JP2021047871A - Watching system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a monitoring system capable of monitoring a patient by treating and treating a patient based on a common biological signal in various medical sites such as a hospital, a clinic, and home medical treatment. SOLUTION: The biological information of a user is detected, and further, the illuminance and noise of the environment are detected. Then, the accuracy of the biometric information is determined based on the illuminance and noise, and when the biometric information is accurate, an abnormality determination is performed using the biometric information, and when the biometric information is not accurate, the biometric information is described. Abnormality determination is performed using the biological information obtained by modifying the biological information based on the illuminance and noise. At this time, when a desired number of biometric information of the first user is accumulated in the storage unit, machine learning is used to calculate a second reference adjusted to the first reference, and the first user's biometric information is calculated. Based on the biological information or the corrected biological information and the second criterion, the abnormality of the first user is determined. [Selection diagram] Fig. 2

Description

The present invention relates to a monitoring system capable of sharing a patient's biological signal in hospitals, clinics, long-term care facilities, home care, and the like.

Biosignals such as pulse and respiration are measured on the hospital bed using a hospital biosignal detector when the patient is admitted to the hospital. On the other hand, when the patient leaves the hospital and obtains the same biological signal at a clinic near his / her home, the biological signal detection device provided in the clinic is used. In addition, when the patient is receiving medical treatment at home, the biological signal is detected by using the biological signal detection device installed at home. However, the detected values of these biological signals are limited to use in hospitals, clinics and homes. In that case, the characteristics unique to each detection device may affect the accuracy of the detection result and cause variations in the diagnosis of the doctor or the nurse.

In addition, a breathing pattern for reporting of a patient is registered in advance, and when the breathing pattern detected by the breathing pattern detecting means matches this breathing pattern for reporting, a communication line is sent to a remote medical management server. A medical device and a home medical system for reporting via the above have been proposed (Patent Document 1).

Patent No. 4607365

However, the conventional monitoring technique described in Patent Document 1 requests an emergency hospital or the like to be urgently dispatched via a server when an abnormality occurs in breathing during home medical treatment, and from the time of home medical treatment. , Hospitals and nearby clinics, etc., do not watch over patients.

The present invention has been made in view of the above problems, and the patient is treated and treated based on a common biological signal in various medical settings such as hospitals, clinics, and home medical treatments. The purpose is to provide a patient watching system that can be used.

The monitoring system according to the present invention is
A detection unit that detects the illuminance and noise of the environment that detects the biometric information of the user, which is continuous data, and detects the biometric information.
A first criterion used for determining an abnormality in biometric information, a storage unit capable of holding biometric information for each user, and a storage unit.
Based on the illuminance and noise, the accuracy of the biometric information is determined, and when the biometric information is accurate, an abnormality determination is performed using the biometric information, and when the biometric information is not accurate, the biological body is determined. When an abnormality is determined using the biometric information obtained by modifying the information based on the illuminance and noise and a desired number of biometric information of the first user is accumulated in the storage unit, machine learning is used to perform the first method. The second standard adjusted from the first standard is calculated, and the abnormality of the first user is determined based on the biometric information or the corrected biometric information of the first user and the second standard, and the second user is used. When the desired number of biometric information is not stored in the storage unit, the abnormality of the second user is determined based on the biometric information of the second user or the modified biometric information and the first criterion. Control unit and
To be equipped.

In this watching system
For example
The detection unit includes a sheet-shaped bag laid under the user and a piezoelectric sensor installed in the bag, and the piezoelectric sensor detects fluctuations in air pressure in the bag.

Also, in this watching system,
For example
The detection unit includes a load sensor provided on the bed used by the first user or the second user, detects the presence or absence of the bed of the first user or the second user from the bed, and the detection unit. Calculate the movement of the center of gravity position on the bed of the first user or the second user,
The control unit determines whether or not the first user has an abnormality in the range of movement of the center of gravity position of the first user based on the second criterion, and determines whether or not the first user has an abnormality in the movement range of the center of gravity position of the second user. It is determined whether or not the second user has an abnormality in the range of movement based on the first criterion.

Further, in the present invention,
The detection unit includes a first sensor and a second sensor.
The storage unit holds the biological information of the first user acquired by the first sensor, and holds the biometric information of the first user.
The control unit calculates the second reference based on the biological information of the first user acquired by the first sensor.
The control unit can determine the abnormality of the first user based on the biological information of the first user acquired by the second sensor and the second criterion.

Furthermore, the control unit can notify the outside when it is determined that there is an abnormality.

According to the present invention, a biological signal with an ID (identification symbol) associated with a patient and a detection device is stored in a server, and the data of this server is analyzed in real time by machine learning and continuously updated. Therefore, data suitable for the patient can be stored. As a result, the mutation point suitable for each patient can be stored in the server, so that when the control unit determines that the abnormality is abnormal, the execution unit can issue a suitable alarm signal or the like.

The biological signals stored in this server are, for example, respiratory signals, but are not limited to these, and various biological signals can be stored in the server, so that any biological signal necessary for treatment or medical treatment for one patient can be stored. Can be stored and the biological signal can be grasped in association with the detection device. In addition, not only doctors at hospitals (first medical institutions) but also doctors at family clinics (second medical institutions) near their homes can access this server to obtain living organisms at the first medical institution. The signal can be grasped together with the detection device. Therefore, all medical institutions related to one patient can appropriately make a diagnosis for that patient based on the common data shared, and the accuracy and efficiency of diagnosis are extremely improved. In addition, since the same device can be used to diagnose the patient's medical condition based on continuous data at all hospitals, clinics, and homes, it is possible to accurately grasp the mutation point of the patient's biological signal.

It is a block diagram which shows the watching system which concerns on embodiment of this invention. It is also a conceptual diagram.

Hereinafter, embodiments of the present invention will be specifically described with reference to the accompanying drawings. As shown in FIG. 1, at a specific medical institution (first medical institution), various biological signals are acquired from the detection device 1 by the detection device 1, and the basics such as the patient's name are obtained from the input device 2. In addition to the information being input, so-called medical record information such as the diagnosis result is further input. Then, the diagnostic information (medical record information) of these patients and the information of the detection device 1 are input to the ID assigning device 3, the patient's diagnostic information and the detection device information are associated with each other, and one ID is assigned. Will be done. The patient information to which this ID is given and also includes the information of the detection device is input from the ID giving device 3 to the server 4 and stored. In the storage device of the server 4, the normal respiratory rate of the patient is input and stored from the biological signal, and the data regarding the type of the detection device when the respiratory rate or the like is detected is also stored in the same ID. It is stored in association. The biological signals detected by the detection device 1 include data indicating the physiological state of the patient's human body such as respiratory rate, heart rate, body temperature, blood pressure, SPO2 (arterial oxygen saturation) and body weight, as well as on the bed. There is data showing the behavioral state of the human body such as body movement and falling from the bed (getting out of bed), and it is a detection signal of various patient states. All of these are data that contribute to the diagnosis of patients. Further, the information detected by the detection device 1 may include environmental signals such as temperature, humidity, illuminance and noise in addition to biological signals. This environmental signal is processed from various angles using this environmental signal at the time of data analysis as to whether or not the measured biological signal data is accurate, thereby determining the accuracy of the measured biological signal. Used to fix.

The control unit 5 reads out the data stored in the server 4 and determines whether or not the respiratory rate or the like grasped from the current biological signal is within the normal normal range of the patient. Then, when this biological signal deviates from the normal normal range of the patient, the control unit 5 outputs an abnormal signal to the executing unit 6, and the executing unit 6 executes processing based on the abnormal signal.

As shown in FIG. 2, the detection device 1, the input device 2, and the ID assigning device 3 are provided for each medical institution or each medical facility including a home. That is, the medical facility 10 including the detection device 1, the input device 2, and the ID assigning device 3 is provided in, for example, a hospital or the like, and the test data (biological signal) and the diagnosis result (medical record) acquired by this medical institution are provided. Information) is stored in the server. A nearby clinic, which is another medical institution (second medical institution), is also equipped with a medical facility 10a including a detection device 1a, an input device 2a, and an ID assignment device 3a. Similarly, a medical facility such as a home is also provided with a medical facility 10b including a detection device 1b, an input device 2b, and an ID assigning device 3b. Each of the medical facilities 10, 10a and 10b is provided with output devices 7, 7a and 7b, respectively, and patient information stored in the server 4 is transmitted via the output devices 7, 7a and 7b. , Will be acquired. The diagnosis result (medical record information) may be known only to each medical institution, and the diagnosis result (medical record information) may not be normally known to other medical institutions.

The detection device 1 includes, for example, a respiratory rate sensor. As this respiratory rate sensor, there is one in which air is sealed in a sheet-shaped bag and a piezoelectric sensor detects fluctuations in the pressure of the air. This sheet-shaped sensor is placed under the patient on the bed (between the patient and the bed), and the state in which the air pressure changes according to the patient's breathing is detected by the piezoelectric sensor to detect the patient's respiratory rate. be able to. This normal range of respiratory rate is set in the server 4. Further, a load sensor is provided on a support column or the like that supports the frame of the bed, and based on the load detection value of the load sensor, it is possible to detect whether the patient is on the bed or is out of bed. .. Furthermore, by detecting the load applied to the struts on the four struts and calculating the position of the center of gravity on the bed, whether or not the patient on the bed is in the sitting position of the bed and is about to leave the bed. Can be predicted. Furthermore, the movement of the patient on the bed can be detected by moving the position of the center of gravity. For example, the normal range of the amount of movement of the center of gravity is set in the server 4. From these detection results, the behavior of the patient on the bed can be predicted.

Next, the operation of the monitoring system configured as described above will be described. For example, as a biological signal, a normal range of respiratory rate is stored in the server 4. The normal range of respiratory rate stored in the server 4 is, for example, 12 to 20 times / minute as a default reference. Then, each time the patient's respiratory rate specified by this ID is measured in this hospital, this data is input to the server 4, and the true normal range of the patient's respiratory rate is machine-learned. As a default reference, the normal range of respiratory rate considered standard for all patients and detection device 1 (respiratory sensor) is set in the server 4, and the measured value of the patient's biological signal is usually from this normal range. When it comes off, the control unit 5 outputs an abnormal signal to the execution unit 6 and instructs the execution unit 6 to issue an alarm or the like. However, this normal range is considered to be patient-specific and peculiar, and the measured respiratory rate may be abnormal for one patient but not for another. The control unit 5 machine-learns such a normal range of respiratory rate peculiar to the patient each time a biological signal is input to the server 4. For example, when the detected value of the respiratory rate of this patient is often 10 to 20 times / minute, the normal range of the respiratory rate of this patient is corrected by setting the range of 10 to 20 times / minute as the normal range. To do. That is, each time the respiratory rate biological signal is input to the server 4, the control unit 5 corrects the mutation point of the respiratory rate biological signal, that is, the upper limit value and the lower limit value of the normal range. By such machine learning, the control unit 5 corrects the mutation point of the patient specified by the ID, and sets the mutation point peculiar to the patient in the server 4. In addition, this ID is linked not only to the patient but also to the detection device that acquired the biological signal, so that the appearance of the detected value of the respiratory rate based on the individuality of the detection device can be taken into consideration. .. If the detector is of a different type, slight fluctuations can occur, even if the patient's respiratory rate itself does not change. Therefore, the ID is associated not only with information about a specific patient but also with the type of detection device that acquires the biological signal.

When the patient is discharged from the hospital and is being treated at home, or is being treated or examined at his / her local clinic, the biological signals and medical record information detected in the same manner are transmitted to the server 4. Is stored. In this way, the biological signal of the patient, the detection device, and the medical record information are stored in the server 4 based on the ID, and any doctor at any medical institution can access and output the server 4. The information can be extracted by the devices 7, 7a and 7b. Therefore, the doctor can grasp the biological signal when the examination is performed at another medical institution, which contributes to the realization of appropriate treatment.

In this way, for example, in the case of respiratory rate, the patient's unique normal range modified by machine learning is set in the server 4. Therefore, when the patient is discharged from the hospital and is being treated at home, even if the patient has an abnormality and the respiratory rate deviates from the normal range, the control unit 5 causes the abnormality via the execution unit 6. Notify the outside. Notification of this abnormality may be given to a hospital or clinic, in which case a doctor or the like visits the patient's home via the hospital or clinic that detected the abnormality, or is related to a medical institution. The person will call the patient's home to understand the degree of the abnormality, and if necessary, transport the patient to the hospital or clinic by ambulance or the like. Alternatively, the execution device 6 notifies the family or relatives of the patient of the abnormality of the patient and calls attention to the family or relatives. The transmission of this abnormal signal is based on the normal range peculiar to the patient, and is not the normal range that is suitable for the general majority of people. Therefore, it is necessary to transmit an extremely accurate abnormal signal. Can be done.

As described above, the biological signals are not limited to the respiratory rate, but also the heart rate, body temperature, blood pressure, SPO2 (arterial oxygen saturation), weight, sleep state, body movement on the bed, and falling from the bed (getting out of bed). There are various patient state detection signals such as. In any case, the respiratory rate, heart rate, sleep state, body movement distance, etc. can be corrected by machine learning to correct the normal range peculiar to the patient, and more accurate abnormality determination can be performed.

Further, the server 4 may be installed in a hospital that is the basis of patient treatment, but it is not necessarily such a large hospital, and there are various installation modes such as a private facility. In addition to hospitals and clinics, it goes without saying that there are nursing care facilities and the like as facilities where patients need medical care.

1,1a, 1b: Detection device 2,2a, 2b: Input device 3,3a, 3b: ID assignment device 4: Server 5: Control unit 6: Execution unit 7,7a, 7b: Output device 10,10a, 10b: Medical equipment

Claims (4)

A detector that detects biological information including the movement of the center of gravity of the user on the bed,
A storage unit capable of holding a first criterion including a normal range of the amount of movement of the center of gravity position used for determining an abnormality related to the fall of the user from the bed, and biological information for each user.
When a desired number of biometric information of the user is accumulated in the storage unit, machine learning is used to calculate a second criterion peculiar to the user, which is a modification of the first criterion, and the living body of the user. When the abnormality of the user is determined based on the information and the second criterion and the desired number of biometric information of the user is not stored in the storage unit, the biometric information of the user and the first biometric information of the user are not stored. Based on the criteria, a control unit that determines an abnormality of the user and predicts whether or not the user is sitting on the edge of the bed and is about to leave the bed.
A watching system equipped with. The detection unit includes a sheet-shaped bag laid under the user and a piezoelectric sensor installed in the bag, and the piezoelectric sensor detects fluctuations in air pressure in the bag. The monitoring system according to claim 1. The detection unit includes a first sensor and a second sensor.
The storage unit holds the biometric information of the user acquired by the first sensor, and holds the biometric information of the user.
The control unit calculates the second reference based on the biometric information of the user acquired by the first sensor.
The monitoring system according to claim 1 or 2, wherein the control unit determines an abnormality of the user based on the biological information of the user acquired by the second sensor and the second criterion. The monitoring system according to any one of claims 1 to 3, wherein the control unit notifies the outside when it is determined to be abnormal.

Images