KR102647018B1 - Methods for creating data - Google Patents

Abstract

According to the present disclosure, a method for generating a data set for event prediction is disclosed. Specifically, according to the present disclosure, a computing device acquires medical data of a patient to generate a first data set and, based on at least one condition related to an intervention for the patient, at least a portion of the medical data of the patient. A second data set is created by removing a section from the first data set.

Description

Methods for creating data sets {METHODS FOR CREATING DATA}

The present disclosure relates to a method of generating a data set for event prediction, and specifically, at least a portion of the medical data that meets at least one condition related to an intervention for the patient from a first data set containing the patient's medical data. It relates to a method of generating a purified data set by excluding .

Recently, with the development of artificial intelligence technology, much research is being conducted in the medical field on artificial neural network models that receive patient data and perform diagnosis. In order to properly learn an artificial neural network model that predicts the occurrence of a specific patient event, such as a patient's cardiac arrest or sepsis, among these models, a learning data set or model that contributes to the model performing the task better There is a need to construct a verification data set that can accurately measure performance.

However, in actual medical settings, situations such as medical interventions being performed on patients with high severity or warning systems malfunctioning frequently occur. In such an environment, if accumulated medical data is used as a learning and verification data set, it may have a negative impact on the model's predictive performance or performance evaluation.

Accordingly, there is a need in the art for a method of generating refined data sets for machine learning models that predict events for patients.

Korean Patent No. 2387887 discloses a clean label data purification device for artificial intelligence learning.

The present disclosure was made in response to the above-described background technology, and aims to create a refined data set for event prediction.

Meanwhile, the technical problem to be achieved by the present disclosure is not limited to the technical problems mentioned above, and may include various technical problems within the scope of what is apparent to those skilled in the art from the contents described below.

According to an embodiment of the present disclosure for realizing the above-described problem, a method for generating an event data set by a computing device is disclosed. The method includes obtaining medical data of a patient to generate a first data set, and based on at least one condition related to intervention on the patient, at least a portion of the medical data of the patient is generated by the first data set. It may include creating a second data set by removing from the first data set.

In one embodiment, based on at least one condition associated with an intervention for the patient, removing at least a portion of the patient's medical data from the first data set to create a second data set includes: Excluding from the first data set at least a portion of the medical data of patients who satisfy the first condition among patients who did not experience an event, or excluding medical data of patients who satisfied the second condition among patients where an event occurred from the first data set It may include performing at least one of the following:

In one embodiment, the first condition may include a condition related to a change in the patient's condition based on a retrospective study.

In one embodiment, the first condition includes a case in which whether or not an event occurs changes due to intervention of a medical staff, and at least a portion of the medical data of a patient that satisfies the first condition is determined by the intervention. It can be decided based on the time it was made.

In one embodiment, the intervention of the medical staff may include medical actions performed to prevent the occurrence of a specific event in the patient.

In one embodiment, the second condition may include a case where the medical staff was unable to predict the occurrence of an event through the patient's medical data.

In one embodiment, when the medical staff was unable to predict the occurrence of the patient's event through the patient's medical data: When the medical staff's intervention was not performed from the time of the patient's event occurrence to the time before the predetermined value, and the patient This may include cases where an alarm of the warning system is not generated.

In one embodiment, the method further includes generating a training data set based on the second data set and training an event prediction model based on the training data set, wherein the event prediction model includes: It may be a machine learning model that receives medical data as input and outputs predictive information related to the occurrence of events for patients.

In one embodiment, the method further includes generating a validation data set based on the second data set and evaluating performance of an event prediction model based on the validation data set, wherein the event prediction model may be a machine learning model that receives the patient's medical data and outputs predictive information related to the occurrence of events for the patient.

In one embodiment, the performance of the event prediction model may include the accuracy of prediction information generated by the event prediction model when the verification data set is input to the event prediction model.

In one embodiment, the event prediction model may be a machine learning model that receives the patient's medical data and outputs prediction information related to the patient's cardiac arrest or sepsis.

According to an embodiment of the present disclosure for realizing the above-described problem, a computer program that causes a computing device to perform operations for generating a data set for event prediction is disclosed. The operations include generating a first data set by obtaining medical data of the patient and converting at least a portion of the medical data of the patient into the first data set based on at least one condition related to intervention on the patient. It may include an operation of generating a second data set by removing the data from the data set.

According to an embodiment of the present disclosure for realizing the above-described problem, a computing device for generating a data set for event prediction is disclosed. The computing device includes one or more processors and memory, wherein the processor acquires medical data of a patient to generate a first data set, and based on at least one condition related to an intervention for the patient, A second data set may be created by removing at least a portion of the medical data from the first data set.

The present disclosure has the effect of generating a more refined data set for event prediction. In particular, using the refined data set of the present disclosure, the performance of a machine learning model that predicts the occurrence of a patient's event can be improved, and a more accurate performance evaluation can be performed on the machine learning model that predicts the occurrence of a patient's event. there is.

1 is a block diagram of a computing device that generates a data set for event prediction according to an embodiment of the present disclosure.
Figure 2 is a schematic diagram showing a network function according to an embodiment of the present disclosure.
Figure 3 is a flowchart showing a process for generating a data set for event prediction according to an embodiment of the present disclosure.
FIG. 4 is a conceptual diagram illustrating medical data of a patient satisfying the first condition and at least a partial section of the medical data according to an embodiment of the present disclosure.
Figure 5 is a conceptual diagram showing medical data of a patient satisfying the second condition according to an embodiment of the present disclosure.
6 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

The present disclosure discloses a method for generating a refined data set by removing at least a portion of a patient's medical data from an initial data set based on at least one condition related to an intervention on the patient.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the disclosure. However, it is clear that these embodiments may be practiced without these specific descriptions.

As used herein, the terms “component,” “module,” “system,” and the like refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an implementation of software. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, both an application running on a computing device and the computing device can be a component. One or more components may reside within a processor and/or thread of execution. A component may be localized within one computer. In the present disclosure, one or more components may be distributed between two or more computers, or execution environments. Additionally, these components can execute from various computer-readable media having various data structures stored thereon. Components can transmit signals, for example, with one or more data packets (e.g., data and/or signals from one component interacting with other components in a local system, a distributed system, to other systems and over a network such as the Internet). Depending on the data being transmitted, they may communicate through local and/or remote processes.

Additionally, the term “or” is intended to mean an inclusive “or” and not an exclusive “or.” That is, unless otherwise specified or clear from context, “X utilizes A or B” is intended to mean one of the natural implicit substitutions. That is, either X uses A; X uses B; Or, if X uses both A and B, “X uses A or B” can apply to either of these cases. Additionally, the term “and/or” as used herein should be understood to refer to and include all possible combinations of one or more of the related listed items.

Additionally, the terms “comprise” and/or “comprising” should be understood to mean that the corresponding feature and/or element is present. However, the terms “comprise” and/or “comprising” should be understood as not excluding the presence or addition of one or more other features, elements and/or groups thereof. Additionally, unless otherwise specified or the context is clear to indicate a singular form, the singular terms herein and in the claims should generally be construed to mean “one or more.”

And, the term “at least one of A or B” should be interpreted to mean “when it contains only A,” “when it contains only B,” or “when it is a combination of A and B.”

Those skilled in the art will additionally understand that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or both. It should be recognized that it can be implemented with combinations of. To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or software will depend on the specific application and design constraints imposed on the overall system. A skilled technician can implement the described functionality in a variety of ways for each specific application. However, such implementation decisions should not be construed as causing a departure from the scope of the present disclosure.

The description of the presented embodiments is provided to enable anyone skilled in the art to use or practice the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Therefore, the present disclosure is not limited to the embodiments presented herein. This disclosure is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

In this disclosure, 'machine learning model' may refer to an algorithm that allows a computer system to predict and classify new data by learning patterns and rules from data. A machine learning model learns the relationship between input and output for given data and can make predictions about new input data through this. Machine learning models can be automatically optimized based on data, and accuracy can improve as learning progresses. The machine learning model of the present disclosure may include a model with an artificial neural network structure, but a model using other machine learning algorithms such as a decision tree may be used as the machine learning model of the present disclosure.

In the present disclosure, intervention may refer to the overall medical practice performed on a patient to prevent the occurrence of a specific event. For example, interventions may include medical actions such as CPR and drug administration performed by medical staff on patients admitted to the intensive care unit.

In the present disclosure, an event may mean an important change in the patient's condition. For example, when cardiac arrest or sepsis occurs in a patient hospitalized in a general ward or intensive care unit, the patient's cardiac arrest or sepsis may be included in the event. However, in the present disclosure, the event is not limited to examples such as cardiac arrest or sepsis, and may include various status changes that are of interest in retrospective research on patients.

In the present disclosure, a warning system may refer to a computing device, computer program, or system that receives a patient's medical data in real time and generates a warning alarm to the medical staff when a significant event is expected to occur in the patient. For example, systems such as Single Parameter Track and Trigger System (SPTTS) may be included in the warning system. SPTTS is a system that monitors and detects the patient's condition using single vital signs such as blood pressure, breathing rate, pulse, etc., which are generally one of the important measures related to maintaining the patient's life, in intensive care units, operating rooms, emergency rooms, etc. within hospitals. It may be the system being used. SPTTS measures the patient's vital signs at regular intervals and can determine whether the patient's condition is stable or unstable based on predetermined standards. If a patient's condition exceeds predetermined criteria, SPTTS can automatically generate an alarm to alert medical staff to take appropriate intervention.

However, the warning system of the present disclosure is not limited to examples such as SPTTS, and a system that sends an alarm using indicators such as a conventional MEWS (Modified Early Warning System) may be included in the warning system.

1 is a block diagram of a computing device that generates a data set for event prediction according to an embodiment of the present disclosure.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device 100 may include different configurations for performing the computing environment of the computing device 100, and only some of the disclosed configurations may configure the computing device 100.

The computing device 100 may include a processor 110, a memory 130, and a network unit 150.

The processor 110 may be composed of one or more cores, and may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit) may include a processor for data analysis and deep learning. The processor 110 may read a computer program stored in the memory 130 and perform data processing for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning a neural network. The processor 110 is used for learning neural networks, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation. Calculations can be performed.

At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, CPU and GPGPU can work together to process learning of network functions and data classification using network functions. Additionally, in one embodiment of the present disclosure, the processors of a plurality of computing devices can be used together to process learning of network functions and data classification using network functions. Additionally, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

The processor 110 may obtain medical data of a patient and generate a first data set. In the present disclosure, patient medical data is time series information representing the patient's physical condition, and may include, but is not limited to, the patient's vital signs. For example, a patient's medical data may refer to vital signs such as the patient's heart rate, diastolic blood pressure, systolic blood pressure, and respiratory rate measured over a certain period of time, but may also refer to electronic data including blood tests, urine tests, and administered drug information. It may also refer to electronic medical record information.

The first data set may include the patient's medical data and labels for each medical data. For example, if the data set relevant to event prediction to be generated in the present disclosure is a data set for predicting cardiac arrest or sepsis in a patient, the label for the patient's medical data may be a label for survival or a label for cardiac arrest or sepsis. It can be. The processor 110 may label medical data of a patient who survived by expressing survival as 0, or label medical data of a patient who suffered cardiac arrest or sepsis by expressing cardiac arrest or sepsis as 1.

The processor 110 may generate a second data set by removing at least some sections of the medical data of the patient included in the first data set based on at least one condition related to intervention on the patient. For example, the processor 110 may remove at least some of the medical data of patients who satisfy the first condition among patients labeled as having not occurred an event from the first data set. As another example, the processor 110 may remove medical data that satisfies the second condition among patients labeled as having occurred an event from the first data set. Specific examples of the first condition and the second condition will be described later with reference to FIGS. 4 and 5.

The processor 110 may generate a learning data set based on the second data set. In this case, the learning data set may refer to data used in the process of training a machine learning model to perform a specific task. The processor 110 may train an event prediction model based on the second data set. At this time, the event prediction model may be a machine learning model that receives the patient's medical data and outputs prediction information related to the occurrence of an event for the patient. For example, the event prediction model may be a cardiac arrest or sepsis prediction model that receives the patient's medical data and outputs prediction information related to the patient's cardiac arrest or sepsis.

The processor 110 may generate a verification data set based on the second data set. At this time, the verification data set may be a data set used to evaluate the performance of the learned machine learning model. Typically, the performance of a machine learning model can refer to the accuracy of the prediction information output by the machine learning model when a verification data set is input. In this disclosure, the performance of the machine learning model can be expressed numerically using indicators such as AUROC (Area Under ROC).

In the present disclosure, the second data set is not used solely as either a training data set or a validation data set, and the processor 110 generates a training data set based on a portion of the second data set while the remaining portion of the second data set A verification data set can be created based on . Thereafter, the processor 110 may train an event prediction model using the training data set, and after training of the event prediction model is completed, the performance of the event prediction model may be evaluated using a verification data set.

Due to the present disclosure, a second data set, which is a kind of refined data set, can be created by removing some data from the first data set. By using the second data set, the performance of the machine learning model (event prediction model) that predicts events for patients can be increased, and the performance of the event prediction model can be evaluated more accurately.

According to an embodiment of the present disclosure, the memory 130 is a flash memory type, hard disk type, multimedia card micro type, or card type memory (e.g. (e.g. SD or -Only Memory), and may include at least one type of storage medium among magnetic memory, magnetic disk, and optical disk. The computing device 100 may operate in connection with web storage that performs a storage function of the memory 130 on the Internet. The description of the memory described above is merely an example, and the present disclosure is not limited thereto.

The network unit 150 according to an embodiment of the present disclosure includes Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), and VDSL ( A variety of wired communication systems can be used, such as Very High Speed DSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and Local Area Network (LAN).

In addition, the network unit 150 presented in this specification includes Code Division Multi Access (CDMA), Time Division Multi Access (TDMA), Frequency Division Multi Access (FDMA), Orthogonal Frequency Division Multi Access (OFDMA), and SC-FDMA ( A variety of wireless communication systems can be used, such as Single Carrier-FDMA) and other systems.

In the present disclosure, the network unit 150 may use any type of wired or wireless communication system.

The techniques described herein can be used in the networks mentioned above, as well as other networks.

Figure 2 is a schematic diagram showing a network function according to an embodiment of the present disclosure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node. Nodes (or neurons) that make up neural networks may be interconnected by one or more links.

Within a neural network, one or more nodes connected through a link may form a relative input node and output node relationship. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the data of the output node may be determined based on the data input to the input node. Here, the link connecting the input node and the output node may have a weight. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network can be determined according to the number of nodes and links within the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. For example, if the same number of nodes and links exist and two neural networks with different weight values of the links exist, the two neural networks may be recognized as different from each other.

A neural network may consist of a set of one or more nodes. A subset of nodes that make up a neural network can form a layer. Some of the nodes constituting the neural network may form one layer based on the distances from the first input node. For example, a set of nodes with a distance n from the initial input node may constitute n layers. The distance from the initial input node can be defined by the minimum number of links that must be passed to reach the node from the initial input node. However, this definition of a layer is arbitrary for explanation purposes, and the order of a layer within a neural network may be defined in a different way than described above. For example, a layer of nodes may be defined by distance from the final output node.

The initial input node may refer to one or more nodes in the neural network through which data is directly input without going through links in relationships with other nodes. Alternatively, in a neural network network, in the relationship between nodes based on links, it may mean nodes that do not have other input nodes connected by links. Similarly, the final output node may refer to one or more nodes that do not have an output node in their relationship with other nodes among the nodes in the neural network. Additionally, hidden nodes may refer to nodes constituting a neural network other than the first input node and the last output node.

The neural network according to an embodiment of the present disclosure is a neural network in which the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as it progresses from the input layer to the hidden layer. You can. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be less than the number of nodes in the output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as it progresses from the input layer to the hidden layer. You can. A neural network according to another embodiment of the present disclosure may be a neural network that is a combination of the above-described neural networks.

A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to the input layer and output layer. Deep neural networks allow you to identify latent structures in data. In other words, it is possible to identify the potential structure of a photo, text, video, voice, or music (e.g., what object is in the photo, what the content and emotion of the text are, what the content and emotion of the voice are, etc.) . Deep neural networks include convolutional neural networks (CNN), recurrent neural networks (RNN), auto encoders, generative adversarial networks (GAN), and restricted Boltzmann machines (RBM). machine), deep belief network (DBN), Q network, U network, Siamese network, Generative Adversarial Network (GAN), etc. The description of the deep neural network described above is only an example and the present disclosure is not limited thereto.

In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network to output output data similar to input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be placed between input and output layers. The number of nodes in each layer may be reduced from the number of nodes in the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically and reduced from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform nonlinear dimensionality reduction. The number of input layers and output layers can be corresponded to the dimension after preprocessing of the input data. In an auto-encoder structure, the number of nodes in the hidden layer included in the encoder may have a structure that decreases as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, not enough information may be conveyed, so if it is higher than a certain number (e.g., more than half of the input layers, etc.) ) may be maintained.

A neural network may be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Learning of a neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

Neural networks can be trained to minimize output errors. In neural network learning, learning data is repeatedly input into the neural network, the output of the neural network and the error of the target for the learning data are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. This is the process of updating the weight of each node in the neural network through backpropagation. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (i.e., labeled learning data), and in the case of non-teacher learning, the correct answer may not be labeled in each learning data. That is, for example, in the case of teacher learning regarding data classification, the learning data may be data in which each learning data is labeled with a category. Labeled training data is input to the neural network, and the error can be calculated by comparing the output (category) of the neural network with the label of the training data. As another example, in the case of non-teachable learning for data classification, the error can be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the reverse direction (i.e., from the output layer to the input layer) in the neural network, and the connection weight of each node in each layer of the neural network can be updated according to backpropagation. The amount of change in the connection weight of each updated node may be determined according to the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently depending on the number of repetitions of the learning cycle of the neural network. For example, in the early stages of neural network training, a high learning rate can be used to increase efficiency by allowing the neural network to quickly achieve a certain level of performance, and in the later stages of training, a low learning rate can be used to increase accuracy.

In the learning of neural networks, the training data can generally be a subset of real data (i.e., the data to be processed using the learned neural network), and thus the error for the training data is reduced, but the error for the real data is reduced. There may be an incremental learning cycle. Overfitting is a phenomenon in which errors in actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that learned a cat by showing a yellow cat fails to recognize that it is a cat when it sees a non-yellow cat may be a type of overfitting. Overfitting can cause errors in machine learning algorithms to increase. To prevent such overfitting, various optimization methods can be used. To prevent overfitting, methods such as increasing the training data, regularization, dropout to disable some of the network nodes during the learning process, and use of a batch normalization layer are used. It can be applied.

Figure 3 is a flowchart showing a data set creation process for event prediction according to an embodiment of the present disclosure.

According to FIG. 3, the process of generating a data set for event prediction of the present disclosure includes obtaining medical data of a patient to generate a first data set (S310) and based on at least one condition related to intervention on the patient, It may include generating a second data set by removing at least a portion of the patient's medical data from the first data set (S320).

In step S310, the processor 110 may obtain the patient's medical data and generate a first data set. Specific examples of patient medical data were described above with reference to FIG. 1 .

In step S320, the processor 110 may generate a second data set by removing at least a portion of the patient's medical data from the first data set based on at least one condition related to intervention on the patient.

In one embodiment of the present disclosure, the at least one condition associated with the intervention for the patient may include at least one of a first condition or a second condition.

In one embodiment of the present disclosure, the first condition may include a condition related to a change in the patient's condition based on a retrospective study. At this time, retrospective research refers to conducting research on data that has already been collected, and can be a concept that contrasts with prospective research.

Specifically, the condition related to a change in the patient's condition based on a retrospective study included in the first condition may mean a case where the occurrence of an event for the patient changes due to the intervention of a medical staff. For example, if a patient is predicted to have cardiac arrest or sepsis, but the medical staff performs CPR or administers medication to the patient and the patient survives, this is a case where the occurrence of an event for the patient has changed due to the medical staff's intervention. The patient's medical data may be medical data that satisfies the first condition.

Medical data that satisfies the first condition is data that is labeled as having not occurred an event, but data in a certain period of time before intervention or action by medical staff is data in which an event is predicted to occur, so an event prediction model is created using this data. When training or evaluating the performance of an event prediction model, inaccurate results may be obtained. Accordingly, purified data can be obtained by removing at least a portion of the medical data that satisfies the first condition from the data set.

The processor 110 may determine at least a portion of the medical data of a patient that satisfies the first condition based on the point in time when intervention was performed, and exclude the medical data of the corresponding section from the first data set. For example, the processor may exclude medical data for certain time periods that include when medical intervention occurred. A specific method of removing at least some sections of medical data from medical data that satisfies the first condition will be described later with reference to FIG. 4 .

In another embodiment of the present disclosure, the second condition may include a case where the medical staff was unable to predict the occurrence of a patient's event through the patient's medical data. In addition, in the present disclosure, if the medical staff was unable to predict the occurrence of a patient's event through the patient's medical data, the medical staff's intervention was not performed from the time of the patient's event occurrence to the time before the predetermined value, and a warning such as SPTTS was issued to the patient. This may include cases where a system alarm is not generated.

For example, if cardiac arrest or sepsis occurred because there was no medical intervention before cardiac arrest or sepsis occurred in the patient and no alarm from the warning system was generated, or if the patient's death occurred after cardiac arrest or sepsis occurred, the patient's medical care The data may be medical data that satisfies the second condition.

If an alarm from the warning system is not generated and there is no intervention by medical staff until an event such as cardiac arrest or sepsis occurs in a patient, it is difficult to accurately predict the occurrence of the event or perform performance evaluation of the model based on the patient's medical data. They will say it is difficult. Therefore, training a machine learning model based on the patient's medical data or using the patient's medical data as verification data to evaluate the performance of the learned machine learning model may be practically meaningless tasks. . Rather, such data is likely to reduce the accuracy of the model being trained or make it impossible to accurately evaluate the performance of the learned model.

Therefore, by excluding medical data that satisfies the second condition from the first data set, refined data can be obtained. A specific method of excluding medical data that satisfies the second condition from the first data set will be described later with reference to FIG. 5 .

FIG. 4 is a conceptual diagram illustrating medical data of a patient satisfying the first condition and at least a partial section of the medical data according to an embodiment of the present disclosure.

The patient's medical data 400 shown in FIG. 4 is medical data of a patient in which no event occurred, and the intervention of a medical staff occurred at time t. When the medical staff intervenes, the processor 110 identifies the time point 430 after the predetermined time interval from the time point 410 before the predetermined time interval from the intervention point 420 based on the intervention time point 420 (t). can do. Thereafter, the processor 110 identifies a time interval 440 between a time point 410 before the predetermined time interval and a time point 430 after the predetermined time interval, and converts the medical data corresponding to this time interval into first data. can be excluded from.

In the present disclosure, the predetermined parameters that determine the time point 410 before the predetermined time interval and the time point 430 after the predetermined time interval may be fixed values, but may have the effect of refining a data set such as deep learning. It may be a variable number determined by various methods.

Figure 5 is a conceptual diagram showing medical data of a patient satisfying the second condition according to an embodiment of the present disclosure.

The patient's medical data 500 shown in FIG. 5 is medical data of a patient in which an event occurred. For a patient in whom an event occurred, the processor 110 may identify the event occurrence point (520, t). Thereafter, the processor 110 determines whether the medical staff intervenes within the time interval 530 from the time interval 510 before the event occurrence 520 to the event occurrence 520 and alarms the warning system such as SPTTS. By identifying whether the medical data has been created, it is possible to identify whether the corresponding medical data satisfies the second condition.

The processor 110 has no medical intervention or action within the time interval 530 from the time before the predetermined time interval 510 to the event occurrence 520, and an alarm from a warning system such as SPTTS is generated within the time interval 530. If not generated, it can be identified that the corresponding medical data satisfies the second condition. If the medical data satisfies the second condition, the processor 110 may exclude the entire medical data from the first data set.

In the present disclosure, the predetermined parameter that determines the time point 510 before the predetermined time interval may be a fixed number, but is determined by various methods that can produce the effect of refining the data set, such as machine learning and deep learning. , may be a variable number.

Meanwhile, a computer-readable medium storing a data structure is disclosed according to an embodiment of the present disclosure.

Data structure can refer to the organization, management, and storage of data to enable efficient access and modification of data. Data structure can refer to the organization of data to solve a specific problem (e.g., retrieving data, storing data, or modifying data in the shortest possible time). A data structure may be defined as a physical or logical relationship between data elements designed to support a specific data processing function. Logical relationships between data elements may include connection relationships between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements that are physically stored in a computer-readable storage medium (e.g., a persistent storage device). A data structure may specifically include a set of data, relationships between data, and functions or instructions applicable to the data. Effectively designed data structures allow computing devices to perform computations while minimizing the use of the computing device's resources. Specifically, computing devices can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and search through effectively designed data structures.

Data structures can be divided into linear data structures and non-linear data structures depending on the type of data structure. A linear data structure may be a structure in which only one piece of data is connected to another piece of data. Linear data structures may include List, Stack, Queue, and Deque. A list can refer to a set of data that has an internal order. The list may include a linked list. A linked list may be a data structure in which data is connected in such a way that each data is connected in a single line with a pointer. In a linked list, a pointer may contain connection information to the next or previous data. Depending on its form, a linked list can be expressed as a singly linked list, a doubly linked list, or a circularly linked list. A stack may be a data listing structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (for example, inserted or deleted) at only one end of the data structure. Data stored in the stack may have a data structure (LIFO-Last in First Out) where the later it enters, the sooner it comes out. A queue is a data listing structure that allows limited access to data. Unlike the stack, it can be a data structure (FIFO-First in First Out) where data stored later is released later. A deck can be a data structure that can process data at both ends of the data structure.

A non-linear data structure may be a structure in which multiple pieces of data are connected behind one piece of data. Nonlinear data structures may 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. Graph data structure may include a tree data structure. A tree data structure may be a data structure in which there is only one path connecting two different vertices among a plurality of vertices included in the tree. In other words, it may be a data structure that does not form a loop in the graph data structure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Below, it is described in a unified manner as a neural network. Data structures may include neural networks. And the data structure including the neural network may be stored in a computer-readable medium. Data structures including neural networks also include data preprocessed for processing by a neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may include a loss function for learning. A data structure containing a neural network may include any of the components disclosed above. In other words, the data structure including the neural network includes preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may be configured to include all or any combination of the loss function for learning. In addition to the configurations described above, a data structure containing a neural network may include any other information that determines the characteristics of the neural network. Additionally, the data structure may include all types of data used or generated in the computational process of a neural network and is not limited to the above. Computer-readable media may include computer-readable recording media and/or computer-readable transmission media. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node.

The data structure may include data input to the neural network. A data structure containing data input to a neural network may be stored in a computer-readable medium. Data input to the neural network may include learning data input during the neural network learning process and/or input data input to the neural network on which training has been completed. Data input to the neural network may include data that has undergone pre-processing and/or data subject to pre-processing. Preprocessing may include a data processing process to input data into a neural network. Therefore, the data structure may include data subject to preprocessing and data generated by preprocessing. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, weights and parameters may be used with the same meaning.) And the data structure including the weights of the neural network may be stored in a computer-readable medium. A neural network may include multiple weights. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. Based on the weight, the data value output from the output node can be determined. The above-described data structure is only an example and the present disclosure is not limited thereto.

As an example and not a limitation, the weights may include weights that are changed during the neural network learning process and/or weights for which neural network learning has been completed. Weights that change during the neural network learning process may include weights that change at the start of the learning cycle and/or weights that change during the learning cycle. Weights for which neural network training has been completed may include weights for which a learning cycle has been completed. Therefore, the data structure including the weights of the neural network may include weights that are changed during the neural network learning process and/or the data structure including the weights for which neural network learning has been completed. Therefore, the above-mentioned weights and/or combinations of each weight are included in the data structure including the weights of the neural network. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure including the weights of the neural network may be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be the process of converting a data structure into a form that can be stored on the same or a different computing device and later reorganized and used. Computing devices can transmit and receive data over a network by serializing data structures. Data structures containing the weights of a serialized neural network can be reconstructed on the same computing device or on a different computing device through deserialization. The data structure including the weights of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network is a data structure to increase computational efficiency while minimizing the use of computing device resources (e.g., in non-linear data structures, B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree) may be included. The foregoing is merely an example and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of a neural network. And the data structure including the hyperparameters of the neural network can be stored in a computer-readable medium. A hyperparameter may be a variable that can be changed by the user. Hyperparameters include, for example, learning rate, cost function, number of learning cycle repetitions, weight initialization (e.g., setting the range of weight values subject to weight initialization), Hidden Unit. It may include a number (e.g., number of hidden layers, number of nodes in hidden layers). The above-described data structure is only an example and the present disclosure is not limited thereto.

6 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Although the disclosure has been described above as being generally capable of being implemented by a computing device, those skilled in the art will understand that the 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 hardware. It will be well known that it can be implemented as a combination of software.

Typically, program modules include routines, programs, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Additionally, those skilled in the art will understand that the methods of the present disclosure can be used on single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. It will be appreciated that other computer system configurations may be implemented, including, but not limited to, each of which may operate in connection with one or more associated devices.

The described embodiments of the disclosure can also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer-readable media. Computer-readable media can be any medium that can be accessed by a computer, and such computer-readable media includes volatile and non-volatile media, transitory and non-transitory media, removable and non-transitory media. Includes removable media. By way of example, and not limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media refers to volatile and non-volatile media, transient and non-transitory media, removable and non-removable, implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Includes media. Computer readable storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage. This includes, but is not limited to, a device, or any other medium that can be accessed by a computer and used to store desired information.

A computer-readable transmission medium typically implements computer-readable instructions, data structures, program modules, or other data on a modulated data signal, such as a carrier wave or other transport mechanism. Includes all information delivery media. The term modulated data signal refers to a signal in which one or more of the characteristics of the signal have been set or changed to encode information within the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

An example environment 1100 is shown that implements various aspects of the present disclosure, including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 couples system components, including but not limited to system memory 1106, to processing unit 1104. Processing unit 1104 may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be used as processing unit 1104.

System bus 1108 may be any of several types of bus structures that may further be interconnected to a memory bus, peripheral bus, and local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112. The basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, and EEPROM, and is a basic input/output system that helps transfer information between components within the computer 1102, such as during startup. Contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

Computer 1102 may also include an internal hard disk drive (HDD) 1114 (e.g., EIDE, SATA)—the internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes - a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from or writing to a removable diskette 1118), and an optical disk drive 1120 (e.g., a CD-ROM (for reading the disk 1122 or reading from or writing to other high-capacity optical media such as DVD). Hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 are connected to system bus 1108 by hard disk drive interface 1124, magnetic disk drive interface 1126, and optical drive interface 1128, respectively. ) can be connected to. The interface 1124 for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. For computer 1102, drive and media correspond to storing any data in a suitable digital format. Although the description of computer-readable media above refers to removable optical media such as HDDs, removable magnetic disks, and CDs or DVDs, those of ordinary skill in the art will also recognize zip drives, magnetic cassettes, flash memory cards, and cartridges. It will be appreciated that other types of computer-readable media may also be used in the example operating environment, and that any such media may contain computer-executable instructions for performing the methods of the present disclosure. .

A number of program modules may be stored in drives and RAM 1112, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. All or portions of the operating system, applications, modules and/or data may also be cached in RAM 1112. It will be appreciated that the present disclosure may be implemented on various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into computer 1102 through one or more wired/wireless input devices, such as a keyboard 1138 and a pointing device such as mouse 1140. Other input devices (not shown) may include microphones, IR remote controls, joysticks, game pads, stylus pens, touch screens, etc. These and other input devices are connected to the processing unit 1104 through an input device interface 1142, which is often connected to the system bus 1108, but may also include a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, It can be connected by other interfaces, etc.

A monitor 1144 or other type of display device is also connected to system bus 1108 through an interface, such as a video adapter 1146. In addition to monitor 1144, computers typically include other peripheral output devices (not shown) such as speakers, printers, etc.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148, via wired and/or wireless communications. Remote computer(s) 1148 may be a workstation, computing device computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and is generally connected to computer 1102. For simplicity, only memory storage device 1150 is shown, although it includes many or all of the components described. The logical connections depicted include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, such as a wide area network (WAN) 1154. These LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a worldwide computer network, such as the Internet.

When used in a LAN networking environment, computer 1102 is connected to local network 1152 through wired and/or wireless communication network interfaces or adapters 1156. Adapter 1156 may facilitate wired or wireless communication to LAN 1152, which also includes a wireless access point installed thereon for communicating with wireless adapter 1156. When used in a WAN networking environment, the computer 1102 may include a modem 1158 or be connected to a communicating computing device on the WAN 1154 or to establish communications over the WAN 1154, such as over the Internet. Have other means. Modem 1158, which may be internal or external and a wired or wireless device, is coupled to system bus 1108 via serial port interface 1142. In a networked environment, program modules described for computer 1102, or portions thereof, may be stored in remote memory/storage device 1150. It will be appreciated that the network connections shown are exemplary and that other means of establishing a communications link between computers may be used.

Computer 1102 may be associated with any wireless device or object deployed and operating in wireless communications, such as a printer, scanner, desktop and/or portable computer, portable data assistant (PDA), communications satellite, wirelessly detectable tag. Performs actions to communicate with any device or location and telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, communication may be a predefined structure as in a conventional network or may simply be ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) allows connection to the Internet, etc. without wires. Wi-Fi is a wireless technology, like cell phones, that allows these devices, such as computers, to send and receive data indoors and outdoors, anywhere within the coverage area of a base station. Wi-Fi networks use wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, the Internet, and wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz wireless bands, for example, at data rates of 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band). .

Those skilled in the art will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols and chips that may be referenced in the above description include voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields. It can be expressed by particles or particles, or any combination thereof.

Those skilled in the art will understand that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein may be used in electronic hardware, (for convenience) It will be understood that it may be implemented by various forms of program or design code (referred to herein as software) or a combination of both. To clearly illustrate this interoperability of hardware and software, various illustrative components, blocks, modules, circuits and steps have been described above generally with respect to their functionality. Whether this functionality is implemented as hardware or software depends on the specific application and design constraints imposed on the overall system. A person skilled in the art of this disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of this disclosure.

The various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash. Includes, but is not limited to, memory devices (e.g., EEPROM, cards, sticks, key drives, etc.). Additionally, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of illustrative approaches. It is to be understood that the specific order or hierarchy of steps in processes may be rearranged within the scope of the present disclosure, based on design priorities. The appended method claims present elements of the various steps in a sample order but are not meant to be limited to the particular order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Thus, the present disclosure is not limited to the embodiments presented herein but is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

Claims (12)

1. A method of generating a data set for event prediction, performed by a computing device, comprising:
Obtaining medical data of a patient to generate a first data set; and
generating a second data set by removing at least a portion of the medical data of the patient from the first data set based on at least one condition related to intervention with the patient;
Including,
Creating the second data set includes:
At least some sections of medical data of patients who satisfy the first condition among patients in whom the event did not occur are excluded from the first data set, or medical data of patients who satisfy the second condition among patients where the event occurs are excluded from the first data set. 1 performing at least one of excluding from the data set;
Including,
method.
delete According to claim 1,
The first condition is,
Conditions related to changes in the patient's condition based on retrospective studies;
Including,
method.
According to claim 3,
The first condition is,
Includes cases where the occurrence of the event changes due to intervention by medical staff,
At least some sections of the patient's medical data that satisfy the first condition are determined based on the time when the intervention was performed,
method.
According to claim 4,
The intervention of the medical staff is,
Medical action performed to prevent the occurrence of said event;
Including,
method.
According to claim 1,
The second condition is,
When the medical staff was unable to predict the occurrence of the event through the patient's medical data;
Including,
method.
According to claim 6,
In cases where the medical staff was unable to predict the occurrence of the event through the patient's medical data:
When there is no intervention by medical staff from the time of occurrence of the patient's event to the time before the predetermined value; and
If an alarm in the warning system is not generated for the patient;
Including,
method.
According to claim 1,
generating a learning data set based on the second data set; and
Learning an event prediction model based on the learning data set;
It further includes,
The event prediction model is a machine learning model that receives the patient's medical data and outputs prediction information related to the occurrence of the event.
method.
According to claim 1,
generating a verification data set based on the second data set; and
Evaluating the performance of an event prediction model based on the verification data set;
It further includes,
The event prediction model is a machine learning model that receives the patient's medical data and outputs prediction information related to the occurrence of the event.
method.
According to claim 8 or 9,
The event prediction model is a machine learning model that receives the patient's medical data and outputs prediction information related to the patient's cardiac arrest or sepsis.
method.
A computer program stored on a computer-readable storage medium that includes operations for causing a computing device to generate a data set for event prediction, the operations comprising:
Obtaining medical data of a patient to generate a first data set; and
generating a second data set by removing at least a portion of the medical data of the patient from the first data set based on at least one condition related to intervention on the patient;
Including,
The operation of generating the second data set is:
At least some sections of medical data of patients who satisfy the first condition among patients in whom the event did not occur are excluded from the first data set, or medical data of patients who satisfy the second condition among patients where the event occurs are excluded from the first data set. 1 performing at least one of the following: excluding from a data set;
Including,
A computer program stored on a computer-readable storage medium.
As a computing device,
One or more processors; and
Memory;
Including,
The processor,
Obtain the patient's medical data to create a first data set, and
Based on at least one condition related to an intervention for the patient, remove at least a portion of the patient's medical data from the first data set to create a second data set,
Creating the second data set:
At least a portion of the medical data of a patient who satisfies the first condition among patients in whom an event did not occur is excluded from the first data set, or the medical data of a patient who satisfies the second condition among patients in whom the event occurs is excluded from the first data set. Perform at least one of the following: exclude from the data set;
Including,
Computing device.

Images