JP2021166037A - Prediction, recording, and comparison device for examination data involved in medical treatment - Google Patents

Abstract

To utilize the following result for treatment of a disease by predicting subsequent examination data (a disease state) on the basis of a correlation between treatment information and various examination data.SOLUTION: The invention includes treatment storage means for storing treatment information of a treatment object person, well-known information storage means for storing well-known information derived from treatment, and examination data storage means for storing various examination data of the treatment object person, compares the well-known information stored in the well-known information storage means with the examination data stored in the examination data storage means, and predicts future examination data.SELECTED DRAWING: Figure 1

Description

The present invention records the treatment content of a treatment subject in association with various test data, predicts how the test data will change when the same treatment is continued, and in some cases. , The purpose is to give the treatment subject a motivation to change (improve) the treatment content in order to change (improve) the test data.
In the present invention, the term "treatment" refers to an act of physically, chemically, biologically, or psychologically affecting the body of a subject to be treated based on the instructions of a doctor to improve or heal an illness or injury, that is, medication. It refers to surgery, radiation, rehabilitation, conservative treatment, etc., but does not include lifestyles that are not based on doctor's instructions.

For example, when a certain treatment target person continues treatment without changing the current treatment content, the pathological condition is predicted by predicting the trend of the test result and encouraging the treatment target person to understand the necessity of treatment and the treatment behavior. It is intended to lead to improvement actions.
The purpose is to predict the future value of the test data when the current treatment content is continued or not, and to make the treatment subject aware of the importance of changing or continuing the treatment content.

From the viewpoint of reducing medical expenses, appropriate treatments have been screamed loudly, and many medical papers have published and publicized the causal relationship between treatment contents and various diseases.
For example, the discontinuation of treatment for early-stage diabetes mellitus without subjective symptoms and the increase in dialysis patients due to the resulting aggravation have become a social problem. In addition, although various types of therapeutic agents are provided, it is difficult to match each individual treatment target, and many publicly known papers describe various dosing methods.

However, recently, it is known that diseases should be evaluated by a complex test value, but in reality, for example, in the case of diabetes, only the blood pressure level and HbA1C are confirmed. Comprehensive evaluation based on complex test results due to multiple organs, decreased visual acuity, blood pressure, lipids, decreased renal function, etc., which become problems as the condition progresses, has not been possible.

Therefore, when the increase in postprandial blood glucose level is suppressed after dosing and HbA1C is evaluated as having a therapeutic effect as a reference value, side effects and related diseases due to the treatment are overlooked or become severe.

Japanese Patent No. 6473988

In the above-mentioned Patent Document 1, the lifestyle of the subject and various inspection data are recorded in association with each other, and how the inspection data changes when the same lifestyle is continued is predicted. In some cases, inventions are described that motivate the subject to change (improve) lifestyle in order to change (improve) test data.
However, in the present invention, there is no concept of associating and recording the treatment content during treatment with the test data.
Therefore, it was not possible to predict the future value of the test data when the current treatment content was continued or not, and to recognize the importance of changing or continuing the treatment content of the treatment subject.

In that respect, the present invention is intended to associate the treatment content with various test results and give the treatment subject a guideline for reviewing (or not reviewing in some cases) the future treatment content from the test result.

(1) The present invention is an apparatus for predicting future test data when the treatment is continued by comparing the treatment information and various test data of the treatment subject with various known test data derived from the treatment. , A treatment storage means for storing the treatment information of the treatment subject, a known information storage means for storing known information regarding treatment results derived from various treatments, and a test data storage for storing various test data of the treatment target. Means and means are provided, and by periodically inputting the treatment information and information on the test data into the test data storage means, the test data of the treatment target person is accumulated, and the data and the publicly known information storage means are provided with the means. The stored known information is collated by artificial intelligence, an initial prediction function is generated from the known information by using artificial intelligence, and the prediction function is combined with the inspection data accumulated in the past multiple times. It is a test data prediction device characterized in that treatment information is added, additional learning is performed in an artificial intelligence prediction formula, and future test data is predicted as the analysis result.
According to the present invention, treatment information (for example, data on administration of a specific drug to a subject to be treated) and data described in known medical papers (data on the relationship between blood glucose level and HbA1C and a specific drug) are provided. In comparison, it may be predicted that the current symptoms (blood glucose level and HbA1C data) will not be reduced simply by continuing to administer a specific drug in this state.
In such a case, it is possible to select whether the blood glucose level or HbA1C can be suppressed or lowered by applying another drug or treatment method to the treatment target. It becomes.

(2) The present invention is an apparatus for predicting future test data based on past test data when a certain treatment is continued by associating the treatment information of the treatment target with the test data, and treating the treatment target. A treatment storage means for storing information, a known information storage means for storing known information regarding treatment results derived from various treatments, and a test data storage means for storing various test data of the treatment subject are provided. Test data under the same treatment is stored multiple times at intervals of time, past test data performed each time is accumulated, and the data and known information stored in the publicly known information storage means are artificially intelligent. An initial prediction function is generated from the known information by using artificial intelligence, and the test data and treatment information accumulated in the past are added to the prediction function to obtain an artificial intelligence prediction formula. It is an inspection data prediction device characterized in that additional learning is performed and future inspection data is predicted as the analysis result.

According to the present invention, for example, the administration of a specific antihypertensive agent to a treatment subject and blood pressure data are stored a plurality of times at intervals, and the past test data performed each time is accumulated. It is predicted that the increase in blood pressure will be suppressed if a specific antihypertensive agent is continuously administered.

In such cases, the treatment subject can prevent or reduce the increase in blood pressure based on the past administration of the specific antihypertensive drug and blood pressure data. You can predict if you can do it.

(3) It is desirable that the treatment information includes any of medication, surgery, radiation, rehabilitation, and conservative treatment.
In addition, the treatment information may include information on relatives other than the person himself / herself.

(4) It is desirable that the treatment information includes one or both of the genetic information and the medical history of the subject to be treated.

(5) It is desirable that the test data includes any of various sample tests and physical information.
Specimen tests may include test data for glucose metabolism, lipid metabolism, liver function, anemia, and renal function, and physical information may include age, gender, height, weight, abdominal circumference, and blood pressure.

(6) Future test data may be predicted when the treatment content is changed.
For example, based on the blood pressure data in which the treatment subject has changed the past treatment contents and increased the dose of the specific drug, the blood pressure should be increased in the future by increasing the dose of the specific drug. It will be possible to predict whether it can be prevented or lowered.

(7) The present invention predicts various test data derived from the treatment information of the treatment target person, and stores the treatment information of the treatment target person in a device for comparing the predicted data with the actual test data. Means, known information storage means for storing known information derived from treatment, prediction means for predicting various test data derived from treatment in association with the known information, and various test data of the treatment target person are stored. The test data storage means to be performed, the prediction data output means for which the prediction data is output from the prediction means according to the treatment information stored in the treatment storage means of the treatment subject, and the test data and the prediction data are compared. , A data difference storage means for storing the difference, and the difference between the inspection data and the prediction data stored in the data difference storage means are collated by artificial intelligence, and the artificial intelligence is obtained from the known information. An initial prediction function is generated by using it, test data and treatment information accumulated in the past are added to the prediction function, and additional learning is performed in the artificial intelligence prediction formula. As a result of the analysis, the treatment target is described. It is characterized by identifying it as a person's constitution.

According to the present invention, for example, administration of a specific antihypertensive agent to a treatment subject and blood pressure data can be stored a plurality of times at intervals, and past test data performed each time can be recorded in association with treatment information. can.
Therefore, it is possible to store the administration of the specific antihypertensive agent and the blood pressure data to the treatment subject a plurality of times at intervals, and record the past test data performed for each time.

(8) The same treatment information and test data may be stored a plurality of times at intervals of time, and the difference between the test data and the predicted data performed each time may be accumulated.

(9) The present invention compares various test data of a subject to be treated with various known test data derived from the treatment, and predicts future onset of the disease when the treatment is continued and the disease. In a device for presenting improvement contents of treatment for prevention, a treatment storage means for storing treatment information of the treatment target person, a known information storage means for storing known information derived from the treatment, and the treatment target person. The test data storage means for storing various test data of the above is provided, and the publicly known information stored in the publicly known information storage means and the test data stored in the test data storage means are compared with the treatment information. By periodically inputting information about the test data into the test data storage means, the test data of the treatment subject is accumulated, and the data and the known information stored in the known information storage means are artificially intelligent. An initial prediction function is generated from the known information by using artificial intelligence, and the test data and treatment information accumulated in the past are added to the prediction function to obtain an artificial intelligence prediction formula. Additional learning is performed, and the results are supplied to the selection of the physical constitution, prediction of post-examination test data, and recommended treatment, and the accuracy and probability of each constitution selection, prediction, and selection of recommended treatment content. It is characterized by improving the degree.

According to the present invention, for example, when a test result is obtained that the blood pressure does not decrease even if the treatment subject ingests a specific antihypertensive agent, the test result and the information described in a known document, that is, the said By comparing with the information that the blood pressure decreases with the intake of a specific antihypertensive drug, it is judged that the subject to be treated has an unusual constitution (body type).

Therefore, if the subject to be treated has hypertension, it should be considered to change the treatment method such as changing the drug.

(10) It is desirable that the treatment improvement recommendation information includes test items to be improved and test value targets for avoiding the estimated future risk of aggravation.
(11) It is desirable to predict the multiple types of treatment and the corresponding future improvement or aggravation risk, and present the patient so that the optimum treatment can be selected from the multiple types of treatment.
For example, there are multiple types of treatment methods for lowering the HbA1c level, and depending on the patient, there are cases where it is better to lower the HbA1c level sharply and cases where it is better to lower it slowly. If the change in HbA1c value in the case can be predicted and provided to the patient, more appropriate treatment can be performed.

In the present invention, the treatment content can be associated with various test results, and the treatment subject can be given a guideline for reviewing (or not reviewing in some cases) the future treatment content based on the test result, which is a great control measure against the exacerbation of the disease. Will be able to be executed.

It is a control block diagram of one Embodiment of this invention. It is a block diagram which shows the relationship between various examination data of one Embodiment of this invention, and treatment information. It is a figure which shows the process for predicting the state of a future disease from various test data and treatment information of one Embodiment of this invention. It is a figure which shows the process for inputting the personal attribute, the dosing information, etc. and the blood glucose level, etc. of one Embodiment of this invention, and outputting the future dosing information, etc. using the coming test value prediction engine. It is a related figure which shows the relationship between various examination data of one Embodiment of this invention, and treatment information. It is a figure which shows the content of various medication information (treatment information) of one Embodiment of this invention. It is a line graph which shows the prediction of the inspection data of one Embodiment of this invention. It is a figure which shows the guideline of the status quo maintenance and improvement target of one Embodiment of this invention. It is a table which showed the relationship between the lifestyle and the test value of one Embodiment of this invention. It is a figure which shows the explanatory text of one Embodiment of this invention. It is a figure following FIG. 9 of one Embodiment of this invention. The therapeutic effect by artificial intelligence of one embodiment of the present invention is shown. It is a graph of the contents of FIG. 12 according to the embodiment of the present invention.

FIG. 1 is a control block diagram of the entire device. The central processing device (CPU) 1 has a treatment information memory 3 for storing treatment information of a treatment target person via a bus line 2, and various types of treatment target persons. Test data memory 4 for storing test data, public information memory 5 for storing publicly known information published in medical papers, and difference storage memory 9 for storing differences between predicted data and test data. Various memories are connected.

Further, in the bus line 2, a prediction data display unit 6 that displays the test data predicted by inputting the treatment information of the treatment target person, and a test data comparison unit 7 that compares the past test data with the current test data. , The test data comparison unit 8 that compares the test data with the publicly known information, and the recommended treatment display unit 10 that teaches the treatment subject to be recommended based on the test data are connected.
Further, the bus line 2 is connected to an examination data input unit 11 for inputting various examination data and a treatment information input unit 12 for inputting treatment information.

To predict test data using this device, first enter information about the treatment of the treatment subject as shown in FIG.

Specifically, the drugs currently being taken by the treatment target, that is, drugs for diabetes (oral drugs and insulin) as shown in FIG. 6, drugs for hypertension, anticoagulants, drugs for heart disease, drugs for lowering corsterol, etc. , Gastrointestinal drugs, gout drugs, tranquilizers, corticosteroids, and other anti-cancer drugs.
In addition, ask them to enter other treatment information such as surgery history and radiation therapy history.
In addition, as treatment information, the family history (blood pressure, blood glucose level, lipid, liver function, treatment experience, weight of 20 years old) of the treatment target can be mentioned.

Next, information on various inspection data as shown in FIG. 5 is input.
This test item includes physique (abdominal circumference, body weight, BMI), blood pressure (maximum blood glucose, diastolic blood glucose), glucose metabolism (fasting blood glucose level, estimated average blood glucose level, HbA1c level), lipid metabolism (HDL corsterol, LDL corsterol, Neutral fat, liver function (AST, ALT, γ-GTP) and the like can be mentioned.

Then, as shown in FIGS. 2 and 4, by periodically inputting the above-mentioned information on the treatment information and the test data, the data of the treatment subject is accumulated and introduced in the data and the medical paper. Various publicly known information is collated by an artificial intelligence (AI) engine, and as the analysis result, future test value prediction (deterioration or improvement), genetic test value prediction, deterioration risk determination and pathological condition worsening factor analysis and pathological condition Improvement factor analysis sleep) is output.

From these analysis results, treatment evaluation (future test value, treatment content), test value prediction graph, test value target for pathological improvement and cure, risk of aggravation and complications, action plan and superiority ranking for recovery , The relationship between eating habits and illness is evaluated for each test item, the recommended treatment is displayed as a result, and medication information that can achieve the treatment goal is output.
Not only medication information but also recommended treatment information such as surgery and radiation therapy is output.

It can be understood that the person to be treated improves his / her physical condition by performing regular examinations while performing the recommended treatment.
On the other hand, it can be understood that even if the recommended treatment is not performed, regular examinations will worsen one's physical condition.
Therefore, the treatment subject can manage the physical condition well by using this device.

FIG. 7 is a line graph showing how the future test value will change if a specific treatment subject does not continue the treatment as it is. Among them, for example, HbA1c whose target value is 6.3%. The values are currently projected to be 6.5%, 3 years later 6.6%, 6 years later 6.8%, and 9 years later 7.3%.
At the bottom, a radar chart shows the risk prediction of complications based on the treatment method, lifestyle, and test results.

Next, the relationship between various test data and treatment information will be described with reference to FIG.
In this figure, the vertical column on the left side represents a state in which examination data and treatment information are input and finally examination data and treatment information are accumulated.

That is, the subsequent examination data is predicted by first inputting the examination data and the treatment information and then selecting the type of the current pathological condition. For example, assuming that the subject to be treated has a constitution that does not affect blood pressure even if a specific antihypertensive drug is ingested, the ex post facto test data is predicted on the premise of that. In addition, if the constitution is that the blood pressure decreases when the antihypertensive drug is ingested, the test data corresponding to the constitution is predicted.

Then, based on the predicted value of the test data, the recommended treatment for improving the test data is selected. For example, for a person to be treated who has a constitution in which blood pressure does not decrease even if a specific antihypertensive drug is ingested, a treatment of "prescribe another antihypertensive drug" is recommended.
Then, it accumulates test data and treatment information of multiple times and provides the treatment target with a guideline for future treatment.

In selecting the constitution of the subject to be treated, the modification of the subject to be treated is selected from the constitution selection logic according to some types disclosed in publicly known information such as papers.
In addition, AI (artificial intelligence) is used to generate an initial prediction function from publicly known information such as papers, and the test data and treatment information accumulated in the past multiple times are added to the prediction function to create an AI prediction formula. Make additional learning.
Then, the result is supplied to the selection of the physical constitution, the prediction of the examination data after the fact, and the recommended treatment information, and the accuracy and the probability of each constitution selection, prediction, and selection of the recommended treatment are improved. Try.

Next, according to FIG. 3, a mode in which the risk of aggravation of the current disease is suppressed if the treatment is improved so that the treatment subject becomes the improvement recommendation information will be described.
First, follow the medical examinations of the treated subject for the past 6 years or more, estimate the future disease type of the disease that may become severe if the treatment is continued as it is, and determine the severity of the estimated future disease. By setting a test value target for avoidance and notifying the treatment target person of the test value target, the possibility of suppressing the onset is improved.

That is, as shown in the lower part of FIG. 3, if the physical condition and treatment are left as they are, the risk of future deterioration (severity) is predicted from the test value trend and the disease type. And in order to avoid this risk, by setting a test value target for avoiding future diseases and setting a treatment improvement target to achieve that target, diseases that may occur in the future for the treatment target It is intended to prevent the aggravation of current diseases.

Specifically, for the diabetic treatment target shown in FIG. 8, the blood glucose level can be controlled unless the calorie intake is suppressed and the basal metabolic energy amount is increased only by the medication treatment as the "maintenance / improvement target of the medical condition". It is expected to be difficult. Make the following behavioral improvements to avoid additional medications and dose increases. "
More specifically, the following proposals are made as action items for aiming at dose reduction and drug withdrawal. They are listed from top to bottom in descending order of effectiveness (listed below because the display is small in the figure).

・ In the title of "Continue", make a proposal to "take the medicine correctly".
More specifically, "The treatment of diabetes is based on diet and exercise therapy, but if good blood glucose control cannot be achieved by diet and exercise therapy, the treatment of diabetes is based on diet and exercise therapy, but diet. If good glycemic control cannot be achieved with therapy and exercise therapy, drug therapy will be given to control the onset and progression of complications. "
・ The first title, "Increase," proposes "8000 steps in life, of which 20 minutes are moderate activities."
More specifically, "If you have less than 8000 steps and 20 minutes, first take 4000 steps and 5 minutes for 2 months, then 6000 steps and 10 minutes for 2 months, and so on." Make a suggestion.
・ In the first title, "Become a habit," make a proposal to "eat vegetables and mushrooms, meat and fish, and rice and bread in that order."
・ In the second title, "Become a habit," we propose to "finish the meal 3 hours before going to bed."
・ In the third title, "Become a habit," make a proposal to "chew slowly and eat 20-30 times a bite."
More specifically, he proposes, "Increase vegetables, do not pour in and eat, and if you put food in your mouth, put up a bridge until you finish chewing a fixed number of times."
・ In the first title, "Reduce", we propose "Avoid single grain dishes such as noodles, fried rice, rice bowls, sweet buns, and rice balls."
・ In the second title, "Reduce," we propose to "refrain from eating oil-rich dishes such as fried foods, Chinese dishes, and Western-style dishes."
・ In the third title, "Reduce," we make a proposal that "we devise seasonings other than salt to get used to light seasoning."
More specifically, we propose that "the flavors of vinegar, citrus juice, ginger, garlic, etc., spices such as wasabi and Japanese pepper, and herbs are used to accentuate the taste."
・ Propose the third title, "Increase," to "eat a blue-backed fish dish that contains high-quality fat and protein."
More specifically, we will propose "Purchase fillets, ask for pretreatment at the store, use frying pans and microwave ovens, and devise simple cooking such as canning."

Then, as shown in FIG. 9, "What is the dietary improvement including the test values that affect related diseases?", The vertical axis lists the test values (test contents) such as blood pressure, blood sugar, and triglyceride, and the horizontal axis. The contents of the above proposals are listed in the above, and as items that are considered to have high priority in artificial intelligence analysis, for example, "blood pressure" on the vertical axis and "do not drink too much alcohol" on the horizontal axis are related, and are shown in "△". It is represented by a mark with a "!".

Furthermore, in Fig. 10, the title "Explanation" is "What is happening in your body ...!? Dangerous worsening of the condition and the onset of complications can occur in this way." The state of "If you leave hyperglycemia (diabetes) alone !?" is shown by the explanation and the cross-sectional view inside the blood vessel.

Then, as shown in FIG. 11, various countermeasures are displayed under the subtitle "Suppressing the meal speed and suppressing the rapid rise of the blood glucose level".

In FIG. 12, a patient having a current HbA1c value of 8.4, a fasting blood glucose level of 180, and a postprandial blood glucose level of 220 using artificial intelligence was treated with three types of treatments, one without treatment and the other with 220 treatments. The table shows the predicted values after 3 months of the case.
Here, drug A (biguanide drug) mainly acts on the liver and has the effect of lowering the blood glucose level by suppressing the excessive release of glucose from the liver, improving insulin resistance and lowering the blood glucose level. It lowers it.

In addition, drug B (sulfonylurea (SU) drug) acts on the pancreas to promote insulin secretion, and is effective for the type of diabetes in which the insulin secretion function, which is common in Japanese people, is weakened.
In FIG. 12, artificial intelligence predicts that if the patient is not treated in the future, the HbA1c value will be 9.1, the fasting blood glucose will be 200, and the postprandial 2-hour blood glucose will be 240 after 3 months. doing.
Artificial intelligence predicts that if the patient only exercises and diets, the HbA1c level will be 7.8, the fasting blood glucose will be 160, and the 2-hour postprandial blood glucose will be 190 after 3 months. ing.

In addition, when the patient took a biguanide drug (A) and used exercise and diet in combination, the HbA1c value became 6.8, the fasting blood glucose became 120, and the postprandial blood glucose became 2 hours after 3 months. Artificial intelligence predicts that it will be 160.
Furthermore, when the patient took a sulfonylurea drug (B) and used exercise and diet in combination, the HbA1c level was 6.1, the fasting blood glucose was 90, and the postprandial blood glucose was 2 hours after 3 months. Is predicted by artificial intelligence to be 110.

FIG. 13 is a graph of the predicted value of the HbA1c value of the patient after 3 months.
Depending on the patient, it is not always necessary to lower the HbA1c value sharply, but it may be recommended to lower it slowly.
In the case of the patient shown in FIG. 13, it is considered appropriate for the doctor to lower the HbA1c level moderately to some extent, and it is recommended to take the biguanide drug (A) and to use exercise and diet in combination. In the figure, it is surrounded by □.

1 Central processing unit (CPU)
2 Bus line 3 Treatment information memory 4 Examination data memory 5 Known information memory 6 Prediction data display unit 7 Examination data comparison unit 8 Examination data comparison unit 9 Difference accumulation memory 10 Recommended treatment display unit 11 Examination data input unit 12 Treatment information input unit

Claims (11)

In a device that predicts future test data when the treatment is continued by comparing the treatment information and various test data of the treatment target person with various known test data derived from the treatment.
A treatment memory means for storing the treatment information of the treatment subject and
Known information storage means for storing known information about treatment results derived from various treatments,
An examination data storage means for storing various examination data of the treatment subject, and
Is equipped,
By periodically inputting the treatment information and the information related to the test data into the test data storage means, the test data of the treatment target person is accumulated, and the data and the known information stored in the publicly known information storage means are stored. And are collated by artificial intelligence
An initial prediction function is generated from the known information using artificial intelligence, and test data and treatment information accumulated in the past are added to the prediction function to be additionally learned in the artificial intelligence prediction formula.
An inspection data prediction device characterized by predicting future inspection data as the analysis result. In a device that associates the treatment information of the treatment target with the test data and predicts future test data based on the past test data when a certain treatment is continued.
A treatment memory means for storing the treatment information of the treatment subject and
Known information storage means for storing known information about treatment results derived from various treatments,
An examination data storage means for storing various examination data of the treatment subject, and
Is equipped,
Test data under the same treatment is stored multiple times at intervals of time, past test data performed each time is accumulated, and the data and known information stored in the publicly known information storage means are artificially intelligent. Match by
An initial prediction function is generated from the known information using artificial intelligence, and test data and treatment information accumulated in the past are added to the prediction function to be additionally learned in the artificial intelligence prediction formula.
An inspection data prediction device characterized by predicting future inspection data as the analysis result. The test data predictor according to claim 1 or 2, wherein the treatment information includes any of medication, surgery, radiation, rehabilitation, and conservative treatment. The test data prediction device according to claim 1 or 2, wherein the treatment information includes either or both of the genetic information and the medical history of the subject to be treated. The test data prediction device according to any one of claims 1 to 4, wherein the test data includes various sample tests, physical information, genetic information, and medical history. The test data prediction device according to any one of claims 1 to 5, which predicts future test data when the treatment content is changed. In a device that predicts various test data derived from the treatment information of the treatment target and compares the predicted data with the actual test data.
A treatment memory means for storing the treatment information of the treatment subject and
A known information storage means for storing known information derived from treatment,
Predicting means for predicting various test data derived from treatment in association with the known information,
An examination data storage means for storing various examination data of the treatment subject, and
A predictive data output means for which predictive data is output from the predictive means according to the treatment information stored in the treatment memory means of the treatment subject.
A data difference storage means for comparing the inspection data with the prediction data and storing the difference,
Is equipped,
The difference between the inspection data and the prediction data stored in the data difference storage means is collated by artificial intelligence.
An initial prediction function is generated from the known information using artificial intelligence, and test data and treatment information accumulated in the past are added to the prediction function to be additionally learned in the artificial intelligence prediction formula.
A test data comparison device characterized in that the analysis result is specified as the constitution of the treatment target person. The test data comparison device according to claim 7, further comprising a storage means for storing the same treatment information and test data a plurality of times at intervals of time and accumulating the difference between the test data and the predicted data performed each time. By comparing various test data of the treatment target with various known test data derived from the treatment, diseases that are expected to develop in the future when the treatment is continued and treatments for preventing the diseases. In the device that presents the improvement contents,
A treatment memory means for storing the treatment information of the treatment subject and
A known information storage means for storing known information derived from treatment,
An examination data storage means for storing various examination data of the treatment subject, and
Is equipped,
Comparing the publicly known information stored in the publicly known information storage means with the test data stored in the test data storage means,
By periodically inputting the treatment information and the information related to the test data into the test data storage means, the test data of the treatment target person is accumulated, and the data and the known information stored in the publicly known information storage means are stored. And are collated by artificial intelligence
An initial prediction function is generated from the known information using artificial intelligence, and test data and treatment information accumulated in the past are added to the prediction function to be additionally learned in the artificial intelligence prediction formula.
The results will be supplied to the selection of the physical constitution, the prediction of post-examination test data, and the recommended treatment, and the accuracy and probability of each constitution selection, prediction, and selection of recommended treatment content will be improved. A device that presents the content of improvement in treatment, which is characterized by planning. The device for presenting the treatment improvement content according to claim 9, wherein the treatment improvement recommendation information includes a test item to be improved and a test value target for avoiding a presumed future aggravation risk. The treatment improvement content according to claim 9, which predicts a plurality of treatment types and the corresponding future improvement or aggravation risk, and presents the patient so that the optimum treatment can be selected from the plurality of treatment types. The device to present.

Images