KR102346824B1 - System of providing complex living support solution by monitoring and analyzing biosignal based on artificial intelligence and operating method thereof - Google Patents

Abstract

The present invention is a technology for providing a complex life support solution by monitoring and analyzing a biosignal measured using a biosignal measuring device based on artificial intelligence, and according to an embodiment, the complex life support solution providing system is a A gateway for transmitting monitoring information including a biosignal including at least one of an electrocardiogram signal, a motion signal, and a pulse wave signal to a server, and extracting the electrocardiogram signal of the biosignal from the transmitted monitoring information, and pre-stored artificial intelligence machine learning Extracting morphological information through conversion of the extracted electrocardiogram signal into a time-standardized image based on an algorithm as feature information, determining a plurality of cardiac abnormality type models using the extracted feature information, and the determined plurality calculates the classification accuracy for the cardiac abnormality model of , a server that feeds back the determined information on whether the cardiovascular disease and the emergency state and the change information of the biosignal to the user terminal device.

Description

SYSTEM OF PROVIDING COMPLEX LIVING SUPPORT SOLUTION BY MONITORING AND ANALYZING BIOSIGNAL BASED ON ARTIFICIAL INTELLIGENCE AND OPERATING METHOD THEREOF}

The present invention relates to a technical idea of providing a complex life support solution by monitoring and analyzing bio-signals measured using a bio-signal measuring device based on artificial intelligence. By learning and analyzing using an artificial intelligence algorithm to determine the type of heart abnormality model, and supporting more accurate decisions on cardiovascular disease based on the evaluation of the determined type of cardiac abnormality model, customized medical services are provided and related to heart disease It is about technology that supports decision-making.

Referring to demographic changes, the population aged 65 and over is expected to reach 10.5 million in 2025, accounting for 20% of the total population of 56.21 million. have.

Cardiocerebrovascular disease accounts for 24.3% of all deaths and has a direct correlation with the aging of the population.

According to information released by hospitals, the in-hospital mortality rate of intensive care unit patients is 18%, which is about twice that of developed countries, and one-third of all deaths in the country in 2018 are deaths in elderly care hospitals and nursing homes.

Intensive care units that have obtained grade 2 or higher in the adequacy assessment account for only about one-third of the total, and the quality of medical services needs to be improved. It accounts for about half of all medical expenses.

The low number of intensive care units contributes to the deficit of tertiary hospitals/general hospitals, and among medical institutions, nursing hospitals contribute the most to job creation, but inpatient income per 100 beds is the lowest.

Representative technologies for solving the above-mentioned problems are monitoring technologies using electrocardiogram (ECG), photoplethysmogram (PPG), physical activity measurement system (Actigraph), and 3D depth camera in terms of patient monitoring technology. .

On the other hand, in terms of AI-based physiological signal processing technology, deep-learning model related artifact removal and deep-learning model related signal encoding and decoding (Signal encoding and decoding), deep-learning model-related arrhythmia detection and classification, and deep-learning model-related risk assessment of chronic diseases contains

In addition, in terms of general signal analysis technology, it includes HRV (Heart rate variability), BRS (Baroreflex sensitivity), and pulse morphology analysis, and in terms of edge computing technology, Centralized monitoring of hospital, Embedded artificial intelligence model , real-time stream data analysis may be included.

However, in the current technology for patient monitoring in the ward, false alarms occur very frequently during monitoring of patients in the intensive care unit according to low-quality biosignal data, thereby deteriorating the work efficiency of the medical staff and the prognosis of the patient.

In addition, medical data is doubling every 73 days until 2020, but labor-intensive and retrospective analysis is required to process large amounts of low-quality data.

In addition, compared to the exploding data, there are not enough manpower to analyze it, so it is difficult to increase the number of medical personnel due to problems with revenue.

Korean Patent Publication No. 10-2020-0062685 "Method of collecting patient monitoring information using Internet of Things service" Korean Patent Application Laid-Open No. 10-2020-0002241 "Method, device and computer program for monitoring biological signals" Korea Patent Publication No. 10-2020-0002201 "Smart healthcare system through artificial intelligence" Korean Patent Publication No. 10-2017-0129689 "Mobile Wearable Monitoring System"

The present invention determines a classification model for major cardiovascular diseases such as myocardial infarction and coronary artery disease based on a biosignal measuring device attached to a patient to detect the patient's condition and a server using an artificial intelligence algorithm for biosignals related to the heart condition and to prevent the occurrence of false diagnosis and false alarms by doctors based on the determined major cardiovascular disease classification model.

An object of the present invention is to provide a complex life support solution including a telemedicine service in preparation for the post-corona era.

The present invention transmits emergency situation information and basic biosignal information to medical staff and emergency centers of nursing hospitals and emergency centers when an emergency such as cardiac arrest or a fall is detected, and an external related institution receives the analysis data in real time to detect the emergency situation of the person being supported It aims to provide a complex life support solution to prepare for.

An object of the present invention is to reduce the number of false alarms that may be generated in a hospital room by accurately measuring and analyzing a patient's current condition, thereby improving the work efficiency of medical staff and the patient's prognosis.

An object of the present invention is to detect the heart condition of a patient so that heart condition analysis for real-time arrhythmia detection, biosignal quality control for improving signal analysis reliability, and major cardiovascular disease evaluation for early disease management can be performed.

According to the present invention, tachycardia, bradycardia, atrial fibrillation, left-angle block, right-angle block, and atrial premature ejaculation are analyzed based on a pre-stored artificial intelligence algorithm for bio-signals measured from a bio-signal measuring device attached to a patient and detecting the patient's heart condition. It aims to detect major types of cardiac abnormalities such as contractions, ventricular premature contractions, and cardiac arrest.

The present invention uses a pre-stored artificial intelligence algorithm and open data set to calculate cardiac function abnormality classification accuracy, emergency situation classification accuracy, and artifact signal detection accuracy. The purpose of the present invention is to improve the measurement accuracy of biosignals by learning and evaluating the measurement accuracy of biosignals.

An object of the present invention is to contribute to diagnosis assistance and reduction of medical costs through continuous monitoring of arrhythmias.

An object of the present invention is to provide a function of evaluating the risk of chronic diseases through analysis of pulse waves and ECG waveforms using artificial intelligence learning technology.

According to an embodiment of the present invention, a system for providing a complex life support solution includes a gateway for transmitting monitoring information including a biosignal including at least one of an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal of a subject to be supported to a server, and the Extracting the ECG signal of the biosignal from the transmitted monitoring information, and extracting the morphological information through conversion of the extracted ECG signal into a time-standardized image based on a pre-stored artificial intelligence machine learning algorithm as feature information, A plurality of cardiac abnormality type models are determined using the extracted characteristic information, classification accuracy of the plurality of determined cardiac abnormality type models is calculated, and the determined cardiac abnormality type model and published models are based on the calculated accuracy. A server that determines whether the support target has a cardiovascular disease and an emergency state using the cardiovascular disease data, and feeds back information on the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal to a user terminal device may include

The user terminal device includes at least one of a medical staff terminal device, a guardian terminal device, and an emergency center terminal device, and the user terminal device includes information about the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignals. Information including at least one is output, and the prescription information may be updated in the guardian terminal device and the emergency center terminal device based on prescription information generated according to the information output to the medical staff terminal device.

The user terminal device includes a nursing management service, a disease data management service, a disease data visualization, a disease data statistical service and At least one of an emergency push notification service may be provided.

The server includes a monitoring information collection unit that collects monitoring information including a 3D depth image, an electrocardiogram signal, a motion signal, a body temperature signal, and a biosignal including a pulse wave signal measured from the support target, and the transmitted monitoring information includes A signal extraction unit for extracting an electrocardiogram signal, extracts morphological information through conversion of the extracted electrocardiogram signal into a time-standardized image based on a pre-stored artificial intelligence machine learning algorithm, into feature information, and extracts the extracted feature information a plurality of cardiac abnormality type models are determined using the an artificial intelligence processing unit that determines whether the support target has cardiovascular disease and an emergency state, and at least one of information about the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal to the user terminal device It may include a control unit for controlling the feedback.

The artificial intelligence processing unit generates a normalized signal based on the time domain of the extracted electrocardiogram signal, the artificial intelligence processing unit converts the generated normalized signal into the time normalized image, and the converted image A compressed signal is generated by applying the pre-stored artificial intelligence machine learning algorithm-based weight to the , and a restored signal is generated from the compressed signal using the applied weight, and the difference between the generated normalized signal and the generated restored signal is The morphological information of the ECG signal may be extracted as the feature information by machine learning the weight to correspond to a preset threshold range.

The artificial intelligence processing unit machine-learns the characteristic information and converts the plurality of heart abnormality type models into a tachycardia model, bradycardia model, atrial fibrillation model, left-angle block model, right-angle block model, atrial premature contraction model, ventricular premature contraction model, cardiac arrest model and at least one model of a normal heart state model.

The artificial intelligence processing unit includes at least one of an open data set and the tachycardia model, the bradycardia model, the atrial fibrillation model, the left-angle block model, the right-angle block model, the atrial premature contraction model, and the ventricular premature contraction model; In the case of TP (True Positive) that classifies the cardiac abnormality as the cardiac abnormality using a normal heart condition model, and the FN (False Negative) case that classifies the cardiac abnormality as the normal, FP (False) that classifies the normal as the cardiac abnormality Positive) case and TN (True Negative) case that classifies the normal into the normal, the TP (True Positive) case, the FN (False Negative) case, the FP (False Positive) case The tachycardia model, the bradycardia model, the tachycardia model based on the ratio of the combination of the TP (True Positive) value and the TN (True Negative) case value to the combination of the numerical value and the TN (True Negative) case value. A classification accuracy for at least one of the atrial fibrillation model, the left-angle block model, the right-angle block model, the atrial premature contraction model, and the ventricular premature contraction model may be calculated.

The artificial intelligence processing unit uses an open data set, the cardiac arrest model, and the normal heart state model to divide the cardiac arrest section into the cardiac arrest section (True Positive) (TP), which divides the cardiac arrest section into a normal section (False Negative FN) ), classifying the FP (false positive) case that divides the normal section into the cardiac arrest section and the TN (True Negative) case that classifies the normal section into the normal section, the TP (True Positive) case, The TN (True Negative) case and the TP (True Positive) case for the combination of the FN (False Negative) case, the FP (False Positive) case, and the TN (True Negative) case. It is possible to calculate the emergency classification accuracy based on the ratio of the combination of the numerical values of .

The artificial intelligence processing unit divides the artifact signal into the artifact signal in a True Positive (TP) case, in a FN (False Negative) case in which the artifact signal is classified as a normal signal, and in a FP (False Positive) case that classifies the normal signal into the artifact signal. ), the normal signal is classified as a TN (True Negative) case for classifying the normal signal, the TP (True Positive) case, the FN (False Negative) case, and the FP (False Positive) case Artifact removal accuracy may be calculated based on the ratio of the combination of the numerical value of the TP (True Positive) case to the combination of the numerical value of the TN (True Negative) case and the numerical value of the TN (True Negative) case.

After at least one of the ECG signal and the motion signal is measured, the controller calculates the measured number of ECG signals and the measured number of motion signals, and calculates the number of ECG signals and the calculated motion signals. By comparing the number with a threshold value, a data reception state of the ECG signal and the motion signal may be confirmed.

According to an embodiment of the present invention, the complex life support solution providing system measures a biosignal including at least one of a 3D depth image, an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal from the support subject, and the measured biometric signal A biosignal measuring device comprising: a biosignal monitoring unit that outputs monitoring information including signals through an artificial intelligence encoder; and a control unit that controls the outputted monitoring information to be transmitted to the server through the gateway using short-range wireless communication may further include.

The bio-signal monitoring unit monitors a physical activity measurement (Actigraph) and body temperature measured from at least one of an ear, neck, or wrist as the bio-signal, and artificially generates the movement signal and body temperature signal according to the body reaction. It can be encrypted and output through an intelligent encoder.

The biosignal monitoring unit monitors a neural response by photoplethysmography (PPG) measured from at least one of the ear, neck, or wrist as the biosignal, and encodes and outputs autonomic neural information according to the neural response through an artificial intelligence encoder. can do.

The controller may simulate data traffic generated when measuring at least one of a 3D depth image, an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal, and determine an operating state of the biosignal measuring device based on the simulation .

The controller may detect an emergency including cardiac arrest and a fall of the support target based on the measured 3D depth image, an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal.

According to an embodiment of the present invention, a method of operating a system for providing a complex life support solution includes: measuring, in a biosignal measuring device, a biosignal including at least one of an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal from a subject to be supported , transmitting, in the biosignal measuring device, monitoring information including the measured biosignal to a server through a gateway, in the server, extracting an electrocardiogram signal of the biosignal from the transmitted monitoring information, and pre-stored Extracting morphological information through conversion of the extracted electrocardiogram signal into a time-standardized image based on an artificial intelligence machine learning algorithm into feature information, in the server, a plurality of hearts using the extracted feature information Determining an abnormality type model, calculating, in the server, classification accuracy for the plurality of determined cardiac abnormality type models, in the server, based on the calculated accuracy, the determined cardiac abnormality type model and published cardiovascular system determining whether the support target has cardiovascular disease and an emergency state using relational disease data, and in the server, information about the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal to the user terminal device It may include the step of providing feedback.

The user terminal device may include at least one of a medical staff terminal device, a guardian terminal device, and an emergency center terminal device.

According to an embodiment of the present invention, the method of operating a system for providing a complex life support solution includes, in the user terminal device, at least one of information on whether the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal outputting information, and in the user terminal device, updating the prescription information to the guardian terminal device and the emergency center terminal device based on the prescription information generated according to the information output to the medical staff terminal device. may include

According to an embodiment of the present invention, the method of operating a system for providing a complex life support solution includes, in the user terminal device, the support target based on the determined information on whether the cardiovascular disease and the emergency state and the change information of the biosignal The method may further include providing at least one of a nursing management service, a disease data management service, a disease data visualization, a disease data statistical service, and an emergency push notification service.

In the extracting of the feature information, a normalized signal generated based on a time domain of the extracted electrocardiogram signal is converted into the time normalized image, and an artificial intelligence model-based weight is applied to the converted image. generating a compressed signal, generating a restored signal from the compressed signal using the applied artificial intelligence model-based weight, and a difference between the generated normalized signal and the generated restored signal falls within a preset threshold range The method may include extracting the feature information from the morphological information of the ECG signal by machine learning the artificial intelligence model-based weights.

The step of determining a plurality of cardiac abnormality type models by machine learning the extracted characteristic information may include machine learning the characteristic information to convert the plurality of cardiac abnormality type models into a tachycardia model, bradycardia model, atrial fibrillation model, left angle block model, right leg. It may include determining as at least one of a block model, an atrial premature contraction model, a ventricular premature contraction model, a cardiac arrest model, and a normal heart state model.

Calculating the classification accuracy for the determined plurality of cardiac abnormality type models includes: an open data set and the tachycardia model, the bradycardia model, the atrial fibrillation model, the left-angle block model, the right-angle block model, and the atrial premature contraction model. and a TP (True Positive) case that classifies the cardiac abnormality as the cardiac abnormality using at least one of the ventricular premature contraction model and the normal heart condition model, and a FN (False Negative) case that classifies the cardiac abnormality as normal , classifying the normal into the FP (False Positive) case and the TN (True Negative) case for classifying the normal as the cardiac abnormality, and the TP (True Positive) case, the FN (False) Combination of the numerical value in the case of the TP (True Positive) and the numerical value in the case of the TN (True Negative) to the combination of the numerical value in the negative) case, the numerical value in the FP (False Positive) case, and the TN (True Negative) case numerical value. Calculating classification accuracy for at least one of the tachycardia model, the bradycardia model, the atrial fibrillation model, the left-angle block model, the right-angle block model, the atrial premature contraction model, and the ventricular premature contraction model based on the ratio of may include

The present invention determines a classification model for major cardiovascular diseases such as myocardial infarction and coronary artery disease based on a biosignal measuring device attached to a patient to detect the patient's condition and a server using an artificial intelligence algorithm for biosignals related to the heart condition In addition, based on the determined major cardiovascular disease classification model, it is possible to prevent a doctor's misdiagnosis and false alarm.

The present invention can provide a complex life support solution including a remote medical service in preparation for the post-corona era.

The present invention transmits emergency situation information and basic biosignal information to medical staff and emergency centers of nursing hospitals and emergency centers when an emergency such as cardiac arrest or a fall is detected, and an external related institution receives the analysis data in real time to detect the emergency situation of the person being supported We can provide a complex life support solution to prepare for.

The present invention can reduce the number of false alarms that may be generated in a ward by accurately measuring and analyzing the patient's current condition, thereby improving the work efficiency of the medical staff and the patient's prognosis.

The present invention can detect the heart condition of a patient to perform heart condition analysis for real-time arrhythmia detection, biosignal quality management for improving signal analysis reliability, and major cardiovascular disease evaluation for early disease management.

According to the present invention, tachycardia, bradycardia, atrial fibrillation, left-angle block, right-angle block, and atrial premature ejaculation are analyzed based on a pre-stored artificial intelligence algorithm for bio-signals measured from a bio-signal measuring device attached to a patient and detecting the patient's heart condition. It can detect major types of heart abnormalities such as contractions, ventricular premature contractions, and cardiac arrest.

The present invention uses a pre-stored artificial intelligence algorithm and open data set to calculate cardiac function abnormality classification accuracy, emergency situation classification accuracy, and artifact signal detection accuracy. By learning and evaluating the measurement accuracy of the bio-signal, the measurement accuracy of the bio-signal can be improved.

The present invention can contribute to diagnosis assistance and reduction of medical costs through continuous monitoring of arrhythmias.

The present invention can provide a function of evaluating the risk of chronic diseases through analysis of pulse waves and ECG waveforms using artificial intelligence learning technology.

1 and 2 are diagrams illustrating a system for providing a complex life support solution according to an embodiment of the present invention.
3 is a view for explaining the components of a biosignal measuring apparatus according to an embodiment of the present invention.
4 is a diagram illustrating a deep learning model related to an artificial intelligence encoder of a biosignal measuring device according to an embodiment of the present invention.
5A and 5B are diagrams for explaining a heart condition sensor device among biosignal measuring devices according to an embodiment of the present invention.
6 is a view for explaining additional components of a heart condition detection sensor device among the biosignal measuring device according to an embodiment of the present invention.
7 is a view for explaining the flow of major events of biosignal measurement and data transmission according to an embodiment of the present invention.
8 is a view for explaining the components of a server according to an embodiment of the present invention.
9 is a view for explaining an operation method of a system for providing a complex life support solution according to an embodiment of the present invention.

Hereinafter, various embodiments of the present document will be described with reference to the accompanying drawings.

Examples and terms used therein are not intended to limit the technology described in this document to a specific embodiment, but it should be understood to include various modifications, equivalents, and/or substitutions of the embodiments.

In the following, when it is determined that a detailed description of a known function or configuration related to various embodiments may unnecessarily obscure the gist of the present invention, a detailed description thereof will be omitted.

In addition, the terms to be described later are terms defined in consideration of functions in various embodiments, which may vary according to the intention or custom of a person to be supported and an operator. Therefore, the definition should be made based on the content throughout this specification.

In connection with the description of the drawings, like reference numerals may be used for like components.

The singular expression may include the plural expression unless the context clearly dictates otherwise.

In this document, expressions such as “A or B” or “at least one of A and/or B” may include all possible combinations of items listed together.

Expressions such as "first," "second," "first," or "second," can modify the corresponding elements regardless of order or importance, and to distinguish one element from another element. It is used only and does not limit the corresponding components.

When an (eg, first) component is referred to as being “connected (functionally or communicatively)” or “connected” to another (eg, second) component, that component is It may be directly connected to the component or may be connected through another component (eg, a third component).

As used herein, "configured to (or configured to)" according to the context, for example, hardware or software "suitable for," "having the ability to," "modified to ," "made to," "capable of," or "designed to" may be used interchangeably.

In some circumstances, the expression “a device configured to” may mean that the device is “capable of” with other devices or parts.

For example, the phrase "a processor configured (or configured to perform) A, B, and C" refers to a dedicated processor (eg, an embedded processor) for performing the corresponding operations, or by executing one or more software programs stored in a memory device. , may refer to a general-purpose processor (eg, a CPU or an application processor) capable of performing corresponding operations.

Also, the term 'or' means 'inclusive or' rather than 'exclusive or'.

That is, unless stated otherwise or clear from context, the expression 'x employs a or b' means any one of natural inclusive permutations.

Terms such as '.. unit' and '.. group' used below mean a unit that processes at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software.

1 and 2 are diagrams illustrating a system for providing a complex life support solution according to an embodiment of the present invention.

1 illustrates the components of a complex life support solution providing system according to an embodiment of the present invention.

Referring to FIG. 1 , the complex life support solution providing system 100 combines the living indoor monitoring system 110 and the heart condition monitoring system 120 to combine the living indoor monitoring system 110 with a biosignal measuring device and heart The complex life support platform 130 may be provided by combiningly utilizing the measurement data of the biosignal measuring device utilized in the condition monitoring system 120 .

According to an embodiment of the present invention, the complex life support platform 130 determines a heart abnormality type model according to analysis and learning based on artificial intelligence, and based on the evaluation of the determined heart abnormality type model, for cardiovascular disease Supporting more accurate decisions can help deliver personalized health care and support decision-making related to heart disease.

Therefore, the complex life support platform 130 analyzes and learns the measurement data of the biosignal measuring device based on artificial intelligence toward the user terminal device 140 used by related institutions, emergency centers, guardians, and medical staff, so that the types of heart abnormalities By determining a model and supporting a more accurate decision on cardiovascular disease based on the evaluation of the determined type of heart disease model, it is possible to provide customized medical services and support decision-making related to heart disease.

According to an embodiment of the present invention, the living indoor monitoring system 110 acquires a 3D image for analyzing the daily life pattern of the support subject through a 3D camera to detect the fall accident of the support subject, and a smart band worn by the support subject can be used to provide biosignal monitoring and real-time cardiac abnormality evaluation functions.

According to an embodiment of the present invention, the heart condition monitoring system 120 transmits the transmitted data to the server in real time while monitoring the ECG, pulse wave, motion, and body temperature of the support target using a heart condition detection sensor, and transmits the transmitted data to the user terminal device. can be provided to

According to an embodiment of the present invention, the complex life support solution providing system 100 may include a biosignal measuring device, a gateway, a server, and a user terminal device.

As an example, the biosignal measuring apparatus may measure a biosignal including at least one of an electrocardiogram signal, a motion signal, and a pulse wave signal from a support target, and transmit monitoring information including the measured biosignal.

Also, the gateway may transmit monitoring information to the server.

In addition, the server may extract an electrocardiogram signal of the biosignal from monitoring information transmitted from the biosignal measuring device, and extract morphological information through conversion of the extracted electrocardiogram signal into a time-standardized image as feature information.

In addition, the server determines a plurality of cardiac abnormality type models by using the extracted characteristic information, calculates classification accuracy for the plurality of determined cardiac abnormality type models, and based on the calculated accuracy, the determined cardiac abnormality type model and the published It is possible to determine whether the support target has a cardiovascular disease or an emergency state using the cardiovascular disease data, and feed back information on the determined cardiovascular disease and the emergency state and information on fluctuations in biosignals to the user terminal device.

According to an embodiment of the present invention, the user terminal device may include at least one of a medical staff terminal device, a guardian terminal device, and an emergency center terminal device.

In addition, the user terminal device outputs information including at least one of information on the determined cardiovascular disease and emergency status and biosignal variation information, and based on the prescription information generated according to the information output to the medical staff terminal device Prescribing information may also be updated in the guardian terminal device and the emergency center terminal device.

For example, the support target may correspond to at least one of the elderly living alone, the disabled, the critically ill, and the young patient.

Therefore, the complex life support solution providing system 100 may provide a complex life support solution in a facility for at least one of ward monitoring, a nursing hospital, and a silver town for health management of the elderly living alone.

In addition, the complex life support solution providing system 100 can improve the health management of the elderly living alone, emergency detection and prevention of sudden and lonely death, and increase the efficiency of hospital patient management based on monitoring of nursing hospitals and general wards.

Therefore, the complex life support solution providing system 100 can prevent sudden and lonely death for the elderly living alone, and provide heart health management for the elderly living alone, prevention of chronic diseases for the elderly living alone, and rapid patient transport and treatment in emergency situations.

Hereinafter, components of the heart condition monitoring system 120 will be further described with reference to FIG. 2 .

2 illustrates components of a heart condition monitoring system in a system for providing a complex life support solution according to an embodiment of the present invention.

Referring to FIG. 2 , the heart condition monitoring system 200 may include a biosignal measuring device 210 , a gateway 220 , a server 230 , and a user terminal device 240 .

According to an embodiment of the present invention, the bio-signal measuring device 220 measures bio-signals including an electrocardiogram signal, a motion signal, and a body temperature signal from a subject to be supported, and compresses and encrypts the measured bio-signal with an artificial intelligence encoder to reduce power consumption. It is transmitted to the gateway 220 using Bluetooth.

For example, as a pre-processing process for applying the measured bio-signal to the deep learning model, the artificial intelligence encoder can divide and normalize the bio-signal into signals having the same length through sliding window technology.

For example, the length of the window may be 2 seconds, and the update period may be 1 second.

Here, the sliding window can analyze a signal with a relatively short measurement time, and through a normalization process, various signal amplitudes and offsets can be set so that the deep learning model does not affect it. In addition, the configuration of the artificial intelligence encoder will be described supplementally with reference to FIG.

The gateway 220 transmits the transmitted signal to the server 230 .

The gateway 220 interworks with the heart condition sensor device 220 and the server 220, supports environment settings such as hospital, ward, bed number of the server 230, and data collection and storage for each patient, and low battery It supports event (battery low event) transmission and process monitoring and automatic fail over (fail over).

In addition, the gateway 220 supports automatic node search, registration, and connection of the heart condition detection sensor device 220 , and supports a low-power Bluetooth communication interface and a battery level check of the heart condition detection sensor 220 .

The server 230 extracts the bio-signals measured by the heart condition detection sensor device 220 with an artificial intelligence decoder, and machine learning and analyzing the ECG signals of the extracted bio-signals using a pre-stored artificial intelligence algorithm, so that various environments Performs heart condition detection performance optimization using the public biosignal data set measured in Model learning and performance evaluation can be performed on the measured biosignals.

In addition, the server 230 uses morphological information through conversion of the ECG signal into a time-standardized image as feature information in order to reflect various patterns of the ECG signal in the risk assessment model based on the artificial intelligence algorithm.

For example, the server 230 uses machine learning models such as Convolutional Neural Network (CNN) and Deep Belief Network (DBN), or by using various machine learning techniques such as Gradient Boost and XGBooST, corresponding to major cardiovascular diseases. A sub-classification model can be determined to classify myocardial infarction, coronary artery disease, and the like.

In addition, the server 230 calculates the accuracy of the classification model by comparing the results using machine learning techniques such as support vector machine (SVM) and random forest (RF) based on the public biosignal dataset, and the effectiveness of the classification model can also be evaluated.

In addition, the server 230 determines a cardiovascular disease related to the heart condition of the support target that is learned and analyzed using an artificial intelligence algorithm, and provides the determined cardiovascular disease and analysis result to the user terminal device 240 to provide medical staff It may assist in diagnosing cardiovascular disease or assist in recognizing changes in the patient's prognosis.

Therefore, the present invention is a classification model of major cardiovascular diseases such as myocardial infarction and coronary artery disease based on a biosignal measuring device attached to a patient to detect the patient's condition and a server using an artificial intelligence algorithm for biosignals related to the heart condition. can be determined, and based on the determined major cardiovascular disease classification model, a doctor's misdiagnosis and occurrence of false alarms can be prevented.

In addition, the present invention can provide a complex life support solution including a remote medical service in preparation for the post-corona era.

3 is a view for explaining the components of a biosignal measuring apparatus according to an embodiment of the present invention.

3 illustrates components of a biosignal measuring device included in a system for providing a complex life support solution according to an embodiment of the present invention.

Referring to FIG. 3 , the biosignal measuring apparatus 300 includes a biosignal monitoring unit 310 and a controller 320 .

According to an embodiment of the present invention, the biosignal measuring apparatus 300 is attached to the upper part of the heart of or near the heart of the support person to measure data related to the heart condition from the support person, or is worn in the form of a band on the user's wrist in the form of a wearable device. to measure data related to the condition of the heart.

In addition, the biosignal measuring device 300 includes a 3D depth camera for taking 3D depth images for analysis of daily life patterns, a smart band wearable on at least one of the ear, neck, or wrist of the support target, and a heart condition detection sensor device can do.

For example, the bio-signal monitoring unit 310 measures a bio-signal including at least one of a 3D depth image, an electrocardiogram signal, a pulse wave signal, a body temperature signal, and a movement signal from a subject to be supported, and monitoring information including the measured bio-signal can be output through an artificial intelligence encoder.

According to an embodiment of the present invention, the bio-signal monitoring unit 310 encodes and compresses the heart state information according to the change in the heart state of the support subject and the movement state information according to the change in the movement of the support subject through the artificial intelligence encoder, and outputs it can do.

According to an embodiment of the present invention, the biosignal monitoring unit 310 monitors the body reaction and body temperature by Actigraph measured from at least one of the ear, neck, or wrist as a biosignal, and Motion signals and body temperature signals can be encoded and output through an artificial intelligence encoder.

As an example, the biosignal monitoring unit 310 monitors a neural response by PPG (photoplethysmography) measured from at least one of an ear, neck, or wrist as a biosignal, and uses an artificial intelligence encoder to generate autonomic neural information according to the neural response. It can be encrypted and printed.

For example, the controller 330 may transmit the monitoring information to the server through a gateway located nearby using short-range wireless communication.

According to an embodiment of the present invention, the controller 330 extracts the ECG signal included in the monitoring information by the server, and converts the extracted ECG signal to a time-standardized image based on a pre-stored artificial intelligence machine learning algorithm. Morphological information is extracted as characteristic information, a plurality of cardiac abnormality type models are determined using the extracted characteristic information, classification accuracy for the determined plurality of cardiac abnormality type models is calculated, and a heart determined based on the calculated accuracy Monitoring information may be provided to the server to determine the cardiovascular disease of the support target using the abnormal type model and the published cardiovascular disease data.

For example, the controller 330 simulates data traffic generated when measuring at least one of a 3D depth image, an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal, and based on the simulation, the operating state of the biosignal measuring device can determine

For example, the controller 330 may periodically check the battery state, determine the low battery state, and provide alarm information.

According to an embodiment of the present invention, the control unit 330 provides monitoring information to the server to detect an emergency including cardiac arrest and a fall of a subject to be supported based on a 3D depth image, an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal. can do.

According to an embodiment of the present invention, the biosignal measuring apparatus 300 may further include an artificial intelligence processing unit 320 .

For example, the artificial intelligence processing unit 320 extracts an electrocardiogram signal included in the monitoring information output from the biosignal monitoring unit 310, and based on a pre-stored artificial intelligence machine learning algorithm, the time standardized Extracts morphological information through transformation into images as characteristic information, determines a plurality of cardiac abnormality types models using the extracted characteristic information, calculates classification accuracy for the determined multiple cardiac abnormality types models, and calculates the calculated The user's cardiovascular disease can be determined using the heart abnormality type model determined based on the accuracy and the published cardiovascular disease data.

For example, the artificial intelligence processing unit 320 may automatically calculate the classification accuracy by comparing the open data set and the heart abnormality type model based on the artificial intelligence learning technology.

For example, the artificial intelligence processing unit 320 may include a convolutional product neural network layer and a bidirectional long short-term memory (BLSTM) layer.

According to an embodiment of the present invention, the artificial intelligence processing unit 320 has the same information processing function as the artificial intelligence processing unit of the server to be described in FIG. 8, so that learning and analysis based on the artificial intelligence machine learning algorithm is possible.

That is, the biosignal measuring apparatus 300 according to an embodiment of the present invention may provide monitoring information information for classifying left-angle blockage, right-angle blockage, atrial premature contraction and ventricular premature contraction related to arrhythmias to the server side.

In addition, the biosignal measuring device 300 according to an embodiment of the present invention provides separate information by machine learning monitoring information on its own to classify left-angle block, right-angle block, atrial premature contraction, and ventricular premature contraction related to arrhythmias. can do.

Therefore, the present invention transmits emergency situation information and basic bio-signal information to the medical staff and emergency center of the nursing hospital when an emergency such as cardiac arrest or a fall is detected, and an external related institution receives the analysis data in real time, so that the patient's emergency We can provide a complex life support solution that prepares for the situation.

In addition, the present invention can reduce the number of false alarms that can be generated in a hospital room by accurately measuring and analyzing the patient's current condition, thereby improving the work efficiency of medical staff and the patient's prognosis.

4 is a diagram illustrating a deep learning model related to an artificial intelligence encoder of a heart condition detection sensor device according to an embodiment of the present invention.

Referring to FIG. 4 , the artificial intelligence encoder 400 is composed of an encoding block 410 and a deep learning neural network 420 , and the encoding block 410 is a deep learning neural network layer, a pooling layer, and a reshape ) can be composed of layers.

The artificial intelligence encoder 400 according to an embodiment of the present invention may compress a signal for morphological information through conversion of an electrocardiogram signal into a time-standardized image, and output the compressed signal as monitoring information.

For example, the artificial intelligence encoder 400 may be composed of a convolutional product neural network layer and a bidirectional long-term short-term memory layer.

For example, the artificial intelligence encoder 400 may provide signal information compressed by about 64 times to the artificial intelligence processing unit of the heart condition detection sensor device or the artificial intelligence processing unit of the server.

For example, morphological information through transformation into a temporal normalized image may be generated based on a signal divided and normalized into a signal having the same length through a sliding window technique.

5A and 5B are diagrams for explaining a heart condition sensor device among biosignal measuring devices according to an embodiment of the present invention.

5A illustrates a case in which the heart condition detection sensor device 500 according to an embodiment of the present invention includes three leads, and each lead is connected to and worn by a user.

Referring to FIG. 5A , the heart condition detection sensor device 500 is configured by connecting three leads. The first lead is positioned in the heart condition sensor device 500 , and the second lead 510 is located in two parts of the user's body. and the third lead 512 are made of an adhesive material and are attached to the user's skin.

For example, the heart condition detection sensor device 500 may be a main body of the heart condition detection sensor device, a first lead corresponding to one measurement point is positioned, and a second lead 510 and a third lead 512 are connected to each other. Biosignals can be measured by synthesizing the measured information.

According to an embodiment of the present invention, the heart condition sensor device 500 includes a power supply unit, a sensor, and a first lead, and the sensor may measure an electrocardiogram (ECG), a physical activity measurement (Actigraph), and a body temperature.

For example, the second lead 510 and the third lead 512 may be connected to the heart condition detection sensor device 500 through a covering wire.

As an example, the heart condition detection sensor device 500 may monitor a heart condition by an electrocardiogram (ECG) measured as a biosignal, and compress and encode an electrocardiogram signal according to the heart condition through an artificial intelligence encoder to output it.

For example, the heart condition sensor device 500 may monitor a body reaction by measuring a physical activity measured as a biosignal, and may compress and encode a motion signal according to the body reaction through an artificial intelligence encoder and output it.

For example, the heart condition detection sensor device 500 may compress and encrypt a body temperature signal measured as a biosignal through an artificial intelligence encoder and output it.

5B illustrates a case in which the heart condition detection sensor device 520 according to an embodiment of the present invention is composed of one lead and is worn by the user.

Referring to FIG. 5B , the heart condition detection sensor device 520 may have a wristband type wearable device shape.

According to an embodiment of the present invention, the heart condition sensor device 520 includes a power supply unit, a sensor, and a lead, and the sensor may measure an electrocardiogram (ECG), a physical activity measurement (Actigraph), and a body temperature.

For example, the heart condition detection sensor device 520 may monitor a heart condition by an electrocardiogram (ECG) measured as a biosignal, and compress and encrypt an electrocardiogram signal according to the heart condition through an artificial intelligence encoder and output it.

For example, the heart condition detection sensor device 520 may monitor a body reaction by measuring physical activity measured as a biosignal, and may compress and encode a motion signal according to the body reaction through an artificial intelligence encoder and output it.

As an example, the heart condition detection sensor device 520 may compress and encrypt a body temperature signal measured as a biosignal through an artificial intelligence encoder and output it.

According to an embodiment of the present invention, the heart condition detection sensor device 500 and the heart condition detection sensor device 520 convert the measured ECG signal into a heart condition analysis technology for real-time arrhythmia detection, and biosignal quality for enhancing signal analysis reliability. It can be provided as data that can be applied to management AI technology and major cardiovascular disease evaluation AI technology for early disease management.

For example, the heart condition detection sensor device 500 performs relatively more accurate cardiac function monitoring than the heart condition detection sensor device 520 , and the heart condition detection sensor device 520 is more user-friendly than the heart condition detection sensor device 500 . Cardiac function monitoring can be performed while enjoying a convenient daily life.

6 is a view for explaining additional components of a heart condition detection sensor device among the biosignal measuring device according to an embodiment of the present invention.

Referring to FIG. 6 , the heart state detection sensor device 600 includes a micro USB port 610 , a lithium polymer battery 620 , a power/action switch 630 , an ECG sensor 640 , and an acceleration/angular velocity sensor 650 . and low-power Bluetooth/Wi-Fi 660 , and controls the above-described device components through the microcontroller 670 .

According to an embodiment of the present invention, the heart condition sensor device 600 may charge the lithium polymer battery 620 using the micro USB port 610 .

For example, the power/action switch 630 may operate the heart condition detection sensor device 600 when receiving a push input from a support target.

For example, the ECG sensor 640 measures the ECG signal of the support subject, and the acceleration/angular velocity sensor 650 measures the movement signal of the support subject.

According to an embodiment of the present invention, the heart state detection sensor device 600 controls the low-power Bluetooth/Wi-Fi 660 to interwork with a gateway located in a hospital room or home, and an ECG sensor 640 and an acceleration/angular velocity sensor 650 ), the measured ECG signal and movement signal can be transmitted to the server through the gateway.

7 is a view for explaining the flow of major events of biosignal measurement and data transmission according to an embodiment of the present invention.

Referring to FIG. 7 , the biosignal monitoring unit may measure High Resolution/Speed ECG through the ECG sensor 710 . In addition, a resolution of 14 bits or more and 100Hz sampled ECG may be A/D converted through the AD converter 720 .

In addition, the microcontroller 730 is responsible for signal processing along with overall control of each component, and the low-power Bluetooth/Wi-Fi module 740 provides a short-range wireless communication function or connects to a network to enable wired/wireless data communication . In particular, in the present invention, it is possible to transmit raw data of the ECG and 6-Axis MEMS sensors using the low-power Bluetooth/Wi-Fi module 740 .

On the other hand, reference numeral 750 performs a function of a battery status measurement module for measuring the state of the battery for the device, reference numeral 760 denotes a 3-axis accelerometer, and reference numeral 770 denotes a 3-axis gyroscope ( 3-Axis Gyroscope MEMS Motiontracking).

The 3-Axis Accelerometer and 3-Axis Gyroscope MEMS Motiontracking can measure the minimum ±16g range, 16bit 100Hz angular velocity, and the maximum ±2000dps range, 16bit 100Hz angular velocity .

8 is a view for explaining the components of a server according to an embodiment of the present invention.

8 illustrates the components of a server included in the complex life support solution providing system according to an embodiment of the present invention.

Referring to FIG. 8 , the server 800 includes a monitoring information collection unit 810 , a signal extraction unit 820 , an artificial intelligence processing unit 830 , and a control unit 840 .

According to an embodiment of the present invention, the server 800 may provide status information of a subject to be supported by interworking with the biosignal measuring device.

As an example, the monitoring information collecting unit 810 may collect monitoring information including biosignals including electrocardiogram signals and movement signals measured from the support subject.

For example, the monitoring information collecting unit 810 may collect monitoring information transmitted by the biosignal measuring device through a gateway.

For example, the biosignal may be interpreted as a signal measured by the biosignal measuring device attached to the heart of the support subject or through a lead worn on the wrist.

In addition, the biosignal is a signal that the biosignal measurement device monitors the body reaction by the physical activity measurement (Actigraph) measured from at least one of the ear, neck, or wrist of the subject and the nerve reaction by PPG (photoplethysmography) is monitored. It may contain signals.

According to an embodiment of the present invention, the signal extraction unit 820 may extract an electrocardiogram signal for analyzing the heart condition of the support target by using an artificial intelligence algorithm from the transmitted monitoring information.

For example, the signal extractor 820 may decode the collected monitoring information and extract a biosignal corresponding to the ECG signal from the monitoring information.

Also, the signal extractor 820 may convert the biosignal encrypted and compressed by the biosignal measuring device using an artificial intelligence encoder into a biosignal using an artificial intelligence decoder.

According to an embodiment of the present invention, the artificial intelligence processing unit 830 extracts a time domain and a frequency domain of the ECG signal extracted based on a pre-stored artificial intelligence machine learning algorithm as feature information, A plurality of cardiac abnormality type models are determined using the extracted characteristic information, classification accuracy of the plurality of determined cardiac abnormality type models is calculated, and the determined cardiac abnormality type model and published cardiovascular disease data based on the calculated accuracy. can be used to determine the cardiovascular disease of the recipient.

Specifically, the artificial intelligence processing unit 830 divides a frequency domain into specific time intervals based on a time domain, and normalizes the divided frequency domain to a binary number to generate a normalized signal. The generated normalized signal is converted into an image, a compressed signal is generated by applying a weight based on a pre-stored artificial intelligence machine learning algorithm to the converted image, a restored signal is generated from the compressed signal using the applied weight, and the generated By machine learning the weight so that the difference between the normalized signal and the generated reconstructed signal falls within a preset threshold range, feature information corresponding to the morphological feature of the electrocardiogram signal may be extracted.

In addition, the artificial intelligence processing unit 830 machine-learning the characteristic information to generate a plurality of cardiac abnormality type models: a tachycardia model, a bradycardia model, an atrial fibrillation model, a left-brain block model, a right-angle block model, atrial premature contraction model, a ventricular premature contraction model, and at least one of the cardiac arrest models.

For example, the artificial intelligence processing unit 830 may calculate classification accuracy with respect to the determined plurality of heart abnormality type models.

Specifically, the artificial intelligence processing unit 830 may calculate classification accuracy for a plurality of heart abnormality type models based on Equation 1 below.

[Equation 1]

Accuracy = (TP + TN)/(TP + TN + FP + FN)

In Equation 1, TP may represent a case in which an abnormal state is accurately classified into an abnormal state, TN may represent a case in which a normal state is divided into a normal state, and FP may represent a case in which a normal state is classified as an abnormal state. , and FN may indicate a case in which a normal state is divided into an abnormal state.

According to an embodiment of the present invention, the artificial intelligence processing unit 830 includes at least one of an open data set, a tachycardia model, a bradycardia model, an atrial fibrillation model, a left-angle block model, a right-angle block model, atrial premature contraction model, and a ventricular premature contraction model. TP (True Positive) that classifies cardiac abnormalities as cardiac abnormalities using a model and a normal heart condition model, FN (False Negative) cases that distinguish cardiac abnormalities as normal, and FP (False Positive) that distinguishes normal as cardiac abnormalities It is classified as a TN (True Negative) case that classifies normal and normal cases.

Next, the artificial intelligence processing unit 830 is a TP for a combination of a numerical value in the case of TP (True Positive), a numerical value in the case of FN (False Negative), a numerical value in the case of FP (False Positive), and a numerical value in the case of TN (True Negative). Tachycardia model, bradycardia model, atrial fibrillation model, left-angle block model, right-angle block model, atrial premature contraction model, and ventricular premature contraction model based on the ratio of the combination of the values in the (True Positive) case and the values in the TN (True Negative) case. Classification accuracy for at least one of them may be calculated.

In addition, the artificial intelligence processing unit 830 uses an open data set, a cardiac arrest model, and a normal heart state model to divide a cardiac arrest section into a cardiac arrest section in a TP (True Positive) case that divides the cardiac arrest section into a normal section (False Negative FN). ), it can be classified into a false positive (FP) case in which a normal section is divided into a cardiac arrest section and a true negative (TN) case in which a normal section is divided into a normal section.

Next, the artificial intelligence processing unit 830 is a TP for a combination of a numerical value in the case of TP (True Positive), a numerical value in the FN (False Negative) case, a numerical value in the FP (False Positive) case, and a numerical value in the TN (True Negative) case. The emergency classification accuracy can be calculated based on the ratio of the combination of the numerical value in the (True Positive) case and the numerical value in the TN (True Negative) case.

In addition, the artificial intelligence processing unit 830 is configured to divide an artifact signal into the artifact signal in a True Positive (TP) case, in a FN (False Negative) case in which an artifact signal is classified as a normal signal, and in a FP (False) case that classifies a normal signal into an artifact signal. Positive), it is classified as a TN (True Negative) case that classifies a normal signal as a normal signal, and the TP (True Positive) case, FN (False Negative) case, FP (False Positive) case, and TN Artifact removal accuracy can be calculated based on the ratio of the combination of the numerical value in the TP (True Positive) case and the numerical value in the TN (True Negative) case to the combination of the values in the (True Negative) case.

For example, the artificial intelligence processing unit 830 may automatically calculate the classification accuracy by comparing the open data set and the heart abnormality type model based on the artificial intelligence learning technology.

According to an embodiment of the present invention, the artificial intelligence processing unit 830 manages the signal quality of the biosignals transmitted from the biosignal measuring device, including signal quality management artificial intelligence, arrhythmia detection artificial intelligence, and cardiovascular disease evaluation artificial intelligence. , can evaluate and detect arrhythmias and cardiovascular diseases.

According to an embodiment of the present invention, the control unit 840 may control to provide the cardiovascular disease determined by the artificial intelligence processing unit 830 to the user terminal device. Here, the controlled device may correspond to a communication device.

For example, the user terminal device may receive analysis information related to cardiovascular disease, and provide cardiovascular disease determination information and analysis results included in the received analysis information through a display.

According to an embodiment of the present invention, after at least one of an electrocardiogram signal and a motion signal is measured, the controller 840 calculates the number of measured electrocardiogram signals and the number of measured motion signals, and calculates the number of electrocardiogram signals and The data reception state of the ECG signal and the motion signal may be checked by comparing the calculated number of motion signals with a threshold value.

Also, when the reception state of the electrocardiogram signal and the motion signal is poor, the controller 840 may request additional data or additional measurement from the biosignal measuring device.

In addition, the controller 840 may control to feed back at least one of information on whether a cardiovascular disease or an emergency state and information on changes in biosignals to the user terminal device.

9 is a view for explaining an operation method of a system for providing a complex life support solution according to an embodiment of the present invention.

9 is a view showing the cardiovascular disease of the support target after the system for providing a complex life support solution according to an embodiment of the present invention learns and analyzes the bio-signals measured using the bio-signal measuring device using a pre-stored artificial intelligence algorithm. An embodiment of providing a complex life support solution by feeding back at least one of information on whether there is an emergency and information on changes in biosignals to a user terminal device will be described.

Referring to FIG. 9 , in the operating method of the system for providing a complex life support solution according to an embodiment of the present invention, in step 901 , a biosignal of a support target is measured.

In other words, the operation method of the complex life support solution providing system uses a bio-signal measuring device attached to the upper side of the support subject's heart and a bio-signal measuring device worn on at least one of the support subject's ear, neck, or wrist to obtain an electrocardiogram signal, movement A biosignal including a signal, a body temperature signal, and a pulse wave signal is measured.

In the operation method of the system for providing a complex life support solution according to an embodiment of the present invention in step 902, the monitoring information including the biosignal measured in step 901 is transmitted to the server.

That is, the operation method of the complex life support solution providing system generates monitoring information by encrypting and compressing bio-signals including an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal using an artificial intelligence encoder, and the generated monitoring information is sent to the server through an adjacent gateway.

In step 903, the operation method of the complex life support solution providing system determines a heart abnormality type model based on an artificial intelligence machine learning algorithm, and calculates a degree of classification based on the cardiac abnormality type model.

Specifically, the operation method of the complex life support solution providing system is based on an artificial intelligence machine learning algorithm pre-stored in the converted image by converting a normalized signal generated based on the time domain of the electrocardiogram signal into a time standardized image. A compressed signal is generated by applying a weight, a reconstructed signal is generated from the compressed signal using the applied weight, and the weight is machine learned so that the difference between the generated normalized signal and the generated reconstructed signal falls within a preset threshold range to obtain an ECG signal It is possible to extract feature information corresponding to the morphological features of

In addition, the operation method of the complex life support solution providing system is a tachycardia model, bradycardia model, atrial fibrillation model, left leg block model, right leg block model, atrial premature contraction model, It can be determined with a ventricular premature contraction model, a normal heart condition model, and a cardiac arrest model.

In addition, the operation method of the complex life support solution providing system calculates classification accuracy for a plurality of cardiac abnormality type models.

That is, the operating method of the complex life support solution providing system may quantify the classification accuracy of the plurality of cardiac abnormality type models according to the determination result of the plurality of cardiac abnormality type models.

Specifically, the operation method of the complex life support solution providing system is TP (True Positive), which classifies cardiac abnormalities as cardiac abnormalities, and FN (False Negative) cases, which classifies cardiac abnormalities as normal, for each of a plurality of cardiac abnormality type models. , It is divided into four types of cases corresponding to FP (False Positive), which classifies normal as cardiac abnormality, and TN (True Negative), which classifies normal as normal.

In addition, the operation method of the complex life support solution providing system depends on the combination of the numerical values in the case of TP (True Positive), FN (False Negative), FP (False Positive), and TN (True Negative). The classification accuracy is calculated based on the ratio of the combination of the values in the TP (True Positive) case and the TN (True Negative) case.

In addition, the operation method of the complex life support solution providing system is the calculated classification accuracy, and the classification accuracy of cardiac abnormalities related to tachycardia, bradycardia, atrial fibrillation, left-brain block, right-angle block, atrial premature contraction, and ventricular premature contraction is the threshold value. If higher, the type of cardiac abnormality is determined as at least one of tachycardia, bradycardia, atrial fibrillation, left-angle block, right-angle block, atrial premature contraction, and ventricular premature contraction, an emergency situation related to cardiac arrest is determined, and artifact is removed based on the artifact removal probability. The removal rate can be determined.

In step 904 , the operating method of the system for providing a complex life support solution according to an embodiment of the present invention determines a cardiovascular disease using accuracy, a heart abnormality type model, and published cardiovascular disease data.

That is, the operation method of the complex life support solution providing system is based on the accuracy calculated in step 903 , the cardiac abnormality type model determined in step 903 and the cardiovascular disease data published as public data are compared and analyzed to measure biosignals Cardiovascular disease of the support subject wearing the device may be determined.

In step 905, the operating method of the system for providing a complex life support solution according to an embodiment of the present invention may feed back biosignal variation information, cardiovascular disease, and emergency status to the user terminal device.

In step 906 , the method of operating the complex life support solution providing system according to an embodiment of the present invention may display feedback information and provide alarm feedback according to the feedback information.

That is, the operating method of the system for providing a complex life support solution according to an embodiment of the present invention outputs information including at least one of information on the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignals, Based on the prescription information generated according to the information output to the medical staff terminal device, the prescription information may also be updated in the guardian terminal device and the emergency center terminal device.

In addition, the operation method of the system for providing a complex life support solution according to an embodiment of the present invention is based on the determined information on the cardiovascular disease and emergency status and the change information of the bio-signal, the patient's nursing management service, disease data management At least one of a service, a disease data visualization, a disease data statistical service, and an emergency push notification service may be provided.

Therefore, the present invention can detect the heart condition of a patient so that a heart condition analysis for real-time arrhythmia detection, biosignal quality control for improving signal analysis reliability, and major cardiovascular disease evaluation for early disease management can be performed.

In addition, the present invention provides tachycardia, bradycardia, atrial fibrillation, left-angle block, right-angle block, It can detect major types of cardiac abnormalities such as atrial premature contraction, ventricular premature contraction, and cardiac arrest.

In addition, the present invention is a biosignal measuring device that is attached to a patient and detects the patient's heart condition by calculating cardiac function abnormality classification accuracy, emergency situation classification accuracy, and artifact signal detection accuracy using a pre-stored artificial intelligence algorithm and open data set. By learning and evaluating the measurement accuracy of the bio-signal measured from the , it is possible to improve the measurement accuracy of the bio-signal.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

Software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or apparatus, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with reference to the limited drawings, various modifications and variations are possible by those skilled in the art from the above description. For example, the described techniques are performed in an order different from the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (20)

In the complex life support solution providing system,
A biosignal including at least one of an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal of a support subject, including a neural response by PPG (photoplethysmography) measured from at least one of the support subject's ear, neck, or wrist a gateway for transmitting monitoring information to the server; and
Extracting the ECG signal of the biosignal from the transmitted monitoring information, and extracting the morphological information through conversion of the extracted ECG signal into a time-standardized image based on a pre-stored artificial intelligence machine learning algorithm as feature information, , determine a plurality of cardiac abnormality type models using the extracted characteristic information, calculate classification accuracy for the plurality of determined cardiac abnormality type models, and disclose the determined cardiac abnormality type model and the based on the calculated accuracy Determining whether the support target has a cardiovascular disease or an emergency state using the obtained cardiovascular disease data, and feeds back information on the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal to a user terminal device containing the server
Complex life support solution provision system. According to claim 1,
The user terminal device includes at least one of a medical staff terminal device, a guardian terminal device, and an emergency center terminal device,
The user terminal device outputs information including at least one of information on whether the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal,
Based on the prescription information generated according to the information output to the medical staff terminal device, the prescription information is also updated in the guardian terminal device and the emergency center terminal device
Complex life support solution provision system. 3. The method of claim 2,
The user terminal device includes a nursing management service, a disease data management service, a disease data visualization, a disease data statistical service and providing at least one of the emergency push notification services
Complex life support solution provision system. According to claim 1,
The server may include: a monitoring information collection unit configured to collect monitoring information including biosignals including 3D depth images, electrocardiogram signals, motion signals, body temperature signals, and pulse wave signals measured from the support subject;
a signal extraction unit for extracting an electrocardiogram signal included in the transmitted monitoring information;
Based on a pre-stored artificial intelligence machine learning algorithm, the morphological information through the conversion of the extracted ECG signal into a time-standardized image is extracted as feature information, and a plurality of cardiac abnormality types models are generated using the extracted feature information. determining, calculating the classification accuracy for the plurality of heart abnormality type models determined, and using the determined cardiac abnormality type model and published cardiovascular disease data based on the calculated accuracy to determine the cardiovascular disease and Artificial intelligence processing unit to determine whether there is an emergency; and
and a controller configured to control to feed back at least one of the determined information on the cardiovascular disease and the emergency state and information on fluctuations in the biosignal to the user terminal device.
Complex life support solution provision system. 5. The method of claim 4,
The artificial intelligence processing unit generates a normalized signal based on a time domain of the extracted electrocardiogram signal, converts the generated normalized signal into the time normalized image, and the artificial intelligence stored in the converted image in advance. A compressed signal is generated by applying a weight based on an intelligent machine learning algorithm, a restored signal is generated from the compressed signal using the applied weight, and the difference between the generated normalized signal and the generated restored signal is in a preset threshold range. Characterized in extracting the morphological information of the electrocardiogram signal as the feature information by machine learning the weight so as to correspond to it
Complex life support solution provision system. 5. The method of claim 4,
The artificial intelligence processing unit machine-learns the characteristic information and converts the plurality of heart abnormality type models into a tachycardia model, bradycardia model, atrial fibrillation model, left-angle block model, right-angle block model, atrial premature contraction model, ventricular premature contraction model, cardiac arrest model and determining as at least one model of a normal heart state model.
Complex life support solution provision system. 7. The method of claim 6,
The artificial intelligence processing unit includes at least one of an open data set and the tachycardia model, the bradycardia model, the atrial fibrillation model, the left-angle block model, the right-angle block model, the atrial premature contraction model, and the ventricular premature contraction model; In the case of TP (True Positive) that classifies the cardiac abnormality as the cardiac abnormality using a normal heart condition model, and the FN (False Negative) case that classifies the cardiac abnormality as the normal, FP (False) that classifies the normal as the cardiac abnormality Positive) case and TN (True Negative) case that classifies the normal into the normal, the TP (True Positive) case, the FN (False Negative) case, the FP (False Positive) case The tachycardia model, the bradycardia model, the tachycardia model based on the ratio of the combination of the TP (True Positive) value and the TN (True Negative) case value to the combination of the numerical value and the TN (True Negative) case value. Characterized in calculating the classification accuracy for at least one of the atrial fibrillation model, the left-angle block model, the right-angle block model, the atrial premature contraction model, and the ventricular premature contraction model
Complex life support solution provision system. In the complex life support solution providing system,
a gateway for transmitting monitoring information including a biosignal including at least one of an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal of a subject to be supported to a server;
Extracting the ECG signal of the biosignal from the transmitted monitoring information, and extracting the morphological information through conversion of the extracted ECG signal into a time-standardized image based on a pre-stored artificial intelligence machine learning algorithm as feature information, , determine a plurality of cardiac abnormality type models using the extracted characteristic information, calculate classification accuracy for the plurality of determined cardiac abnormality type models, and disclose the determined cardiac abnormality type model and the based on the calculated accuracy Determining whether the support target has a cardiovascular disease or an emergency state using the obtained cardiovascular disease data, and feeds back information on the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal to a user terminal device including the server;
The server may include: a monitoring information collection unit configured to collect monitoring information including biosignals including 3D depth images, electrocardiogram signals, motion signals, body temperature signals, and pulse wave signals measured from the support subject;
a signal extraction unit for extracting an electrocardiogram signal included in the transmitted monitoring information;
Based on a pre-stored artificial intelligence machine learning algorithm, the morphological information through the conversion of the extracted ECG signal into a time-standardized image is extracted as feature information, and a plurality of cardiac abnormality types models are generated using the extracted feature information. determining, calculating the classification accuracy for the plurality of heart abnormality type models determined, and using the determined cardiac abnormality type model and published cardiovascular disease data based on the calculated accuracy to determine the cardiovascular disease and Artificial intelligence processing unit to determine whether there is an emergency; and
and a control unit controlling to feed back at least one of information on the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal to the user terminal device,
The artificial intelligence processing unit machine-learns the characteristic information and converts the plurality of heart abnormality type models into a tachycardia model, bradycardia model, atrial fibrillation model, left-angle block model, right-angle block model, atrial premature contraction model, ventricular premature contraction model, cardiac arrest model and at least one model of a normal heart condition model,
The artificial intelligence processing unit uses an open data set, the cardiac arrest model, and the normal heart state model to divide the cardiac arrest section into the cardiac arrest section (True Positive) (TP), which divides the cardiac arrest section into a normal section (False Negative FN) ), classifying the FP (false positive) case that divides the normal section into the cardiac arrest section and the TN (True Negative) case that classifies the normal section into the normal section, the TP (True Positive) case, The TN (True Negative) case and the TP (True Positive) case for the combination of the FN (False Negative) case, the FP (False Positive) case, and the TN (True Negative) case. Characterized in calculating the emergency classification accuracy based on the ratio of the combination of the numerical values of
Complex life support solution provision system. In the complex life support solution providing system,
a gateway for transmitting monitoring information including a biosignal including at least one of an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal of a subject to be supported to a server;
Extracting the ECG signal of the biosignal from the transmitted monitoring information, and extracting the morphological information through conversion of the extracted ECG signal into a time-standardized image based on a pre-stored artificial intelligence machine learning algorithm as feature information, , determine a plurality of cardiac abnormality type models using the extracted characteristic information, calculate classification accuracy for the plurality of determined cardiac abnormality type models, and disclose the determined cardiac abnormality type model and the based on the calculated accuracy Determining whether the support target has a cardiovascular disease or an emergency state using the obtained cardiovascular disease data, and feeds back information on the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal to a user terminal device including the server;
The server may include: a monitoring information collection unit configured to collect monitoring information including biosignals including 3D depth images, electrocardiogram signals, motion signals, body temperature signals, and pulse wave signals measured from the support subject;
a signal extraction unit for extracting an electrocardiogram signal included in the transmitted monitoring information;
Based on a pre-stored artificial intelligence machine learning algorithm, the morphological information through the conversion of the extracted ECG signal into a time-standardized image is extracted as feature information, and a plurality of cardiac abnormality types models are generated using the extracted feature information. determining, calculating the classification accuracy for the plurality of heart abnormality type models determined, and using the determined cardiac abnormality type model and published cardiovascular disease data based on the calculated accuracy to determine the cardiovascular disease and Artificial intelligence processing unit to determine whether there is an emergency; and
and a control unit controlling to feed back at least one of information on the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal to the user terminal device,
The artificial intelligence processing unit machine-learns the characteristic information and converts the plurality of heart abnormality type models into a tachycardia model, bradycardia model, atrial fibrillation model, left-angle block model, right-angle block model, atrial premature contraction model, ventricular premature contraction model, cardiac arrest model and at least one model of a normal heart condition model,
The artificial intelligence processing unit divides the artifact signal into the artifact signal in a True Positive (TP) case, in a FN (False Negative) case in which the artifact signal is classified as a normal signal, and in a FP (False Positive) case that classifies the normal signal into the artifact signal. ), the normal signal is classified as a TN (True Negative) case for classifying the normal signal, the TP (True Positive) case, the FN (False Negative) case, and the FP (False Positive) case Artifact removal accuracy is calculated based on the ratio of the combination of the numerical value in the TP (True Positive) case and the numerical value in the TN (True Negative) case to the combination of the numerical value of , and the numerical value of the TN (True Negative) case. to do
Complex life support solution provision system. In the complex life support solution providing system,
a gateway for transmitting monitoring information including a biosignal including at least one of an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal of a subject to be supported to a server;
Extracting the ECG signal of the biosignal from the transmitted monitoring information, and extracting the morphological information through conversion of the extracted ECG signal into a time-standardized image based on a pre-stored artificial intelligence machine learning algorithm as feature information, , determine a plurality of cardiac abnormality type models using the extracted characteristic information, calculate classification accuracy for the plurality of determined cardiac abnormality type models, and disclose the determined cardiac abnormality type model and the based on the calculated accuracy Determining whether the support target has a cardiovascular disease or an emergency state using the obtained cardiovascular disease data, and feeds back information on the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal to a user terminal device including the server;
The server may include: a monitoring information collection unit configured to collect monitoring information including biosignals including 3D depth images, electrocardiogram signals, motion signals, body temperature signals, and pulse wave signals measured from the support subject;
a signal extraction unit for extracting an electrocardiogram signal included in the transmitted monitoring information;
Based on a pre-stored artificial intelligence machine learning algorithm, the morphological information through the conversion of the extracted ECG signal into a time-standardized image is extracted as feature information, and a plurality of cardiac abnormality types models are generated using the extracted feature information. determining, calculating the classification accuracy for the plurality of heart abnormality type models determined, and using the determined cardiac abnormality type model and published cardiovascular disease data based on the calculated accuracy to determine the cardiovascular disease and Artificial intelligence processing unit to determine whether there is an emergency; and
and a control unit controlling to feed back at least one of information on the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal to the user terminal device,
After at least one of the ECG signal and the motion signal is measured, the controller calculates the measured number of ECG signals and the measured number of motion signals, and calculates the number of ECG signals and the calculated motion signals. Comparing the number with a threshold value to check the data reception state of the electrocardiogram signal and the motion signal
Complex life support solution provision system. 11. The method of claim 10,
A biometric that measures a biosignal including at least one of a 3D depth image, an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal from the support subject, and outputs monitoring information including the measured biosignal through an artificial intelligence encoder signal monitoring unit and
The apparatus further comprising a biosignal measuring device including a control unit for controlling the output monitoring information to be transmitted to the server through the gateway using short-range wireless communication
Complex life support solution provision system. 12. The method of claim 11,
The bio-signal monitoring unit monitors a physical activity measurement (Actigraph) and body temperature measured from at least one of an ear, neck, or wrist as the bio-signal, and artificially generates the movement signal and body temperature signal according to the body reaction. Characterized in encoding and outputting through an intelligent encoder
Complex life support solution provision system. 12. The method of claim 11,
The biosignal monitoring unit monitors a neural response by photoplethysmography (PPG) measured from at least one of the ear, neck, or wrist as the biosignal, and encodes and outputs autonomic neural information according to the neural response through an artificial intelligence encoder. characterized by
Complex life support solution provision system. 12. The method of claim 11,
The controller simulates data traffic generated when measuring at least one of a 3D depth image, an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal, and determines an operating state of the biosignal measuring device based on the simulation;
The control unit detects an emergency including cardiac arrest and a fall of the support target based on the measured 3D depth image, an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal
Complex life support solution provision system. In the operating method of a system for providing a complex life support solution using an artificial intelligence algorithm of a server interworking with a biosignal measuring device,
In the biosignal measuring device, as a biosignal including at least one of an electrocardiogram signal, a motion signal, a body temperature signal, and a pulse wave signal from a support subject, PPG (photoplethysmography) measured from at least one of the support subject's ear, neck, or wrist measuring a neural response by;
transmitting, in the biosignal measuring device, monitoring information including the measured biosignal to a server through a gateway;
In the server, the ECG signal of the biosignal is extracted from the transmitted monitoring information, and morphological information through conversion of the extracted ECG signal into a time-standardized image based on a pre-stored artificial intelligence machine learning algorithm is obtained. extracting the feature information;
determining, in the server, a plurality of cardiac abnormality type models by using the extracted characteristic information;
calculating, in the server, classification accuracy for the determined plurality of heart abnormality type models;
determining, in the server, whether the support subject has cardiovascular disease and an emergency state using the determined type of heart disease model and published cardiovascular disease data based on the calculated accuracy; and
and feeding back, in the server, information on whether the determined cardiovascular disease and the emergency state and information on changes in the bio-signals to a user terminal device
How the complex life support solution provision system works. 16. The method of claim 15,
The user terminal device includes at least one of a medical staff terminal device, a guardian terminal device, and an emergency center terminal device,
outputting, in the user terminal device, information including at least one of information on the determined cardiovascular disease and the emergency state and information on fluctuations in the biosignal; and
In the user terminal device, based on the prescription information generated according to the information output to the medical staff terminal device, the step of updating the prescription information also in the guardian terminal device and the emergency center terminal device further comprising
How the complex life support solution provision system works. 17. The method of claim 16,
In the user terminal device, based on the determined information on whether the cardiovascular disease and the emergency state and the change information of the bio-signal, the support target's nursing management service, disease data management service, disease data visualization, and disease data statistical service and providing at least one of an emergency push notification service.
How the complex life support solution provision system works. 16. The method of claim 15,
The step of extracting the feature information,
Based on the time domain of the extracted ECG signal
converting the generated normalized signal into the time normalized image, and applying an artificial intelligence model-based weight to the converted image to generate a compressed signal;
generating a restored signal from the compressed signal using the applied artificial intelligence model-based weight; and
Machine learning the artificial intelligence model-based weights so that the difference between the generated normalized signal and the generated reconstructed signal falls within a preset threshold range, and extracting the morphological information of the ECG signal as the feature information
How the complex life support solution provision system works. 16. The method of claim 15,
The step of determining a plurality of heart abnormality type models by machine learning the extracted feature information
A tachycardia model, bradycardia model, atrial fibrillation model, left-angle block model, right-angle block model, atrial premature contraction model, ventricular premature contraction model, cardiac arrest model, and normal heart condition model are machine-learned by machine learning the characteristic information. Determining at least one model of
How the complex life support solution provision system works. 20. The method of claim 19,
Calculating the classification accuracy for the determined plurality of heart abnormality type models comprises:
an open data set, and at least one of the tachycardia model, the bradycardia model, the atrial fibrillation model, the left-angle block model, the right-angle block model, the atrial premature contraction model, and the ventricular premature contraction model and the normal heart state model. TP (True Positive) that classifies the cardiac abnormality as the cardiac abnormality using classifying the normal into the TN (True Negative) case for classifying the normal; and
The TP (True Positive) case for the combination of the numerical value in the case of the TP (True Positive), the numerical value in the FN (False Negative) case, the numerical value in the FP (False Positive) case, and the TN (True Negative) case The tachycardia model, the bradycardia model, the atrial fibrillation model, the left-angle block model, the right-angle block model, the atrial premature contraction model and the ventricle based on the ratio of the combination of the value of Comprising the step of calculating the classification accuracy for at least one of the preconstriction models
How the complex life support solution provision system works.

Images