processor, a processor, an object, an execution thread, a program, and / or a computer. For example, an application executed on a computing device and the computing device can both be components. One or more components can reside within a processor and / or an execution thread. One component can be localized within one computer. One component can be distributed among two or more computers. Also, such components can be executed in various computer-readable media having various data structures stored therein. A component can communicate through local and / or remote processing, etc., using, for example, a signal that includes one or more data packets (e.g., data and / or signals from one component interacting with other components in a local system or a distributed system and transmitted through a network such as the Internet to other systems).

[0027] Note that the term "or" is used with the intention of meaning an inclusive "or" rather than an exclusive "or". That is, unless specifically specified and not clear from the context, "X uses A or B" is meant to mean one of the natural inclusive substitutions. That is, it is possible that "X uses A or B" applies to any of the following: X uses A; X uses B; or X uses both A and B. Also, the term "and / or" as used herein should be understood to refer to all possible combinations of one or more of the recited multiple related items and to include them.

[0028] Also, the term "comprising (including)" as a predicate and / or "comprising (including)" as a modifier should be understood to mean that the feature and / or component exists. However, the term "comprising (including)" as a predicate and / or "comprising (including)" as a modifier should be understood not to exclude the existence or addition of one or more other additional features, components, and / or groups thereof. Further, when the number is not specifically specified, or when it is not clear from the context that the singular form is indicated, the singular in this specification and the claims should generally be interpreted to mean "one or more".

[0029] And the term "at least one of A or B" should be interpreted to mean "the case of including only A", "the case of including only B", and "the case of a combination of A and B".

[0030] Those skilled in the art should further recognize that the various exemplary logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described as being related to the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability between hardware and software, the various exemplary components, blocks, configurations, means, logics, modules, circuits, and steps have been generally described in terms of their functionality. Whether such functionality is implemented as hardware or as software depends on the specific application and design constraints of the overall system. A skilled technician can implement the functionality described in various ways for individual specific applications. However, the determination regarding such implementation should not be construed as departing from the scope of the present disclosure.

[0031] The description of the embodiments shown herein is provided so that those having ordinary knowledge in the technical field of the present disclosure can use or implement the present invention. Various modifications to such embodiments will be clearly understood by those having ordinary knowledge in the technical field of the present disclosure. The general principles defined herein can be applied to other embodiments without departing from the scope of the present disclosure. Therefore, the present invention is not limited only to the embodiments shown herein. The present invention should be construed in the broadest scope consistent with the principles and novel features shown herein.

[0032] In the present disclosure, "Bio event" can mean an event related to a disease that is predetermined as affecting the health status of a patient. For example, a bio event can include life-threatening events such as cardiac arrest, sepsis, stroke, arrhythmia, myocardial infarction, heart failure, and unplanned ICU admission.

[0033] FIG. 1 is a block configuration diagram of a computing device for predicting a bio event according to an embodiment of the present disclosure.

[0034] The configuration of the computing device (100) shown in FIG. 1 is merely a simplified example. In an embodiment of the present disclosure, the computing device (100) can include other configurations for implementing the computing environment of the computing device (100), and it is also possible to configure the computing device (100) with only a part of the disclosed configurations.

[0035] The computer device (100) can include a processor (110), a memory (130), and a network unit (150).

[0036] In one embodiment of the present disclosure, the processor (100) can be composed of one or more cores and can include processors for data analysis and deep learning, such as a central processing unit (CPU), a general-purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU). The processor (110) can read a computer program stored in the memory (130) and execute data processing for machine learning in one embodiment of the present disclosure. Based on one embodiment of the present disclosure, the processor (110) can perform operations for neural network learning. In deep learning (DL), the processor (110) can execute calculations for neural network learning, such as processing of input data for learning, extraction of features from the input data, error calculation, and update of neural network weights using backpropagation.

[0037] At least one of the CPU, GPGPU, and TPU of the processor (110) can process network function learning. For example, both the CPU and GPGPU can perform network function learning and data classification using network functions. In one embodiment of the present disclosure, the processors of multiple computing devices can be used together to perform network function learning and data classification using network functions. Also, the computer program executed in the computing device in one embodiment of the present disclosure can be a program executable by the CPU, GPGPU, or TPU.

[0038] According to an embodiment of the present disclosure, a processor (110) can acquire biometric information of a patient. In this case, the route for acquiring biometric information can be data stored in the memory (130) of the computing device, information measured in real time from a biometric information measuring device connected to the computing device, or information received via the network unit (150). However, the present disclosure is not limited to the acquisition routes described above.

[0039] The biometric information can include various biometric-related signals such as the patient's body temperature, blood pressure, respiratory rate, heart rate, electrocardiogram (ECG), electromyogram (EMG), electroencephalogram (EEG), electrodermal activity (EDA), skin temperature (SKT), photoplethysmography (PPG), X-ray image signal, magnetic resonance imaging (MRI) signal, computed tomography (CT) image signal, etc. Also, the biometric information is not limited to the above examples and can include various information acquired from a subject using medical devices, wearable devices, mobile devices, etc.

[0040] The processor (110) can utilize a pre-trained artificial neural network model to generate a first output indicating the predicted occurrence time of a biological event based on the biometric information. A specific method for generating the first output will be described later with reference to FIG. 3.

[0041] In the present disclosure, the above biological event includes an event related to a disease that affects the patient's health state and refers to clinically important symptoms, disease names, etc. In one embodiment, the above biological event can mean cardiac arrest, sepsis, myocardial infarction, heart failure, arrhythmia, etc. However, similar to the above biometric information, the above biological event should not be construed as being limited to what is described as an example in the present disclosure.

[0042] In one embodiment, the artificial neural network model can generate, as a first output, the predicted time of cardiac arrest or sepsis based on the patient's vital signs. In other embodiments, the artificial neural network model can generate, as a first output, the predicted time of occurrence of myocardial infarction, heart failure, arrhythmia, chronic kidney disease, and abnormal serum potassium levels, which are major cardiovascular diseases, based on the patient's electrocardiogram (ECG).

[0043] The processor (110) can generate a second output indicating the likelihood of a biological event based on biological information using a pre-trained artificial neural network model. A specific method for generating the second output will be described later with reference to FIG. 3.

[0044] In one embodiment, the artificial neural network model can generate, as a second output, the likelihood of cardiac arrest or sepsis based on the patient's vital signs. In other embodiments, the artificial neural network model can generate, as a second output, the likelihood of occurrence of myocardial infarction, heart failure, arrhythmia, chronic kidney disease, and abnormal serum potassium levels, which are major cardiovascular diseases, based on the patient's electrocardiogram (ECG).

[0045] The processor (110) can provide the user with comprehensive prediction information regarding the biological event based on the first output and the second output.

[0046] The comprehensive prediction information can serve as a criterion for determining the level of monitoring required for patients who may experience a biological event.

[0047] For example, based on the second output, the processor (110) can predict patients who may experience cardiac arrest within a predetermined time and perform primary filtering, and then, based on the first output, rearrange the patients in ascending order of the predicted time of cardiac arrest occurrence, thereby providing the user with comprehensive prediction information.

[0048] As another example, the processor (110) can output the likelihood and predicted occurrence time of multiple types of biological events, consider the lethality risk and predicted occurrence time for each biological event simultaneously, and provide comprehensive prediction information to the user.

[0049] In the present disclosure, by providing comprehensive prediction information related to biological events to the user, the frequency or amount of information provided, such as alerts being notified to human doctors, increases, so that more detailed monitoring can be efficiently performed.

[0050] In one embodiment of the present disclosure, the memory (130) can include at least one type of storage medium such as flash memory type, hard disk type, multimedia card micro type, card type memory (such as SD or XD memory, etc.), Random Access Memory (RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), magnetic memory, magnetic disk, and optical disk. The computing device (100) can also operate in cooperation with a web storage that executes the storage function of the memory (130) on the internet. The description regarding the above-mentioned memory is merely exemplary, and the present disclosure is not limited thereto.

[0051] In one embodiment of the present disclosure, the network unit (150) can use various wired communication systems such as the Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), Very High Speed DSL (VDSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and a local area network (LAN).

[0052] Also, the network unit (150) in this specification can utilize various wireless communication systems such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single Carrier - FDMA (SC - FDMA), and other systems.

[0053] In the present disclosure, the network unit (150) can utilize any form of wired or wireless communication system.

[0054] The technology described in this specification can be used not only in the above - mentioned network but also in other networks.

[0055] Figure 2 is a schematic diagram showing network functions in one embodiment of the present disclosure.

[0056] Throughout this specification, the terms computational model, neural circuit network, network function, and neural network can be used interchangeably. A neural circuit network generally consists of a set of interconnected computational units, often referred to as nodes. Such nodes can also be called neurons. A neural circuit network is composed of at least one or more nodes. The nodes (or neurons) that make up a neural circuit network can be interconnected by one or more links.

[0057] In a neural circuit network, one or more nodes connected via a link can form a relative relationship of input nodes and output nodes. The concepts of input nodes and output nodes are relative. Any node that is an output node with respect to a certain node can be an input node in its relationship with other nodes, and vice versa. As described above, the relationship between input nodes and output nodes can be established centered around the link. One input node can be connected via a link to one or more output nodes, and vice versa.

[0058] In the relationship between an input node and an output node connected via one link, the value of the data of the output node can be determined based on the data input to the input node. Here, the node connecting the input node and the output node can have a weight value. The weight value can be variable and can be changed by the user or an algorithm for the neural circuit network to perform the desired function. For example, when one or more input nodes are interconnected by each link to one output node, the output node can determine the value of the output node based on the values input to the input nodes connected to the output node and the weight values set for the links corresponding to each input node.

[0059] As described above, a neural circuit network is formed by interconnecting one or more nodes via one or more links to form the relationship between the input nodes and the output nodes within the neural circuit network. In a neural circuit network, the characteristics of the neural circuit network can be determined by the number of nodes and links, the correlation relationship between the nodes and links, and the values of the weighted values assigned to each link. For example, if there are two neural circuit networks with the same number of nodes and links, but different values of the weighted values of the links, the two neural circuit networks can be recognized as different ones.

[0060] A neural circuit network can be composed of a set of one or more nodes. A subset of the nodes that make up the neural circuit network can form a layer. Among the multiple nodes that make up the neural circuit network, some can form one layer based on the distance from the first input node. For example, a set of nodes with a distance of n from the first input node can form the nth layer. The distance from the first input node can be defined based on the minimum number of links that must be passed through to reach the node from the first input node. However, such a definition of a layer is arbitrarily cited for the purpose of explanation, and the composition of layers in a neural circuit network can be defined in a way different from the above description. For example, the layer of nodes can also be defined based on the distance from the final output node.

[0061] The first input node can mean one or more nodes among the nodes in the neural circuit network where data is directly input without passing through a link in the relationship with other nodes. Or, in the relationship between nodes based on links in the neural network of the neural circuit network, it can mean a node that does not have other input nodes connected via a link. Similarly, the final output node can mean one or more nodes among the nodes in the neural circuit network that do not have an output node in the relationship with other nodes. Also, a hidden node can mean a node that is not the first input node or the final output node and constitutes the nodes of the neural circuit network.

[0062] The neural circuit network according to an embodiment of the present disclosure can be a neural circuit network in which the number of nodes in the input layer is the same as the number of nodes in the output layer, and as it progresses from the input layer to the hidden layer, the number of nodes first decreases and then increases again. The neural circuit network according to an embodiment of the present disclosure can be a neural circuit network in which the number of nodes in the input layer is less than the number of nodes in the output layer, and as it progresses from the input layer to the hidden layer, the number of nodes decreases. Also, the neural circuit network according to another embodiment of the present disclosure can be a neural circuit network in which the number of nodes in the input layer is more than the number of nodes in the output layer, and as it progresses from the input layer to the hidden layer, the number of nodes increases. The neural circuit network in another embodiment of the present disclosure can be a neural circuit network that combines the above-described neural circuit networks.

[0063] A deep neural network (DNN: deep neural network, deep neural circuit network) can be meant to refer to a neural circuit network that includes a plurality of hidden layers in addition to the input layer and the output layer. By using a deep neural network, the latent structures of data can be grasped. That is, the latent structures of photos, articles, videos, voices, music (for example, whether a certain object is shown in a photo, what the content and sentiment of an article are, what the content and sentiment of a voice are, etc.) can be grasped. Deep neural networks can include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, GANs (Generative Adversarial Networks), restricted boltzmann machines (RBMs), deep belief networks (DBNs), Q networks, U networks, Sham networks, Generative Adversarial Networks (GANs), etc. The above-mentioned deep neural networks are merely illustrative and the present disclosure is not limited thereto.

[0064] In one embodiment of the present disclosure, the network function may also include an autoencoder. An autoencoder can be a type of artificial neural network circuit for outputting output data similar to the input data. The autoencoder can include at least one hidden layer, and an odd number of hidden layers can be arranged between the input and output layers. The number of nodes in each layer can decrease from the number of nodes in the input layer towards the intermediate layer called the bottleneck layer (encoder), and can also expand in a form symmetric to the reduction from the bottleneck layer towards the output layer (symmetric to the input layer). The autoencoder can perform non-linear dimensionality reduction. The number of input and output layers can correspond to the dimensions after preprocessing of the input data. In the autoencoder structure, the number of nodes in the hidden layers included in the encoder can have a structure that decreases as it gets farther from the input data. If the number of nodes in the bottleneck layer (the layer with the fewest number of nodes located between the encoder and the decoder) is too small, there is a possibility that not enough information will be transmitted, so it may be maintained above a certain number (for example, more than half of the input layer, etc.).

[0065] The neural network can be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. The training of the neural network can be a process of providing the neural network with knowledge for the neural network to perform a specific operation.

[0066] A neural network can be trained in a direction to minimize the error of the output. In the training of a neural network, training data is repeatedly input into the neural network, the error between the output of the neural network regarding the training data and the target is calculated, and the error of the neural network is backpropagated from the output layer to the input layer of the neural network in a direction to reduce the error, and the weight values of each node of the neural network are updated. In the case of supervised learning, training data with the correct answer labeled for each individual training data is used (that is, labeled training data), and in the case of unsupervised learning, there may be cases where the correct answer is not labeled for each individual training data. That is, for example, the training data in supervised learning regarding data classification can be data with a category labeled for each of the training data. By inputting the labeled training data into the neural network and comparing the output (category) of the neural network with the label of the training data, it is possible to calculate the error. As another example, in the case of unsupervised learning regarding data classification, it is possible to calculate the error by comparing the input training data with the output of the neural network. The calculated error is backpropagated in the reverse direction (that is, from the output layer to the input layer direction) in the neural network, and it is possible to update the connection weight values of each node of each layer of the neural network through backpropagation. The amount of change in the connection weight value of each updated node can be determined by the learning rate. The calculation of the neural network for the input data and the backpropagation of the error can constitute a learning cycle (epoch). The application method of the learning rate can change depending on the number of repetitions of the learning cycle of the neural network. For example, at the initial stage of the neural network training, the learning rate can be increased to improve the efficiency by enabling the neural network to quickly secure a certain level of performance, and at the latter half of the training, the learning rate can be decreased to increase the accuracy.

[0067] In the learning of a neural network, generally, the training data can be a subset of the actual data (i.e., the data to be processed using the learned neural network). Therefore, there may be a learning cycle in which the error related to the training data decreases, but the error related to the actual data increases. Overfitting is a phenomenon in which the error increases in the actual data because the training data is overlearned in this way. For example, a neural network that has learned cats by seeing yellow cats may not be able to recognize cats of colors other than yellow, which can be a type of overfitting. Overfitting can cause an increase in the error of machine learning algorithms. To prevent such overfitting, various optimization methods can be applied. To prevent overfitting, methods such as increasing the training data, regularization, dropout (deactivating some of the nodes in the network during the learning process), and using a batch normalization layer can be applied.

[0068] FIG. 3 is a flowchart showing a process for predicting a biological event according to an embodiment of the present disclosure.

[0069] According to FIG. 3, the process for predicting a biological event can include a step of acquiring biological information of a patient (S110), a step of generating a first output indicating an expected occurrence time of a biological event based on the biological information by utilizing an artificial neural network model (S130), a step of generating a second output indicating the possibility of occurrence of a biological event based on the biological information by utilizing the artificial neural network model (S150), and a step of providing comprehensive prediction information related to the biological event to a user (S170).

[0070] In step S110, the processor (110) can acquire the biological information of the patient. The specific method of acquiring the biological information of the patient has been described above with reference to FIG. 1.

[0071] In step S130, the processor (110) can utilize the artificial neural network model to generate a first output indicating the predicted occurrence time of a biological event based on biological information. At this time, the first output can include a value corresponding to the length of the remaining time until the biological event is predicted to occur. For example, the first output can be designed to have a larger value as the predicted time of cardiac arrest in the patient approaches. More specifically, the artificial neural network model can output 0 when it is predicted that a biological event will occur after 24 hours, 0.5 when it is predicted that a biological event will occur after 12 hours, and 0.75 when it is predicted that a biological event will occur after 6 hours, as the first output. A user, for example, a human doctor, can utilize the first output of the artificial neural network model to determine at what point a biological event will occur in the patient.

[0072] In step S150, the processor (110) can utilize the artificial neural network model to generate a second output indicating the possibility of occurrence of a biological event based on biological information. At this time, the second output can include information indicating the possibility of a biological event occurring within a predetermined time.

[0073] For example, the second output can be a value representing, by a real number between 0 and 1, the possibility of cardiac arrest occurring in the patient within the predetermined time. In this case, the higher the possibility of cardiac arrest occurring within the predetermined time, the closer the value can be to 1, and when it is definitely predicted that cardiac arrest will occur, the second output can be 1.

[0074] Specifically, the artificial neural network model is configured to output the possibility of the occurrence of cardiac arrest in a patient. When the possibility of cardiac arrest occurring in patient A within a predetermined time is higher than that in patient B, the second output of the artificial neural network model related to patient A can be set to a higher value than the second output of the artificial neural network model related to patient B. In this case, the second output value related to patient A can be in the form of 0.8, and the second output value related to patient B can be in the form of 0.2.

[0075] In step S170, the processor (110) can provide the user with comprehensive prediction information related to the biological event. At this time, the comprehensive prediction information can be information related to the possibility of a biological event occurring within a predetermined time in a certain patient, and if it is predicted to occur, how much time will elapse before it is predicted to occur.

[0076] For example, based on the second output, the processor (110) can first filter out patients whose predicted probability of cardiac arrest within a predetermined time is equal to or higher than a predetermined threshold among all patients, and then, based on the first output, rank the patients in ascending order of the predicted time of cardiac arrest occurrence. Then, for patients with a higher rank, the comprehensive prediction information can be provided to the user in a way that displays a higher severity of the medical condition. Therefore, based on the above comprehensive prediction information, it is possible to determine the priority order of each patient among all patients.

[0077] In the above example, the artificial neural network model is configured to output the possibility of the occurrence of cardiac arrest in a patient. However, in the present disclosure, the artificial neural network model can also be configured to receive the input of the patient's biological information and generate outputs related to different types of biological events. For example, the artificial neural network model of the present disclosure can include a first sub-model related to cardiac arrest and a second sub-model related to sepsis. In this case, the first sub-model can receive the input of the patient's biological information and output the predicted time and possibility of the occurrence of cardiac arrest in the patient, and the second sub-model can receive the input of the patient's biological information and output the predicted time and possibility of the occurrence of sepsis in the patient, which can be an artificial neural network model.

[0078] However, the types of biological events in the present disclosure are not limited to the above examples. When generating outputs related to different types of biological events, the artificial neural network model can be an artificial neural network model configured to apply the multi-task learning method to generate outputs related to different types of biological events.

[0079] In the following, an artificial neural network model that generates prediction information related to a biological event based on biological information will be described.

[0080] In the present disclosure, the artificial neural network model that generates prediction information related to a biological event based on biological information can be a machine learning model, more specifically, a deep learning model.

[0081] More specifically, the artificial neural circuit network model of the present disclosure can include neural circuit networks such as a Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Transformer. However, in order to configure the artificial neural circuit network model of the present disclosure, it is possible to add or remove a neural circuit network in an appropriate form, and the present disclosure is not limited to the types of neural circuit network models listed in the above examples.

[0082] The artificial neural circuit network model of the present disclosure can receive multiple types of inputs simultaneously. Specifically, the artificial neural circuit network model of the present disclosure can simultaneously receive inputs of multiple types of biological information from human biological information and generate one or more outputs. More specifically, the artificial neural circuit network model can have a "many-to-one" structure that receives the patient's body temperature, blood pressure, respiratory rate, heart rate, and electrocardiogram as inputs and generates one or more outputs from a large number of inputs. Alternatively, the artificial neural circuit network model of the present disclosure can have a "many-to-many" structure that simultaneously receives inputs of multiple types of biological information from human biological information and simultaneously outputs the predicted occurrence times of different biological events.

[0083] The artificial neural circuit network model of the present disclosure can be learned by a multi-task learning method based on the first task of predicting the predicted occurrence time of a biological event and the second task of predicting the possibility of the occurrence of a biological event. Multi-task learning is a learning method of an artificial neural network that enables one model to execute multiple types of tasks that are similar or different from each other. For example, for one neural circuit network model, it is possible to make it classify dog images and cat images from the images given as the first task, and at the same time, learn to predict the age of the animals appearing in the images from the images given as the second task.

[0084] To perform multi-task learning, the artificial neural network model of the present disclosure can be learned based on two or more different learning data sets. In this case, the two or more different learning data sets include a second learning data, which is biological information with binary information related to whether a biological event occurs or not set as a label within a predetermined time, and a first learning data, which is biological information with information related to the occurrence time of a patient's biological event set as a label. Specific explanations regarding each learning data will be described later with reference to FIGS. 4a to 4c.

[0085] By learning two different types of learning data through multi-task learning, the artificial neural network model of the present disclosure can simultaneously generate one output for predicting the expected occurrence time of a biological event and another output for predicting the possibility of occurrence of a biological event. Therefore, in the present disclosure, based on the expected occurrence time of a biological event and the possibility of occurrence of a biological event, it is possible to provide comprehensive prediction information related to the biological event to the user, and it is possible to provide information related to the priority or degree of measures in a plurality of patients to a human doctor.

[0086] For example, an artificial neural network model is configured to generate an output related to cardiac arrest. For patient A, the first output of the artificial neural network model of the present disclosure is 0.8 and the second output is 0.6. For patient B, it is assumed that the first output of the artificial neural network is 0.2 and the second output is 0.8. At this time, the possibility of cardiac arrest occurring within a predetermined time is higher for patient B, but the first output related to patient A has a larger value than the first output related to patient B. Therefore, the time when cardiac arrest is expected to occur is predicted to be closer for patient A than for patient B. In this case, conventionally, only the possibility of cardiac arrest occurring was considered, and measures for patient B were prioritized over measures for patient A. However, according to the artificial neural network model of the present disclosure, it can be seen that patient A has a lower possibility of cardiac arrest occurring, but the occurrence time of the biological event is predicted to be considerably earlier (i.e., the order is earlier) than that of patient B. Therefore, based on the output of the artificial neural network of the present disclosure, it is possible to make a judgment to prioritize measures for patient A over measures for patient B.

[0087] In other embodiments, the second output can be filtered by comparison with a predetermined threshold value, and for a plurality of second outputs having values equal to or greater than the above threshold value, the priority order of the patients can be determined based on the magnitude of the first output. For example, when the above threshold value is determined to be 0.8, the second output of patient A in the above example is filtered because it is less than the above threshold value, and a human doctor can prioritize measures for patient A over measures for patient B without having to judge the urgency of the medical conditions of patient A and patient B themselves.

[0088] As yet another embodiment, the priority order can be determined primarily based on the second output, and the final priority order can be determined based on the magnitude of the first output. For example, the priority order of a plurality of patients whose second output has values from 0.9 to 1 is made the highest, and after classification once, the final priority order can be determined based on the values of the first output of the plurality of patients. At this time, it is obvious to those skilled in the art that the range of the second output for determining the priority order can be appropriately adjusted according to the various environments in which the present invention is implemented.

[0089] As a result, according to the present disclosure, an effect is produced that more appropriate measures can be taken for a patient as compared with the conventional technology that only provided the possibility of the occurrence of a biological event.

[0090] FIGS. 4A and 4B are conceptual diagrams showing labels of first learning data based on an embodiment of the present disclosure.

[0091] Based on an embodiment of the present disclosure, an artificial neural network model can be learned by first learning data including biological information in which information related to the occurrence time of a biological event is set as a label.

[0092] The first learning data can be biological information data in which continuous or discontinuous label values from 0 to 1 are specified by normalizing the time point when a biological event occurs based on a predetermined time. For example, as shown in FIG. 4A, the first learning data can be biological information data labeled so as to have a value that linearly increases as the time point when a biological event occurs is closer. Specifically, when the predetermined time is 24 hours and for a certain learning data, if a biological event, for example, cardiac arrest occurs 18 hours later, the label value of the learning data can be set to 0.25. Also, if cardiac arrest occurs 12 hours later, the label value of the learning data can be set to 0.5. Further, for a certain learning data, if cardiac arrest occurs 6 hours later, the label value of the learning data can be set to 0.75.

[0093] Also, as another example, as shown in FIG. 4B, the first learning data can be biological information data labeled so as to have a value that exponentially grows as the time point when a biological event occurs is closer.

[0094] However, the labeling method in the present disclosure is not limited to the examples shown in FIGS. 4a and 4b, and various labeling methods that determine weights in various ways depending on the timing when a biological event occurs can be used. Also, it is obvious to a person skilled in the art that the design of the artificial neural network model can be selectively changed so as to conform to the labeling method used.

[0095] When learned with such data, the first output of the artificial neural network model that predicts the occurrence time of a biological event can have a value from 0 to 1. The user can interpret that the larger the value of the first output of the artificial neural network model, the closer the predicted time when the biological event occurs in the patient. Thus, it is possible to predict the occurrence time of a biological event through model learning based on the first learning data.

[0096] FIG. 4c is a conceptual diagram showing the label of the second learning data based on an embodiment of the present disclosure.

[0097] An artificial neural network model based on an embodiment of the present disclosure can be learned with second learning data including biological information with a label set to "binary information regarding whether or not a biological event occurs within a predetermined time".

[0098] The second learning data can include biological information data having a binary label, where the label is specified as 1 if a biological event occurs within a predetermined time, for example, within 24 hours, and 0 otherwise.

[0099] As described above, the second output of the artificial neural network model that predicts the likelihood of a biological event, which is learned from data with binary-formatted labels, can have a real number value from 0 to 1. The user can interpret that the higher the value of the second output of the artificial neural network model, the higher the likelihood that a biological event of the patient will occur within a predetermined time. Therefore, through model learning based on the second training data, it is possible to predict the likelihood that a biological event will occur within a predetermined time.

[0100] Based on one embodiment of the present disclosure, a computer-readable storage medium storing a data structure is disclosed.

[0101] A data structure can mean the organization, management, and storage of data that enable efficient access to and modification of the data. A data structure can mean a data organization for solving a specific problem (for example, data search in the shortest time, data storage, data modification). A data structure can also be defined as the physical or logical relationship between data elements designed to support a specific data processing function. The logical relationship between data elements can include the concatenation relationship between data elements considered by the user. The physical relationship between data elements can include the actual relationship between data elements physically stored in a computer-readable storage medium (for example, a hard disk). A data structure can specifically include a set of data, the relationship between data, functions or commands applicable to the data. With an effectively designed data structure, a computing device can perform calculations while minimizing the use of the resources of the computing device. Specifically, the computing device can enhance the efficiency of operations, reading, insertion, deletion, comparison, exchange, and search through an effectively designed data structure.

[0102] Data structures can be classified into linear data structures and non-linear data structures according to their forms. A linear data structure may be a structure in which only one data is connected after another data. Linear data structures can include lists, stacks, queues, and deques. A list can mean a series of data sets with an internal order. A list can include a linked list. A linked list can be a data structure in which data is connected in a way that each data has a pointer and is connected in a column. In a linked list, the pointer can include connection information with the next or previous data. A linked list can be represented as a singly linked list, a doubly linked list, or a circular linked list according to its form. A stack may be a data list structure with restricted access to data. A stack may be a linear data structure that can process (e.g., insert or delete) data only at one end of the data structure. The data stored in a stack may be a data structure (LIFO - Last in First Out) where the later the data enters, the earlier it comes out. A queue is a data arrangement structure with restricted access to data and, unlike a stack, can be a data structure (FIFO - First in First Out) where the later the data is stored, the later it comes out. A deque can be a data structure that can process data at both ends of the data structure.

[0103] A non-linear data structure may be a structure in which multiple data are connected after one data. Non-linear data structures can include graph data structures. A graph data structure can be defined by vertices and edges, and an edge can include a line connecting two different vertices. A graph data structure can include a tree data structure. A tree data structure can be a data structure formed by a path connecting two different vertices among the multiple vertices included in the tree. That is, it can be a data structure that does not form a loop in the graph data structure.

[0104] Throughout this specification, an arithmetic model, a neural circuit network, a network function, and a neural network can be used interchangeably. (Hereinafter, they will be uniformly described using the term "neural network".) A data structure can include a neural network. And a data structure including a neural network can be stored in a computer-readable storage medium. A data structure including a neural network can also include data input to the neural network, weight values of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, and a loss function for training the neural network. A data structure including a neural network can include any of the components of the disclosed configuration. That is, a data structure including a neural network can be configured to include all or any combination of data input to the neural network, weight values of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, a loss function for training the neural network, etc. In addition to the foregoing configuration, a data structure including a neural network can include any other information that determines the characteristics of the neural network. Also, the data structure can include all forms of data used or generated during the arithmetic process of the neural network, and is not limited to the foregoing matters. A computer-readable storage medium can include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network can generally be composed of a set of interconnected computing units commonly called nodes. Such nodes can be called neurons. A neural network is composed of at least one or more nodes.

[0105] A data structure can include data input to a neural network. A data structure including data input to a neural network can be stored in a computer-readable storage medium. The data input to the neural network can include training data input during the learning process of the neural network and / or input data input to the neural network after learning is completed. The data input to the neural network can include pre-processed data and / or data to be pre-processed. Pre-processing can include a data processing process for inputting data to the neural network. Therefore, the data structure can include data to be pre-processed and data generated by pre-processing. The above-described data structure is merely exemplary, and the present disclosure is not limited thereto.

[0106] A data structure can include the weight values of a neural network. (In this specification, weight values and parameters can be used interchangeably.) And a data structure including the weight values of a neural network can be stored in a computer-readable storage medium. A neural network can include a plurality of weight values. The weight values are variable and can be varied by a user or an algorithm to perform the functions desired by the neural network. For example, when one or more input nodes are interconnected by respective links to one output node, the output node can determine an output node value based on the values input to the input nodes connected to the output node and the parameters set for the respective links corresponding to the input nodes. The above-described data structure is merely exemplary, and the present disclosure is not limited thereto.

[0107] By way of example and not limitation, the weighted values can include weighted values that vary during the neural network learning process and / or weighted values after the neural network learning is completed. The weighted values that are varied during the neural network learning process can include the weighted values at the start of the learning cycle and / or the weighted values that are varied during the learning cycle. The weighted values after the neural network learning is completed can include the weighted values after the learning cycle is completed. Accordingly, a data structure including the weighted values of the neural network can include a data structure including the weighted values that vary during the neural network learning process and / or the weighted values after the neural network learning is completed. Accordingly, the above-described weighted values and / or combinations of each weighted value shall be included in a data structure including the weighted values of the neural network. The foregoing data structure is merely illustrative and the present disclosure is not limited thereto.

[0108] A data structure including the weighted values of the neural network can be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization may be a process of converting a data structure into a form that can be stored in the same or another computing device and later reconstructed and used. A computing device can serialize a data structure and transmit and receive data via a network. A data structure including the weighted values of the serialized neural network can be reconstructed on the same computing device or another computing device through deserialization. A data structure including the weighted values of the neural network is not limited to serialization. Further, a data structure including the weighted values of the neural network can include a data structure (e.g., non-linear data structures such as B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree) for enhancing the efficiency of operations while minimizing the use of resources of the computing device. The foregoing matters are merely illustrative and the present disclosure is not limited thereto.

[0109] The data structure can include hyper-parameters of the neural network. And the data structure including the hyper-parameters of the neural network can be stored in a computer-readable storage medium. The hyper-parameters can be variables that can be varied by the user. The hyper-parameters can include, for example, a learning rate, a cost function, the number of learning cycle iterations, weight initialization (e.g., setting the range of weights to be initialized), the number of hidden units (e.g., the number of hidden layers, the number of nodes in the hidden layer). The foregoing data structure is merely exemplary and the present disclosure is not limited thereto.

[0110] FIG. 5 is a simplified and general schematic diagram relating to an exemplary computing environment in which embodiments of the present disclosure can be implemented.

[0111] Although it has been described above that the present disclosure can generally be implemented by a computing device, those skilled in the art will well understand that the present disclosure can be implemented in combination with computer-executable instructions and / or other program modules that can be executed on one or more computers and / or as a combination of hardware and software.

[0112] Generally, a module in this specification includes routines, programs, components, data structures, and the like that perform specific tasks or implement specific abstract data types. Also, those skilled in the art will well understand that the methods of the present disclosure can be implemented by other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based systems, or programmable household appliances, etc. (each of which can operate in connection with one or more associated devices).

[0113] The embodiments described in the present disclosure can further be implemented in a distributed computing environment where a certain task is executed by a remote processing device connected through a communication network. In a distributed computing environment, program modules can be located in both local and remote memory storage devices.

[0114] The computer includes a variety of computer-readable media. Any media accessible by the computer can be a computer-readable media, and such computer-readable media includes volatile and non-volatile media, transitory and non-transitory media, removable and non-removable media. By way of example and not limitation, computer-readable media can include computer-readable storage media and computer-readable transmission media. Computer-readable storage media is volatile and non-volatile media, transitory and non-transitory media, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer-readable storage media includes RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, DVD (digital video disk) or other optical disk storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other media that can be accessed by a computer and can be used to store information, but is not limited thereto.

[0115] Computer-readable transmission media typically implements computer-readable instructions, data structures, program modules or other data, etc. in a modulated data signal such as a carrier wave or other transport mechanism, and includes all information transmission media. The term modulated data signal means a signal in which one or more of the characteristics of the signal are set or changed so as to encode information in the signal. By way of example and not limitation, computer-readable transmission media includes wired media such as a wired network or a direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Any combination by any of the foregoing media is also considered to be within the scope of computer-readable transmission media.

[0116] An exemplary environment (1100) is shown that implements various aspects of the present disclosure, including a computer (1102), which includes a processing device (1104), a system memory (1106), and a system bus (1108). The system bus (1108) connects system components, including but not limited to the system memory (1106), to the processing device (1104). The processing device (1104) can be any of a variety of commercial processors. Dual processors and other multiprocessor architectures can also be utilized as the processing device (1104).

[0117] The system bus (1108) can be any of a plurality of types of bus structures that can be further interconnected to a local bus that uses any of a memory bus, a peripheral device bus, and various commercial bus architectures. The system memory (1106) includes a read-only memory (ROM) (1110) and a random access memory (RAM) (1112). The basic input / output system (BIOS) is stored in non-volatile memory (1110) such as ROM, EPROM, EEPROM, etc., and this BIOS includes basic routines that support the exchange of information between a plurality of components in the computer (1102) during startup and the like. The RAM (1112) can also include high-speed RAM such as static RAM for caching data.

[0118] In the computer (1102), there is also a built-in hard disk drive (HDD) (1114) (e.g., EIDE, SATA) - this built-in hard disk drive (1114) can also be configured for external use within a suitable chassis (not shown) -, a magnetic floppy disk drive (FDD) (1116) (e.g., for reading from and writing to a removable diskette (1118)) and an optical disk drive (1120) (e.g., for reading from a CD-ROM disk (1122), reading from and writing to other high-capacity optical media such as DVDs). The hard disk drive (1114), the magnetic disk drive (1116) and the optical disk drive (1120) can each be connected to the system bus (1108) by a hard disk drive interface (1124), a magnetic disk drive interface (1126) and an optical drive interface (1128). The interface (1124) for the implementation of an external drive includes, for example, at least one or both of USB (Universal Serial Bus) and IEEE1394 interface technologies.

[0119] These drives and the computer-readable media associated therewith provide non-volatile storage of data, data structures, computer-executable instructions, and the like. In the case of the computer (1102), the drives and media correspond to storing any data in a suitable digital format. Although the foregoing description of computer-readable storage media has touched on HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will also recognize that other types of storage media readable by a computer, such as zip drives, magnetic cassettes, flash memory cards, cartridges, and the like, can also be used in exemplary operating environments, and furthermore, it will be well understood that any one of such media can contain computer-executable instructions for performing the methods of the present disclosure.

[0120] A number of program modules, including an operating system (1130), one or more application programs (1132), other program modules (1134), and program data (1136), can be stored in a drive and RAM (1112). All or a portion of the operating system, applications, modules, and / or data can also be cached in RAM (1112). It will be appreciated that the present disclosure can be implemented by various commercially available operating systems or combinations of multiple operating systems.

[0121] A user can input commands and information into the computer (1102) through one or more wired and wireless input devices, such as a keyboard (1138) and a pointing device such as a mouse (1140). Other input devices (not shown) can include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, and the like. These and other input devices can be connected to the processing device (1104) through an input device interface (1142) that is often connected to the system bus (1108), but can also be connected by other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, and the like.

[0122] A monitor (1144) or other type of display device is also connected to the system bus (1108) through an interface such as a video adapter (1146). In addition to the monitor (1144), the computer generally includes other peripheral output devices such as speakers, printers, and the like (not shown).

[0123] The computer (1102) can operate in a networked environment using logical connections to one or more remote computers, such as (a plurality of) remote computers (1148), via wired and / or wireless communication. The (a plurality of) remote computers (1148) can be workstations, server computers, routers, personal computers, portable computers, microprocessor-based entertainment devices, peer devices, or other common network nodes, and generally include many or all of the components described for the computer (1102), but for simplicity, only the memory storage device (1150) is illustrated. The illustrated logical connections include wired and wireless connections in a local area network (LAN) (1152) and / or a larger network, such as a wide area network (WAN) (1154). Such LAN and WAN networking environments are common in offices and companies, facilitating enterprise-wide computer networks such as intranets, all of which can be connected to the world-wide computer network, such as the Internet.

[0124] When used in a LAN networking environment, the computer (1102) is connected to the local network (1152) through a wired and / or wireless communication network interface, or an adapter (1156). The adapter (1156) can facilitate wired or wireless communication to the LAN (1152), and this LAN (1152) also includes a wireless access point installed thereon for communicating with the wireless adapter (1156). When used in a WAN networking environment, the computer (1102) can include a modem (1158), be connected to a communication server on the WAN (1154), or have other means for setting up communication through the WAN (1154), such as through the Internet. The modem (1158), which can be an internal or external, wired or wireless device, is connected to the system bus (1108) through a serial port interface (1142). In a networked environment, the program modules or portions thereof described for the computer (1102) can be stored in a remote memory / storage device (1150). It is readily understood that the illustrated network connections are exemplary, and other means for establishing communication links between multiple computers can be used.

[0125] The computer (1102) operates to communicate with any wireless device or unit arranged and operating in wireless communication, such as a printer, scanner, desktop and / or portable computer, PDA (portable data assistant), communication satellite, any equipment or location related to a wirelessly detectable tag, and a telephone. This includes at least Wi-Fi and Bluetooth (registered trademark) wireless technologies. Thus, the communication can be in a predefined structure like a conventional network or simply an ad hoc communication between at least two devices.

[0126] Wi-Fi (Wireless Fidelity) enables connection to the Internet and the like without being wired. Wi-Fi is a wireless technology like a cell phone that allows such devices, for example, computers to send and receive data both indoors and outdoors, that is, from anywhere within the coverage area of a base station. Wi-Fi networks use wireless technologies such as IEEE802.11 (a, b, g, etc.) to provide a secure, reliable, and high-speed wireless connection. Wi-Fi can be used to connect computers to each other and to the Internet and wired networks (using IEEE802.3 or Ethernet). Wi-Fi networks can operate at data rates such as 11 Mbps (802.11a) or 54 Mbps (802.11b) in unlicensed 2.4 and 5 GHz wireless bands, or can operate in products that include both bands (dual band).

[0127] Those with ordinary knowledge in the technical field of the present disclosure can understand that information and signals can be represented using any of a variety of different technologies and techniques. For example, the data, instructions, commands, information, signals, bits, symbols, and chips that can be referenced in the above description can be represented by voltages, currents, electromagnetic waves, magnetic fields, etc., or particles, optical fields, etc., or particles, or any combination thereof.

[0128] Those of ordinary skill in the art of the present disclosure will appreciate that the various exemplary logical blocks, modules, processors, means, circuits, and algorithm steps recited in the description of the embodiments disclosed herein can be implemented in electronic hardware, various forms of program or design code (referred to herein as "software" for convenience), or any combination thereof. To clearly illustrate such interchangeability of hardware and software, various exemplary components, blocks, modules, circuits, and steps have been generally described above in terms of their functions. Whether such functions are implemented in hardware or software depends upon the particular application and design constraints imposed on the overall system. Those of ordinary skill in the art of the present disclosure can implement the functions described in various ways for each particular application, but such implementations should not be construed as departing from the scope of the present disclosure.

[0129] The various embodiments shown herein can be implemented by a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term "article of manufacture" includes any computer program accessible from any computer-readable device, carrier, or medium. For example, a computer-readable storage medium includes, but is not limited to, magnetic storage devices (e.g., hard disk, floppy disk, magnetic strip, etc.), optical disks (e.g., CD, DVD, etc.), smart cards, and flash memory devices (e.g., EEPROM, card, stick, key drive, etc.). Also, the various storage media shown herein include one or more devices and / or other machine-readable media for storing information.

[0130] It should be understood that the specific order or hierarchical structure of the multiple steps in the presented process is an example of an exemplary approach. Based on design priorities, it should be understood that within the scope of the present disclosure, the specific order or hierarchical structure of the steps in the process can be rearranged. The appended method claims provide elements of various steps in a sample order, but are not meant to be limited to the specific order or hierarchical structure presented.

[0131] The description of the presented embodiments is provided so that those of ordinary skill in any art of the present disclosure can make use of or practice the present disclosure. Various modifications to such embodiments will be readily understood by those of ordinary skill in the art of the present disclosure, and the general principles defined herein can be applied to other embodiments without departing from the scope of the present disclosure. Accordingly, the present disclosure is not limited by the embodiments shown herein, but should be construed in the broadest scope consistent with the principles and novel features shown herein.

[0132] As described above, based on the best mode for carrying out the invention, the relevant content has been described.

Claims

1. A method executed by a computing device for predicting a bio event, comprising: obtaining biometric information of a patient; and utilizing an artificial neural network model to generate a first output indicating an expected occurrence time of the bio event based on the biometric information. A method.

2. In claim 1, the bio event includes an event related to a disease predetermined to affect the health state of the patient. A method.

3. In claim 1, further comprising utilizing the artificial neural network model to generate a second output representing the probability of the bio event occurring within a predetermined time. A method.

4. In claim 1, the first output includes a value corresponding to the length of the remaining time from the time when the biometric information is obtained to the time when the bio event is expected to occur. A method.

5. In claim 3, the method further comprises providing comprehensive prediction information related to the bio event to a user based on the first output and the second output; the comprehensive prediction information includes information capable of determining the priority of each patient among all patients. A method.

6. In claim 5, the comprehensive prediction information includes information filtered by comparing the second output with a predetermined threshold value, and information related to the priority of the patient determined based on the filtering result and the magnitude of the first output. A method.

7. A method executed by a computing device for predicting a bio event, comprising: obtaining biometric information of a patient; and utilizing an artificial neural network model to generate prediction information related to the bio event based on the biometric information. The artificial neural network model is a model learned by multi-task learning based on a first task of predicting an expected occurrence time of the bio event and a second task of predicting the probability of occurrence of the bio event. A method.

8. In claim 7, the artificial neural network model is learned based on two or more different learning datasets. A method.

9. In claim 8, the two or more different learning datasets include first learning data which is biometric information with information related to the occurrence time of the bio event of the patient set as a label. A method.

10. In claim 8, ​ ​ ​ ​ ​ The two or more different learning data sets are second learning data, which is biological information with binary information related to whether a biological event occurs within a predetermined time set as a label; including method.

11. A computer program stored in a computer-readable storage medium, including instructions to cause an operation to predict a biological event, the operation comprising: an operation to acquire biological information of a patient; and an operation to utilize an artificial neural network model and generate a first output indicating an expected occurrence time of a biological event based on the biological information; including a computer program stored in a computer-readable storage medium.

12. A computing device for predicting a biological event, comprising: at least one processor; and a memory; including the at least one processor: acquires biological information of a patient and utilizes an artificial neural network model to generate a first output indicating an expected occurrence time of a biological event based on the biological information, computing device.

Images