Apparatus and method for generating acute cardiac arrest prediction information based on cardiac ballistic signals

Abstract

The present invention relates to an apparatus and method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate. More specifically, an acute cardiac arrest prediction information generation device based on heart rate and respiratory rate according to one embodiment of the present invention includes a memory and a processor connected to said memory, and said processor receives a first biosignal from a biosignal measurement sensor installed on a patient's bed that generates a first biosignal for said patient, analyzes said biosignal through an artificial intelligence module to detect a cardiac arrest abnormality, and when said cardiac arrest abnormality is detected, can transmit a warning notification to said patient to a medical diagnostic terminal.

Description

Technology Field

[0001] The present invention relates to an apparatus and method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate. Background Technology

[0003] Unless otherwise indicated in this specification, the contents described in this section are not prior art for the claims of this application, and are not to be recognized as prior art simply because they are included in this section.

[0004] In the case of critically ill patients, such as cancer patients, sudden cardiac arrest can occur, so medical professionals must monitor them 24 hours a day. However, it may be difficult to provide adequate patient care with limited personnel.

[0005] Accordingly, the present invention proposes an AI-based acute cardiac arrest prediction technology for safe cancer patient care that can be utilized in institutions such as cancer treatment centers or hospice care centers where 24-hour monitoring by medical professionals is difficult, by predicting the occurrence of cardiac arrest within 24 hours and allowing medical professionals to take remote measures for the patient in advance through decision-making based on the patient's condition. Prior art literature

[0007] Registered Patent Publication No. 10-1744691 (June 1, 2017) The problem to be solved

[0008] The disclosed embodiment provides an apparatus and method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate.

[0009] The technical problems to be solved by the present invention are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which the present invention belongs from the description below. means of solving the problem

[0011] To achieve the above-mentioned objective, a building underground drainage control device according to one embodiment of the present invention includes a memory and a processor connected to the memory, wherein the processor receives the first heart rate and respiratory rate from a biosignal measurement sensor installed on the patient's bed that generates the first heart rate and respiratory rate for the patient, analyzes the first biosignal through an artificial intelligence module to detect signs of cardiac arrest abnormality, and when signs of cardiac arrest abnormality are detected, transmits a warning notification to the patient to a medical diagnostic terminal.

[0012] At this time, the first biosignal refers to a graph showing changes in heart rate and respiratory rate over time, and the processor distinguishes the first heart rate signal and the first respiratory signal from the first biosignal and can detect the cardiac arrest abnormality based on the first heart rate signal and the first respiratory signal.

[0013] At this time, the processor can derive a first correlation score between the first heart rate signal and the first respiration signal through the artificial intelligence module, and detect the case where the first correlation score corresponds to a preset threshold correlation score and is within a preset error range as the cardiac arrest abnormality.

[0014] At this time, the processor can divide the first heart rate signal, which represents a change in value over time, into multiple intervals based on a preset period time, derive the intervals based on a preset number of judgments retrospectively from the current time point to set them as the first evaluation intervals, derive the first average evaluation graph using the average of the values ​​for the multiple first evaluation intervals, divide the first respiration signal, which represents a change in value over time, into multiple intervals based on the preset period time, derive the intervals based on a preset number of judgments retrospectively from the current time point to set them as the second evaluation intervals, derive the second average evaluation graph using the average of the values ​​for the multiple second evaluation intervals, normalize the values ​​of the first average evaluation graph and the second average evaluation graph to a preset same range to derive the first normalized graph and the second normalized graph, respectively, and derive the first correlation score representing the correlation between the first normalized graph and the second normalized graph through the artificial intelligence module.

[0015] At this time, the processor can derive the critical correlation score based on a learning DB containing information on a second biosignal including the second heart rate signal and the second respiration signal of an emergency critical patient.

[0016] At this time, the processor may divide the second heart rate signal, which represents a change in value over time, into multiple intervals based on the period time, derive a third average evaluation graph based on the average of the values ​​over the entire interval, divide the second respiration signal, which represents a change in value over time, into multiple intervals based on the period time, derive a fourth average evaluation graph based on the average of the values ​​over the entire interval, normalize the values ​​of the third average evaluation graph and the fourth average evaluation graph to the same range to derive a third normalized graph and a fourth normalized graph, respectively, derive a second correlation score representing the correlation between the third normalized graph and the fourth normalized graph through the artificial intelligence module, and set the second correlation score as the critical correlation score.

[0017] At this time, the first correlation score may be the similarity between the vectors of the first normalized graph and the second normalized graph after vectorizing the first normalized graph and the second normalized graph through the artificial intelligence module, and the second correlation score may be the similarity between the vectors of the third normalized graph and the fourth normalized graph after vectorizing the third normalized graph and the fourth normalized graph through the artificial intelligence module. Effects of the invention

[0019] According to the disclosed embodiments, an apparatus and method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate can be provided.

[0020] The effects obtainable from the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description below. Brief explanation of the drawing

[0022] Other aspects, features, and benefits of specific preferred embodiments of the present invention, as described above, will become more apparent from the following description in conjunction with the accompanying drawings. FIG. 1 is a schematic diagram of an apparatus and method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate according to one embodiment of the present invention. FIG. 2 is a diagram showing an acute cardiac arrest prediction information generation device based on heart rate and respiratory rate according to one embodiment of the present invention. FIG. 3 is a diagram showing the process of deriving a first correlation score according to an embodiment of the present invention. FIG. 4 is an exemplary diagram showing the period time and interval according to one embodiment of the present invention. FIG. 5 is a diagram showing the derivation of a critical correlation score according to an embodiment of the present invention. FIG. 6 is a flowchart of a method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate according to an embodiment of the present invention. It should be noted that in the drawings above, similar reference numbers are used to illustrate identical or similar elements, features, and structures. Specific details for implementing the invention

[0023] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various different forms. These embodiments are provided merely 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. Throughout the specification, the same reference numerals refer to the same components.

[0024] In describing the embodiments of the present invention, specific descriptions of known functions or configurations will be omitted if it is determined that such detailed descriptions could unnecessarily obscure the essence of the invention. Furthermore, the terms described below are defined considering their functions in the embodiments of the present invention, and these definitions may vary depending on the intentions or practices of the user or operator. Therefore, such definitions should be based on the content throughout this specification.

[0025] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various different forms. These embodiments are provided merely 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. Throughout the specification, the same reference numerals refer to the same components.

[0026] At this point, it will be understood that each block of the process flow diagrams and combinations of the flow diagrams can be executed by computer program instructions. Since these computer program instructions can be loaded into the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, the instructions executed through the processor of the computer or other programmable data processing equipment create means to perform the functions described in the flow diagram block(s). Since these computer program instructions can also be stored in computer-available or computer-readable memory that can be directed toward the computer or other programmable data processing equipment to implement the function in a specific way, the instructions stored in computer-available or computer-readable memory can also produce a manufactured item containing instruction means to perform the function described in the flow diagram block(s). Since computer program instructions can be loaded onto a computer or other programmable data processing equipment, instructions that perform a series of operation steps on the computer or other programmable data processing equipment to create a process executed by the computer can also provide steps for executing the functions described in the flowchart block(s).

[0027] Additionally, each block may represent a module, segment, or part of code containing one or more executable instructions for executing a specified logical function(s). It should also be noted that in some alternative execution examples, the functions mentioned in the blocks may occur out of order. For instance, two blocks described in succession may actually be executed substantially simultaneously, or the blocks may be executed in reverse order according to their corresponding functions.

[0028] In this embodiment, the term "part" refers to a software or hardware component such as a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC), and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or configured to run one or more processors. Accordingly, as an example, the "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and '~parts' may be implemented to play one or more CPUs within the device or secure multimedia card.

[0029] In describing the embodiments of the present invention in detail, the primary focus will be on examples of specific systems, but the main point claimed in this specification is applicable to other communication systems and services having a similar technical background without significantly departing from the scope disclosed in this specification, and this will be possible at the judgment of a person with skilled technical knowledge in the relevant technical field.

[0031] Hereinafter, an apparatus and method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate according to an embodiment of the present invention will be described in detail with reference to the attached drawings.

[0032] FIG. 1 is a schematic diagram of an apparatus and method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate according to one embodiment of the present invention.

[0033] Referring to FIG. 1, an apparatus and method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate according to one embodiment of the present invention predicts that a patient will experience sudden cardiac arrest through a biosignal measurement sensor installed on a bed used by the patient, and if it is determined that cardiac arrest will occur, transmits a warning notification to a medical diagnostic terminal in advance, thereby enabling the efficient utilization of limited medical personnel and immediate treatment of the patient's emergency situation.

[0035] At this time, the medical diagnostic terminal may include a communication-enabled desktop computer, laptop computer, notebook, smartphone, tablet PC, mobile phone, smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital audio recorder, digital audio player, digital video recorder, digital video player, PDA (Personal Digital Assistant), etc.

[0037] FIG. 2 is a diagram showing an acute cardiac arrest prediction information generation device based on heart rate and respiratory rate according to an embodiment of the present invention.

[0038] An acute cardiac arrest prediction information generation device based on heart rate and respiratory rate according to one embodiment includes a processor and a memory. The processor may perform at least one of the methods described above. The memory may store information related to the method described above or store a program in which the method described above is implemented. The memory may be volatile memory or non-volatile memory. The memory may be referred to as a 'database', 'storage unit', etc.

[0039] At this time, the processor receives the first biosignal from a biosignal measurement sensor installed on the patient's bed that generates the first biosignal for the patient, analyzes the first biosignal through an artificial intelligence module to detect signs of cardiac arrest, and when signs of cardiac arrest are detected, transmits a warning notification to the patient to a medical diagnostic terminal.

[0040] At this time, the artificial intelligence module may use deep learning techniques, which is a field of machine learning.

[0041] In addition, various models such as RNN (Recurrent Neural Network), DNN (Deep Neural Network), and DRNN (Dynamic Recurrent Neural Network) can be used as artificial intelligence network models for learning in the artificial intelligence module.

[0042] Here, RNN is a deep learning technique that considers current and past data simultaneously, and a Recurrent Neural Network (RNN) represents a neural network in which the connections between units constituting the artificial neural network form a directed cycle. Furthermore, various methods can be used for structures that can construct a Recurrent Neural Network (RNN); for example, representative examples include the Fully Recurrent Network, Hopfield Network, Elman Network, Echo State Network (ESN), Long Short-Term Memory Network (LSTM), Bi-directional RNN, Continuous-Time RNN (CTRNN), Hierarchical RNN, and Second-Order RNN. Additionally, methods such as Gradient Descent, Hessian Free Optimization, and Global Optimization Method can be used to train the Recurrent Neural Network (RNN).

[0044] The biosignal measurement sensor according to an embodiment of the present invention is installed on a bed and can recognize the user's biosignal without the user being aware of it.

[0045] At this time, the first biosignal refers to a graph showing changes in heart rate and respiratory rate over time, and the processor distinguishes the first heart rate signal and the first respiratory signal from the first biosignal and can detect the cardiac arrest abnormality based on the first heart rate signal and the first respiratory signal.

[0046] As described below, based on the second vital sign of an emergency critical patient, the relationship between the heart rate signal and the respiratory signal is derived before cardiac arrest occurs, and if the relationship between the heart rate signal and the respiratory signal in the first vital sign is similar to that of the emergency critical patient, it can be considered that there is a possibility of cardiac arrest occurring.

[0047] Accordingly, with reference to FIGS. 3 and 4, the processor derives a first correlation score between the first heart rate signal and the first respiration signal through the artificial intelligence module, and can detect the first correlation score as a sign of cardiac arrest if it falls within a preset threshold correlation score and a preset error range.

[0048] Looking more closely, the processor can divide the first heart rate signal, which represents a change in value over time, into multiple segments based on a preset period time, derive a preset number of segments based on the current time point to set a first evaluation segment, derive a first average evaluation graph based on the average of the values ​​for the multiple first evaluation segments, divide the first respiration signal, which represents a change in value over time, into multiple segments based on the preset period time, derive a preset number of segments based on the current time point to set a second evaluation segment, derive a second average evaluation graph based on the average of the values ​​for the multiple second evaluation segments, normalize the values ​​of the first average evaluation graph and the second average evaluation graph to a preset same range to derive a first normalized graph and a second normalized graph, respectively, and derive a first correlation score representing the correlation between the first normalized graph and the second normalized graph through the artificial intelligence module.

[0049] At this time, the above cycle time can be arbitrarily set by the operator of the present invention, for example, 1 minute or 10 minutes, etc.

[0050] At this time, the number of judgments can be arbitrarily set by the operator of the present invention, for example, 100, 1000, etc.

[0051] In addition, the above normalization is intended to standardize the values ​​of heart rate and respiration signals, which have different units, in order to derive the correlation more clearly.

[0053] FIG. 5 is a diagram showing the derivation of a critical correlation score according to an embodiment of the present invention.

[0054] Referring to FIG. 5, the processor can derive the threshold correlation score based on a learning DB containing information on a second biosignal including the second heart rate signal and the second respiration signal of an emergency critical patient.

[0055] This establishes criteria for determining the possibility of cardiac arrest based on the secondary vital signs of critically ill emergency patients at risk of cardiac arrest.

[0056] Looking more closely, the processor divides the second heart rate signal, which represents a change in value over time, into multiple intervals based on the period time, derives a third average evaluation graph based on the average of the values ​​over the entire interval, divides the second respiration signal, which represents a change in value over time, into multiple intervals based on the period time, derives a fourth average evaluation graph based on the average of the values ​​over the entire interval, normalizes the values ​​of the third average evaluation graph and the fourth average evaluation graph to the same range to derive a third normalized graph and a fourth normalized graph, respectively, derives a second correlation score representing the correlation between the third normalized graph and the fourth normalized graph through the artificial intelligence module, and sets the second correlation score as the critical correlation score.

[0057] Through this, it is possible to determine whether there is a possibility of cardiac arrest.

[0058] In another embodiment, the first correlation score may be the similarity between the vectors of the first normalized graph and the second normalized graph after vectorizing the first normalized graph and the second normalized graph through the artificial intelligence module, and the second correlation score may be the similarity between the vectors of the third normalized graph and the fourth normalized graph after vectorizing the third normalized graph and the fourth normalized graph through the artificial intelligence module.

[0059] In this case, the similarity between vectors may refer to any one of cosine similarity, Euclidean distance similarity, Jaccard similarity, or Levenstein distance similarity.

[0061] FIG. 6 is a flowchart of a method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate according to one embodiment of the present invention.

[0062] Referring to FIG. 6, a method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate according to one embodiment of the present invention can receive a first biosignal from a biosignal measurement sensor installed on the patient's bed that generates a first biosignal for the patient (S100).

[0063] In addition, the method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate according to one embodiment of the present invention can detect signs of cardiac arrest abnormality by analyzing the first biosignal through an artificial intelligence module (S200).

[0064] In addition, the method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate according to one embodiment of the present invention can transmit a warning notification to the patient to a medical diagnostic terminal when the cardiac arrest abnormal sign is detected (S300).

[0065] In addition, the method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate according to one embodiment of the present invention may be configured in the same way as the device for generating acute cardiac arrest prediction information based on heart rate and respiratory rate disclosed in FIGS. 1 to 6.

[0066] Furthermore, the embodiments of the invention disclosed in this specification and drawings are merely specific examples provided to facilitate the explanation of the technical content of the invention and to aid in understanding the invention, and are not intended to limit the scope of the invention. That is, it is obvious to those skilled in the art that other variations based on the technical concept of the invention are possible. In addition, each of the above embodiments may be combined and operated together as needed.

[0067] In addition, the device and method for generating acute cardiac arrest prediction information based on heart rate and respiratory rate according to one embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium.

[0068] Various embodiments of the present invention may be implemented as computer-readable code on a computer-readable recording medium in a particular aspect. A computer-readable recording medium is any data storage device capable of storing data that can be read by a computer system. Examples of computer-readable recording media may include read-only memory (ROM), random-access memory (RAM), compact disk-read-only memory (CD-ROM), magnetic tapes, floppy disks, optical data storage devices, and carrier waves (such as data transmission over the Internet). Computer-readable recording media may also be distributed through networked computer systems, and thus computer-readable code is stored and executed in a distributed manner. Furthermore, functional programs, codes, and code segments for achieving various embodiments of the present invention can be easily interpreted by programmers skilled in the field to which the present invention applies.

[0069] It will also be understood that the apparatus and method according to various embodiments of the present invention may be realized in the form of hardware, software, or a combination of hardware and software. Such software may be stored in a volatile or non-volatile storage device, such as a storage device such as ROM, regardless of whether it is eraseable or rewritable, for example; a memory, such as RAM, a memory chip, a device, or an integrated circuit, for example; or a storage medium that is optically or magnetically writable and simultaneously machine-readable (e.g., computer), such as a compact disk (CD), DVD, magnetic disk, or magnetic tape, for example. It will be understood that the method according to various embodiments of the present invention may be implemented by a computer or a portable terminal comprising a control unit and a memory, and that such memory is an example of a machine-readable storage medium suitable for storing a program or programs containing instructions for implementing the embodiments of the present invention.

[0070] Accordingly, the present invention comprises a program including code for implementing the device or method described in the claims of this specification, and a machine-readable storage medium (such as a computer) for storing such a program. Additionally, such a program may be electronically transmitted through any medium, such as a communication signal transmitted via a wired or wireless connection, and the present invention appropriately includes equivalents thereof.

[0071] The embodiments of the invention disclosed in this specification and drawings are provided merely as specific examples to facilitate the explanation of the technical content of the invention and to aid in understanding the invention, and are not intended to limit the scope of the invention. Furthermore, the embodiments according to the invention described above are merely illustrative, and those skilled in the art will understand that various modifications and equivalent embodiments are possible therefrom. Accordingly, the true technical scope of protection of the invention should be determined by the following claims.

Claims

Claim 1 A device for generating acute cardiac arrest prediction information based on heart rate and respiratory rate comprises a memory and a processor connected to the memory, wherein the processor receives a first biosignal from a biosignal measurement sensor installed on the patient's bed that generates a first biosignal for the patient, analyzes the first biosignal through an artificial intelligence module to detect signs of cardiac arrest abnormality, and transmits a warning notification to the patient to a medical diagnostic terminal when signs of cardiac arrest abnormality are detected, wherein the first biosignal refers to a graph representing changes in heart rate and respiratory rate over time, wherein the processor distinguishes a first heart rate signal and a first respiratory signal from the first biosignal, and detects signs of cardiac arrest abnormality based on the first heart rate signal and the first respiratory signal, wherein the processor derives a first correlation score between the first heart rate signal and the first respiratory signal through the artificial intelligence module, and detects signs of cardiac arrest abnormality when the first correlation score corresponds to a preset threshold correlation score and a preset error range, and wherein The processor divides the first heart rate signal, which represents a change in value over time, into multiple intervals based on a preset period time, derives the said intervals by retrospectively calculating a preset number of judgments based on the current time point to set them as the first evaluation intervals, derives the first average evaluation graph using the average of the values ​​for the multiple first evaluation intervals, divides the first respiration signal, which represents a change in value over time, into multiple intervals based on the preset period time, derives the said intervals by retrospectively calculating a preset number of judgments based on the current time point to set them as the second evaluation intervals, derives the second average evaluation graph using the average of the values ​​for the multiple second evaluation intervals, and normalizes the values ​​of the first average evaluation graph and the second average evaluation graph to a preset identical range to derive the first normalized graph and the second normalized graph, respectively.A heart rate and respiratory rate-based acute cardiac arrest prediction information generation device, characterized by deriving the first correlation score representing the correlation between the first normalization graph and the second normalization graph through the artificial intelligence module. Claim 2 A heart rate and respiratory rate-based acute cardiac arrest prediction information generation device according to claim 1, wherein the processor derives the threshold correlation score based on a learning DB containing information on a second biosignal including a second heart rate signal and a second respiratory signal of an emergency critical patient. Claim 3 A heart rate and respiratory rate-based acute cardiac arrest prediction information generation device according to claim 2, wherein the processor divides the second heart rate signal, which indicates a change in value over time, into multiple intervals based on the period time, derives a third average evaluation graph based on the average of the values ​​over the entire interval, divides the second respiration signal, which indicates a change in value over time, into multiple intervals based on the period time, derives a fourth average evaluation graph based on the average of the values ​​over the entire interval, normalizes the values ​​of the third average evaluation graph and the fourth average evaluation graph to the same range to derive a third normalized graph and a fourth normalized graph, respectively, derives a second correlation score representing the correlation between the third normalized graph and the fourth normalized graph through the artificial intelligence module, and sets the second correlation score as the critical correlation score. Claim 4 A heart rate and respiratory rate-based acute cardiac arrest prediction information generation device according to claim 3, wherein the first correlation score is the similarity between vectors of the first normalized graph and the second normalized graph, vectorized through the artificial intelligence module, and the second correlation score is the similarity between vectors of the third normalized graph and the fourth normalized graph, vectorized through the artificial intelligence module. Claim 5 delete Claim 6 delete Claim 7 delete

Images