JP7337316B2 - Equipment for predicting, recording, and comparing test data associated with treatment - Google Patents

Description

The present invention records the treatment content of the subject of treatment in association with various test data, predicts how the test data will change when the same treatment is continued, and in some cases , to motivate the person to be treated to change (improve) the contents of the treatment in order to change (improve) the examination data.
In the present invention, the term “treatment” refers to the act of exerting physical, chemical, biological, and psychological effects on the body of a subject to be treated under the direction of a doctor to improve or heal illnesses and injuries. It refers to surgery, radiation, rehabilitation, conservative treatment, etc., but does not include lifestyle habits that are not based on a doctor's instructions.

For example, if a person to be treated continues treatment without changing the current treatment content, predicting the trend of test results and encouraging the person to understand the need for treatment and taking treatment actions This is intended to lead to improvement actions of employees.
It is intended to predict the future value of test data when the current treatment is continued or not, and to make the person to be treated aware of the importance of changing or continuing the treatment.

Appropriate medical treatment has long been called out loudly from the viewpoint of reducing medical costs, and the causal relationship between treatment content and various diseases has been published in many medical papers and is well known.
For example, discontinuation of treatment for early-stage diabetes without subjective symptoms and an increase in the number of dialysis patients due to aggravation resulting from such treatment have become social problems. In addition, various types of drugs for treatment are provided, but it is difficult to match them to individual patients to be treated, and many known papers describe various methods of drug administration.

However, recently, it is known that diseases should be evaluated by multiple test values. Comprehensive evaluation based on multiple examination results due to multiple organs, decreased visual acuity, blood pressure, lipids, decreased renal function, etc., which becomes a problem as the disease progresses, cannot be performed.

For this reason, if the rise in postprandial blood glucose level is suppressed after administration and HbA1C becomes the standard value and the therapeutic effect is evaluated, side effects and related diseases due to treatment are overlooked or become more severe.

Japanese Patent No. 6473988

In the above Patent Document 1, lifestyle habits of a subject and various test data are recorded in association with each other, and when the same lifestyle habits are continued, how the test data will change is predicted. , in some cases, inventions are described which are intended to motivate subjects to change (improve) their lifestyle habits in order to change (improve) test data.
However, in this invention, there is no concept of correlating and recording the contents of treatment and examination data during treatment.
Therefore, it was not possible to predict the future value of the examination data when the current treatment content is continued or not, and to make the subject recognize the importance of changing the treatment content or continuing the treatment.

In this respect, the present invention associates the details of treatment with the results of various tests, and provides a guideline for reviewing (or not reviewing) future treatment details based on the test results.

(1) The present invention is a device that compares treatment information and various examination data of a person to be treated with known various examination data derived from the treatment, and predicts future examination data when the treatment is continued. , treatment storage means for storing treatment information of the treatment subject; publicly known information storage means for storing publicly known information on treatment results derived from various treatments; and examination data storage for storing various examination data of the treatment subject. and means for accumulating examination data of the person to be treated by periodically inputting information on the treatment information and the examination data into the examination data storage means, storing the data and the known information storage means. Artificial intelligence is used to collate stored known information, an initial prediction function is generated from the known information using artificial intelligence, and the prediction function is combined with inspection data accumulated multiple times in the past. This examination data prediction device is characterized by adding treatment information to an artificial intelligence prediction formula for additional learning, and predicting future examination data as an 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 sugar levels and HbA1C and specific drugs) are combined. By comparison, it may be predicted that the current symptoms (blood sugar level and HbA1C data) will not decrease if only a specific drug is continued to be administered in this state.
In such cases, it is possible to select whether the increase in blood glucose level and HbA1C can be suppressed or lowered by applying a different drug or treatment method to the subject of treatment. becomes.

(2) The present invention relates to a device for predicting future examination data based on past examination data in the case of continuing a certain treatment by associating treatment information and examination data of the treatment recipient. Treatment storage means for storing information, known information storage means for storing known information on treatment results derived from various treatments, and test data storage means for storing various test data of the subject, The test data under the same treatment are stored multiple times at intervals of time, the past test data performed each time are accumulated, and the data and the known information stored in the known information storage means are stored by artificial intelligence. to generate an initial prediction function using artificial intelligence from the known information, and add examination data and treatment information accumulated in the past multiple times to the prediction function to create an artificial intelligence prediction formula This inspection data prediction device is characterized by performing additional learning and predicting future inspection data as an analysis result.

According to the present invention, for example, the administration of a specific antihypertensive drug to a subject and blood pressure data are stored multiple times at intervals of time, and the past examination data performed each time are accumulated, thereby achieving the above-described It is expected that continued administration of a specific antihypertensive drug will suppress the increase in blood pressure.

In such a case, the subject will be able to determine, based on past administration of a specific antihypertensive drug and blood pressure data, how long the subject should continue administration of the specific antihypertensive drug in the future to prevent or decrease blood pressure. It is possible to predict whether it will be possible.

(3) Treatment information should preferably include any of medication, surgery, radiation, rehabilitation, and conservative treatment.
Further, the treatment information may include information on relatives other than the subject.

(4) The treatment information preferably includes either or both of the genetic information and medical history of the person to be treated.

(5) It is desirable that the test data include either various sample tests or physical information.
Analyte tests may include test data for glucose metabolism, lipid metabolism, liver function, anemia, and renal function, and physical information may include age, sex, height, weight, waist circumference, and blood pressure.

(6) Future examination data may be predicted when the content of treatment is changed.
For example, based on the blood pressure data in a state in which the treatment subject has changed the content of past treatment and increased the dosage of a specific drug, it is possible to predict how much the dosage of the specific drug will increase blood pressure in the future. It will be possible to predict whether it can be prevented or lowered.

(7) The present invention provides a treatment memory for storing the treatment information of the person to be treated in an apparatus for predicting various examination data derived from the treatment information of the person to be treated and comparing the predicted data with the actual examination data. known information storage means for storing known information derived from the treatment; prediction means for predicting various test data derived from the treatment in association with the known information; and storage of the various test data of the patient prediction data output means for outputting prediction data from the prediction means in accordance with the treatment information stored in the treatment storage means of the person to be treated; and comparison between the examination data and the prediction data. and 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 is collated by artificial intelligence, and the artificial intelligence is calculated from the known information. to generate an initial prediction function, add test data and treatment information accumulated in the past multiple times to the prediction function, let the artificial intelligence prediction formula learn additionally, and as the analysis result, the treatment target It is characterized by specifying it as a person's constitution.

According to the present invention, for example, administration of a specific antihypertensive drug to a subject to be treated and blood pressure data can be stored multiple times at intervals of time, and past examination data performed each time can be recorded in association with treatment information. can.
Therefore, the administration of a specific antihypertensive drug to the subject of treatment and the blood pressure data can be stored multiple times at intervals, and the past examination data performed each time can be recorded.

(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 performed each time and the predicted data 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 the disease and the disease that are predicted to develop in the future when the treatment is continued. In the device for presenting the improvement contents of the treatment for preventing from and an examination data storage means for storing various kinds of examination data, wherein the known information stored in the known information storage means is compared with the examination data stored in the examination data storage means, and the treatment information and the By periodically inputting the information about the examination data into the examination data storage means, the examination data of the person to be treated is accumulated, and the data and the known information stored in the known information storage means are combined with artificial intelligence. to generate an initial prediction function using artificial intelligence from the known information, and add examination data and treatment information accumulated multiple times in the past to the prediction function to create an artificial intelligence prediction formula Additional learning is performed, and the results are supplied to the selection of the physical constitution, the prediction of post-test data, and the 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 showing that blood pressure does not decrease even if a person to be treated takes a specific antihypertensive drug, the test result and information described in known literature, that is, the By comparing this with information that blood pressure decreases with the intake of a specific antihypertensive agent, it is determined that the subject has an unusual constitution (physical 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) Treatment improvement recommendation information preferably includes test items to be improved and test value targets for avoiding the estimated risk of exacerbation in the future.
(11) It is desirable to predict a plurality of types of treatment and the corresponding future improvement or risk of aggravation, and present them to the patient so that he/she can select the most suitable one from a plurality of types of treatment.
For example, there are multiple treatment methods for lowering the HbA1c level, and depending on the patient, it is better to lower the HbA1c level rapidly, and in other cases, it is better to lower it slowly. If the change in HbA1c value in each case can be predicted and provided to the patient, more appropriate treatment can be performed.

In the present invention, it is possible to associate treatment content with various test results, and to provide a guideline for reviewing future treatment content (not reviewing in some cases) from the test results to the subject of treatment. can be executed.

It is a control block diagram of one embodiment of the present invention. It is a block diagram which shows the relationship between various test data and treatment information of one embodiment of this invention. FIG. 4 is a diagram showing a process for predicting a future disease state from various examination data and treatment information according to one embodiment of the present invention; FIG. 4 is a diagram showing a process for inputting personal attributes, medication information, etc., blood glucose level, etc., and outputting future medication information, etc. using a future test value prediction engine, according to an embodiment of the present invention. FIG. 4 is a relationship diagram showing relationships between various examination data and treatment information according to one embodiment of the present invention; It is a figure showing the content of various medication information (treatment information) of one embodiment of this invention. 4 is a line graph representing prediction of inspection data according to one embodiment of the present invention. It is a figure which shows the guideline of the present condition maintenance of one embodiment of this invention, and an improvement target. It is the table|surface which showed the relationship between the lifestyle of one embodiment of this invention, and a test value. It is a figure which shows the commentary text of one embodiment of this invention. FIG. 10 is a diagram following FIG. 9 of one embodiment of the present invention; FIG. 4 shows therapeutic effects by artificial intelligence according to one embodiment of the present invention; FIG. FIG. 12 is a graph of the contents of FIG. 12 of one embodiment of the present invention.

FIG. 1 is a control block diagram of the entire apparatus. A central processing unit (CPU) 1 includes, via a bus line 2, a treatment information memory 3 for storing treatment information of a person to be treated, and various information on the person to be treated. a test data memory 4 for storing test data, a publicly known information memory 5 for storing publicly known information published in medical papers, etc., and a difference accumulation memory 9 for accumulating differences between predicted data and test data, etc. various memories are connected.

The bus line 2 also has a prediction data display unit 6 for displaying test data predicted by inputting treatment information of a person to be treated, and a test data comparison unit 7 for comparing past test data and current test data. , an examination data comparison unit 8 for comparing examination data with the known information, and a recommended treatment display unit 10 for instructing the treatment to be recommended to the subject based on the examination data.
Furthermore, the bus line 2 is connected to an examination data input section 11 for inputting various examination data and a treatment information input section 12 for inputting treatment information.

In order to predict examination data using this apparatus, first, information regarding the treatment of the person to be treated as shown in FIG. 6 is input.

Specifically, drugs currently being taken by the subject of treatment, namely diabetes drugs (oral drugs and insulin) shown in FIG. 6, hypertension drugs, anticoagulants, heart disease drugs, cholesterol lowering drugs, etc. , gastrointestinal drugs, gout drugs, tranquilizers, adrenal corticosteroids, other anticancer drugs, etc.
In addition, other treatment information such as surgical history and radiotherapy history is input.
The treatment information includes family history (blood pressure, blood sugar level, lipid, liver function, experience of treatment, body weight at age 20) of the subject of treatment.

Next, information on various inspection data as shown in FIG. 5 is input.
The test items include physique (abdominal circumference, weight, BMI), blood pressure (systolic blood pressure, diastolic blood pressure), glucose metabolism (fasting blood glucose level, estimated average blood glucose level, HbA1c level), lipid metabolism (HDL cholesterol, LDL cholesterol, Neutral fat, liver function (AST, ALT, γ-GTP) and the like.

As shown in FIGS. 2 and 4, by periodically inputting information on treatment information and examination data as described above, data on the subject of treatment is accumulated and introduced in medical papers and the like. The artificial intelligence (AI) engine collates various publicly known information, and as the analysis results, future test value prediction (worsening or improving), genetic test value prediction, deterioration risk judgment, disease exacerbation factor analysis, and disease state improvement factor analysis sleep) is output.

Based on these analysis results, treatment evaluation (future test values, treatment content), test value prediction graph, test value targets for improving disease condition and healing, risk of aggravation and complications, action plans and precedence for recovery , the relationship between eating habits and disease is evaluated for each inspection item, recommended treatment is displayed as a result, and medication information that can achieve treatment goals is output.
In addition to the medication information, recommended treatment information such as surgery and radiotherapy is also output.

Patients can understand that their physical condition will improve if they perform the recommended treatment and undergo regular examinations.
On the other hand, it is understandable that regular examinations will deteriorate one's physical condition even if the recommended treatment is not carried out.
Therefore, the person to be treated can take good physical condition control by using this device.

FIG. 7 is a line graph showing how future test values change if a specific treatment subject does not continue treatment as it is. The value is projected to be 6.5% at present, 6.6% in 3 years, 6.8% in 6 years, and 7.3% in 9 years.
In addition, the risk prediction of complications based on treatment methods, lifestyle habits, and test results is shown in a radar chart at the bottom.

Next, the relationship between various examination data and treatment information will be described with reference to FIG.
In this figure, the vertical line on the left represents the state of inputting examination data and treatment information and finally accumulating examination data and treatment information.

That is, by first entering examination data and treatment information, and then selecting the type of current condition, future examination data is predicted. For example, if a person to be treated has a constitution in which taking a specific antihypertensive drug does not affect blood pressure, post-test data is predicted based on that assumption. Also, if the person has a constitution in which taking the antihypertensive agent lowers the blood pressure, the corresponding test data is predicted.

A recommended treatment is then selected for improvement of the test data based on the predictive value of the test data. For example, for a patient whose blood pressure does not go down even after taking a specific antihypertensive drug, a treatment such as "prescribe another antihypertensive drug" is recommended.
Then, it accumulates examination data and treatment information for multiple times, and provides a guideline for future treatment to the person to be treated.

In selecting the constitution of the person to be treated, the modification of the person to be treated is selected from the constitution selection logic in accordance with several types disclosed in publicly known information such as papers.
In addition, an initial prediction function is generated using AI (artificial intelligence) from public information such as papers, and the AI prediction formula is obtained by adding examination data and treatment information accumulated in the past multiple times to the prediction function. Learn more.
Then, the results are supplied to the selection of the physical constitution, prediction of post-test data, and recommended treatment information, thereby improving the accuracy and probability of each constitution selection, prediction, and selection of recommended treatment. Plan.

Next, referring to FIG. 3, a mode will be described in which the risk of aggravation of the current disease is suppressed if the treatment is improved so that the person to be treated is subject to the improvement recommendation information.
First, follow up on medical examinations for the past 6 years or more in the subject of treatment, estimate the future disease type of the disease that may become severe if the same treatment is continued in the future, and predict the future severity of the disease. By setting a test value target for avoidance and notifying the target test value to the person to be treated, 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 aggravation (severity) is predicted from the test value trend and disease type. In order to avoid this risk, a test value target for avoiding future diseases is set, and treatment improvement targets are set to achieve the target. It is intended to prevent the exacerbation of the current disease.

Specifically, for the diabetic patients shown in Fig. 8, the "maintenance/improvement goal of the disease condition" was set as follows: It is predicted that it will become difficult.Let's make the following behavioral improvements and do not administer additional medications or increase the dosage."
More specifically, the following proposals will be made as items to be addressed to reduce or stop medication. They are listed from top to bottom in descending order of effectiveness.

・In the title of "Continuation", the suggestion to "Take the medicine correctly" is made.
More specifically, "Diabetes is basically treated with diet and exercise therapy, but if good blood sugar control cannot be achieved with diet and exercise therapy, diabetes treatment is basically diet and exercise therapy, but diet When good glycemic control cannot be achieved with therapy and exercise therapy, drug therapy is performed to suppress the occurrence and progression of complications.”
・In the first title, "Increase," a proposal is made to say, "8000 steps in life, 20 minutes of which are moderate activities."
More specifically, "For those who do not walk 8,000 steps for 20 minutes, first take 4,000 steps for 5 minutes for 2 months, then take 6,000 steps for 10 minutes for 2 months." make suggestions.
・In the first title, ``Make a habit'', we propose to eat ``vegetables and mushrooms, meat and fish, and rice and bread in that order''.
・In the second title, "Make a habit", a suggestion is made to "finish meals three hours before going to bed."
・In the third title, "Make a habit," suggest "chew each mouthful 20-30 times slowly and thoroughly before eating."
More concretely, he makes suggestions such as increasing the amount of vegetables, avoiding pouring down food, and placing a bridge until you finish chewing the food a set number of times after putting it in your mouth.
・The first title, "Reduce," proposes to "avoid single grain dishes such as noodles, fried rice, rice bowls, pastries, and rice balls."
・In the second title, "Reduce," suggest "Refrain from eating foods that use a lot of oil, such as fried foods, Chinese food, and Western-style food."
・In the title of the third item, "Reduce", a proposal is made to "Use seasonings other than salt to get used to light seasonings."
More specifically, he proposes to accentuate the taste by using vinegar, squeezed citrus juice, ginger, garlic and other flavors, wasabi, Japanese pepper and other spices, and herbs.
- Under the third title, "Increase," make a proposal to "eat blue fish dishes containing high-quality fat and protein."
More concretely, the proposal is to "purchase fillets, ask the store to pre-process them, use frying pans and microwave ovens, and devise simple cooking methods such as canning."

Then, as shown in FIG. 9, the test values (test contents) such as blood pressure, blood sugar, triglycerides, etc. are listed on the vertical axis, and the horizontal axis indicates "dietary improvement including test values that affect related diseases". List the above proposal contents, and as items that have been given 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 in "△" It is represented by a mark with "!".

Furthermore, in Fig. 10, as a "commentary", the title is "What is happening in your body...! Dangerous deterioration of condition and development of complications may develop in this way." A description and a cross-sectional view of the blood vessel indicate the state of "If hyperglycemia (diabetes) is left alone!?"

Then, as shown in FIG. 11, various countermeasures are displayed with a subtitle of "Slow Meal Speed to Suppress Sudden Rise in Blood Sugar Level."

Fig. 12 shows a patient with a current HbA1c level of 8.4, a fasting blood sugar level of 180, and a 2-hour postprandial blood sugar level of 220 using artificial intelligence, with no treatment and three types of treatment. The table shows predicted values after 3 months.
Here, drug A (biguanide drug) acts mainly on the liver, suppresses excessive release of glucose from the liver, and has the effect of lowering blood sugar levels, improving insulin resistance and lowering blood sugar levels. It is to be lowered.

Drug B (sulfonylurea (SU) drug) acts on the pancreas to promote insulin secretion, and is effective for diabetes of the type in which the action of insulin secretion, which is common among Japanese people, is weakened.
In FIG. 12, artificial intelligence predicts that the HbA1c value will be 9.1, the fasting blood sugar will be 200, and the 2-hour postprandial blood sugar will be 240 after 3 months if the patient is not treated in the future. are doing.
Artificial intelligence predicts that the patient's HbA1c value will be 7.8, fasting blood sugar will be 160, and 2-hour postprandial blood sugar will be 190 after 3 months if the patient only performs exercise and diet therapy. ing.

In addition, when the patient took the biguanide drug (A) and combined exercise and diet therapy, after 3 months, the HbA1c value was 6.8, the fasting blood sugar was 120, and the 2-hour postprandial blood sugar was Artificial intelligence predicts that it will be 160.
Furthermore, when the patient took the sulfonylurea drug (B) and combined exercise and diet therapy, after 3 months, the HbA1c value was 6.1, the fasting blood sugar was 90, and the 2-hour postprandial blood sugar was Artificial intelligence predicts that will be 110.

FIG. 13 is a graph of the patient's HbA1c value predicted after 3 months.
Depending on the patient, there are cases where it is recommended to lower the HbA1c level gradually, rather than suddenly lowering it.
In the case of the patient shown in FIG. 13, the doctor considered it appropriate to moderately lower the HbA1c level to some extent, and recommended taking a biguanide drug (A) and combining exercise and diet therapy. 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 storage memory 10 recommended treatment display unit 11 examination data input unit 12 treatment information input unit

Claims (6)

A device that compares the treatment information and various test data of the subject to be treated with the known various test data derived from the treatment, and predicts future test data when the treatment is continued,
treatment storage means for storing treatment information of the person to be treated;
known information storage means for storing known information including various known test data related to treatment results derived from various treatments;
an examination data storage means for storing various examination data of the person to be treated;
is equipped with
By periodically inputting information about the treatment information and the examination data into the examination data storage means, the examination data of the person to be treated is accumulated, and the data and the known information stored in the known information storage means. is matched by artificial intelligence,
Using artificial intelligence to generate an initial prediction function from the known information, adding to the prediction function a plurality of previously accumulated non-public test data and treatment information to obtain an artificial intelligence prediction formula is additionally trained to
An examination data prediction device that predicts future examination data as the analysis result and suggests a treatment method based on the prediction . A device that predicts future test data based on past test data in the case of continuing a certain treatment by associating treatment information and test data of a person to be treated,
treatment storage means for storing treatment information of the person to be treated;
known information storage means for storing known information including various known test data related to treatment results derived from the various treatments;
an examination data storage means for storing various examination data of the person to be treated;
is equipped with
The test data under the same treatment are stored multiple times at intervals of time, the past test data performed each time are accumulated, and the data and the known information stored in the known information storage means are stored by artificial intelligence. match by
Using artificial intelligence to generate an initial prediction function from the known information, adding to the prediction function a plurality of previously accumulated non-public test data and treatment information to obtain an artificial intelligence prediction formula is additionally trained to
An examination data prediction device that predicts future examination data as the analysis result and suggests a treatment method based on the prediction . 3. The examination data prediction apparatus according to claim 1, wherein the treatment information includes any one of medication, surgery, radiation, rehabilitation, and conservative treatment. 3. The examination data prediction apparatus according to claim 1, wherein the treatment information includes either one or both of genetic information and medical history of the person to be treated. 5. The test data prediction device according to any one of claims 1 to 4, wherein the test data includes any one of various sample tests, physical information, genetic information, and medical history. 6. The examination data prediction device according to any one of claims 1 to 5, which predicts future examination data when treatment contents are changed.