JP2019086839A - High-risk patient group extraction apparatus and high-risk patient group extraction method - Google Patents

Abstract

To provide a high-risk patient group extraction apparatus and a high-risk patient group extraction method capable of suitably extracting a patient group having a relatively high risk of developing a specific disease from among a plurality of patients.SOLUTION: A high-risk patient group extraction apparatus includes: a relative risk degree acquisition unit acquiring a relative risk degree which is a relative index indicating the magnitude of a risk of developing a specific disease, for each population stratified by at least one factor that may contribute to the risk of developing the specific disease, based on examination data obtained by examinations performed on a plurality of patients or interview data obtained by interviews with the plurality of patient; a health degree score calculation unit calculating, for each patient, a health degree score, which is an index indicating the lowness of the risk of developing the specific disease for each factor, based on the reciprocal of the relative risk degree of the population including the patient; and a high-risk patient group extraction unit extracting a high-risk patient group based on the health degree score.SELECTED DRAWING: Figure 2

Description

  The present disclosure relates to a high risk patient group extraction device and a high risk patient group extraction method for extracting a high risk patient group that is a population of patients who are at high risk of developing a specific disease.

  Studies have shown that certain diseases are at increased risk of development due to multiple factors (risk factors). For example, as factors of cardiovascular disease (hypertension, stroke, cerebral infarction, ischemic heart disease (angina, myocardial infarction, etc.)), blood pressure, obesity, diabetes, dyslipidemia, smoking and the like It is considered to include lifestyle habits such as drinking habits.

  From such a point of view, techniques for managing the health of an individual (hereinafter, patient) in consideration of a plurality of factors are in widespread use. For example, Patent Document 1 includes at least one of a test value, an interview value, a measurement result by various measurement devices such as a blood pressure monitor and a urine glucose tester, information on lifestyle, personal attributes, medical history, family history, and medical condition. Health management that supports health management by calculating the degree of health such as deviation from normal values, deviation from standard values, disease risk, etc. using health data consisting of multiple items (factors) including A support method and apparatus is disclosed.

Patent No. 4055600

  By the way, there is a demand to extract a group (patient group) of patients having a particularly high risk of developing a specific disease among a plurality of patients. Although the technology disclosed in Patent Document 1 can calculate the degree of health of each patient, it extracts a group of patients who have a relatively high risk of developing a specific disease among a plurality of patients. It is not possible.

  Under such circumstances, the present invention provides a high-risk patient group extraction apparatus and high-risk patient group capable of suitably extracting a patient group having a relatively high risk of developing a specific disease among a plurality of patients. The purpose is to provide an extraction method.

  The high-risk patient group extraction device of the present disclosure may contribute to the risk of developing a specific disease based on examination data obtained from examinations performed on a plurality of patients or interview data obtained from interviews on a plurality of patients. A relative risk acquiring unit for acquiring a relative risk, which is a relative index indicating a high risk of the specific disease, for each group stratified by at least one factor; And a health score calculation unit that calculates a health score, which is an index indicating the low risk of the specific disease for each factor, based on the reciprocal of the relative risk of the group in which the patient is included. And a high risk patient group extraction unit that extracts a high risk patient group based on the health score.

  The high-risk patient group extraction method of the present disclosure may contribute to the risk of developing a specific disease based on test data obtained from tests performed on a plurality of patients or interview data obtained from interviews on a plurality of patients. For each population stratified by at least one factor, obtain a relative risk, which is a relative indicator that indicates the high risk of developing the specific disease, and for each patient, the patient is included Based on the reciprocal of the relative risk of the group to be calculated, a health score, which is an index indicating the low risk of the specific disease for each factor, and distribution of patients having the calculated health score And a high-risk patient group that is a group having a health score less than a predetermined threshold value is extracted.

  According to the present disclosure, a group of patients having a relatively high risk of developing a specific disease can be suitably extracted from among a plurality of patients.

A figure showing an example of composition of a high risk patient group extraction device concerning an embodiment of this indication. Diagram showing the processing block of the control unit Flow chart for explaining high risk patient group extraction processing by high risk patient group extraction apparatus Figure that illustrates the relative risk of cardiovascular disease by population stratified by blood pressure when factored into blood pressure Figure showing an example of a frequency distribution chart in high-risk patient group extraction processing Figure illustrating the extraction of high risk patients Figure illustrating the extracted high risk patient group

  Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. However, a detailed description more than necessary, for example, a detailed description of already well-known matters, redundant description of substantially the same configuration, and the like may be omitted.

  The following description and the drawings referred to are provided to enable those skilled in the art to understand the present disclosure, and are not intended to limit the scope of the claims of the present disclosure.

<Description of configuration>
FIG. 1 is a diagram illustrating an example of the configuration of the high-risk patient group extraction device 1 according to the embodiment of the present disclosure. As shown in FIG. 1, the high-risk patient group extraction device 1 is a computer having an operation unit 11, a control unit 12, a storage unit 13, and a display unit 14. Examples of the computer of the present disclosure include, for example, a PC (Personal Computer), a workstation, a general-purpose computer, and the like. Alternatively, the high-risk patient group extraction device 1 according to the present embodiment may be configured by a computer network system or the like in which a plurality of computers are connected by a network.

  The operation unit 11 is, for example, various operation devices such as a mouse, a keyboard, a trackball, various switches, and a touch panel. The operation unit 11 transmits, to the control unit 12, the result of the operation input performed by the user of the high-risk patient group extraction apparatus 1 (hereinafter, simply referred to as the user) on the operation unit 11.

  The control unit 12 includes a working memory such as a central processing unit (CPU) 121, a read only memory (ROM) 122 storing a control program, and a random access memory (RAM) 123. The CPU 121 reads a program from the ROM 122 and expands it in the RAM 123 based on the operation input performed to the operation unit 11, and cooperates with the expanded program to execute a high risk patient group extraction process described later The result of the process is displayed on the display unit 14.

  FIG. 2 is a diagram illustrating processing blocks included in the control unit 12. As shown in FIG. 2, the control unit 12 includes a relative risk degree acquisition unit 201, a health degree score calculation unit 202, an overall score calculation unit 203, a frequency distribution chart generation unit 204, and a high risk patient group extraction unit 205. And a deviation value calculation unit 206. Details of the operation of each block will be described later.

  The storage unit 13 is a storage device such as a flash memory or a hard disk drive (HDD), for example, and stores data necessary for each process executed by the control unit 12. The storage unit 13 appropriately outputs, stores, erases, etc. necessary data based on the control of the control unit 12.

  The display unit 14 is a display device such as a liquid crystal display, a cathode ray tube (CRT), or an organic electroluminescence (EL) display. The display unit 14 performs predetermined display based on the control of the control unit 12.

<Operation example>
FIG. 3 is a flowchart for explaining high-risk patient group extraction processing by the high-risk patient group extraction apparatus 1.

{Step S101}
In step S101, the relative risk degree acquisition unit 201 of the control unit 12 is the result of past epidemiological research on a specific disease, that is, the test data or inquiries to a plurality of patients by a test performed on a plurality of patients in the past. Based on the interview data from the above, a value (hereinafter referred to as relative risk) indicating the relationship between the factor for the specific disease and the onset risk is obtained.

  In the present embodiment, the specific disease is a cardiovascular disease. Cardiovascular diseases include, for example, hypertension, stroke, cerebral infarction, ischemic heart disease (angina, myocardial infarction) and the like.

  NIPPON DATA (National Integrated Project for Prospective Observation of Non-communicable Diseases and the Trends in the Aged) is known as an epidemiological study for cardiovascular diseases. In the present embodiment, the NIPPON DATA result data is an example of examination data obtained by examinations performed on a plurality of patients or inquiry data obtained by interviewing a plurality of patients in the present invention.

  NIPPON DATA 80 is a national survey conducted by the Ministry of Health and Welfare (at that time) in 1980 in response to the Cardiovascular Disease Basic Survey (Health survey for residents over 30 years old who live in 300 locations randomly extracted from all over Japan). This is a long-term follow-up study conducted to examine the relationship between cardiovascular disease factors and mortality risk. Similarly, NIPPON DATA 90 is a long-term follow-up study on cardiovascular disease basic research conducted by the Ministry of Health and Welfare (at that time) in 1990. NIPPON DATA 80 and NIPPON DATA 90 (hereinafter, NIPPON DATA 80/90) have features such as high tracking rate (90% or more) and long tracking period.

  In NIPPON DATA 80, height, weight, blood pressure, electrocardiogram, total cholesterol, serum albumin, occasional blood sugar, creatinine, γ-GTP, urine protein, urine sugar, disease history, lifestyle (drinking, smoking, physical activity, diet Surveys are being conducted on items such as ADL (daily life activities) and QOL (Quality of Life). In NIPPON DATA 90, in addition to these, items such as HDL-C, triglyceride, hemoglobin A1c, and white blood cell count are being investigated.

  Therefore, in the present embodiment, the relative risk degree acquiring unit 201 calculates the relative risk degree by calculating the relative risk degree for each factor using the data of NIPPON DATA 80/90 stored in advance in the storage unit 13. get.

In the present embodiment, the following seven items are used as factors of cardiovascular disease.
Blood pressure Degree of diabetes (HbA1c value)
・ The degree of dyslipidemia (LDL cholesterol level)
・ The presence or absence of smoking habits ・ The presence or absence of heavy drinking habits ・ The presence or absence of exercise habits ・ The presence or absence of obesity

  In addition, although description is abbreviate | omitted in this Embodiment in order to avoid becoming complicated, you may consider the age and sex for every patient at the time of stratification.

FIG. 4 is a diagram illustrating the relative risk of cardiovascular disease for each group grouped (stratified) by blood pressure when blood pressure is a factor. In FIG. 4, the blood pressure is stratified into seven groups I-VII. The criteria for stratification are as follows.
Group I: Optimal blood pressure (less than 120/80 mmHg)
Group II: Normal blood pressure (less than 130/85 mmHg)
Group III: Normal high blood pressure (less than 140/90 mmHg)
Group IV: Mild hypertension (less than 160/100 mmHg)
Group V: Moderate hypertension (less than 180/110 mmHg)
Group VI: Severe hypertension (over 180/110 mmHg)
Group VII: Treating hypertension (group currently using medication to lower blood pressure)

  Note that the description of 120/80 mmHg indicates that the systolic blood pressure is less than 120 mmHg and the diastolic blood pressure is less than 80 mmHg.

  The relative risk shown in FIG. 4 is an index representing the incidence frequency of cardiovascular diseases of patients included in other groups, where the incidence frequency of cardiovascular diseases of patients included in group I is 1. In the present embodiment, as described above, at the time when step S101 is executed, the relative risk degree acquiring unit 201 appropriately performs stratification based on the criteria for each factor, and from the storage unit 13 to NIPPON DATA It is calculated by reading 80/90 and counting the number of patients included in each group. Here, the criteria for stratification are preset so that high-risk patient groups can be suitably extracted.

  Below, the example of the criteria of stratification is demonstrated about the factor (other than a blood pressure) of 7 items in this embodiment illustrated above.

Examples of stratification criteria for the degree of diabetes are, for example: HbA1c indicates hemoglobin A1c (%) and BS indicates fasting blood glucose (mg / dL). In the following stratification, the value of HbA1c is used if it is present, otherwise the value of BS is used.
Group I: HbA1c <5.9 (or BS <126)
Group II: 5.9 ≦ HbA1c <6.5
Group III: 6.5 ≦ HbA1c <7.0 (or 126 ≦ BS)
Group IV: 7.0 ≦ HbA1c <7.5
Group V: 7.5 ≦ HbA1c
Group VI: During diabetes treatment (group currently using insulin injection or drug that lowers blood sugar)

Examples of stratification criteria for the degree of dyslipidemia are, for example: Note that LDL-C indicates LDL cholesterol level (mg / dL), HDL-C indicates HDL cholesterol level (mg / dL), and TG indicates neutral fat (triglyceride) (mg / dL). In the following stratification, the value of LDL-C is used if it is present, the value of HDL-C is used if it is not, and the value of TG is used if it is not both.
Group I: LDL-C <120 (or 40 <HDL-C, or TG <150)
Group II: 120 ≦ LDL-C <160 (or HDL-C ≦ 40, or 150 ≦ TG)
Group III: 160 ≦ LDL-C <180
Group IV: 180 ≦ LDL-C
Group V: Under treatment for dyslipidemia (group currently using drugs to reduce LDL-C)

An example of stratification criteria for the presence or absence of smoking habits is, for example:
Group I: Does not smoke Group II: Sucks

Stratification about the presence or absence of heavy drinking habit is performed, for example, by the amount of drinking per time.
Group I: hardly drink or less than 1 combination Group II: 1 or more combination less than 2 combination Group III: 2 or more combination less than 3 combination Group IV: 3 or more combination

Stratification about the presence or absence of exercise habits is, for example, "whether or not light sweat for at least 30 minutes or more and exercise was performed for 2 days or more a week or more for 1 week or more", and "walking or equivalent in daily life It is performed by "whether or not physical activity was carried out more than one hour a day".
Group I: both implemented Group II: implemented only one or the other Group III: neither implemented

Stratification for the presence or absence of obesity is, for example, "whether or not BMI is less than 25" and "whether or not abdominal girth is less than 85 cm (for men) or less than 90 cm (for women)" Done by BMI is a body mass index (body mass index).
Group I: both meet Group II: only one is met Group III: neither is met

  By providing a group under treatment in this way, more realistic stratification can be performed. In addition, the reference | standard of stratification according to the factor which was illustrated above is an example, and this indication is not limited to this.

{Step S102}
It returns to the explanation of FIG. In step S102, the health level score calculation unit 202 calculates a health level score indicating the health level of each group based on the relative risk level calculated in step S101 for each factor of the specific disease. Here, the health level score is an index indicating the degree of health of the patient, and is a value indicating the difficulty in developing a specific disease (in the present embodiment, cardiovascular disease). In this embodiment, using the relative risk R calculated in step S101, it is defined as 100 / R health score S _h. That is, in this embodiment, the health score S _h, a value obtained by multiplying 100 to the inverse of the relative risks.

Hereinafter, the health degree score will be specifically described with reference to the relative risk degree related to blood pressure exemplified in FIG. 4 as an example. As shown in FIG. 4, when the group I is 1, the relative risk R _BP of cardiovascular disease related to blood pressure is 1.25 for group II, 2 for group III, 2.5 for group IV, and group V 3.33, the group VI is 5.0, and the group VII is 2. The relative risk R _bp shown in FIG. 4 is a value for explanation in the present embodiment, and is not based on NIPPON DATA 80/90.

Since the health scores S _h as described above is 100 / R, health scores S _{H_BP} per group on blood pressure as follows.
Group I: 100
Group II: 80
Group III: 50
・ Group IV: 40
・ Group V: 30
・ Group VI: 20
・ Group VII: 50

Thus, by taking the reciprocal of the relative risk, the health score S _h is the lowest relative risk, in other words, the group I who has a relatively low risk of developing cardiovascular disease and is relatively healthy. Defined to be And, the health score S _h is defined so that the relative risk is relatively high, in other words, the lower the health is, the lower the value.

  The health score calculation unit 202 calculates the health score not only for blood pressure but also for other factors. In the present embodiment, the description of a specific example of the health degree score regarding other factors is omitted.

{Step S103}
In step S103, the total score calculation unit 203 calculates a total score that comprehensively takes into consideration the health score relating to all the factors for each patient included in NIPPON DATA 80/90. The overall score _{Sh_TOTAL} is calculated, for example, using the following equation (1). The following equation (1) is used to calculate an overall score using a multiple regression model based on the health score for each factor.

In the formula _(1), the _{S H_BP} health scores regarding blood _{pressure, S H_DM} the health scores regarding the degree of _diabetes, the _{S H_HL} health scores regarding the degree of _{dyslipidemia, S H_SM} the statuses smoking habits _{Sh_AL} indicates a health score related to the presence or absence of heavy drinking habits, _{Sh_EX} indicates a health score related to the presence or absence of exercise habits, and _{Sh_OB} indicates a health score related to the presence or absence of obesity.

In equation (1), the overall score _{Sh_TOTAL} is calculated by taking the logarithm of the health score for each factor and adding it. Therefore, the overall score _{Sh_TOTAL} is a value that comprehensively considers the health score of each factor.

Moreover, in Formula (1), the health score _{s_HL} related to the degree of _dyslipidemia alone has a lower contribution to the overall score _{Sh_TOTAL} compared to other factors. The reason is that although dyslipidemia contributes to the risk of developing acute myocardial infarction among cardiovascular diseases, it contributes to the risk of developing other cardiovascular diseases (stroke, cerebral infarction, hypertension, etc.) It is because the small thing is clarified by research.

  The reason for taking the square root of the whole in Equation (1) is to narrow the range of possible values of the health score and improve the symmetry of the distribution.

{Step S104}
In step S104, the frequency distribution chart generating unit 204 generates a frequency distribution chart (histogram) indicating the relationship between the total score _{Sh_TOTAL} calculated in step S103 and the number of patients. The created frequency distribution chart is displayed on the display unit 14.

FIG. 5 is a diagram showing an example of a frequency distribution chart in the high risk patient group extraction process. In the present disclosure, as described in step S103 above, the health degree score is calculated by taking the reciprocal of the relative risk degree for each factor, and the overall score _{Sh_TOTAL} based on the formula (1) using this distribution, as shown in FIG. 5 shows a bimodal, i.e., has a peak P _a and P _b are found empirically. Here, peak P _a includes patients with relatively high overall score, ie relatively healthy and relatively low risk of developing a specific disease, and peak P _b relatively low or overall score It includes patients who are not healthy and who are at relatively high risk of developing cardiovascular disease.

{Step S105}
In step S105, the high risk patient group extraction unit 205 determines, with respect to the operation unit 11, whether or not a high risk patient group extraction operation has been performed on the frequency distribution map created in step S104. In the high-risk patient group extraction operation, the user who refers to the frequency distribution chart displayed on the display unit 14 selects a group (high-risk patient group) including a peak P _b including a patient group having a low overall score. This means an operation on the operation unit 11 for extraction. Details of the high risk patient group will be described later.

  If the high-risk patient group extraction unit 205 determines in step S105 that the high-risk patient group extraction operation has been performed, the process proceeds to step S106. If not, the process of step S105 is repeated.

{Step S106}
In step S106, the high risk patient group extraction unit 205 extracts a high risk patient group based on the high risk patient group extraction operation.

FIG. 6 illustrates the extraction of high risk patient groups. A region surrounded by a dotted line in FIG. 6 is a high risk patient group to be extracted. FIG. 7 is a diagram illustrating the extracted high-risk patient group. As mentioned above, a high risk patient group means a group of patients with a relatively low overall score. In other words, the extraction of the high-risk patient group in step S106 excludes the patient group with _a high overall score (patient group including Peak Pa), that is, the patient group that does not need to consider the risk of developing cardiovascular disease at present. Equivalent to

  As described in step S103 above, in the present disclosure, the health degree score is calculated by taking the reciprocal of the relative risk degree for each factor. When high risk patient groups are extracted from the frequency distribution map generated using such a method, as shown in FIG. 7, it is empirically known that the high risk patient groups exhibit a distribution close to normal distribution . This is considered to be because the width of the distribution can be suppressed by making the health degree score the inverse of the relative risk degree.

In high-risk patients extraction operation, the user while looking at the histogram displayed on the display unit 14, between the peak P _a and the peak P _b, most frequency (number of patients) low point (hereinafter, the boundary score ) Is selected via the operation unit 11. Thus, when the high risk patient group extraction operation is input, the high risk patient group extraction unit 205 extracts a group including patients with a boundary score or less as a high risk patient group. By such processing, it is possible to preferably extract a population including a group of patients who are at high risk for cardiovascular disease.

<Example of application>
In the following, as an application example of the high risk patient group extraction process described above, for example, the following may be mentioned.

  A health check is performed on a certain patient P, and it is assumed that test values of each factor of the patient P are obtained. In this case, the overall score of the patient P can be calculated by performing the same processing as the above steps S102 and S103 using each test value. If the total score of the patient P calculated in this manner is less than the boundary score, it can be determined that the patient P is included in the high risk patient group.

Here, the deviation value T _i of the patients in the high risk patient group can be calculated by regarding the high risk patient group extracted by the high risk patient group extraction processing shown in FIG. 7 as the normal distribution. Specifically, the deviation value calculation unit 206 determines, for example, whether or not the patient P is included in the high risk patient group when information (examination value etc.) regarding the patient P is input through the operation unit 11, for example. If it is determined that it is included, the deviation value of the patient P is calculated.

但し、μは高リスク患者群の総合スコアの平均値、ｓは標準偏差である。平均値μおよび標準偏差ｓは、上記高リスク患者群抽出処理に用いたすべての患者の総合スコアの平均値および標準偏差である。 The deviation value calculation unit 206 calculates the deviation value T _i of the patient i using, for example, the following formula (2).

Where μ is the average score of the high-risk patient group and s is the standard deviation. The mean value μ and the standard deviation s are the mean value and the standard deviation of the total score of all the patients used in the high-risk patient group extraction process.

  The deviation value calculated in this manner allows the patient P to be presented in an easy-to-understand manner to what extent the health level of the patient P is in comparison with other patients. Specifically, for example, when the deviation value of the patient P is less than 50, the patient P has a higher risk of having the patient P among the high risk patient group which is a group having a relatively high risk of developing cardiovascular disease. It can be easily presented that it is higher than average. In addition, by referring to the test value (health score) for each factor of patient P, it is immediately known which factor contributes to the low overall score. It is easy to make a suggestion about what is good.

<Operation and effect>
As described above, the high-risk patient group extraction device 1 according to the embodiment of the present disclosure is based on examination data obtained by examinations performed on a plurality of patients or inquiry data obtained by interviewing a plurality of patients. For each population stratified by at least one factor that may contribute to the risk of developing a specific disease, obtain a relative risk, which is a relative indicator of the high risk of developing a specific disease. Based on the reciprocal of the relative risk of the group in which the patient is included, the health score, which is an index indicating the low risk of the specific disease for each factor, is calculated for each patient based on the relative risk acquiring unit 201 And a high risk patient group extraction unit 205 for extracting a high risk patient group based on the health score.

  With such a configuration, a group of patients who have a relatively high risk of developing a specific disease, using test data from tests performed on multiple patients in the past or interview data from multiple patient interviews High-risk patient groups that are

  Further, the high-risk patient group extraction device 1 according to the embodiment of the present disclosure further includes a frequency distribution chart generation unit 204 that generates a frequency distribution chart indicating the distribution of patients having the calculated health score, The patient group extraction unit 205 extracts a group having a health score less than a predetermined threshold value as a high risk patient group in the frequency distribution chart. Furthermore, the high-risk patient group extraction device 1 according to the embodiment of the present disclosure calculates an overall score, which is a score that comprehensively takes account of a plurality of factors, using the health score of a plurality of factors. The frequency distribution diagram generation unit 204 further includes a unit 203, and generates a frequency distribution diagram based on the total score.

  With such a configuration, it is possible to extract a high risk patient group by comprehensively considering contributions of multiple factors to the onset risk of a specific disease.

<Modification>
In the above-described embodiment, the specific disease to be subjected to the high-risk patient group extraction process is a cardiovascular disease, but the present disclosure is not limited thereto. For example, it may be other diseases such as digestive diseases and respiratory diseases.

  Moreover, in the embodiment described above, NIPPON DATA 80/90 is used as an examination performed on a plurality of patients, but the present disclosure is not limited to this. The high-risk patient group extraction device 1 of the present disclosure may perform high-risk patient group extraction processing using data obtained as a result of another follow-up study or the like indicating the association between a plurality of factors and a specific disease.

  Further, in the embodiment described above, blood pressure, the degree of diabetes (HbA1c), the degree of dyslipidemia (LDL cholesterol level), the presence or absence of smoking habit, the presence or absence of heavy drinking habit, exercise habit as factors of cardiovascular disease Seven items were used: presence or absence of obesity, and presence or absence of obesity. However, the present disclosure is not limited to this, and all of the above seven items may not be used, or other factors other than the above seven items may be used.

  In the above-described embodiment, the relative risk acquiring unit 201 acquires the relative risk by calculating the relative risk by appropriately performing stratification at the time of step S101 in FIG. Is not limited to this. For example, appropriate stratification (grouping) and counting of the number of patients included in each group are performed in advance (before the start of high-risk patient group extraction processing) for each factor, and the total data is stored in the storage unit 13 If the relative degree of risk is stored in step S101 in the figure, the relative degree of risk obtaining unit 201 reads out the relative degree of risk of the necessary factor from the storage unit 13 instead to calculate the relative degree of risk. It may be acquired.

  In the embodiment described above, the criteria for stratification to be performed when calculating the relative risk is set in advance so that high risk patient groups can be suitably extracted, but the present disclosure is limited thereto I will not. The criteria for stratification may be appropriately adjusted so that the frequency distribution chart generated by the frequency distribution chart generation unit 204 has a suitable distribution.

  In the embodiment described above, although the result data of NIPPON DATA 80/90 is stored in advance in storage unit 13, the present invention is not limited to this. The result data of NIPPON DATA 80/90 may be appropriately input by the user of the high-risk patient group extraction apparatus 1 through, for example, the operation unit 11.

  In the embodiment described above, based on the result data of NIPPON DATA 80/90, stratification is performed based on the preset criteria for stratification, and the relative risk for each group is obtained. The reference value for stratification may not be set in advance. For example, the reference value of stratification may be appropriately adjusted during the high-risk patient group extraction process so that the health score is a manageable value when the health score is calculated for each group.

  In the embodiment described above, the overall score calculation unit 203 calculates the overall score in consideration of plural factors comprehensively by taking the logarithm of the health score relating to each factor and adding it in equation (1). Although the present disclosure is not limited thereto. The overall score calculation unit 203 may calculate the overall score by simply multiplying the health score relating to each factor.

In the embodiment described above, the extraction of the high risk patient group in step S106 is performed according to the operation performed by the user in step S105. However, the present invention is not limited to this. For example, after the histogram generation unit 204 creates a histogram in step S104, the high-risk patient group extracting unit 205 regardless of the operation of the operation unit 11, automatically between the peak P _a and the peak P _b The place with the lowest frequency among the intervals may be detected, and the place may be used as a boundary score to extract a group including patients less than the boundary score as a high risk patient group.

  In the embodiment described above, the high-risk patient extraction process has been described as an example implemented as software by expanding the control program stored in the ROM 122 by the CPU 121 of the control unit 12 in the RAM 123. However, the present invention is not limited to this, and the high risk patient extraction process may be realized by dedicated hardware, for example.

  The present disclosure is a group of high-risk patients who are a group of patients who are at high risk of developing a specific disease, based on test data from tests performed on multiple patients in the past or interview data from multiple patient interviews. Useful for high-risk patient group extraction to extract

1 High-Risk Patient Group Extraction Device 11 Operation Unit 12 Control Unit 121 CPU
122 ROM
123 RAM
201 Relative risk acquisition unit 202 Health degree score calculation unit 203 Overall score calculation unit 204 Frequency distribution chart generation unit 205 High risk patient group extraction unit 206 Deviation value calculation unit 13 Storage unit 14 Display unit

Claims (7)

Based on examination data from examinations conducted on multiple patients or interview data from multiple patient interviews, stratified by at least one factor that may contribute to the risk of developing a specific disease A relative risk degree acquiring unit for acquiring a relative risk degree, which is a relative index indicating a high risk of developing the specific disease, for each group;
The health score, which is an index indicating the low risk of the specific disease for each factor, based on the reciprocal of the relative risk of the population in which the patient is included, for each patient. A calculation unit,
A high-risk patient group extraction unit that extracts a high-risk patient group based on the health score;
High-risk patient group extractor with. It further has a frequency distribution chart generation unit that generates a frequency distribution chart showing the distribution of patients having the calculated health score.
The high risk patient group extraction unit extracts a group having a health score less than a predetermined threshold value as the high risk patient group in the frequency distribution chart.
The high risk patient group extraction device according to claim 1. The high risk patient group extraction unit extracts, as the high risk patient group, a patient group less than the health score with the lowest frequency between the peaks, when the frequency distribution map has two peaks.
The high risk patient group extraction device according to claim 2. The system further includes a total score calculation unit that calculates a total score that is a score obtained by comprehensively considering a plurality of factors using the health score of a plurality of factors,
The frequency distribution chart generation unit generates the frequency distribution chart based on the total score.
The high-risk patient group extraction device according to any one of claims 1 to 3. The specific disease is a cardiovascular disease,
The factors include at least one of blood pressure, degree of diabetes, degree of dyslipidemia, smoking habit, heavy drinking habit, exercise habit, and obesity.
The high-risk patient group extraction device according to any one of claims 1 to 4. The apparatus further includes a deviation value calculation unit that calculates the deviation value of the specific patient, regarding the specific patient included in the high risk patient group, considering the high risk patient group as a normal distribution.
The high-risk patient group extraction device according to any one of claims 1 to 5. Based on examination data from examinations conducted on multiple patients or interview data from multiple patient interviews, stratified by at least one factor that may contribute to the risk of developing a specific disease For each population, obtain a relative risk, which is a relative index indicating the high risk of developing the specific disease,
For each of the patients, based on the reciprocal of the relative risk of the population in which the patient is included, a health score, which is an index indicating the low risk of developing the specific disease for each factor, is calculated.
Generating a frequency distribution chart showing a distribution of patients having the calculated health score;
Extract a high risk patient group that is a group having a health score less than a predetermined threshold value in the frequency distribution chart.
High risk patient group extraction method.

Images