Apparatus and method for predicting disease based on sleep analysis installed in senior house

Abstract

The present invention relates to a sleep analysis-based disease prediction device installed in a senior house. The sleep analysis-based disease prediction device according to an embodiment of the present invention may be installed in a senior house and include: a bio-signal sensor which is installed in a bedroom to remotely measure the heart rate or respiration of a sleeper and generate bio-signal data; and a sleep analysis unit for analyzing a sleep pattern of the sleeper on the basis of the bio-signal data and generating an alarm message when a disease suspicion pattern is determined from the sleep pattern.

Description

Disease prediction device and disease prediction method based on sleep analysis installed in a senior citizen's home

[0001] The present invention relates to a disease prediction device and disease prediction method based on sleep analysis, installed in a senior citizen's home, which enable the elderly to receive a diagnosis in advance by predicting diseases that may occur based on sleep analysis.

[0002]

[0003] Korea's population is aging rapidly, and it is projected that the country will become a super-aged society by 2025. The population aged 65 and older is projected to reach 10 million in 2025, just five years from now, and over 15 million in 2036. The proportion of the elderly population is projected to increase from 16.1% in 2020 to over 20% in 2025 and 30% in 2035.

[0004] In addition, single-person households are increasing, and according to the Ministry of the Interior and Safety, the number of elderly people living alone increased by 30.9% from 1,275,316 in 2016 to 1,674,116 in 2021. In particular, among the lonely deaths that occurred from 2016 to June 2020, nearly half (43%) were among elderly people aged 65 or older, with 388 deaths (42%) as of June 2020, indicating that lonely deaths among elderly people aged 65 or older account for more than 40% every year.

[0005] To address these issues, senior care services are being implemented to ensure a stable retirement, maintain functional and health functions, and prevent deterioration by providing appropriate care services to vulnerable seniors who have difficulty managing their daily lives. However, with the growing number of care recipients and the resulting rise in welfare costs, various research and development efforts are underway on IoT-based smart care systems.

[0006]

[0007] The present invention aims to provide a disease prediction device and disease prediction method based on sleep analysis, which are installed in a senior citizen's home, to enable the elderly to receive a diagnosis of a disease in advance by predicting a disease that may occur in the elderly based on sleep analysis.

[0008] The present invention aims to provide a disease prediction device and disease prediction method based on sleep analysis, which can be installed in a senior citizen's home, to analyze sleep patterns without disturbing the sleep of the sleeper by remotely measuring the sleeper's breathing or heart rate, etc.

[0009] The present invention aims to provide a disease prediction device and disease prediction method based on sleep analysis installed in a senior citizen's home, which can accurately determine a disease suspicion pattern corresponding to a target disease based on artificial intelligence.

[0010] The present invention aims to provide a disease prediction device and disease prediction method based on sleep analysis, which can be installed in a senior citizen's home, and which can remove noise from bio-signal data for sleep analysis by determining when a sleeper is not sleeping.

[0011]

[0012] A disease prediction device based on sleep analysis installed in a senior citizen's home according to one embodiment of the present invention may include a biosignal sensor installed in a bedroom to remotely measure the heartbeat or respiration of a sleeper to generate biosignal data; and a sleep analysis unit that analyzes the sleeper's sleep pattern based on the biosignal data and generates an alarm message when a disease-suspicious pattern is determined from the sleep pattern.

[0013] Here, the bio-signal sensor may be installed on the ceiling or side wall of the bedroom to irradiate radar signals to the sleeper and receive reflected radar signals to measure the sleeper's heart rate or breathing rate.

[0014] Here, the sleep analysis unit collects the bio-signal data during a preset sleep time and analyzes the sleep pattern of the sleeper. The sleep time may be set based on the sleeper's preset value, changes in the lighting level in the bedroom, and the on / off operation of the lights in the bedroom.

[0015] Here, the sleep analysis unit may determine a disease suspicion pattern for at least one of Alzheimer's disease, Parkinson's disease, stroke, and myocardial infarction from the sleep pattern.

[0016] Here, the sleep analysis unit may include an analysis model created by learning the sleep patterns of patients with at least one of Alzheimer's disease, Parkinson's disease, stroke, and myocardial infarction as learning data.

[0017] Here, the sleep analysis unit may determine that the sleeper has left the sleeper if the bio-signal data is measured to be less than the threshold value for a set period of time, and may process the bio-signal data measured during the sleeper's leaving the sleeper as noise.

[0018] Here, the sleep analysis unit may further include a posture detection sensor installed in the bedroom to remotely measure the posture of the sleeper and generate posture data, and if the posture data corresponds to a posture other than the sleeping posture within a preset sleep time, the sleep analysis unit may determine that the sleeper has left the room and process the bio-signal data measured during the sleeper's leaving the room as noise.

[0019] Here, the sleep analysis unit may transmit the alarm message to a wall pad installed in the senior citizen's home or a pre-registered mobile communication terminal.

[0020] A disease prediction method based on sleep analysis according to one embodiment of the present invention may include a step of generating bio-signal data by remotely measuring a heartbeat or respiration of a sleeper using a bio-signal sensor installed in a bedroom in a senior citizen's home; and a step of analyzing a sleep pattern of the sleeper based on the bio-signal data using a sleep analysis unit, and generating an alarm message if a disease-suspicious pattern is determined from the sleep pattern.

[0021] Here, the bio-signal sensor may be installed on the ceiling or side wall of the bedroom to irradiate radar signals to the sleeper and receive reflected radar signals to measure the sleeper's heart rate or breathing rate.

[0022] Here, the step of generating the above notification message is to collect the bio-signal data during a preset sleep time and analyze the sleep pattern of the sleeper. The sleep time may be set based on the sleeper's set value, changes in the lighting level in the bedroom, and on / off operations of lights in the bedroom.

[0023] Here, the step of generating the above notification message can determine a disease suspicion pattern for at least one of Alzheimer's disease, Parkinson's disease, stroke, and myocardial infarction from the above sleep pattern.

[0024] Here, the step of generating the above-mentioned notification message can determine the disease suspicion pattern by using an analysis model generated by learning the sleep patterns of patients with at least one of Alzheimer's disease, Parkinson's disease, stroke, and myocardial infarction as learning data.

[0025] Here, the step of generating the above notification message may be such that if the bio-signal data is measured to be less than the threshold value for a set period of time, the sleeper's departure is determined, and the bio-signal data measured during the sleeper's departure may be processed as noise.

[0026] Here, a disease prediction method based on sleep analysis according to one embodiment of the present invention further includes a step of remotely measuring the posture of a sleeper using a posture detection sensor installed in a bedroom in a senior citizen's home to generate posture data, and the step of generating a notification message may determine that the sleeper has left if the posture data corresponds to a posture other than a sleeping posture within a preset sleeping time, and may process the bio-signal data measured during the sleeper's leaving as noise.

[0027] Here, the step of generating the above notification message may transmit the alarm message to a wall pad installed in the senior citizen's home or a pre-registered mobile communication terminal.

[0028] According to one embodiment of the present invention, a computer program stored in a medium can be implemented to perform the above-described sleep analysis-based disease prediction method in combination with hardware.

[0029] Additionally, the solutions to the aforementioned problems do not enumerate all features of the present invention. The various features of the present invention, along with their corresponding advantages and effects, can be understood in more detail by referring to the specific embodiments below.

[0030]

[0031] According to a disease prediction device and disease prediction method based on sleep analysis installed in a senior citizen's home according to one embodiment of the present invention, diseases that may occur in the elderly can be predicted based on sleep analysis, so it is possible to promptly induce a diagnosis for the disease.

[0032] According to one embodiment of the present invention, a disease prediction device and disease prediction method based on sleep analysis, installed in a senior citizen's home, can predict diseases based on remotely measured data such as the sleeper's breathing and heart rate. In other words, since the sleeper does not need to wear any additional equipment, it is possible to accurately analyze sleep patterns without disturbing the sleeper's sleep.

[0033] According to a disease prediction device and disease prediction method based on sleep analysis installed in a senior citizen's home according to one embodiment of the present invention, it is possible to accurately determine a disease suspicion pattern corresponding to a target disease based on artificial intelligence, and to distinguish cases where a sleeper is not sleeping, so it is possible to provide more accurate disease prediction results.

[0034] However, the effects that can be achieved by the disease prediction device and disease prediction method based on sleep analysis installed in a senior citizen's home according to embodiments of the present invention are not limited to those mentioned above, and other effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention pertains from the description below.

[0035]

[0036] Figure 1 is a schematic diagram showing a disease prediction system based on sleep analysis installed in a senior citizen's home according to one embodiment of the present invention.

[0037] Figure 2 is a block diagram showing a disease prediction device according to one embodiment of the present invention.

[0038] Figure 3 is a schematic diagram showing the operation of a posture detection sensor according to one embodiment of the present invention.

[0039] Figure 4 is an exemplary diagram showing biometric data and posture data of a sleeper according to one embodiment of the present invention.

[0040] Figure 5 is a block diagram showing a computing device according to one embodiment of the present invention.

[0041] Figure 6 is a flowchart showing a disease prediction method based on sleep analysis according to one embodiment of the present invention.

[0042]

[0043] Hereinafter, embodiments disclosed in the present specification will be described in detail with reference to the attached drawings. Regardless of the drawing numbers, identical or similar components will be given the same reference numbers, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are given or used interchangeably only for the convenience of writing the specification, and do not have distinct meanings or roles in themselves. That is, the term "part" used in the present invention means a hardware component such as software, FPGA, or ASIC, and the "part" performs certain roles. However, the "part" is not limited to software or hardware. The "part" may be configured to be on an addressable storage medium, or may be configured to reproduce one or more processors. Thus, as an example, a 'part' may include components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or further separated into additional components and 'parts'.

[0044] In addition, when describing the embodiments disclosed in this specification, if it is determined that a detailed description of a related known technology may obscure the gist of the embodiments disclosed in this specification, the detailed description thereof will be omitted. In addition, the attached drawings are only intended to facilitate easy understanding of the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the attached drawings, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and technical scope of the present invention.

[0045]

[0046] Figure 1 is a schematic diagram showing a disease prediction system based on sleep analysis installed in a senior citizen's home according to one embodiment of the present invention.

[0047] Referring to FIG. 1, a disease prediction system based on sleep analysis installed in a senior citizen's home according to one embodiment of the present invention may include a disease prediction device including a biosignal sensor (110), a posture detection sensor (120), and a sleep analysis unit (130), a wall pad (D1), and a mobile communication terminal (D2).

[0048] Referring to FIG. 1 below, a disease prediction system according to one embodiment of the present invention is described.

[0049] The sleeper (1) may be an elderly person, an elderly person living alone, a patient, or other elderly person, and the sleeper (1) may reside in a senior housing (Housing for the Elderly). A senior housing may be a house built based on the residence of the elderly or a household in which the elderly live, taking into consideration the physical and situational characteristics of the elderly.

[0050] A senior citizen's home may include a number of sensors to detect emergencies such as falls, fires, and crime prevention, and may include a wall pad (D1) that can be integrated and controlled so that the elderly can conveniently adjust the lighting, temperature, humidity, etc. in the home. Here, the wall pad (D1) may be configured to integrate and manage data received from sensors installed in the senior citizen's home, and in some embodiments, the sleep analysis unit (130) of the disease prediction device (100) may be implemented within the wall pad (D1).

[0051] The disease prediction device (100) can collect bio-signal data, posture data, etc. of a sleeper (1) based on a bio-signal sensor (110) and a posture detection sensor (120) installed in a senior citizen's home, and based on this, analyze the sleep pattern of the sleeper (1) to determine diseases that may occur in the sleeper (1). Here, if it is determined that the sleeper (1) has developed a disease, an alarm message can be transmitted to a wall pad (D1) or a pre-registered mobile communication terminal (D2).

[0052] Here, the disease prediction device (100) can communicate with the bio-signal sensor (110) and the posture detection sensor (120) through a network. The communication method between the disease prediction device (100) and the bio-signal sensor (110) and the posture detection sensor (120) is not limited, and may include not only a communication method that utilizes a communication network that the network can include (for example, a mobile communication network, wired Internet, wireless Internet, broadcasting network, satellite network, etc.), but also short-range wireless communication between devices. For example, the network may include one or more arbitrary networks among networks such as a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), and the Internet.

[0053] Specifically, referring to FIG. 2, a disease prediction device (100) according to one embodiment of the present invention may include a biosignal sensor (110), a posture detection sensor (120), and a sleep analysis unit (130).

[0054] The biosignal sensor (110) can be installed in a bedroom in a senior citizen's home. That is, it can be installed on the ceiling or side wall of the bedroom where the sleeper (1) sleeps, and after irradiating the sleeper (1) with a radar signal, the reflected radar signal can be received to measure the sleeper's (1) heart rate or respiration rate, etc. Here, the biosignal sensor (110) can generate biosignal data including the sleeper's (1) heart rate or respiration rate, etc., and transmit it to the sleep analysis unit (130).

[0055] As illustrated in Fig. 1, the biosignal sensor (110) may be installed vertically above the chest of the sleeper (1) to increase the accuracy of the measurement results. Here, the biosignal sensor (110) may use a millimeter wave frequency band capable of measuring millimeter-level changes in the chest of the sleeper (1), and may measure heart rate and respiratory rate, etc. from the movement of the chest of the sleeper (1).

[0056] The position of the bed (B) of the sleeper (1) can be determined based on the position of the bio-signal sensor (110) installed in the senior citizen's home, and the sleeper (1) can be guided to lie down so that his / her chest is positioned vertically below the bio-signal sensor (110) during sleep. In addition, the sleeper (1) can be guided to assume a sleeping posture of lying down correctly in a direction facing the ceiling.

[0057] A posture detection sensor (120) can be installed in a bedroom to remotely measure the posture of a sleeper (1) and generate posture data. As illustrated in Fig. 1, the posture detection sensor (120) can be installed on the ceiling or side wall of the bedroom where the sleeper (1) sleeps, and can be installed in a direction facing the sleeper (1) positioned on the bed (B).

[0058] Referring to FIG. 3, the posture detection sensor (120) can be divided into a posture sensor (121) and a fall sensor (122). Here, the posture sensor (121) is installed facing the bed (B) to detect the posture of the sleeper (1) on the bed (B). For example, the posture sensor (121) can distinguish and recognize the sleeping posture of the sleeper (1) lying on the bed (B), the sitting posture on the bed (B), the standing posture from the bed (B), etc. In addition, the fall sensor (122) can be installed facing a fall risk area (A) preset around the bed (B) to detect the fall of the sleeper (1) from the bed (B). The posture detection sensor (120) can generate posture data that detects the posture or fall of the sleeper (1) and transmit the data to the sleep analysis unit (130).

[0059] The sleep analysis unit (130) can analyze the sleep pattern of a sleeper (1) based on biosignal data, and if a disease-suspicious pattern is found from the sleep pattern of the sleeper (1), an alarm message can be generated.

[0060] Since the sleep analysis unit (130) analyzes the sleep pattern from the bio-signal data of the sleeper (1) while the sleeper is sleeping, it is necessary to determine whether the sleeper (1) is currently sleeping. However, since the bio-signal sensor (110) measures the bio-signal of the sleeper (1) based on the radar signal, it may be difficult to determine whether the sleeper (1) is sleeping. Therefore, the sleep analysis unit (130) can collect bio-signal data during a preset sleep time and analyze the sleep pattern for bio-signal data such as breathing or heartbeat that appears during sleep based on the bio-signal data collected during the sleep time.

[0061] Here, the sleep time may be a preset value set by the sleeper (1) as his / her sleep time. For example, if the sleeper (1) sets his / her sleep time from 9 PM to 4 AM, the sleep analysis unit (130) can collect biosignal data between 9 PM and 4 AM and analyze the sleep pattern of the sleeper (1) based on this.

[0062] In addition, depending on the embodiment, it is possible to measure the change in the illuminance in the bedroom using a light sensor installed in the bedroom, estimate the sleep time of the sleeper (1) based on the change in illuminance, or estimate the sleep time based on the on / off operation of the lights in the bedroom. That is, the lights in the bedroom may be turned off before falling asleep and turned on after waking up, so the time in between can be estimated as the sleep time.

[0063] In addition, the sleep time of the sleeper (1) can be estimated based on the charging and uncharging times of the mobile communication terminal (D2) of the sleeper (1), or the sleep time of the sleeper (1) can be estimated in various ways by combining the above-described sleep time estimation methods.

[0064] Meanwhile, the sleep analysis unit (130) can determine whether there are disease-suspicious patterns corresponding to various target diseases such as Alzheimer's disease, Parkinson's disease, stroke, and myocardial infarction from the sleep pattern of the sleeper (1).

[0065] In some embodiments, the sleep analysis unit (130) can analyze the sleep pattern of the sleeper (1) in a time series manner to find a regular pattern, and if an irregular pattern that deviates from the regular pattern appears, it can be determined that a disease-suspicious pattern exists. For example, the sleep analysis unit (130) can find a regular pattern through a time series analysis of the sleep pattern of the sleeper (1) for 3 months, and if an irregular pattern that deviates from the regular pattern continues for a set period of time (for example, more than 1 week), it can be determined that a disease-suspicious pattern exists. Here, since the regular pattern may appear differently for each sleeper (1), the sleep analysis unit (130) can recognize a personalized regular pattern for each sleeper (1).

[0066] In addition, depending on the embodiment, an analysis model may be included in the sleep analysis unit (130), and the analysis model may be generated by learning the sleep patterns of a plurality of patients with the target disease as learning data. That is, if the sleep patterns of patients who already have the target disease are set as correct data and the analysis model is trained, then when the sleep pattern of a sleeper (1) is input into the analysis model, it is possible to determine and provide which target disease the sleep pattern corresponds to. For example, when a sleep pattern is input into the analysis model, it is also possible to calculate and provide a score indicating the degree to which the sleep pattern is similar to the sleep pattern corresponding to each target disease. In this case, if there is a target disease with a score higher than a set value, it can be determined that the sleeper (1) is highly likely to have the target disease. Here, the analysis model can be implemented based on various types of machine learning models, deep learning models, neural network models, etc.

[0067] Meanwhile, the sleep analysis unit (130) may not diagnose an actual disease, but rather informs that the risk of developing the target disease is high. In other words, it may predict a high probability of contracting the target disease and recommend that the sleeper (1) visit a hospital or similar institution to receive a diagnosis for the target disease.

[0068] Additionally, a sleeper (1) may not remain in a continuous state of sleep during sleep, and may wake up or leave their position during sleep. For example, they may move to the bathroom or drink water. In this case, noise may be included in the collected biosignal data, and thus, noise corresponding to non-sleep states needs to be removed.

[0069] In some embodiments, if the bio-signal data is measured to be below the threshold for a set period of time, the sleep analysis unit (130) may determine that the sleeper (1) has left the bed. That is, if the sleeper (1) leaves the bed, the heart rate or respiration rate measured by the bio-signal sensor (110) may show values ​​close to 0. Since a person's heart rate and respiration rate do not suddenly and simultaneously drop below the threshold, the sleep analysis unit (130) may determine that the sleeper (1) has left the bed in this case, and may process the bio-signal data measured during the leave as noise.

[0070] In addition, depending on the embodiment, it is also possible to determine whether the sleeper (1) has deviated based on the posture data generated by the posture detection sensor (120). That is, the sleep analysis unit (130) can determine that the sleeper (1) has deviated if the posture data of the sleeper (1) corresponds to a posture other than the sleeping posture during the sleep time.

[0071] As illustrated in FIG. 4, the posture detection sensor (120) can distinguish the posture of the sleeper (1) into a sitting posture (P1), a sleeping posture (P2), a standing posture (P3), etc. Here, if the posture of the sleeper (1) is detected as a sitting posture (P1) or a standing posture (P3) other than the sleeping posture (P2) during the sleeping time, it can be determined that the sleeper (1) is not sleeping. Therefore, all bio-signal data measured in postures other than the sleeping posture (P2) can be processed as noise. That is, although the respiration rate and heart rate, etc. are indicated as being measured in the sitting posture (P1) or the standing posture (P3) other than the sleeping posture (P2) in FIG. 4, the respiration rate and heart rate, etc. measured in the sitting posture (P1) or the standing posture (P3) can all be processed as noise.

[0072] Thereafter, the sleep analysis unit (130) can transmit an alarm message to the wall pad (D1) installed in the senior citizen's home or the pre-registered mobile communication terminal (D2). That is, when a disease suspicion pattern is determined, an alarm message can be generated to notify this, and the sleep analysis unit (130) can transmit the alarm message in various ways. Depending on the embodiment, it can be displayed on the wall pad (D1) installed in the senior citizen's home so that the sleeper (1) or the guardian can easily check it. In addition, the phone numbers of the mobile communication terminals (D2) of the sleeper, the guardian, the attending physician, and other related persons can be pre-registered in the disease prediction device (100). Therefore, the sleep analysis unit (130) can transmit the corresponding alarm message to the registered phone number, thereby notifying the sleeper (1) to visit a hospital for a diagnosis in relation to the target disease.

[0073]

[0074] Figure 5 is a block diagram illustrating a computing environment (10) suitable for use in exemplary embodiments. In the illustrated embodiment, each component may have different functions and capabilities other than those described below, and may include additional components other than those described below.

[0075] The illustrated computing environment (10) includes a computing device (12). In one embodiment, the computing device (12) may be a disease prediction device (100) or a sleep analysis unit (130).

[0076] A computing device (12) includes at least one processor (14), a computer-readable storage medium (16), and a communication bus (18). The processor (14) may cause the computing device (12) to operate according to the exemplary embodiments mentioned above. For example, the processor (14) may execute one or more programs stored in the computer-readable storage medium (16). The one or more programs may include one or more computer-executable instructions, which, when executed by the processor (14), may be configured to cause the computing device (12) to perform operations according to the exemplary embodiments.

[0077] A computer-readable storage medium (16) is configured to store computer-executable instructions or program code, program data, and / or other suitable forms of information. A program (20) stored in the computer-readable storage medium (16) includes a set of instructions executable by the processor (14). In one embodiment, the computer-readable storage medium (16) may be a memory (volatile memory such as random access memory, non-volatile memory, or a suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, any other form of storage medium that is accessible by the computing device (12) and capable of storing desired information, or a suitable combination thereof.

[0078] A communication bus (18) interconnects various other components of the computing device (12), including the processor (14) and computer-readable storage media (16).

[0079] The computing device (12) may also include one or more input / output interfaces (22) that provide interfaces for one or more input / output devices (24) and one or more network communication interfaces (26). The input / output interfaces (22) and the network communication interfaces (26) are connected to the communication bus (18). The input / output devices (24) may be connected to other components of the computing device (12) via the input / output interfaces (22). Exemplary input / output devices (24) may include input devices such as pointing devices (such as a mouse or a trackpad), a keyboard, a touch input device (such as a touchpad or a touchscreen), a voice or sound input device, various types of sensor devices and / or photographing devices, and / or output devices such as display devices, printers, speakers and / or network cards. The exemplary input / output devices (24) may be included within the computing device (12) as a component constituting the computing device (12), or may be connected to the computing device (12) as a separate device distinct from the computing device (12).

[0080]

[0081] Figure 6 is a flowchart illustrating a disease prediction method based on sleep analysis according to one embodiment of the present invention. Here, each step of Figure 6 may be performed by a disease analysis device.

[0082] Referring to Figure 6, the disease analysis device can remotely measure the heartbeat or respiration of a sleeper using a biosignal sensor installed in a bedroom in a senior citizen's home to generate biosignal data (S110). Here, the biosignal sensor can be installed on the ceiling or side wall of the bedroom where the sleeper sleeps, and can irradiate radar signals to the sleeper. At this time, the biosignal sensor can be installed vertically above the sleeper's chest, and can irradiate radar signals to the sleeper's chest.

[0083] Afterwards, the biosignal sensor can measure the sleeper's heart rate and breathing rate by receiving radar signals reflected from the sleeper's chest. The biosignal sensor can transmit the measured biosignal data, such as the sleeper's heart rate and breathing rate, to the sleep analysis unit.

[0084] Additionally, the disease analysis device can remotely measure a sleeper's posture using a posture detection sensor installed in a bedroom within a senior housing unit, thereby generating posture data (S120). Specifically, along with the biosignal sensor, the posture detection sensor can be installed on the ceiling or side wall of the bedroom where the sleeper sleeps, and the posture detection sensor can be installed in a direction facing the sleeper in bed.

[0085] The posture detection sensor may include a posture sensor and a fall sensor. The posture sensor may be installed facing the bed to detect the sleeper's posture on the bed. In other words, the posture sensor can distinguish and recognize the sleeper's sleeping posture, such as lying down on the bed, sitting up on the bed, or standing up from the bed.

[0086] Additionally, fall sensors can be installed around the bed, facing preset fall risk areas, and can detect falls where the sleeper falls from the bed. The posture detection sensor can use the posture sensor and fall sensor to detect the sleeper's posture or falls, generating posture data. The generated posture data can then be transmitted to the sleep analysis unit.

[0087] Thereafter, the disease analysis device analyzes the sleep pattern of the sleeper based on the biosignal data using the sleep analysis unit, and if a disease-suspicious pattern is determined from the sleep pattern, an alarm message can be generated (S130).

[0088] Since the sleep analysis unit analyzes sleep patterns from bio-signal data while the sleeper is sleeping, it must first determine whether the sleeper is currently sleeping. To this end, the sleep analysis unit can receive a preset sleep time from the sleeper, in which case it can collect bio-signal data during the input sleep time to analyze the sleep pattern. In other words, the sleep time is a preset value set by the sleeper as his or her own sleep time. Therefore, if the sleeper sets the sleep time to be from 9 PM to 4 AM, the sleep analysis unit can collect bio-signal data between 9 PM and 4 AM and analyze the sleeper's sleep pattern based on this.

[0089] In addition, depending on the embodiment, the sleep time of the sleeper may be estimated based on the change in the brightness in the bedroom by using a brightness sensor installed in the bedroom, or the sleep time may be estimated based on the on / off operation of the lights in the bedroom, or the sleep time of the sleeper may be estimated based on the charging and uncharging time of the mobile communication terminal of the sleeper, or the sleep time of the sleeper may be estimated by combining the above-described sleep time estimation methods.

[0090] Meanwhile, the sleep analysis unit can determine whether there are disease-suspicious patterns corresponding to various target diseases such as Alzheimer's disease, Parkinson's disease, stroke, and myocardial infarction based on the sleep pattern of the sleeper.

[0091] In some embodiments, the sleep analysis unit can analyze a sleeper's sleep patterns over time to identify regular patterns. If an irregular pattern deviates from the regular pattern, the sleep analysis unit can determine the presence of a suspicious pattern for disease. Since the regular pattern may appear differently for each sleeper, the sleep analysis unit can recognize a personalized regular pattern for each sleeper.

[0092] Additionally, depending on the embodiment, the sleep analysis unit may include an analysis model, and the analysis model may be generated by learning the sleep patterns of a number of patients with the target disease as training data. In other words, after training the analysis model by setting the sleep patterns of patients with the target disease as correct data, by inputting the sleep pattern of the sleeper into the analysis model, it is possible to determine which target disease the sleep pattern corresponds to and provide the information.

[0093] For example, by inputting sleep patterns into an analysis model, it is possible to calculate and provide a score indicating the degree to which the sleep pattern resembles the sleep pattern corresponding to each target disease. In this case, if the target disease has a score above a preset value, the sleeper is likely to have that disease. Here, the analysis model can be implemented based on various machine learning models, deep learning models, neural network models, etc.

[0094] Meanwhile, the sleep analysis unit may not diagnose an actual disease, but rather only informs the sleeper of a high risk of developing the disease. In other words, it may predict a high likelihood of developing the disease and recommend that the sleeper visit a hospital or other similar facility for diagnosis.

[0095] Additionally, sleepers may not remain in a continuous state of sleep throughout their sleep period, and may wake up or leave their position during sleep. In this case, noise may be present in the biosignal data collected, and noise corresponding to non-sleep states needs to be removed.

[0096] In some embodiments, if bio-signal data is measured below a threshold for a set period of time, the sleep analysis unit may determine that the sleeper has left the bed. That is, if the sleeper leaves the bed, the heart rate or respiration rate measured by the bio-signal sensor may show values ​​close to zero. Since a person's heart rate and respiration rate do not suddenly and simultaneously drop below the threshold, the sleep analysis unit may determine that the sleeper has left the bed in this case, and may process the bio-signal data measured during the leave as noise.

[0097] Additionally, depending on the embodiment, it is also possible to determine whether a sleeper has left the bed based on posture data generated by the posture detection sensor. Specifically, if the sleeper's posture data during the sleep period corresponds to a posture other than the sleeping posture, the sleep analysis unit can determine that the sleeper has left the bed and process all corresponding biosignal data as noise.

[0098] Afterwards, the sleep analysis unit can send an alarm message to a wall pad installed in the senior home or a pre-registered mobile device. Specifically, if a suspected disease pattern is identified, an alarm message can be generated to notify the individual. The sleep analysis unit can deliver the alarm message in various ways. In some embodiments, the alarm message can be displayed on a wall pad installed in the senior home, allowing the individual or their caregiver to easily check the information.

[0099] In addition, if the mobile phone numbers of the sleeper, guardian, attending physician, and other related persons are registered in advance in the disease prediction device, the sleep analysis unit can recommend a hospital visit, etc. to the sleeper in relation to the target disease by sending an alarm message to the registered phone number.

[0100]

[0101] The present invention described above can be implemented as computer-readable code on a medium recording a program. The computer-readable medium may be one that continuously stores a computer-executable program or one that temporarily stores it for execution or download. Furthermore, the medium may be a variety of recording or storage means, including a single or multiple hardware components, and is not limited to media directly connected to a computer system, but may also be distributed across a network. Examples of the medium include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and ROM, RAM, flash memory, and other media configured to store program instructions. Furthermore, other examples of media include recording or storage media managed by app stores that distribute applications, sites that supply or distribute various software, servers, etc. Therefore, the above detailed description should not be construed as limiting in all respects, but rather as illustrative. The scope of the present invention should be determined by a reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention.

[0102]

[0103] The present invention is not limited to the above-described embodiments and the attached drawings. It will be apparent to those skilled in the art that components of the present invention can be substituted, modified, and altered without departing from the technical spirit of the present invention.

Claims

1. In a disease prediction device based on sleep analysis installed in a senior citizen's home, A biosignal sensor installed in the bedroom to remotely measure the sleeper's heart rate or breathing to generate biosignal data; and A disease prediction device based on sleep analysis, comprising a sleep analysis unit that analyzes the sleep pattern of the sleeper based on the bio-signal data and generates an alarm message when a disease-suspicious pattern is determined from the sleep pattern.

2. In the first paragraph, the biosignal sensor A disease prediction device based on sleep analysis, which is installed on the ceiling or side wall of the bedroom to irradiate radar signals to the sleeper and receive reflected radar signals to measure the sleeper's heart rate or breathing rate.

3. In paragraph 1, the sleep analysis unit By collecting the bio-signal data during the preset sleeping time and analyzing the sleep pattern of the sleeper, A disease prediction device based on sleep analysis, wherein the above sleep time is set based on the sleeper's settings, changes in the lighting level in the bedroom, and the on / off operation of the lights in the bedroom.

4. In paragraph 1, the sleep analysis unit A disease prediction device based on sleep analysis, which determines a disease suspicion pattern for at least one of Alzheimer's disease, Parkinson's disease, stroke, and myocardial infarction from the above sleep pattern.

5. In paragraph 4, the sleep analysis unit A disease prediction device based on sleep analysis, comprising an analysis model created by learning the sleep patterns of patients with at least one of the diseases Alzheimer's disease, Parkinson's disease, stroke, and myocardial infarction as learning data.

6. In paragraph 1, the sleep analysis unit A disease prediction device based on sleep analysis, wherein if the bio-signal data is measured to be less than a threshold value for a set period of time, the sleeper is determined to have left the sleeper, and the bio-signal data measured during the sleeper's leaving the sleeper is processed as noise.

7. In paragraph 1, It further includes a posture detection sensor installed in the above bedroom to remotely measure the posture of the sleeper and generate posture data, The above sleep analysis department A disease prediction device based on sleep analysis, wherein if the posture data corresponds to a posture other than a sleeping posture within a preset sleep time, the sleeper is determined to have left the sleeper, and the bio-signal data measured during the sleeper's leaving the sleeper is processed as noise.

8. In paragraph 1, the sleep analysis unit A disease prediction device based on sleep analysis that transmits the alarm message to a wall pad installed in the senior citizen's home or a pre-registered mobile communication terminal.

9. A step of remotely measuring the heartbeat or respiration of a sleeping person using a bio-signal sensor installed in a bedroom in a senior citizen's home to generate bio-signal data; and A disease prediction method based on sleep analysis, comprising a step of analyzing the sleep pattern of the sleeper based on the bio-signal data using a sleep analysis unit, and generating an alarm message when a disease-suspicious pattern is determined from the sleep pattern.

10. In the 9th paragraph, the biosignal sensor A disease prediction method based on sleep analysis, which is installed on the ceiling or side wall of the bedroom to irradiate radar signals to the sleeper and receive reflected radar signals to measure the sleeper's heart rate or breathing rate.

11. In paragraph 9, the step of generating the notification message is By collecting the bio-signal data during the preset sleeping time and analyzing the sleep pattern of the sleeper, A disease prediction method based on sleep analysis, wherein the above sleep time is set based on the sleeper's settings, changes in the lighting level in the bedroom, and the on / off operation of the lights in the bedroom.

12. In paragraph 9, the step of generating the notification message is A disease prediction method based on sleep analysis, which determines a disease suspicion pattern for at least one of Alzheimer's disease, Parkinson's disease, stroke, and myocardial infarction from the above sleep pattern.

13. In the 12th paragraph, the step of generating the notification message A disease prediction method based on sleep analysis, wherein the disease-suspicious pattern is determined by using an analysis model created by learning the sleep patterns of patients with at least one of the above-mentioned Alzheimer's disease, Parkinson's disease, stroke, and myocardial infarction as learning data.

14. In paragraph 9, the step of generating the notification message is A disease prediction method based on sleep analysis, wherein if the bio-signal data is measured to be less than a threshold value for a set period of time, the sleeper is determined to have left the sleeper, and the bio-signal data measured during the sleeper's leaving the sleeper is processed as noise.

15. In paragraph 9, It further includes a step of remotely measuring the sleeping person's posture using a posture detection sensor installed in a bedroom in a senior citizen's home to generate posture data. The steps to generate the above notification message are A disease prediction method based on sleep analysis, wherein if the posture data corresponds to a posture other than a sleeping posture within a preset sleep time, the sleeper is determined to have left the bed, and the bio-signal data measured during the sleeper's leaving the bed is processed as noise.

16. In paragraph 9, the step of generating the notification message A disease prediction method based on sleep analysis, wherein the alarm message is transmitted to a wall pad installed in the senior citizen's home or a pre-registered mobile communication terminal.

17. A computer program stored in a medium to perform a disease prediction method based on sleep analysis according to any one of claims 9 to 16, in combination with hardware.

Images