KR102357041B1 - Method for Analyzing and Predicting Disease by Using Artificial Intelligence - Google Patents

Abstract

The present invention provides a digital twin of a patient by utilizing big data and artificial intelligence, and based on the result of the change in the disease state by performing various computational simulations on the digital twin, the patient, the patient's guardian, and a medical institution, etc. It relates to a disease analysis and prediction method that provides bioinformation factors and lifestyle information factors to be changed.

Description

Method for Analyzing and Predicting Disease by Using Artificial Intelligence

The present invention provides a digital twin of a patient by utilizing big data and artificial intelligence, and based on the result of the change in the disease state by performing various computational simulations on the digital twin, the patient, the patient's guardian, and a medical institution, etc. It relates to a disease analysis and prediction method that provides bioinformation factors and lifestyle information factors to be changed.

Recently, various diseases, such as cancer, cardiovascular disease, diabetes, obesity, dementia, etc., are appearing in the general public at a high rate due to an increase in lifespan and westernization of diet/lifestyle.

However, in the conventional case, except for some diseases, it is predicted that the disease is likely to occur in the future by being diagnosed with the disease only through periodic health checkups, or by checking the results of the checkup by a doctor. Even in this case, there is a problem of vaguely predicting the possibility of future disease occurrence through a simple comparison of the effect or universality between diseases or a predetermined value or normal state by a physician's empirical judgment.

As such, there is a problem in that one has to rely only on expensive health check-ups to check one's own health condition, so he regularly checks his or her health condition and receives a prescription suitable for his/her health condition, so that he/she manages his/her health regularly. Personal and social demands to reduce the likelihood of occurrence are increasing.

In this regard, Korean Patent Application Laid-Open No. 10-2017-0011389 discloses a disease risk prediction method that can increase the accuracy of results by assigning weights from user result feedback to genetic mutations used for disease risk prediction based on genetic information. is starting

Conventionally, when an individual manages health, there are not many techniques for predicting changes according to an exercise and diet plan on a system basis. And, in addition, techniques for managing health and diseases by predicting changes in the body according to changes in an individual's exercise and diet are not well known.

Accordingly, the technical task of the present invention is based on this point, and the object of the present invention is to provide a digital twin of a patient by utilizing big data and artificial intelligence, and based on the results of changes in the disease state by performing various computational simulations on the digital twin To provide a disease analysis and prediction method that provides bio-information factors and lifestyle information factors that patients need to change in order to improve the disease state in patients, their guardians, and medical institutions.

The disease analysis and prediction method of the present invention utilizes a digital twin and does not impose a physical burden on the actual patient, and the computational simulation can be performed at any time as needed for various factors, and each step of the disease analysis and prediction method is performed in real time can be linked and fed back.

One aspect of the present application for realizing the object of the present invention, the first step of collecting the patient's biometric information factor and lifestyle information factor through one or more Internet of Things (IoT) terminals;

A big data-based database including biometric information factors and lifestyle information factors of an unspecified number of people with the same disease as the patient is received from the data server, and the patient's biometric information factors and lifestyle habits collected in the first step a second step of providing a digital twin corresponding to the current state of the disease of the patient, compared with the information factor, capable of computational simulation;

A third method for predicting a change in the disease state of a patient according to changes in the biometric information factor and the lifestyle information factor by performing the computational simulation of changing the biometric information factor and the lifestyle information factor in the digital twin step; and

A fourth step of providing biometric information factors and lifestyle information factors to be changed by the patient in order to improve the disease state to the patient, the patient's guardian, and a medical institution based on the change in the disease state predicted by the computerized simulation containing,

It provides methods for disease analysis and prediction.

Any one or more of the second step and the third step of the method may be performed by machine-learning artificial intelligence, and the first to fourth steps may be fed back in real time.

In addition, the disease may be mild cognitive impairment or dementia.

On the other hand, the lifestyle information factor is food intake time, food intake amount, food intake type, exercise amount, walking speed, stride length, gait symmetry, finger tapping speed, tracing accuracy, periodic or non-periodic when using language Any one or more of periodic segment length, speech response time, relative length of question and answer, sleep pattern change (eg, bedtime, etc.), driving style change, alcohol use, drug use, and smoking, said The bioinformatic factor may be any one or more of blood sugar level, blood pressure level, cholesterol level, low-density lipoprotein level, thyroid-stimulating hormone level, eye movement, pupillary reflex, number of blinks, heart rate change, and obesity.

The lifestyle factor and the biometric information factor may have different weights for each individual patient.

In addition, the IoT terminal may be carried by the user or mounted on the user to collect the biometric information factor and the lifestyle information factor of the user.

The disease analysis and prediction method of the present invention utilizes a digital twin and does not impose a physical burden on the actual patient, and the computational simulation can be performed at any time as needed for various factors, and each step of the disease analysis and prediction method is performed in real time can be linked and fed back.

Accordingly, it is possible to minimize the time and cost required for disease analysis and prediction.

Hereinafter, embodiments and examples of the present invention will be described in detail so that those of ordinary skill in the art to which the present invention pertains can easily carry out the present invention. However, the present application may be embodied in several different forms and is not limited to the embodiments and examples described herein.

Throughout this specification, when a part "includes" a certain element, it means that other elements may be further included, rather than excluding other elements, unless otherwise stated.

Also, throughout this specification, "step to" or "step for" does not mean "step for".

Hereinafter, embodiments or examples of the present application will be described in detail. However, the present application is not limited to these embodiments or examples and drawings.

The disease analysis and prediction method of the present invention comprises: a first step of collecting biometric information factors and lifestyle information factors of a patient through one or more Internet of Things (IoT) terminals;

A big data-based database including biometric information factors and lifestyle information factors of an unspecified number of people with the same disease as the patient is received from the data server, and the patient's biometric information factors and lifestyle habits collected in the first step a second step of providing a digital twin corresponding to the current state of the disease of the patient, compared with the information factor, capable of computational simulation;

A third method for predicting a change in the patient's disease state according to changes in the biometric information factor and the lifestyle information factor by executing the computational simulation of changing the biometric information factor and the lifestyle information factor in the digital twin step; and

A fourth step of providing biometric information factors and lifestyle information factors to be changed by the patient in order to improve the disease state to the patient, the patient's guardian, and a medical institution based on the change in the disease state predicted by the computerized simulation include

The IoT terminal of the first stage is a device carried by a user, such as a mobile phone, a smartphone, etc., and a wearable device worn by a user such as a watch, glasses, a patch, or accessories (rings, bracelets, necklaces, earrings, etc.). An IoT terminal may be used.

The IoT terminal includes biometric information factors such as the user's blood sugar level, blood pressure level, cholesterol level, low-density lipoprotein level, thyroid-stimulating hormone level, eye movement, pupillary reflex, number of blinks, heart rate change, and obesity. of food intake, amount of food intake, type of food intake, amount of exercise, gait speed, stride length, gait symmetry, finger tapping speed, tracing accuracy, periodic or aperiodic segment length in language use, speech response time Various sensors are built-in to measure lifestyle information such as the relative length of questions and answers, changes in sleep patterns (e.g. bedtime, etc.), changes in driving style, alcohol consumption, drug use, and smoking. and an Internet communication device for transmitting data measured through the sensor to the outside may be provided.

For example, the amount of exercise may be measured by a heart rate, a number of steps, and the like generated during exercise.

On the other hand, since the measuring device or various electronic devices themselves can communicate with the Internet, it is possible to monitor and manage the measured information and information about the electronic device through the Internet communication, as well as a device capable of communicating between IoT terminals.

In addition, the IoT terminal is a device that not only measures a user's biometric information factor and lifestyle information factor, but also can be carried or mounted on the body. It is recorded through this, and it is also possible to obtain such personal life log information.

On the other hand, it is possible to measure the user's biometric information factor and lifestyle information factor in real time through the IoT terminal, and it is also possible to measure it at a specific time period.

The present invention already measures personal health-related information in various angles and methods through various electronic devices or Internet of Things terminals equipped with measurement sensors and Internet communication devices, and analyzes and processes vast amounts of measured data using big data techniques, It is possible to more conveniently provide high-quality, user-centered, personalized healthcare information that is updated in real time.

The data server of the second step may provide biometric information factors and lifestyle information factors of a large number of unspecified persons suffering from the same disease as the patient.

In this case, the biometric information factor and lifestyle information factor of an unspecified number of people may include various factors, but in particular, when the patient suffers from mild cognitive impairment or dementia, biometric information factors and lifestyle information related to mild cognitive impairment or dementia Arguments may be included.

These biometric information factors and lifestyle information factors specifically include food intake time, food intake amount, food intake type, amount of exercise, walking speed, stride length, gait symmetry, finger tapping speed, tracing accuracy, Periodic or non-periodic segment length in speech use, speech response time, relative length of question-and-answer time, sleep pattern changes (e.g. bedtime, etc.), changes in driving style, alcohol use, drug use, smoking, blood sugar Internet of Things Any biometric information factors and lifestyle information factors related to a patient's disease, particularly mild cognitive impairment or dementia, that can be collected through the terminal may be included.

All of the above-described biometric information factors and lifestyle information factors can be viewed as biometric information factors and lifestyle information factors related to mild cognitive impairment or dementia.

As a non-limiting specific example for the collection of bioinformatic factors and lifestyle information factors related to mild cognitive impairment or dementia, dementia patients begin to experience impairment in daily movement from the early stage of dementia, so information on gait speed, stride length, and gait symmetry is detected as movement It can be collected through sensors.

Since it is possible to measure the progress of the patient's dementia even by the speed and accuracy of detailed movements, the finger tapping speed and tracing accuracy can be measured at the end of the Internet of Things that the patient can carry or wear (e.g., It can be collected through the touch sensor built into the smartphone).

In addition, as dementia progresses, abnormalities in language ability occur, so periodic or aperiodic segment lengths, voice response times, and relative lengths for questions and answers are built into the end of the Internet of Things that patients can carry or wear when using language. It can be collected through a microphone sensor.

In addition, eye movement, pupillary reflex, and the number of blinks can be indication factors for neurological diseases including dementia. can be collected through

Dementia also appears as a disorder of the autonomic nervous system, and a representative indication factor for this is a change in heart rate. or electrocardiograms (ECG) sensors.

Dementia patients show changes in their sleep patterns, which can be measured by a ballistocardiography sensor built into the end of the Internet of Things that the patient can carry or wear.

In addition, dementia patients have a reduced ability to perceive space, which greatly affects the driving method of a car, so that the patient can carry or wear a change in the driving method (eg, change of the driving route, etc.) It can be collected through a location sensor built into the edge of the Internet of Things.

All of the first to fourth steps may be performed by machine-learning artificial intelligence, and in particular, the second and third steps may be performed by machine-learning artificial intelligence. For example, you can select and train an algorithm for analyzing and predicting multiple diseases. The biometric information factor and lifestyle information factor of a large number of unspecified persons suffering from the same disease are set as input, and the result of a computational simulation in which the patient's digital twin setting and the biometric information factor for the digital twin and the lifestyle information factor are changed After training by setting the output, when the patient's biometric information factor and lifestyle information factor are input, an algorithm that outputs the most accurate disease analysis and prediction probability value can be selected and applied.

Such a plurality of algorithms may include artificial neural networks or hidden Markov models (HMM)-based algorithms, as well as convolutional neural networks (CNNs), recurrent neural networks (RNNs), etc. .

As an example, the input node for the biometric information factor and the lifestyle information factor of a large number of unspecified persons with the same disease as the patient is designated as the input layer of the artificial intelligence neural network, and the patient's digital twin setting and biometric information factor for the digital twin And it is possible to create a final trained artificial intelligence neural network by generating and learning an initial artificial intelligence neural network through supervised learning in which an output node for a computational simulation result value obtained by changing the lifestyle information factors is designated as an output layer. .

After the final trained artificial intelligence neural network is generated, the patient's biometric information factors and lifestyle information factors received from the Internet of Things (IoT) terminal may be designated as input nodes of the final artificial intelligence neural network.

The digital twin of the second stage is a technology for pre-analyzing and predicting results by making twins of things in the real world on a computer, and simulating situations that may occur in reality computationally.

Digital twins are attracting attention as a technology that can solve various industrial and social problems as well as manufacturing, and are applied in computer-aided design (CAD) fields because they are virtual representations of physical entities.

In the present invention, the patient's biometric information factors and lifestyle information factors collected through the Internet of Things (IoT) are refined through a big data platform and reflected in the digital twin.

The patient's digital twin, which can be applied to reality, is analyzed by computational simulation with artificial intelligence to determine abnormal symptoms, or through simulation, improvement factors are discovered and reflected in the patient.

In addition, real-time feedback and monitoring are possible through the application of a digital twin, so a preemptive response beyond a quick response to a dangerous situation can be made possible.

Accordingly, the first to fourth steps of the present invention may be fed back in real time.

For example, through a digital twin of an individual patient, information such as the most effective drug, treatment method, diet, and exercise method can be identified and provided in computational simulation prior to actual patient clinical treatment.

Such information (especially, biometric information factors and lifestyle information factors to be changed by a patient for improvement of a disease state) may be provided to a patient, a patient's protector, a medical institution, and the like.

The information may be provided through various user devices such as a patient, a guardian of the patient, and a medical institution.

For example, when information is provided in real time through a user device carried or worn by the patient, and the patient who received the information changes his or her lifestyle to improve the disease state based on this information, Biometric information factors and lifestyle information factors are collected in real time by the Internet of Things and reflected in the patient's digital twin.

For digital twins that reflect real-time changes, computerized simulations are also performed in real time, and the results of computerized simulations are fed back to patients, their guardians, and medical institutions in real time.

In addition, in the first to fourth steps of the present invention, the weight of the lifestyle factor and the biometric information factor may be different for each individual patient. Through this, it is possible to analyze and predict disease tailored to each individual.

Claims (8)

A first step of collecting the patient's biometric information factors and lifestyle information factors through one or more Internet of Things (IoT) terminals;
A big data-based database including biometric information factors and lifestyle information factors of an unspecified number of people with the same disease as the patient is received from the data server, and the patient's biometric information factors and lifestyle habits collected in the first step a second step of providing a digital twin corresponding to the current state of the disease of the patient, compared with the information factor, capable of computational simulation;
A third method for predicting a change in the patient's disease state according to changes in the biometric information factor and the lifestyle information factor by executing the computational simulation of changing the biometric information factor and the lifestyle information factor in the digital twin step; and
A fourth step of providing biometric information factors and lifestyle information factors to be changed by the patient in order to improve the disease state to the patient, the patient's guardian, and a medical institution based on the change in the disease state predicted by the computerized simulation including,
The lifestyle information factors include food intake time, food intake amount, food intake type, exercise amount, gait speed, stride length, gait symmetry, finger tapping speed, tracing accuracy, periodic or aperiodic segments when using language any one or more of length, speech reaction time, relative length of questions and answers, changes in sleep patterns, changes in driving style, alcohol use, drug use, and smoking;
The bioinformation factor is any one or more of blood sugar level, blood pressure level, cholesterol level, low-density lipoprotein level, thyroid-stimulating hormone level, eye movement, pupillary reflex, number of blinks, heart rate change, and obesity,
The lifestyle factor and the biometric information factor may have different weights for each patient,
Disease analysis and prediction methods. According to claim 1,
Any one or more of the second step and the third step is characterized in that it is performed by machine-learning artificial intelligence,
Disease analysis and prediction methods. According to claim 1,
The first to fourth steps are characterized in that the feedback in real time,
Disease analysis and prediction methods. According to claim 1,
The disease is characterized in that mild cognitive impairment or dementia,
Disease analysis and prediction methods. delete delete According to claim 1,
wherein the IoT terminal is carried by the user or is mounted on the user to collect the user's biometric information factor and lifestyle information factor;
Disease analysis and prediction methods. delete