Severity prediction methods for diagnosing sepsis
The artificial neural network model improves the accuracy of SOFA score prediction and sepsis diagnosis by processing EMR data and vital signs, addressing the inaccuracies in existing methods due to missing values.
Patent Information
- Application Number
- JP2023137465
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-04-26
- Filing Date
- 2023-08-25
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2043-08-25
AI Technical Summary
Existing methods for calculating the Sequential Organ Failure Assessment (SOFA) score in sepsis diagnosis are inaccurate due to missing values and reliance on imputation or machine learning models, leading to decreased accuracy over time.
A severity prediction method using an artificial neural network model that processes Electronic Medical Record (EMR) data and vital signs to generate predicted values for SOFA scores, incorporating time intervals and biosignals to improve accuracy.
The method accurately predicts SOFA scores and identifies sepsis and septic shock, enhancing the precision of sepsis diagnosis by leveraging EMR data and vital signs through an artificial neural network model.
Smart Images

Figure 2024159401000001_ABST
Abstract
Description
[Technical field]
[0001] The present disclosure relates to a method for predicting severity for diagnosing sepsis, and more particularly to a method for generating a predicted value for a patient's severity based on medical data of the patient using a severity prediction model that is an artificial neural network model. [Background technology]
[0002] A variety of multidimensional evaluation indices are used in the medical field to evaluate the severity of various diseases. Among the indices for evaluating the severity, predicting the Sequential Organ Failure Assessment (SOFA) score, which is an index that can identify whether and when sepsis occurs in patients suspected of infection, is an important issue in evaluating the severity, especially in diagnosing sepsis.
[0003] The SOFA score is a score obtained by adding up the scores of six predetermined items, and for accurate measurement, all six items (respiration, coagulation, bilirubin, cardiovascular hypotension, CNS Glasgow Coma Scale, and renal creatinine) must have records at a specific time point. However, in actual medical practice, each item is often not measured at the same time point, and the interval between measurements is relatively long. Conventionally, in order to calculate the SOFA score at a time point when there is a missing value among the six items, a method of imputing the missing value with a measurement value at a previous time point or predicting the missing value using a machine learning model has been used. However, the method of imputing the missing value has a disadvantage that the accuracy decreases the further back the actual measurement time point is, and the method of predicting the missing value using a machine learning model has a disadvantage that errors occurring in each item are accumulated, and the final SOFA score is not accurately measured. Therefore, there is a demand in the industry for a method of calculating an accurate SOFA score for diagnosing the severity of sepsis, etc., even when there is a missing value among the six items.
[0004] Korean Patent No. 2460948 discloses a method for providing information necessary for assessing the severity of coronary artery stenosis. Summary of the Invention [Problem to be solved by the invention]
[0005] The present disclosure has been devised in response to the above-mentioned background art, and aims to generate a prediction value for a patient's severity based on the patient's medical data by utilizing a severity prediction model, which is an artificial neural network model.
[0006] However, the technical problems that the present disclosure aims to solve are not limited to the above-mentioned technical problems, and may include a variety of technical problems within the scope that is obvious to a person skilled in the art from the content described below. [Means for solving the problem]
[0007] According to an embodiment of the present disclosure for achieving the above object, a method for predicting severity executed by a computing device is disclosed, which may include the steps of acquiring EMR (Electronic Medical Record) data and vital signs of a patient, and generating a predicted value related to the severity of the patient based on the EMR data and the vital signs of the patient using a severity prediction model, and the severity prediction model may be an artificial neural network model trained using a portion of training EMR data extracted based on a time interval during which a predetermined number of items are acquired and the training vital signs corresponding to the time interval.
[0008] In one embodiment, the method may further include generating a prediction value for severity of the patient based on information regarding whether the patient is suspected of infection.
[0009] In one embodiment, the method may further include a step of calculating at least one of information related to sepsis and information related to septic shock for the patient based on the predicted value related to the severity of the patient.
[0010] In one embodiment, the method may further include a step of labeling the medical data of the patient with information related to sepsis or information related to septic shock of the patient, and generating a second training data set based on the labeling, and a step of training a sepsis diagnosis model, which is an artificial neural network model, based on the second training data set.
[0011] In one embodiment, the sepsis diagnosis model may be an artificial neural network model that generates a prediction value for at least one of the onset time of sepsis and the onset time of septic shock in a patient suspected of sepsis based on medical data of the patient suspected of sepsis.
[0012] According to an embodiment of the present disclosure for achieving the above object, a method for generating learning data for predicting severity, executed by a computing device, is disclosed. The method may include identifying a time interval during which a plurality of predetermined items are acquired from EMR (Electronic Medical Record) data, and generating learning data for predicting the severity based on a portion of the EMR data corresponding to the identified time interval and a vital sign corresponding to the identified time interval.
[0013] In one embodiment, the predetermined items may be items related to prediction of a Sequential Organ Failure Assessment (SOFA) score.
[0014] In one embodiment, identifying a time period during which the predetermined number of items were obtained includes: identifying a time period during which a predetermined number or more of the six items predictive of the SOFA score were obtained, each of the predetermined number or more items being capable of being obtained at at least one time point in the identified time period.
[0015] In one embodiment, identifying a time period during which the predetermined number of items were obtained includes identifying a time period during which all six items relevant to predicting the SOFA score were obtained, each of the six items being capable of being obtained at at least one time point during the identified time period.
[0016] In one embodiment, the step of generating learning data for predicting the severity based on a portion of the EMR data corresponding to the identified time interval and a vital sign corresponding to the identified time interval may further include a step of masking the portion of the EMR data corresponding to the identified time interval and at least a portion of the vital sign corresponding to the identified time interval, and generating learning data for predicting the severity based thereon.
[0017] According to an embodiment of the present disclosure for achieving the above object, a computer program stored in a computer-readable storage medium is disclosed, which causes a computing device to perform a plurality of operations for predicting severity, including: acquiring EMR data and a biosignal of the patient, and using a severity prediction model to generate a prediction value related to the severity of the patient based on the EMR data and the biosignal of the patient, wherein the severity prediction model can be an artificial neural network model trained using a portion of training EMR data extracted based on a time interval during which a plurality of predetermined items are acquired and the training biosignal corresponding to the time interval.
[0018] In order to solve the above-mentioned problems, a computing device according to an embodiment of the present disclosure is disclosed, the device includes a processor including one or more cores and a memory, the processor is configured to acquire EMR data of a patient and a biosignal of the patient, and generate a prediction value of the severity of the patient based on the EMR data of the patient and the biosignal of the patient using a severity prediction model, the severity prediction model can be an artificial neural network model trained using a part of the training EMR data extracted based on a time interval during which a predetermined number of items are acquired and the training biosignal corresponding to the time interval. Effect of the Invention
[0019] The present disclosure provides an effect of more accurately assessing the severity of a disease to diagnose sepsis, etc. In particular, the severity prediction model, which is an artificial neural network model of the present disclosure, can be used to accurately predict a patient's SOFA score based on the patient's medical data, and the SOFA score can be used to more accurately predict the onset of sepsis and septic shock. [Brief description of the drawings]
[0020] [Figure 1] FIG. 2 is a block diagram of a computing device for predicting severity in one embodiment of the present disclosure. [Diagram 2] FIG. 2 is a schematic diagram illustrating a network function in one embodiment of the present disclosure. [Diagram 3] 1 is a flowchart illustrating a process for predicting the severity of a patient in one embodiment of the present disclosure. [Figure 4] FIG. 1 is a conceptual diagram showing a conventional method used to calculate a patient's SOFA score. [Diagram 5] FIG. 1 is a conceptual diagram showing a method for predicting a SOFA score using a severity prediction model in one embodiment of the present disclosure. [Figure 6] 1 is a flowchart showing a process of training a sepsis diagnosis model in one embodiment of the present disclosure. [Figure 7a] 1 is a conceptual diagram showing learning data for training a severity prediction model in one embodiment of the present disclosure. [Figure 7b] 1 is a conceptual diagram showing expanded learning data for training a severity prediction model in one embodiment of the present disclosure. [Figure 8] FIG. 1 is a conceptual diagram showing a method for training a severity prediction model in one embodiment of the present disclosure. [Figure 9] FIG. 1 is a simplified generalized diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0021] The present disclosure discloses a method for generating a predicted value for a patient's severity based on the patient's medical data using a severity prediction model, which is an artificial neural network model, and a method for generating information related to sepsis and septic shock based on the predicted value for the patient's severity.
[0022] Various embodiments will be described below with reference to the drawings. Various descriptions are provided herein to facilitate understanding of the present disclosure. However, it is apparent that such embodiments can be practiced without such specific descriptions.
[0023] As used herein, terms such as "component," "module," and "system" refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or software execution. For example, a component can be, but is not limited to, a procedure 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 can reside within a processor and / or thread of execution. A component can be localized within one computer. A component can be distributed across two or more computers. Such components can also be executed on various computer-readable media having various data structures stored therein. Components can communicate through local and / or remote processes, etc., using signals (e.g., data transmitted over a network such as the Internet to other systems using data and / or signals from one component interacting with other components in a local or distributed system), including, for example, one or more data packets.
[0024] It should be noted that the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified and unless otherwise clear from the context, "X utilizes A or B" is intended to mean one of the natural inclusive permutations. That is, if X utilizes A; X utilizes B; or X utilizes both A and B, then "X utilizes A or B" can apply to any of these. 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 associated items listed.
[0025] Additionally, the predicate "comprises" and / or the modifier "comprises" should be understood to mean the presence of the feature and / or component in question. However, the predicate "comprises" and / or the modifier "comprises" should be understood not to exclude the presence or addition of one or more other further features, components and / or groups thereof. Additionally, in the present specification and claims, the singular should generally be construed to mean "one or more," unless a specific number is specified or the context is clear to indicate the singular form.
[0026] Furthermore, the term "at least one of A or B" should be interpreted as meaning "a case in which only A is included," "a case in which only B is included," or "a case in which a combination of A and B is included."
[0027] Those skilled in the art should further appreciate that the various exemplary logical blocks, configurations, modules, circuits, means, logic, and algorithm steps described in accordance with the embodiments disclosed herein can be realized by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the various exemplary components, blocks, configurations, means, logic, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design limitations of the overall system. Skilled artisans can implement the described functionality in various ways for each particular application. However, such implementation decisions should not be interpreted as departing from the scope of the present disclosure.
[0028] The description of the embodiments set forth herein is provided to enable any person skilled in the art to use or practice the present disclosure. Various modifications to the embodiments will be apparent to those skilled in the art to which the present disclosure pertains. The generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present invention is not limited to the embodiments set forth herein. The present invention is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.
[0029] In the present disclosure, medical data may include EMR (Electronic Medical Record) data and vital signs of a patient. In the present disclosure, EMR data may refer to data in which medical records related to a patient are recorded in electronic form, and data related to multiple detailed items for calculating the severity of a patient may be included in the EMR data. For example, data related to Respiration, Coagulation, Bilirubin, Cardiovascular Hypotension, CNS Glasgow Coma Scale, and Renal Creatinine, which are indexes for calculating a patient's SOFA score, may be included in the EMR data.
[0030] In the present disclosure, "detailed information related to severity" may refer to detailed items for determining various indexes capable of expressing the severity of a patient, such as the SOFA score, etc. For example, detailed information related to severity may refer to six items for calculating the SOFA score, namely, Respiration, Coagulation, Bilirubin, Cardiovascular Hypotension, CNS Glasgow Coma Scale, and Renal Creatinine.
[0031] In the present disclosure, the onset time of sepsis and the onset time of septic shock are estimated for patients suspected of infection, and can be estimated by the following method. First, the suspected infection time of the patient is estimated. The time of culture test in cases where a culture test is performed within 24 hours after antibiotics are administered, and the time of antibiotic administration in cases where antibiotics are administered within 72 hours after the culture test are performed are recorded, and the earlier of the two time points can be estimated as the suspected infection time.
[0032] If the SOFA score increases by 2 or more points within a 24-hour period 48 hours before and 24 hours after the suspected infection, it can be assumed that this is the time when sepsis occurred.
[0033] Furthermore, if certain conditions are satisfied from the time of onset of sepsis, it is possible to estimate that the time at which a vasopressor is administered to a patient is the time at which septic shock occurs.
[0034] FIG. 1 is a block diagram of a computing device for predicting severity in one embodiment of the present disclosure.
[0035] 1 is merely a simplified example, and in one embodiment of the present disclosure, the computer device (100) may include other components for implementing the computing environment of the computer device (100), and the computer device (100) may be configured with only some of the disclosed components.
[0036] The computer device (100) may include a processor (110), a memory (130), and a network unit (150).
[0037] In one embodiment of the present disclosure, the processor (100) may be configured with one or more cores and may include a processor for data analysis and deep learning, such as a computing central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU). The processor (110) may read a computer program stored in the memory (130) and execute data processing for machine learning in one embodiment of the present disclosure. According to one embodiment of the present disclosure, the processor (110) may perform calculations for learning a neural network. In deep learning (DL), the processor (110) may execute calculations for learning a neural network, such as processing input data for learning, extracting features from the input data, calculating errors, and updating the weights of the neural network using backpropagation.
[0038] At least one of the CPU, GPGPU, and TPU of the processor (110) can process the learning of the network function. For example, the CPU and the GPGPU can both perform the learning of the network function or the classification of data using the network function. In one embodiment of the present disclosure, the processors of multiple computing devices can be used together to perform the learning of the network function or the classification of data using the network function. In one embodiment of the present disclosure, the computer program executed in the computing device can be a program executable by the CPU, the GPGPU, or the TPU.
[0039] The processor 110 may use the severity prediction model to generate a prediction value for the severity of the patient based on the patient's medical data. In the present disclosure, the patient's medical data may include at least a portion of the patient's vital sign information and the patient's electronic medical record data.
[0040] In the present disclosure, the predicted value of the patient's severity generated by the processor (110) may be time-series data including the patient's SOFA score at each time point (hereinafter, "predicted SOFA score value"). A more specific method for the processor (110) to generate the predicted value of the patient's severity will be described later with reference to FIG. 3.
[0041] In the present disclosure, the processor 110 may further generate a prediction of the severity of the patient based on the patient's medical data and information regarding whether the patient is suspected of infection. For example, the processor 110 may receive the patient's medical data and information regarding whether the patient is suspected of infection and generate a prediction of the patient's SOFA score.
[0042] The processor 110 is capable of calculating information on sepsis or septic shock for the patient based on the predicted value of the severity of the patient, labeling the medical data of the patient with this information as label data, and generating second learning data. The processor 110 is capable of training a sepsis diagnosis model, which is an artificial neural network model, based on the second learning data thus generated. A specific method of generating learning data and a learning method for training the sepsis diagnosis model will be described later with reference to FIG. 6.
[0043] In the present disclosure, the processor (110) is capable of generating training data for training a severity prediction model based on at least a portion of the EMR data and vital sign information of the patient corresponding to the identified time interval.
[0044] Specifically, the processor (110) can identify a time period during which a predetermined number of items were acquired from the patient's entire EMR data, and generate learning data using only a portion of the EMR data corresponding to that time period.
[0045] In addition, in the present disclosure, the learning data for training the severity prediction model can include not only the EMR data of the patient but also the vital sign information of the patient. For example, when the severity prediction model is a model for predicting the SOFA score of the patient, the learning data for training the severity prediction model can include not only data related to six items related to prediction of the SOFA score measured in a specific time interval, namely, Respiration, Coagulation, Bilirubin, Cardiovascular Hypotension, CNS Glasgow Coma Scale, and Renal Creatinine, but also vital sign data measured in a time interval corresponding to the signal.
[0046] As described above, a specific method for generating learning data for training a severity prediction model based on a portion of EMR data corresponding to a time interval in which a predetermined number of items were acquired and a biological signal corresponding to an identified time interval will be described later with reference to Figures 7a and 7b.
[0047] In the present disclosure, in order to generate a patient's severity, for example, a predicted SOFA score value, not only is data related to six items of EMR data related to prediction of SOFA score learned, but also biosignal information of the patient measured in a time period corresponding to the data is learned. Biosignals such as pulse and blood pressure have a shorter measurement period and fewer missing values compared to the six items. Therefore, when a model is trained by including all biosignals of the same patient corresponding to the time period of the data in addition to the six items of data of the patient's EMR data related to prediction of SOFA score, the model also learns the relationship between the two types of data (six items of EMR data related to prediction of SOFA score and biosignals), and the accuracy of the predicted value generated by the severity prediction model is improved.
[0048] In one embodiment of the present disclosure, the memory (130) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., 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) may also operate in conjunction with a web storage that performs the storage function of the memory (130) over the Internet. The above description of the memory is merely exemplary, and the present disclosure is not limited thereto.
[0049] In one embodiment of the present disclosure, the network unit (150) can use various wired communication systems such as a Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), Very High Speed DSL (VDSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and a local area network (LAN).
[0050] In addition, the network unit (150) in this specification can use 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. In the present disclosure, the network unit 150 can utilize any type of wired or wireless communication system.
[0051] The techniques described herein can be used in the networks mentioned above as well as other networks.
[0052] FIG. 2 is a schematic diagram illustrating a network function in one embodiment of the present disclosure.
[0053] Throughout this specification, the terms computational model, neural network, network function, and neural network may be used interchangeably. A neural network is often composed of a collection of interconnected computational units, generally called nodes. Such nodes may also be referred to as neurons. A neural network is composed of at least one or more nodes. The nodes (or neurons) that make up a neural network may be interconnected by one or more links.
[0054] In a neural network, one or more nodes connected via links can form a relationship of input node and output node relative to each other. The concept of input node and output node is relative, and any node that is an output node for one node can be an input node in relation to another node, and vice versa. As mentioned above, the relationship between input node and output node can be established around the link. One or more output nodes can be connected to one input node via links, and vice versa.
[0055] In the relationship between an input node and an output node connected via a link, the data of the output node can 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. The weight can be variable and can be changed by a user or an algorithm so that the neural network performs a desired function. For example, when one or more input nodes are interconnected to one output node by each link, the output node can determine the value of the output node based on the value input to the input node connected to the output node and the weight set to the link corresponding to each input node.
[0056] As mentioned above, in a neural network, one or more nodes are interconnected through one or more links to form a relationship between an input node and an output node in the neural network. In a neural network, the characteristics of the neural network can be determined by the number of nodes and links, the correlation between the nodes and links, and the weight value assigned to each link. For example, if there are two neural networks that have the same number of nodes and links but different link weight values, the two neural networks can be recognized as different.
[0057] A neural network may be composed of a set of one or more nodes. A subset of the nodes in a neural network may form a layer. A portion of the nodes in a neural network may form a layer based on their distance from a first input node. For example, a set of nodes whose distance from a first input node is n may form an n-layer. The distance from the first input node may be defined based on the minimum number of links that must be traversed to reach the node from the first input node. However, this definition of a layer is given arbitrarily for the purpose of explanation, and the configuration of layers in a neural network may be defined in a manner different from that described above. For example, a layer of nodes may be defined based on their distance from a final output node.
[0058] The first input node may refer to one or more nodes in a neural network to which data is directly input without passing through a link in relation to other nodes. Alternatively, the first input node may refer to a node that does not have other input nodes connected via a link in relation between nodes based on links in a neural network. Similarly, the final output node may refer to one or more nodes in a neural network that do not have an output node in relation to other nodes. In addition, the hidden node may refer to a node that is neither a first input node nor a final output node and that constitutes a neural network.
[0059] The neural network according to an embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer is the same as the number of nodes in the output layer, and the number of nodes decreases once and then increases again as the input layer progresses to the hidden layer. The neural network according to an embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer is smaller than the number of nodes in the output layer, and the number of nodes decreases as the input layer progresses to the hidden layer. Furthermore, 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 is greater than the number of nodes in the output layer, and the number of nodes increases as the input layer progresses to the hidden layer. The neural network according to another embodiment of the present disclosure may be a neural network in which the above-mentioned neural networks are combined.
[0060] Deep neural networks (DNNs) can refer to neural networks that include multiple hidden layers in addition to input and output layers. Deep neural networks can be used to understand the latent structures of data. In other words, they can understand the latent structures of photos, text, videos, audio, and music (e.g., whether an object is in the photo, what is the content and emotion of the text, what is the content and emotion of the audio, etc.). Deep neural networks can include convolutional neural networks (CNNs), recurrent neural networks (RNNs), autoencoders, generative adversarial networks (GANs), restricted boltzmann machines (RBMs), deep belief networks (DBNs), Q networks, U networks, Siamese networks, generative adversarial networks (GANs), etc. The above-mentioned deep neural networks are merely examples and the present disclosure is not limited thereto.
[0061] In one embodiment of the present disclosure, the network function may include an autoencoder. The autoencoder may be a type of artificial neural network for outputting output data similar to input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be disposed between the input and output layers. The number of nodes in each layer may decrease from the number of nodes in the input layer toward an intermediate layer called a bottleneck layer (encode), and may be expanded from the bottleneck layer toward the output layer (symmetrical to the input layer) in a manner symmetrical to the reduction. The autoencoder may perform nonlinear dimensionality reduction. The number of input layers and output layers may correspond to the dimensions after preprocessing of the input data. In the autoencoder structure, the number of nodes in the hidden layer included in the encoder may decrease 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 a sufficient amount of information may not be transmitted, so it may be maintained at a certain number or more (e.g., more than half of the input layer, etc.).
[0062] A neural network can be trained by at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Training a neural network can be a process of providing the neural network with knowledge to perform a specific operation.
[0063] Neural networks can be trained in a direction that minimizes the error of the output. In training a neural network, training data is repeatedly input to the neural network, the error of the neural network output and the target regarding the training data is calculated, and the weight value of each node of the neural network is updated by backpropagating the error of the neural network from the output layer of the neural network to the input layer as a direction to reduce the error. In the case of supervised learning, training data in which the correct answer is labeled is used for each training data (i.e., labeled training data), and in the case of unsupervised learning, the correct answer may not be labeled for each training data. That is, for example, the training data in supervised learning for data classification can be data in which each training data is labeled with a category. The 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 unsupervised learning for data classification, the error can be calculated by comparing the input training data with the output of the neural network. 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 value of each node in each layer of the neural network can be updated through backpropagation. The amount of change in the connection weight value of each node to be updated can be determined by a 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 be changed depending on the number of iterations of the neural network learning cycle. For example, in the early stage of neural network learning, the learning rate can be increased to increase efficiency by allowing the neural network to quickly achieve a certain level of performance, and in the later stage of learning, the learning rate can be decreased to increase accuracy.
[0064] In the training of a neural network, the training data may generally be a subset of the actual data (i.e., data to be processed using the trained neural network), and therefore there may be a training cycle in which the error associated with the training data decreases, but the error associated with the actual data increases. Overfitting is a phenomenon in which errors increase in the actual data due to excessive learning of the training data. For example, a neural network that has learned about cats by looking at a yellow cat may be unable to recognize that it is a cat when it sees a cat of a color other than yellow, which may be a type of overfitting. Overfitting may cause an increase in errors in machine learning algorithms. To prevent overfitting, various optimization methods may be applied. To prevent overfitting, methods such as increasing the training data, regularization, dropout, which deactivates some of the nodes of the network during the training process, and the use of a batch normalization layer may be applied.
[0065] FIG. 3 is a flow chart illustrating a process of predicting the severity of a patient in one embodiment of the present disclosure.
[0066] According to FIG. 3, in one embodiment of the present disclosure, a process of predicting a patient's severity may include a step of acquiring the patient's EMR data and the patient's vital signs (S310), and a step of using a severity prediction model to generate a predicted value for the patient's severity based on the patient's EMR data and the patient's vital signs (S320). In step S310, the processor (110) can obtain medical data including EMR data of the patient and vital signs of the patient. For example, the medical data can include EMR data such as Respiration, Coagulation, Bilirubin, Cardiovascular Hypotension, CNS Glasgow Coma Scale, and Renal Creatinine values measured for the patient, and vital signs such as the patient's respiration rate, pulse rate, blood pressure, etc.
[0067] In step S320, the processor 110 can use the severity prediction model to generate a prediction value for the severity of the patient based on the EMR data of the patient and the patient's vital signs acquired in step S310. For example, the processor 110 can use the severity prediction model to generate time series data including a predicted SOFA score value of the patient at each time point.
[0068] The SOFA score is calculated as the sum of the item-specific SOFA scores measured for six items in the EMR data. Below, we will use Figure 4 to describe the method that has traditionally been used to calculate a patient's SOFA score.
[0069] As mentioned above, the SOFA score is calculated as the sum of the item-specific SOFA scores calculated for the measurements of six items in the EMR data. When there are missing values for multiple items used to calculate the SOFA score at each time point, the data for the same item at the previous time point was used to impute the missing values at each time point, and then the values of all six items were added up at each time point to derive the SOFA score at each time point.
[0070] For example, in FIG. 4, white dots can represent data points with no measured value, and black dots can represent data points with actual measured values. In this case, at 20:23, of the six items for calculating the SOFA score, three items, Coagulation, Cardiovascular Hypotension (Cardiovascular), and Glasgow Coma Scale (Central nervous system), were measured as 1, 3, and 1, respectively. Conventionally, for the remaining three items that were not measured, if there was no past measurement record, such as Respiration and Bilirubin (Liver), they were substituted with 0, and if there was a past measurement record, such as Renal Creatinine (Renal), they were substituted with the past value. In FIG. 4, Renal Creatinine was measured as 1 at 13:32, so it is possible to replace the Renal item at 20:23 with 1. As a result, the SOFA scores for each item were [0, 1, 0, 3, 1, 1], and the patient's SOFA score at 20:23 was calculated to be the sum of these, 6. However, such conventional methods have the problem that if the past data to substitute for missing values was measured too far in the past, or if no measurements exist at all, the SOFA score may be calculated inaccurately.
[0071] In the present disclosure, it is possible to input data that does not use substitute values, i.e., a portion of the actually measured EMR data and vital sign information of the patient, into the severity prediction model as shown in Fig. 5, and calculate the predicted SOFA score at each time point. For example, when data as shown in Fig. 5 is input into the severity prediction model, there is a missing value at the time point of 20:23, but in the present disclosure, it is possible to immediately predict the SOFA score as 6 at the time point of 20:23 without being affected by the missing value.
[0072] In the conventional method, in the process of substituting missing values with past values, if past data was measured too far in the past or if there was no measurement from the beginning, there was a high possibility that the substituted data would not match the actual patient's condition. Therefore, the patient's SOFA score finally derived by the substituted value may also be inaccurate. In contrast, in the present disclosure, the artificial neural network model receives only data actually measured in the past without a separate substitution process and generates a predicted value of the SOFA score, so it is possible to generate a more accurate SOFA score compared to the conventional method.
[0073] FIG. 6 is a flowchart illustrating a process for training a sepsis diagnostic model in one embodiment of the present disclosure.
[0074] According to FIG. 6, the process of training the sepsis diagnostic model of the present disclosure can include a step (S410) of calculating at least one of information related to sepsis and information related to septic shock for the patient based on a predicted value related to the severity of the patient, a step (S420) of labeling the medical data of the patient with the information related to sepsis or information related to septic shock for the patient and generating second training data based on the labeling, and a step (S430) of training the sepsis diagnostic model, which is an artificial neural network model, based on the second training data.
[0075] In step S410, the processor 110 can calculate at least one of information related to sepsis and information related to septic shock for the patient based on the predicted value related to the severity of the patient. For example, the processor 110 can estimate the time of onset of sepsis or septic shock for the patient based on medical data including a predicted value of the patient's SOFA score generated through a severity prediction model for the patient or the like. A specific method for estimating the time of onset of sepsis or septic shock based on the SOFA score has been described above.
[0076] In step S420, the processor (110) can label the information related to sepsis or septic shock calculated in step S410 to the medical data on which the calculation was based, to generate second learning data.
[0077] At step S430, the processor (110) can train a sepsis diagnosis model, which is an artificial neural network model, based on the second learning data. In the present disclosure, the sepsis diagnosis model can refer to an artificial neural network model that generates a prediction value related to at least one of the onset time of sepsis and the onset time of septic shock in a patient suspected of sepsis, based on medical data of the patient suspected of sepsis.
[0078] The present disclosure makes it possible to predict an accurate SOFA score at each point in time from a patient's medical data, and makes it possible to accurately estimate the time when sepsis or septic shock occurs from the medical data and the SOFA score.
[0079] 7a and 7b are conceptual diagrams showing training data for training a severity prediction model in one embodiment of the present disclosure.
[0080] To generate training data for training the severity prediction model, the processor (110) can identify a time interval during which a predetermined number of items are acquired from the patient's EMR data. For example, if the severity prediction model is an artificial neural network model for predicting the patient's SOFA score, the six items of the EMR data related to the prediction of the SOFA score include Respiration, Coagulation, Bilirubin, Cardiovascular Hypotension, CNS Glasgow Coma Scale, and Renal Creatinine. The processor (110) can identify a time interval during which all six items related to the prediction of the SOFA score are acquired from the patient's EMR data in a particular time interval (e.g., 24 hours). That is, in this case, each of the six items is acquired at at least one time point in the identified time interval.
[0081] For example, if in a patient's EMR data, there is at least one measurement for each of the six items related to predicting SOFA score in the time interval from 13 hours 32 minutes after admission to 37 hours 32 minutes after admission, i.e., there is a time interval in which all six items are obtained, the processor (110) can identify the time interval from 13 hours 32 minutes after admission to 37 hours 32 minutes after admission.
[0082] The processor (110) is capable of generating learning data for predicting severity based on a portion of the EMR data corresponding to the identified time interval and a biological signal corresponding to the identified time interval.
[0083] For example, if the severity prediction model is an artificial neural network model that predicts a patient's SOFA score, and the time interval during which a predetermined number of items are acquired is the interval from 13 hours and 32 minutes after the patient's admission to 37 hours and 32 minutes after the patient's admission, the processor (110) can generate learning data for predicting severity, including all data acquired for six items of EMR data measured during that time interval and all of the patient's biosignals measured during that time interval.
[0084] However, in the present disclosure, the method of generating training data is not limited to the above example, and an appropriate training data generation method can be selected taking into consideration the type of data, the training time, etc. For example, when the severity prediction model is a model for predicting a patient's SOFA score, the processor (110) can identify a time interval in which five of six items related to the prediction of the SOFA score were acquired, that is, a time interval in which one or less items were not measured at all, and generate training data based on data related to the five items measured in that time interval and the corresponding biological signals.
[0085] When the severity prediction model is an artificial neural network model for predicting a patient's SOFA score, an exemplary structure of training data for training the severity prediction model is illustrated in Fig. 7a. The training data may be data including six items related to the prediction of the SOFA score, i.e., respiration, coagulation, liver, cardiovascular, central nervous system, and renal, obtained in a specific time period (e.g., 24 hours), and the patient's biosignals obtained in the time period.
[0086] Each of the six items for calculating the SOFA score is not measured in a period as short as that of a biological signal, and all items may not be measured at the same time. Therefore, when training an artificial neural network model that predicts the SOFA score using the entire EMR data recorded on a patient, if the trained EMR data does not contain sufficient useful data, a problem occurs in which the predictive performance of the model is reduced. In the present disclosure, the entire EMR data of the patient is not used as training data, but training data is generated using only data from a time period (e.g., 24 hours) that contains a sufficient amount of data to predict the SOFA score. Therefore, it is possible to train the model by filtering out only the useful data through training, and the effect of improving the performance of the final completed model is obtained.
[0087] Moreover, in the present disclosure, the input of the artificial neural network model includes not only the patient's EMR data but also biosignal information, so that the artificial neural network model can reflect the relationship between the two types of data and predict a more accurate SOFA score.
[0088] In the present disclosure, in order to improve the accuracy of the severity prediction model, the training data can be expanded and the model can be trained using the expanded training data. The processor (110) can identify a time interval during which a predetermined number of items were acquired, mask a portion of the EMR data and at least a portion of the biological signal included in the time interval, and generate expanded training data based thereon.
[0089] An exemplary structure of the training data expanded by the above-mentioned method is shown in Fig. 7b. As shown in Fig. 7b, data in which a part of the measurement values of the biological signal or a part of the measurement values of each item of the EMR data is masked and has the same form as the missing value can be used as training data for training the severity prediction model.
[0090] In this way, when data augmentation is performed on the learning data based on masking, the severity prediction model can stably generate a predicted value related to the severity even when the medical data input to the model contains many missing values. As a result, the performance of the severity prediction model can be improved by the present disclosure.
[0091] FIG. 8 is a conceptual diagram showing a method for training a severity prediction model in one embodiment of the present disclosure.
[0092] The time series data (810) including the patient's EMR data and biosignals can be input as training data to the severity prediction model (830). At this time, the input training data can be labeled with the patient's SOFA score at each time point. The severity prediction model can be in the form of a recurrent neural network suitable for processing time series data, but various forms of artificial neural network models for processing the training data of the present disclosure can be used.
[0093] The severity prediction model (830) is trained using supervised learning by comparing the patient's SOFA score prediction value (840) with label data, and as a result, the severity prediction model (830) is able to learn the characteristics of the patient's EMR data and time series data (810) including biosignals.
[0094] In the present disclosure, the severity prediction model (830) can be trained based on not only the medical data, which is the patient's EMR data and time-series data including biosignals (810), but also on information regarding whether or not the patient is suspected of infection (820). By using not only the patient's medical data but also information regarding whether or not the patient is suspected of infection, the severity prediction model (830) can learn the relationship between different types of information during the training process, and as a result, the performance of the model can be improved.
[0095] In accordance with one embodiment of the present disclosure, a computer-readable storage medium having a data structure stored thereon is disclosed.
[0096] A data structure can refer to the organization, management, and storage of data that allows efficient access and modification of the data. A data structure can refer to the organization of data to solve a specific problem (e.g., data retrieval, data storage, data modification in the shortest time). A data structure can also be defined as a physical or logical relationship between data elements designed to support a specific data processing function. A logical relationship between data elements can include a connection relationship between data elements as thought by a user. A physical relationship between data elements can include an actual relationship between data elements that is physically stored in a computer-readable storage medium (e.g., a hard disk). A data structure can specifically include a collection of data, a relationship between data, and a function or command that can be applied to the data. An effectively designed data structure allows a computing device to perform calculations while minimizing the use of computing device resources. Specifically, a computing device can increase the efficiency of operations, reading, inserting, deleting, comparing, exchanging, and searching through an effectively designed data structure.
[0097] Data structures can be classified into linear data structures and non-linear data structures according to the type of the data structure. A linear data structure can be a structure in which only one piece of data is linked after another. Linear data structures can include lists, stacks, queues, and deques. A list can refer to a series of data sets that are internally ordered. A list can include linked lists. A linked list can be a data structure in which data is linked in a manner in which each piece of data is linked in a row with a pointer. In a linked list, the pointer can contain information about the connection to the next or previous piece of data. A linked list can be expressed as a singly linked list, a doubly linked list, or a circularly linked list depending on the type of the data structure. A stack can be a data list structure that allows limited access to data. A stack can be a linear data structure in which data can be manipulated (e.g., inserted or deleted) only at one end of the data structure. Data stored in a stack can be a LIFO (Last in First Out) data structure in which the last in comes first. A queue is a data structure that allows limited access to data, and unlike a stack, it can be a FIFO (First in First out) data structure where the slowest data is stored is the slowest data is available. A deck can be a data structure that allows data to be processed on both ends of the data structure.
[0098] A nonlinear data structure may be a structure in which multiple pieces of data are concatenated after one piece of data. A nonlinear data structure may include a graph data structure. A graph data structure may be defined by vertices and edges, and the edges may include a line connecting two different vertices. A graph data structure may include a tree data structure. A tree data structure may be a data structure in which a path connecting two different vertices among multiple vertices included in a tree is one data structure. In other words, a graph data structure may be a data structure that does not form a loop.
[0099] Throughout this specification, the terms computation model, neural network, network function, and neural network can be used interchangeably. (Hereinafter, they will be uniformly described as neural network.) The data structure may include a neural network. The data structure including the neural network may be stored in a computer-readable storage medium. The data structure including the neural network may also include 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, and a loss function for training the neural network. The data structure including the neural network may include any of the components of the disclosed configurations. That is, the data structure including the neural network may include all or any combination of 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, and a loss function for training the neural network. In addition to the above configurations, the data structure including the neural network may include any other information that determines the characteristics of the neural network. Furthermore, the data structure may include all forms of data used or generated in the process of computing the neural network, and is not limited to the above. The computer-readable storage medium may include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network may be comprised of a collection of interconnected computing units, generally referred to as nodes. Such nodes may be referred to as neurons. A neural network is comprised of at least one or more nodes.
[0100] The data structure may include data to be input to the neural network. The data structure including the data to be input to the neural network may be stored in a computer-readable storage medium. The data to be input to the neural network may include training data input during the training process of the neural network and / or input data to be input to the neural network after training has been completed. The data to be input to the neural network may include data that has undergone pre-processing and / or data to be pre-processed. Pre-processing may include a data processing process for inputting data to the neural network. Thus, the data structure may include data to be pre-processed and data generated in pre-processing. The above data structures are merely examples, and the present disclosure is not limited thereto.
[0101] The data structure may include weights of the neural network. (In this specification, weights and parameters may be used interchangeably.) The data structure including the weights of the neural network may be stored in a computer-readable storage medium. The neural network may include a plurality of weights. The weights are variable and may be varied by a user or an algorithm to allow the neural network to perform a desired function. For example, when one or more input nodes are interconnected to an output node by respective links, the output node may determine an output node value based on values input to the input nodes connected to the output node and parameters set for the links corresponding to the respective input nodes. The above data structures are merely examples, and the present disclosure is not limited thereto.
[0102] By way of example and not limitation, the weights may include weights that are variable during the neural network training process and / or weights at which neural network training has been completed. The weights that are variable during the neural network training process may include weights at the start of a learning cycle and / or weights that are variable during a learning cycle. The weights at which neural network training has been completed may include weights at which a learning cycle has been completed. Thus, a data structure including weights of a neural network may include a data structure including weights that are variable during the neural network training process and / or weights at which neural network training has been completed. Thus, the above-mentioned weights and / or combinations of each weight are included in a data structure including weights of a neural network. The above-mentioned data structures are merely exemplary and the present disclosure is not limited thereto.
[0103] The data structure including the neural network weights may be stored in a computer-readable storage medium (e.g., memory, hard disk) after a serialization process. Serialization may be a process of converting a data structure into a form that can be stored in the same or another computing device and later reconstructed for use. The computing device may serialize the data structure and transmit and receive the data over a network. The serialized data structure including the neural network weights may be reconstructed in the same or another computing device through deserialization. The data structure including the neural network weights is not limited to serialization. Furthermore, the data structure including the neural network weights may include a data structure for increasing the efficiency of calculations while minimizing the use of computing device resources (e.g., nonlinear data structures such as B-Tree, Trie, m-way search tree, AVLtree, Red-Black Tree). The above is merely an example, and the present disclosure is not limited thereto.
[0104] The data structure may include hyper-parameters of the neural network. The data structure including the hyper-parameters of the neural network may be stored in a computer-readable storage medium. The hyper-parameters may be variables that are changed by a user. The hyper-parameters may include, for example, a learning rate, a cost function, a number of learning cycle iterations, weight initialization (e.g., setting a range of weights to be initialized), and the number of Hidden Units (e.g., the number of hidden layers, the number of nodes in the hidden layers). The above data structures are merely examples, and the present disclosure is not limited thereto.
[0105] FIG. 9 is a simplified general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure can be implemented.
[0106] Although the present disclosure has been described above as generally being embodied in a computing device, those skilled in the art will appreciate that the present disclosure can also be embodied in combination with computer-executable instructions and / or other program modules capable of being executed on one or more computers and / or as a combination of hardware and software.
[0107] Generally, modules herein include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Additionally, those skilled in the art will appreciate that the methods of the present disclosure can be practiced with 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 or programmable consumer electronics, etc., each of which can operate in conjunction with one or more associated devices.
[0108] The embodiments described in this disclosure may 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.
[0109] A computer includes a variety of computer-readable media. Any medium accessible by a computer can be a computer-readable medium, including volatile and non-volatile media, transitory and non-transitory media, mobile and non-mobile 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 include volatile and non-volatile media, transitory and non-transitory media, mobile and non-mobile media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, 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 medium that can be accessed by a computer and used to store information.
[0110] Computer-readable transmission media typically embodies computer-readable instructions, data structures, program modules or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and includes all information delivery media. The term modulated data signal means a signal that has one or more of its characteristics set or changed in such a manner 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 direct-wired connection, and wireless media, such as acoustic, RF, infrared and other wireless media. Any combination of any of the above media should also be included within the scope of computer-readable transmission media.
[0111] An exemplary environment (1100) for implementing various aspects of the present disclosure is shown including a computer (1102) including a processing unit (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 unit (1104). The processing unit (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 unit (1104).
[0112] The system bus (1108) can be any of several types of bus structures that can be further interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercially available bus architectures. The 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, or EEPROM, and contains the basic routines that support the exchange of information between the various components of the computer (1102), such as during start-up. The RAM (1112) can also include high-speed RAM, such as static RAM, for caching data.
[0113] The computer 1102 also includes an internal hard disk drive (HDD) 1114 (e.g., EIDE, SATA) - although the internal hard disk drive 1114 can also be configured for external use in a suitable chassis (not shown) - a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from and writing to a removable diskette 1118), and an optical disk drive 1120 (e.g., for reading from CD-ROM disks 1122 and for reading from and writing to other high capacity optical media such as DVDs). The hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 can be connected to the system bus 1108 by a hard disk drive interface 1124, a magnetic disk drive interface 1126, and an optical drive interface 1128, respectively. The interface (1124) for implementing an external drive includes, for example, at least one or both of the Universal Serial Bus (USB) and IEEE 1394 interface technologies.
[0114] These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. In the case of computer 1102, the drives and media accommodate the storage of any data in a suitable digital format. While the above 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 appreciate that other types of computer-readable storage media, such as zip drives, magnetic cassettes, flash memory cards, cartridges, and the like, can also be used in the exemplary operating environment, and further that any such media can contain computer-executable instructions for performing the methods of the present disclosure.
[0115] A number of program modules may be stored in the 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 with various commercially available operating systems or combinations of operating systems.
[0116] A user may enter 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) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, and the like. These and other input devices are often connected to the processing unit 1104 through an input device interface 1142 that is connected to the system bus 1108, but may also be connected through other interfaces, such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, and the like.
[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, computers typically include other peripheral output devices (not shown), such as speakers, printers, etc.
[0118] The computer 1102 can 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. The remote computer(s) 1148 can be a workstation, a server computer, a router, a personal computer, a handheld computer, a microprocessor-based entertainment device, a peer device or other conventional network node, and typically includes many or all of the components depicted for the computer 1102, although for simplicity, only a memory storage device 1150 is illustrated. The logical connections depicted include wired and wireless connections in a local area network (LAN) 1152 and / or larger networks, such as a wide area network (WAN) 1154. Such LAN and WAN networking environments are commonplace in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which may connect to a global computer network, such as the Internet.
[0119] When used in a LAN networking environment, the computer 1102 connects to the local network 1152 through a wired and / or wireless communication network interface or adapter 1156. The adapter 1156 can facilitate wired or wireless communication to the LAN 1152, which may also include a wireless access point installed thereon for communicating with the wireless adapter 1156. When used in a WAN networking environment, the computer 1102 can include a modem 1158 or have other means for establishing communications over the WAN 1154, such as connecting to a communications server on the WAN 1154 or through the Internet. The modem 1158, which can be internal or external and can be a wired or wireless device, connects to the system bus 1108 through the serial port interface 1142. In a networked environment, program modules described for computer 1102, or portions thereof, may be stored in a remote memory / storage device 1150. It will be readily appreciated that the network connections shown are exemplary and other means of establishing a communications link between the computers may be used.
[0120] The computer 1102 is operable to communicate with any wireless device or unit that is deployed and operates in wireless communication, such as printers, scanners, desktop and / or handheld computers, portable data assistants (PDAs), communication satellites, any equipment or location associated with a wirelessly detectable tag, and telephones. This includes at least Wi-Fi and Bluetooth wireless technologies. Thus, communication can be in a predefined structure, such as a traditional network, or simply ad hoc communication between at least two devices.
[0121] Wi-Fi (Wireless Fidelity) allows devices to connect to the Internet without being wired. Wi-Fi is a wireless technology like a cell phone that allows such devices, e.g., computers, to send and receive data indoors and outdoors, anywhere within the range of a base station. Wi-Fi networks use IEEE 802.11 (a, b, g, etc.) radio technology to provide secure, reliable, and fast wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz radio bands, e.g., at data rates of 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual bands).
[0122] Those of ordinary skill in the art will appreciate that information and signals may be represented using any of a variety of different technologies and techniques. For example, the data, instructions, commands, information, signals, bits, symbols, and chips referred to in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields, etc. or particles, optical fields, etc. or particles, or any combination thereof.
[0123] Those of ordinary skill in the art will appreciate that the various exemplary logic blocks, modules, processors, means, circuits, and algorithm steps described in the description of the embodiments disclosed herein can be implemented by electronic hardware, various forms of program or design code (for convenience, referred to herein as "software"), or a combination of all of these. To clearly illustrate such interoperability of hardware and software, the various exemplary components, blocks, modules, circuits, and steps have been generally described above with a focus on their functionality. Whether such functionality is implemented in hardware or software depends on the design constraints imposed on the particular application and the overall system. Those of ordinary skill in the art will appreciate that the described functionality can be implemented in various ways for each particular application, and such implementation decisions should not be interpreted as departing from the scope of the present disclosure.
[0124] The various embodiments disclosed herein may be implemented by 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 by 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., EEPROM, cards, sticks, key drives, etc.). Additionally, the various storage media disclosed herein may include one or more devices and / or other machine-readable media for storing information.
[0125] It should be understood that the particular order or hierarchy of the stages in the processes depicted is an example of an exemplary approach. Based on design priorities, it should be understood that the particular order or hierarchy of the stages in the processes can be rearranged within the scope of the present disclosure. The accompanying method claims provide elements of the various stages in a sample order, but are not meant to be limited to the particular order or hierarchy depicted.
[0126] The description of the illustrated embodiments is provided to enable any person of ordinary skill in the art to which the disclosure pertains to the present disclosure to utilize or practice the present disclosure. Various modifications to such embodiments will be apparent to those of ordinary skill in the art to which the disclosure pertains, and the general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not intended to be limited by the embodiments shown herein, but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.
Claims
1. 1. A method for predicting severity, executed by a computing device, comprising: acquiring electronic medical record (EMR) data of a patient and a vital sign of said patient; and generating a prediction of severity of the patient based on the EMR data of the patient and the vital signs of the patient using a severity prediction model; Including, The severity prediction model is an artificial neural network model trained using a portion of training EMR data extracted based on a time interval during which a predetermined number of items are acquired and training biological signals corresponding to the time interval. method.
2. The method according to claim 1, Further, generating a prediction value for the severity of the patient based on information regarding whether the patient is suspected of being infected; Including, method.
3. 10. The method of claim 1 , calculating at least one of information on sepsis and information on septic shock for the patient based on the predicted value of the severity of the patient; Further comprising: method.
4. 4. The method of claim 3, The method comprises: Labeling the medical data of the patient with information related to sepsis or information related to septic shock of the patient, and generating a second learning dataset based on the labeling; and training a sepsis diagnosis model, which is an artificial neural network model, based on the second training data set; Further comprising: method.
5. 5. The method of claim 4, The sepsis diagnostic model comprises: An artificial neural network model that generates a prediction value for at least one of the onset time of sepsis and the onset time of septic shock. method.
6. A method for generating learning data for predicting severity, executed by a computing device, comprising: Identifying a time interval during which a predetermined number of items were acquired from the EMR data; and generating learning data for predicting the severity based on a portion of the EMR data corresponding to the identified time period and a vital sign corresponding to the identified time period; Including, method.
7. 7. The method of claim 6, The predetermined plurality of items are a plurality of items related to prediction of a SOFA (Sequential Organ Failure Assessment) score, method.
8. 8. The method of claim 7, The step of identifying a time interval during which the predetermined number of items were acquired comprises: identifying a time period during which a predetermined number or more of the six items related to the prediction of the SOFA score were obtained; Including, each of the predetermined number or more items is acquired at at least one time point during the identified time interval; method.
9. 8. The method of claim 7, The step of identifying a time period during which the predetermined number of items were acquired comprises: identifying a time period during which all six items related to the prediction of the SOFA score were obtained; Including, Each of the six items is acquired at least one time point during the identified time interval. method.
10. 7. The method of claim 6, The step of generating learning data for predicting the severity based on a portion of the EMR data corresponding to the identified time period and a vital sign corresponding to the identified time period includes: masking a portion of the EMR data corresponding to the identified time interval and at least a portion of the biological signal corresponding to the identified time interval, and generating learning data for predicting the severity based thereon; Including, method.
11. A computer program stored on a computer readable storage medium that causes a computing device to perform operations for predicting severity, the operations including: acquiring EMR data of a patient and biosignals of said patient; and generating a prediction of severity of the patient based on the EMR data of the patient and the vital signs of the patient using a severity prediction model; Including, The severity prediction model is an artificial neural network model trained using a portion of the training EMR data extracted based on a time interval during which a predetermined number of items are acquired and a training biological signal corresponding to the time interval. A computer program stored on a computer readable storage medium.
12. 1. A computing device comprising: A processor including one or more cores; and memory; Including, The processor, acquiring EMR data of a patient and biosignals of said patient; and configured to generate a prediction of a severity of the patient based on the EMR data of the patient and the vital signs of the patient using a severity prediction model; The severity prediction model is an artificial neural network model trained using a portion of the training EMR data extracted based on a time interval during which a predetermined number of items are acquired and a training biological signal corresponding to the time interval. Computing device.
