Sleep disorder onset risk prediction device, disease onset risk prediction device, sleep disorder onset risk prediction marker set, sleep disorder onset risk prediction method, disease onset risk prediction method, program, and recording medium

Abstract

The purpose of the present disclosure is to provide a sleep disorder onset risk prediction device for easily predicting an onset risk of a sleep disorder.　A sleep disorder onset risk prediction device according to the present disclosure includes an information acquisition unit, a prediction unit, and an output unit. The information acquisition unit acquires disease-related information of a prediction target person. The prediction unit predicts a sleep disorder onset risk of the prediction target person from the disease-related information, and the output unit outputs the sleep disorder onset risk.

Description

Sleep disorder onset risk prediction device, disease onset risk prediction device, sleep disorder onset risk prediction marker set, sleep disorder onset risk prediction method, disease onset risk prediction method, program, and recording medium

[0001] The present disclosure relates to a sleep disorder onset risk prediction device, a disease onset risk prediction device, a sleep disorder onset risk prediction marker set, a sleep disorder onset risk prediction method, a disease onset risk prediction method, a program, and a recording medium.

[0002] Patent Document 1 discloses a sleep disorder discrimination device that constructs an algorithm that models the amplitude envelope of a respiratory signal and sequentially searches for peaks, which are local maximum values ​​of amplitude fluctuations, and estimates the subject's respiratory state as apnea or hypopnea based on the algorithm.

[0003] Japanese Patent Application Laid-Open No. 2023-115691

[0004] As described above, the device described in Patent Document 1 can predict whether or not a subject has a sleep disorder by checking the subject's respiratory state. However, in order to predict the risk of developing a sleep disorder, a dedicated device or the like must be prepared to check the respiratory state as described in Patent Document 1. People who are not aware of their risk of developing a sleep disorder may not be motivated to prepare such a dedicated device, and therefore may not be able to grasp their risk of developing a sleep disorder. Because sleep disorders can be associated with various diseases, a method that allows anyone to easily predict the risk of developing a sleep disorder would be useful.

[0005] Therefore, the present disclosure aims to provide a sleep disorder onset risk prediction device, a disease onset risk prediction device, a sleep disorder onset risk prediction marker set, a sleep disorder onset risk prediction method, a disease onset risk prediction method, a program, and a recording medium for easily predicting the risk of developing a sleep disorder.

[0006] In order to achieve the above-mentioned objective, the sleep disorder development risk prediction device of the present disclosure includes an information acquisition unit, a prediction unit, and an output unit, wherein the information acquisition unit acquires disease-related information of the prediction subject, the prediction unit predicts the risk of developing a sleep disorder of the prediction subject from the disease-related information, and the output unit outputs the risk of developing a sleep disorder.

[0007] The disease onset risk prediction device disclosed herein includes an information acquisition unit, a prediction unit, and an output unit, wherein the information acquisition unit acquires the risk of developing a sleep disorder of the person being predicted, the risk of developing a sleep disorder being the risk of developing a sleep disorder predicted from disease-related information of the person being predicted, the prediction unit predicts the risk of developing a disease of the person being predicted from the risk of developing a sleep disorder, the disease includes at least one of diabetes and cardiovascular disease, and the output unit outputs the risk of developing the disease.

[0008] The sleep disorder risk prediction marker set disclosed herein includes, in addition to age, at least one marker of information related to obesity, information related to high blood pressure, or information related to high diabetes, and the obesity-related information includes at least one of information of waist circumference, weight, and BMI, and serves as an indicator for predicting the risk of developing a sleep disorder.

[0009] The sleep disorder development risk prediction method disclosed herein includes an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires disease-related information of the subject to be predicted, the prediction step predicts the risk of developing a sleep disorder of the subject to be predicted from the disease-related information, and the output step outputs the risk of developing a sleep disorder, and each of the steps is performed by a computer.

[0010] The disease onset risk prediction method disclosed herein includes an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires the risk of developing a sleep disorder of the person being predicted, the risk of developing a sleep disorder being the risk of developing a sleep disorder predicted from disease-related information of the person being predicted, the prediction step predicts the disease onset risk of the person being predicted from the risk of developing a sleep disorder, the disease includes at least one of diabetes and cardiovascular disease, and the output step outputs the disease onset risk, and the disease onset risk prediction method is a disease onset risk prediction method in which each of the steps is performed by a computer.

[0011] The program of the present disclosure is a program for causing a computer to execute the steps of the method of the present disclosure as procedures.

[0012] The recording medium of the present disclosure is a computer-readable recording medium on which the program of the present disclosure is recorded.

[0013] According to the present disclosure, the risk of developing a sleep disorder can be easily predicted.

[0014] FIG. 1 is a block diagram showing the configuration of an example of a sleep disorder onset risk prediction device of the present disclosure. FIG. 2 is a block diagram showing an example of the hardware configuration of a sleep disorder onset risk prediction device of the present disclosure. FIG. 3 is a flowchart showing an example of processing in the sleep disorder onset risk prediction device of the present disclosure. FIG. 4 is a block diagram showing the configuration of an example of a disease onset risk prediction device of the present disclosure. FIG. 5 is a block diagram showing an example of the hardware configuration of a disease onset risk prediction device of the present disclosure. FIG. 6 is a flowchart showing an example of processing in the disease onset risk prediction device of the present disclosure. FIG. 7 is a diagram showing a breakdown of training data and evaluation data. FIG. 8 is a diagram showing an example of selection of data to be used for training data. FIG. 9 is a scatter plot showing the relationship between age- and sex-adjusted hazard ratios and p-values. FIG. 10 is a diagram showing details of a created trained model. FIG. 11 is a graph showing the results of an ROC analysis of the created trained model. FIG. 12 is a diagram showing details of another created trained model. FIG. 13 is a graph showing the results of an ROC analysis of another created trained model. FIG. 14 is a graph showing the results of detection of a sleep disorder onset risk using the created trained model. FIG. 15 is another graph showing the results of predicting the risk of developing a sleep disorder using the created trained model. FIG. 16 is a diagram showing the relationship between BMI and the onset of a sleep disorder. FIG. 17 is a heat map showing the correlation between sleep disorders and other diseases. FIG. 18 shows an example of the results of predicting the risk of developing a sleep disorder for a predicted subject and monitoring the onset. FIG. 19 shows an example of the results of predicting the risk of developing a sleep disorder for another predicted subject and monitoring the onset.

[0015] Embodiments of the present disclosure will be described with reference to the drawings. The present disclosure is not limited to the following embodiments. In the following drawings, the same parts are denoted by the same reference numerals. Furthermore, the descriptions of the embodiments can be mutually incorporated unless otherwise specified, and the configurations of the embodiments can be combined unless otherwise specified.

[0016] In this disclosure, unless otherwise specified, the term "sleep disorder" refers to a sleep disorder classified as G47 of the International Classification of Diseases (ICD-10). More specifically, examples include disorders of sleep initiation and maintenance (insomnia) (G470) and sleep apnea (G473).

[0017] [Embodiment 1] Fig. 1 is a block diagram showing an example of the configuration of a sleep disorder onset risk prediction device 10 (hereinafter also referred to as "the device 10") according to the present disclosure. As shown in Fig. 1, the device 10 includes an information acquisition unit 11, a prediction unit 12, and an output unit 13.

[0018] The device 10 may be, for example, a single device including the above-mentioned components, or a device in which the components can be connected via a communication network. The device 10 may also be connected to an external device (described later) via the communication network. The communication network is not particularly limited and may be any known network, for example, wired or wireless. Examples of the communication network include the Internet, the World Wide Web (WWW), a telephone line, a Local Area Network (LAN), a Storage Area Network (SAN), a Delay Tolerant Networking (DTN), a Low Power Wide Area Network (LPWA), and a Local 5G (L5G). Examples of wireless communication include Wi-Fi (registered trademark), Bluetooth (registered trademark), local 5G, and LPWA. The wireless communication may be a form in which each device communicates directly (ad hoc communication), infrastructure communication, indirect communication via an access point, or the like. The device 10 may be incorporated into a system server, for example. The device 10 may also be, for example, a personal computer (PC, e.g., desktop or laptop) on which the program of the present disclosure is installed, a smartphone, a tablet terminal, or the like. Furthermore, the device 10 may be, for example, in the form of cloud computing or edge computing, in which at least one of the components is located on a server and the other components are located on a terminal.

[0019] 2 is a block diagram illustrating an example of the hardware configuration of the device 10. The device 10 includes, for example, a central processing unit (CPU, GPU, etc.) 101, a memory 102, a bus 103, a storage device 104, an input device 105, an output device 106, and a communication device 107. The components of the device 10 are connected to each other via the bus 103 and their respective interfaces (I / F).

[0020] The central processing unit 101 operates in cooperation with other components via a controller (such as a system controller or an I / O controller) and is responsible for overall control of the device 10. In the device 10, the central processing unit 101 executes, for example, the program disclosed herein and other programs, and also reads and writes various types of information. Specifically, for example, the central processing unit 101 functions as an information acquisition unit 11, a prediction unit 12, and an output unit 13. The device 10 may include, as a computing device, other computing devices such as a CPU, a GPU (Graphics Processing Unit), an APU (Accelerated Processing Unit), or the like, or may include a combination of a CPU and these.

[0021] The bus 103 can also be connected to, for example, external devices. Examples of the external devices include a user terminal, an external storage device (such as an external database), a printer, an external input device, an external display device, and an external imaging device. The device 10 can be connected to an external network (the communication line network) by, for example, a communication device 107 connected to the bus 103, and can also be connected to other devices via the external network.

[0022] The memory 102 may be, for example, a main memory (primary storage device). When the central processing unit 101 performs processing, the memory 102 reads various operating programs, such as the program of the present disclosure, stored in the storage device 104 (described later), and the central processing unit 101 receives data from the memory 102 and executes the programs. The main memory may be, for example, a RAM (random access memory). Alternatively, the memory 102 may be, for example, a ROM (read only memory).

[0023] The storage device 104 is also referred to as an auxiliary storage device, for example, in contrast to the main memory (primary storage device). As described above, the storage device 104 stores an operating program including the program of the present disclosure. The storage device 104 may be, for example, a combination of a recording medium and a drive that reads and writes from and to the recording medium. The recording medium is not particularly limited and may be, for example, an internal or external type, such as a hard disk drive (HDD), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, or memory card. The storage device 104 may be, for example, a hard disk drive (HDD) or a solid state drive (SSD) in which the recording medium and drive are integrated.

[0024] In the present device 10, the memory 102 and the storage device 104 can also store various information such as log information, information acquired from an external database (not shown) or an external device, information generated by the present device 10, and information used when the present device 10 executes processing. In this case, the memory 102 and the storage device 104 may store, for example, disease-related information, etc., as described below. Note that at least a portion of the information may be stored, for example, in an external server other than the memory 102 and the storage device 104, or may be stored in a distributed manner across multiple terminals using blockchain technology or the like.

[0025] The device 10 further includes, for example, an input device 105 and an output device 106. Examples of the input device 105 include pointing devices such as a touch panel, track pad, or mouse; a keyboard; imaging means such as a camera or scanner; card readers such as an IC card reader or a magnetic card reader; and audio input means such as a microphone. Examples of the output device 106 include display devices such as an LED display or a liquid crystal display; audio output devices such as a speaker; a printer; etc. In the present disclosure 1, the input device 105 and the output device 106 are configured separately, but the input device 105 and the output device 106 may be configured as an integrated device, such as a touch panel display.

[0026] Next, an example of the method for predicting the risk of developing a sleep disorder according to the present disclosure will be described with reference to the flowchart in Figure 3. The method for predicting the risk of developing a sleep disorder according to the present disclosure is carried out as follows, for example, using the device 10 shown in Figure 1 or Figure 2. Note that the method for predicting the risk of developing a sleep disorder according to the present disclosure is not limited to use with the device 10 shown in Figure 1 or Figure 2.

[0027] First, the information acquisition unit 11 acquires disease-related information of the prediction subject (S11, information acquisition step). Examples of the disease-related information include medical record information, health checkup information, etc. Examples of the medical record information and the health checkup information include test result information, interview information, and subject attribute information (gender, age, etc.). The disease-related information may include, for example, age, as well as at least one of information related to obesity, information related to hypertension, and information related to hyperglycemia. That is, the disease-related information may include, in addition to age, all or only some of the information related to obesity, information related to hypertension, and information related to hyperglycemia. Examples of the obesity-related information include, for example, waist circumference, weight, and BMI (Body Mass Index). Examples of the hypertension-related information include a medical history of hypertension, medication or administration information for hypertension, blood pressure test values, etc. Examples of the medication or administration information for hypertension include insulin administration information, antihypertensive medication administration information, etc. Examples of the blood pressure test value include information that the systolic blood pressure is 140 mmHg or higher, as described below, and information that the diastolic blood pressure is 90 mmHg or higher, as described below. Examples of the information related to hyperglycemia include a history of diabetes, medication or administration information for hyperglycemia, and blood glucose levels. Examples of the medication or administration information for hyperglycemia include insulin administration information and hypoglycemic drug administration information. Examples of the blood glucose level include information that the fasting blood glucose level is 126 mg / dL or higher, as described below, and information that the HbA1c (hemoglobin A1c) is 6.5% or higher. The disease-related information may further include at least one of the following: sex (male), blood test values ​​(HDL (High Density Lipoprotein), LDL (Low Density Lipoprotein), TG (triglyceride), AST (aspartate aminotransferase), diastolic blood pressure, fasting blood glucose, medical history of dyslipidemia, and medical interview information regarding lifestyle habits (weight gain since age 20, amount of alcohol consumed per day (1 to 2 go), quality of sleep, walking speed, weight change over the past year, etc.).The disease-related information is not limited to these, and may include other information, as long as it provides information necessary for predicting the risk of developing a sleep disorder. The disease-related information may be, for example, information selected based on the results of analyzing the association with a sleep disorder using a Cox proportional hazards model. The disease-related information may be, for example, a sleep disorder risk prediction marker set described later in the present disclosure. The disease-related information may be acquired by, for example, acquiring it from a connected external database, acquiring it via a communication line, or directly inputting required information into the device 10, but is not limited to these methods.

[0028] Next, the prediction unit 12 predicts the risk of developing a sleep disorder of the prediction subject based on the disease-related information (S12, prediction step). The prediction of the risk of developing a sleep disorder is based on, for example, the association between the disease-related information and the sleep disorder. The prediction of the risk of developing a sleep disorder may be, for example, a prediction of the risk of developing a sleep disorder within an arbitrary period of time.

[0029] The prediction unit 12 may be a trained model (sleep disorder risk prediction model). In this case, the sleep disorder risk prediction model predicts the risk of sleep disorder development of the prediction subject based on the disease-related information. The sleep disorder risk prediction model is, for example, a trained model that outputs the risk of sleep disorder development of the prediction subject when the disease-related information is input. The sleep disorder risk prediction model can also be a trained model that is machine-learned using, for example, multiple pieces of disease-related information as training data and causes a computer to function to predict the risk of sleep disorder development of the prediction subject. The multiple pieces of disease-related information may or may not include the disease-related information of the prediction subject. The sleep disorder risk prediction model may be, for example, a trained model using a Cox proportional hazards model. The covariates may be selected, for example, by stepwise selection and Akaike's Information Criterion (AIC). The trained model may evaluate, for example, the area under curve (AUC) for sleep disorder development within an arbitrary period using ROC analysis. The trained model may be a trained model for predicting the risk of developing a sleep disorder within a given period of time. In this case, the probability of developing a sleep disorder within a given period of time can be calculated, for example, by the following formula (1): In the formula, t is the given period of time, S ０ is the baseline survival function, X is the test value, β is the regression coefficient of the prediction model, and the X bar represents the mean of the test value.

[0030] The output unit 13 then outputs the sleep disorder development risk (S13, output step), and the process ends. The output sleep disorder development risk is not particularly limited as long as it can grasp the sleep disorder development risk of the prediction subject, and may be, for example, an absolute evaluation, a relative evaluation, a numerical value, or an evaluation result based on a threshold value. The output may be, for example, output to the output device 106 included in the present device 10, or may be output to an output device included in a device other than the present device 10.

[0031] In this way, the sleep disorder onset risk prediction device and sleep disorder onset risk prediction method disclosed herein can predict the risk of developing a sleep disorder from disease-related information alone, without requiring any special device, etc. Therefore, the risk of developing a sleep disorder can be easily predicted.

[0032] [Embodiment 2] Fig. 4 is a block diagram showing an example of the configuration of a disease onset risk prediction device 20 (hereinafter also referred to as "the device 20") according to the present disclosure. As shown in Fig. 4, the device 20 includes an information acquisition unit 21, a prediction unit 22, and an output unit 23.

[0033] The device 20 may be, for example, a single device including the above-mentioned units, or a device in which the above-mentioned units can be connected via a communication network. The device 20 may also be connected to an external device (described later) via the communication network. The communication network is not particularly limited and may be a known network, for example, wired or wireless. Examples of the communication network include the Internet, the World Wide Web (WWW), a telephone line, a Local Area Network (LAN), a Storage Area Network (SAN), a Delay Tolerant Networking (DTN), a Low Power Wide Area Network (LPWA), and a Local 5G (L5G). Examples of wireless communication include Wi-Fi (registered trademark), Bluetooth (registered trademark), local 5G, and LPWA. The wireless communication may be a form in which each device communicates directly (ad hoc communication), infrastructure communication, indirect communication via an access point, or the like. The device 20 may be incorporated into a system server, for example. The device 20 may also be, for example, a personal computer (PC, e.g., desktop or laptop) on which the program of the present disclosure is installed, a smartphone, a tablet terminal, or the like. Furthermore, the device 20 may be, for example, in the form of cloud computing or edge computing, in which at least one of the units is located on a server and the other units are located on a terminal.

[0034] 5 shows a block diagram of the hardware configuration of the device 20. The device 20 includes, for example, a central processing unit (CPU, GPU, etc.) 201, a memory 202, a bus 203, a storage device 204, an input device 205, an output device 206, and a communication device 207. The components of the device 20 are connected to each other via the bus 203 and their respective interfaces (I / F).

[0035] The central processing unit 201 operates in cooperation with other components via a controller (such as a system controller or an I / O controller) and is responsible for overall control of the device 20. In the device 20, the central processing unit 201 executes, for example, the program disclosed herein and other programs, and also reads and writes various types of information. Specifically, for example, the central processing unit 201 functions as an information acquisition unit 21, a prediction unit 22, and an output unit 23. The device 20 may include, as a computing device, other computing devices such as a CPU, a GPU (Graphics Processing Unit), an APU (Accelerated Processing Unit), or the like, or may include a combination of a CPU and these.

[0036] The bus 203 can also be connected to, for example, external devices. Examples of the external devices include a user terminal, an external storage device (external database, etc.), a printer, an external input device, an external display device, an external imaging device, etc. The device 20 can be connected to an external network (the communication line network) by, for example, a communication device 207 connected to the bus 203, and can also be connected to other devices via the external network.

[0037] The memory 202 may be, for example, a main memory (primary storage device). When the central processing unit 201 performs processing, the memory 202 reads various operating programs, such as the program of the present disclosure, stored in the storage device 204 (described later), and the central processing unit 201 receives data from the memory 202 and executes the programs. The main memory may be, for example, a RAM (random access memory). Alternatively, the memory 202 may be, for example, a ROM (read only memory).

[0038] The storage device 204 is also referred to as an auxiliary storage device, for example, in contrast to the main memory (primary storage device). As described above, the storage device 204 stores an operating program including the program of the present disclosure. The storage device 204 may be, for example, a combination of a recording medium and a drive that reads and writes from and to the recording medium. The recording medium is not particularly limited and may be, for example, an internal or external type, and examples include a hard disk (HD), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, and memory card. The storage device 204 may be, for example, a hard disk drive (HDD) or a solid state drive (SSD) in which the recording medium and drive are integrated.

[0039] In the present device 20, the memory 202 and the storage device 204 can also store various information such as log information, information acquired from an external database (not shown) or an external device, information generated by the present device 20, and information used when the present device 20 executes processing. In this case, the memory 202 and the storage device 204 may store, for example, the risk of developing a sleep disorder, which will be described later. Note that at least a portion of the information may be stored, for example, in an external server other than the memory 202 and the storage device 204, or may be stored in a distributed manner across multiple terminals using blockchain technology or the like.

[0040] The device 20 further includes, for example, an input device 205 and an output device 206. Examples of the input device 205 include pointing devices such as a touch panel, track pad, or mouse; a keyboard; imaging means such as a camera or scanner; card readers such as an IC card reader or a magnetic card reader; and audio input means such as a microphone. Examples of the output device 206 include display devices such as an LED display or a liquid crystal display; audio output devices such as a speaker; a printer; etc. In the present disclosure 1, the input device 205 and the output device 206 are configured separately, but the input device 205 and the output device 206 may be configured as an integrated device, such as a touch panel display.

[0041] Next, an example of the disease onset risk prediction method of the present disclosure will be described based on the flowchart of Fig. 6. The disease onset risk prediction method of the present disclosure is carried out as follows, for example, using the present device 20 of Fig. 4 or Fig. 5. Note that the disease onset risk prediction method of the present disclosure is not limited to use of the present device 20 of Fig. 4 or Fig. 5.

[0042] First, the information acquisition unit 21 acquires the sleep disorder risk of the person to be predicted (S21, information acquisition step). The sleep disorder risk is a sleep disorder risk predicted from the disease-related information of the person to be predicted. The sleep disorder risk may be, for example, a sleep disorder risk output by the sleep disorder risk prediction device of the present disclosure.

[0043] Next, the prediction unit 22 predicts the risk of developing a disease of the subject based on the risk of developing a sleep disorder (S22, prediction step). The disease includes at least one of diabetes and cardiovascular disease. Examples of diabetes include type 2 diabetes. Examples of cardiovascular disease include acute myocardial infarction and heart failure. The disease risk is predicted based on, for example, the correlation between the risk of developing a sleep disorder and the disease.

[0044] The prediction unit 22 may be a trained model (disease onset risk prediction model). In this case, the disease onset risk prediction model predicts the disease onset risk of the prediction subject based on the sleep disorder onset risk. The disease onset risk prediction model is, for example, a trained model that outputs the disease onset risk of the prediction subject when the sleep disorder onset risk is input. The disease onset risk prediction model can also be said to be, for example, a trained model that is machine-learned based on multiple sleep disorder onset risks and causes a computer to function to predict the disease onset risk of the prediction subject. The multiple sleep disorder onset risks may or may not include disease-related information of the prediction subject.

[0045] Thereafter, the output unit 23 outputs the disease development risk (S23, output step), and the process ends. The disease development risk to be output is not particularly limited as long as it can grasp the disease development risk of the prediction subject, and may be, for example, an absolute evaluation, a relative evaluation, a numerical value, an evaluation result based on a threshold, etc. The output may be, for example, output to the output device 206 included in the present apparatus 20, or may be output to an output device included in another apparatus other than the present apparatus 20.

[0046] In this way, according to the disease onset risk prediction device and disease onset risk prediction method of the present disclosure, for example, it is possible to predict the risk of developing other diseases based on the predicted risk of developing a sleep disorder.

[0047] Third Embodiment Next, a sleep disorder onset risk prediction marker set, which serves as an index for predicting the risk of developing a sleep disorder, will be described.

[0048] The sleep disorder onset risk prediction marker set of the present disclosure includes, in addition to age, at least one marker of information related to obesity, information related to hypertension, and information related to hyperglycemia. That is, in addition to age, the set may include all or some of the information related to obesity, information related to hypertension, and information related to hyperglycemia. Examples of the obesity-related information include abdominal circumference, weight, and BMI (Body Mass Index). Examples of the hypertension-related information include a medical history of hypertension, information on the administration or administration of medication for hypertension, blood pressure test values, etc. Examples of the medication or administration information for hypertension include information on insulin administration and antihypertensive medication, etc. Examples of the blood pressure test values ​​include information on systolic blood pressure of 140 mmHg or higher (described below) and information on diastolic blood pressure of 90 mmHg or higher (described below). Examples of the hyperglycemia-related information include a medical history of diabetes, information on the administration or administration of medication for hyperglycemia, blood glucose levels, etc. The medication or medication information for hyperglycemia may include, for example, information on insulin medication, information on hypoglycemic medication, etc. The blood glucose level may include, for example, information that fasting blood glucose is 126 mg / dL or more, or information that HbA1c (hemoglobin A1c) is 6.5% or more, which will be described later. The sleep disorder development risk prediction marker set may further include at least one of the following: gender (male), blood test values ​​(HDL (High Density Lipoprotein), LDL (Low Density Lipoprotein), TG (triglyceride), AST (aspartate aminotransferase), diastolic blood pressure, fasting blood glucose, medical history of dyslipidemia, and medical interview information regarding lifestyle habits (weight gain since age 20, amount of alcohol consumed per day (1 to 2 go), sleep quality, walking speed, weight change over the year, etc.). Note that the sleep disorder development risk prediction marker set is not limited to these and may include other markers as long as it provides information necessary for predicting the risk of developing a sleep disorder. The sleep disorder development risk prediction marker set of the present disclosure may be, for example, a marker set selected based on the results of an analysis of the association with sleep disorders using a Cox proportional hazards model.

[0049] [Embodiment 4] Next, the selection of disease-related information (covariates) for predicting the risk of developing a sleep disorder, the creation of a trained model, the prediction of the risk of developing a sleep disorder using the trained model, the accuracy of the trained model, and the relationship between sleep disorders and diseases will be described with reference to Figures 7 to 20.

[0050] 7 is a diagram showing the breakdown of training data and evaluation data. In creating a trained model, as shown in FIG. 7, for example, 50% of the plurality of pieces of disease-related information (health checkup information and medical record information) are randomly selected and used as training data, 25% are used as evaluation data, and the remaining 25% can be used for final evaluation.

[0051] The training data may be, for example, data selected based on arbitrary conditions. Fig. 8 is a diagram showing an example of data selection for use as training data. The arbitrary conditions may be, for example, as shown in Fig. 8, excluding data (3) in the case where a sleep disorder developed before the start of observation (initial observation, baseline), and using the other data (1, 2, 4, 5) as training data.

[0052] Next, an example of a method for selecting disease-related information (covariates) for predicting the risk of developing a sleep disorder based on selected training data is described. The disease-related information can be obtained using a Cox proportional hazards model. The Cox proportional hazards model can be used to analyze the association between sleep disorders and, for example, age, gender, height, weight, BMI, abdominal circumference, blood test results (HDL, LDL, TG, γGTP, AST, ALT, fasting blood glucose, uric acid), systolic blood pressure, diastolic blood pressure, other disease data (diabetes, hypertension, dyslipidemia), and lifestyle habits (exercise, walking speed, weight gain since age 20, weight change over the year, smoking, skipping breakfast, eating a late dinner, snacking, drinking frequency, amount of alcohol, and sleep quality). An example of the analysis results is shown in Figure 9 and Table 1 below. Figure 9 is a scatter plot showing the relationship between age- and gender-adjusted hazard ratios and p-values. In Figure 9, the vertical axis represents -log(p-value) and the horizontal axis represents the hazard ratio. In addition, the "corrected p-value" in Table 1 means the p-value after Bonferroni correction.

[0053]

[0054] Next, an example of creating a sleep disorder risk prediction model using disease-related information is shown. The sleep disorder risk prediction model utilizes a Cox proportional hazards model, and covariates can be selected by applying stepwise selection and AIC from, for example, age, gender, height, weight, BMI, waist circumference, blood test results (HDL, LDL, TG, γGTP, AST, ALT, fasting blood glucose, uric acid), systolic blood pressure, diastolic blood pressure, other disease data (diabetes, hypertension, dyslipidemia), and lifestyle habits (exercise, walking speed, weight gain since age 20, weight change over the year, smoking, skipping breakfast, late dinner, snacking, drinking frequency, amount of alcohol, and sleep quality). The created prediction model can be evaluated by evaluating the AUC (area under curve) for the onset of sleep disorders within a given period using ROC analysis. The risk of developing a sleep disorder can be predicted using the trained model created in this way. Figure 10 shows details of the created trained model. Figure 10 shows that waist circumference, poor sleep quality, slow walking speed, history of diabetes, history of hypertension, high AST and low ALT (presence or absence of liver damage), and high triglyceride levels can be indicators of the risk of developing sleep disorders. Therefore, lifestyle improvement measures can be proposed based on these indicators. Figure 11 is a graph showing the results of an ROC analysis of the trained model. In Figure 11, the vertical axis represents sensitivity and the horizontal axis represents specificity. As an example, Figure 11 shows the AUC evaluation results for the onset of sleep disorders over a four-year period. As shown in Figure 11, the trained model can predict sleep disorders with high accuracy.

[0055] FIG. 12 shows details of another trained model that was created. Neither the right nor the left of FIG. 12 includes blood test results. Furthermore, in FIG. 12, the left graph does not include abdominal circumference information, while the right graph does. The trained model shown in FIG. 12 does not use blood test results, allowing for non-invasive and easy prediction of the risk of developing a sleep disorder. Furthermore, the trained model shown in the left of FIG. 12 does not include abdominal circumference information, and can predict the risk of developing a sleep disorder based only on age, weight, and medical interview information. Therefore, the trained model shown in the left of FIG. 12 can predict the risk of developing a sleep disorder more easily than the trained model shown in the right of FIG. 12. FIG. 13 shows a graph showing the results of an ROC analysis of another trained model that was created. Note that neither the right nor the left of FIG. 13 includes blood test results. In FIG. 13, the left graph does not include abdominal circumference information, while the right graph includes abdominal circumference information. In both graphs of FIG. 13, the vertical axis represents sensitivity and the horizontal axis represents specificity. Note that Figure 13 shows, as an example, the evaluation results of AUC for the onset of sleep disorders over a four-year period. As shown in Figure 13, it is possible to predict sleep disorders with high accuracy using other trained models created, regardless of whether or not waist circumference is measured. As described above, such trained models can easily and non-invasively predict the risk of developing a sleep disorder. Furthermore, since the risk of developing a sleep disorder can be predicted without the subject having to measure their waist circumference themselves, it is possible to more easily predict the risk of developing a sleep disorder.

[0056] Figure 14 is a graph showing the prediction results of the risk of developing a sleep disorder using the created trained model. In Figure 14, the vertical axis represents the risk of developing a sleep disorder, and the horizontal axis represents whether an event has occurred. As shown in Figure 14, the created trained model can detect people who are at risk of developing a sleep disorder with the same accuracy as people who have symptoms and have developed a sleep disorder, even if they respond that they are getting enough rest through sleep (i.e., people who have no subjective symptoms).

[0057] Figure 15 is another graph showing the prediction results of the risk of developing a sleep disorder using the created trained model. In Figure 15, the vertical axis represents the risk of developing a sleep disorder, and the horizontal axis represents whether an event has occurred. As shown in Figure 15, the created trained model can detect people at risk of developing a sleep disorder with the same accuracy as unhealthy people who have developed a sleep disorder, even if they are healthy (without symptoms of hypertension, a history of diabetes, symptoms of dyslipidemia, or obesity (BMI less than 25)).

[0058] FIG. 16 is a diagram showing the relationship between BMI and the onset of sleep disorders. In the right diagram of FIG. 16, the vertical axis represents the risk of developing a sleep disorder, and the horizontal axis represents whether an event has occurred. As shown in the left diagram of FIG. 16, all subjects predicted to develop a sleep disorder have a sleep disorder regardless of whether their BMI is high or low. A high BMI, i.e., being obese, is believed to be associated with sleep disorders. Therefore, when making a diagnosis, doctors often recommend sleep disorder testing for individuals diagnosed with obesity, but do not proceed with sleep disorder testing for individuals not diagnosed with obesity. Therefore, the sleep disorder onset risk prediction device disclosed herein can accurately predict the risk of developing a sleep disorder, even for individuals not diagnosed with obesity whose risk of developing a sleep disorder would otherwise be overlooked.

[0059] Figure 17 is a heat map showing the correlation between sleep disorders and other diseases. As shown in the heat map, type 2 diabetes (DM), acute myocardial infarction (MI), and heart failure (HF) are each correlated with sleep disorders (SD). Therefore, if the risk of developing sleep disorders is known, the risk of developing diabetes and cardiovascular disease can be predicted.

[0060] 18 and 19 show examples of the results of predicting the risk of developing a sleep disorder and monitoring the onset of the sleep disorder for a prediction subject. The prediction subjects in FIGS. 18 and 19 are both male. The prediction subject in FIG. 18 has no subjective symptoms of a sleep disorder and has been diagnosed with hypertension, diabetes, and dyslipidemia. The prediction subject in FIG. 18 has subjective symptoms of a sleep disorder and has been diagnosed with hypertension and dyslipidemia after the onset of a sleep disorder. According to the present disclosure, as shown in FIG. 18, it is possible to detect an increased risk of a sleep disorder even in cases where the subject is unaware of the sleep disorder. Furthermore, as shown in FIG. 19, it is possible to guide treatment for a sleep disorder for a subject who is aware of the sleep disorder.

[0061] Fifth Embodiment A program of the present disclosure is a program for causing a computer to execute each of the steps of the present disclosure described above. Specifically, the program of the present disclosure is a program for causing a computer to execute, for example, an information acquisition procedure, a prediction procedure, and an output procedure.

[0062] The program of the present disclosure can also be said to be a program that causes a computer to function as, for example, an information acquisition procedure, a prediction procedure, and an output procedure.

[0063] The program of the present disclosure can be implemented by invoking the descriptions of the sleep disorder onset risk prediction device and sleep disorder onset risk prediction method, and the disease onset risk prediction device and disease onset risk prediction method according to Embodiment 1 and Embodiment 2 of the present disclosure. For each of the steps, for example, "step" can be read as "processing." The program of the present disclosure may be recorded on, for example, a computer-readable recording medium. The recording medium is, for example, a non-transitory computer-readable storage medium. The recording medium is not particularly limited, and examples thereof include random access memory (RAM), read-only memory (ROM), hard disk (HD), flash memory (e.g., solid state drive (SSD), USB flash memory, SD / SDHC card, etc.), optical disc (e.g., CD-R / CD-RW, DVD-R / DVD-RW, BD-R / BD-RE, etc.), magneto-optical disk (MO), floppy disk (FD), etc. Furthermore, the program of the present disclosure (e.g., a programming product or a program product) may be distributed from an external computer, for example. The "distribution" may be, for example, distribution via a communication network or distribution via a device connected via a wire. The program of the present disclosure may be installed and executed on the device to which it is distributed, or may be executed without being installed.

[0064] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure.

[0065] <Supplementary Notes> Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. (Supplementary Note 1) A sleep disorder onset risk prediction device including an information acquisition unit, a prediction unit, and an output unit, wherein the information acquisition unit acquires disease-related information of a subject to be predicted, the prediction unit predicts the subject's risk of developing a sleep disorder from the disease-related information, and the output unit outputs the risk of developing a sleep disorder. (Supplementary Note 2) The sleep disorder onset risk prediction device according to Supplementary Note 1, wherein the disease-related information includes, in addition to age, at least one of information related to obesity, information related to high blood pressure, and information related to hyperglycemia, and the obesity-related information includes at least one of information on waist circumference, weight, and BMI. (Supplementary Note 3) The sleep disorder onset risk prediction device according to Supplementary Note 2, wherein the disease-related information further includes at least one of gender, blood test results, systolic blood pressure, diastolic blood pressure, fasting blood glucose, a medical history of dyslipidemia, and questionnaire information related to lifestyle habits. (Supplementary Note 4) A disease onset risk prediction device including an information acquisition unit, a prediction unit, and an output unit, wherein the information acquisition unit acquires a sleep disorder development risk of a subject, the sleep disorder development risk being predicted from disease-related information of the subject, the prediction unit predicts a disease development risk of the subject from the sleep disorder development risk, the disease including at least one of diabetes and cardiovascular disease, and the output unit outputs the disease development risk. (Supplementary Note 5) A sleep disorder onset risk prediction marker set including, in addition to age, at least one marker of information related to obesity, high blood pressure, and hyperglycemia, wherein the obesity-related information includes at least one of waist circumference, weight, and BMI, and serves as an index for predicting the risk of developing a sleep disorder. (Supplementary Note 6) The sleep disorder onset risk prediction marker set according to Supplementary Note 5, further including at least one of gender, blood test values, systolic blood pressure, diastolic blood pressure, fasting blood glucose, a medical history of dyslipidemia, and lifestyle-related questionnaire information.(Supplementary Note 7) A method for predicting risk of developing a sleep disorder, comprising an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires disease-related information of the subject, the prediction step predicts the risk of developing a sleep disorder of the subject from the disease-related information, and the output step outputs the risk of developing a sleep disorder, wherein each of the steps is performed by a computer. (Supplementary Note 8) The method for predicting risk of developing a sleep disorder according to Supplementary Note 7, wherein the disease-related information includes, in addition to age, at least one of information related to obesity, information related to high blood pressure, and information related to hyperglycemia, and the obesity-related information includes at least one of information on waist circumference, weight, and BMI. (Supplementary Note 9) The method for predicting risk of developing a sleep disorder according to Supplementary Note 8, wherein the disease-related information further includes at least one of sex, blood test results, systolic blood pressure, diastolic blood pressure, fasting blood glucose, a medical history of dyslipidemia, and questionnaire information related to lifestyle habits. (Supplementary Note 10) A disease onset risk prediction method, the method comprising: an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires a sleep disorder development risk of the person to be predicted, the sleep disorder development risk being predicted from disease-related information of the person to be predicted, the prediction step predicts a disease onset risk of the person to be predicted from the sleep disorder development risk, the disease includes at least one of diabetes and cardiovascular disease, and the output step outputs the disease onset risk, the steps being executed by a computer. (Supplementary Note 11) A sleep disorder onset risk prediction program, the method comprising: an information acquisition step, a prediction step, and an output step, the information acquisition step acquires disease-related information of the person to be predicted, the prediction step predicts the sleep disorder onset risk of the person to be predicted from the disease-related information, and the output step outputs the sleep disorder onset risk, the steps being executed by a computer. (Appendix 12) The program according to Appendix 11, wherein the disease-related information includes, in addition to age, at least one of information related to obesity, information related to high blood pressure, and information related to hyperglycemia, and the obesity-related information includes at least one of information on waist circumference, weight, and BMI.(Supplementary Note 13) The program according to Supplementary Note 12, wherein the disease-related information further includes at least one of gender, blood test values, systolic blood pressure, diastolic blood pressure, fasting blood glucose, a medical history of dyslipidemia, and questionnaire information related to lifestyle habits. (Supplementary Note 14) A disease onset risk prediction program for causing a computer to execute each of the steps, including an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires a sleep disorder development risk of the prediction subject, the sleep disorder development risk is a sleep disorder development risk predicted from disease-related information of the prediction subject, the prediction step predicts a disease onset risk of the prediction subject from the sleep disorder development risk, the disease includes at least one of diabetes and cardiovascular disease, and the output step outputs the disease onset risk. (Supplementary Note 15) A computer-readable recording medium having recorded thereon a program for causing a computer to execute each of the steps, including an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires disease-related information of the subject to be predicted, the prediction step predicts the subject's risk of developing a sleep disorder from the disease-related information, and the output step outputs the risk of developing a sleep disorder. (Supplementary Note 16) The recording medium of Supplementary Note 15, wherein the disease-related information includes, in addition to age, at least one of information related to obesity, information related to high blood pressure, and information related to hyperglycemia, and the obesity-related information includes at least one of information on waist circumference, weight, and BMI. (Supplementary Note 17) The recording medium of Supplementary Note 16, wherein the disease-related information further includes at least one of sex, blood test results, systolic blood pressure, diastolic blood pressure, fasting blood glucose, a medical history of dyslipidemia, and questionnaire information related to lifestyle habits. (Supplementary Note 18) A computer-readable recording medium having recorded thereon a program for causing a computer to execute each of the steps, the computer-readable recording medium including an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires a risk of developing a sleep disorder for a subject to be predicted, the risk of developing a sleep disorder being a risk of developing a sleep disorder predicted from disease-related information of the subject to be predicted, the prediction step predicts a risk of developing a disease for the subject to be predicted from the risk of developing a sleep disorder, the disease including at least one of diabetes and cardiovascular disease, and the output step outputs the risk of developing the disease.

[0066] This application claims priority based on Japanese Patent Application No. 2023-186914, filed October 31, 2023, the disclosure of which is incorporated herein in its entirety by reference.

[0067] According to the present disclosure, it is possible to easily predict the risk of developing a sleep disorder. The fields to which the present disclosure can be applied are not limited, and the present disclosure can be applied to a wide range of fields using a sleep disorder development risk prediction device.

[0068] 10 Sleep disorder onset risk prediction device 20 Disease onset risk prediction device 11, 21 Information acquisition unit 12, 22 Prediction unit 13, 23 Output unit 101, 201 Central processing unit 102, 201 Memory 103, 203 Bus 104, 204 Storage device 105, 205 Input device 106, 206 Output device 107, 207 Communication device

Claims

1. A sleep disorder development risk prediction device comprising an information acquisition unit, a prediction unit, and an output unit, wherein the information acquisition unit acquires disease-related information of a subject to be predicted, the prediction unit predicts the risk of developing a sleep disorder of the subject from the disease-related information, and the output unit outputs the risk of developing a sleep disorder.

2. A sleep disorder onset risk prediction device as described in claim 1, wherein the disease-related information includes, in addition to age, at least one of information related to obesity, information related to high blood pressure, and information related to hyperglycemia, and the obesity-related information includes at least one of information on waist circumference, weight, and BMI.

3. A sleep disorder onset risk prediction device as described in claim 2, wherein the disease-related information further includes at least one of gender, blood test results, systolic blood pressure, diastolic blood pressure, fasting blood glucose, medical history of dyslipidemia, and questionnaire information regarding lifestyle habits.

4. A disease onset risk prediction device comprising an information acquisition unit, a prediction unit, and an output unit, wherein the information acquisition unit acquires the risk of developing a sleep disorder of a subject to be predicted, the risk of developing a sleep disorder being predicted from disease-related information of the subject to be predicted, the prediction unit predicts the risk of developing a disease of the subject to be predicted from the risk of developing a sleep disorder, the disease including at least one of diabetes and cardiovascular disease, and the output unit outputs the risk of developing the disease.

5. A marker set for predicting risk of developing a sleep disorder, which includes, in addition to age, at least one marker of information related to obesity, information related to high blood pressure, or information related to hyperglycemia, and the obesity-related information includes at least one of waist circumference, weight, and BMI, and which serves as an indicator for predicting the risk of developing a sleep disorder.

6. The marker set for predicting the risk of developing a sleep disorder according to claim 5, further comprising at least one of the following interview information: gender, blood test results, systolic blood pressure, diastolic blood pressure, fasting blood glucose, medical history of dyslipidemia, and lifestyle habits.

7. A method for predicting risk of developing a sleep disorder, comprising an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires disease-related information of the subject, the prediction step predicts the risk of developing a sleep disorder of the subject from the disease-related information, and the output step outputs the risk of developing a sleep disorder, and each of the steps is executed by a computer.

8. A method for predicting the risk of developing a sleep disorder as described in claim 7, wherein the disease-related information includes, in addition to age, at least one of information related to obesity, information related to high blood pressure, and information related to hyperglycemia, and the obesity-related information includes at least one of information on waist circumference, weight, and BMI.

9. A method for predicting the risk of developing a sleep disorder as described in claim 8, wherein the disease-related information further includes at least one of gender, blood test results, systolic blood pressure, diastolic blood pressure, fasting blood glucose, history of dyslipidemia, and questionnaire information regarding lifestyle habits.

10. A disease onset risk prediction method comprising an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires the risk of developing a sleep disorder of the subject, the risk of developing a sleep disorder being predicted from disease-related information of the subject, the prediction step predicts the risk of developing a disease of the subject from the risk of developing a sleep disorder, the disease including at least one of diabetes and cardiovascular disease, and the output step outputs the risk of developing the disease, and each of the steps is performed by a computer.

11. A sleep disorder development risk prediction program including an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires disease-related information of a subject to be predicted, the prediction step predicts the risk of developing a sleep disorder of the subject from the disease-related information, and the output step outputs the risk of developing a sleep disorder, the program causing a computer to execute each of the steps.

12. The program according to claim 11, wherein the disease-related information includes, in addition to age, at least one of information related to obesity, information related to high blood pressure, and information related to hyperglycemia, and the obesity-related information includes at least one of information on waist circumference, weight, and BMI.

13. The program of claim 12, wherein the disease-related information further includes at least one of gender, blood test results, systolic blood pressure, diastolic blood pressure, fasting blood glucose, history of dyslipidemia, and questionnaire information regarding lifestyle habits.

14. A disease onset risk prediction program comprising an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires the risk of developing a sleep disorder of a subject to be predicted, the risk of developing a sleep disorder being a risk of developing a sleep disorder predicted from disease-related information of the subject to be predicted, the prediction step predicts the risk of developing a disease of the subject to be predicted from the risk of developing a sleep disorder, the disease including at least one of diabetes and cardiovascular disease, and the output step outputs the risk of developing the disease, for causing a computer to execute each of the steps.

15. A computer-readable recording medium having recorded thereon a program for causing a computer to execute each of the steps, including an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires disease-related information of a subject to be predicted, the prediction step predicts the risk of developing a sleep disorder of the subject from the disease-related information, and the output step outputs the risk of developing a sleep disorder.

16. The recording medium according to claim 15, wherein the disease-related information includes, in addition to age, at least one of information related to obesity, information related to high blood pressure, and information related to hyperglycemia, and the obesity-related information includes at least one of information on waist circumference, weight, and BMI.

17. The recording medium according to claim 16, wherein the disease-related information further includes at least one of gender, blood test results, systolic blood pressure, diastolic blood pressure, fasting blood glucose, medical history of dyslipidemia, and questionnaire information regarding lifestyle habits.

18. A computer-readable recording medium having recorded thereon a program for causing a computer to execute each of the steps, the steps including an information acquisition step, a prediction step, and an output step, wherein the information acquisition step acquires the risk of developing a sleep disorder of the subject, the risk of developing a sleep disorder being predicted from disease-related information of the subject, the prediction step predicts the risk of developing a disease of the subject from the risk of developing a sleep disorder, the disease including at least one of diabetes and cardiovascular disease, and the output step outputting the risk of developing the disease.

Images