KR20220112994A - Artificial intelligence based electronic apparatus for early determination on negative result of infectious disease, control method, and computer program - Google Patents

Abstract

An electronic device is disclosed. The present electronic device comprises: a memory in which an artificial intelligence model trained to predict whether an infectious disease is negative is stored; and a processor that inputs biometric information of a patient to an artificial intelligence model to identify whether the patient is negative for an infectious disease. The artificial intelligence model is a model trained based on biometric information of a plurality of patients and real time-polymerase chain reaction (RT-PCR) performed for the plurality of patients.

Description

Artificial intelligence-based electronic device, control method, and computer program for early determination of whether an infectious disease is negative

The present disclosure relates to an electronic device, and more particularly, to an electronic device using an artificial intelligence model for early determining whether an infectious disease is negative.

Due to the COVID-19 virus infection, the world is exposed to the risk of an infectious disease pandemic.

Various efforts are being made to block the spread of infectious diseases such as COVID 19, especially when receiving patients in hospitals, patients with screening symptoms (fever, cough, sputum, difficulty breathing, headache, body aches, chills, etc.) In this case, it is necessary to wait until the test result is confirmed in isolation through screening treatment (ex. isolation room).

In this process, it takes as little as 6 hours to as long as 12 hours for a voice to be confirmed through RT-PCR (Real Time Polymerase Chain Reaction), etc. do.

In particular, when RT-PCR is performed and diagnosis is performed with patients with screening symptoms placed in an isolation room, most of the patients are often found to be negative, and only a small number of patients are subject to positive confirmation. , it could be of great help in overcoming the problem of serious patient acceptance if we can find patients who are positively negative more quickly.

Registered Patent Publication No. 10-20200047452 (Artificial Intelligence Infectious Disease Unmanned Diagnosis Service Provision System)

The present disclosure provides an electronic device and a control method for early diagnosis of whether a patient has an infectious disease using an artificial intelligence model trained based on accumulated data.

Objects of the present disclosure are not limited to the above-mentioned purposes, and other objects and advantages of the present disclosure that are not mentioned may be understood by the following description, and will be more clearly understood by examples of the present disclosure. Moreover, it will be readily apparent that the objects and advantages of the present disclosure may be realized by the means and combinations thereof indicated in the claims.

The electronic device according to an embodiment of the present disclosure inputs a memory in which an artificial intelligence model trained to predict whether or not an infectious disease is negative, and biometric information of a patient, is input to the artificial intelligence model, and whether the patient is negative for the infectious disease and a processor that identifies The artificial intelligence model is a model trained based on biometric information of a plurality of patients and a result of RT-PCR (Real Time Polymerase Chain Reaction)-based infectious disease diagnosis performed on the plurality of patients.

The biometric information may include information on the patient's gender, age, body temperature, pulse, respiration rate, blood pressure, and symptoms.

The biometric information may include information on at least one of a blood test result of the patient, a chest X-ray image, and a chest computed tomography (CT) image.

Meanwhile, the artificial intelligence model may be a model trained based on information on a contact history between each of the plurality of patients and at least one confirmed patient diagnosed as positive for the infectious disease. In this case, the processor may input the biometric information of the patient and information on a contact history between the patient and at least one confirmed patient into the artificial intelligence model to identify whether the patient is negative for the infectious disease. have.

In this case, the processor calculates a score according to the contact history between the patient and the confirmed patient based on the location information for each time of the patient and the location information for each time of the confirmed patient, and calculates the patient's biometric information and the score By input to the artificial intelligence model, it is possible to identify whether the patient is negative for the infectious disease.

In addition, the artificial intelligence model is a positive infectious disease diagnosis result among a plurality of RT-PCR-based infectious disease diagnosis results within the quarantine period of a specific patient including one or more negatives and a positive subsequent to the one or more negatives. It may be a model trained based on it.

In addition, the artificial intelligence model may be a recurrent neural network (RNN) model trained to output the negative probability of the infectious disease based on biometric information continuously input according to a preset period. In this case, the processor inputs the biometric information of the patient measured according to the preset period into the artificial intelligence model to obtain a negative probability of the patient for the infectious disease, and the obtained negative probability is equal to or greater than a threshold In this case, it can be identified that the patient is negative for the infectious disease.

According to an embodiment of the present disclosure, there is provided a training method of an electronic device for training an artificial intelligence model for outputting a negative probability of an infectious disease, the first plurality of patients having positive diagnostic results of an infectious disease based on RT-PCR (Real Time Polymerase Chain Reaction). A first training step of training the artificial intelligence model based on the biometric information for each cycle, training the AI model based on the biometric information for each cycle of a second plurality of patients whose RT-PCR-based infectious disease diagnosis result is negative and a second training phase.

The training method may further include verifying the artificial intelligence model based on the biometric information for each cycle of the third plurality of patients and the RT-PCR-based infectious disease diagnosis result of the third plurality of patients.

A method of controlling an electronic device according to an embodiment of the present disclosure includes: inputting biometric information of a patient into an artificial intelligence model trained to predict whether or not an infectious disease is negative; based on the output of the artificial intelligence model, the patient's and identifying whether the infection is negative for the infectious disease. The artificial intelligence model is a model trained based on biometric information of a plurality of patients and a result of RT-PCR (Real Time Polymerase Chain Reaction)-based infectious disease diagnosis performed on the plurality of patients.

The electronic device and control method according to the present disclosure provide a positive diagnosis of an infectious disease through result data such as age, sex, main symptoms, symptom onset time, accompanying symptoms, vital signs, and blood test findings during screening treatment. /Negative has the effect of early diagnosis.

In particular, the electronic device and control method according to the present disclosure newly define the criteria for release of quarantine by building/using an artificial intelligence model capable of predicting positive/negative infectious disease with an accuracy exceeding that of RT-PCR, which has been mainly used in the prior art. It is expected that the release date will be accelerated. In this case, there is an effect of minimizing unnecessary isolation to facilitate the provision of medical services to critically ill patients.

1 is a block diagram illustrating a configuration of an electronic device according to an embodiment of the present disclosure;
2 is a flowchart illustrating an operation of an electronic device according to an embodiment of the present disclosure;
3 is a diagram for explaining an operation of determining whether an electronic device is negative for an infectious disease by inputting biometric information for each period of a patient according to an embodiment of the present disclosure;
4 is a view for explaining an operation of an electronic device determining whether an infectious disease is negative in consideration of a contact history between a confirmed patient and a patient according to an embodiment of the present disclosure;
5 is a flowchart illustrating an operation in which an electronic device trains an artificial intelligence model according to an embodiment of the present disclosure; and
6 is a block diagram illustrating a configuration of an electronic device according to various embodiments of the present disclosure.

Prior to describing the present disclosure in detail, a description will be given of the description of the present specification and drawings.

First, terms used in the present specification and claims have been selected in consideration of functions in various embodiments of the present disclosure. However, these terms may vary depending on the intention or legal or technical interpretation of a person skilled in the art, and the emergence of new technology. Also, some terms are arbitrarily selected by the applicant. These terms may be interpreted in the meaning defined in the present specification, and if there is no specific term definition, it may be interpreted based on the general content of the present specification and common technical knowledge in the art.

Also, the same reference numerals or reference numerals in each drawing attached to this specification indicate parts or components that perform substantially the same functions. For convenience of description and understanding, the same reference numbers or reference numerals are used in different embodiments. That is, even though all components having the same reference number are illustrated in a plurality of drawings, the plurality of drawings do not mean one embodiment.

In addition, in this specification and claims, terms including an ordinal number, such as "first" and "second", may be used to distinguish between elements. This ordinal number is used to distinguish the same or similar elements from each other, and the meaning of the term should not be construed as limited due to the use of the ordinal number. For example, the components combined with such an ordinal number should not be limited in the order of use or arrangement by the number. If necessary, each ordinal number may be used interchangeably.

In this specification, the singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as "comprises" or "consisting of" are intended to designate that the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification exist, and are intended to indicate that one or more other It is to be understood that this does not preclude the possibility of addition or presence of features or numbers, steps, operations, components, parts, or combinations thereof.

In an embodiment of the present disclosure, terms such as “module”, “unit”, “part”, etc. are terms for designating a component that performs at least one function or operation, and such component is hardware or software. It may be implemented or implemented as a combination of hardware and software. In addition, a plurality of "modules", "units", "parts", etc. are integrated into at least one module or chip, except when each needs to be implemented as individual specific hardware, and thus at least one processor. can be implemented as

In addition, in an embodiment of the present disclosure, when a part is connected to another part, this includes not only direct connection but also indirect connection through another medium. In addition, the meaning that a certain part includes a certain component means that other components may be further included without excluding other components unless otherwise stated.

1 is a block diagram illustrating a configuration of an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 1 , the electronic device 100 includes a memory 110 and a processor 120 .

The electronic device 100 may be implemented as various electronic devices or systems including one or more computers.

As an example, the electronic device 100 may be implemented as a server for performing communication with at least one terminal device.

In this case, the electronic device 100 may communicate with at least one measurement device for measuring biometric information (eg, blood pressure, pulse, respiration rate, body temperature, etc.) It may communicate with at least one input device.

The electronic device 100 may be implemented as a medical robot, a medical computer, a medical monitoring system, or the like. In this case, the electronic device 100 may be provided with means for measuring various kinds of biometric information or may communicate with at least one measuring device for measuring biometric information.

In addition, the electronic device 100 may be implemented as various terminal devices such as a smart phone, a desktop PC, a tablet PC, a notebook PC, a wearable device, a VR/AR device, and a PDA.

The memory 110 is a configuration for storing an operating system (OS) for controlling overall operations of components in the electronic device 100 , at least one instruction, and data.

The memory 110 may include non-volatile memory such as ROM and flash memory, and may include volatile memory such as DRAM. Also, the memory 110 may include a hard disk, a solid state drive (SSD), or the like.

Referring to FIG. 2 , the memory 110 may include at least one artificial intelligence model 111 trained to predict whether an infectious disease is negative.

Infectious diseases may correspond to COVID 19, which has recently become a problem, but may also correspond to various infectious diseases caused by pathogen penetration.

The artificial intelligence model 111 may correspond to a network model based on a neural network. The network model may include a plurality of network nodes having weights. A plurality of network nodes may form a connection relationship based on weights between nodes of different layers.

The artificial intelligence model 111 may be learned through a deep neural network (DNN) method, and may be a model based on a recurrent neural network (RNN), a convolutional neural network (CNN), or the like, but is not limited thereto.

The artificial intelligence model 111 may be a model trained based on biometric information of a plurality of patients and a result of RT-PCR (Real Time Polymerase Chain Reaction)-based infectious disease diagnosis performed on the plurality of patients.

At this time, the biometric information of each patient corresponds to the training data for input of the artificial intelligence model 111 , and the (RT-PCR) diagnosis result (ex. positive or negative) of each patient is training for output of the artificial intelligence model 111 . It may be data. However, the training data for output does not necessarily have to be a diagnosis result according to RT-PCR, and may be a diagnosis result of another test method such as an immunoassay-based method. In addition, it goes without saying that the diagnosis results according to various infectious disease testing methods to be developed in the future can be used for training the AI model.

The artificial intelligence model 111 may be trained to determine whether the patient's infectious disease is negative (positive) as biometric information of the patient is input.

As a specific example, when biometric information of a specific patient is input at regular intervals, the artificial intelligence model 111 may output a probability that the corresponding patient is negative (or positive) for an infectious disease.

The biometric information may include information on the patient's gender, age, body temperature, pulse, respiration rate, blood pressure (systolic/diastolic), symptoms, and the like. Here, the symptoms may be various, such as cough, sputum, shortness of breath, headache, body aches, chills, abdominal pain, diarrhea, nausea, vomiting, frequent urination, back pain, sore throat, and the like. The biometric information may also include information on a time when a symptom starts, a severity of a symptom, and the like.

In addition, the biometric information may include information on various blood test results. Specifically, the biometric information for the patient is CBC (Complete Blood Cell count), Electrolyte, LFT (Liver Function Test), PT (Prothrombin Time), aPTT (activated Partial Thromboplastin Time), Urine analysis, ABGA (Arterial Blood Gas Analysis) ), lactate, CRP (Creactive Protein), etc. may include the results of various blood tests in the emergency room. The above-described biometric information based on a blood test may be used on the premise that the test speed is faster than that of RT-PCR.

In addition, the biometric information may include a chest X-ray image, a chest computed tomography (CT) image, and the like. When at least one type of image (X-ray, CT, etc.) is defined as an input of the artificial intelligence model 111 as biometric information, the artificial intelligence model 111 uses a convolutional layer for extracting feature information from the image. It may be included as at least a part of the model 111 .

As such, the artificial intelligence model 111 may be trained to predict whether or not an infectious disease is negative based on at least one type of biometric information among the various types of biometric information described above.

Meanwhile, a separate artificial intelligence model may be used for each gender and/or age. That is, the memory 110 is divided by gender (ex. male, female) and/or age (eg, under 10, 10s, 20s, 30s, 40s, 50s, 60s, 70s, etc.) A plurality of artificial intelligence models trained independently for each biometric information of each patient group may be included.

The above-described training of the artificial intelligence model 111 may be performed through the processor 120 of the electronic device 100 or may be performed by at least one external device. A specific process of training will be described later with reference to FIG. 5 .

The processor 120 is a configuration for overall controlling each configuration included in the electronic device 100 , and includes a central processing unit (CPU), an application processor (AP), a graphic processing unit (GPU), and a visual processing unit (VPU). , a Neural Processing Unit (NPU), and the like.

The processor 120 may control the electronic device 100 by executing an instruction stored in the memory 110 .

In addition, the processor 120 may identify whether at least one patient is negative for an infectious disease using the artificial intelligence model 111 stored in the memory 110 .

In relation to this, FIG. 2 is a flowchart illustrating an operation of an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 2 , the electronic device 100 may input the patient's biometric information into the artificial intelligence model 111 ( S210 ).

Specifically, the electronic device 100 may input biometric information, such as a patient's gender, age, body temperature, blood pressure, pulse, X-ray image, CT image, etc., into the artificial intelligence model 111 . As a result, the artificial intelligence model 111 may output whether the infectious disease is negative (probability).

Also, as an example, the artificial intelligence model 111 may be a recurrent neural network (RNN) model trained to output a negative probability of an infectious disease based on biometric information continuously input according to a preset period.

The preset period may be, for example, 30 minutes, one hour, two hours, four hours, etc., but is not limited thereto. However, it may be undesirable for the preset period to be set to 6 hours or more in that the diagnosis is aimed at a faster speed than RT-PCR diagnosis.

In this case, the electronic device 100 may obtain at least some of the above-described biometric information for each preset period and input it into the artificial intelligence model 111 . That is, the electronic device 100 may input biometric information measured for each preset period into the artificial intelligence model 111 .

Then, the electronic device 100 may identify whether the patient is negative for an infectious disease based on the output of the artificial intelligence model 111 ( S220 ).

At this time, the artificial intelligence model 111 may output whether the patient is negative for the infectious disease (positive/negative) or may output a negative probability.

For example, when the probability of a voice output from the artificial intelligence model 111 is equal to or greater than a threshold (eg, 99.8%), the electronic device 100 may identify that the patient is negative for an infectious disease.

FIG. 3 is a diagram for explaining an operation in which an electronic device determines whether or not an infectious disease is negative by inputting biometric information for each period of a patient according to an embodiment of the present disclosure.

Referring to FIG. 3 , the electronic device 100 uses the RNN-based biometric information on the body temperature, pulse, respiration rate, blood pressure, and symptoms of a specific patient sequentially measured (acquired) according to a preset period (eg, 2 hours). It can be input into the trained artificial intelligence model 111 .

Here, the specific patient may correspond to a patient with suspected symptoms such as fever, cough, body aches, and chills.

Specifically, the electronic device 100 converts biometric information more than recently measured a certain number of times (eg, 3 or more times when the cycle is 2 hours) including the current time point (2021.01.01 14:00) to the artificial intelligence model 111 . ) can be entered.

In this case, the artificial intelligence model 111 may output a negative probability (99.8%) of the patient's infectious disease at the current time (ex. 2021.01.01 14:00) based on the above-described biometric information.

In FIG. 3 , when the threshold is 99.8%, the electronic device 100 can identify that the patient has a voice because the patient's voice probability is 99.8%, and outputs information indicating that the patient has a (final) voice. can In addition, the electronic device 100 may output information indicating that isolation of the corresponding patient is possible.

Alternatively, the artificial intelligence model may output a negative probability of an infectious disease for each time point. Specifically, in the situation of FIG. 3 , the artificial intelligence model 111 may output the negative probability of an infectious disease (of the patient) at each time point (10 o’clock, 12 o’clock, 14:00) using the biometric information input for each cycle. have.

Here, the electronic device 100 may identify whether or not there is a voice by comprehensively considering the voice probability output for each period.

Specifically, in the electronic device 100, on the premise that the probability of a voice sequentially output for each time point exceeds a threshold value (ex. 99.8%) continuously for a threshold number of times (ex. 3 times) or more, and does not gradually decrease, the patient It can be identified (finally) that it is negative for an infectious disease, and it can be determined that isolation is possible.

As a specific example, the (patient's) negative probability output based on the patient's biometric information obtained by 10 o'clock is 99.8%, and the (patient's) negative output based on the patient's biometric information obtained by 12 o'clock is 99.8 %, and it is assumed that the outputted voice probability is 99.9% based on the biometric information obtained by 14:00.

In this case, since the negative probability is equal to or greater than the threshold (99.8%) for three consecutive times and does not gradually decrease, the electronic device 100 may (finally) identify that the corresponding patient is negative for the infectious disease. In addition, the electronic device 100 may identify that isolation of the corresponding patient is possible.

As another example, the probability of a (patient's) voice output based on the patient's biometric information acquired by 10 o'clock is 99.9%, and the (patient's) voice probability output based on the patient's biometric information acquired by 12 o'clock is 99.7 %, and when the (patient's) voice probability output based on the patient's biometric information obtained by 14:00 is 99.8%, the electronic device 100 identifies that isolation is impossible for the patient as of 14:00 can do. However, if the negative probability is identified as 99.8% and 99.9% for 16:00 and 18:00, respectively, the electronic device 100 identifies the patient as (final) negative and provides information indicating that isolation is possible can do.

As such, when biometric information measured for each period is input, the prediction accuracy of the artificial intelligence model 111 trained using the RNN model can be secured.

Meanwhile, according to an embodiment, the artificial intelligence model 111 may be trained based on information about a contact history with a confirmed person in addition to the various types of biometric information described above.

Specifically, the artificial intelligence model 111 may be a model trained based on information about a contact history between each of a plurality of patients and at least one confirmed patient diagnosed as positive for an infectious disease. That is, biometric information and contact history (with a confirmed person) may be input training data, and a diagnosis result may be output training data.

In this case, the electronic device 100 may input the biometric information of the patient and information on the contact history between the patient and at least one confirmed patient into the artificial intelligence model 111 to identify whether the patient is negative for an infectious disease. have.

The information on the contact history may include information on the number of confirmed cases the patient has contacted, the contact period, the degree of close contact, and the like, and may be in the form of a score reflecting the above items.

The contact may include both a case in which physical contact occurs, and a case in which a person is located in close proximity or shares an enclosed space. In particular, in the case of COVID 19, where droplet infection is the main route of infection, it is natural to interpret contact as a concept that includes proximity or space sharing. In this case, the space sharing may include not only a case of being located in the same space at the same time, but also a case of being located in the same space at a nearby view.

The electronic device 100 may calculate a score (related to the contact history) by analyzing the movement of the confirmed patient (eg, location by time) and the movement of the patient (eg, location by time), respectively.

In this case, the electronic device 100 may calculate a score in the form of a contact index between a patient and a confirmed person, and may calculate the score using at least one artificial intelligence model.

4 is a diagram for explaining an operation of determining whether an electronic device is negative for an infectious disease in consideration of a contact history between a confirmed patient and a patient, according to an embodiment of the present disclosure.

Referring to FIG. 4 , the electronic device 100 may calculate a score according to a contact history between a patient and a confirmed patient based on location information of a patient by time and location information of a confirmed person by time.

In this case, the score may be calculated according to the time at which each of the patient and the confirmed patient are located in the same place. If the patient and the confirmed patient are located at the same place at the same time, a higher score may be calculated than if the patient and the confirmed person are located at the same place at different time points (eg, close time).

As a specific example, referring to FIG. 4 , a first weight is given (first weight * 30 minutes) for 30 minutes (12:30 ~ 13:00) when the patient and the confirmed person were located in the same place, and confirmed at the location. A second weight smaller than the first weight may be given for one hour (13:00 to 14:00) when only the patient was located at the corresponding place in a state in which the self is not located (second weight * 1 hour). As a result, it can be calculated as “(contact history) score = (first weight * 30 minutes) + (second weight * 1 hour)”.

The electronic device 100 may identify whether the patient is negative for an infectious disease based on the calculated (contact history) score.

As an example, the electronic device 100 may input biometric information of the patient and a (contact history) score related to the patient into the artificial intelligence model 111 . In this case, the artificial intelligence model 111 may output whether or not a voice is voiced and/or a voice probability based on the biometric information and the score.

As another example, the electronic device 100 may change whether to use the artificial intelligence model according to the calculated score.

As a specific example, when the calculated score is less than the threshold score, the electronic device 100 may obtain the voice probability by inputting the patient's biometric information into the artificial intelligence model 111 . In this case, the electronic device 100 may identify whether the patient has a voice based on the acquired voice probability.

On the other hand, when the calculated score is equal to or greater than the threshold score, the electronic device 100 may not input the patient's biometric information into the artificial intelligence model 111 . In this case, the electronic device 100 may output (provide) a message indicating that isolation is required until a specific diagnostic test (eg, RT-PCR) is issued, regardless of the output of the artificial intelligence model 111 . .

Meanwhile, FIG. 5 is a flowchart illustrating an operation in which an electronic device trains an artificial intelligence model according to an embodiment of the present disclosure.

The training of the artificial intelligence model 111 may be performed in the electronic device 100 or an external device. In FIG. 5 , it is assumed that the training is performed in the electronic device 100 through the processor 120 .

Referring to FIG. 5 , the electronic device 100 is configured to train the artificial intelligence model 111 based on the cycle-specific biometric information of a first plurality of patients who have positive RT-PCR (Real Time Polymerase Chain Reaction)-based infectious disease diagnosis results. can be (S510).

Also, the electronic device 100 may train the artificial intelligence model 111 based on the biometric information for each cycle of the second plurality of patients whose RT-PCR-based infectious disease diagnosis result is negative ( S520 ).

That is, the electronic device 100 may train the artificial intelligence model 111 using training data sets corresponding to different outputs (eg, positive/negative).

Although, in FIG. 5 , the training ( S510 ) for the biometric information of positive patients and the training ( S520 ) for the biometric information of the negative patients are respectively performed separately, the biometric information of the positive patients and the biometric information of the negative patients Of course, it can be used for training (weight change between nodes) according to the random shuffle order.

Meanwhile, the artificial intelligence model 111 may be a model that has not been trained for an inaccurate part of a diagnosis result through RT-PCR.

Specifically, it is assumed that, as a result of multiple RT-PCR-based infectious disease diagnoses performed within a specific patient's quarantine period (ex. within 2 weeks), positive results are derived after at least one negative result. In this case, one or more negative diagnoses prior to positive may be interpreted as misdiagnosis or errors in the RT-PCR method.

In this case, the artificial intelligence model 111 may be trained through only the positive infectious disease diagnosis result among the diagnosis results for the corresponding patient. Here, the selection of the diagnosis result to be used for the training data may be performed by a human or through at least one electronic device.

As a result, ultimately, the construction of the artificial intelligence model 111 with higher prediction accuracy for infectious diseases than RT-PCR can be expected.

Meanwhile, referring to FIG. 5 , the electronic device 100 provides an artificial intelligence (AI) trained in advance (S510 to S520) based on biometric information for each cycle of a third plurality of patients and an infectious disease diagnosis result (ex. RT-PCR). Verification of the model 111 may be performed (S530).

As a result of the verification, when the output of the artificial intelligence model 111 is different from the actual diagnosis result for the third plurality of patients, the electronic device 100 performs the diagnosis based on the biometric information and the diagnosis result information of the patients including the third plurality of patients. Additional training for the artificial intelligence model 111 may be performed.

6 is a block diagram illustrating a configuration of an electronic device according to various embodiments of the present disclosure;

Referring to FIG. 6 , the electronic device 100 may further include a communication unit 130 , a user input unit 140 , an output unit 150 , and the like in addition to the memory 110 and the processor 120 .

The communication unit 130 may include a circuit as a configuration for the electronic device 100 to communicate with at least one external device.

The communication unit 130 is TCP/IP (Transmission Control Protocol/Internet Protocol), UDP (User Datagram Protocol), HTTP (Hyper Text Transfer Protocol), HTTPS (Secure Hyper Text Transfer Protocol), FTP (File Transfer Protocol), SFTP ( A communication protocol (protocol) such as Secure File Transfer Protocol) and MQTT (Message Queuing Telemetry Transport) may be used to transmit/receive various information to and from one or more external electronic devices.

To this end, the communication unit 130 may be connected to an external device based on a network implemented through wired communication and/or wireless communication. In this case, the communication unit 170 may be directly connected to an external device, or may be connected to an external electronic device through one or more external servers (eg, Internet Service Providers (ISPs)) that provide a network.

The network may be a personal area network (PAN), a local area network (LAN), a wide area network (WAN), etc. depending on the area or size, and depending on the openness of the network, an intranet, It may be an extranet or the Internet.

Wireless communication includes long-term evolution (LTE), LTE Advance (LTE-A), 5th generation (5G) mobile communication, code division multiple access (CDMA), wideband CDMA (WCDMA), universal mobile telecommunications system (UMTS), WiBro (Wireless Broadband), GSM (Global System for Mobile Communications), DMA (Time Division Multiple Access), WiFi (Wi-Fi), WiFi Direct, Bluetooth, NFC (near field communication), at least one of the communication methods such as Zigbee may include

Wired communication may include at least one of communication methods such as Ethernet, optical network, USB (Universal Serial Bus), and ThunderBolt.

Here, the communication unit 130 may include a network interface or a network chip according to the above-described wired/wireless communication method. Meanwhile, the communication method is not limited to the above-described example, and may include a communication method newly appearing according to the development of technology.

For example, when the electronic device 100 is implemented as a server, the electronic device 100 may communicate with at least one terminal (eg, a smartphone, a blood pressure/pulse measuring device, etc.) through the communication unit 130 . have. Specifically, the electronic device 100 as a server may be linked with the user terminal through at least one web page or application.

In this case, the electronic device 100 may receive at least one type of biometric information through the terminal or may provide information on whether or not an infectious disease is negative according to the output of the artificial intelligence model 111 through the terminal.

The user input unit 140 is configured to receive various commands or biometric information from a user. The user input unit 140 may be implemented as a touch sensor, a button, a camera, a microphone, a keypad, a mouse, and the like.

The electronic device 100 may receive data on various types of biometric information for at least one patient (for each period) through the user input unit 140 , and (based on the biometric information) of at least one patient. It may receive a user command requesting to identify whether it is an infectious disease or not.

The output unit 150 is configured to output various information, and may include a display, an audio output unit, and the like. The audio output unit may include a speaker, an audio/headphone connection terminal, and the like.

In an embodiment, the electronic device 100 displays data on the patient's biometric information, information on whether the patient has negative infectious disease (probability), information on whether the patient can release quarantine, etc. on a display or through a speaker or the like. It can be output in audio format.

According to the above-described embodiments, when it is identified that the patient is (finally) negative for an infectious disease, the electronic device 100 may provide information indicating that isolation is possible along with information on whether the patient is negative.

Meanwhile, the various embodiments described above may be implemented by combining a plurality of embodiments as long as they do not conflict with each other.

Meanwhile, the various embodiments described above may be implemented in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof.

According to the hardware implementation, the embodiments described in the present disclosure are ASICs (Application Specific Integrated Circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays) ), processors, controllers, micro-controllers, microprocessors, and other electrical units for performing other functions may be implemented using at least one.

In some cases, the embodiments described herein may be implemented by the processor itself. According to the software implementation, embodiments such as the procedures and functions described in this specification may be implemented as separate software modules. Each of the software modules described above may perform one or more functions and operations described herein.

Meanwhile, computer instructions or a computer program for performing a processing operation in each device in the system according to various embodiments of the present disclosure described above are stored in a non-transitory computer-readable medium. can be saved. When the computer instructions or computer program stored in the non-transitory computer-readable medium are executed by the processor of the specific device, the specific device performs the processing operation in the electronic device according to the various embodiments described above.

The non-transitory computer-readable medium refers to a medium that stores data semi-permanently, rather than a medium that stores data for a short moment, such as a register, cache, memory, etc., and can be read by a device. Specific examples of the non-transitory computer-readable medium may include a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, and the like.

In the above, preferred embodiments of the present disclosure have been illustrated and described, but the present disclosure is not limited to the specific embodiments described above, and it is common in the technical field pertaining to the present disclosure without departing from the gist of the present disclosure as claimed in the claims. Various modifications may be made by those having the knowledge of

100: electronic device 110: memory
120: processor

Claims (11)

In an electronic device,
a memory in which an artificial intelligence model trained to predict whether an infectious disease is negative; and
A processor for inputting the patient's biometric information into the artificial intelligence model to identify whether the patient is negative for the infectious disease;
The artificial intelligence model is
An electronic device, which is a model trained based on biometric information of a plurality of patients and a result of RT-PCR (Real Time Polymerase Chain Reaction)-based infectious disease diagnosis performed on the plurality of patients. According to claim 1,
The biometric information is
An electronic device comprising information about the patient's gender, age, body temperature, pulse, respiration rate, blood pressure, and symptoms. According to claim 1,
The biometric information is
The electronic device comprising information on at least one of a blood test result of the patient, a chest X-ray image, and a chest computed tomography (CT) image. According to claim 1,
The artificial intelligence model is
It is a model trained based on information on contact history between each of the plurality of patients and at least one confirmed positive diagnosed with the infectious disease,
The processor is
An electronic device for identifying whether the patient is negative for the infectious disease by inputting the biometric information of the patient and information on a contact history between the patient and at least one confirmed patient into the artificial intelligence model. 5. The method of claim 4,
The processor is
calculating a score according to a contact history between the patient and the confirmed patient based on the location information by time of the patient and location information by time of the confirmed person;
and inputting the biometric information and the score of the patient into the artificial intelligence model to identify whether the patient is negative for the infectious disease. According to claim 1,
The artificial intelligence model is
Among the plurality of RT-PCR-based infectious disease diagnosis results within the quarantine period of a specific patient including one or more negatives and one or more negatives followed by positive, a model trained based on the positive infectious disease diagnosis result, the former Device. According to claim 1,
The artificial intelligence model is
It is a Recurrent Neural Network (RNN) model trained to output the negative probability of the infectious disease based on biometric information continuously input according to a preset period,
The processor is
inputting the biometric information of the patient measured according to the preset period into the artificial intelligence model to obtain a negative probability of the patient for the infectious disease,
and when the acquired negative probability is greater than or equal to a threshold, identifying the patient as negative for the infectious disease. In the training method of an electronic device for training an artificial intelligence model that outputs the negative probability of an infectious disease,
a first training step of training the artificial intelligence model based on biometric information for each cycle of a first plurality of patients with positive results of RT-PCR (Real Time Polymerase Chain Reaction)-based infectious disease diagnosis; and
A second training step of training the artificial intelligence model based on the biometric information for each cycle of a second plurality of patients whose RT-PCR-based infectious disease diagnosis result is negative. 9. The method of claim 8,
Based on the biometric information for each cycle of the third plurality of patients and the RT-PCR-based infectious disease diagnosis result of the third plurality of patients, verifying the AI model; further comprising: a training method. A method for controlling an electronic device, comprising:
inputting the patient's biometric information into an artificial intelligence model trained to predict whether an infectious disease is negative; and
based on the output of the artificial intelligence model, identifying whether the patient is negative for the infectious disease;
The artificial intelligence model is
A method for controlling an electronic device, which is a model trained based on biometric information of a plurality of patients and a result of RT-PCR (Real Time Polymerase Chain Reaction)-based infectious disease diagnosis performed on the plurality of patients. A computer program stored in a computer readable medium,
A computer program stored in a computer readable medium, which is executed by at least one processor of an electronic device to cause the electronic device to perform the control method of claim 10 .

Images