Method for providing clinical decision making support system and server performing same

Abstract

The present invention relates to a method for providing a clinical decision making support system, comprising the steps of: acquiring medical data including a diagnosis history of an object; determining a plurality of treatment guides for the object by inputting the medical data to each of a plurality of medical information providing models trained to determine a treatment guide by using medical data as an input; and providing a user interface including the plurality of treatment guides for the object.

Description

Method for providing a clinical decision support system and a server performing the same

[0001] The present invention relates to a method for providing a clinical decision support system and a server performing the same.

[0002] A Clinical Decision Support System (CDSS) is a computerized knowledge base that integrates individual patient characteristics to provide optimized information for diagnosis and treatment, assisting clinical decision-making during treatment. Through CDSS, physicians can assist in assessing patient testing, deciding whether to perform procedures, and deciding on medications.

[0003] However, even with CDSS, the final diagnosis for a patient is determined by the physician's subjective opinion. This means that a comprehensive diagnosis is based on variables and data, such as the physician's experience and knowledge, as well as the patient's physical and financial circumstances. Consequently, different tests, procedures, treatments, and medications may be administered to each patient.

[0004] Accordingly, a method is required to assist clinicians in making final diagnoses by predicting and providing various judgments of doctors regarding the same patient data through CDSS.

[0005] The background technology of the invention has been prepared to facilitate a better understanding of the present invention. It should not be construed as an admission that the matters described in the background technology of the invention constitute prior art.

[0006] A technology has been disclosed that uses a deep learning model that has learned accumulated data on a specific disease to predict the occurrence or likelihood of a clinical event (e.g., disease, accident, death) that may occur to a patient (hereinafter referred to as an "individual") and provides this to a clinician (hereinafter referred to as "medical staff") through a CDSS.

[0007] However, because each patient's clinical information is different and there is a variety of diseases associated with it, the development of artificial intelligence models that have not been sufficiently verified in the medical field has limitations in their use in actual diagnosis.

[0008] Accordingly, the inventors of the present invention developed a method that can help medical staff provide the best medical treatment to a subject by synthesizing the opinions of several medical staff interpreting clinical information about the subject.

[0009] In particular, the inventors of the present invention have constructed a method to collect the history of judgments (e.g., examinations, procedures, treatments, medications) of multiple medical staff on the same subject, and to learn the judgments of the medical staff using statistical mathematical formulas, machine learning, artificial neural networks, or reinforcement learning, thereby obtaining a treatment guide that is the same as the actual diagnosis made by multiple medical staff based on a single medical data.

[0010] Furthermore, the inventors of the present invention have configured a method to provide a rapid diagnosis service by providing a CDSS user interface that can intuitively check medical information defined as a treatment guide for multiple medical professionals.

[0011] The tasks of the present invention are not limited to the tasks mentioned above, and other tasks not mentioned will be clearly understood by those skilled in the art from the description below.

[0012] In order to solve the above-described problem, a method for providing a clinical decision support system according to an embodiment of the present invention is provided. The method is a method for providing a clinical decision support system implemented by a processor, and is configured to include the steps of: acquiring medical data including a diagnosis history of an individual; inputting the medical data into each of a plurality of medical information providing models trained to determine treatment guides using the medical data as input, thereby determining a plurality of treatment guides for the individual; and providing a user interface including the plurality of treatment guides for the individual.

[0013] According to a feature of the present invention, the step of acquiring the medical data further includes a step of determining, based on the diagnosis history, the type of any one treatment guide to be provided to the subject among consultation, examination, prescription, treatment, procedure, and surgery, and the step of determining the plurality of treatment guides may further include a step of inputting the medical data into each of the plurality of medical information provision models corresponding to the types of the treatment guides.

[0014] According to another feature of the present invention, the step of determining the plurality of treatment guides may be a step of determining the treatment guide including whether to perform at least one medical act among consultation, examination, prescription, treatment, procedure, and surgery of the subject.

[0015] According to another feature of the present invention, the step of providing the user interface may be a step of providing a user interface that further includes whether or not the at least one medical act is performed, and the type or degree of treatment depending on whether or not the at least one medical act is performed.

[0016] According to another feature of the present invention, prior to acquiring the medical data, the method may further include the step of acquiring a plurality of medical data sets including different diagnosis and treatment histories for the same individual in a single medical subject, and the step of generating a plurality of medical information providing models configured to determine a treatment guide by using the medical data as input based on each of the plurality of medical data sets.

[0017] According to another feature of the present invention, the step of providing the user interface may further include the step of generating a recommended treatment guide by combining treatment guides determined using two or more medical information providing models among the plurality of medical information providing models.

[0018] According to another feature of the present invention, the medical data may be data obtained from an EHR (Electronic Health Record) including at least one of an EMR (Electronic Medical Record), an OCS (Order Communication System), and a PACS (Picture Archiving and Communication System) of the subject.

[0019] In order to solve the above-described problem, a clinical decision support system providing server according to another embodiment of the present invention is provided. The server includes a communication interface, a memory, and a processor operably connected to the communication interface and the memory, wherein the processor is configured to obtain medical data including a diagnosis history of an individual, input the medical data into each of a plurality of medical information providing models trained to determine a treatment guide using the medical data as input, and determine a plurality of treatment guides for the individual, and provide a user interface including the plurality of treatment guides for the individual.

[0020] Specific details of other embodiments are included in the detailed description and drawings.

[0021] By providing multiple treatment guides for a single individual, the present invention can assist medical professionals in making optimal diagnoses. For example, by providing information on whether surgery or procedures are performed, as well as the need for consultations and tests, and the type and extent of treatment and prescriptions, the scope of medical professionals' interpretation can be broadened.

[0022] In addition, the present invention collects the history of judgments (e.g., examinations, procedures, and medication administration) of multiple medical staff on the same subject, and learns the judgments of the medical staff using statistically based mathematical formulas, machine learning, artificial neural networks, or reinforcement learning, thereby obtaining an accurate treatment guide that is the same as the diagnosis made by the medical staff.

[0023] In addition, the present invention can intuitively provide necessary information to medical staff by displaying multiple treatment guides that can be provided to the subject on a single screen as medical data is input.

[0024] The effects according to the present invention are not limited to those exemplified above, and more diverse effects are included within the present invention.

[0025] FIG. 1 is a block diagram of a clinical decision support system according to one embodiment of the present invention.

[0026] Figure 2 is a block diagram showing the configuration of a medical device according to one embodiment of the present invention.

[0027] Figure 3 is a block diagram showing the configuration of a server providing a clinical decision support system according to one embodiment of the present invention.

[0028] Figure 4 is a schematic flowchart of a method for providing a clinical decision support system according to one embodiment of the present invention.

[0029] FIG. 5 is a schematic diagram illustrating a method for establishing a medical information provision model according to one embodiment of the present invention.

[0030] FIG. 6a and FIG. 6b are exemplary diagrams of interface screens representing a clinical decision support system according to one embodiment of the present invention.

[0031] FIG. 7a, FIG. 7b, FIG. 7c, FIG. 8a, 8b, and FIG. 8c are tables showing evaluation results for a medical information provision model according to one embodiment of the present invention.

[0032] The advantages and features of the present invention, and the methods for achieving them, will become clearer with reference to the embodiments described in detail below together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms. These embodiments are provided solely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. In connection with the description of the drawings, similar reference numerals may be used for similar components.

[0033] In this document, the expressions "has," "may have," "includes," or "may include" indicate the presence of a feature (e.g., a number, function, operation, or component such as a part), but do not exclude the presence of additional features.

[0034] In this document, the expressions "A or B," "at least one of A and / or B," or "one or more of A or / and B" can include all possible combinations of the listed items. For example, "A or B," "at least one of A and B," or "at least one of A or B" can all refer to cases where (1) at least one A is included, (2) at least one B is included, or (3) at least one A and at least one B are included.

[0035] The terms "first," "second," "first," or "second," as used herein, may describe various components, regardless of order and / or importance, and are only used to distinguish one component from another, without limiting the components. For example, a first user device and a second user device may represent different user devices, regardless of order or importance. For example, without departing from the scope of the rights set forth in this document, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component.

[0036] When it is said that a component (e.g., a first component) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., a second component), it should be understood that the component is directly coupled to the other component, or can be connected via another component (e.g., a third component). Conversely, when it is said that a component (e.g., a first component) is "directly coupled to" or "directly connected to" another component (e.g., a second component), it should be understood that no other component (e.g., a third component) exists between the first component and the other component.

[0037] The expression "configured to" as used herein can be used interchangeably with, for example, "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of." The term "configured to" does not necessarily mean something that is "specifically designed to" in hardware. Instead, in some contexts, the expression "a device configured to" can mean that the device, together with other devices or components, is "capable of." For example, the phrase "a processor configured (or set) to perform A, B, and C" may mean a dedicated processor (e.g., an embedded processor) for performing those operations, or a general-purpose processor (e.g., a CPU or application processor) that can perform those operations by executing one or more software programs stored in a memory device.

[0038] The terms used in this document are used only to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include the plural expression unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the art described in this document. Terms defined in general dictionaries among the terms used in this document may be interpreted as having the same or similar meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this document. In some cases, even if a term is defined in this document, it cannot be interpreted to exclude the embodiments of this document.

[0039] The individual features of the various embodiments of the present invention can be partially or wholly combined or combined with each other, and as can be fully understood by those skilled in the art, various technical connections and operations are possible, and each embodiment can be implemented independently of each other or can be implemented together in a related relationship.

[0040] For clarity in the interpretation of this specification, the terms used in this specification are defined below.

[0041] As used herein, the term "subject" may refer to any entity for which treatment guidance is to be provided based on medical data, including a diagnostic history. For example, the subject may be a patient, and the diagnostic history may be a diagnostic history for various parts of the patient's body. The subject disclosed herein may include any mammal, including humans. However, for the sake of convenience, the present invention defines the subject as a "patient" among "humans" with a diagnostic history.

[0042] As used herein, the term "medical information provision model" may be a model trained to determine a treatment guide using an individual's medical data as input. Here, the medical data includes the individual's diagnostic history and may be obtained from an EHR (Electronic Health Record) that includes at least one of an EMR (Electronic Medical Record), an OCS (Order Communication System), and a PACS (Picture Archiving and Communication System). Specifically, the medical data may include the individual's identification data (e.g., age, gender, genetics, vaccination status), prescription data (e.g., medications taken, allergies), examination data (e.g., medical history), and image data (e.g., radiological images). In addition, the treatment guide may be understood as data indicating whether to perform a certain medical procedure on the individual, or the probability of performing the medical procedure. For example, based on the current diagnosis history, the treatment guide may provide information on whether to perform one of a specific medical procedure among consultation, examination, prescription, treatment, procedure, and surgery on the individual. In addition, the treatment guide may be defined differently for each medical specialty.

[0043] In various embodiments, the medical information provision model can be established using supervised learning or unsupervised learning. In addition, depending on the type of medical data, the artificial intelligence model can be composed of at least one model or two or more ensemble models among VGG net, R, DenseNet based on CNN (Convolutional Neural Network), FCN (Fully Convolutional Network) with encoder-decoder structure, SegNet, DeconvNet, DeepLAB V3+, DNN (deep neural network) such as U-net, SqueezeNet, Alexnet, ResNet18, MobileNet-v2, GoogLeNet, Resnet50, Resnet101, Inception-v3, or a model based on RNN (Recurrent Neural Network).

[0044] In various embodiments, the medical information provision model may be a model comprising one or a combination of a mathematical model learned based on statistics, a machine learning model, an artificial neural network model, and a reinforcement learning model.

[0045] FIG. 1 is a block diagram of a clinical decision support system according to one embodiment of the present invention.

[0046] Referring to FIG. 1, the clinical decision support system (1000) may be a system that can support the decision-making of a clinical doctor by providing a treatment guide to medical staff treating a patient through a clinical decision support system (CDSS).

[0047] A clinical decision support system (1000) may include a medical device (100) that provides a treatment guide, a clinical decision support system providing server (200) (hereinafter referred to as a 'decision server') that provides a treatment guide, and a medical database (300) that stores various types of data of an entity required to provide a treatment guide.

[0048] The medical device (100) is a device that can acquire medical data of an individual and display a treatment guide, and may include a smartphone, a tablet PC (personal computer), a laptop, and a PC.

[0049] The medical device (100) can input medical data through examination or acquire medical data through a medical database (300). For example, the medical data may include individual identification data (e.g., age, gender, genetics, vaccination status), prescription data (e.g., medications taken, allergies), examination data (e.g., medical history), and image data (e.g., radiological images).

[0050] In various embodiments, the medical device (100) may request a treatment guide from the decision-making server (200) based on the acquired medical data. Specifically, the medical device (100) may receive multiple treatment guides from the decision-making server (200) by making a request to inquire about whether to perform any one of the following medical actions: consultation, examination, prescription, treatment, procedure, or surgery on an individual along with the medical data. However, the present invention is not limited thereto, and multiple treatment guides may be received simply by transmitting medical data to the decision-making server (200).

[0051] In various embodiments, the medical device (100) may display a user interface screen (10) including a plurality of treatment guides from the decision-making server (200). For example, the user interface screen (10) may include individual identification data (11) and a plurality of treatment guides (12) determined through a plurality of medical information provision models. In this way, the medical device (100) may provide a plurality of treatment guides obtained through a plurality of medical information provision models, rather than providing a single result data obtained through a single prediction model, thereby reducing the uncertainty of treatment actions for medical personnel in the medical field where clear answers do not exist.

[0052] The decision server (200) generates multiple medical information provision models and may include a general-purpose computer, laptop, data server, web server, etc. as a server capable of providing CDSS to a medical device (100). Specifically, the decision server (200) may determine multiple treatment guides for a single piece of medical data through multiple medical information provision models.

[0053] In various embodiments, the decision-making server (200) may generate multiple medical information provision models to provide treatment guides to the medical device (100) via the CDSS. Specifically, the decision-making server (200) may obtain multiple medical data sets including different diagnosis and treatment histories for the same individual in a single clinical subject via the treatment database (300). The decision-making server (200) may generate medical information provision models having different configurations based on the history of diagnosis and treatment for a single individual in different directions. In other words, the decision-making server (200) may generate multiple medical information provision models configured to determine treatment guides by inputting medical data based on each of the multiple medical data sets.

[0054] In various embodiments, the decision-making server (200) may provide a user interface including multiple treatment guides. Here, the user interface may include, as multiple treatment guides, whether to perform at least one medical procedure among consultation, examination, prescription, treatment, procedure, and surgery, and the type and extent of treatment depending on whether the procedure is performed. The decision-making server (200) may go beyond simply listing multiple treatment guides determined through multiple medical information provision models on the user interface and, in addition, generate a recommended treatment guide combining two or more treatment guides and provide this through the user interface.

[0055] In various embodiments, the decision server (200) may provide a web / app application that can provide treatment guides using multiple medical information provision models via the CDSS to the medical device (100). For example, the decision server (200) may provide a web browser accessible to the medical device (100), or an application or program installable on the medical device (100).

[0056] The treatment database (300) can store various medical data about an individual. For example, the treatment database (300) can be an Electronic Health Record (EHR) that uses EMR (Electronic Medical Record), OCS (Order Communication System), and PACS (Picture Archiving and Communication System) stored in each hospital as data sources. That is, the treatment database (300) can store the diagnosis history of multiple individuals, and for example, the treatment database (300) can include the individual's age, gender, medical history, diagnosis, medication, treatment plan, vaccination date, presence or absence of allergies, and imaging medical images.

[0057] So far, a clinical decision support system (1000) according to one embodiment of the present invention has been described. According to the present invention, the clinical decision support system (1000) can provide meaningful data helpful for diagnosis rather than providing result values ​​using a single diagnostic model by generating and utilizing multiple medical information provision models.

[0058] Below, a medical device that provides a treatment guide will be described with reference to FIG. 2.

[0059] Figure 2 is a block diagram showing the configuration of a medical device according to one embodiment of the present invention.

[0060] Referring to FIG. 2, the medical device (100) may include a memory interface (110), one or more processors (120), and a peripheral interface (130). Various components within the medical device (100) may be connected by one or more communication buses or signal lines.

[0061] The memory interface (110) is connected to the memory (150) and can transmit various data to the processor (120). Here, the memory (150) can include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage, cloud, and blockchain database.

[0062] In various embodiments, the memory (150) may store at least one of an operating system (151), a communication module (152), a graphical user interface module (GUI) (153), a sensor processing module (154), a telephone module (155), and an application (156). Specifically, the operating system (151) may include instructions for processing basic system services and instructions for performing hardware operations. The communication module (152) may communicate with at least one of one or more other devices, computers, and servers. The graphical user interface module (GUI) (153) may process a graphical user interface. The sensor processing module (154) may process sensor-related functions (e.g., processing voice input received using one or more microphones (192). The telephone module (155) may process telephone-related functions. The application module (156) may perform various functions of user applications, such as electronic messaging, web browsing, media processing, navigation, imaging, and other processing functions. Additionally, the medical device (100) can store one or more software applications (156-1, 156-2) associated with one type of service (e.g., an application for providing CDSS) in the memory (150).

[0063] In various embodiments, the memory (150) may store various data for providing treatment guidance for an individual via the CDSS. Specifically, the memory (150) may store identification data for the individual, medical data such as individual EMR, OCS, and PACS, and data configuring a user interface screen including multiple treatment guides.

[0064] In various embodiments, the memory (150) may store a digital assistant client module (157) (hereinafter, DA client module), and accordingly, may store commands for performing client-side functions of the digital assistant and various user data (158) (e.g., user-customized vocabulary data, preference data, user's electronic address book, to-do list, shopping list, and other data).

[0065] Meanwhile, the DA client module (157) can obtain the user's voice input, text input, touch input, and / or gesture input through various user interfaces (e.g., I / O subsystem (140)) provided in the medical device (100).

[0066] Additionally, the DA client module (157) can output data in audiovisual and tactile forms. For example, the DA client module (157) can output data consisting of a combination of at least two or more of voice, sound, notification, text message, menu, graphic, video, animation, and vibration. In addition, the DA client module (157) can communicate with a digital assistant server (not shown) using a communication subsystem (180).

[0067] In various embodiments, the DA client module (157) may collect additional information about the surroundings of the medical device (100) from various sensors, subsystems, and peripheral devices to construct a context associated with the user input. For example, the DA client module (157) may provide context information along with the user input to a digital assistant server to infer the user's intent. Here, the context information that may accompany the user input may include sensor information, such as lighting, ambient noise, ambient temperature, images of the surrounding environment, video, etc. As another example, the context information may include the physical state of the medical device (100) (e.g., device orientation, device position, device temperature, power level, speed, acceleration, motion patterns, cellular signal strength, etc.). As yet another example, the context information may include information related to the software state of the medical device (100) (e.g., processes running on the medical device (100), installed programs, past and present network activity, background services, error logs, resource usage, etc.).

[0068] In various embodiments, the memory (150) may include added or deleted instructions, and further, the medical device (100) may include additional configurations other than those illustrated in FIG. 2, or may exclude some configurations.

[0069] The processor (120) can control the overall operation of the medical device (100) and execute various commands to implement a user interface capable of displaying multiple treatment guides by driving an application or program stored in the memory (150).

[0070] The processor (120) may correspond to a computing device such as a CPU (Central Processing Unit) or an AP (Application Processor). In addition, the processor (120) may be implemented in the form of an integrated chip (IC), such as a SoC (System on Chip) that integrates various computing devices such as an NPU (Neural Processing Unit).

[0071] In various embodiments, the processor (120) may control various operations for implementing a CDSS (Clinical Decision Support System). Specifically, the processor (120) may obtain medical data input from medical staff and obtain medical data on a specific individual from a medical database (300). The processor (120) may request a treatment guide including medical data from the decision-making server (200) through the CDSS, and may receive and display a user interface screen including multiple treatment guides from the decision-making server (200). For example, the processor (120) may display a plurality of treatment guides indicating whether at least one medical act among consultation, examination, prescription, treatment, procedure, and surgery of an individual is performed, along with the type or degree of treatment according to whether it is performed, on the user interface screen. Here, whether it is performed and the type and degree thereof may be displayed in various forms such as text, an image, or a graph.

[0072] The peripheral interface (130) can be connected to various sensors, subsystems, and peripheral devices to provide data so that the medical device (100) can perform various functions. Here, the function performed by the medical device (100) can be understood as being performed by the processor (120).

[0073] The peripheral interface (130) can receive data from a motion sensor (160), a light sensor (light sensor) (161), and a proximity sensor (162), through which the medical device (100) can perform orientation, light, and proximity detection functions, etc. For another example, the peripheral interface (130) can receive data from other sensors (163) (positioning system - GPS receiver, temperature sensor, biometric sensor), through which the medical device (100) can perform functions related to the other sensors (163).

[0074] In various embodiments, the medical device (100) may include a camera subsystem (170) connected to a peripheral interface (130) and an optical sensor (171) connected thereto, which enables the medical device (100) to perform various photographing functions, such as taking pictures and recording video clips.

[0075] In various embodiments, the medical device (100) may include a communication subsystem (180) connected to a peripheral interface (130). The communication subsystem (180) may be comprised of one or more wired / wireless networks and may include various communication ports, radio frequency transceivers, and optical transceivers.

[0076] In various embodiments, the medical device (100) includes an audio subsystem (190) connected to the peripheral interface (130), the audio subsystem (190) including one or more speakers (191) and one or more microphones (192), such that the medical device (100) can perform voice-activated functions, such as voice recognition, voice replication, digital recording, and telephony.

[0077] In various embodiments, the medical device (100) may include an I / O subsystem (140) connected to a peripheral interface (130). For example, the I / O subsystem (140) may control a touch screen (143) included in the medical device (100) via a touch screen controller (141). As an example, the touch screen controller (141) may detect a user's contact and movement or cessation of contact and movement using any one of a plurality of touch sensing technologies, such as capacitive, resistive, infrared, surface acoustic wave technology, proximity sensor array, etc. In another example, the I / O subsystem (140) may control other input / control devices (144) included in the medical device (100) via other input controller(s) (142). As an example, the other input controller(s) (142) may control one or more buttons, rocker switches, thumb-wheels, infrared ports, USB ports, and pointer devices such as a stylus.

[0078] So far, a medical device (100) according to one embodiment of the present invention has been described. According to the present invention, the medical device (100) can provide medical personnel with not only simple data such as a diagnosis history and recommendations for an individual through a CDSS, but also multiple treatment guides, thereby helping to provide an optimal diagnosis for an individual.

[0079] Hereinafter, a medical information provision model is established with reference to FIGS. 3 to 6b, and a decision server (200) that provides multiple treatment guides to a medical staff device (100) is described.

[0080] Figure 3 is a block diagram showing the configuration of a server providing a clinical decision support system according to one embodiment of the present invention.

[0081] Referring to FIG. 3, the decision server (200) may include a communication interface (210), a memory (220), an I / O interface (230), and a processor (240), and each component may communicate with each other through one or more communication buses or signal lines.

[0082] The communication interface (210) can be connected to a medical device (100) and a medical database (300) via a wired / wireless communication network to exchange data. For example, the communication interface (210) can receive a request for providing a treatment guide including medical data on an individual from the medical device (100) and can transmit a user interface including a plurality of treatment guides to the medical device (100). As another example, the communication interface (210) can receive medical data on an individual from the medical database (300) at the request of the medical device (100) and can also receive medical data for establishing and updating a medical information provision model.

[0083] Meanwhile, the communication interface (210) that enables transmission and reception of such data includes a communication port (211) and a wireless circuit (212), wherein the wired communication port (211) may include one or more wired interfaces, for example, Ethernet, Universal Serial Bus (USB), FireWire, etc. In addition, the wireless circuit (212) may transmit and receive data with an external device via an RF signal or an optical signal. In addition, the wireless communication may use at least one of a plurality of communication standards, protocols, and technologies, for example, GSM, EDGE, CDMA, TDMA, Bluetooth, Wi-Fi, VoIP, Wi-MAX, or any other suitable communication protocol.

[0084] The memory (220) can store various data used in the decision server (200). For example, the memory (220) can store identification data of the medical device (100) and identification data of the individual. As another example, the memory (220) can store a plurality of medical prediction models and learning data used to learn the models (e.g., a medical data set including diagnosis and treatment history).

[0085] In various embodiments, the memory (220) may include a volatile or non-volatile storage medium capable of storing various data, commands, and information. For example, the memory (220) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., an SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage, cloud, and a blockchain database.

[0086] In various embodiments, the memory (220) may store configurations of at least one of an operating system (221), a communication module (222), a user interface module (223), and one or more applications (224).

[0087] An operating system (221) (e.g., embedded operating systems such as LINUX, UNIX, MAC OS, WINDOWS, VxWorks, etc.) may include various software components and drivers to control and manage general system operations (e.g., memory management, storage device control, power management, etc.) and may support communication between various hardware, firmware, and software components.

[0088] The communication module (223) can support communication with other devices through the communication interface (210). The communication module (220) can include various software components for processing data received by the wired communication port (211) or wireless circuit (212) of the communication interface (210).

[0089] The user interface module (223) can receive a user's request or input from a keyboard, touch screen, microphone, etc. through an I / O interface (230) and provide a user interface on the display.

[0090] The application (224) may include a program or module configured to be executed by one or more processors (240). Here, the application for providing multiple treatment guides using multiple medical information provision models may be implemented on a server farm.

[0091] The I / O interface (230) can connect at least one of input / output devices (not shown) of the decision server (200), such as a display, a keyboard, a touch screen, and a microphone, to the user interface module (223). The I / O interface (230) can receive user input (e.g., voice input, keyboard input, touch input, etc.) together with the user interface module (223) and process commands according to the received input.

[0092] The processor (240) is connected to a communication interface (210), a memory (220), and an I / O interface (230) to control the overall operation of the decision server (200), and can perform various commands to provide various types of treatment guides on a CDSS (clinical decision support system) through an application or program stored in the memory (220).

[0093] The processor (240) may correspond to a computing device such as a Central Processing Unit (CPU) or an Application Processor (AP). Furthermore, the processor (240) may be implemented in the form of an integrated chip (IC), such as a System on Chip (SoC) in which various computing devices are integrated. Alternatively, the processor (240) may include a module for calculating an artificial neural network model, such as a Neural Processing Unit (NPU).

[0094] In various embodiments, the processor (240) may provide multiple treatment guides based on medical data on the CDSS, as described below with reference to FIG. 4.

[0095] Figure 4 is a schematic flowchart of a method for providing a clinical decision support system according to one embodiment of the present invention. For the explanation of Figure 4, reference is also made to the symbols of the devices in Figure 6.

[0096] The processor (240) can obtain input data including the diagnosis history of the subject (S110). Specifically, the processor (240) can obtain identification data or medical data of the subject along with a request for providing a treatment guide for the subject from the medical device (100) via the communication interface (210). If only identification data is received, the processor (240) can obtain medical data including the diagnosis history of the subject based on the identification data of the subject from the medical database (300).

[0097] In various embodiments, the processor (240) may obtain medical data from an Electronic Health Record (EHR) including at least one of an Electronic Medical Record (EMR), an Order Communication System (OCS), and a Picture Archiving and Communication System (PACS). Specifically, the medical data may include individual identification data (e.g., age, gender, genetics, immunization status), prescription data (e.g., medications taken, allergies), examination data (e.g., medical history), and image data (e.g., radiological images).

[0098] As such, medical data about an individual encompasses various types of data. Interpreting this data is crucial for diagnosing and treating an individual's disease. For example, in the case of a kidney biopsy, the biopsy can be performed based on the following interpretation criteria.

[0099] IndicationsCommentsHematuria1) Presence of visible red blood cells or red blood cell casts with an increase in Scr (Serum creatinine) level or proteinuriaProteinuria1) Multiple measured proteinuria > 1 g / d without a clear overlapping disorder;2) Proteinuria > 3 g / d without diabetes or a sharp increase in proteinuria in the presence of diabetes;3) Proteinuria < 3 g / d, with an elevated Scr level without a clear overlapping disorder such as diabetes or hypertensionAcute kidney injury1) Persistent injury despite reversal of the cause in the setting of acute tubular injury or failure of Scr to return to baseline 7-14 days after the onset of injury;2) Failure to resolve injury despite removal of the underlying drug in the setting of presumed AIN;Chronic kidney disease1) New-onset hematuria or proteinuria with an increase in Scr level rapid rise

[0100] However, for example, in cases of acute kidney injury, interpretive indicators such as "persistent damage," "return to baseline," and "injury resolution" have unclear numerical values ​​and cannot be defined. Therefore, they can vary depending on the experience and knowledge of the medical staff and the individual's circumstances. Accordingly, the present invention can generate a medical information provision model that predicts the medical staff's diagnosis by learning the diagnostic and treatment histories of multiple medical staff based on a single individual's medical data.

[0101] In relation to this, FIG. 5 is a schematic diagram for explaining a method for establishing a medical information provision model according to one embodiment of the present invention.

[0102] Referring to FIG. 5, the processor (240) can acquire multiple sets of medical data including different diagnosis and treatment histories for the same individual in a single medical subject. That is, in the present invention, when medical data (21) including diagnosis history for an individual (e.g., basic examination data of an individual obtained through EMR data (21-1), OCS data (21-2), PACS data (21-3)) is provided to medical staff, multiple sets of medical data (22) including diagnosis and treatment histories for the individual can be acquired.

[0103] The processor (240) can generate multiple medical information provision models (23) configured to determine treatment guides based on each of multiple medical data sets, each using medical data as input. That is, the processor (240) can obtain accurate treatment guides, similar to those diagnosed by medical staff, by generating multiple medical information provision models that have learned from the experiences of medical staff. However, the present invention is not limited thereto, and multiple medical information provision models (23) may be generated and provided in advance.

[0104] After step S110, the processor (240) may input medical data into each of a plurality of medical information providing models trained to determine treatment guides using medical data as input, thereby determining a plurality of treatment guides for the individual (S120). Here, the treatment guide may be understood as data indicating whether to perform a certain medical procedure on the individual, or the probability of performing the medical procedure. To this end, the processor (240) may determine the type of any one of the treatment guides to be provided to the individual among consultation, examination, prescription, treatment, procedure, and surgery, based on the diagnosis history. The processor (240) may determine which of the consultation, examination, prescription, treatment, procedure, and surgery is necessary for the individual based on the current diagnosis history, and may distinguish the types of treatment guides by treatment subject. The processor (240) may input medical data into each of a plurality of medical information providing models corresponding to the distinguished types, thereby determining a plurality of treatment guides. For example, the processor (240) may determine a treatment guide that includes whether to perform at least one medical action among consultation, examination, prescription, treatment, procedure, and surgery of the individual.

[0105] After step S120, the processor (240) may provide a user interface including multiple treatment guides for the subject (S130). Specifically, the processor (240) may provide the medical device (100) with a user interface including whether at least one medical procedure is performed, along with the type or degree of treatment depending on whether it is performed.

[0106] In various embodiments, the processor (240) may combine multiple treatment guides determined using two or more of the multiple medical information providing models. For example, if the type of treatment guide corresponds to whether or not surgery is performed, and at least two of the multiple medical information providing models determine that surgery is to be performed, the processor (240) may provide "Performance of Surgery" as the recommended treatment guide. Meanwhile, the number of medical information providing models that determine the recommended treatment guides may be determined by an administrator or the medical staff device (100).

[0107] In relation to this, FIGS. 6A and 6B are exemplary diagrams of interface screens representing a clinical decision support system according to one embodiment of the present invention.

[0108] Referring to FIG. 6A, the processor (240) may provide a user interface screen (30) for providing multiple treatment guides to the medical staff device (100). The user interface screen (30) may include multiple areas for checking the diagnosis history along with the individual's identification data (31). For example, the diagnosis history may be categorized by treatment subject (32) and may include a treatment timeline (33) and test results (34) performed on a selected date. In addition, the user interface screen (30) may include a graphic object (35) for allowing the medical staff to input a new diagnosis history and a graphic object (36) for requesting a treatment guide from the decision-making server (200).

[0109] If a graphic object (36) requesting a treatment guide for a specific object is selected through the user interface screen (30), the processor (240) may provide a treatment guide such as that shown in FIG. 6b through the user interface screen (30). Here, the treatment guide may include a plurality of treatment guides (37) obtained through each of a plurality of medical information provision models, and may also include a recommended treatment guide (38) that combines two or more treatment guides. In addition, the plurality of treatment guides (37) may display not only whether a medical procedure is performed but also the accuracy of the treatment guide prediction as a numerical value. However, the present invention is not limited thereto, and a user interface screen such as that shown in FIG. 6b may be provided by being integrated into the user interface screen of FIG. 6a.

[0110] So far, a decision-making server (200) according to one embodiment of the present invention has been described. According to the present invention, multiple treatment guides that can be provided to a subject are displayed on a single screen through an interface provided by the decision-making server (200), thereby intuitively providing necessary information to medical staff.

[0111] Hereinafter, the evaluation results of the medical information provision model used in the present invention will be described with reference to FIGS. 7a to 8c.

[0112] FIGS. 7a, 7b, 7c, 8a, 8b, and 8c are tables showing evaluation results for a medical information provision model according to one embodiment of the present invention. The evaluation of the medical information provision model of FIGS. 7a, 7b, 7c, 8a, 8b, and 8c was learned and performed under the following conditions.

[0113] Specifically, the medical information provision model was trained based on the training data of 6,171 patients (75%) out of a total of 8,228 patients, the validation data of 411 patients (5%), and the test set data of the remaining 1,646 patients (20%), and the results were verified based on the test set data.

[0114] Referring to FIGS. 7a, 7b, and 7c, the medical information provision model learned using the medical data set of the present invention determines a treatment guide by inputting previously stored medical data, and the ROC values ​​are 0.967, 0.976, and 0.839, respectively, confirming that the medical information provision model has a high predictive ability. In other words, the medical information provision model generated by the decision-making server (200) can provide results that are the same as those actually diagnosed by medical staff using the medical data set.

[0115] In addition, referring to FIGS. 8a, 8b, and 8c, when combining treatment guides determined from one medical information provision model, two medical information provision models, and three medical information provision models, respectively, it can be confirmed that the predictive ability of the recommended treatment guide is as follows. When two or more medical information provision models are combined, the ROC values ​​are 0.973 and 0.957, respectively, confirming that the medical information provision models have a high enough predictive ability to provide the optimal treatment guide to an individual.

[0116] Although the embodiments of the present invention have been described in more detail with reference to the attached drawings, the present invention is not necessarily limited to these embodiments, and various modifications may be implemented without departing from the technical spirit of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to explain it, and the scope of the technical spirit of the present invention is not limited by these embodiments. Therefore, it should be understood that the embodiments described above are illustrative in all aspects and not restrictive. The protection scope of the present invention should be interpreted by the following claims, and all technical ideas within a scope equivalent thereto should be interpreted as being included in the scope of the rights of the present invention.

Claims

1. A method for providing a clinical decision support system implemented by a processor, A step of obtaining medical data including the diagnostic history of an entity; A step of inputting medical data into each of a plurality of medical information providing models learned to determine treatment guides by inputting medical data, thereby determining a plurality of treatment guides for the subject; and A method for providing a clinical decision support system, comprising: providing a user interface including the plurality of treatment guides for the object; 2. In paragraph 1, The steps of obtaining the above medical data are: Further comprising a step of determining the type of any one treatment guide to be provided to the subject during consultation, examination, prescription, treatment, procedure and surgery, based on the above diagnostic history; The step of determining the above multiple treatment guides is: A method for providing a clinical decision support system, further comprising: a step of inputting the medical data into each of a plurality of medical information provision models corresponding to the types of the above treatment guides; 3. In paragraph 2, The step of determining the above multiple treatment guides is: A method for providing a clinical decision support system, the method comprising a step of determining the treatment guide including whether to perform at least one medical act among consultation, examination, prescription, treatment, procedure, and surgery of the above entity.

4. In paragraph 3, The step of providing the above user interface is: A method for providing a clinical decision support system, comprising the step of providing a user interface further including whether to perform at least one of the above medical acts, and the type or degree of treatment depending on whether or not to perform the act.

5. In paragraph 1, Prior to obtaining the above medical data, A step of obtaining multiple sets of medical data containing different diagnostic and treatment histories for the same individual in one medical subject; and A method for providing a clinical decision support system, further comprising: a step of generating a plurality of medical information providing models configured to determine a treatment guide by using medical data as input based on each of the plurality of medical data sets; 6. In paragraph 1, The step of providing the above user interface is: A method for providing a clinical decision support system, further comprising: a step of generating a recommended treatment guide by combining treatment guides determined using two or more medical information providing models among the above-mentioned multiple medical information providing models; 7. In paragraph 1, The above medical data, A method for providing a clinical decision support system, wherein the data is acquired from an EHR (Electronic Health Record) including at least one of an EMR (Electronic Medical Record), an OCS (Order Communication System) and a PACS (Picture Archiving and Communication System) of the above entity.

8. Communication interface; memory; a processor operably connected to the communication interface and the memory; The above processor, A clinical decision support system providing server configured to obtain medical data including a diagnosis history of an individual, input the medical data into each of a plurality of medical information providing models trained to determine a treatment guide using the medical data as input, determine a plurality of treatment guides for the individual, and provide a user interface including the plurality of treatment guides for the individual.

9. In paragraph 8, The above processor, Based on the above diagnostic history, it is further configured to determine the type of any one treatment guide to be provided to the subject during consultation, examination, prescription, treatment, procedure and surgery. A clinical decision support system providing server configured to input the medical data into each of the plurality of medical information providing models corresponding to the types of the above treatment guides to determine the plurality of treatment guides.

10. In paragraph 9, The above processor, A clinical decision support system providing server configured to determine the treatment guide including whether to perform at least one medical act among consultation, examination, prescription, treatment, procedure and surgery of the above entity.

11. In paragraph 10, The above processor, A clinical decision support system providing server configured to provide a user interface further including whether to perform at least one of the above medical acts, and the type or degree of treatment depending on whether the act is performed.

12. In paragraph 8, Prior to acquiring the above medical data, multiple sets of medical data containing different diagnosis and treatment histories for the same individual in one medical subject are acquired, A clinical decision support system providing server further configured to generate a plurality of medical information providing models configured to determine a treatment guide by taking medical data as input based on each of the plurality of medical data sets.

13. In paragraph 8, The above processor, A clinical decision support system providing server configured to generate a recommended treatment guide by combining treatment guides determined using two or more medical information providing models among the above-mentioned multiple medical information providing models.

14. In paragraph 8, The above medical data, A clinical decision support system providing server, which is data obtained from an EHR (Electronic Health Record) including at least one of an EMR (Electronic Medical Record), an OCS (Order Communication System) and a PACS (Picture Archiving and Communication System) of the above entity.

Images