JP6948497B1 - Biometric information evaluation system and biometric information evaluation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To estimate the possibility of a symptom of a disease by estimating a hormone level or the like. A biological information evaluation system includes a biological information acquisition means for acquiring information on blood cell count, enzyme, lipid, and nitrogen-containing component as biological information for evaluation, previously acquired biological information for reference, and a pituitary gland. Using the degree of association with the evaluation result consisting of the hormone level secreted from the above three or more stages, the above evaluation result for the reference biometric information according to the evaluation biometric information acquired by the biometric information acquisition means 3 It is characterized by comprising an estimation means for estimating the above evaluation result based on the degree of association of steps or more. [Selection diagram] Fig. 5

Description

The present invention relates to a biometric information evaluation system and a biometric information evaluation program, and more particularly to a biometric information evaluation system and a program for estimating evaluation results for evaluation biometric information such as blood cell counts newly acquired by using artificial intelligence.

Conventionally, it has been practiced to predict the name of a disease that is likely to develop based on the result of a previously acquired health diagnosis (health diagnosis data). For example, Patent Document 1 incorporates, for example, medical examination data of a user's BMI and blood glucose level measurement result, predicts the user's future blood glucose level based on these results, and further uses the predicted blood glucose level. A risk-onset predictor that predicts the risk of developing diabetes in a user is disclosed.

Furthermore, in recent years, the name of a disease has been predicted using artificial intelligence. For example, Patent Document 2 discloses a technique for predicting a user's disease using artificial intelligence. Specifically, the health estimation system shows the possibility of suffering from each disease such as arteriosclerosis based on the storage unit in which the medical examination data such as BMI and corsterol are stored and the medical examination data read from the storage unit. It is equipped with an estimation unit that calculates. Further, Patent Document 1 describes that the estimation unit may estimate the probability of suffering from each disease by machine learning such as a neural network.

Japanese Patent No. 6659049 JP-A-2019-79532

By the way, the test items obtained from the medical examination data are diverse, and items that are related to a specific disease and items that are not related to the specific disease are mixed. Therefore, even if there is a need to predict a specific disease, a technique that can fully utilize the test items that lead to the prediction of the symptom has not yet been proposed.

Therefore, the present invention has been devised in view of the above-mentioned problems, and an object of the present invention is to estimate that there is a possibility of a symptom of a disease by estimating a hormone level or the like. The purpose is to provide an effective biometric information evaluation system and program.

The biological information evaluation system to which the present invention is applied is a biological information acquisition means for acquiring information on blood cell counts, enzymes, lipids, and nitrogen-containing components as biological information for evaluation, previously acquired biological information for reference, and hormones. Using the three or more levels of association with the evaluation result consisting of values, the three or more levels of association with the evaluation result for the reference biological information according to the evaluation biological information acquired by the biological information acquisition means. Based on the above, the estimation means is provided with an estimation means for estimating the evaluation result, and the estimation means includes pineapple, hypothalamus, pituitary gland, thyroid gland, parathyroid gland, thoracic gland, heart, vascular endothelium, gastrointestinal tract, pancreatic Langerhans island, Using the degree of association with the evaluation result consisting of the above hormone levels secreted from any of the liver, white adipose tissue, adrenal gland, kidney, gonad, placenta, semen, lung, brain, and skin, as the above evaluation result , It is characterized in that it is possible to estimate the site where there is a possibility of having a hormonal system disease.

The biometric information evaluation program to which the present invention is applied includes a biometric information acquisition step of acquiring information on blood cell count, enzymes, lipids, and nitrogen-containing components as biometric information for evaluation, previously acquired biometric information for reference, and hormones. Using the degree of association with the evaluation result consisting of values in three or more stages, the degree of association with the evaluation result in three or more stages with respect to the reference biological information according to the evaluation biological information acquired in the biological information acquisition step. In the above estimation step, the pineal gland, hypothalamus, pituitary gland, thyroid gland, parathyroid gland, thoracic gland, heart, vascular endothelium, gastrointestinal tract, and pancreatic Langerhans island are executed. , Liver, white adipose tissue, adrenal gland, kidney, gonad, placenta, semen, lung, brain, skin. It is characterized in that it is possible to estimate even a site having a possibility of having a hormonal system disease.

According to the present invention having the above-described configuration, it is possible to estimate that there is a possibility of a symptom of a disease by estimating a hormone level or the like.

FIG. 1 is a block diagram showing an overall configuration of a biometric information evaluation system in which a biometric information evaluation program to which the present invention is applied is implemented. FIG. 2 is a diagram showing biological information for reference and attribute information for reference. FIG. 3 is a diagram showing the evaluation results. FIG. 4 is a diagram showing a specific configuration example of the estimation device. FIG. 5 is a diagram showing an example of the degree of association that uses biological information for reference as an input parameter and outputs an evaluation result as an output solution. FIG. 6 is a diagram showing another example of the degree of association that uses biometric information for reference as an input parameter and outputs an evaluation result as an output solution. FIG. 7 is a diagram showing another example of the degree of association in which the reference biological information and the attribute information are used as the input parameters and the evaluation result is output as the output solution. FIG. 8 is a diagram showing an example of the degree of association in which attribute information is used as an input parameter and an evaluation result is output as an output solution. FIG. 9 is a diagram showing the measurement results of hyperthyroidism. FIG. 10 is a diagram showing the measurement results of hypothyroidism.

Biometric Information Evaluation System Hereinafter, the biometric information evaluation system to which the present invention is applied will be described in detail with reference to the drawings.

FIG. 1 is a block diagram showing an overall configuration of a biological information evaluation system 1 to which the present invention is applied. The biological information evaluation system 1 includes an information acquisition unit 9, an estimation device 2 connected to the information acquisition unit 9, and a database 3 connected to the estimation device 2.

The information acquisition unit 9 is a device for a person (user) who uses this system to input various commands and information, and specifically, is composed of a keyboard, buttons, a touch panel, a mouse, a switch, and the like. The information acquisition unit 9 acquires various biological information such as a user's blood cell count, enzymes, lipids, and nitrogen-containing components. The information acquisition unit 9 is not limited to a device for inputting text information, and may be configured by a device such as a microphone that can detect voice and convert it into text information. Further, the information acquisition unit 9 may be configured as an image pickup device capable of capturing an image of a camera or the like. The information acquisition unit 9 may be configured by a scanner having a function of recognizing a character string from a paper-based document. Further, the information acquisition unit 9 may be integrated with the estimation device 2 described later. The information acquisition unit 9 outputs the detected information to the estimation device 2. The information acquisition unit 9 may be configured by means for automatically fetching character strings and data posted on a site on the Internet.

Various information necessary for obtaining the evaluation result is accumulated in the database 3. In the database 3, in addition to the reference biometric information indicating the user's biometric information, the reference attribute information which is the information related to the user's attribute is stored. This reference biometric information is typically medical examination data, and is data on previously acquired hematology and biochemical test results.

FIG. 2 shows specific examples of reference biological information and reference attribute information. The reference biological information corresponds to, for example, the test results of a hematology test, a biochemical test, a blood information, a general test, and an immunology test among the medical examination data. Hematological tests include, but are not limited to, blood cell counts, morphological tests, and coagulation / fibrinolysis tests. The blood cell count is the number of red blood cells (RBC). Biochemical tests include, but are not limited to, enzyme activity tests, protein tests, lipid-related tests, glucose metabolism tests, nitrogen-containing component tests, electrolyte tests, biopigment-related tests, metal tests, and the like. .. Of these, the enzyme is a result indicated by the values of ALP, AST (GOT), ALT (GPT), etc. obtained by the enzyme activity test in the biochemical test. The lipid is a result indicated by the values of γ-GTP, HDL-C, LDL-C, etc. obtained by the lipid-related test among the biochemical tests. The nitrogen-containing component is a result indicated by the value of URIC_ACID (uric acid) obtained by the nitrogen-containing component test in the biochemical test. The general test is, for example, a urine test, but is not limited to this. Immunological tests are, but are not limited to, infectious disease-related tests and protein tests.

The reference attribute information is information related to the user's attributes, and is, for example, a user other than medical examination data such as age, gender, blood type, height, weight, medical history information, medication history information, and hospital visit history information. Contains all the information about. Note that FIG. 2 shows the gender of the reference attribute information.

Information on the evaluation results is also accumulated in the database 3. The evaluation result includes the evaluation result consisting of the hormone level secreted from the pituitary gland or the evaluation result consisting of the hormone level secreted from the thyroid gland, and is an index showing, for example, how prone the user is to have hyperthyroidism or hypothyroidism. be. Hyperthyroidism is a disease in which thyroid hormone is excessively secreted, and hypothyroidism is a disease in which thyroid hormone is insufficiently secreted.

FIG. 3 shows an example of the evaluation result. The evaluation result is, for example, a hormone as a major item. Hormones include pineal gland, hypothalamus, pituitary gland, thyroid gland, parathyroid gland, chest line, heart, vascular endothelium, gastrointestinal tract, pancreatic islets of Langerhans, liver, white adipose tissue, adrenal gland, kidney, etc. It includes, but is not limited to, the reproductive line, placenta, semen / lung / brain, and skin. Hormones secreted by the pineal gland include, but are not limited to, sub-items such as melatonin. Hormones secreted from the hypothalamus include, for example, growth hormone-releasing hormone, prolactin-releasing hormone, thyroid stimulating hormone-releasing hormone, corticostimulatory hormone-releasing hormone, luteinizing hormone-releasing hormone, growth hormone-suppressing hormone, and prolactin-releasing hormone. Including, but not limited to. Hormones secreted from the pituitary gland (pituitary hormones) are sub-items such as growth hormone, prolactin, thyroid stimulating hormone, adrenal cortex stimulating hormone, follicular stimulating hormone, luteinizing hormone, stromal cell stimulating hormone, and melanin cell stimulating. Includes, but is not limited to, hormones, antidiuretic hormones, and oxytocin. Hormones secreted from the thyroid gland (thyroid hormone) include, but are not limited to, sub-items such as triiodothyronine, thyroxine (free triiodothyronine, free thyroxine), and calcitonin. Hormones secreted by the parathyroid gland include, but are not limited to, parathyroid hormone and parathyroid hormone as sub-items. Hormones secreted by the thymus include, but are not limited to, thymosin as a sub-item. Hormones secreted by the heart include, but are not limited to, atrial natriuretic peptides and brain natriuretic peptides as sub-items. Hormones secreted from the vascular endothelium include, but are not limited to, endothelin as a sub-item. Hormones secreted by the gastrointestinal tract include, but are not limited to, sub-items such as gastrin, ghrelin, cholecystokinin, secretin, VIP vasoactive intestinal pepitide, motilin, and incretin. Hormones secreted by pancreatic islets of Langerhans (pancreatic hormones) include, but are not limited to, subitems such as glucagon, insulin, somatostatin, and pancreatic polypeptide. Hormones secreted by the liver include, but are not limited to, sub-items such as IGF-1 and angiotensinogen. Hormones secreted by white adipose tissue include, but are not limited to, subitems such as leptin, adiponectin, Paiwan PAI-1, and tumor necrosis factor-α. Hormones secreted by the adrenal glands (adrenal hormones) include, but are not limited to, minor items such as electrolyte corticoids, glucocorticoids, androgen, adrenaline, noradrenaline, and adrenomedullin. Hormones secreted by the kidney include, but are not limited to, sub-items such as nylen and erythropoietin. Hormones secreted from the germline (gonadal hormones) include, but are not limited to, sub-items such as follicular hormone, luteal hormone, relaxin, androgen, activin, and activin. Hormones secreted from the placenta (placental hormones) include, but are limited to, sub-items such as human chorionic gonadotropin, human chorionic gonadotropin, estrogen, progesterone, renin, relaxin, androgen. is not it. Hormones related to semen, lungs, and brain include, but are not limited to, prostaglandins, for example, as sub-items. Hormones related to skin, liver and kidney include, but are not limited to, vitamin D as a sub-item. To improve the accuracy of the evaluation results, estimate the value of thyroid-stimulating hormone (TSH) among the hormones secreted from the pituitary gland, and free triiodothyronine (FT3) or among the hormones secreted from the thyroid gland. It is desirable to estimate the value of free thyroxine (FT4).

The estimation device 2 is composed of, for example, an electronic device such as a personal computer (PC), but is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc., in addition to the PC. It may be converted. The user can obtain the evaluation result by the estimation device 2.

FIG. 4 shows a specific configuration example of the estimation device 2. The estimation device 2 performs wired communication or wireless communication with a control unit 24 for controlling the entire estimation device 2 and an operation unit 25 for inputting various control commands via operation buttons, a keyboard, or the like. A communication unit 26 for the purpose, an estimation unit 27 for making various judgments, and a storage unit 28 for storing a program for performing a search to be executed represented by a hard disk or the like are connected to the internal bus 21, respectively. .. Further, a display unit 23 as a monitor that actually displays information is connected to the internal bus 21.

The control unit 24 is a so-called central control unit for controlling each component mounted in the estimation device 2 by transmitting a control signal via the internal bus 21. Further, the control unit 24 transmits various control commands via the internal bus 21 in response to the operation via the operation unit 25.

The operation unit 25 is embodied by a keyboard or a touch panel, and an execution command for executing a program is input from the user. When the execution command is input by the user, the operation unit 25 notifies the control unit 24 of the execution command. Upon receiving this notification, the control unit 24, including the estimation unit 27, executes a desired processing operation in cooperation with each component. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The estimation unit 27 estimates the evaluation result. The estimation unit 27 reads out various information stored in the storage unit 28 and various information stored in the database 3 as necessary information when executing the estimation operation. The estimation unit 27 may utilize the degree of association corresponding to the weighting coefficient of each output of the node of the neural network in artificial intelligence. This artificial intelligence may be based on any well-known artificial intelligence technique.

The display unit 23 is composed of a graphic controller that creates a display image based on the control by the control unit 24. The display unit 23 is realized by, for example, a liquid crystal display (LCD) or the like.

When the storage unit 28 is composed of a hard disk, predetermined information is written to each address based on the control by the control unit 24, and is read out as needed. Further, the storage unit 28 stores a program for executing the present invention. This program is read and executed by the control unit 24.

The operation in the biological information evaluation system 1 having the above-described configuration will be described.

In the biometric information evaluation system 1, for example, as shown in FIG. 5, it is premised that the degree of association between the reference biometric information and the evaluation result is set in advance and acquired. The biometric information evaluation system 1 can know what kind of evaluation results have been obtained for various acquired reference biometric information through the reference biometric information and the evaluation result data set. That is, by collecting a data set of reference biometric information extracted from the past medical examination data for each user and the evaluation result for the user, any evaluation result can be estimated from the user who has any medical examination data in the past. It becomes possible to know whether it was done.

In the example of FIG. 5, it is assumed that the input data is, for example, reference biological information P01 to P03. Reference biometric information as such input data is linked to the output. In this output, the evaluation results Q1 to Q4 are displayed as the output solution.

The reference biometric information is associated with each other through three or more levels of association with the evaluation result. The reference biometric information is arranged on the left side via this degree of association, and each evaluation result is arranged on the right side via this degree of association. The degree of association indicates which evaluation result is highly relevant to the reference biometric information arranged on the left side. In other words, this degree of association is an index indicating what kind of evaluation result each reference biometric information is likely to be associated with, and is used to select the most probable evaluation result from the reference biometric information. It shows the accuracy. In the example of FIG. 5, w13 to w19 are shown as the degree of association. As shown in Table 1 below, w13 to w19 are shown in 10 stages. The closer to 10 points, the higher the degree of relevance to the evaluation result, and conversely, the closer to 1 point, the higher the evaluation result. It shows that the degree of relevance to each other is low.

The estimation device 2 acquires in advance the degree of association w13 to w19 of three or more stages shown in FIG. That is, the estimation device 2 accumulates past data as to which of the reference biometric information and the evaluation result in that case was adopted in performing the actual estimation, and analyzes and analyzes these. Create the degree of association shown in 5.

Specifically, it is assumed that the blood cell count value of the reference biological information P01 set in the past is ●● and the lipid value is Δ△. At this time, it is investigated what kind of evaluation result the user having such reference biometric information P01 had in the past. For example, the past reference biological information P01 is "red blood cell count (RBC): 4.8 million / μL, ALP: 325 U / L, HDL-C: 50 mg / dL, uric acid: 5.0 mg / dL", and the evaluation result is It is assumed that it was "thyroid stimulating hormone (TSH): 3.0 μU / mL" or "free thyroxine (FT4): 1.5 ng / dL".

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, when the reference biological information P01 is "red blood cell count (RBC): 4.8 million / μL, ALP: 325 U / L, HDL-C: 50 mg / dL, uric acid: 5.0 mg / dL". Analyze from historical data in databases stored in medical institutions. If there are many applied evaluation results Q1, the degree of association that leads to this evaluation result Q1 is set higher, and if there are many cases of evaluation result Q2 and there are few evaluation results Q1, the association that leads to evaluation result Q2 is set. Set the degree high and the degree of association leading to the evaluation result Q1 low.

Further, the degree of association shown in FIG. 5 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In such a case, as shown in FIG. 6, reference biometric information is input as input data, evaluation results are output as output data, and at least one or more hidden layers are provided between the input node and the output node. Machine learning may be performed. On the contrary, the evaluation result may be input and the reference biometric information may be output.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually setting an evaluation result for a new user from now on, the optimum evaluation result will be estimated using the above-mentioned learned data. In such a case, the evaluation biological information including at least one of the blood cell count, the enzyme, the lipid, and the nitrogen-containing component of the user who intends to newly set the evaluation result is newly acquired.

The newly acquired biometric information for evaluation is acquired by the above-mentioned information acquisition unit 9, and based on the acquired biometric information for evaluation, it is estimated what kind of evaluation result should actually be applied. In such a case, the degree of association shown in FIG. 5 (Table 1) acquired in advance is referred to. For example, when the newly acquired evaluation biometric information is the same as or similar to the reference biometric information P02, the evaluation result Q2 is associated with w15 and the evaluation result Q3 is associated with the association degree w16 via the degree of association. Has been done. In such a case, the evaluation result Q2 having a higher degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the evaluation result Q3 in which the degree of association is low but the association itself is recognized may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In this way, the newly acquired biometric information for evaluation and the biometric information for reference are matched with each other in terms of information type. Therefore, when new biometric information for evaluation is acquired, it is the same. Alternatively, it is possible to immediately refer to similar biological information for reference and estimate the optimum evaluation result.

By the way, when any one or more of the information such as blood cell count, enzyme, lipid, nitrogen-containing component, etc. is acquired as the evaluation biometric information, the blood cell count, enzyme, lipid, and the like are included as the reference biometric information. It is necessary to learn in advance from information such as nitrogen components. Then, the optimum evaluation result is estimated through the reference biological information according to the information such as the blood cell count, the enzyme, the lipid, and the nitrogen-containing component actually acquired.

At this time, the above-mentioned degree of association may be composed of a combination of any two or more of information such as blood cell count, enzyme, lipid, and nitrogen-containing component. Then, the estimation may be made by learning the evaluation result as the estimation result for the combination.

That is, as the biological information for evaluation, any two or more of the previous information such as blood cell count, enzyme, lipid, nitrogen-containing component, etc. are acquired. Then, among the reference biometric information, the combination of the reference information according to the two or more acquired information and the degree of association with the evaluation result in three or more stages are acquired in advance. Next, using this, the evaluation result to be proposed is estimated based on the degree of association with the evaluation result for the combination of the reference information corresponding to the newly acquired two or more information as described above in three or more stages (). Explore.

In the example of FIG. 7, it is premised that a combination of reference biometric information and reference attribute information is formed.

In the example of FIG. 7, it is assumed that the input data is, for example, reference biological information P11 to P13 and reference attribute information P14 to 17. The intermediate node shown in FIG. 7 is a combination of reference attribute information and reference biometric information as such input data. Each intermediate node is further linked to the output. In this output, the evaluation result as the output solution is displayed.

Each combination (intermediate node) of the reference biometric information and the reference attribute information is associated with each other through three or more levels of association with the evaluation result as this output solution. The reference biometric information and the reference attribute information are arranged on the left side via the degree of association, and the evaluation results are arranged on the right side via the degree of association. The degree of association indicates the degree of relevance to which evaluation result is higher with respect to the reference biometric information and the reference attribute information arranged on the left side. In other words, this degree of association is an index indicating what kind of evaluation result each reference biometric information and reference attribute information is likely to be associated with, and is the most among the reference biometric information and the reference attribute information. It shows the accuracy in selecting a probable evaluation result. In the example of FIG. 7, w13 to w22 are shown as the degree of association. As shown in Table 1, these w13 to w22 are shown in 10 stages, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the value as an output, and conversely. The closer it is to one point, the less the each combination as an intermediate node is related to the value as an output.

The estimation device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. 7. That is, the estimation device 2 accumulates past data on the reference biometric information, the reference attribute information, and the evaluation result in that case in determining the actual estimation result, and stores these. By analyzing and analyzing, the degree of association shown in FIG. 7 is created.

For example, it is assumed that the user's medical examination data set in the past is the reference biometric information P11. At this time, when the attribute information of the user is "male, 40s, experience of suffering from pneumonia", the evaluation result is investigated in the previous data.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, when the reference biological information P11 and the reference attribute information P16 “male, 40s, experience of suffering from pneumonia”, the evaluation result is analyzed from the past data. If the evaluation result has many cases of evaluation result Q3, the degree of association leading to this evaluation result Q3 is set higher, and if there are many cases of evaluation result Q4 and few cases of evaluation result Q3, the evaluation result is evaluated. The degree of association leading to Q4 is set high, and the degree of association leading to the evaluation result Q3 is set low. For example, in the example of the intermediate node 61a, the output of the evaluation result Q1 and the evaluation result Q2 is linked. The degree of association is set to 2 points.

Further, the degree of association shown in FIG. 7 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In such a case, as shown in FIG. 7, reference biometric information or reference attribute information is input as input data, an evaluation result is output as output data, and at least one or more between the input node and the output node. An intermediate node (hidden layer) may be provided for machine learning. On the contrary, the evaluation result may be input and the reference biometric information or the reference attribute information may be output. As the machine learning algorithm, various methods such as a linear regression model, SVM (Support Vector Machine), decision tree, random forest, etc. can be adopted.

In the example of the degree of association shown in FIG. 7, the node 61b is a node in which the reference attribute information P14 is combined with the reference biological information P11, the degree of association of the evaluation result Q3 is w15, and the degree of association of the evaluation result Q5. Is w16. The node 61c is a node in which the reference attribute information P15 and P17 are combined with respect to the reference biometric information P12, and the degree of association of the evaluation result Q2 is w17 and the degree of association of the evaluation result Q4 is w18.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually estimating the evaluation result from now on, the evaluation result will be estimated using the above-mentioned learned data. In such a case, the biometric information for evaluation of the user who intends to newly set the evaluation result is newly acquired, and the attribute information of the user is acquired.

The newly acquired evaluation biometric information and attribute information may be acquired via a user interface such as a keyboard.

Based on the newly acquired biometric information for evaluation and attribute information in this way, an attempt is made to estimate the optimum evaluation result. In such a case, the degree of association shown in FIG. 7 (Table 1) acquired in advance is referred to. For example, when the newly acquired biometric information for evaluation is the same as or similar to P12 and the attribute information is P17, the node 61d is associated via the degree of association. The node 61d is associated with the evaluation result Q3 by w19 and the evaluation result Q4 by the degree of association w20. In such a case, the evaluation result Q3 having a higher degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the evaluation result Q4 in which the degree of association is low but the association itself is recognized may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

Further, an example of the degree of association w1 to w12 extending from the input is shown in Table 2 below.

The intermediate node 61 may be selected based on the degree of association w1 to w12 extending from this input. That is, the larger the degree of association w1 to w12, the heavier the weighting in the selection of the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weights in the selection of the intermediate node 61 may all be the same.

By the way, when acquiring any one or more of age, gender, blood type, height, weight, medical history information, medication history information, and hospital visit history information as attribute information, these are used as reference attribute information. It is necessary to learn in advance the age, gender, blood type, height, weight, medical history information, medication history information, hospital visit history information, etc. according to the above, together with the reference biometric information, from the evaluation results. Then, the evaluation result is estimated through the actually acquired age, gender, blood type, height, weight, medical history information, medication history information, and reference attribute information according to the hospital visit history information.

At this time, the above-mentioned degree of association may be composed of any two or more combinations of age, gender, blood type, height, weight, medical history information, medication history information, and hospital visit history information. Then, the evaluation result may be estimated by learning the evaluation result as the estimation result (search solution) for the combination.

In the biometric information evaluation system 1, when the reference attribute information is learned from the evaluation result, the reference attribute information is independently used as the evaluation result as shown in FIG. 8 without including the reference biometric information. You may train with the linked data set. That is, it is premised that the degree of association between the reference attribute information and the evaluation result in three or more stages is set and acquired in advance. That is, through this reference attribute information and the evaluation result data set, it is possible to know what kind of evaluation result was applied according to the reference attribute information. Regarding the formation and estimation of the degree of association shown in FIG. 8, the explanation below will be omitted by quoting the explanation of FIG.

According to the present invention having the above-described configuration, anyone can easily propose the optimum evaluation result or judge the possibility of including the evaluation result without any special skill or experience. Further, according to the present invention, it is possible to make a judgment at the time of this estimation with higher accuracy than that made by a human being. Further, by configuring the above-mentioned degree of association with artificial intelligence (neural network or the like), it is possible to further improve the discrimination accuracy by learning this.

Further, according to the present invention, it is characterized in that the optimum estimation is performed through the degree of association set in three or more stages. The degree of association can be described by, for example, a numerical value from 0 to 100% in addition to the above-mentioned 5 stages, but the degree of association is not limited to this, and any stage can be described as long as it can be described by a numerical value of 3 or more stages. It may be configured.

By proposing the most probable evaluation results based on the degree of association expressed by such numerical values of three or more stages, or by judging the inclusiveness of the evaluation results, multiple possible candidates for the evaluation results can be considered. Under such circumstances, it is also possible to estimate and display in descending order of the degree of association. If the users can be displayed in descending order of the degree of association, it is possible to preferentially display the more probable evaluation results.

As the evaluation result, the user is given hyperthyroidism or hypothyroidism by estimating the hormone level, particularly the evaluation result consisting of the hormone level secreted from the pituitary gland or the evaluation result consisting of the hormone level secreted from the thyroid gland. It is possible to estimate whether or not there is any of the symptoms. That is, by estimating the hormone level secreted from the thyroid gland, it is useful to estimate the possibility of symptom of the disease. In particular, by using either thyroid-stimulating hormone (TSH), which is a hormone secreted from the pituitary gland, or free triiodothyronine (FT3) or free thyroxine (FT4), which is a hormone secreted from the thyroid gland. , It is possible to more accurately estimate whether or not there is an abnormality in thyroid function.

In addition to this, according to the present invention, it is possible to judge without overlooking the discrimination result of the output having an extremely low degree of association such as 1%. It warns the user that even a judgment result with an extremely low degree of association is connected as a slight sign and may be useful as the judgment result once every tens or hundreds of times. be able to.

Further, according to the present invention, there is an advantage that the estimation policy can be determined by the method of setting the threshold value by estimating based on the degree of association of three or more stages. If the threshold value is lowered, even if the above-mentioned degree of association is 1%, it can be picked up without omission, but it is unlikely that a more appropriate discrimination result can be detected favorably, and a lot of noise may be picked up. be. On the other hand, if the threshold value is raised, there is a high possibility that the optimum evaluation result can be detected with a high probability. Sometimes the solution is overlooked. It is possible to decide which one to prioritize based on the ideas of the user side and the system side, but it is possible to increase the degree of freedom in selecting the points to be emphasized.

Further, in the present invention, the above-mentioned degree of association may be updated. This update may reflect information provided via a public communication network such as the Internet. In addition, when regional characteristic information is acquired, and in addition to this, property information, external environment information, and knowledge, information, and data regarding the type of industry and real estate prices to be introduced are acquired, the degree of association is increased accordingly. Or lower it.

In other words, this update corresponds to learning in the sense of artificial intelligence. It can be said that it is a learning act because it acquires new data and reflects it in the learned data.

In addition, this update of the degree of association is not based on the information that can be obtained from the public communication network, but is also updated by the system side or the user side based on the contents of research data, treatises, conference presentations, newspaper articles, books, etc. by experts. It may be updated artificially or automatically. Artificial intelligence may be utilized in these update processes.

Further, the process of first creating the trained model and the above-mentioned update may use not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, and the like. In the case of unsupervised learning, instead of reading and learning the data set of input data and output data, information corresponding to the input data is read and trained, and the degree of association related to the output data is self-formed from there. You may let it.

Further, the degree of association of each combination described above is the degree of association of a combination having one factor and another factor, and it goes without saying that other elements other than these may be associated with the degree of association.

Hereinafter, the biological information evaluation system to which the present invention is applied will be specifically described with reference to Examples and Comparative Examples. 9 (a) to 9 (d) are the measurement results of AUC (adaptation rate), correct answer rate, sensitivity, and specificity for hyperthyroidism, respectively. 10 (a) to 10 (d) are the measurement results of AUC, correct answer rate, sensitivity, and specificity for hypothyroidism, respectively.

In this example, AUC is used as reference biological information using all data of ALP, LDL-C_HDL-C, gender (female), LDL-C, HDL-C, RBC, URIC_ACID, γ-GTP, GPT, and GOT. , Correct answer rate, sensitivity, and specificity were evaluated by four types of evaluation methods. As a result, as shown in FIGS. 9 and 10, evaluation results were obtained with a high accuracy of 0.8 or more in both hyperthyroidism and hypothyroidism.

On the other hand, as a comparative example, each item of ALP, LDL-C_HDL-C, gender (female), LDL-C, HDL-C, RBC, URIC_ACID, γ-GTP, GPT, GOT is excluded one by one, and AUC, Evaluation was performed by four types of evaluation methods: correct answer rate, sensitivity, and specificity. As a result, as shown in FIGS. 9 and 10, in both hyperthyroidism and hypothyroidism, the accuracy was lower than when all the items were used.

1 Biometric information evaluation system 2 Estimator 21 Internal bus 23 Display unit 24 Control unit 25 Operation unit 26 Communication unit 27 Estimate unit 28 Storage unit 61 Node

Claims (11)

Biological information acquisition means for acquiring information on blood cell count, enzymes, lipids, and nitrogen-containing components as biological information for evaluation,
Using the three or more levels of association between the previously acquired reference biometric information and the evaluation result consisting of hormone levels, the reference biometric information according to the evaluation biometric information acquired by the biometric information acquisition means. It is provided with an estimation means for estimating the evaluation result based on the degree of association with the evaluation result in three or more stages .
The above estimation means are pineal gland, hypothalamus, pituitary gland, thyroid gland, parathyroid gland, thoracic gland, heart, vascular endothelium, gastrointestinal tract, pancreatic islets of Langerhans, liver, white adipose tissue, adrenal gland, kidney, gonad, placenta, semen, Using the degree of association with the evaluation result consisting of the above hormone levels secreted from any of the lungs, brain, and skin, it is possible to estimate the site that may have a hormonal disease as the above evaluation result. biological information evaluation system, characterized in that. The biological information obtaining means, according to claim, characterized RBC, ALP, AST, ALT, γ-GTP, HDL-C, LDL-C, to obtain the evaluation biometric information including at least one of uric acid 1 serial mounting of biological information evaluation system. The above estimation means consists of any one of growth hormone, thyroid stimulating hormone, adrenal cortex stimulating hormone, follicular stimulating hormone, luteinizing hormone, stromal cell stimulating hormone, melanocyte stimulating hormone, prolactin, antidiuretic hormone, and oxytocin. biological information evaluation system according to claim 1, wherein utilizing three or more stages of association degree between the evaluation result consisting of hormone levels secreted from the pituitary gland. The estimation means has three or more levels of association with the evaluation result consisting of the hormone level secreted from the thyroid gland, which consists of any one of triiodothyronine, thyroxine (free triiodothyronine, free thyroxine), and calcitonin. The biometric information evaluation system according to claim 1 , wherein the biometric information evaluation system is used. Further equipped with an attribute information acquisition means for acquiring gender information as attribute information,
The above-mentioned estimation means has three or more levels of association between a combination having reference attribute information regarding previously acquired attributes, reference biometric information, and an evaluation result consisting of hormone levels secreted from the pituitary gland for the combination. 3 The evaluation results of the reference attribute information according to the attribute information acquired by the attribute information acquisition means and the reference bioinformation according to the evaluation bioinformation acquired by the biometric information acquisition means. The biometric information evaluation system according to claim 1 or 3 , wherein the evaluation result is estimated based on the degree of association of one or more stages. Further equipped with an attribute information acquisition means for acquiring gender information as attribute information,
The above-mentioned estimation means determines the degree of association between the combination having the reference attribute information regarding the previously acquired attribute and the reference biometric information and the evaluation result consisting of the hormone level secreted from the thyroid gland for the combination in three or more stages. Three stages of evaluation results for reference attribute information according to the attribute information acquired by the attribute information acquisition means and reference bioinformation according to the evaluation bioinformation acquired by the biometric information acquisition means. The biometric information evaluation system according to claim 1 or 4 , wherein the evaluation result is estimated based on the above degree of association. The biometric information evaluation system according to any one of claims 1 to 6 , wherein the estimation means utilizes the degree of association corresponding to the weighting coefficient of each output of the node of the neural network in artificial intelligence. A biometric information acquisition step for acquiring information on blood cell count, enzymes, lipids, and nitrogen-containing components as biometric information for evaluation,
Using the degree of association between the previously acquired reference biometric information and the evaluation result consisting of hormone levels in three or more stages, the reference biometric information corresponding to the evaluation biometric information acquired in the biometric information acquisition step A computer is made to execute an estimation step for estimating the evaluation result based on the degree of association with the above evaluation result in three or more stages .
In the above estimation steps, the pineal gland, hypothalamus, pituitary gland, thyroid gland, parathyroid gland, thoracic gland, heart, vascular endothelium, gastrointestinal tract, pancreatic islets of Langerhans, liver, white adipose tissue, adrenal gland, kidney, gonad, placenta, semen, Using the degree of association with the evaluation result consisting of the above hormone levels secreted from any of the lungs, brain, and skin, it is possible to estimate the site that may have a hormonal disease as the above evaluation result. biological information evaluation program, characterized in that there. The eighth aspect of claim 8, wherein in the biometric information acquisition step, evaluation biometric information including at least one of RBC, ALP, AST, ALT, γ-GTP, HDL-C, LDL-C, and uric acid is acquired. Biometric information evaluation program. The estimation step consists of any of growth hormone, thyroid stimulating hormone, adrenal cortex stimulating hormone, follicular stimulating hormone, luteinizing hormone, stromal cell stimulating hormone, melanocyte stimulating hormone, prolactin, antidiuretic hormone, and oxytocin. The biometric information evaluation program according to claim 8, wherein the degree of association with the evaluation result consisting of the hormone level secreted from the pituitary gland is used in three or more stages. In the above estimation step, the degree of association with the evaluation result consisting of the hormone level secreted from the thyroid gland consisting of any one of triiodothyronine, thyroxine (free triiodothyronine, free thyroxine), and calcitonin in three or more stages. 8. The biometric information evaluation program according to claim 8, wherein the biometric information evaluation program is used.

Images