Method of providing differential diagnosis information based on pet data

Abstract

A method for providing differential diagnosis information based on pet data is disclosed according to one embodiment of the present disclosure. The method may include the steps of receiving pet data, selecting one or more valid neural networks among a plurality of neural networks for providing diagnosis information based on the pet data, and inputting the pet data into the valid neural network to obtain a list containing a plurality of differential diagnosis information for the pet.

Description

Technology Field

[0001] The present disclosure relates to a method for providing differential diagnosis information based on pet data, and more specifically, to a method for providing differential diagnosis information by selecting one or more effective neural networks among a plurality of neural networks for providing diagnosis information based on said pet data. Background Technology

[0002] Currently, large-scale language AI models are available in various versions. While accuracy improves as the number of parameters increases, these models also have drawbacks due to their nature, such as hallucinations and the consumption of excessive computing resources. In particular, if misdiagnosis occurs in humans or animals due to hallucinations, it not only undermines trust in the diagnostic model but can also endanger lives; therefore, ensuring the reliability of the diagnostic model is essential. Prior art literature

[0003] Republic of Korea Published Patent Application No. 10-2021-0158272 (2021.11.17) Republic of Korea Published Patent Application No. 10-2018-0057300 (2018.05.30) The problem to be solved

[0004] The present disclosure is conceived in response to the aforementioned background technology and aims to provide a method for providing differential diagnosis information based on the said pet data.

[0005] The technical problems of the present disclosure are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0006] According to one embodiment of the present disclosure for solving the problem described above, a method for providing differential diagnosis information based on patient data is disclosed. The method may include: receiving patient data; selecting one or more valid neural networks among a plurality of neural networks for providing diagnosis information based on the patient data; and inputting the patient data into the valid neural network to obtain a list including a plurality of differential diagnosis information for the patient.

[0007] In one embodiment, the pet data may include at least one of the patient's profile data, the patient's consultation data, the patient's treatment history data, or the patient's health measurement information.

[0008] In one embodiment, the differential diagnosis information may be information provided to medical personnel who have performed consultation or treatment on the patient.

[0009] In one embodiment, the step of selecting one or more valid neural networks among a plurality of neural networks for providing diagnostic information based on the pet data may include the step of classifying valid neural networks suitable for the pet data based on criteria set based on medical knowledge.

[0010] In one embodiment, the step of selecting one or more valid neural networks among a plurality of neural networks for providing diagnostic information based on the pet data includes the step of inputting the pet data into a neural network classification model to calculate the degree of fit between the neural networks constituting the plurality of neural networks for providing diagnostic information, and the neural network classification model may include an artificial neural network model trained in medical knowledge.

[0011] In one embodiment, the step of inputting the pet data into the valid neural network may include the step of selecting a portion of the pet data based on the valid neural network; and the step of inputting the pet data into the valid neural network.

[0012] In one embodiment, the plurality of neural networks for providing diagnostic information may include at least two neural networks for diagnosing anatomy, physiology, cardiology, oncology, neurology, endocrinology, gastroenterology, respiratory medicine, dermatology, ophthalmology, obstetrics, orthopedics, animal behavior, microbiology, parasitology, animal nutrition, infectious diseases, nephrology, emergency medicine, radiology, pathology, dentistry, zoonotic diseases, or genetics.

[0013] In one embodiment, a list containing multiple differential diagnosis information for the patient may be information that further includes additional testing methods capable of supporting or excluding the multiple differential diagnoses included in the list.

[0014] In one embodiment, a list containing multiple differential diagnosis information for the patient may be information that further includes grounds for the multiple differential diagnoses included in the list.

[0015] According to another embodiment of the present disclosure for solving the problem described above, a computer program stored on a computer-readable storage medium may be provided. When the program is executed by one or more processors, the one or more processors perform operations to provide differential diagnosis information based on pet data, and the operations may include: an operation of receiving pet data; an operation of selecting one or more valid neural networks among a plurality of neural networks for providing diagnostic information based on the pet data; and an operation of inputting the pet data into the valid neural network to obtain a list containing a plurality of differential diagnosis information for the patient.

[0016] According to another embodiment of the present disclosure for solving the problem described above, a computing device for providing differential diagnosis information based on pet data may be provided. The device comprises at least one processor; and a memory; wherein the at least one processor may be configured to receive pet data and, based on the pet data, select one or more valid neural networks among a plurality of neural networks for providing diagnostic information; and input the pet data into the valid neural network to obtain a list containing a plurality of differential diagnosis information for the patient.

[0017] The technical solutions obtainable in this disclosure are not limited to the solutions mentioned above, and other solutions not mentioned will be clearly understood by those skilled in the art to which this disclosure belongs from the description below. Effects of the invention

[0018] A method for providing differential diagnosis information according to one embodiment of the present disclosure can provide highly accurate differential diagnosis information even with limited computing resources.

[0019] The effects obtainable from the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure belongs from the description below. Brief explanation of the drawing

[0020] FIG. 1 is a drawing for illustrating an example of a medical diagnostic system based on a medical diagnostic server and an external server, in which various aspects of the present disclosure can be implemented. FIG. 2 is a schematic diagram showing a network function according to one embodiment of the present disclosure. FIG. 3 is a flowchart illustrating an example of a method for providing patient diagnostic information based on patient data according to one embodiment of the present disclosure. FIG. 4 is a drawing for illustrating an example of a method for collecting patient data according to one embodiment of the present disclosure. FIG. 5 is a diagram illustrating a rule-based neural network classification model for selecting an effective neural network according to one embodiment of the present disclosure. FIG. 6 is a diagram illustrating a method for performing additional examinations and differential diagnoses based on a plurality of differential diagnosis information obtained according to one embodiment of the present disclosure. FIG. 7 is a flowchart illustrating an example of a method for providing pet diagnostic information based on pet data according to one embodiment of the present disclosure. FIG. 8 illustrates a brief and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented. Specific details for implementing the invention

[0021] Various embodiments and / or aspects are now disclosed with reference to the drawings. For illustrative purposes, numerous specific details are disclosed in the following description to aid in a general understanding of one or more aspects. However, it will be apparent to those skilled in the art that these aspects may be practiced without such specific details. The following description and the accompanying drawings describe specific exemplary aspects of one or more aspects in detail. However, these aspects are exemplary, and some of the various methods in the principles of the various aspects may be used, and the descriptions are intended to include all such aspects and their equivalents. Specifically, terms such as “exemplary,” “example,” “aspect,” and “example” as used herein may not be interpreted as implying that any described aspect or design is superior or advantageous over other aspects or designs.

[0022] In addition, various aspects and features will be presented by a system that may include one or more devices, terminals, servers, devices, components and / or modules, etc. It should also be understood and recognized that various systems may include additional devices, terminals, servers, devices, components and / or modules, etc., and / or may not include all of the devices, terminals, servers, devices, components, modules, etc. discussed in relation to the drawings.

[0023] As used herein, terms such as “computer program,” “component,” “module,” “system,” etc., may be used interchangeably and refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or executions of software. For example, a component may be, but is not limited to, a procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer. For example, both an application executed on a computing device and the computing device itself may be components. One or more components may reside within a processor and / or an execution thread. A component may be localized within a single computer. A component may be distributed among two or more computers.

[0024] Additionally, these components may be executed from various computer-readable media having various data structures stored therein. The components may communicate through local and / or remote processing, for example, according to a signal having one or more data packets (e.g., data from one component interacting with another component in a local or distributed system, and / or data transmitted through a network such as the Internet to another system via a signal).

[0025] Hereinafter, identical or similar components are assigned the same reference numeral regardless of drawing symbols, and redundant descriptions thereof are omitted. Furthermore, in describing the embodiments disclosed in this specification, detailed descriptions of related prior art are omitted if it is determined that such detailed descriptions may obscure the essence of the embodiments disclosed in this specification. Additionally, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification, and the technical concept disclosed in this specification is not limited by the attached drawings.

[0026] The terms used herein are for describing the embodiments and are not intended to limit the disclosure. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. As used herein, "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components in addition to the components mentioned.

[0027] Although terms such as "first," "second," etc. are used to describe various elements or components, it goes without saying that these elements or components are not limited by these terms. These terms are used merely to distinguish one element or component from another. Therefore, it goes without saying that the first element or component mentioned below may be the second element or component within the technical scope of this disclosure.

[0028] Unless otherwise defined, all terms used in this specification (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which this disclosure pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0029] Furthermore, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any 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 enumerated related items.

[0030] In addition, the terms "information" and "data" as used in this specification may often be used interchangeably.

[0031] The suffixes “module” and “part” for components used in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not inherently possess distinct meanings or roles.

[0032] The purpose and effects of the present disclosure, and the technical configurations for achieving them, will become clear by referring to the embodiments described in detail below in conjunction with the accompanying drawings. In describing the present disclosure, if it is determined that a detailed description of known functions or configurations might unnecessarily obscure the essence of the present disclosure, such detailed description will be omitted. Furthermore, the terms described below are defined considering their functions in the present disclosure, and these may vary depending on the intentions or practices of the user or operator.

[0033] However, the present disclosure is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to make the present disclosure complete and to fully inform those skilled in the art of the scope of the disclosure, and the present disclosure is defined only by the scope of the claims. Therefore, such definitions should be based on the content throughout this specification.

[0034] The scope of rights for the steps in the claims of this disclosure is determined by the functions and features described in each step, and is not affected by the order in which the steps are described in the claims unless the order of precedence is specified in each step. The order between the steps may be changed. Additionally, at least one of the steps may be omitted, and other steps may be performed additionally. For example, in a claim describing steps including Step A and Step B, even if Step A is described before Step B, the scope of rights is not limited to the requirement that Step A must precede Step B.

[0035] FIG. 1 is a drawing for illustrating an example of a medical diagnostic system based on a medical diagnostic server and an external server, in which various aspects of the present disclosure can be implemented.

[0036] Referring to FIG. 1, a method for providing information for medical diagnosis according to one embodiment of the present disclosure may be performed by a computing device (100), a user terminal (200), and an external server (300). However, the components described above are not essential for providing the information, so the medical diagnosis system may be performed by more or fewer components than those listed above.

[0037] A computing device (100) according to one embodiment of the present disclosure may include a medical diagnosis server that derives a medical diagnosis or a plurality of potential diagnoses for said patient based on patient data. For example, the computing device (100) may be a server that provides an application that provides diagnosis information to a user terminal (200). As another example, the computing device may provide diagnosis information in API format to an external medical information server, such as a hospital. However, it is not limited thereto.

[0038] The computing device (100) may include any type of computer system or computer device, such as, for example, a microprocessor, a mainframe computer, a digital processor, a portable device, and a device controller. However, it is not limited thereto.

[0039] According to one embodiment of the present disclosure, a computing device (100) may include a processor (110), a communication unit (120), and a memory (130). However, the above-described components are not essential for implementing the computing device (100), so the computing device (100) may have more or fewer components than those listed above. Here, each component may be composed of a separate chip, module, or device, or may be included within a single device.

[0040] The processor (110) of the computing device (100) can typically control the overall operation of the computing device (100). The processor (110) can provide or process appropriate information or functions to the user by processing signals, data, information, etc. that are input or output through the components of the computing device (100) or by running an application program stored in memory (130).

[0041] The processor (110) may be composed of one or more cores and may include processors for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. The processor (110) may read a computer program stored in memory (130) and perform data processing for machine learning according to one embodiment of the present disclosure. According to one embodiment of the present disclosure, the processor (110) may perform operations for learning a neural network. The processor (110) may perform calculations for learning a neural network, 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. At least one of the CPU, GPGPU, and TPU of the processor (110) may process the learning of a network function. For example, a CPU and a GPGPU can work together to process the learning of a network function and data classification using the network function. Additionally, in one embodiment of the present disclosure, processors of a plurality of computing devices can be used together to process the learning of a network function and data classification using the network function. Furthermore, a computer program executed on a computing device according to one embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

[0042] Additionally, the processor (110) can control at least some of the components of the computing device (100) to run an application stored in memory (130). Furthermore, the processor (110) can operate at least two or more of the components included in the computing device (100) in combination with each other to run the application.

[0043] The communication unit (120) of the computing device (100) may include one or more modules that enable communication between the computing device (100) and a user terminal (200) or between the computing device (100) and an external server (300). Additionally, the communication unit (120) may include one or more modules that connect the computing device (100) to one or more networks.

[0044] The memory (130) of the computing device (100) stores data that supports various functions of the computing device (100). The memory (130) can store a number of application programs (or applications) running on the computing device (100), data for the operation of the computing device (100), and instructions. At least some of these application programs may be downloaded from an external server via wireless communication. Additionally, at least some of these application programs may exist on the computing device (100) from the time of shipment for the basic functions of the computing device (100). Meanwhile, the application programs may be stored in the memory (130), installed on the computing device (100), and driven by the processor (110) to perform the operation (or function) of the computing device (100).

[0045] A network unit (150) according to one embodiment of the present disclosure can use various wired communication systems such as a public switched telephone network (PSTN), xDSL (x Digital Subscriber Line), RADSL (Rate Adaptive DSL), MDSL (Multi Rate DSL), VDSL (Very High Speed ​​DSL), UADSL (Universal Asymmetric DSL), HDSL (High Bit Rate DSL), and a local area network (LAN).

[0046] In addition, the network unit (150) presented in this specification may 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.

[0047] In the present disclosure, the network unit (150) can be configured regardless of the communication mode, such as wired and wireless, and can be configured as various communication networks such as a Local Area Network (LAN), a Personal Area Network (PAN), and a Wide Area Network (WAN). In addition, the network may be a known World Wide Web (WWW) and may utilize wireless transmission technology used for short-range communication, such as Infrared Data Association (IrDA) or Bluetooth.

[0048] The technologies described in this specification can be used not only in the networks mentioned above but also in other networks.

[0049] In the present disclosure, the user terminal (200) may include, for example, a mobile phone, a smartphone, a laptop computer, a PDA (personal digital assistant), a slate PC, a tablet PC, etc. However, it is not limited thereto.

[0050] According to one embodiment of the present disclosure, a user terminal (200) may include a processor, a communication unit, and a memory. However, since the above-described components are not essential for implementing the user terminal (200), the user terminal (200) may have more or fewer components than those listed above. Here, each component may be composed of a separate chip, module, or device, or may be included within a single device.

[0051] The processor of the user terminal (200) can typically control the overall operation of the user terminal (200). The processor can provide or process appropriate information or functions to the user by processing signals, data, information, etc. that are input or output through the components of the user terminal (200) or by running an application program stored in memory.

[0052] Additionally, the processor can control at least some of the components of the user terminal (200) to run an application stored in memory. Furthermore, the processor can operate at least two or more of the components included in the user terminal (200) in combination with each other to run the application.

[0053] According to one embodiment of the present disclosure, a processor (110) of a computing device (100) can transmit a diagnosis result or a provisional diagnosis result to a medical professional. Specifically, the diagnosis result or provisional diagnosis result can be transmitted through a medical data server or directly to a transmission or medical terminal possessed by the medical professional.

[0054] According to one embodiment of the present disclosure, a computing device (100) may receive patient data from a medical data server through the network unit (150). Meanwhile, the user terminal (200) may be a terminal of a patient or a guardian, but is not limited thereto. The communication unit of the user terminal (200) may include one or more modules that enable communication between the user terminal (200) and the computing device (100) or between the user terminal (200) and an external server (300). Additionally, the communication unit may include one or more modules that connect the user terminal (200) to one or more networks.

[0055] The memory of the user terminal (200) stores data that supports various functions of the user terminal (200). The memory can store a number of application programs (or applications) running on the user terminal (200), data for the operation of the user terminal (200), and commands, and can be connected to additional sensors that collect patient data. At least some of these application programs can be downloaded from an external server via wireless communication. In addition, at least some of these application programs may exist on the user terminal (200) from the time of shipment for the basic functions of the user terminal (200). Meanwhile, the application programs can be stored in memory, installed on the user terminal (200), and driven by a processor to perform the operation (or function) of the user terminal (200).

[0056] FIG. 2 is a schematic diagram showing a network function according to one embodiment of the present disclosure.

[0057] Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. A neural network may consist of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node. The nodes (or neurons) constituting the neural networks may be interconnected by one or more links.

[0058] In a neural network, one or more nodes connected via links can form relative input and output node relationships. The concepts of input and output nodes are relative; any node in an output node relationship with respect to one node may be in an input node relationship with respect to another node, and vice versa. As described above, the input node versus output node relationship can be generated based on links. One or more output nodes may be connected to a single input node via links, and vice versa.

[0059] In a relationship between an input node and an output node connected through a single link, the value of the output node's data can be determined based on the data input to the input node. Here, the link interconnecting the input node and the output node may have a weight. The weight can be variable and can be varied by the user or an algorithm to enable the neural network to perform the desired function. For example, if one or more input nodes are interconnected to a single output node by respective links, the output node's value can be determined based on the values ​​input to the input nodes connected to the output node and the weights set on the links corresponding to each input node.

[0060] As described above, a neural network consists of one or more nodes interconnected through one or more links, forming input-output node relationships within the network. The characteristics of a neural network can be determined by the number of nodes and links within the network, the relationships between the nodes and links, and the weight values ​​assigned to each link. For example, if two neural networks exist with the same number of nodes and links but different weight values ​​for the links, the two neural networks may be recognized as different from each other.

[0061] A neural network can be composed of a set of one or more nodes. A subset of nodes constituting a neural network can form a layer. Some of the nodes constituting a neural network can form a layer based on their distances from an initial input node. For example, a set of nodes with a distance of n from an initial input node can form n layers. The distance from the initial input node can be defined by the minimum number of links that must be traversed to reach that node from the initial input node. However, this definition of a layer is arbitrary for illustrative purposes, and the degree of a layer within a neural network can be defined in a way different from that described above. For example, a layer of nodes may be defined by its distance from a final output node.

[0062] Initial input nodes may refer to one or more nodes within a neural network to which data is directly input without passing through links in their relationships with other nodes. Alternatively, in terms of link-based relationships between nodes within the neural network, they may refer to nodes that do not have other input nodes connected by links. Similarly, final output nodes may refer to one or more nodes within a neural network that do not have output nodes in their relationships with other nodes. Furthermore, hidden nodes may refer to nodes constituting the neural network that are neither initial input nodes nor final output nodes.

[0063] A neural network according to one embodiment of the present disclosure may have the number of nodes in the input layer equal to the number of nodes in the output layer, and may be a neural network in which the number of nodes decreases and then increases again as it progresses from the input layer to the hidden layer. Additionally, a neural network according to another embodiment of the present disclosure may have the number of nodes in the input layer less than the number of nodes in the output layer, and may be a neural network in which the number of nodes decreases as it progresses from the input layer to the hidden layer. Additionally, a neural network according to yet another embodiment of the present disclosure may have the number of nodes in the input layer greater than the number of nodes in the output layer, and may be a neural network in which the number of nodes increases as it progresses from the input layer to the hidden layer. A neural network according to yet another embodiment of the present disclosure may be a neural network in which the above-described neural networks are combined.

[0064] A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to input and output layers. Using a deep neural network allows for the identification of latent structures in data. That is, it is possible to identify the latent structures of photos, text, videos, voice, and music (e.g., what objects are present in a photo, what the content and emotions of a text are, what the content and emotions of a voice are, etc.). Deep neural networks may include convolutional neural networks (CNN), recurrent neural networks (RNN), autoencoders, Generative Adversarial Networks (GAN), restricted Boltzmann machines (RBM), deep belief networks (DBN), Q networks, U networks, Siamese networks, Generative Adversarial Networks (GAN), etc. The description of deep neural networks described above is merely illustrative and the present disclosure is not limited thereto.

[0065] 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 the input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be placed between the 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 a bottleneck layer (encoding), and then expanded symmetrically from the bottleneck layer to the output layer (symmetrically with respect to the input layer). The autoencoder may perform non-linear dimensionality reduction. The number of input and output layers may correspond to the dimension after preprocessing of the input data. In the autoencoder structure, the number of nodes in the hidden layer included in the encoder may have a structure in which the number of nodes decreases as it moves away from the input layer. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, 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).

[0066] Neural networks can be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. The training of a neural network may be the process of applying knowledge to the neural network to perform a specific action.

[0067] Neural networks can be trained to minimize the error in their output. The training process involves repeatedly inputting training data into the network, calculating the error between the network's output and the target for the training data, and updating the weights of each node by backpropagating the error from the output layer to the input layer in a direction that reduces the error. In supervised learning, training data is used where the correct answer is labeled for each data point (i.e., labeled training data), whereas in unsupervised learning, the correct answer may not be labeled for each training data point. For instance, in the case of supervised learning for data classification, the training data may consist of data where each training point is labeled with a category. The labeled training data is input into the neural network, and the error can be calculated by comparing the network's output (category) with the labels 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 neural network's output. The calculated error is backpropagated in the neural network (i.e., from the output layer to the input layer), and through backpropagation, the connection weights of each node in each layer of the neural network can be updated. The amount of change in the connection weights of each node being updated can be determined by the learning rate. The neural network's calculation of the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle. For example, a high learning rate can be used in the early stages of training to quickly achieve a certain level of performance and increase efficiency, while a low learning rate can be used in the later stages to improve accuracy.

[0068] In the training of neural networks, the training data is generally a subset of the real-world data (i.e., the data intended to be processed by the trained neural network). Consequently, a training cycle may exist where errors decrease on the training data but increase on the real-world data. Overfitting is a phenomenon where the network learns excessively on the training data, leading to increased errors on the real-world data. For example, a neural network trained on yellow cats might fail to recognize cats when seeing anything other than yellow, which can be considered a form of overfitting. Overfitting can act as a cause for increased errors in machine learning algorithms. Various optimization methods can be used to prevent this overfitting. To prevent overfitting, methods such as increasing the training data, regularization, dropout (which disables some nodes in the network during training), and the use of batch normalization layers can be applied.

[0069] According to one embodiment of the present disclosure, a computer-readable medium storing a data structure is disclosed.

[0070] Data structure can refer to the organization, management, and storage of data that enables efficient access and modification. Data structure can also refer to the organization of data to solve specific problems (e.g., data retrieval, data storage, data modification in the shortest possible time). Data structure may also be defined by the physical or logical relationships between data elements designed to support specific data processing functions. The logical relationships between data elements are User Defined It may include the relationships between data elements. The physical relationships between data elements are computer-readable storage media (e.g., Permanent storage deviceIt may include actual relationships between data elements physically stored in ). Specifically, a data structure may include a set of data, relationships between data, and functions or instructions that can be applied to the data. Through an effectively designed data structure, a computing device can perform operations while using the computing device's resources minimally. Specifically, through an effectively designed data structure, a computing device can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and searching.

[0071] Data structures can be classified into linear and non-linear data structures based on their form. A linear data structure is one where only one piece of data is connected to the next. Linear data structures can include lists, stacks, queues, and deques. A list can refer to a set of data that maintains an internal order. Lists can include linked lists. A linked list is a data structure where data is connected in a line, with each piece of data possessing a pointer. In a linked list, the pointer can contain information regarding the connection to the next or previous data. Depending on its form, a linked list can be represented as a singly linked list, a doubly linked list, or a circular linked list. A stack is a data arrangement structure that allows for restricted access to data. A stack can be a linear data structure where data can be processed (e.g., insertion or deletion) only at one end. Data stored in a stack can be a Last-In, First-Out (LIFO) data structure, meaning that the later an item is entered, the sooner it is retrieved. A queue is a data sequence structure that allows for limited access to data; unlike a stack, it can be a FIFO (First in First Out) data structure where data stored later is retrieved later. A deque is a data structure that can process data at both ends.

[0072] Non-linear data structures can be structures where multiple data are connected after a single piece of data. Non-linear data structures may include graph data structures. A graph data structure can be defined by vertices and edges, and an edge may include a line connecting two different vertices. Graph data structures may include tree data structures. A tree data structure may be a data structure where there is only one path connecting two different vertices among the multiple vertices included in the tree. In other words, it may be a data structure that does not form a loop in a graph data structure.

[0073] Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, the term neural network will be used consistently. A data structure may include a neural network. Furthermore, a data structure including a neural network may be stored on a computer-readable medium. A data structure including a neural network may also include data preprocessed for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. A data structure including a neural network may include any of the components disclosed above. That is, a data structure including a neural network may be configured to include all or any combination thereof, such as data preprocessed for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, and loss functions for learning the neural network. In addition to the configurations described above, a data structure including a neural network may include any other information that determines the characteristics of the neural network. Furthermore, the data structure may include any form of data used or generated during the computational process of the neural network, and is not limited to the foregoing. A computer-readable medium may include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network may be composed of a set of interconnected computational units that may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node.

[0074] A data structure may include data input to a neural network. A data structure including data input to a neural network may be stored on a computer-readable medium. Data input to a neural network may include training data input during the neural network learning process and / or input data input to a neural network after training is complete. Data input to a neural network may include pre-processed data and / or data subject to pre-processing. Pre-processing may include a data processing process for inputting data into a neural network. Accordingly, a data structure may include data subject to pre-processing and data generated by pre-processing. The aforementioned data structure is merely an example, and the present disclosure is not limited thereto.

[0075] 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 on a computer-readable medium. The neural network may include multiple weights. The weights may be variable and may be varied by a user or an algorithm to enable the neural network to perform a desired function. For example, if one or more input nodes are interconnected to a single output node by respective links, the output node may determine the data value output from the output node based on values ​​input to the input nodes connected to the output node and weights set on the links corresponding to each input node. The aforementioned data structure is merely an example and the present disclosure is not limited thereto.

[0076] As an example rather than a limitation, weights may include weights that vary during the neural network learning process and / or weights for which neural network learning is completed. Weights that vary during the neural network learning process may include weights at the start of the learning cycle and / or weights that vary during the learning cycle. Weights for which neural network learning is completed may include weights for which the learning cycle is completed. Accordingly, a data structure containing the weights of a neural network may include a data structure containing weights that vary during the neural network learning process and / or weights for which neural network learning is completed. Therefore, the weights and / or combinations of each weight described above are included in the data structure containing the weights of a neural network. The aforementioned data structure is merely an example and the present disclosure is not limited thereto.

[0077] Data structures containing the weights of a neural network may be stored on a computer-readable storage medium (e.g., memory, hard disk) after undergoing a serialization process. Serialization may be a process of converting a data structure into a form that can be stored on the same or different computing devices and later reconstructed for use. A computing device may serialize the data structure to transmit and receive data over a network. A serialized data structure containing the weights of a neural network may be reconstructed on the same or different computing devices through deserialization. Data structures containing the weights of a neural network are not limited to serialization. Furthermore, data structures containing the weights of a neural network may include data structures designed to increase computational efficiency while minimizing the use of computing device resources (e.g., B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree in non-linear data structures). The foregoing is merely an example and the present disclosure is not limited thereto.

[0078] The data structure may include hyperparameters of the neural network. The data structure including the neural network hyperparameters may be stored on a computer-readable medium. The hyperparameters may be variables that are varied by the user. The hyperparameters may include, for example, a learning rate, a cost function, the number of learning cycle iterations, weight initialization (e.g., setting the range of weight values ​​subject to weight initialization), and the number of hidden units (e.g., the number of hidden layers, the number of nodes in the hidden layers). The aforementioned data structure is merely an example, and the present disclosure is not limited thereto.

[0079] FIG. 3 is a flowchart illustrating an example of a method for providing patient diagnostic information based on patient data according to one embodiment of the present disclosure.

[0080] Referring to FIG. 3, the computing device (100) may include the step of receiving the patient data (S100), the step of receiving the patient data and selecting one or more valid neural networks among a plurality of neural networks for providing diagnostic information (S200), and the step of inputting the patient data into the valid neural network to obtain a list (S300) containing a plurality of differential diagnostic information for the patient.

[0081] In the above step S100, the patient data may include at least one of the patient's profile data, the patient's treatment history data, the patient's health measurement information, or the patient's counseling data. For example, the patient's profile data may include at least one of the patient's gender, occupation, age, residence, or cohabiting family. Additionally, the patient's treatment history data may include clinical records, imaging data, genetic data, electronic medical records (EMR), etc. Additionally, the patient's health measurement information may be data collected by a portable biosignal measuring device, such as a heart rate monitor or a blood glucose meter. The types and processing steps of the patient data are described later in FIGS. 4 and FIGS. 5.

[0082] In the above S200 step, the valid neural network may be determined by a neural network classification model that receives the patient data as input. The neural network classification model may include a rule-based classifier that classifies the patient data according to a certain algorithm. The step of the neural network classification model determining the valid neural network based on the patient data is described later in FIG. 5.

[0083] In the above S300 step, the list containing the plurality of differential diagnosis information can provide information for medical staff (medical staff, medical institution) to quickly perform a final diagnosis or to create a differential diagnosis list as an intermediate step to reach a final diagnosis. In order for the medical staff to perform a final diagnosis, the list information may further include grounds that can support the list information, which will be described later in FIG. 6.

[0084] FIG. 4 is a drawing for illustrating an example of a method for collecting patient data according to one embodiment of the present disclosure.

[0085] Referring to FIG. 4, the patient data (420) may include data derived from the patient's profile data (411), the patient's medical record (412), or biosensor data (413).

[0086] The patient's profile data (411) may include at least one of the patient's gender, occupation, age, residence, or cohabiting family. Through the patient's profile data (411), information regarding epidemiology, such as demographic characteristics or environmental factors that are difficult to identify in other data among the patient data (420), can be verified.

[0087] The patient medical record (412) may include a comprehensive patient history, diagnostic records, treatment plans, medication lists, allergies, vaccination dates, imaging data, laboratory and test results, vital signs, and personal statistics such as age and weight. The imaging data may include images such as X-rays, MRI scans, CT scans, ultrasound images, lesion images, and tissue slides that provide visual insight into the patient's condition, in addition to images of lesions. Genetic data is information about the patient's genetic makeup, which may be important for understanding genetic diseases or finding personalized medicine approaches. Laboratory test results may be data from blood tests, urine tests, biopsies, and other laboratory tests that provide important insights into the patient's health status. Clinical notes may include findings observed by doctors, nurses, and other healthcare providers interacting with the patient, as well as hypotheses and details regarding the patient's diagnosis. The patient medical record (412) may be in electronic form, but may include images taken or scanned in analog form.

[0088] The above biosensor data (413) can be very useful for inputting into an artificial neural network (ANN) for differential diagnosis (DDx) when collecting patient data using devices such as a thermometer, continuous glucose monitoring (CGM), electrocardiogram (ECG), electromyogram, or pulse oximeter. These devices can provide continuous real-time data that can reveal patterns and trends that are not evident in in-hospital vital measurements.

[0089] In order to load the patient's profile data (411), the patient's medical record (412), or the biosensor data (413) possessed by the patient into the patient data (420), several steps such as data collection, data organization, and data conversion may be required. As a result, the patient data (420) may have a format suitable for input into an artificial neural network.

[0090] During the data collection process, consent is obtained from the patient, and if necessary, pseudonymization may be required at this stage. The data cleaning stage may include error correction, filling in missing values, and removing irrelevant data. For example, if the patient's age is missing or unrealistic, such as 250 years old, it may be corrected or estimated based on other information. In the data transformation stage, the data may be converted into a format that can be easily analyzed by an artificial neural network. Additionally, for continuous data such as age, normalization, standardization, or encoding may be performed so that the values ​​are of a similar scale. For example, age may be normalized to a range between 0 and 1, and categorical data such as gender, occupation, and place of residence may be converted into a numerical format using techniques such as one-hot encoding or label encoding. If the data in the medical record is in text format, natural language processing techniques may be required to convert it into a numerical format suitable for artificial neural network analysis. Furthermore, the computing device (100) may perform data processing on the text data, such as at least one of data cleaning, tokenization, normalization, removal of unusables, vectorization, feature extraction, or categorical data encoding.

[0091] The collected patient data (420) can be input into a neural network classification model (430) for selecting a valid neural network (441). The valid neural network (441) may be any one of a plurality of neural networks (440) for providing diagnostic information or a plurality of artificial neural networks. The neural network classification model (430) may classify the valid neural network (441) based on medical knowledge. The medical knowledge must be based on authoritative medical information sources. These sources can verify that the diagnostic suggestions of the artificial neural network are reliable, up-to-date, and consistent with current medical standards and practices. These sources may include peer-reviewed medical journals, clinical practice guidelines, medical textbooks, drug databases, expert consensus, medical institution protocols, and / or health organizations such as governments or the WHO.

[0092] For example, peer-reviewed medical journals such as The New England Journal of Medicine, The Lancet, and JAMA (Journal of the American Medical Association) are widely respected for their rigorous review processes and are considered authoritative in the field of medicine. Guidelines provided by the American Medical Association, the World Health Organization, national medical associations, or reputable medical institutions offer comprehensive guidance based on the latest research and can cover various aspects of diagnosing and treating diverse medical conditions. Standard medical textbooks widely used in medical education, such as Harrison's Principles of Internal Medicine and Cecil's Essentials of Medicine, provide foundational knowledge and are frequently referenced for diagnostic criteria and treatment options. Data contained in comprehensive and regularly updated databases of drugs or clinical trials, such as Physicians' Desk Reference or Lexicomp, can provide detailed information about drugs, including indications, contraindications, interactions, and side effects, which are essential for accurate diagnosis and treatment planning. Information from government or global health organizations, such as the Centers for Disease Control and Prevention (CDC), the National Institutes of Health (NIH), or the World Health Organization (WHO), is considered authoritative, particularly regarding public health diagnoses and guidelines.

[0093] The aforementioned medical knowledge may be veterinary knowledge. Peer-reviewed journals such as the Journal of the American Veterinary Medical Association, Veterinary Record, and Journal of Veterinary Internal Medicine publish research studies, reviews, and case reports that are important for evidence-based veterinary practice. Guidelines issued by veterinary associations, such as the American Veterinary Medical Association (AVMA), or international organizations, such as the World Small Animal Veterinary Association (WSAVA), provide detailed instructions for diagnosing and treating various animal health conditions. Core veterinary textbooks, such as Ettinger and Feldman's *Veterinary Internal Medicine* and the *Merck Veterinary Manual*, can provide comprehensive information on various animal diseases and treatments. Veterinary prescription books, such as Plumb's Veterinary Drugs, can provide detailed information on drugs used in animals, including dosages, indications, contraindications, and side effects. In addition, it may include information from government agencies or international organizations responsible for animal health, such as the U.S. Department of Agriculture (USDA), the Animal and Plant Health Authority (APHA) of the United Kingdom, the Animal and Plant Quarantine Agency of Korea, or the World Organisation for Animal Health (OIE).

[0094] Meanwhile, the neural network classification model (430) may include a rule-based classifier and may be in the form of an artificial neural network. Here, the rule may be a conditional statement set based on the medical knowledge. In this case, the neural network classification model (430) may classify a valid neural network (441) suitable for the patient data (420) based on a pre-set criterion, and the specific operation method is described later in FIG. 5.

[0095] If the above neural network classification model (430) includes an artificial neural network, the artificial neural network can learn medical knowledge and determine an effective neural network (441) by checking the suitability between the patient data (420) and the artificial neural networks included in the plurality of neural networks for providing diagnostic information (440). For example, the above neural network classification model (430) can select an effective neural network (441) among the plurality of neural networks for providing diagnostic information (440) according to the main characteristics of the data, such as the type, dimension, volume, variance, and noise of the patient data (420).

[0096] As another example, the neural network classification model (430) can determine valid neural networks (441) based on the content of the patient data (420). For example, the computing device (100) can utilize natural language processing (NLP) technology to understand the meaning, context, and nuances of text data or voice data. Alternatively, the computing device (100) can identify whether the content constituting the data is text, numbers, image-based, etc., and can determine the type of data, such as structured data, unstructured text, or time-series format. Additionally, classification, prediction, generation, etc., to identify the intent and purpose of the patient data (420) can be verified. Furthermore, the complexity of the data can be evaluated, including the level of abstraction, ambiguity, subtlety, or nuances, and a larger number of valid neural networks (441) can be selected when the complexity is high compared to when the complexity is low. As a result, when the complexity is high, diagnosis can be performed from a more diverse perspective, and computing resources for providing diagnostic information can be saved when the symptoms are simple.

[0097] Here, the plurality of neural networks (440) for providing diagnostic information may include neural networks specialized in multiple different fields. For example, the plurality of neural networks for providing diagnostic information may include at least two artificial neural networks for diagnosing cardiology, oncology, neurology, endocrinology, gastroenterology, respiratory medicine, dermatology, ophthalmology, obstetrics, pediatrics, rheumatology, orthopedics, psychiatry, infectious diseases, nephrology, geriatrics, emergency medicine, radiology, pathology, or genetics. In this case, each artificial neural network can not only increase accuracy for each specialized field but also collect the types of data required for each artificial neural network, thereby reducing the overall computing resources required for data preprocessing, learning, and inference, and allowing the system to be effectively scaled to accommodate various data sizes and complexities. Additionally, the artificial neural networks may be modularized so that parts of the artificial neural networks can be replaced or added. In addition, it can be used to evaluate and improve the neural network classification model (430) by providing insight into why a specific network was selected for a specific data type.

[0098] For example, an artificial neural network specialized in endocrinology can be specialized in diagnosing and distinguishing various types of diabetes, insulin resistance states, and other metabolic disorders by receiving data on blood glucose variability, hypoglycemic episodes, and the effectiveness of diabetes management. On the other hand, an artificial neural network specialized in cardiology can receive input data such as heart rate and oxygen saturation (SpO2) measured by a smartwatch or electrocardiogram (ECG) measured by a portable ECG device to provide information for diagnosing conditions such as arrhythmias, heart rate variability, and stress-related disorders. It can also provide diagnostic information regarding the patient's fitness level, circulatory health, and overall cardiac function.

[0099] Furthermore, restrictions on diagnostic information provided by artificial neural networks can be minimized while complying with the data privacy and security standards required by specific countries. For example, if a specific country imposes a sales ban on oxygen saturation (SpO2) measuring devices, that country may take measures to replace an artificial neural network specialized for cardiology with one that does not utilize SpO2 data, or to exclude the use of such artificial neural networks.

[0100] Meanwhile, the above-mentioned effective neural network (441) may include a Large Language Model (LLM), such as a Generative Pretrained Transformer (GPT). The Large Language Model includes advanced natural language processing capabilities and can extract and interpret medical information from text inputs provided by patients or doctors, such as symptom descriptions or medical history. In particular, the Large Language Model can rapidly examine a vast amount of medical literature and databases to find relevant information, such as similar cases, recent studies, or guidelines that may aid in diagnosis, and generate a list of potential diagnoses. Furthermore, the Large Language Model can be integrated with other diagnostic models, such as image analysis tools or predictive analysis models, to provide more comprehensive diagnostic information.

[0101] FIG. 5 is a diagram illustrating a rule-based neural network classification model for selecting an effective neural network according to one embodiment of the present disclosure.

[0102] According to FIG. 5, the rule-based neural network classification model can receive at least one of unstructured data or structured data as input and determine an effective neural network (e.g., the effective neural network (441) of FIG. 4). Here, the unstructured data may include consultation text data (511) or consultation image data (512) derived from a patient consultation app (510), and may undergo a preprocessing process to be processed by a rule-based classifier (533). For example, the rule-based neural network classification model may include at least one of a text preprocessing model (531) or an image preprocessing model (532).

[0103] The text preprocessing model (531) may, for example, perform normalization to convert all text into a unified lowercase format to reduce variability. As another example, it may perform tokenization to divide the text into individual units, such as words, phrases, or symbols, to facilitate further processing. Additionally, it may perform stop word removal to remove common words with little analytical value, such as "the," "is," and "at." Furthermore, it may reduce words to their base form or root form by applying morphological analysis and lemma extraction processes, such as converting "running" to "run." Finally, the computing device (100) may process the text data by removing or encoding special characters and punctuation marks included in the text data, depending on the characteristics of the classifier (533).

[0104] Next, the computing device (100) may be equipped with various configurations for feature extraction and representation. Vectorization, particularly TF-IDF (Term Frequency-Inverse Document Frequency), can be used to convert tokens into numerical values ​​representing the importance of words within documents of a collection. Word embeddings utilizing pre-trained models such as Word2Vec or GloVe can convert words into vectors that encapsulate semantic meanings and relationships. For more complex models, contextual embeddings such as BERT or GPT can be utilized to capture the context of words within sentences, thereby improving the understanding of text nuances.

[0105] The above image preprocessing model (532) may include the following various configurations. First, through image resizing, each image is adjusted to a constant resolution and size to ensure consistency in data processing. Next, through color normalization, the color range of the image is standardized to enable consistent color analysis even under various shooting conditions. Next, various image processing techniques may be used, such as noise removal with filtering applied to minimize noise or distortion that may occur in digital images, or feature enhancement. Finally, through the segmentation of image data, each image is segmented to separate and identify specific structures or objects, which can play an important role in increasing the accuracy of classification by the classifier (533).

[0106] FIG. 6 is a diagram illustrating a method for performing additional examinations and differential diagnoses based on a plurality of differential diagnosis information obtained according to one embodiment of the present disclosure.

[0107] The above method can be performed by the first effective neural network (641), data obtained from the effective diagnostic means (661), and the second effective neural network (640). When the first effective neural network (641), selected by the neural network classification model, receives initial patient data such as symptoms, medical history, and preliminary test results, it obtains a plurality of first differential diagnosis information (651) based on the patient data, and can determine an effective diagnostic means (661) among a plurality of diagnostic means (660) based on the plurality of differential diagnosis information (650). The first differential diagnosis information (651) includes an initial differential diagnosis list created based on an integrated analysis of the provided data and can identify potential medical conditions related to the patient's symptoms.

[0108] The first effective neural network (641) may include the step of acquiring a plurality of first differential diagnosis information (651) based on the patient data, and the step of determining an effective diagnostic means (661) among a plurality of diagnostic means (660) based on the first differential diagnosis information (651). While generating the first differential diagnosis information (651) generated through the first effective neural network (641), the computing device (100) may identify a specific region where additional data can significantly improve the accuracy of the diagnosis, and may propose an effective diagnostic means (661) capable of verifying the specific region. The effective diagnostic means (661) may correspond to a targeted test or analysis specifically selected to distinguish the conditions listed in the initial diagnosis. The proposal process is based on a comprehensive database of medical conditions and corresponding diagnostic indicators.

[0109] The first differential diagnosis information (651) may be information to be provided to medical staff, and the medical staff may be medical staff who created the medical record for the patient (e.g., patient medical record (412) in FIG. 4) or medical staff who performed counseling (e.g., text data (511) in FIG. 5). Through this, the medical staff may take quick follow-up action on the patient and may identify aspects that were overlooked during treatment or counseling.

[0110] Medical personnel may perform tests corresponding to the above-mentioned effective diagnostic means (661). The above-mentioned effective diagnostic means (661) may be tests including imaging such as CT or MRI, laboratory tests, genetic tests, or other diagnostic procedures related to the condition confirmed in the first differential diagnosis. Data generated based on the above-mentioned effective diagnostic means (661) may be input into the second effective neural network (542). The second effective neural network (542) may be selected from among a plurality of neural networks for providing diagnostic information (e.g., a plurality of neural networks for providing diagnostic information (440) of FIG. 4) and may be selected by a neural network classification model (e.g., a neural network classification model (430) of FIG. 4). Meanwhile, the second effective neural network (542) may be the same as or different from the first effective neural network (641).

[0111] If the second effective neural network (542) is different from the first effective neural network (641), it may provide second differential diagnosis information (652) that examines aspects that the first effective neural network (641) could not determine. In this case, the second differential diagnosis information (652) may be different from the first differential diagnosis information (651).

[0112] On the other hand, if the second effective neural network (542) is identical to the first effective neural network (641), it can provide second differential diagnosis information (652) with higher accuracy than the first differential diagnosis information (651) obtained from the first effective neural network (641). In this case, the second differential diagnosis information (652) may be a list of differential diagnoses that has been rejected by the effective diagnosis means (661) among the list of differential diagnoses that have been primarily differentially diagnosed.

[0113] The second differential diagnosis information (652) may have a higher accuracy and a narrowed differential diagnosis list compared to the first differential diagnosis information (651). Additionally, the second differential diagnosis information (652), like the first differential diagnosis information (651), may include a step of determining an effective diagnostic means (661) among a plurality of diagnostic means (660), thereby allowing for the repetition of additional tests and diagnoses. At this time, due to the effective diagnostic means (661), the number of additional tests and diagnoses can be reduced while the accuracy of the diagnostic information can be increased.

[0114] Meanwhile, the first differential diagnosis information (651) and the second differential diagnosis information (652) may further include grounds for multiple differential diagnoses included in the list. When grounds include grounds for the differential diagnoses, they can enable medical staff to understand the results and processes of the artificial neural network model. As a result, medical staff can determine an effective diagnostic means (661) based on the first differential diagnosis information (651) or make a final differential diagnosis based on the second differential diagnosis information (652), as well as gain insight into patient data. Furthermore, through the grounds, it is possible to determine whether the artificial neural network for differential diagnosis is operating correctly, thereby more effectively diagnosing and correcting errors that the diagnostic model may contain, improving the model, and enhancing accuracy and reliability.

[0115] FIG. 7 is a flowchart illustrating an example of a method for providing patient diagnostic information based on pet data according to one embodiment of the present disclosure.

[0116] Referring to FIG. 7, the computing device (100) may include the step of receiving the pet data (S110), the step of receiving the pet data and selecting one or more valid neural networks among a plurality of neural networks for providing diagnostic information (S210), and the step of inputting the pet data into the valid neural network to obtain a list (S310) containing a plurality of differential diagnostic information for the pet.

[0117] In the above step S110, the pet data may include at least one of the pet profile data, the pet treatment history data, the pet health measurement information, or the pet counseling data. For example, the pet profile data may include at least one of the pet's breed, age, weight, gender, residence, cohabiting family, or food fed, which may have a significant impact on the diagnosis of the pet. Additionally, the pet treatment history data may include clinical records, imaging data, genetic data, electronic medical records (EMR), etc. Furthermore, the pet health measurement information may be data collected by a portable biosignal measuring device, such as a heart rate monitor or a blood glucose monitor.

[0118] The above pet data may be entered by a person or system that owns or manages the animal. The above pet data may be entered via a special veterinary interface accessible by a veterinarian, animal care manager, or animal care system. Alternatively, the above patient data may be entered via a dedicated portal or app that allows the pet owner to enter data regarding the pet.

[0119] In addition, the aforementioned pet data may include medical data generated at an animal hospital. For example, the medical data may include past health information such as the pet's vaccination records, previous diseases, known allergies, records of regular medication administration, and / or imaging information.

[0120] In addition, the above patient data may include health information of the pet. For example, the above patient data may include at least one of the following information related to diet: whether vomiting occurs; whether diarrhea occurs; whether bloody stools are present; the color of the stool or diarrhea; the form of the stool or diarrhea; and the smell of the stool or diarrhea. Alternatively, it may include at least one of the following information related to the pet's skin problems: swelling of the skin or mucous membranes; whether the ears or skin are scratched; whether the pet continuously licks specific parts of the body; the presence of spots; and changes in the color of the skin or mucous membranes. Alternatively, it may include at least one of the following information related to the pet's eyes: swelling of the eyeball or other mucous membranes; whether tears are flowing or the amount of tears; the presence of eye discharge; and the amount of eye discharge. Alternatively, it may include information related to the pet's movements: the degree of movement; whether convulsions occur or changes in the degree of convulsions; whether tremors occur or changes in the degree of tremors; paralysis; and whether the pet lies on its belly. It may include at least one of the information regarding the posture of lowering the head. Alternatively, it may include at least one of the information regarding the pet's respiration, such as whether or not there is coughing; the number of coughs; the intensity of the cough; the timing of the cough; the type of cough; the type of respiration; and whether or not there is panting and the frequency of panting. However, it is not limited thereto. Due to the above information, the veterinarian can obtain more detailed information about the pet, thereby enabling more accurate treatment for pets that are difficult to communicate with directly.

[0121] In the above step S210, the valid neural network may be determined by a neural network classification model that receives the pet data as input. The neural network classification model may include a rule-based classifier that classifies the pet data according to a certain algorithm. The step of the neural network classification model determining the valid neural network based on the pet data is described later in FIG. 5.

[0122] In the above step S310, the list containing the plurality of differential diagnosis information may provide information for medical staff (medical staff, medical institution) to quickly perform a final diagnosis or to create a differential diagnosis list as an intermediate step to reach a final diagnosis. To enable the medical staff to perform a final diagnosis, the list information may further include grounds that support the list information.

[0123] The step of inputting the pet data into the valid neural network may include the step of selecting a portion of the pet data based on the valid neural network and the step of inputting the pet data into the valid neural network.

[0124] The above plurality of neural networks for providing diagnostic information may include at least two neural networks for diagnosing anatomy, physiology, cardiology, oncology, neurology, endocrinology, gastroenterology, respiratory medicine, dermatology, ophthalmology, obstetrics, orthopedics, ethology, microbiology, parasitology, animal nutrition, infectious diseases, nephrology, emergency medicine, radiology, pathology, dentistry, zoonotic diseases, or genetics.

[0125] FIG. 8 illustrates a brief and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0126] Although the present disclosure has generally been described in relation to computer-executable instructions that can be executed on one or more computers, those skilled in the art will know that the present disclosure may be combined with other program modules and / or implemented as a combination of hardware and software.

[0127] Generally, modules in this specification include routines, procedures, programs, components, data structures, etc., that perform specific tasks or implement specific abstract data types. Furthermore, those skilled in the art will be well aware that the method of this disclosure may be implemented in 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 may be connected to and operated with one or more associated devices).

[0128] The embodiments described in this disclosure may also be implemented in a distributed computing environment in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0129] Computers typically include various computer-readable media. Any medium accessible by a computer may be a computer-readable medium, and such computer-readable media include volatile and non-volatile media, transitory and non-transitory media, and removable and non-removable media. By example, but not limiting, computer-readable media may include computer-readable storage media and computer-readable transmission media.

[0130] Computer-readable storage media include volatile and non-volatile media, transient and non-transient media, and removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, DVD (digital video disk) or other optical disk storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other media that can be accessed by a computer and used to store desired information.

[0131] Computer-readable transmission media typically include all information transmission media that implement computer-readable instructions, data structures, program modules, or other data, etc., on a modulated data signal, such as a carrier wave or other transport mechanism. The term modulated data signal means a signal in which one or more of the characteristics of the signal are set or modified to encode information within the signal. By example, not limiting, computer-readable transmission media include wired media, such as wired networks or direct-wired connections, and wireless media, such as acoustic, RF, infrared, and other wireless media. Any combination of the media described above is also considered to be within the scope of computer-readable transmission media.

[0132] An exemplary environment (1500) for implementing various aspects of the present disclosure, including a computer (1502), is shown, wherein the computer (1502) includes a processing unit (1504), system memory (1506), and a system bus (1508). The system bus (1508) connects system components, including system memory (1506) (but not limited thereto), to the processing unit (1504). The processing unit (1504) may be any processor among various commercial processors. Dual processor and other multiprocessor architectures may also be used as the processing unit (1504).

[0133] The system bus (1508) may be any of several types of bus structures that can be additionally interconnected to a local bus using any of the memory bus, peripheral bus, and various commercial bus architectures. System memory (1506) includes read-only memory (ROM) (1510) and random access memory (RAM) (1512). The basic input / output system (BIOS) is stored in non-volatile memory (1510), such as ROM, EPROM, EEPROM, etc., and this BIOS includes basic routines that help transfer information between components within the computer (1502) at times such as during startup. The RAM (1512) may also include high-speed RAM, such as static RAM, for caching data.

[0134] The computer (1502) also includes an internal hard disk drive (HDD) (1514) (e.g., EIDE, SATA)—this internal hard disk drive (1514) may also be configured for external use within a suitable chassis (not shown)—a magnetic floppy disk drive (FDD) (1516) (e.g., for reading from or writing to a removable diskette (1518)), and an optical disk drive (1520) (e.g., for reading from a CD-ROM disk (1522) or reading from or writing to other high-capacity optical media such as a DVD). The hard disk drive (1514), the magnetic disk drive (1516), and the optical disk drive (1520) may each be connected to the system bus (1508) by a hard disk drive interface (1524), a magnetic disk drive interface (1526), ​​and an optical drive interface (1528). The interface (1524) for implementing an external drive includes, for example, at least one or both of USB (Universal Serial Bus) and IEEE 1394 interface technologies.

[0135] These drives and associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, etc. In the case of a computer (1502), the drives and media correspond to storing any data in a suitable digital format. Although the description of computer-readable storage media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will know that other types of computer-readable storage media, such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc., may also be used in exemplary operating environments and that any of these media may contain computer-executable instructions for performing the methods of the present disclosure.

[0136] A number of program modules, including an operating system (1530), one or more application programs (1532), other program modules (1534), and program data (1536), may be stored in the drive and RAM (1512). All or part of the operating system, application, module and / or data may also be cached in RAM (1512). It will be well known that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

[0137] The user can input commands and information into the computer (1502) through one or more wired / wireless input devices, such as a pointing device like a keyboard (1538) and a mouse (1540). Other input devices (not shown) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, etc. These and other input devices are often connected to the processing unit (1504) via an input device interface (1542) connected to the system bus (1508), but may also be connected via other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, etc.

[0138] A monitor (1544) or other type of display device is also connected to the system bus (1508) via an interface such as a video adapter (1546). In addition to the monitor (1544), the computer generally includes other peripheral output devices (not shown), such as speakers, a printer, and so on.

[0139] The computer (1502) may operate in a networked environment using a logical connection to one or more remote computers, such as remote computer(s) (1548), via wired and / or wireless communication. The remote computer(s) (1548) may be a workstation, server computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and generally include many or all of the components described for the computer (1502), but for brevity, only the memory storage device (1550) is illustrated. The illustrated logical connection includes a wired / wireless connection to a local area network (LAN) (1552) and / or a larger network, e.g., a wide area network (WAN) (1554). Such 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 global computer network, e.g., the Internet.

[0140] When used in a LAN networking environment, the computer (1502) is connected to a local network (1552) via a wired and / or wireless communication network interface or adapter (1556). The adapter (1556) may facilitate wired or wireless communication to the LAN (1552), and the LAN (1552) may also include a wireless access point installed therein to communicate with the wireless adapter (1556). When used in a WAN networking environment, the computer (1502) may include a modem (1558), be connected to a communication server on the WAN (1554), or have other means of establishing communication through the WAN (1554), such as through the Internet. The modem (1558), which may be an internal or external and a wired or wireless device, is connected to the system bus (1508) via a serial port interface (1542). In a networked environment, the program modules described for the computer (1502) or parts thereof may be stored in a remote memory / storage device (1550). It will be well known that the illustrated network connection is exemplary and that other means of establishing a communication link between computers may be used.

[0141] The computer (1502) operates to communicate with any wireless device or object that is deployed and operated by wireless communication, for example, a printer, scanner, desktop and / or portable computer, PDA (portable data assistant), communication satellite, any equipment or place associated with a wireless detectable tag, and a telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network, or simply ad hoc communication between at least two devices.

[0142] Wi-Fi (Wireless Fidelity) enables connectivity to the Internet and other sources without wires. Wi-Fi is a wireless technology, similar to a cell phone, that allows devices, such as computers, to transmit and receive data indoors and outdoors—that is, anywhere within the coverage area of ​​a base station. Wi-Fi networks use a 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, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in 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).

[0143] Those skilled in the art will understand that the various exemplary logic blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented by electronic hardware, various forms of programs or design code (referred to herein as “software”), or a combination of all such. To clearly illustrate this interoperability between hardware and software, various exemplary components, blocks, modules, circuits, and steps have been generally described above in relation to their functions. Whether such functions are implemented as hardware or software depends on the design constraints imposed on the specific application and the overall system. Those skilled in the art may implement the functions described in various ways for each specific application, but such implementation decisions should not be interpreted as being outside the scope of this disclosure.

[0144] The various embodiments presented herein may be implemented as methods, devices, or articles of manufacture using standard programming and / or engineering techniques. The term “article of manufacture” includes a computer program, carrier, or medium accessible from any computer-readable device. For example, computer-readable storage media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical discs (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). The term “machine-readable medium” includes, but is not limited to, wireless channels and various other media capable of storing, holding, and / or transmitting command(s) and / or data.

[0145] It should be understood that the specific order or hierarchy of steps in the presented processes is an example of exemplary approaches. It should be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of this disclosure based on design priorities. The appended method claims provide elements of various steps in a sample order, but do not imply being limited to the specific order or hierarchy presented.

[0146] Description of the presented embodiments is provided so that a person skilled in the art may use or practice the present disclosure. Various modifications to these embodiments will be apparent to a person skilled in the art, 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 limited to the embodiments presented herein, but should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

Claims

Claim 1 A method for providing differential diagnosis information based on pet data, comprising: a step of receiving pet data; a step of selecting one or more valid neural networks among a plurality of neural networks for providing diagnostic information based on the pet data; and a step of inputting the pet data into the valid neural network to obtain a list containing a plurality of differential diagnosis information for the pet; wherein the step of selecting one or more valid neural networks is performed by classifying valid neural networks suitable for the pet data based on criteria set based on medical knowledge, inputting the pet data into a neural network classification model to calculate the degree of fit between neural networks constituting the plurality of neural networks for providing diagnostic information, wherein the neural network classification model includes an artificial neural network model trained on medical knowledge, and the list containing a plurality of differential diagnosis information for the pet further includes the basis for the plurality of differential diagnoses included in the list. Claim 2 A method according to claim 1, wherein the pet data comprises at least one of the pet profile data, the pet counseling data, the pet treatment history data, or the pet health measurement information. Claim 3 In claim 2, the differential diagnosis information is information intended to be provided to medical personnel who have performed consultation or treatment on the pet. Claim 4 delete Claim 5 delete Claim 6 A method according to claim 1, wherein the step of inputting the pet data into the valid neural network comprises: a step of selecting a portion of the pet data based on the valid neural network; and a step of inputting the pet data into the valid neural network. Claim 7 The method according to claim 1, wherein the plurality of neural networks for providing diagnostic information comprises at least two neural networks for diagnosing anatomy, physiology, cardiology, oncology, neurology, endocrinology, gastroenterology, respiratory medicine, dermatology, ophthalmology, obstetrics, orthopedics, ethology, microbiology, parasitology, animal nutrition, infectious diseases, nephrology, emergency medicine, radiology, pathology, dentistry, zoonotic diseases, or genetics. Claim 8 In claim 1, the method wherein the list containing multiple differential diagnosis information for the pet further includes additional testing methods that can support or exclude the multiple differential diagnoses included in the list. Claim 9 delete Claim 10 A computer program stored on a computer-readable storage medium, wherein when the program is executed by one or more processors, the one or more processors perform operations to provide differential diagnosis information based on pet data, the operations include: an operation of receiving pet data; an operation of selecting one or more valid neural networks among a plurality of neural networks for providing diagnostic information based on the pet data; and an operation of inputting the pet data into the valid neural network to obtain a list containing multiple differential diagnosis information for the pet; wherein the operation of selecting one or more valid neural networks is performed by classifying valid neural networks suitable for the pet data based on criteria set based on medical knowledge, inputting the pet data into a neural network classification model to calculate the degree of fit between neural networks constituting the plurality of neural networks for providing diagnostic information, the neural network classification model includes an artificial neural network model trained on medical knowledge, and the list containing multiple differential diagnosis information for the pet further includes grounds for multiple differential diagnoses included in the list. Claim 11 A computing device for providing differential diagnosis information based on pet data, comprising at least one processor and memory; wherein the at least one processor receives pet data and, based on the pet data, selects one or more valid neural networks among a plurality of neural networks for providing diagnostic information; and is configured to input the pet data into the valid neural network to obtain a list containing a plurality of differential diagnosis information for the pet, wherein the operation of selecting the one or more valid neural networks is performed by classifying valid neural networks suitable for the pet data based on criteria set based on medical knowledge, inputting the pet data into a neural network classification model to calculate the degree of fit between neural networks constituting the plurality of neural networks for providing diagnostic information, wherein the neural network classification model includes an artificial neural network model trained on medical knowledge, and the list containing a plurality of differential diagnosis information for the pet further includes grounds for the plurality of differential diagnoses included in the list.

Images