Method for predicting the possibility of entering a treatment facility

Abstract

To provide a method for prediction which can generate multiple prediction information for predicting the possibility that a patient will enter a room for a treatment by inputting biological information of the patient into an artificial neural circuit net model.SOLUTION: The present invention relates to a method for predicting the possibility that a patient will enter a room for a treatment executed by a computing device. The computing device acquires biological information of a patient, uses an artificial neural circuit net model, and generates prediction information for predicting the possibility that the patient will enter a room for a treatment on the basis of the acquired biological information. The prediction information includes plural multiple predictions showing the possibility that the patient will enter a room for a treatment at each of plural points in time.SELECTED DRAWING: Figure 5

Description

Technical Field

[0001] The present disclosure relates to a method for predicting the possibility of entering a treatment location. Specifically, it relates to a method for generating multiple prediction information for predicting the possibility of a patient entering a treatment location by inputting the patient's biological information into an artificial neural network model.

Background Art

[0002] It can be said that it is an essential element in hospital bed operation to accommodate patients with high severity in special types of treatment locations such as intensive care units, constantly monitor the patient's condition, and take appropriate measures to prevent the deterioration of the condition.

[0003] However, in today's medical field, there is no quantitative index or response manual regarding discharge from the intensive care unit, and admission or discharge is determined considering the patient's current overall situation.

[0004] In such cases, there is a problem that appropriate hospital bed operation becomes difficult, such as a case where a patient is currently of low severity and has been discharged from the intensive care unit but soon becomes of high severity again and needs to be readmitted.

[0005] Therefore, there is a need in the industry for a method that can assist in appropriately operating the hospital beds by predicting the possibility of entering various treatment locations including the intensive care unit, considering not only the current state but also the possibility of future deterioration of the condition.

Summary of the Invention

Problems to be Solved by the Invention

[0006] The present disclosure was devised in response to the aforementioned background art, and aims to generate multiple prediction information for predicting the possibility of a patient entering a treatment location by inputting the patient's biological information into an artificial neural network model.

[0007] However, the technical problems to be solved by the present disclosure are not limited to the foregoing technical problems, and it is assumed that various technical problems may be included within the scope obvious to those skilled in the art from the content described below.

Means for Solving the Problems

[0008] Based on an embodiment of the present disclosure for realizing the foregoing problems, a method for a computing device to predict the possibility of entering a patient's treatment location is disclosed. The method may include obtaining the patient's biometric information and generating prediction information representing the possibility of entering the patient's treatment location based on the obtained biometric information by utilizing an artificial neural network model, and the prediction information may include the possibility of entering at each of a plurality of time points after the prediction time point.

[0009] In one embodiment, the artificial neural network model may be a model trained based on learning data with multi-labeling performed.

[0010] In one embodiment, the treatment location includes an intensive care unit, and the prediction information may represent the possibility that the patient will re-enter the intensive care unit when the patient discharges from the intensive care unit.

[0011] In one embodiment, it may further include generating a graph related to the possibility of entering at the plurality of time points.

[0012] In one embodiment, it may further include providing to the user the time point at which the patient is expected to enter the treatment location based on a predetermined threshold value.

[0013] In one embodiment, it may further include providing to the user information related to the hospital bed management of the treatment location based on the expected time point.

[0014] In one embodiment, the information related to the hospital bed management at the treatment location may include at least one of the information related to the discharge plan of the patients staying in the treatment location and the information related to the admission plan of new patients related to the treatment location.

[0015] Based on one embodiment of the present disclosure for realizing the above problems, a method for a computing device to train an artificial neural network model for predicting the possibility of a patient's admission to a treatment location is disclosed. The method may include the step of acquiring the biometric information of the patient and the step of performing multi-labeling on the biometric information of the patient to generate training data for training the artificial neural network model, and the multi-labeling may include multi-labeling representing the admission status related to the treatment location of the patient at each of a plurality of time points.

[0016] In one embodiment, the training data may be data in which labels related to a plurality of time points before the patient enters the treatment location and labels related to a plurality of time points after entering the treatment location among the plurality of time points are labeled with different binary values.

[0017] In one embodiment, the biometric information of the patient may include biometric information measured during the period when the patient is staying in the treatment location.

[0018] Based on one embodiment of the present disclosure for realizing the above problems, a computer program is disclosed that causes a computing device to perform a plurality of operations for predicting the possibility of a patient's admission to a treatment location. The plurality of operations include an operation of acquiring the biometric information of the patient and an operation of utilizing an artificial neural network model to generate prediction information representing the possibility of the patient's admission to the treatment location based on the acquired biometric information, and the prediction information may include a plurality of multi-predictions representing the possibility of admission at each of a plurality of time points after the prediction time point.

[0019] Based on an embodiment of the present disclosure for realizing the above problems, a computing device for predicting the possibility of a patient entering a treatment location is disclosed. The computing device includes a processor including one or more cores, a network unit, and a memory. The processor can acquire the biometric information of the patient, utilize an artificial neural network model, and generate prediction information representing the possibility of the patient entering the treatment location based on the acquired biometric information. The prediction information can include a plurality of multiple predictions representing the possibility of entry at each of a plurality of time points after the prediction time point.

Advantages of the Invention

[0020] The present disclosure can predict the possibility of a patient entering a treatment location based on the patient's biometric information. For example, the present disclosure can input the patient's biometric information into an artificial neural network model and generate prediction information representing the possibility of the patient entering an intensive care unit.

Brief Description of the Drawings

[0021]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Mode for Carrying Out the Invention

[0022] The present disclosure discloses a method of inputting a patient's biological information into an artificial neural network model and generating prediction information representing the possibility of the patient entering a treatment location at each of a plurality of time points after the prediction time point.

[0023] Various embodiments will be described below with reference to the drawings. In this specification, various explanations are presented to facilitate the understanding of the present disclosure. However, it is obvious that such embodiments can be implemented without such specific explanations.

[0024] 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, for example, using signals (e.g., data and / or signals from one component interacting with other components in a local system or a distributed system and transmitted via a network such as the Internet) including one or more data packets.

[0025] Note that the term "or" is used with the intention of meaning an inclusive "or" rather than an exclusive "or". That is, when not otherwise specified and not clear from the context, "X uses A or B" is intended 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" herein is to be understood to refer to all possible combinations of one or more of the recited related items and to include them.

[0026] Also, the term "comprising (including)" as a predicate and / or "comprising (including)" as a modifier should be understood to mean the presence of the feature and / or component. However, the term "comprising (including)" as a predicate and / or "comprising (including)" as a modifier should be understood not to exclude the presence or addition of one or more other additional features, components and / or groups thereof. Also, 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".

[0027] 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".

[0028] 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 realized by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability between hardware and software, 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. Skilled engineers can realize the functionality described in various ways for individual specific applications. However, such a determination regarding the realization should not be construed as departing from the scope of the present disclosure.

[0029] The description of the embodiments shown herein is provided so that those of ordinary skill in the art of the present disclosure can make use of or practice the present invention. Various modifications to such embodiments will be readily apparent to those of ordinary skill in the art 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 to the embodiments shown herein. The present invention should be construed in the broadest sense consistent with the principles and novel features shown herein.

[0030] In the present disclosure, the "treatment location" can mean a location where medical acts are performed, including an intensive care unit (ICU), a closed ward, an isolation ward, a sterile treatment room, and a general inpatient ward.

[0031] In the present disclosure, "admission" can mean that a patient in the hospital moves from the current treatment location to another treatment location, or a patient who is not currently in the hospital is admitted and moves to the treatment location. For example, a patient's admission to the intensive care unit can mean that the patient's condition deteriorates and the patient moves from the general ward to the intensive care unit, or it can mean that a patient who is not in the hospital is admitted to the intensive care unit.

[0032] In the present disclosure, "discharge" can mean that a patient in the hospital moves to another treatment location, or a patient in the hospital is discharged. For example, a patient's discharge from the intensive care unit can mean that the patient's condition improves and the patient moves from the intensive care unit to the general ward, or it can mean that a patient admitted to the intensive care unit is discharged.

[0033] FIG. 1 is a block configuration diagram of a computing device for predicting the possibility of a patient's admission to a treatment location in an embodiment of the present disclosure.

[0034] The configuration of the computing device 100 illustrated in FIG. 1 is merely an exemplary illustration shown in a simplified manner. In one embodiment of the present disclosure, the computing device 100 may 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 computing 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 110 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 the 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 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 the learning of network functions. For example, both the CPU and the GPGPU can perform the learning of network functions and the classification of data using network functions. In an embodiment of the present disclosure, the processors of a plurality of computing devices can be used together to perform the learning of network functions and the data classification using network functions. Also, the computer program executed in the computing device 100 in an embodiment of the present disclosure can be a program executable by a CPU, GPGPU, or TPU.

[0038] The processor 110 can acquire the biometric information of a patient. Here, the biometric information of the patient can be a time-series biometric signal. For example, the biometric information of the patient can include the patient's body temperature, the patient's systolic blood pressure, the patient's diastolic blood pressure, and the patient's heart rate per minute. The biometric information of the patient acquired by the processor 110 can be the data stored in the memory 130 of the computing device 100, but can also be the data transmitted through the network unit 150 and the data acquired from the biometric signal measurement equipment (not shown) connected to the computing device 100. However, the present disclosure is not limited to such a data acquisition path.

[0039] The processor 110 can utilize an artificial neural network model and generate prediction information for predicting the possibility of the patient entering the treatment location based on the acquired biometric information.

[0040] In one embodiment of the present disclosure, the prediction information output by the artificial neural network model includes multiple predictions representing the possibility of a patient entering a treatment location at each of a plurality of time points after the prediction time. For example, the prediction information can include individual output values related to a plurality of time points after the preset prediction time, such as 0 days, 1 day, 2 days, 3 days, 7 days, and 30 days after the prediction time. Specifically, when a patient is discharged from the intensive care unit, the artificial neural network model receives the biometric information during the patient's stay in the intensive care unit as input data, and at each of the preset time points after the prediction time, it can output a value from 0 to 1 representing the possibility of the patient entering the intensive care unit again. In an example as described above, the values output by the artificial neural network can be in the form of [0.1, 0.2, 0.25, 0.7, 0.8, 0.9]. However, in the present disclosure, the prediction information can perform various types of predictions representing the possibility of entering a treatment location, such as the possibility of a patient staying in a general ward entering a sterile treatment room, in addition to the possibility of a patient discharged from the intensive care unit entering the intensive care unit again. Also, in the present disclosure, the plurality of time points can be set differently from the above examples, and the magnitudes of the output values related to each time point can also be set on other scales.

[0041] In one embodiment of the present disclosure, the artificial neural network model that generates prediction information can be a model learned based on learning data with multi-labeling performed. Also, the learning data for training the artificial neural network model can be learning data where all time points before the entry time are labeled as first labeling values and all time points after the entry time are labeled as second labeling values. A specific method for training the artificial neural network model of the present disclosure will be described later with reference to FIG. 6.

[0042] Based on the prediction information output by leveraging the artificial neural network model, the processor 110 can generate a graph related to the likelihood of a patient entering the treatment location over time. For example, if the artificial neural network model is a model that outputs the likelihood of a patient who is discharged from the intensive care unit re-entering the intensive care unit, and the outputs of the artificial neural network model are [0.1, 0.2, 0.25, 0.7, 0.8, 0.9], the processor 110 can generate a graph as shown in FIG. 5 and provide it to the user. In this case, each point on the horizontal axis of the graph is a preset time point, and the vertical axis can mean the likelihood of the patient re-entering the intensive care unit.

[0043] Based on a predetermined threshold value, the processor 110 can provide the user with the time point at which the patient is expected to re-enter the treatment location. For example, in the case of an artificial neural network model that predicts the likelihood of a patient who is discharged from the intensive care unit re-entering the intensive care unit from the biological information of the patient, the processor 110 outputs a predicted value representing the likelihood of the patient re-entering the intensive care unit for each preset time point, and can determine the time point at which the likelihood of re-entry exceeds the predetermined threshold value as the time point at which the patient is expected to re-enter the intensive care unit. Thereafter, the processor 110 can provide the user with the information related to the determined re-entry prediction time point.

[0044] Specifically, referring to FIG. 5, a plurality of predetermined time points are six time points of 0 days, 1 day, 2 days, 3 days, 7 days, and 30 days after the prediction time point. When the outputs of the artificial neural network model corresponding to each time point are [0.1, 0.2, 0.25, 0.7, 0.8, 0.9], the processor 110 can represent the output of the artificial neural network model in a graph similar to that shown in FIG. 5. Based on a predetermined threshold (cut-off) of 0.5, the processor 110 determines the time point when the possibility of the patient's re-admission to the intensive care unit exceeds the threshold of 0.5, that is, the time point when 2.5 days (60 hours) have elapsed from the prediction time point, as the time point (onset time) when the patient is expected to re-admit to the intensive care unit, and can provide the information related thereto to the user.

[0045] Based on the time when the patient is expected to enter the treatment location, the processor 110 can provide information related to the bed management of the treatment location to the user. In this case, the information related to the bed management of the treatment location can include at least one of the information related to the discharge plan of the patients staying in the above treatment location and the information related to the admission plan of new patients related to the above treatment location. For example, for a patient who is about to be discharged from the intensive care unit, the processor 110 utilizes the above artificial neural network model and, based on the user's biometric information measured during the stay in the intensive care unit, can generate prediction information for predicting the possibility of re-entering the intensive care unit 0 days, 1 day, 2 days, 3 days, 7 days, and 30 days after the current time. Subsequently, the processor 110 calculates the time when the patient is expected to re-enter the intensive care unit from the prediction information, and if the time is within a predetermined threshold (e.g., 3 days), it is possible to plan in a direction that does not discharge the patient from the intensive care unit. Subsequently, the processor 110 can provide the information related to the intensive care unit discharge plan to the user as proposed information. As another example, based on the biometric signals of the patients staying in the general ward rather than the intensive care unit, the processor 110 generates prediction information for predicting the possibility of the patients entering the intensive care unit, calculates the time when the condition of the patients deteriorates rapidly from the prediction information, and can plan to admit the patients to the intensive care unit. Subsequently, the processor 110 can provide the information related to the intensive care unit admission plan to the user as proposed information for the relevant patients.

[0046] Processor 110 can consider prediction information related to other patients when generating information related to the discharge plan of a patient present in the treatment location or information related to the admission plan of a new patient to the treatment location. For example, if there are patients A and B who are about to be discharged from the intensive care unit and patient C who has a high probability of being admitted to the intensive care unit, processor 110 can plan in a direction to admit only the patient among patients A, B, and C who is expected to re-enter the intensive care unit earlier. Specifically, among patients A, B, and C, if the predicted admission time of patient B is the latest, it is possible to plan in a direction to discharge patient B from the intensive care unit and admit patient C to the intensive care unit. Also, among patients A, B, and C, if the predicted admission time of patient C is the latest, it is possible to plan in a direction to keep patients A and B in the room and not admit patient C to the intensive care unit.

[0047] That is, in the present disclosure, processor 110 can plan the admission and discharge of each of a plurality of patients to and from the treatment location.

[0048] In one embodiment of the present disclosure, the memory 130 can include a storage medium of at least one type among 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 aforementioned memory is merely illustrative and the present disclosure is not limited thereto.

[0049] The network unit 150 in one embodiment of the present disclosure 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 local area network (LAN).

[0050] In addition, the network unit 150 in this specification can utilize various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA), and other systems.

[0051] In the present disclosure, the network unit 150 can utilize any form of wired or wireless communication system.

[0052] The technology described in this specification can be used not only in the above network but also in other networks.

[0053] FIG. 2 is a schematic diagram showing a network function in an embodiment of the present disclosure.

[0054] Throughout this specification, the 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 commonly called nodes. Such nodes can also be referred to as neurons. A neural circuit network is configured to include at least one or more nodes. The nodes (or neurons) constituting the neural circuit network can be interconnected by one or more links.

[0055] In a neural circuit network, one or more nodes connected via links can form a relative relationship of input nodes and output nodes. The concepts of input nodes and output nodes are relative. Any node that becomes an output node for a certain node can become an input node in relation to other nodes, and vice versa. As described above, the relationship between input nodes and output nodes can be established centered around links. One input node can be connected via links to one or more output nodes, and vice versa.

[0056] In the relationship between an input node and an output node connected via one link, it is possible for the value of the data of the output node to be determined based on the data input to the input node. Here, the node interconnecting the input node and the output node can have a weight value. The weight value can be variable and can be changed by a user or an algorithm for the neural circuit network to perform a desired function. For example, when one or more input nodes are interconnected by respective links 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 respective links corresponding to the input nodes.

[0057] As described above, a neural circuit network is formed by one or more nodes interconnected via one or more links, forming a relationship between input nodes and 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 between nodes and links, and the values of the weight 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 weight values of the links, the two neural circuit networks can be recognized as different.

[0058] 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 traversed 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 configuration of layers in the neural circuit network can be defined in a way different from the above explanation. For example, the layer of nodes can also be defined based on the distance from the final output node.

[0059] 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 relation to other nodes. Or, in the network of the neural circuit network, it can mean a node that has no other input nodes connected via a link in the relationship between nodes based on the link. Similarly, the final output node can mean one or more nodes among the nodes in the neural circuit network that have no output nodes in relation to 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.

[0060] 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. Further, 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 in a form that combines the above neural circuit networks.

[0061] A deep neural network (DNN) can be defined as a neural network that includes multiple hidden layers in addition to an input layer and an output layer. By using a deep neural network, the latent structures of data can be grasped. That is, it is possible to understand the latent structures of photos, articles, videos, voices, music, etc. (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.). 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 examples and the present disclosure is not limited thereto.

[0062] In one embodiment of the present disclosure, the network function may also include an autoencoder. The autoencoder can be a type of artificial neural network 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 (encoding), and can also expand in a form symmetrical to the reduction from the bottleneck layer towards the output layer (symmetrical 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.).

[0063] 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.

[0064] 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 of the neural network to the input layer in the 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 correct answers 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 correct answers are not labeled for individual training data. That is, for example, the training data in supervised learning regarding data classification can be data with categories 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 improve the accuracy.

[0065] 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 trained neural network). Therefore, there can be a learning cycle in which the error related to the training data decreases while the error related to the actual data increases. Overfitting is a phenomenon in which, due to overlearning the training data in this way, the error increases in the actual data. For example, a neural network that has learned cats by seeing yellow cats may not be able to recognize a cat of a color 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 utilizing a batch normalization layer can be applied.

[0066] Figure 3 is a flowchart showing the process of predicting the possibility of a patient entering a treatment location in an embodiment of the present disclosure.

[0067] According to Figure 3, in the present disclosure, the process of predicting the possibility of a patient entering a treatment location can include a step of acquiring the biological information of the patient (S310) and a step of generating prediction information for predicting the possibility of the patient entering the treatment location based on the acquired biological information by utilizing an artificial neural network model (S320).

[0068] In step S310, the processor 110 can acquire the biological signal data of the user. In this case, the types and acquisition paths of the biological information have been described above with reference to Figure 1.

[0069] In step S320, the processor 110 can utilize the artificial neural network model to generate prediction information for predicting the likelihood of the patient entering the treatment location based on the acquired biological information. As described above, the prediction information can include multiple predictions representing the likelihood of the patient entering the treatment location at each of multiple time points. Also, the likelihood of the patient entering the treatment location can include the likelihood of a patient who intends to leave the intensive care unit re-entering the intensive care unit. In this case, the processor 110 can create in the form of a graph the likelihood of the patient re-entering the intensive care unit and provide it to the user, or calculate the information related to the time point when the patient is predicted to re-enter the intensive care unit and provide it to the user.

[0070] Next, in the present disclosure, a method for training an artificial neural network model for predicting the likelihood of a patient entering a treatment location will be described.

[0071] FIG. 4 is a conceptual diagram showing data including a patient's biological information in one embodiment of the present disclosure.

[0072] In one embodiment of the present disclosure, the processor 110 can generate training data based on the patient's biological information 410 measured during the period when the patient is present in the treatment location, the biological information related to the patient's discharge time 420, and the biological information related to the patient's re-entry time 430 in order to train the artificial neural network. In this case, the patient's biological information 410 can include time-series biological signals such as body temperature (Temp), blood pressure (SBP, DBP), and heart rate (HR).

[0073] The processor 110 can perform multi-labeling on the patient's biological information as described above to generate training data for training the artificial neural network model. In this case, multi-labeling can mean assigning a plurality of labels representing the entry state related to the patient's treatment location for each of multiple time points.

[0074] For example, in the present disclosure, the processor 110 can generate learning data for training an artificial neural network by labeling, as first labeling values, a plurality of time points before a patient enters a treatment location among a plurality of time points, and labeling, as second labeling values, a plurality of time points after the patient enters the treatment location. In this case, the first labeling value and the second labeling value can be different binary values.

[0075] Specifically, with reference to FIG. 6, for a patient who has left the intensive care unit but re-enters 60 hours later, the processor 110 labels as 0 for time points earlier than 60 hours later (0 days later, 1 day later, 2 days later), and labels as 1 for time points later than 60 hours later (3 days later, 7 days later, 30 days later), thereby generating one piece of learning data by a method of assigning a plurality of labels to one piece of data.

[0076] However, in the present disclosure, the method for generating learning data for an artificial neural network model that predicts the possibility of a patient entering a treatment location is not limited to the above example, and learning data for training the artificial neural network can be generated at various time points and with various numerical values.

[0077] In the present disclosure, instead of assigning one label to one piece of biological signal data, learning data is generated by assigning labels based on whether the patient enters the treatment location for a plurality of time points. Based on such learning data, the processor 110 designs a loss function between the prediction information output by the artificial neural network and the label for each of the plurality of time points, and can train the artificial neural network model so that the higher the probability that the patient re-enters the intensive care unit, the higher the value is output. That is, the artificial neural network of the present disclosure can be trained to perform multi-label classification.

[0078] For example, the artificial neural network model of the present disclosure includes a plurality of hidden layers and fully connected layers, and the fully connected layer can be trained to treat each of a plurality of time points as a class and output a plurality of predicted values for each class. However, in the present disclosure, the specific form of the artificial neural network model for predicting the possibility of a patient entering a treatment location is not limited to the above examples, and various forms of models capable of performing multi-label classification can be used without limitation.

[0079] Through the present disclosure, it is possible to utilize an artificial neural network model for predicting the possibility of a patient entering a treatment location to predict the possibility of a patient entering a treatment location, such as the predicted time of re-entry of a patient who intends to leave the intensive care unit. By using this, an effect can occur where elements such as the severity of the patient can be quantitatively evaluated from a long-term perspective. In addition, by predicting the long-term state of the patient in advance, an effect can occur where resources such as hospital beds, medical equipment, and personnel in treatment locations including the intensive care unit can be used efficiently.

[0080] Based on an embodiment of the present disclosure, a computer-readable storage medium storing a data structure is disclosed.

[0081] A data structure can mean the organization, management, and storage of data that enable efficient access to and modification of data. A data structure can mean a data organization for solving a specific problem (for example, data search, data storage, data modification in the shortest time). A data structure can also be defined as the physical or logical relationship between data elements designed to support a specific data processing function.

[0082] The logical relationship between data elements can include the connection 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).

[0083] A data structure can specifically include a set of data, the relationships between the data, and 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.

[0084] Data structures can be classified into linear data structures and non-linear data structures according to the form of the data structure. A linear data structure may be a structure in which only one piece of data is connected after one piece of data. Linear data structures can include lists, stacks, queues, and deques.

[0085] A list can mean a series of data sets with an internal order. Lists can include linked lists. A linked list can be a data structure in which data is linked in such a way that each piece of data has a pointer and is linked in a column. In a linked list, the pointer can include connection information with the next or previous data. Linked lists can be represented as singly linked lists, doubly linked lists, or circular linked lists according to their form.

[0086] A stack may be a data list structure with restricted access to data. A stack may be a linear data structure in which data can be processed (e.g., inserted or deleted) only at one end of the data structure. The data stored in a stack may be a data structure where the later-entering data comes out earlier (LIFO - Last in First Out).

[0087] A queue is a data arrangement structure with restricted access to data, and unlike a stack, it can be a data structure where the later-stored data comes out later (FIFO - First in First Out).

[0088] The deck can be a data structure capable of processing data at both ends of the data structure.

[0089] A non-linear data structure may be a structure in which a plurality of data are connected after one data. The non-linear data structure can include a graph data structure.

[0090] The graph data structure can be defined by vertices and edges, and the edges can include lines connecting two different vertices. The graph data structure can include a tree data structure. The tree data structure can be a data structure formed by a path connecting two different vertices among the plurality of vertices included in the tree. That is, it can be a data structure that does not form a loop in the graph data structure.

[0091] In this specification, an operation model, a neural circuit network, a network function, and a neural network can be used in the same meaning (hereinafter, they will be uniformly described as "neural network").

[0092] The data structure can include a neural network. And the data structure including the neural network can be stored in a computer-readable storage medium. The data structure including the neural network can 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 related to each node or layer of the neural network, and a loss function for learning the neural network. The data structure including the neural network can include any component of the above-disclosed configuration.

[0093] 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, weighted 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, and the like. In addition to the above-described configuration, a data structure including a neural network can include any other information that determines the characteristics of the neural network.

[0094] Also, the data structure can include all forms of data used or generated in the operation 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.

[0095] A neural network can generally be composed of a set of interconnected computing units generally called nodes. Such nodes can be called neurons. A neural network is configured to include at least one or more nodes.

[0096] 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 learning 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. The pre-processing can include a data processing process for inputting the data to the neural network. Therefore, the data structure can include data to be pre-processed and data generated by the pre-processing. The above-described data structure is merely exemplary, and the present disclosure is not limited thereto.

[0097] A data structure can include the weights of a neural network (in this specification, weights and parameters can be used interchangeably). And a data structure including the weights of a neural circuit network can be stored in a computer-readable storage medium.

[0098] A neural network can include a plurality of weights. The weights are variable and can be varied by a user or an algorithm to perform the function 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 the 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.

[0099] By way of example and not limitation, the weighted value can include a weighted value that varies during the neural network learning process and / or a weighted value after the neural network learning is completed. The weighted value that is varied during the neural network learning process can include the weighted value at the start of the learning cycle and / or the weighted value that is varied during the learning cycle. The weighted value after the neural network learning is completed can include the weighted value after the learning cycle is completed.

[0100] Accordingly, a data structure including the weighted values of a 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-mentioned weighted values and / or combinations of each weighted value shall be included in the data structure including the weighted values of the neural network. The foregoing data structure is merely exemplary and the present disclosure is not limited thereto.

[0101] A data structure including the weighted values of a neural network can be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be a process of converting a data structure into a form that can be stored in the same or another computing device and reconfigured and used later. A computing device can serialize a data structure and transmit and receive data via a network.

[0102] A data structure containing the weights of a serialized neural network can be reconstructed on the same computing device or another computing device through deserialization. The data structure containing the weights of the neural network is not limited to serialization. Further, the data structure containing the weights of the neural circuit network can include a data structure (e.g., a non-linear data structure such as a B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree) for enhancing the efficiency of operations while minimizing the resources of the computing device. The foregoing matters are merely illustrative and the present disclosure is not limited thereto.

[0103] 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.

[0104] 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 structures are merely illustrative and the present disclosure is not limited thereto.

[0105] FIG. 7 is a simplified and general schematic diagram relating to an exemplary computing environment in which an embodiment of the present disclosure can be implemented.

[0106] Although it has been described above that the present disclosure can generally be embodied by a computing device, those skilled in the art will well understand that the present disclosure can be embodied in combination with computer-executable instructions that can be executed on one or more computers and / or other program modules and / or as a combination of hardware and software.

[0107] Generally, modules herein include 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 devices, or programmable household appliances, etc. (each of which can operate in connection with one or more related devices).

[0108] The embodiments described in the present disclosure can further be implemented in a distributed computing environment where a 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.

[0109] 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.

[0110] 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 that sets or changes one or more of the characteristics of the signal 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.

[0111] An exemplary environment is shown for implementing various aspects of the present disclosure that includes a computer 1102, which includes a processing device 1104, a system memory 1106, and a system bus 1108. The system bus 1108 couples 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 commercially available processors. Dual processors and other multi-processor architectures can also be utilized as the processing device 1104.

[0112] The system bus 1108 can be any of several types of bus structures that can further be interconnected to a local bus using any one of a memory bus, a peripheral device bus, and various commercially available 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 such as ROM 1110, EPROM, EEPROM, etc., and the BIOS includes basic routines that support the exchange of information between the various components within the computer 1102, such as during startup. The RAM 1112 can include high speed RAM such as static RAM for caching data.

[0113] In computer 1102, it includes a built-in hard disk drive (HDD) 1114 (e.g., EIDE, SATA), a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from and writing to removable diskette 1118), and an optical disk drive 1120 (e.g., for reading CD-ROM disk 1122, reading from and writing to other high-capacity optical media such as DVDs). Note that hard disk drive 1114 can be configured for external use within an appropriate chassis (not shown) (external HDD). Hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 can each be connected to system bus 1108 by a hard disk drive interface 1124, a magnetic disk drive interface 1126, and an optical drive interface 1128, respectively. Interfaces for implementing external drives include, for example, at least one or both of USB (Universal Serial Bus) and IEEE 1394 interface technologies.

[0114] These drives and the computer-readable media associated with them provide non-volatile storage for data, data structures, computer-executable instructions, and so on. In the case of computer 1102, the drives and media correspond to storing any data in an appropriate digital format. Although the foregoing description of computer-readable storage media refers to 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 so on, can also be used in an exemplary operating environment, and it will be well understood that any one of such media can contain computer-executable instructions for performing the methods of this disclosure.

[0115] A number of program modules, including the operating systems 1130, one or more application programs 1132, other program modules 1134, and program data 1136, can be stored in the drive and RAM 1112. All or a portion of the operating system, applications, modules, and / or data can also be cached in the 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.

[0116] A user can input commands and information into the computer 1102 through one or more wired or 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 so on. These and other input devices may 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 so on.

[0117] 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 so on (not shown).

[0118] Computer 1102 can operate in a networked environment using logical connections to one or more remote computers, such as (multiple) remote computers 1148, via wired and / or wireless communication. The (multiple) 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 computer 1102. For simplicity, only the memory / storage device 1150 is shown. 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 networking environments of LAN 1152 and WAN 1154 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.

[0119] When used in a LAN networking environment, computer 1102 is connected to LAN 1152 through a wired and / or wireless communication network interface, or network adapter 1156. Network adapter 1156 can facilitate wired or wireless communication to LAN 1152, which includes a wireless access point installed thereon for communicating with wireless network adapter 1156. When used in a WAN networking environment, computer 1102 can include a modem 1158, connect to a communication server on WAN 1154, or have other means of establishing communication through WAN 1154, such as through the Internet. Modem 1158, which can be an internal or external, wired or wireless device, is connected to system bus 1108 through serial port input device interface 1142. In a networked environment, program modules or portions thereof described with respect to computer 1102 can be stored in remote memory / storage device 1150. It is readily understood that the illustrated network connections are exemplary and that other means of establishing communication links between multiple computers can be used.

[0120] 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 (Wireless Fidelity: registered trademark) and Bluetooth (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.

[0121] Wi-Fi enables connection to the Internet and the like without being wired. Wi-Fi is a wireless technology such as a cell phone that allows such devices, for example, computers to send and receive data indoors and outdoors, that is, from anywhere within the coverage area of a base station. Wi-Fi networks use wireless technologies such as IEEE 802.11 (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 IEEE 802.3 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).

[0122] 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 voltage, current, electromagnetic waves, magnetic fields, etc. or particles, optical fields, etc. or particles, or any combination thereof.

[0123] Those of ordinary skill in the art of the present disclosure will appreciate that the various exemplary logical blocks, modules, processors, means, circuits, algorithm steps recited in the description of the embodiments disclosed herein can be implemented in electronic hardware (for convenience, referred to herein as "software"), various forms of programs or design codes, or any combination thereof. To clearly illustrate such interchangeability between hardware and software, the 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 on the design constraints imposed on a particular application and the overall system. Those of ordinary skill in the art of the present disclosure can implement the functions described in various ways for individual specific applications, but such implementation decisions should not be construed as departing from the scope of the present disclosure.

[0124] 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, carrier, or medium accessible from any computer-readable device. For example, computer-readable storage media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Also, the various storage media shown herein include one or more devices for storing information and / or other machine-readable media.

[0125] It should be understood that the specific order or hierarchical structure of the multiple steps in the processes shown in this specification 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 the elements of the various steps in sample order, but are not meant to be limited to the specific order or hierarchical structure shown.

[0126] The description of the embodiments shown in this specification is provided so that a person of ordinary skill in any technical field of the present disclosure can utilize or implement the present disclosure. Various modifications to such embodiments will be clearly understood by a person of ordinary skill in the technical field 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. Therefore, the present disclosure is not limited by the embodiments shown herein and should be construed in the broadest scope consistent with the principles and novel features shown herein.

Description of Reference Numerals

[0127] 100 Computing device 110 Processor 130 Memory 150 Network unit

Claims

1. A method for predicting the likelihood of a patient entering a treatment location, which is executed by a computing device, comprising: obtaining the biometric information of the patient; and utilizing an artificial neural network model to generate prediction information representing the likelihood of the patient entering the treatment location based on the obtained biometric information, wherein the prediction information includes the likelihood of entry at each of a plurality of time points after the prediction time point, the artificial neural network model is a model trained based on training data generated by performing multi-labeling on the biometric information of the patient, and the multi-labeling assigns a label representing the entry state of the patient at the treatment location at each of the plurality of time points to one biometric signal data respectively A method for predicting the likelihood of a patient entering a treatment location, characterized by the above.

2. In the method for predicting the likelihood of a patient entering a treatment location according to Claim 1, when the treatment location is an intensive care unit, the prediction information represents the likelihood of the patient re-entering the intensive care unit at each of a plurality of time points after the prediction time point based on the biometric information of the patient measured during the patient's stay in the intensive care unit A method for predicting the likelihood of a patient entering a treatment location, characterized by the above.

3. In the method for predicting the likelihood of a patient entering a treatment location according to Claim 1, generating a graph related to the likelihood of entry at the plurality of time points further comprising A method for predicting the likelihood of a patient entering a treatment location, characterized by the above.

4. In the method for predicting the likelihood of a patient entering a treatment location according to Claim 1, providing to the user, as the time point when the patient is expected to enter the treatment location, the time point at which the predicted value representing the likelihood of the patient entering the treatment location output for each preset time point exceeds a preset first threshold further comprising A method for predicting the likelihood of a patient entering a treatment location, characterized by the above.

5. In the method for predicting the likelihood of a patient entering a treatment location according to Claim 4, information calculated by comparing the expected time point with a preset second threshold, or information related to the likelihood of entry at each of the plurality of time points after the prediction time point based on at least one of providing to the user information related to the bed management of the treatment location further comprising A method for predicting the possibility of entering a treatment location, characterized by the above. **Claim 6** In the method for predicting the possibility of entering a treatment location according to Claim 5, the information related to the hospital bed management of the treatment location is information related to the discharge plan of the patients staying in the treatment location, or information related to the admission plan of new patients related to the treatment location including at least one of the above A method for predicting the possibility of entering a treatment location, characterized by the above. **Claim 7** A method for training an artificial neural network model that predicts the possibility of a patient entering a treatment location, which is executed by a computing device, comprising: the step of acquiring the biometric information of the patient, and the step of performing multi-labeling on the biometric information of the patient to generate training data for training the artificial neural network model. Including the above The multi-labeling is for each of a plurality of time points of one biometric signal data, respectively assigning a label representing the admission status of the patient related to the treatment location at each time point. A method for training an artificial neural network model, characterized by the above. **Claim 8** In the method for training the artificial neural network model according to Claim 7, the training data is data in which labels related to a plurality of time points before the patient enters the treatment location and labels related to a plurality of time points after the patient enters the treatment location among the plurality of time points are labeled with different binary values. A method for training an artificial neural network model, characterized by the above. **Claim 9** In the method for training the artificial neural network model according to Claim 7, the biometric information of the patient is biometric signals measured during the period when the patient stays in the treatment location. A method for training an artificial neural network model, characterized by the above. **Claim 10** A computer program stored in a computer-readable storage medium including instructions for causing a computing device to execute operations for predicting the possibility of a patient entering a treatment location, where the operations are the operation of acquiring the biometric information of the patient, and the operation of utilizing an artificial neural network model and generating prediction information representing the possibility of the patient entering the treatment location based on the acquired biometric information. Including the above the prediction information includes the possibility of admission at each of a plurality of time points after the prediction time point. The artificial neural network model is a model trained based on training data generated by performing multi-labeling on the biological information of the patient. The multi-labeling assigns labels representing the admission status related to the treatment location of the patient at each of the plurality of time points to one biological signal data respectively. A computer program characterized by the above. **Claim 11** A computing device comprising: A processor including one or more cores, A network unit, and A memory, wherein: The processor: Obtains the biological information of the patient, Utilizes an artificial neural network model to generate prediction information representing the possibility of admission of the patient to the treatment location based on the obtained biological information, and The prediction information includes the possibility of admission at each of a plurality of time points after the prediction time point, The artificial neural network model is a model trained based on training data generated by performing multi-labeling on the biological information of the patient. The multi-labeling assigns labels representing the admission status related to the treatment location of the patient at each of the plurality of time points to one biological signal data respectively. A computing device characterized by the above.

Images