WO2022085407A1 - Disease incidence prediction system - Google Patents

Disease incidence prediction system Download PDF

Info

Publication number
WO2022085407A1
WO2022085407A1 PCT/JP2021/036649 JP2021036649W WO2022085407A1 WO 2022085407 A1 WO2022085407 A1 WO 2022085407A1 JP 2021036649 W JP2021036649 W JP 2021036649W WO 2022085407 A1 WO2022085407 A1 WO 2022085407A1
Authority
WO
WIPO (PCT)
Prior art keywords
body temperature
subject
disease
continuously measured
morbidity
Prior art date
Application number
PCT/JP2021/036649
Other languages
French (fr)
Japanese (ja)
Inventor
朱里 丸井
彩諭理 田中
Original Assignee
株式会社Medita
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社Medita filed Critical 株式会社Medita
Priority to JP2022557370A priority Critical patent/JPWO2022085407A1/ja
Publication of WO2022085407A1 publication Critical patent/WO2022085407A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems

Definitions

  • the present invention relates to a disease morbidity prediction system using a computer.
  • Japanese Patent No. 6472153 describes a health condition evaluation system based on pulse measurement. As described above, a system for evaluating a health condition using biological information is known.
  • Re-table 2019-073963 discloses an umbilical temperature measuring device.
  • a device for continuously measuring body temperature by attaching it to the umbilical region in this way is known.
  • a system for predicting the morbidity of a specific disease of the subject using the continuously measured information on the subject's body temperature was desired.
  • the normal body temperature pattern of the subject is basically obtained. Based on the finding that the morbidity of the subject can be effectively predicted by continuously measuring the body temperature of the subject.
  • the first invention of this specification relates to a disease morbidity prediction system 1 for predicting the morbidity status of a specific disease of a subject.
  • This system 1 has a body temperature measuring unit 3, a normal body temperature information storage unit 5, a disease-related body temperature information storage unit 7, and a disease morbidity prediction unit 9.
  • the body temperature measuring unit 3 is an element for continuously measuring the body temperature of the subject and obtaining the continuously measured body temperature.
  • the body temperature measuring unit 3 is preferably a temperature measuring device attached to the umbilical region of the subject.
  • the normal body temperature information storage unit 5 is an element for storing an example of continuously measured body temperature of a subject in normal times.
  • the disease-related body temperature information storage unit 7 is an element for storing information on continuously measured body temperature when a specific disease (a third party, a specific person, or many ordinary people) suffers from a specific disease.
  • the disease morbidity prediction unit 9 uses the continuously measured body temperature of the subject, an example of the continuously measured body temperature of the subject in normal times, and the information on the continuously measured body temperature when suffering from the specific disease, and uses the information on the continuously measured body temperature of the subject. It is an element for predicting the morbidity of the disease.
  • the disease morbidity prediction unit 9 preferably includes a difference calculation unit 11 and a pattern matching unit 13.
  • the difference calculation unit 11 is an element for obtaining the difference continuous body temperature, which is the difference between the continuously measured body temperature of the subject and the example of the continuously measured body temperature of the subject in normal times.
  • a preferred example of information about continuously measured body temperature when suffering from a specific disease is the difference pattern when suffering from a specific disease, which is the pattern of the difference between the continuously measured body temperature when suffering from a specific disease and the continuously measured body temperature during normal times.
  • the pattern matching unit 13 is an element for performing pattern matching between the difference continuous body temperature of the subject obtained by the difference calculation unit 11 and the difference pattern at the time of suffering from a specific disease, and obtaining a pattern matching result.
  • a preferred example of the disease morbidity prediction unit 9 predicts the morbidity status of the subject regarding a specific disease based on the pattern matching result by the pattern matching unit 13.
  • This specification also provides a program for making the computer function as the above system and an information recording medium containing the program.
  • the morbidity of the subject can be effectively predicted by using the continuously measured information on the body temperature of the subject.
  • FIG. 1 is a block diagram showing a basic configuration example of a disease morbidity prediction system.
  • FIG. 2 is a block diagram showing a basic configuration of a computer.
  • FIG. 3 is a conceptual diagram showing an example of the system of the present invention.
  • FIG. 4 is a conceptual diagram showing an example of a body temperature measuring unit.
  • FIG. 5 is a diagram for explaining the differential continuous body temperature.
  • FIG. 5 (a) shows the continuously measured body temperature of the subject
  • FIG. 5 (b) shows an example of the continuously measured body temperature of the subject in normal times
  • FIG. 5 (c) shows the differential continuous body temperature.
  • FIG. 6 is a conceptual diagram for explaining pattern matching.
  • FIG. 6A shows an example of a difference pattern at the time of morbidity of a specific disease.
  • FIG. 6 (b) shows that the difference pattern at the time of morbidity of a specific disease matched with the difference continuous body temperature was extracted.
  • FIG. 1 is a block diagram showing a basic configuration example of a disease morbidity prediction system.
  • This system 1 relates to a disease morbidity prediction system for predicting the morbidity status of a specific disease of a subject.
  • This system is a computer-based system. Computers basically perform various elements and processes.
  • the "morbidity of a specific disease of a subject" includes the beginning of a specific disease, the initial stage of a specific disease without symptoms, the stage of recovering from the specific disease after having once suffered from the specific disease, and the current specific disease.
  • this system 1 has a body temperature measuring unit 3, a normal body temperature information storage unit 5, a disease-related body temperature information storage unit 7, and a disease morbidity prediction unit 9.
  • the disease morbidity prediction unit 9 preferably includes a difference calculation unit 11 and a pattern matching unit 13. For example, the information that a specific medicine has been taken may be separately input to this system 1. In this way, it is possible to analyze how a particular drug is reflected in the patient's situation.
  • FIG. 2 is a block diagram showing the basic configuration of a computer.
  • the computer has an input unit 31, an output unit 33, a control unit 35, a calculation unit 37, and a storage unit 39, and each element is connected by a bus 41 or the like to exchange information.
  • the control program may be stored or various information may be stored in the storage unit.
  • the control unit reads out the control program stored in the storage unit.
  • the control unit reads out the information stored in the storage unit as appropriate and transmits it to the arithmetic unit.
  • the control unit transmits the appropriately input information to the calculation unit.
  • the arithmetic unit performs arithmetic processing using various received information and stores it in the storage unit.
  • the control unit reads the calculation result stored in the storage unit and outputs it from the output unit. In this way, various processes are executed.
  • Each element described below may correspond to any element of the computer.
  • FIG. 3 is a conceptual diagram showing an example of the system of the present invention.
  • the system of the present invention (a system including the apparatus of the present invention) includes a terminal 45 connected to the Internet or an intranet 43, and a server 47 connected to the Internet or an intranet 43.
  • a single computer or mobile terminal may function as the device of the present invention, or a plurality of servers may exist.
  • FIG. 4 is a conceptual diagram showing an example of a body temperature measuring unit.
  • the body temperature measuring unit 3 is connected to, for example, a computer so that information can be exchanged. Further, the device including the body temperature measuring unit 3 may include a computer.
  • the body temperature measuring unit 3 is an element for continuously measuring the body temperature of the subject and obtaining the continuously measured body temperature.
  • the body temperature measuring unit 3 is preferably a temperature measuring device attached to the umbilical region of the subject. However, the body temperature measuring unit 3 may measure the temperature of a portion other than the umbilical region.
  • the body temperature measuring unit may be one that senses the body surface of the subject (for example, the face part, the axilla, or the eardrum) and measures the temperature thereof.
  • the body temperature measuring unit 3 can output the measured body temperature information to, for example, a computer or a server.
  • the computer that receives the body temperature information inputs the body temperature information into the computer. Then, the computer appropriately stores the input body temperature information in the storage unit. Then, the body temperature information stored in the storage unit may be read out to obtain the continuously measured body temperature for a predetermined period. The obtained continuously measured body temperature is appropriately stored in the storage unit.
  • An example of the body temperature measuring unit is the umbilical region temperature measuring device described in Japanese Patent Publication No. 2019-073963.
  • Another example of a body temperature measuring unit is a non-contact type body surface temperature measuring device (for example, a body surface temperature measuring device, a thermal camera or a thermography). The body temperature measuring unit may be used in combination with a contact type and a non-contact type.
  • the normal body temperature information storage unit 5 is an element for storing an example of continuously measured body temperature of the subject in normal times.
  • the storage unit of the computer functions as the normal body temperature information storage unit 5.
  • the continuous measurement body temperature of the subject in normal times may be measured in advance using, for example, the body temperature measuring unit 3.
  • an example of the continuously measured body temperature in normal times can be obtained by repeatedly obtaining the continuously measured body temperature for the above-mentioned predetermined period.
  • the example of the continuously measured body temperature in normal times may be an example of the continuously measured body temperature in normal times for each situation such as resting, sleeping, active, exercising, before meals, after meals, and a predetermined time.
  • Another example of continuous measurement of body temperature in normal times is an example of continuous measurement of body temperature in normal times when there are no symptoms, headache, runny nose, diarrhea, and abdominal pain.
  • normal times mean ordinary or everyday situations. Even in such a situation, it is desirable to memorize an example of continuously measured body temperature in normal times. By doing so, it is possible to predict whether or not the patient is suffering from the disease more appropriately by using the example of continuous measurement body temperature in normal times according to the situation.
  • an example of continuously measured body temperature in normal times should be stored in the storage unit together with information on the situation. Then, the situation may be predicted using the body temperature measured by the body temperature measuring unit 3, and pattern matching may be performed using the information regarding the predicted situation.
  • the disease-related body temperature information storage unit 7 is an element for storing information on continuously measured body temperature when suffering from a specific disease.
  • the storage unit of the computer functions as a disease-related body temperature information storage unit 7.
  • Information on continuous measurement of body temperature when suffering from a specific disease is, for example, for the general public, age, gender, pre-existing illness, weight, amount of drinking and frequency of drinking, daily medication information (eg, type, amount, time of ingestion, symptoms). It may be stored together with information about the measurement target such as (eg, headache, runny nose, diarrhea, etc.) and the situation at the time of measurement (eg, resting, sleeping, before meals, measurement time, exercising, active).
  • the body temperature of a general person may be continuously measured, and if the person suffers from a specific disease, the continuous body temperature data of the person may be acquired. You may memorize the continuous body temperature, such as when you start to get a specific disease or when you get a specific disease in earnest. You may also memorize the continuous body temperature before and after taking a specific medicine. And, as will be described later, the difference between the normal continuous body temperature of the general public and the continuous body temperature when suffering from these specific diseases may be obtained and stored in the storage unit. , The temperature pattern and difference pattern when suffering from such a specific disease may be analyzed by machine learning and stored in the storage unit.
  • a body temperature fluctuation pattern and a difference pattern from normal times. That is, a preferable example of information on continuous measurement body temperature when suffering from a specific disease is continuous measurement body temperature and normality when suffering from a specific disease. It is a difference pattern at the time of symptom of a specific disease which is a pattern of the difference from the continuous measurement body temperature at the time.
  • the disease morbidity prediction unit 9 uses the continuously measured body temperature of the subject, an example of the continuously measured body temperature of the subject in normal times, and the information on the continuously measured body temperature when suffering from the specific disease, and uses the information on the continuously measured body temperature of the subject. It is a factor for predicting the morbidity of the disease.
  • the control unit, the calculation unit, and the storage unit of the computer function as the disease morbidity prediction unit 9.
  • the disease morbidity prediction unit 9 preferably includes a difference calculation unit 11 and a pattern matching unit 13.
  • the difference calculation unit 11 is an element for obtaining the difference continuous body temperature, which is the difference between the continuously measured body temperature of the subject and the example of the continuously measured body temperature of the subject in normal times.
  • the difference calculation unit 11 may be used to obtain the difference between the continuously measured body temperature of a general person when suffering from a specific disease and the example of the continuously measured body temperature of the general person in normal times.
  • an example of the subject's continuously measured body temperature and the subject's normal continuously measured body temperature is stored in the storage unit. Therefore, the difference calculation unit 11 reads an example of the continuously measured body temperature of the target person stored in the storage unit and the continuously measured body temperature of the target person in normal times, and performs the difference calculation to perform these difference values (difference continuous). Body temperature) can be obtained. Then, the obtained difference value may be appropriately stored in the storage unit.
  • the pattern matching unit 13 is an element for performing pattern matching between the difference continuous body temperature of the subject obtained by the difference calculation unit 11 and the difference pattern at the time of suffering from a specific disease, and obtaining a pattern matching result.
  • the difference continuous body temperature of the subject and the difference pattern at the time of morbidity of a specific disease are stored in the memory.
  • the difference pattern at the time of morbidity of a specific disease is age, gender, pre-existing illness, weight, amount of drinking and frequency of drinking, daily medication information (example: type, amount, intake time, symptoms (example: headache, nasal discharge, diarrhea, etc.)).
  • the pattern matching unit 13 may perform pattern matching by, for example, machine learning. At that time, the difference between the above-mentioned subjects. Pattern matching may be performed including not only the continuous body temperature and the difference pattern at the time of suffering from a specific disease but also the above-mentioned information on the measurement target.
  • a preferred example of the disease morbidity prediction unit 9 is to predict the morbidity status of the subject regarding a specific disease based on the pattern matching result by the pattern matching unit 13.
  • the pattern matching unit 13 obtains some difference patterns at the time of morbidity of a specific disease having a high degree of similarity in relation to the difference continuous body temperature of the subject obtained by the difference calculation unit 11. Then, the morbidity status of the subject regarding the specific disease is predicted by using the specific disease related to the obtained morbidity difference pattern of the specific disease.
  • the degree of this prediction may be analyzed by a computer, for example, using information such as whether the patterns are very similar or how many differences patterns at the time of morbidity of a specific disease have a high degree of similarity.
  • the pattern matching unit 13 may analyze the situation regarding the specific disease of the subject by using the continuously measured body temperature of the subject stored by the normal body temperature information storage unit 5 in the normal time.
  • the situation related to such a specific disease when there are multiple types of medicines related to the specific disease, the relationship between the fluctuation pattern of body temperature and the effective drug is pattern-authenticated, and the subject's normal continuous measurement body temperature is measured. Is used to obtain information on effective medicines for the subject. For example, in fibromyalgia, multiple types of pain-improving drugs are administered to patients.
  • the effective drugs for the patients can be identified. In this way, it is possible to prevent the situation of administering unnecessary medicines and the side effects and medical expenses due to the administration.
  • This can be used not only for continuous body temperature in normal times but also for determining whether or not a predetermined drug is effective for a patient with respect to a temperature change after administration of the predetermined drug.
  • This program is intended to make the computer function as the above system.
  • This computer may include various sensors such as a body temperature measuring unit.
  • this program This is a program for making a computer function as a disease morbidity prediction system 1 for predicting the morbidity status of a specific disease of a subject.
  • the computer on which this program is implemented has a body temperature measuring means 3, a normal body temperature information storing means 5, a disease-related body temperature information storing means 7, and a disease morbidity predicting means 9. Each means corresponds to each part described above.
  • This specification also provides an information storage medium that stores the above program.
  • Examples of information storage media are CD-ROMs, DVDs, USBs, hard disks and memory sticks.
  • the body temperature measuring unit 3 continuously measures the body temperature of the subject and obtains the continuously measured body temperature (continuous measurement body temperature measuring step).
  • the normal body temperature information storage unit 5 stores an example of the continuously measured body temperature of the subject in normal times.
  • the disease-related body temperature information storage unit 7 stores information on continuously measured body temperature when suffering from a specific disease.
  • the disease morbidity prediction unit 9 uses the continuously measured body temperature of the subject, an example of the continuously measured body temperature of the subject in normal times, and the information on the continuously measured body temperature when suffering from the specific disease, and uses the information on the continuously measured body temperature of the subject. Predict the morbidity of the disease (prediction process).
  • the difference calculation unit 11 obtains the difference continuous body temperature, which is the difference between the continuously measured body temperature of the subject and the example of the continuously measured body temperature of the subject in normal times (difference calculation step).
  • FIG. 5 is a diagram for explaining the differential continuous body temperature.
  • FIG. 5 shows an example of the continuously measured body temperature of the subject and the continuously measured body temperature of the subject in normal times.
  • the pattern matching unit 13 performs pattern matching between the difference continuous body temperature of the subject obtained by the difference calculation unit 11 and the difference pattern at the time of suffering from a specific disease, and obtains a pattern matching result (pattern matching step).
  • FIG. 6 is a conceptual diagram for explaining pattern matching.
  • FIG. 6A shows an example of a difference pattern at the time of morbidity of a specific disease.
  • FIG. 6 (b) shows that the difference pattern at the time of morbidity of a specific disease matched with the difference continuous body temperature was extracted. As shown in FIG. 6A, a large number of specific disease morbidity difference patterns are stored in the storage unit.
  • the pattern matching unit 13 may perform a pattern matching calculation between a large number of stored difference patterns at the time of morbidity of a specific disease and the difference continuous body temperature of the subject. This pattern matching operation may be performed by machine learning. As shown in FIG. 6 (b), the morbidity status of the subject regarding the specific disease can be predicted by the computer in this way. As described above, in the example of FIG. 6, pattern matching was performed by the difference value between the continuous measurement temperature at the time of morbidity of a specific disease and the normal time.
  • the invention described in this specification is not limited to pattern matching based on difference values, and any pattern matching may be adopted as long as it is pattern matching using continuous measurement temperature.
  • This invention can be used in the medical device industry.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

[Problem] To provide a system for predicting the incidence status relating to a specific disease in a subject using data relating to continuously measured body temperature of the subject. [Solution] A disease incidence prediction system 1 that comprises: a body temperature measurement unit 3 that continuously measures the body temperature of a subject to obtain continuously measured body temperature; an ordinary body temperature data storage unit 5 that stores examples of the continuously measured body temperature of the subject at ordinary times; a disease-related body temperature data storage unit 7 that stores data relating to the continuously measured body temperature when the subject suffers from a specific disease; and a disease incidence prediction unit 9 that predicts the incidence status relating to the specific disease in the subject using the continuously measured body temperature of the subject, the examples of the continuously measured body temperature of the subject at ordinary times, and the data relating to the continuously measured body temperature when the subject suffers from the specific disease.

Description

疾患罹患予測システムDisease morbidity prediction system
　この発明は，コンピュータを用いた疾患罹患予測システムに関する。 The present invention relates to a disease morbidity prediction system using a computer.
　特許６４７２１５３号公報には，脈拍測定による健康状態評価システムが記載されている。このように生体情報を用いて健康状態を評価するシステムは知られている。 Japanese Patent No. 6472153 describes a health condition evaluation system based on pulse measurement. As described above, a system for evaluating a health condition using biological information is known.
　再表２０１９－０７３９６３号公報には，臍部温度測定装置が記載されている。このように臍部に装着することで連続的に体温を測定するための装置は知られている。 Re-table 2019-073963 discloses an umbilical temperature measuring device. A device for continuously measuring body temperature by attaching it to the umbilical region in this way is known.
特許６４７２１５３号公報Japanese Patent No. 6472153 再表２０１９－０７３９６３号公報Re-Table 2019-073963 Gazette
　連続的に測定される対象者の体温に関する情報を用いて，対象者の特定疾患に関する罹患状況予測するためのシステムが望まれた。 A system for predicting the morbidity of a specific disease of the subject using the continuously measured information on the subject's body temperature was desired.
　この発明は，基本的には，特定の者の平常時の体温と，疾患罹患時の体温の差分には，疾患の種類によりいくつかのパターンが存在するので，対象者の平常時の体温パターンを求めておいて，対象者の体温を連続的に測定すれば，対象者の罹患状況を効果的に予想できるという知見に基づく。 In the present invention, basically, there are several patterns in the difference between the normal body temperature of a specific person and the body temperature at the time of illness depending on the type of disease, so that the normal body temperature pattern of the subject is basically obtained. Based on the finding that the morbidity of the subject can be effectively predicted by continuously measuring the body temperature of the subject.
　この明細書の最初の発明は，対象者の特定疾患に関する罹患状況予測するための疾患罹患予測システム１に関する。
　このシステム１は，体温測定部３と，平常時体温情報記憶部５と，疾患関連体温情報記憶部７と，疾患罹患予測部９とを有する。
　体温測定部３は，対象者の体温を連続的に測定し，連続測定体温を得るための要素である。体温測定部３は，対象者の臍部に装着する温度測定装置であることが好ましい 。
　平常時体温情報記憶部５は，対象者の平常時の連続測定体温の例を記憶するための要素である。
　疾患関連体温情報記憶部７は，（第三者，特定の者，又は多くの一般人が）特定疾患に罹患した時の連続測定体温に関する情報を記憶するための要素である。
　疾患罹患予測部９は，対象者の連続測定体温と，対象者の平常時の連続測定体温の例と，特定疾患に罹患した時の連続測定体温に関する情報とを用いて， 対象者の特定疾患に関する罹患状況予測するための要素である。
　疾患罹患予測部９は，差分演算部１１と，パターンマッチング部１３とを有するものが好ましい。
　差分演算部１１は，対象者の連続測定体温と，対象者の平常時の連続測定体温の例との差分である差分連続体温を求めるための要素である。
　特定疾患に罹患した時の連続測定体温に関する情報の好ましい例は，特定疾患に罹患した時の連続測定体温と平常時の連続測定体温との差分のパターンである特定疾患罹患時差分パターンである。
　パターンマッチング部１３は，差分演算部１１が求めた対象者の差分連続体温と，特定疾患罹患時差分パターンとをパターンマッチングを行ってパターンマッチング結果を得るための要素である。
　そして，疾患罹患予測部９の好ましい例は，パターンマッチング部１３によるパターンマッチング結果に基づいて，対象者の特定疾患に関する罹患状況予測する。 The first invention of this specification relates to a disease morbidity prediction system 1 for predicting the morbidity status of a specific disease of a subject.
This system 1 has a body temperature measuring unit 3, a normal body temperature information storage unit 5, a disease-related body temperature information storage unit 7, and a disease morbidity prediction unit 9.
The body temperature measuring unit 3 is an element for continuously measuring the body temperature of the subject and obtaining the continuously measured body temperature. The body temperature measuring unit 3 is preferably a temperature measuring device attached to the umbilical region of the subject.
The normal body temperature information storage unit 5 is an element for storing an example of continuously measured body temperature of a subject in normal times.
The disease-related body temperature information storage unit 7 is an element for storing information on continuously measured body temperature when a specific disease (a third party, a specific person, or many ordinary people) suffers from a specific disease.
The disease morbidity prediction unit 9 uses the continuously measured body temperature of the subject, an example of the continuously measured body temperature of the subject in normal times, and the information on the continuously measured body temperature when suffering from the specific disease, and uses the information on the continuously measured body temperature of the subject. It is an element for predicting the morbidity of the disease.
The disease morbidity prediction unit 9 preferably includes a difference calculation unit 11 and a pattern matching unit 13.
The difference calculation unit 11 is an element for obtaining the difference continuous body temperature, which is the difference between the continuously measured body temperature of the subject and the example of the continuously measured body temperature of the subject in normal times.
A preferred example of information about continuously measured body temperature when suffering from a specific disease is the difference pattern when suffering from a specific disease, which is the pattern of the difference between the continuously measured body temperature when suffering from a specific disease and the continuously measured body temperature during normal times.
The pattern matching unit 13 is an element for performing pattern matching between the difference continuous body temperature of the subject obtained by the difference calculation unit 11 and the difference pattern at the time of suffering from a specific disease, and obtaining a pattern matching result.
A preferred example of the disease morbidity prediction unit 9 predicts the morbidity status of the subject regarding a specific disease based on the pattern matching result by the pattern matching unit 13.
　この明細書は，コンピュータを上記のシステムとして機能させるためのプログラムやそのプログラムを格納した情報記録媒体をも提供する。 This specification also provides a program for making the computer function as the above system and an information recording medium containing the program.
　この発明によれば，連続的に測定される対象者の体温に関する情報を用いて，対象者の罹患状況を効果的に予測できる。 According to the present invention, the morbidity of the subject can be effectively predicted by using the continuously measured information on the body temperature of the subject.
図１は，疾患罹患予測システムの基本構成例を示すブロック図である。FIG. 1 is a block diagram showing a basic configuration example of a disease morbidity prediction system. 図２は，コンピュータの基本構成を示すブロック図である。FIG. 2 is a block diagram showing a basic configuration of a computer. 図３は，本発明のシステム例を示す概念図である。FIG. 3 is a conceptual diagram showing an example of the system of the present invention. 図４は，体温測定部の例を示す概念図である。FIG. 4 is a conceptual diagram showing an example of a body temperature measuring unit. 図５は，差分連続体温を説明するための図である。図５（ａ）は，対象者の連続測定体温を示し，図５（ｂ）は，対象者の平常時の連続測定体温の例を示し，図５（ｃ）は差分連続体温を示す。FIG. 5 is a diagram for explaining the differential continuous body temperature. FIG. 5 (a) shows the continuously measured body temperature of the subject, FIG. 5 (b) shows an example of the continuously measured body temperature of the subject in normal times, and FIG. 5 (c) shows the differential continuous body temperature. 図６は，パターンマッチングを説明するための概念図である。図６（ａ）は，特定疾患罹患時差分パターンの例を示す。図６（ｂ）は，差分連続体温とマッチングした特定疾患罹患時差分パターンが抽出されたことを示す。FIG. 6 is a conceptual diagram for explaining pattern matching. FIG. 6A shows an example of a difference pattern at the time of morbidity of a specific disease. FIG. 6 (b) shows that the difference pattern at the time of morbidity of a specific disease matched with the difference continuous body temperature was extracted.
　以下，図面を用いて本発明を実施するための形態について説明する。本発明は，以下に説明する形態に限定されるものではなく，以下の形態から当業者が自明な範囲で適宜修正したものも含む。 Hereinafter, a mode for carrying out the present invention will be described with reference to the drawings. The present invention is not limited to the forms described below, and includes those modified appropriately by those skilled in the art from the following forms.
　図１は，疾患罹患予測システムの基本構成例を示すブロック図である。このシステム１は，対象者の特定疾患に関する罹患状況予測するための疾患罹患予測システムに関する。このシステムは，コンピュータに基づくシステムである。各種要素や工程は，基本的にはコンピュータが行う。「対象者の特定疾患に関する罹患状況」には，特定疾患のかかり始めや，症状のない特定疾患の初期段階，いったん特定疾患に罹患した後に当該特定疾患から回復している段階，現在特定疾患に罹患しているか，罹患している特定疾患の進行状況，平常時から特定疾患に罹患してそれが回復している状況，特定疾患のかかり始めに特定の医薬を摂取した後の治療・予防状況，特定疾患に罹患した後に特定の医薬を摂取した後の治癒・回復状況を含む。図１に示されるように，このシステム１は，体温測定部３と，平常時体温情報記憶部５と，疾患関連体温情報記憶部７と，疾患罹患予測部９とを有する。疾患罹患予測部９は，差分演算部１１と，パターンマッチング部１３とを有するものが好ましい。例えば，特定の医薬を摂取したという情報は，このシステム１に別途入力されてもよい。このようにすれば，特定の医薬がどのように患者の状況に反映されるかを分析することができる。また，このようにすれば，特定の医薬の有効性や，有効な場合の体温変化を把握でき，特定の医薬が有効な患者を分析することもできることとなる。この場合，平常時や医薬摂取後の温度変化を記憶し，特定医薬が有効であったか有効でなかったかという情報とともに記憶させ，それにより，特定の医薬が有効な患者と有効でない患者とを識別できるようになる。 FIG. 1 is a block diagram showing a basic configuration example of a disease morbidity prediction system. This system 1 relates to a disease morbidity prediction system for predicting the morbidity status of a specific disease of a subject. This system is a computer-based system. Computers basically perform various elements and processes. The "morbidity of a specific disease of a subject" includes the beginning of a specific disease, the initial stage of a specific disease without symptoms, the stage of recovering from the specific disease after having once suffered from the specific disease, and the current specific disease. Affected or suffering progress of a specific disease, a situation in which a specific disease is affected and recovered from normal times, a treatment / prevention situation after taking a specific drug at the beginning of the specific disease ， Includes the healing / recovery status after taking a specific drug after suffering from a specific disease. As shown in FIG. 1, this system 1 has a body temperature measuring unit 3, a normal body temperature information storage unit 5, a disease-related body temperature information storage unit 7, and a disease morbidity prediction unit 9. The disease morbidity prediction unit 9 preferably includes a difference calculation unit 11 and a pattern matching unit 13. For example, the information that a specific medicine has been taken may be separately input to this system 1. In this way, it is possible to analyze how a particular drug is reflected in the patient's situation. In addition, by doing so, it is possible to grasp the effectiveness of a specific drug and the change in body temperature when it is effective, and it is possible to analyze patients for whom a specific drug is effective. In this case, the temperature change during normal times and after ingestion of the drug is memorized, and the information indicating whether the specific drug was effective or not is memorized, thereby distinguishing the patient who is effective from the specific drug from the patient who is not effective. It will be like.
　図２は，コンピュータの基本構成を示すブロック図である。この図に示されるように，コンピュータは，入力部３１，出力部３３，制御部３５，演算部３７及び記憶部３９を有しており，各要素は，バス４１などによって接続され，情報の授受を行うことができるようにされている。例えば，記憶部には，制御プログラムが記憶されていてもよいし，各種情報が記憶されていてもよい。入力部から所定の情報が入力された場合，制御部は，記憶部に記憶される制御プログラムを読み出す。そして，制御部は，適宜記憶部に記憶された情報を読み出し，演算部へ伝える。また，制御部は，適宜入力された情報を演算部へ伝える。演算部は，受け取った各種情報を用いて演算処理を行い，記憶部に記憶する。制御部は，記憶部に記憶された演算結果を読み出して，出力部から出力する。このようにして，各種処理が実行される。以下説明する各要素は，コンピュータのいずれかの要素に対応していてもよい。 FIG. 2 is a block diagram showing the basic configuration of a computer. As shown in this figure, the computer has an input unit 31, an output unit 33, a control unit 35, a calculation unit 37, and a storage unit 39, and each element is connected by a bus 41 or the like to exchange information. Is designed to be able to do. For example, the control program may be stored or various information may be stored in the storage unit. When the specified information is input from the input unit, the control unit reads out the control program stored in the storage unit. Then, the control unit reads out the information stored in the storage unit as appropriate and transmits it to the arithmetic unit. In addition, the control unit transmits the appropriately input information to the calculation unit. The arithmetic unit performs arithmetic processing using various received information and stores it in the storage unit. The control unit reads the calculation result stored in the storage unit and outputs it from the output unit. In this way, various processes are executed. Each element described below may correspond to any element of the computer.
　図３は，本発明のシステム例を示す概念図である。図３に示されるように，本発明のシステム（本発明の装置を含むシステム）は，インターネット又はイントラネット４３と接続された端末４５と，インターネット又はイントラネット４３に接続されたサーバ４７とを含むものであってもよい。もちろん，単体のコンピュータや携帯端末が，本発明の装置として機能してもよいし，複数のサーバが存在してもよい。 FIG. 3 is a conceptual diagram showing an example of the system of the present invention. As shown in FIG. 3, the system of the present invention (a system including the apparatus of the present invention) includes a terminal 45 connected to the Internet or an intranet 43, and a server 47 connected to the Internet or an intranet 43. There may be. Of course, a single computer or mobile terminal may function as the device of the present invention, or a plurality of servers may exist.
　図４は，体温測定部の例を示す概念図である。体温測定部３は，例えば，コンピュータと情報の授受を行うことができるように接続されている。また，体温測定部３を含む装置がコンピュータを含んでもよい。体温測定部３は，対象者の体温を連続的に測定し，連続測定体温を得るための要素である。体温測定部３は，対象者の臍部に装着する温度測定装置であることが好ましい。もっとも，体温測定部３は，臍部以外の部位の温度を測定するものであってもよい。例えば，体温測定部は，対象者の体表（例えば顔部分，腋窩又は鼓膜）をセンシングし，その温度を測定するものであってもよい。体温測定部３は，例えば，コンピュータやサーバに測定した体温情報を出力できる。体温情報を受け取ったコンピュータは，コンピュータ内に体温情報を入力する。そして，コンピュータは，入力された体温情報を適宜記憶部に記憶する。そして，記憶部に記憶された体温情報を読み出して，所定期間の連続測定体温を求めてもよい。求めた連続測定体温は，適宜記憶部に記憶される。体温測定部の例は，再表２０１９－０７３９６３号公報に記載された臍部温度測定装置である。体温測定部の別の例は，非接触型の体表温度測定装置（例えば，体表面温度測定装置，サーマルカメラ又はサーモグラフィ）である。体温測定部は，接触型と非接触型のものを組み合わせて用いてもよい。 FIG. 4 is a conceptual diagram showing an example of a body temperature measuring unit. The body temperature measuring unit 3 is connected to, for example, a computer so that information can be exchanged. Further, the device including the body temperature measuring unit 3 may include a computer. The body temperature measuring unit 3 is an element for continuously measuring the body temperature of the subject and obtaining the continuously measured body temperature. The body temperature measuring unit 3 is preferably a temperature measuring device attached to the umbilical region of the subject. However, the body temperature measuring unit 3 may measure the temperature of a portion other than the umbilical region. For example, the body temperature measuring unit may be one that senses the body surface of the subject (for example, the face part, the axilla, or the eardrum) and measures the temperature thereof. The body temperature measuring unit 3 can output the measured body temperature information to, for example, a computer or a server. The computer that receives the body temperature information inputs the body temperature information into the computer. Then, the computer appropriately stores the input body temperature information in the storage unit. Then, the body temperature information stored in the storage unit may be read out to obtain the continuously measured body temperature for a predetermined period. The obtained continuously measured body temperature is appropriately stored in the storage unit. An example of the body temperature measuring unit is the umbilical region temperature measuring device described in Japanese Patent Publication No. 2019-073963. Another example of a body temperature measuring unit is a non-contact type body surface temperature measuring device (for example, a body surface temperature measuring device, a thermal camera or a thermography). The body temperature measuring unit may be used in combination with a contact type and a non-contact type.
　平常時体温情報記憶部５は，対象者の平常時の連続測定体温の例を記憶するための要素である。例えば，コンピュータの記憶部が，平常時体温情報記憶部５として機能する。対象者の平常時の連続測定体温は，例えば，体温測定部３を用いてあらかじめ測定しておけばよい。この場合，上記した所定期間の連続測定体温を繰り返し求めることで，平常時の連続測定体温の例を得ることができる。平常時の連続測定体温の例は，安静時，睡眠中，活動時，運動中，食事前，食事後，所定時刻といったシチュエーションごとの平常時の連続測定体温の例であってもよい。平常時の連続測定体温の別の例は，全く症状のない際，頭痛のある際，鼻水が出る際，下痢を訴える際，腹痛を訴える際の平常時の連続測定体温の例である。つまり平常時とは，普段や日常的な状況といった意味である。このようなシチュエーションについても平常時の連続測定体温の例を記憶しておくことが望ましい。そのようにすれば，シチュエーションに応じた平常時の連続測定体温の例を用いて，より適切に疾患に罹患しているか予測できることとなる。この場合，シチュエーションに関する情報と合わせて平常時の連続測定体温の例を記憶部に記憶しておけばよい。そして，体温測定部３が測定した体温を用いてシチュエーションを予測し，予測したシチュエーションに関する情報を用いてパターンマッチングを行えばよい。 The normal body temperature information storage unit 5 is an element for storing an example of continuously measured body temperature of the subject in normal times. For example, the storage unit of the computer functions as the normal body temperature information storage unit 5. The continuous measurement body temperature of the subject in normal times may be measured in advance using, for example, the body temperature measuring unit 3. In this case, an example of the continuously measured body temperature in normal times can be obtained by repeatedly obtaining the continuously measured body temperature for the above-mentioned predetermined period. The example of the continuously measured body temperature in normal times may be an example of the continuously measured body temperature in normal times for each situation such as resting, sleeping, active, exercising, before meals, after meals, and a predetermined time. Another example of continuous measurement of body temperature in normal times is an example of continuous measurement of body temperature in normal times when there are no symptoms, headache, runny nose, diarrhea, and abdominal pain. In other words, normal times mean ordinary or everyday situations. Even in such a situation, it is desirable to memorize an example of continuously measured body temperature in normal times. By doing so, it is possible to predict whether or not the patient is suffering from the disease more appropriately by using the example of continuous measurement body temperature in normal times according to the situation. In this case, an example of continuously measured body temperature in normal times should be stored in the storage unit together with information on the situation. Then, the situation may be predicted using the body temperature measured by the body temperature measuring unit 3, and pattern matching may be performed using the information regarding the predicted situation.
　疾患関連体温情報記憶部７は，特定疾患に罹患した時の連続測定体温に関する情報を記憶するための要素である。コンピュータの記憶部が疾患関連体温情報記憶部７として機能する。特定疾患に罹患した時の連続測定体温に関する情報は，例えば，一般人について，年齢，性別，既往症，体重，飲酒量及び飲酒頻度，日常の服薬情報（例：薬の種類、量、摂取時刻，症状（例：頭痛、鼻水、下痢など），測定時の状況（例：安静時，睡眠中，食事前，測定時刻，運動中，活動中）といった測定対象に関する情報と合わせて記憶されてもよい。これらの情報と合わせて，一般人について，連続的に体温を測定しておき，特定疾患に罹患した場合に，その者の連続体温データを取得するようにしてもよい。また，一般人の平常時の連続体温を記憶しておき，特定の疾患のかかりはじめ，特定の疾患に本格的にかかった際などの連続体温を記憶しておいてもよい。また，特定の医薬を摂取する前後の連続体温を記憶してもよい。そして,後述の通り,一般人の平常時の連続体温と，これら特定疾患に罹患した際の連続体温の差分を求めて,記憶部に記憶しておいてもよい。そして，そのような特定疾患に罹患した際の温度パターンや差分パターンを機械学習により分析し，記憶部に記憶しておいてもよい。このようにすることで，一般人の特定疾患に罹患した際の体温変動パターンや，平常時との差分パターンを得ることができることとなる。つまり，特定疾患に罹患した時の連続測定体温に関する情報の好ましい例は，特定疾患に罹患した時の連続測定体温と平常時の連続測定体温との差分のパターンである特定疾患罹患時差分パターンである。 The disease-related body temperature information storage unit 7 is an element for storing information on continuously measured body temperature when suffering from a specific disease. The storage unit of the computer functions as a disease-related body temperature information storage unit 7. Information on continuous measurement of body temperature when suffering from a specific disease is, for example, for the general public, age, gender, pre-existing illness, weight, amount of drinking and frequency of drinking, daily medication information (eg, type, amount, time of ingestion, symptoms). It may be stored together with information about the measurement target such as (eg, headache, runny nose, diarrhea, etc.) and the situation at the time of measurement (eg, resting, sleeping, before meals, measurement time, exercising, active). In addition to this information, the body temperature of a general person may be continuously measured, and if the person suffers from a specific disease, the continuous body temperature data of the person may be acquired. You may memorize the continuous body temperature, such as when you start to get a specific disease or when you get a specific disease in earnest. You may also memorize the continuous body temperature before and after taking a specific medicine. And, as will be described later, the difference between the normal continuous body temperature of the general public and the continuous body temperature when suffering from these specific diseases may be obtained and stored in the storage unit. ， The temperature pattern and difference pattern when suffering from such a specific disease may be analyzed by machine learning and stored in the storage unit. By doing so, when suffering from a specific disease of the general public It is possible to obtain a body temperature fluctuation pattern and a difference pattern from normal times. That is, a preferable example of information on continuous measurement body temperature when suffering from a specific disease is continuous measurement body temperature and normality when suffering from a specific disease. It is a difference pattern at the time of symptom of a specific disease which is a pattern of the difference from the continuous measurement body temperature at the time.
　疾患罹患予測部９は，対象者の連続測定体温と，対象者の平常時の連続測定体温の例と，特定疾患に罹患した時の連続測定体温に関する情報とを用いて， 対象者の特定疾患に関する罹患状況を予測するための要素である。コンピュータの，制御部，演算部，及び記憶部が，疾患罹患予測部９として機能する。疾患罹患予測部９は，差分演算部１１と，パターンマッチング部１３とを有するものが好ましい。 The disease morbidity prediction unit 9 uses the continuously measured body temperature of the subject, an example of the continuously measured body temperature of the subject in normal times, and the information on the continuously measured body temperature when suffering from the specific disease, and uses the information on the continuously measured body temperature of the subject. It is a factor for predicting the morbidity of the disease. The control unit, the calculation unit, and the storage unit of the computer function as the disease morbidity prediction unit 9. The disease morbidity prediction unit 9 preferably includes a difference calculation unit 11 and a pattern matching unit 13.
　差分演算部１１は，対象者の連続測定体温と，対象者の平常時の連続測定体温の例との差分である差分連続体温を求めるための要素である。なお，差分演算部１１は，一般人の特定疾患に罹患した際の連続測定体温と，その一般人の平常時の連続測定体温の例との差分を求める際に用いられてもよい。例えば，記憶部に対象者の連続測定体温と，対象者の平常時の連続測定体温の例が記憶されている。このため差分演算部１１は，記憶部に記憶された対象者の連続測定体温と，対象者の平常時の連続測定体温の例を読み出し，差分演算を行うことで，これらの差分値（差分連続体温）を求めればよい。そして，求めた差分値を適宜記憶部に記憶させればよい。 The difference calculation unit 11 is an element for obtaining the difference continuous body temperature, which is the difference between the continuously measured body temperature of the subject and the example of the continuously measured body temperature of the subject in normal times. The difference calculation unit 11 may be used to obtain the difference between the continuously measured body temperature of a general person when suffering from a specific disease and the example of the continuously measured body temperature of the general person in normal times. For example, an example of the subject's continuously measured body temperature and the subject's normal continuously measured body temperature is stored in the storage unit. Therefore, the difference calculation unit 11 reads an example of the continuously measured body temperature of the target person stored in the storage unit and the continuously measured body temperature of the target person in normal times, and performs the difference calculation to perform these difference values (difference continuous). Body temperature) can be obtained. Then, the obtained difference value may be appropriately stored in the storage unit.
　パターンマッチング部１３は，差分演算部１１が求めた対象者の差分連続体温と，特定疾患罹患時差分パターンとをパターンマッチングを行ってパターンマッチング結果を得るための要素である。例えば，対象者の差分連続体温と，特定疾患罹患時差分パターンは記憶部に記憶される。例えば特定疾患罹患時差分パターンは，年齢，性別，既往症，体重，飲酒量及び飲酒頻度，日常の服薬情報（例：薬の種類、量、摂取時刻，症状（例：頭痛、鼻水、下痢など），測定時の状況（例：安静時，睡眠中，食事前，測定時刻，運動中，活動中）といった測定対象に関する情報と合わせて記憶されてもよい。また特定疾患罹患時差分パターンは，ある測定対象に関する情報に関連して複数のものが記憶部に記憶されていてもよい。パターンマッチング部１３は，例えば，機械学習によりパターンマッチングを行ってもよい。その際，上記した対象者の差分連続体温と，特定疾患罹患時差分パターンのみならず，上記の測定対象に関する情報をも含めてパターンマッチングを行ってもよい。 The pattern matching unit 13 is an element for performing pattern matching between the difference continuous body temperature of the subject obtained by the difference calculation unit 11 and the difference pattern at the time of suffering from a specific disease, and obtaining a pattern matching result. For example, the difference continuous body temperature of the subject and the difference pattern at the time of morbidity of a specific disease are stored in the memory. For example, the difference pattern at the time of morbidity of a specific disease is age, gender, pre-existing illness, weight, amount of drinking and frequency of drinking, daily medication information (example: type, amount, intake time, symptoms (example: headache, nasal discharge, diarrhea, etc.)). , It may be stored together with information about the measurement target such as the situation at the time of measurement (eg, at rest, sleeping, before meals, measurement time, during exercise, during activity). There is also a difference pattern at the time of specific disease. A plurality of items may be stored in the storage unit in relation to the information regarding the measurement target. The pattern matching unit 13 may perform pattern matching by, for example, machine learning. At that time, the difference between the above-mentioned subjects. Pattern matching may be performed including not only the continuous body temperature and the difference pattern at the time of suffering from a specific disease but also the above-mentioned information on the measurement target.
　そして，疾患罹患予測部９の好ましい例は，パターンマッチング部１３によるパターンマッチング結果に基づいて，対象者の特定疾患に関する罹患状況を予測するものである。例えば，パターンマッチング部１３は，差分演算部１１が求めた対象者の差分連続体温と関連して，類似度が高い特定疾患罹患時差分パターンをいくつか得る。そして，得られた特定疾患罹患時差分パターンに関連した特定疾患を用いて対象者の特定疾患に関する罹患状況を予測する。この予測の程度は，例えば，パターンが非常によく似ているか，類似度が高い特定疾患罹患時差分パターンがいくつあったかといった情報を用いて，コンピュータが分析するようにすればよい。また，この際機械学習により, 対象者の特定疾患に関する罹患状況を予測するようにしてもよい。なお，平常時体温情報記憶部５が記憶する対象者の平常時の連続測定体温を用いて， パターンマッチング部１３により対象者の特定疾患に関する状況を分析してもよい。そのような特定疾患に関する状況の例は，特定疾患に関して複数種類の医薬が存在する場合に，体温の変動パターンと有効な薬の関係をパターン認証しておき，対象者の平常時の連続測定体温を用いて，その対象者に有効な医薬に関する情報を得るというものである。例えば線維筋痛症などでは，患者に対し，複数種類の疼痛改善薬が投与される。その場合，各種医薬と有効な患者の連続体温パターンを機械学習させておけば，その患者に有効な医薬を特定することができる。このようにして不要な医薬を投与する事態やそれによる副作用及び医療費を防止できる。これは，平常時の連続体温に限らず，所定の医薬を投与した後の温度変化について，所定の医薬が患者に対し有効であるか否かを判断するためにも用いることができる。 A preferred example of the disease morbidity prediction unit 9 is to predict the morbidity status of the subject regarding a specific disease based on the pattern matching result by the pattern matching unit 13. For example, the pattern matching unit 13 obtains some difference patterns at the time of morbidity of a specific disease having a high degree of similarity in relation to the difference continuous body temperature of the subject obtained by the difference calculation unit 11. Then, the morbidity status of the subject regarding the specific disease is predicted by using the specific disease related to the obtained morbidity difference pattern of the specific disease. The degree of this prediction may be analyzed by a computer, for example, using information such as whether the patterns are very similar or how many differences patterns at the time of morbidity of a specific disease have a high degree of similarity. At this time, machine learning may be used to predict the morbidity of the subject regarding a specific disease. It should be noted that the pattern matching unit 13 may analyze the situation regarding the specific disease of the subject by using the continuously measured body temperature of the subject stored by the normal body temperature information storage unit 5 in the normal time. As an example of the situation related to such a specific disease, when there are multiple types of medicines related to the specific disease, the relationship between the fluctuation pattern of body temperature and the effective drug is pattern-authenticated, and the subject's normal continuous measurement body temperature is measured. Is used to obtain information on effective medicines for the subject. For example, in fibromyalgia, multiple types of pain-improving drugs are administered to patients. In that case, if the continuous body temperature patterns of various drugs and effective patients are machine-learned, the effective drugs for the patients can be identified. In this way, it is possible to prevent the situation of administering unnecessary medicines and the side effects and medical expenses due to the administration. This can be used not only for continuous body temperature in normal times but also for determining whether or not a predetermined drug is effective for a patient with respect to a temperature change after administration of the predetermined drug.
　次に，プログラムについて説明する。このプログラムは，コンピュータを上記のシステムとして機能させるためのものである。このコンピュータには，体温測定部などの各種センサが含まれてもよい。
　つまり，このプログラムは，
　コンピュータを，対象者の特定疾患に関する罹患状況を予測するための疾患罹患予測システム１として機能させるためのプログラムである。
　このプログラムが実装されるコンピュータは，体温測定手段３と，平常時体温情報記憶手段５と，疾患関連体温情報記憶手段７と，疾患罹患予測手段９を有する。各手段は，上記で説明した各部に相当する。 Next, the program will be described. This program is intended to make the computer function as the above system. This computer may include various sensors such as a body temperature measuring unit.
In other words, this program
This is a program for making a computer function as a disease morbidity prediction system 1 for predicting the morbidity status of a specific disease of a subject.
The computer on which this program is implemented has a body temperature measuring means 3, a normal body temperature information storing means 5, a disease-related body temperature information storing means 7, and a disease morbidity predicting means 9. Each means corresponds to each part described above.
　この明細書は，上記のプログラムを記憶した情報記憶媒体をも提供する。情報記憶媒体の例は，ＣＤ－ＲＯＭ，ＤＶＤ，ＵＳＢ，ハードディスク及びメモリースティックである。 This specification also provides an information storage medium that stores the above program. Examples of information storage media are CD-ROMs, DVDs, USBs, hard disks and memory sticks.
　次に，上記のシステム を用いた対象者の特定疾患に関する罹患状況を予測する方法について説明する。
　体温測定部３が対象者の体温を連続的に測定し，連続測定体温を得る（連続測定体温測定工程）。
　平常時体温情報記憶部５は，対象者の平常時の連続測定体温の例を記憶している。疾患関連体温情報記憶部７は，特定疾患に罹患した時の連続測定体温に関する情報を記憶している。
　疾患罹患予測部９は，対象者の連続測定体温と，対象者の平常時の連続測定体温の例と，特定疾患に罹患した時の連続測定体温に関する情報とを用いて， 対象者の特定疾患に関する罹患状況を予測する（予測工程）。　 Next, a method of predicting the prevalence of a specific disease in a subject using the above system will be described.
The body temperature measuring unit 3 continuously measures the body temperature of the subject and obtains the continuously measured body temperature (continuous measurement body temperature measuring step).
The normal body temperature information storage unit 5 stores an example of the continuously measured body temperature of the subject in normal times. The disease-related body temperature information storage unit 7 stores information on continuously measured body temperature when suffering from a specific disease.
The disease morbidity prediction unit 9 uses the continuously measured body temperature of the subject, an example of the continuously measured body temperature of the subject in normal times, and the information on the continuously measured body temperature when suffering from the specific disease, and uses the information on the continuously measured body temperature of the subject. Predict the morbidity of the disease (prediction process).
　予測工程の例は，以下のとおりである。
　差分演算部１１が，対象者の連続測定体温と，対象者の平常時の連続測定体温の例との差分である差分連続体温を求める（差分演算工程）。
　図５は，差分連続体温を説明するための図である。図５には，対象者の連続測定体温と，対象者の平常時の連続測定体温の例が示されている。 An example of the prediction process is as follows.
The difference calculation unit 11 obtains the difference continuous body temperature, which is the difference between the continuously measured body temperature of the subject and the example of the continuously measured body temperature of the subject in normal times (difference calculation step).
FIG. 5 is a diagram for explaining the differential continuous body temperature. FIG. 5 shows an example of the continuously measured body temperature of the subject and the continuously measured body temperature of the subject in normal times.
　パターンマッチング部１３が，差分演算部１１が求めた対象者の差分連続体温と，特定疾患罹患時差分パターンとをパターンマッチングを行ってパターンマッチング結果を得る（パターンマッチング工程）。
　図６は，パターンマッチングを説明するための概念図である。図６（ａ）は，特定疾患罹患時差分パターンの例を示す。図６（ｂ）は，差分連続体温とマッチングした特定疾患罹患時差分パターンが抽出されたことを示す。図６（ａ）に示されるように，記憶部には，多数の特定疾患罹患時差分パターンが記憶されている。このためパターンマッチング部１３は，記憶されている多数の特定疾患罹患時差分パターンと対象者の差分連続体温とのパターンマッチング演算を行えばよい。このパターンマッチング演算は，機械学習により行うものであってもよい。図６（ｂ）に示されるように，このようにしてコンピュータにより，対象者の特定疾患に関する罹患状況を予測できることとなる。上記した通り，図６の例では，特定疾患罹患時と平常時の連続測定温度の差分値によるパターンマッチングを行った。この明細書に記載される発明は，差分値によるパターンマッチングに限定されず，連続測定温度を用いたパターンマッチングであれば，どのようなパターンマッチングを採用してもよい。 The pattern matching unit 13 performs pattern matching between the difference continuous body temperature of the subject obtained by the difference calculation unit 11 and the difference pattern at the time of suffering from a specific disease, and obtains a pattern matching result (pattern matching step).
FIG. 6 is a conceptual diagram for explaining pattern matching. FIG. 6A shows an example of a difference pattern at the time of morbidity of a specific disease. FIG. 6 (b) shows that the difference pattern at the time of morbidity of a specific disease matched with the difference continuous body temperature was extracted. As shown in FIG. 6A, a large number of specific disease morbidity difference patterns are stored in the storage unit. Therefore, the pattern matching unit 13 may perform a pattern matching calculation between a large number of stored difference patterns at the time of morbidity of a specific disease and the difference continuous body temperature of the subject. This pattern matching operation may be performed by machine learning. As shown in FIG. 6 (b), the morbidity status of the subject regarding the specific disease can be predicted by the computer in this way. As described above, in the example of FIG. 6, pattern matching was performed by the difference value between the continuous measurement temperature at the time of morbidity of a specific disease and the normal time. The invention described in this specification is not limited to pattern matching based on difference values, and any pattern matching may be adopted as long as it is pattern matching using continuous measurement temperature.
　この発明は医療機器産業において利用されうる。 This invention can be used in the medical device industry.
　１　疾患罹患予測システム
　３　体温測定部
　５　平常時体温情報記憶部
　７　疾患関連体温情報記憶部
　９　疾患罹患予測部
　１１　差分演算部
　１３　パターンマッチング部 1 Disease morbidity prediction system 3 Body temperature measurement unit 5 Normal body temperature information storage unit 7 Disease-related body temperature information storage unit 9 Disease morbidity prediction unit 11 Difference calculation unit 13 Pattern matching unit

Claims (5)

  1. 　対象者の特定疾患に関する罹患状況を予測するための疾患罹患予測システム（１）であって，
    　前記システム（１）は，
    　　前記対象者の体温を連続的に測定し，連続測定体温を得るための体温測定部（３）と，
    　　前記対象者の平常時の連続測定体温の例を記憶する平常時体温情報記憶部（５）と，
    　　特定疾患に罹患した時の連続測定体温に関する情報を記憶する疾患関連体温情報記憶部（７）と，
    　　前記対象者の特定疾患に関する罹患状況を予測する疾患罹患予測部（９）を有し，
    　前記疾患罹患予測部（９）は，
    　　前記対象者の連続測定体温と，前記対象者の平常時の連続測定体温の例と，前記特定疾患に罹患した時の連続測定体温に関する情報とを用いて， 前記対象者の特定疾患に関する罹患状況を予測する，
    システム。     It is a disease morbidity prediction system (1) for predicting the morbidity status of a specific disease of a subject.
    The system (1) is
    The body temperature measuring unit (3) for continuously measuring the body temperature of the subject and obtaining the continuously measured body temperature, and
    The normal body temperature information storage unit (5) that stores an example of the subject's normal continuous measurement body temperature, and
    A disease-related body temperature information storage unit (7) that stores information on continuous measurement body temperature when suffering from a specific disease, and
    It has a disease morbidity prediction unit (9) that predicts the morbidity of the subject regarding a specific disease.
    The disease morbidity prediction unit (9)
    Using the subject's continuously measured body temperature, an example of the subject's normal continuous measured body temperature, and information on the continuously measured body temperature when suffering from the specific disease, the morbidity status of the subject regarding the specific disease. Predict,
    system.
  2. 　請求項１に記載のシステムであって，前記体温測定部（３）は，前記対象者の臍部に装着する温度測定装置である，システム。 The system according to claim 1, wherein the body temperature measuring unit (3) is a temperature measuring device attached to the umbilical region of the subject.
  3. 　請求項１に記載のシステムであって，
    　　前記疾患罹患予測部（９）は，
    　　前記対象者の連続測定体温と，前記対象者の平常時の連続測定体温の例との差分である差分連続体温を求める差分演算部（１１）と，
    　　パターンマッチング部（１３）とを有し，
    　　前記特定疾患に罹患した時の連続測定体温に関する情報は，特定疾患に罹患した時の連続測定体温と平常時の連続測定体温との差分のパターンである特定疾患罹患時差分パターンであり，
    　前記パターンマッチング部（１３）は，
    　　前記差分演算部（１１）が求めた前記対象者の差分連続体温と，前記特定疾患罹患時差分パターンとをパターンマッチングを行ってパターンマッチング結果を得るものであり，
    　　前記疾患罹患予測部（９）は，
    　　前記パターンマッチング部（１３）によるパターンマッチング結果に基づいて，前記対象者の特定疾患に関する罹患状況を予測する，システム。     The system according to claim 1.
    The disease morbidity prediction unit (9)
    A difference calculation unit (11) for obtaining a difference continuous body temperature, which is a difference between the continuously measured body temperature of the subject and the example of the continuously measured body temperature of the subject in normal times.
    It has a pattern matching unit (13) and
    The information on the continuously measured body temperature when suffering from the specific disease is a difference pattern when suffering from a specific disease, which is a pattern of the difference between the continuously measured body temperature when suffering from a specific disease and the continuously measured body temperature in normal times.
    The pattern matching unit (13) is
    The pattern matching result is obtained by performing pattern matching between the difference continuous body temperature of the subject obtained by the difference calculation unit (11) and the difference pattern at the time of suffering from the specific disease.
    The disease morbidity prediction unit (9)
    A system for predicting the morbidity of a specific disease of the subject based on the pattern matching result by the pattern matching unit (13).
  4. 　コンピュータを，
    　対象者の特定疾患に関する罹患状況を予測するための疾患罹患予測システム（１）であって，
    　　前記対象者の体温を連続的に測定し，連続測定体温を得るための体温測定手段（３）と，
    　　前記対象者の平常時の連続測定体温の例を記憶する平常時体温情報記憶手段（５）と，
    　　特定疾患に罹患した時の連続測定体温に関する情報を記憶する疾患関連体温情報記憶手段（７）と，
    　　前記対象者の特定疾患に関する罹患状況を予測する疾患罹患予測手段（９）を有し，
    　前記疾患罹患予測手段（９）は，
    　　前記対象者の連続測定体温と，前記対象者の平常時の連続測定体温の例と，前記特定疾患に罹患した時の連続測定体温に関する情報とを用いて， 前記対象者の特定疾患に関する罹患状況を予測する，
    　システムとして機能させるプログラム。     Computer,
    It is a disease morbidity prediction system (1) for predicting the morbidity status of a specific disease of a subject.
    The body temperature measuring means (3) for continuously measuring the body temperature of the subject and obtaining the continuously measured body temperature, and
    The normal body temperature information storage means (5) for storing an example of the subject's normal continuous measurement body temperature, and
    A disease-related body temperature information storage means (7) that stores information on continuous measurement body temperature when suffering from a specific disease, and
    It has a disease morbidity predicting means (9) for predicting the morbidity of a specific disease of the subject.
    The disease morbidity prediction means (9) is
    Using the subject's continuously measured body temperature, an example of the subject's normal continuous measured body temperature, and information on the continuously measured body temperature when suffering from the specific disease, the morbidity status of the subject regarding the specific disease. Predict,
    A program that functions as a system.
  5. 　請求項４に記載のプログラムを格納した情報記録媒体。 An information recording medium containing the program according to claim 4.
PCT/JP2021/036649 2020-10-22 2021-10-04 Disease incidence prediction system WO2022085407A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2022557370A JPWO2022085407A1 (en) 2020-10-22 2021-10-04

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020-177635 2020-10-22
JP2020177635 2020-10-22

Publications (1)

Publication Number Publication Date
WO2022085407A1 true WO2022085407A1 (en) 2022-04-28

Family

ID=81289621

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/036649 WO2022085407A1 (en) 2020-10-22 2021-10-04 Disease incidence prediction system

Country Status (2)

Country Link
JP (1) JPWO2022085407A1 (en)
WO (1) WO2022085407A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0880285A (en) * 1994-09-14 1996-03-26 Matsushita Electric Ind Co Ltd Monitor
JP2011177500A (en) * 2010-02-05 2011-09-15 Cascom:Kk Body temperature management system
JP2012071054A (en) * 2010-09-29 2012-04-12 Terumo Corp Disease prediction device, disease prediction system, and disease prediction method
WO2019073963A1 (en) * 2017-10-10 2019-04-18 株式会社Ｈｅｒｂｉｏ Navel temperature measurement device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0880285A (en) * 1994-09-14 1996-03-26 Matsushita Electric Ind Co Ltd Monitor
JP2011177500A (en) * 2010-02-05 2011-09-15 Cascom:Kk Body temperature management system
JP2012071054A (en) * 2010-09-29 2012-04-12 Terumo Corp Disease prediction device, disease prediction system, and disease prediction method
WO2019073963A1 (en) * 2017-10-10 2019-04-18 株式会社Ｈｅｒｂｉｏ Navel temperature measurement device

Also Published As

Publication number Publication date
JPWO2022085407A1 (en) 2022-04-28

Similar Documents

Publication Publication Date Title
Zeng et al. Parkinson's disease classification using gait analysis via deterministic learning
Whitehouse et al. Quality of life and dementia
Côté et al. Compliance with peak expiratory flow monitoring in home management of asthma
Lum et al. Improving accelerometry-based measurement of functional use of the upper extremity after stroke: machine learning versus counts threshold method
Iannaccone et al. Outcome measures for pediatric spinal muscular atrophy
Zhang et al. Pdmove: Towards passive medication adherence monitoring of parkinson's disease using smartphone-based gait assessment
JP6873910B2 (en) System for providing automatic titration for oral appliance therapy
Azimi et al. Personalized maternal sleep quality assessment: An objective iot-based longitudinal study
US20200205709A1 (en) Mental state indicator
JP2022079774A (en) System and method for biometric identification using sleep physiology
König et al. A review of current information and communication technologies: can they be used to assess apathy?
Weenk et al. A smart all-in-one device to measure vital signs in admitted patients
González-Martin et al. Evaluation of the impact of a pharmaceutical care program in children with asthma
US11442056B2 (en) Systems and methods for detecting a brain condition
WO2019075522A1 (en) Risk indicator
Delaney et al. The feasibility and reliability of actigraphy to monitor sleep in intensive care patients: an observational study
Price et al. Assessment of pruritus in patients with psoriasis and atopic dermatitis: subjective and objective tools
Chernyshev et al. A pilot study: portable out-of-center sleep testing as an early sleep apnea screening tool in acute ischemic stroke
Hung Detection of central sleep apnea based on a single-lead ECG
Hong et al. Personalized sleep-wake patterns aligned with circadian rhythm relieve daytime sleepiness
Sahoo et al. Machine Learning-Based Heart Disease Prediction: A Study for Home Personalized Care
Xue et al. Validation of actigraphy for sleep measurement in children with cerebral palsy
JP2022511739A (en) Treatment monitoring system
WO2022085407A1 (en) Disease incidence prediction system
Huang et al. Use of oximetry as a screening tool for obstructive sleep apnea: a case study in Taiwan

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21882548

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022557370

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21882548

Country of ref document: EP

Kind code of ref document: A1