JP6338298B2 - Physical condition monitoring device - Google Patents

Description

  The present invention relates to a physical condition monitoring apparatus capable of acquiring more information by measuring respiration and heart rate, and detecting body information deeper, including sudden changes in health and apnea syndrome.

Various judgments on the physical condition of a subject from body information such as heart rate and respiration rate of the subject such as a human being or an animal are performed. As such a system, a technique (Patent Document 1, Non-Patent Document 1, etc.) for estimating physical condition by taking a thermal image of a traveler's body surface temperature and measuring the body temperature, microwave radar and thermography are used. A system that detects a person who is suspected of a heated person (patent documents 1 to 4, non-patent documents 2 to 4). Etc.) have been proposed.
However, in the systems according to these proposals, it is only possible to determine whether or not a patient is “presence” or “no”, and the accuracy is still not sufficient.
Therefore, an attempt has been proposed to accurately measure the physical condition of the subject as a material for determination by combining these and the blood oxygen concentration.

For example, in Patent Document 5, in order to remotely monitor a more accurate physical abnormality occurrence state for each subject by analyzing multiple acceleration information of a plurality of sites in the subject along with the biological information of the subject, Biological information measuring device that measures at least one of biological information such as blood pressure, pulse rate, respiratory rate, blood oxygen concentration, and acceleration of multiple parts of the subject's legs, arms, head, chest, and waist , An acceleration measuring device that measures the living body information measured together with the subject ID code, acceleration of a plurality of parts, and acceleration information related to a part identification code corresponding to each, and transmitted from the transmitting apparatus A receiving device that receives each information, a processor device that calculates the exercise amount of the subject based on the received acceleration information, and a display device connected to the processor device, the processor device being tested based on the exercise amount Threshold of the biological information is calculated. If the biometric information by comparing the biometric information with the threshold of the subject exceeds the threshold value has been proposed a system for notifying the occurrence of the body abnormality subject.
In Patent Document 6, a general-purpose / upgrade pulse oximeter (UPO) is integrated with three devices for measuring oxygen saturation and related physiological parameters in order to monitor a patient without interruption. A portable unit and docking station with the same functions, the portable unit functions as a handheld oximeter, and the docked portable part and docking station combine to create a stand-alone, high-performance pulsed oxygen analyzer. Systems that function as densitometers have been proposed.
Furthermore, Patent Document 7 discloses a patient's disease or chief complaint at a plurality of past times and vital information including biological information in order to predict the severity of the patient after a predetermined time from biological information acquired by a simple measuring device. Vital data storage unit storing data for each patient, patient's disease or chief complaint at any time for vital data, and biometric information, and patient's severity after a predetermined time at any time By analyzing the relationship, an analysis unit that creates a criterion for determining a disease or chief complaint at an arbitrary time and a severity after a predetermined time of an arbitrary time based on biological information, and a determination target Based on the vital data acquisition unit that acquires the vital data of the patient, the vital data acquired by the vital data acquisition unit, and the criteria created by the analysis unit Te system and a determining severity determining unit severity of predetermined time after time that vital data acquiring unit acquires the vital data has been proposed.

JP 2009-172176 A JP 2008-237377 A JP 2007-58565 A JP 2009-183608 A Japanese Patent Laid-Open No. 2003-220039 JP 2010-012335 A JP2013-148996A

“Introduction of pandemic countermeasure examples using infrared thermography”, “online”, 2010, NEC Avio infrared technology, “June 6, 2013 search”, Internet <URL: http://jpn.nec.com/techrep/journal/ g10 / n03 / pdf / 100312.pdf> “Introduction of pandemic measures by infrared thermography” Sun G, Hakozaki Y, Abe S, Vinh NQ, Matsui T. A novel infection screening method using a neural network and k-means clustering algorithm which can be applied for screening of unknown or unexpected infectious diseases.J Infect. 2012 Dec; 65 (6): 591-2.http: //dx.doi.org/10.1016/j.jinf.2012.10.010 Sun G, Abe S, Takei O, Hakozaki Y and Matsui T. A Novel Non-contact Infection Screening System Based on Self-Organizing Map with K-means Clustering.Communications in Computer and Information Science, 2011 Volume 258, 125-132. http://dx.doi.org/10.1007/978-3-642-27157-1_14 Sun, G., Hakozaki, Y., Abe, S., Takei, O. and Matsui, T. (2013) A neural network-based infection screening system that uses vital signs and percutaneous oxygen saturation for rapid screening of patients with influenza Health, 5, 7-12.doi: 36 / health.2013.58A5002.

However, the conventional apparatus for measuring physical condition proposed in Patent Documents 5 to 7 has a problem that information to be known that has been subdivided sufficiently accurately has not been obtained yet.
In other words, information on physical condition is currently fragmented, and it is not a single information such as simply suspected infectious disease, suffering from some disease, or severe disease state, but more fragmented. It is necessary to obtain highly accurate information in a shorter time. Therefore, development of a device that satisfies these conditions is desired.

  Therefore, the object of the present invention is to monitor the physical condition of the subject in a short time, not as single information such as simply suffering from a disease, but as more detailed and accurate information. To provide an apparatus.

As a result of intensive studies to solve the above problems, the present inventors have calculated not only the pulse and respiratory rate but also the blood oxygen concentration (oxygen saturation (SpO2)) by a predetermined processing method, a short time. The inventors have found that accurate judgment can be made by measurement, and have completed the present invention.
That is, the present invention provides the following inventions.
1. A device for monitoring physical condition from body surface temperature, pulse rate, respiration and blood oxygen concentration,
A blood oxygen concentration measurement unit for measuring the blood oxygen concentration of the subject;
A body surface temperature measurement unit for measuring the body surface temperature of the subject;
A pulse measurement unit for measuring the pulse of the subject;
A respiration rate measurement unit for measuring the respiration rate of the subject;
Processing the data obtained in each of the measurement units according to a predetermined processing method, and calculating a current physical condition of the subject;
A result display unit for displaying a calculation result ;
The predetermined processing method in the arithmetic unit is a method for obtaining determination data by substituting the blood oxygen concentration, body surface temperature, pulse rate and respiratory rate obtained by measurement into a predetermined determination formula. And
A physical condition monitoring device that is a system in which the determination formula is different depending on whether the blood oxygen concentration obtained by the blood oxygen concentration measurement unit is equal to or higher than a predetermined threshold.
2. A second threshold value is set as a blood oxygen concentration value having a higher degree of risk than the threshold value. If the second threshold value is less than the threshold value, each value is assigned to a different determination formula. 2. The physical condition monitoring device according to 1, wherein data for determination is obtained.
3. The predetermined processing method in the arithmetic unit is a method of calculating an integrated distance matrix result using all measurement results and visualizing the result in a two-dimensional map, and a step of clustering each data by a Fuzzy clustering method. 2. The physical condition monitoring device according to 1.

  The physical condition monitoring device according to the present invention can accurately obtain more detailed and accurate information in a short time rather than single information such as whether the subject's physical condition is simply suffering from a disease. It is.

FIG. 1 is an explanatory diagram schematically showing the outline and usage of the physical condition monitoring apparatus of the present invention. FIG. 2 is a schematic diagram showing an outline of the configuration of the physical condition monitoring apparatus of the present invention. FIG. 3 is a chart showing one embodiment of the processing method of the calculation unit in the physical condition monitoring apparatus of the present invention. FIG. 4 is a flow sheet showing one embodiment of the processing method of the calculation unit in the physical condition monitoring apparatus of the present invention. FIG. 5 is a chart showing the results of a preliminary experiment showing the superiority of the treatment method preferably used in the present invention, where (a) is a chart showing the case where the blood oxygen concentration is taken into account, and (b) is the blood oxygen concentration. It is a chart which shows the case where is not considered.

Embodiments of the present invention will be described below with reference to the drawings.
A physical condition monitoring apparatus 1 (hereinafter also simply referred to as “apparatus”) shown in FIGS. 1 and 2 is an apparatus that monitors physical condition from body surface temperature, pulse, respiration, and blood oxygen concentration.
A blood oxygen concentration measurement unit 10 that measures the blood oxygen concentration of the subject, a body surface temperature measurement unit 20 that measures the body surface temperature of the subject, a pulse measurement unit 30 that measures the pulse of the subject, and the respiratory rate of the subject A respiratory rate measuring unit 40 for measuring the data and a calculation unit (not shown in FIG. 1; see FIG. 2) that processes the data obtained by each measuring unit according to a predetermined processing method and calculates the current physical condition of the subject ) And a result display unit 50 for displaying the calculation result.
The overall configuration of the apparatus will be described with reference to FIG.
The apparatus 1 of the present invention can place a hand at the time of measurement, and has a flat plate-like main body 2 with an inclined top surface, a result display unit 50 and a face temperature extending upward from one end of the main body 2. It comprises a measurement display member 4 having a thermography camera (body surface temperature measurement unit) 20 for measurement.
Further, a 10 G-Hz radar (respiration rate measurement unit and pulse measurement unit) 30 (40) constituting a part of the respiration measurement unit is provided at the subject side end of the main unit 2, and wiring ( A blood oxygen measuring terminal (blood oxygen concentration measuring unit) 10 that is freely connected via a not-shown) is provided. Although not shown, the main body is provided with a switch for starting measurement.
This will be described in more detail below.

[Blood oxygen concentration measurement unit]
In the present embodiment, the blood oxygen measuring terminal is configured. Although this terminal is not particularly shown, it is composed of a light emitting part and a light receiving part (sensor). The light emitting part emits red light and infrared light, and these lights are transmitted through or reflected by the fingertips. It can be measured in the department.
In addition, the pulse rate can usually be counted from a pulse wave component with pulsation.
As such a terminal, a commercially available pulse oximeter module (for example, product name “OEMIII” manufactured by NONIN Co., Ltd.) that measures a pulse can be used, and usually the terminal can display a measured value. .

[Body surface temperature measurement unit]
The body surface temperature measurement unit can be configured using a device that can measure the surface temperature, such as a commonly known infrared thermography camera or thermopile element. For example, a commercially available product such as “Thermo Shot F30” manufactured by Nippon Avionics Co., Ltd. It can also be used.

[Pulse measurement unit and respiratory rate measurement unit]
The pulse measuring unit may be used as the above-described blood oxygen measuring terminal or may be used as the respiratory rate measuring unit.
Hereinafter, it will be described with the dual purpose in the description of the respiratory rate measurement unit.
As a respiration rate measurement part (pulse measurement part) used for the present invention, it can be constituted using a measuring device given in the above-mentioned patent documents 1 or JP, 2013-78413, A.
Specifically, for example, a radio wave irradiation unit that is arranged at a different position on the base and radiates radio waves in the same frequency band toward a person to be detected, and radio waves emitted from the radio wave irradiation unit are reflected by the human A microwave transmission / reception device including a radio wave reception unit that receives a radio wave containing physical information including a detection target biological signal having periodicity, and a radio wave analysis unit that analyzes radio waves received by the radio wave reception unit And a device for acquiring physical information related to the respiration and heartbeat to be detected.
The microwave transmission / reception apparatus includes a radio wave irradiation unit and a radio wave reception unit (not shown). The radio wave irradiation unit and the radio wave reception unit are connected to a control unit that controls transmission / reception of radio waves via wiring (not shown). The radio wave receiving unit is further connected to the radio wave analyzing unit via wiring (not shown).

  Although not specifically illustrated, a microwave transmitter and a microwave receiver will be briefly described. A microwave transmitter includes a transmitter that generates a microwave, a transmitter that transmits the generated microwave, and a transmitter. The microwave receiver includes an antenna that transmits the transmitted microwave to the outside, and the microwave receiver is an antenna that receives the microwave and a receiver that transfers the microwave received by the antenna to various devices for radio wave processing. It consists of.

The control unit is for controlling that the radio wave transmission unit and the radio wave reception unit transmit microwaves and receive reflected microwaves. The control unit includes a ROM (read only memory) (not shown) in which programs and data for performing necessary processing are stored, a RAM (random access memory) (not shown) for temporarily storing signal data, a ROM And a CPU (Central Processing Unit) (not shown) that performs predetermined processing stored in the storage device.
The control unit detects the first input signal from the microwave reflected from the person received by the radio wave receiving unit (the microwave reflected from the abdomen), and the first I and Q channel signals from the first input signal. A part of the program is stored so as to generate the first complex signal forming unit including a hardware circuit other than those described above. Then, the difference between the first input signal (received wave) and the reference signal (local wave) of the local transmitter is extracted as an IF signal by a frequency mixer. At this time, two signals of a signal in phase with the first input signal and a signal delayed by 90 degrees are generated. Here, the in-phase component of the first input signal is the first I channel signal, and the quadrature component is the first Q channel signal. The I channel signal and the Q channel signal are a real component and an imaginary component, respectively, in the complex signal representation of the output signal. In the chest microwave transmission / reception apparatus, a similarly configured control unit functions in the same manner.
Then, using these data, the respiratory rate and the pulse rate are calculated, and the calculation result is sent to the calculation unit.
In this embodiment, a commercially available 10 GHz radar (trade name “NJR4175” manufactured by New JRC Co., Ltd.) is used as a measurement radar, and the respiratory rate measurement unit and the calculation unit that sends the obtained data are combined with the measurement radar. It constitutes a pulse measurement unit.

[Calculation section]
The calculation unit is a part that processes data sent from each measurement unit and calculates a discrimination result related to physical condition, and the calculated result is transferred to and displayed on the result display unit.
Such a calculation unit is configured in the same manner as a so-called computer, and includes a ROM (read only memory) (not shown) in which programs and data for performing necessary processing are stored, and a non-illustrated unit for temporarily storing signal data. A RAM (random access memory) shown in the figure, and a CPU (central processing unit) (not shown) that performs predetermined processing stored in a ROM or the like are provided.

(Processing method)
Here, a plurality of methods can be adopted as a processing method by the calculation unit. Each will be explained.
・ Processing method 1
The processing method 1 is a processing method using a Fuzzy clustering method developed from the k-means method. In general, the k-means method is classified as a hard clustering method. In such a clustering method, since the data belongs to only one group, there is a case where data at the boundary portion between the groups is erroneously discriminated. For this reason, even when “presence” or “normal” is determined using a plurality of vital sign data as in the data handled in the present invention, there is an erroneous determination of data at the boundary, which affects the final system determination accuracy.
In order to improve such a weak point of the k-means method, the Fuzzy clustering method is adopted. Unlike the k-means method, the Fuzzy clustering method is a soft clustering method, which allows data to belong to a plurality of clusters, and the degree of belonging to each group (in Fuzzy, it is represented by a membership function from 0 to 1). Classified. By adopting such a processing method, the ambiguity in which the data belongs to the group is left and the data is classified according to the degree to which the data belongs to the group, so that it is possible to reduce misidentification of the boundary portion.
Specifically, the processing method 1 includes the following steps.
A step of calculating an integrated distance matrix (U-matrix) result using all measurement results and visualizing the result on a two-dimensional map (hereinafter referred to as “step A”).
A step of clustering each data into three of a disease group, a disease possibility group, and a healthy person group by the Fuzzy clustering method, or four of which is a serious person group added thereto (hereinafter referred to as “step B”). ).
Both steps will be described in further detail.

Step A:
This is performed using a nonlinear discriminant function method based on a neural network such as Kohonen's Self-Organizing Map (SOM) combined with a k-means clustering algorithm.
For example, in the case of Example 1 described below, first, four parameters of pulse rate, respiratory rate, facial temperature and SpO ₂ from 109 subjects consisting of 45 flu subjects and 64 healthy controls. Using these data, we create a variety of SOM clusters.
Specifically, the measured heart rate, respiratory rate, body surface temperature, and blood oxygen concentration are used as SOM input data.
First, prior to cluster creation, logarithmic distribution normalization is performed on input data as preprocessing. Then, a map that is divided in advance according to the number of samples of the subject as shown in the two-dimensional map of FIG. 3 is prepared. Setting the map size to 3 to 5 times the number of samples (4 times in the example shown in FIG. 3) increases the accuracy of distribution normalization of the created map. This is preferable in that an SOM cluster can be created with little error. For example, when the number of samples is about 100, the map size is 20 × 20, and a map of 400 nodes is prepared.
Next, the optimum SOM parameter to be learned is determined. In the present invention, a Gaussian function is used as the neighborhood function, the initial value of the neighborhood radius is set to 15, the number of learning of the map is 1000 times, and the learning rate of the map is set to 0.05. These settings are particularly effective when executing SOM offline.

Step B:
Clustering is performed by the Fuzzy-C-means method.
For example, after the two-dimensional map is formed based on each data as in the two-dimensional map shown in FIG. 3, the centers of the clusters are set at random in order to further classify them into the three or four clusters described above. Next, the membership value for each cluster of each individual (subject) is obtained, and the degree of affiliation for all clusters is obtained. Then, the center is recalculated for each cluster, and the calculation is performed again from the point of finding the affiliation until all cluster centers do not change, and the process ends when the center does not change. Thereby, as shown in FIG. 3, it can classify | categorize into three clusters, a disease group, a disease possibility group, and a healthy person group.
And it discriminate | determines as follows about the data of the test subject who belongs to the overlapping part in each group.
As described above, the output of Fuzzy clustering is performed by obtaining the membership value of each individual to each cluster. At this time, it is output which group is involved in what proportion. For example, in the case of subject A, when the membership value belonging to the influenza group is 60% and the membership value belonging to the health group is 40%, the data of this individual is output as it is.
Specifically, as shown in FIG. 3, when there are an infected person group, a pseudo-infected person group, and a healthy person group, most of the solids belong to any two groups. In order to obtain a membership value on the assumption that it may belong to two or more groups (in this manner in the K-Means method), the membership values of each group shown in FIG. A part that is unknown as to which group it belongs to, such as an overlapping part, is detected. The size of the overlapping portion varies depending on the membership value setting. In this embodiment, the membership value belonging to any group is equal to or greater than a predetermined value (90% in this embodiment). Is determined to belong to the group, and is handled as individual data belonging to a non-overlapping portion in FIG. 3 (belonging to only one of the groups). If it is less than the predetermined value, it is assumed that it belongs to the overlapping part because it is unknown which group it belongs to. It is determined that the result converges as belonging to a group in which data of a predetermined value (for example, 60%) or more is obtained.
Here, the predetermined value can be set arbitrarily according to the purpose.For example, when determining infection, it is most important to check the infected person, so the membership value is low to eliminate risk factors. (For example, about 30%) is preferably determined as belonging to an infected person or a pseudo-infected person group.

・ Processing method 2
As another processing method, a blood oxygen concentration, a body surface temperature, a pulse rate, and a respiratory rate obtained by measurement are substituted into a predetermined judgment formula to obtain judgment data, wherein the blood It is also possible to adopt a method in which the determination formula is different depending on whether the blood oxygen concentration obtained by the intermediate oxygen concentration measurement unit is equal to or higher than a predetermined threshold.
This processing method will be described with reference to the flow sheet shown in FIG.
The blood oxygen concentration is extracted from the obtained data, and the blood oxygen concentration is sorted according to the risk of physical condition deterioration. That is, it is divided into a case where the blood oxygen concentration is 95 or more and a case where it is less than 95.
Then, the judgment is performed by different judgment formulas, and information on various physical condition states such as healthy, suffering from some illness, suspected morbidity, and severe is calculated.

The discriminant and the discriminant used at this time will be described in detail.
When SpO ₂ ≧ 95: In this case, discrimination is performed using discriminant 1.
Discriminant 1: y ₁ = aX ₁ + bX ₂ + cX ₃ + d
Here, X ₁ + X ₂ + X ₃ indicate a heart rate, a respiratory rate, and a face surface temperature, respectively.
Each of a, b, c, and d is a variable, and is specifically calculated as follows.
(Variable determination method)
The optimal coefficients a, b, c, and d based on a predetermined number of pre-measured vital sign data for subjects diagnosed as prevalent (for example, infection with influenza) and healthy subjects in the control group are: It is determined.
For example, when determining each coefficient, X ₁ , X ₂ , and X ₃ are explanatory variables, and Y is an objective variable. The objective variable Y is set to “0” when the patient is ill and “1” when the patient is healthy. In addition, X ₁ , X ₂ , and X ₃ of the measured overall prevalence and healthy subjects are substituted for the differential equation by substituting the values of heart rate, respiration rate, and face surface temperature into discriminant 1, respectively. Ask. The solution is obtained by determining the optimum coefficients a, b, c, and d satisfying the conditions for minimizing the distance within each group by increasing the distance between the group of the affected group and the healthy group as much as possible. .
If y ₁ > 0, it is determined that the patient is in a healthy state (“healthy” in FIG. 4). Further, when y ₁ ≦ 0, it is determined that “the physical condition is not good (“ affected ”in FIG. 4)”. In particular, when monitoring an infectious disease, it is determined that “the infection is suspected”.

When SpO ₂ <95: At this time, discrimination is performed using discriminant 2.
Discriminant 2: y ₂ = eX ₁ + fX ₂ + gX ₃ + h
Here, X ₁ + X ₂ + X ₃ indicate a heart rate, a respiratory rate, and a face surface temperature, respectively.
Each of e, f, g, and h is a variable, and is calculated in the same manner as the variable determination method described above.
When y ₂ > 0, it is determined that “the physical condition is not good (“ severe morbidity ”in FIG. 4). In particular, in the case of monitoring for infectious diseases, it is determined that “the risk of infection is high”. Further, when y ₂ ≦ 0, it is determined that “physical condition is not good (“ severe disease ”in FIG. 4)”. In particular, when monitoring an infectious disease, it is determined that “the probability of infection is high”.
Thus, by determining the threshold value based on the blood oxygen concentration and changing the discriminant formula and the discrimination criterion based on this threshold value, the physical condition can be grasped with higher accuracy. This is because only SpO ₂ shows an abnormal value, but it is rather dangerous in the group where other vital signs such as pulse and respiratory rate show normal values, and in physical condition that can not be distinguished on the surface The present inventors have made it clear through research that the “high risk group” is lurking. If SpO ₂ is not added, such a “high risk group” is misjudged and judged as “healthy”, but SpO ₂ has been added to the criteria for judgment, and this SpO ₂ The physical condition can be monitored with higher accuracy by changing the discriminant according to the threshold value.
In addition, the combination of SpO ₂ and conventional vital signs is used in the determination of infectious diseases, and the four phases “health”, “group suspected of infection (“ affected ”in FIG. 4)”, “high risk of infection ( High risk) group ("Suspected seriousness" in Fig. 4) "and" Group with high probability of infection ("Severe seriousness" in Fig. 4) ". Can be removed.

Further, a second threshold value is set as a blood oxygen concentration value having a higher degree of risk than the threshold value. If the threshold value exceeds the threshold value and further exceeds the second threshold value, each value is substituted into a different determination formula. You can also get data.
Specifically, the blood oxygen concentration is extracted from the obtained data, and the blood oxygen concentration is sorted according to the risk of physical condition deterioration. First, the case of 95 or more is divided into the case of 90 or more and the case of less than 90.
Then, the judgment is performed by different judgment formulas, and information on various physical condition states such as healthy, suffering from some illness, suspected morbidity, and severe is calculated.

(Result display section)
The result display unit is configured by a liquid crystal display in the present embodiment. The present invention is not limited to this, and various configurations are possible.

〔how to use〕
When using the apparatus of the present embodiment, as shown in FIG. 1, gently sit or stand in front of the apparatus, insert a finger into the blood oxygen measurement terminal, and press the switch to start measurement.
By measuring for a predetermined time (preferably 15 seconds to 3 minutes), the result of the physical condition is displayed on the display unit.

(Example of change)
The physical condition monitoring device of the present invention has been described in detail above, but the present invention is not limited to these examples, and various modifications can be made within the scope of the gist of the present invention described in the claims. Is possible.
For example, although the subject is a human (subject, subject), the present invention is not limited to this. For example, the present invention can be applied to other living bodies such as animals. In this case, it is necessary to set the diseased body discriminant according to the living body. The thermal image captured by the thermographic apparatus is not limited to the thermal image of the face of the subject, and for example, it is possible to capture a thermal image in another range where the skin is exposed. The position measured by the heart rate measuring device is not limited to the palm measurement position or the back measurement position, and is set to a height corresponding to the average heart height of the human being as the subject, for example. It is also possible to perform measurement at a chest measurement position where irradiation and reception of the heart rate measurement microwave can be performed on the chest of the subject.

The heart rate measuring device CR measures the heart rate in a non-contact manner by being constituted by a so-called microwave radar antenna that irradiates and receives the heart rate measurement microwave for measuring the heart rate on the subject. However, the present invention is not limited to this. For example, a so-called laser blood flow meter (for example, Japanese Patent Application Laid-Open No. 10-290791) that irradiates and receives the heart rate measurement laser light for measuring the heart rate on the subject. In other words, it is possible to measure the heart rate in a non-contact manner.
It is desirable that the subject can be configured to be able to measure the respiration rate and heart rate in a non-contact manner. However, the present invention is not limited to this. For example, the subject can be measured by attaching an electrode, a sensor, or the like. It is. In addition, for example, the heart rate can be measured by measuring a fingertip volume pulse wave that is a blood volume fluctuation of the fingertip of the subject, that is, a so-called pulse wave.

  When it is determined that the subject is the diseased body, the determination result is displayed on the determination result display unit. However, the present invention is not limited to this. It is also possible to notify the user of the client personal computer PC or the like.

  EXAMPLES Hereinafter, although an Example demonstrates this invention further more concretely, this invention is not limited to these.

[Example 1]
The following is an example executed in February 2012 at the SDF Central Hospital.
First, 45 influenza subjects diagnosed with type A influenza using the QuickVue Rapid SP Influ test (Quidel Corp., USA) were collected.
All influenza subjects were treated with oseltamivir and zanamiburu, with an average body temperature of 36.7 ± 0.7 ° C (35.8 ° C <body temperature (armpit temperature) <40.0 ° C).
Apart from this, 64 healthy controls without cold symptoms were collected. The average body temperature of healthy controls was 36.5 ± 0.4 ° C. (35.0 ° C. <body temperature (armpit temperature) <37.5 ° C.).
About these influenza test subjects and healthy controls, physical condition was determined using the apparatus of the present invention as shown in FIG. The determination time was 15 seconds for each person, and the measurement was performed in a state of being quietly seated in front of the apparatus as shown in FIG.
Results (comparative examples) determined by the k-means method are shown in FIGS. 5 (a) and 5 (b).
As shown in FIG. 5 (a), in the apparatus of the present invention in which blood oxygen concentration is taken into account, as a result of screening by the k-means method, 40 out of 45 flu subjects are flu groups (lower clusters). Among the 64 healthy controls, 60 were classified into the healthy group (upper cluster). Five of the influenza subjects (marked with a circle) were misdiagnosed as healthy individuals, and four of the healthy subjects (those marked with a circle) were misdiagnosed as influenza.
In addition, as shown in FIG. 5 (b), when the blood oxygen concentration is not taken into consideration (comparative example), 35 out of 45 flu subjects are included in the flu group from the same subject and control data, It shows that 54 persons out of 64 healthy persons are included in a healthy person group. As a result, 10 influenza subjects were misdiagnosed as healthy individuals, and 10 healthy subjects were misdiagnosed as influenza patients.
From these, calculations were performed to determine what the misdiagnosis factors were. The results are shown in Table 1. Thus, among sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV), sensitivity and negative predictive value are the most important as indicators of mass screening, and include SpO ₂ as a screening parameter. As a result, it was found that the sensitivity and the negative predictive value were improved.
As described above, the determination accuracy is improved by using SpO ₂ , but the accuracy is further improved by using the processing method 1.
That is, in the visualization step, a map visualized in multiple colors as shown in the two-dimensional map of FIG. 3 is used, and a clustering step of processing method 1 is performed using this map, which is shown in the chart “Membership distribution of FCM” of FIG. Thus, it can classify | categorize into three, an infected person group, a suspicious infection group, and a healthy person group, and also can allow the part which overlaps each.
Then, by determining the overlapping portion in the same manner as the determination in the above-described step B, it is possible to determine the infected person and the suspected infection with a high degree of accuracy with as few misdiagnosis as possible.

Further, the threshold value in the blood oxygen concentration described in the processing method 2 described above was used, and the determination was performed using the discriminants 1 and 2.
As a result, 3 out of 10 flu subjects who were determined to be healthy when the blood oxygen concentration shown in FIG. 5 (b) was not taken into account (comparative example) were identified as “persons with a high probability of infection”. It was identified as an “infection group” and three more were diagnosed as a “high risk of infection” group. That is, there were only 4 misdiagnosis, and it was possible to discriminate with higher accuracy than when the blood oxygen concentration was simply taken into account.

  The present invention is useful for easily and easily grasping the health condition at home, hospital, public institution and the like. In addition, since the severity that is not apparent on the surface can also be determined with a high probability, persons with high risk of pandemic can be isolated with high probability at hospitals and immigration offices, including influenza (including new influenza) and Ebola hemorrhagic fever. It is also useful as an apparatus for use in suppressing the scale expansion of infectious diseases such as

1: Physical condition monitoring device

Claims (3)

A device for monitoring physical condition from body surface temperature, pulse rate, respiration and blood oxygen concentration,
A blood oxygen concentration measurement unit for measuring the blood oxygen concentration of the subject;
A body surface temperature measurement unit for measuring the body surface temperature of the subject;
A pulse measurement unit for measuring the pulse of the subject;
A respiration rate measurement unit for measuring the respiration rate of the subject;
Processing the data obtained in each of the measurement units according to a predetermined processing method, and calculating a current physical condition of the subject;
A result display unit for displaying a calculation result;
The predetermined processing method in the arithmetic unit is a method for obtaining determination data by substituting the blood oxygen concentration, body surface temperature, pulse rate and respiratory rate obtained by measurement into a predetermined determination formula. The determination formula is different depending on whether the blood oxygen concentration obtained by the blood oxygen concentration measurement unit is equal to or higher than a predetermined threshold value and less than the predetermined threshold value. Monitoring device.
A second threshold value is set as a blood oxygen concentration value having a higher degree of risk than the above threshold value, and if it is less than the above threshold value and further less than the second threshold value, each value is assigned to a different judgment formula. to obtain data for the determination according to claim 1 physical condition monitoring apparatus according.
The predetermined processing method in the arithmetic unit is a method of performing a step of calculating an integrated distance matrix result using all measurement results, visualizing the result in a two-dimensional map, and a step of clustering using a Fuzzy clustering method. 1. The physical condition monitoring device according to 1.