WO2015008936A1 - 습관을 이용한 진단 장치 및 진단 관리 장치와 그를 이용한 진단 방법 - Google Patents
습관을 이용한 진단 장치 및 진단 관리 장치와 그를 이용한 진단 방법 Download PDFInfo
- Publication number
- WO2015008936A1 WO2015008936A1 PCT/KR2014/005162 KR2014005162W WO2015008936A1 WO 2015008936 A1 WO2015008936 A1 WO 2015008936A1 KR 2014005162 W KR2014005162 W KR 2014005162W WO 2015008936 A1 WO2015008936 A1 WO 2015008936A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- habit
- diagnostic
- diagnosis
- risk group
- Prior art date
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
- A61B5/6898—Portable consumer electronic devices, e.g. music players, telephones, tablet computers
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/63—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for local operation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/08—Elderly
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2560/00—Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
- A61B2560/02—Operational features
- A61B2560/0242—Operational features adapted to measure environmental factors, e.g. temperature, pollution
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
- A61B2562/02—Details of sensors specially adapted for in-vivo measurements
- A61B2562/0204—Acoustic sensors
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
- A61B2562/02—Details of sensors specially adapted for in-vivo measurements
- A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1112—Global tracking of patients, e.g. by using GPS
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4836—Diagnosis combined with treatment in closed-loop systems or methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
Definitions
- Lifestyle disease is a disease that can be caused by bad lifestyle, and there is a close relationship between lifestyle and the occurrence of the disease. Therefore, the medical staff will identify the lifestyle of the patient through an interview with the patient to diagnose the possibility of the disease or the progress of the disease.
- Dementia in which multiple cognitive impairments caused by acquired brain diseases, causes difficulties in daily or social life, is a typical lifestyle disease. Since dementia is closely related to lifestyle, medical staff can determine the possibility of developing dementia through an objective understanding of the patient's lifestyle. In addition, in general, dementia is steadily worsening, so the medical staff can diagnose the progression of dementia early through objective grasp of the patient's lifestyle, and take appropriate measures at the early stage of dementia progression.
- lifestyle-related diseases are closely related to lifestyles of patients, and therefore, collection of objective lifestyles is very important.
- grasping the lifestyle of the patient is entirely dependent on the memory of the patient, there is a problem that the accuracy and reliability of lifestyle collection is low.
- a diagnosis device and a diagnosis management device for diagnosing whether a user is a risk group of a disease and a diagnosis method using the same are provided based on the collected habit data.
- a diagnosis apparatus using a habit may analyze a sensor data detected from at least one sensor and generate a habit data of a user, and compare the generated habit data with diagnosis data that is lifestyle data of a normal person. It includes a diagnostic unit for diagnosing whether or not a risk group.
- the habit analysis unit may further include a log analysis module for generating the habit data by analyzing the log data stored in the usage log.
- the habit analysis unit may further include an input analysis module configured to generate the habit data by analyzing the data input from the user.
- the habit analysis unit may generate the habit data in a normalized form.
- the diagnostic unit may further include a search module for searching for diagnostic data matching the user's profile.
- diagnosis unit may diagnose as a risk group of the disease when the difference value between the habit data and the diagnostic data is greater than or equal to a preset threshold.
- the diagnostic apparatus may further include a storage unit for storing habit data generated at predetermined cycles.
- the diagnosis unit may further include a trend analysis module for determining whether the difference between the stored habit data and the diagnostic data is increasing, and if it is determined that the difference is increasing, the diagnosis may be diagnosed as a risk group of the disease.
- the diagnostic unit may further include a correlation analysis module that converts the change of habit data stored in the storage unit into a sequence, and analyzes the correlation between the converted sequence and the sequence indicating the change of habit data of the patient. If the threshold is more than a predetermined threshold can be diagnosed as a risk group of the disease.
- diagnosis apparatus may further include an action unit configured to provide information about a disease to a user or to notify a medical staff or a guardian of diagnosis of a risk group, when the diagnosis apparatus is diagnosed to correspond to a risk group.
- action unit configured to provide information about a disease to a user or to notify a medical staff or a guardian of diagnosis of a risk group, when the diagnosis apparatus is diagnosed to correspond to a risk group.
- a diagnosis managing apparatus using habits may analyze a behavior data received from a diagnosis apparatus to generate habit data of a user, and compare the generated habit data with diagnosis data, which is a lifestyle data of a normal person, to identify a disease. It may include a diagnostic management to diagnose whether the risk group.
- the behavior data received from the diagnostic apparatus may be one or more of sensor data detected through one or more sensors of the diagnostic apparatus, data directly input by a user through the diagnostic apparatus, and log data stored in a usage log of the diagnostic apparatus.
- the diagnostic management apparatus may further include a habit data storage unit for storing habit data generated at predetermined cycles.
- the diagnosis management unit may further include a trend analysis module for determining whether a difference value between the habit data stored in the habit data storage unit and the diagnostic data is increasing, and if it is determined that the difference value is increased, the diagnosis management unit may diagnose the risk group of the disease.
- the diagnostic management unit may further include a correlation analysis module that converts the change of habit data stored in the habit data storage into a sequence, and analyzes the correlation between the converted sequence and the sequence indicating the change of habit data of the patient. In other words, if the correlation is greater than or equal to a predetermined threshold, the risk group can be diagnosed.
- the diagnosis management apparatus may further include an action management unit configured to provide information regarding a disease to a user or notify a medical staff or a guardian of diagnosis of a risk group when diagnosed as a risk group.
- an action management unit configured to provide information regarding a disease to a user or notify a medical staff or a guardian of diagnosis of a risk group when diagnosed as a risk group.
- a diagnosis method using habits includes searching for diagnosis data which is lifestyle data of a normal person matching a user profile, and comparing the detected diagnosis data with habit data to diagnose whether the disease corresponds to a risk group of a disease. can do.
- the diagnostic method using the lifestyle may further include generating habit data based on the behavior data.
- the behavior data may be one or more of sensor data detected through one or more sensors, data received by a user, or log data stored in a usage log.
- the generating of the habit data may further include normalizing the habit data.
- the step of diagnosing the risk group may be diagnosed as a risk group of the disease if the difference value between the habit data and the diagnostic data is greater than or equal to a preset threshold.
- the generating of the habit data may further include storing the generated habit data every predetermined period.
- the diagnosing step may further include determining whether a difference value between the stored habit data and the diagnostic data is increasing, and when the difference value increases, the diagnosis may correspond to a risk group.
- the diagnosing step may further include converting the change of the stored habit data into a sequence, and analyzing the correlation between the converted sequence and the sequence representing the change of the lifestyle data of the patient. If is greater than or equal to the preset threshold, the risk group can be diagnosed.
- diagnosis method using the habit may further include providing information on the disease to the user of the diagnosis apparatus or notifying the medical staff or guardian of the diagnosis of the risk group, when diagnosed as a risk group.
- habit data may be used as a reference for the treatment and symptom relief of disease.
- FIG. 1 is a block diagram showing an example of a diagnosis system using a habit.
- FIG. 2 is a block diagram illustrating a diagnosis apparatus using a habit, according to an exemplary embodiment.
- FIG. 3 is a block diagram illustrating a sensor unit according to an exemplary embodiment.
- FIG. 4 is a block diagram illustrating a habit analysis unit according to an exemplary embodiment.
- FIG. 5 is a block diagram illustrating a diagnosis unit according to an exemplary embodiment.
- FIG. 6 is a block diagram illustrating a diagnostic management apparatus according to another embodiment.
- FIG. 7 is a block diagram for explaining a habit managing unit according to another exemplary embodiment.
- FIG. 8 is a block diagram illustrating a diagnosis managing unit according to another exemplary embodiment.
- FIG. 9 is a flowchart illustrating a diagnosis method using a habit, according to an exemplary embodiment.
- FIG. 10 is a diagram for describing a method of generating habit data, according to an exemplary embodiment.
- FIG. 11 is a flowchart illustrating an embodiment of step S103 of FIG. 9.
- step S103 of FIG. 12 is a view for explaining an embodiment of step S103 of FIG.
- FIG. 13 is a flowchart illustrating another embodiment of step S103 of FIG. 9.
- step S103 of FIG. 9 is a flowchart for explaining another embodiment of step S103 of FIG. 9.
- FIG. 15 is a view for explaining another embodiment of step S103 of FIG. 9.
- FIG. 1 is a block diagram showing an example of a diagnosis system using a habit.
- the diagnostic system of FIG. 1 collects user's behavior using various diagnostic devices 100 to analyze the user's habits and diagnoses whether the risk group is a risk group based on the analyzed habits.
- the diagnosis system may perform various preventive measures for disease prevention when diagnosed as a risk group of the disease.
- the risk group should be understood as a broad concept including not only a high risk group of a disease, but also a group showing early symptoms of the disease.
- the disease is a disease that can be caused by bad lifestyle, and includes a disease in which the onset of the habit and the disease is closely related.
- diseases include not only dementia but also diseases in which the development of habits and diseases is closely related, such as adult diseases such as diabetes and hypertension.
- a diagnosis system includes a diagnosis apparatus 100 and a diagnosis management apparatus 200.
- the diagnostic apparatus 100 collects the user's behavior through various methods and analyzes the user's habit based on the collected behavior.
- habits generally refer to recurring patterns of behavior.
- the diagnosis apparatus 100 diagnoses whether a disease is a risk group based on the analyzed habit, and performs preventive measures when diagnosed as a risk group.
- the diagnostic apparatus 100 may request and receive data required for a series of diagnosis and preventive measures from the diagnostic management apparatus 200, and may transmit data to the diagnostic management apparatus 200 as necessary.
- the diagnostic management apparatus 200 may provide data to the diagnostic apparatus 100 according to a request of the diagnostic apparatus 100.
- the diagnostic management apparatus 200 may receive and manage various data from the diagnostic apparatus 100.
- the diagnostic management apparatus 200 may be a cloud computing device.
- the diagnostic management apparatus 200 may instead perform some operations performed by the diagnostic apparatus 100 and transmit the result to the diagnostic apparatus 100.
- the diagnostic management apparatus 200 may receive the collected behaviors, analyze the user's habits based on the received behaviors, and diagnose whether the risk group is a risk group based on the analyzed habits.
- the diagnosis management unit 230 may perform necessary preventive measures when diagnosed as a risk group.
- the communication network 300 may use various types of communication networks, and for example, an IP network capable of transmitting and receiving large amounts of data based on an Internet protocol (IP), and a structure in which different networks are integrated based on the Internet protocol.
- IP Internet protocol
- Various types of communication networks such as ALL-IP network, including Wibro (Wireless Broadband) and Wi-Fi, Wireless Personal Area Network (WPAN), Mobile and Wired Network, and Satellite Network Can be used.
- ALL-IP network including Wibro (Wireless Broadband) and Wi-Fi, Wireless Personal Area Network (WPAN), Mobile and Wired Network, and Satellite Network Can be used.
- WPAN Wireless Personal Area Network
- Mobile and Wired Network Wireless Personal Area Network
- Satellite Network Satellite Network
- FIG. 2 is a block diagram illustrating a diagnosis apparatus using a habit, according to an exemplary embodiment.
- the diagnostic apparatus 100 of FIG. 2 is a portable terminal such as a mobile communication terminal, a smart phone, a portable media player (PMP), a personal digital assistant (PDA), a tablet PC, or the like. It is preferable to use an easy device, but is not limited thereto. However, when using a device having a variety of sensors, such as a smart phone, there is an advantage that can generate habit data by collecting behavioral data based on hardware and software included in the existing smart phone.
- the diagnosis apparatus 100 using the habit includes a sensor unit 110, an input unit 120, a log management unit 130, a habit analysis unit 140, a storage unit 150, and a diagnosis unit 160. And an action unit 170.
- the diagnostic apparatus 100 of FIG. 2 collects behavioral data of the user.
- the diagnosis apparatus 100 may generate the habit data by analyzing the collected behavior data to diagnose whether it corresponds to a risk group of the disease.
- the diagnosis apparatus 100 may also perform preventive measures when the user is diagnosed as being at risk.
- Behavior data is data about the behavior of the user throughout the life, such as movement, exercise, sleep, meals, emotions of the user collected by the diagnostic device (100).
- the behavior data may be sensor data detected by the sensor unit 110, data input by a user, or log data stored in the usage log 131.
- Habit data is data about a habit of a user generated by analyzing behavior data.
- One habit data may have a plurality of habit factors.
- one habit data may have eating habits, exercise habits, and emotional states as factors.
- one habit factor of the habit data may be generated by analyzing a plurality of behavior data.
- the exercise habit may be generated by analyzing a plurality of behavior data (data input and data sensed by the sensor) together.
- each habit factor of the habit data may be different depending on the kind of disease, the kind of diagnosis apparatus, and the like.
- the sensor unit 110 generates sensor data. More specifically, the sensor unit 110 detects a change of the external information or the external information of the diagnostic apparatus and generates sensor data based on the detected external information or the change of the external information.
- the input unit 120 may receive data from a user.
- the input unit 120 should be understood as a broad concept including not only an input means such as a keypad and a touch screen but also an input means such as a camera and a microphone. Therefore, the user may input data by voice or an image photographed by a camera as data.
- the input unit 120 may receive data in the form of a voice from the user, or receive data in the form of an image of the expression of the user captured by the camera.
- the input unit 120 may receive a response to a preset query in order to collect a user's behavior. In this case, the input unit 120 may receive a response through voice or may receive an image.
- the log manager 130 manages log data.
- the log manager 130 may store the monitored log data.
- the log manager 130 may further include a usage log 131 for storing log data.
- the log data refers to information about an event occurring in the diagnostic apparatus over time.
- the diagnostic device is a smartphone
- the log data refers to information about various events occurring in the smartphone, such as a user's call history, a history of sending / receiving an inquiry, an internet search history, an application usage history, and the like.
- the habit analysis unit 140 analyzes the behavior data to generate habit data of the user. More specifically, the habit analysis unit 140 based on behavior data such as sensor data detected by the sensor unit 110, data received from the user through the input unit 120, or log data stored in the usage log. We can generate habit data by analyzing the repetitive behavior of.
- the habit analyzer 140 may analyze one or more behavior data to generate habit data having one or more habit factors. For example, if one habit data has a eating habit, an exercise habit, and an emotional state, the habit analyzing unit 140 analyzes behavior data about a meal input from a user to detect factors related to eating habits through an acceleration sensor.
- Factors related to exercise habits may be generated based on the acquired sensor data, and factors related to the emotional state of the user may be generated based on voice data of the user input in response to a phone call.
- the habit analysis unit 140 may analyze a plurality of behavior data to generate one factor of the habit data.
- the storage unit 150 may store and manage various data necessary for operating the diagnostic apparatus.
- the storage unit 150 may store the habit data generated at regular intervals.
- the storage unit 150 may store behavior data.
- the storage unit 150 may store a sequence indicating a change of each element of the diagnosis data or the patient's habit data.
- the storage unit 150 may store data for various measures for preventing disease.
- the diagnosis unit 160 may diagnose whether a disease corresponds to a risk group based on habit data. More specifically, the diagnosis unit 160 compares the diagnosis data and the habit data to diagnose whether or not corresponding to the risk group of the disease.
- the diagnostic data refers to habit data that serves as a criterion for determining whether the disease is a risk group. Diagnostic data may be a habit of a normal person. In addition, diagnostic data may vary in the user's profile (eg, gender, age, race, nationality).
- the diagnostic data may be stored in the storage unit 150 of the diagnostic apparatus, or may be provided from the diagnostic management apparatus 200 of FIG. 1.
- the diagnosis unit 160 may determine whether it is a risk group by analyzing a correlation between a sequence indicating a change in lifestyle data of the patient and a sequence indicating a change in habit data of the user.
- the measurer 170 performs various measures for disease prevention.
- the measurer 170 may provide the user with information about various diseases such as a criterion for diagnosing a risk group, a cause of the disease, a method for preventing the disease, and a method for alleviating the progress of the disease.
- the information about the disease may be stored in the storage unit 150, may be provided from the diagnostic management device (200 of FIG. 1).
- the measurer 170 may notify the medical staff or guardian whether the risk group is diagnosed.
- the storage unit 150 may store information about a medical staff or a guardian.
- the measurer 170 may provide the medical staff with habit data generated by the habit analyzer.
- the measurer 170 may notify the guardian, the medical staff through the diagnosis management device (200 in Figure 1) whether the risk group diagnosis of the disease.
- FIG. 3 is a block diagram illustrating a sensor unit according to an exemplary embodiment.
- the sensor unit of FIG. 2 generates sensor data by detecting external information of the diagnostic apparatus or changes in external information.
- 3 illustrates only some of various sensors that may be included in the sensor unit, and the sensor that may correspond to the sensor unit is not limited to the sensors illustrated in FIG. 3.
- the sensor unit includes a position sensor 111, an acceleration sensor 113, an illuminance sensor 115, an acoustic sensor 117, and a motion sensor 119.
- the position sensor 111 detects the position of the diagnostic device to generate sensor data. More specifically, the position sensor 111 may detect the position of the diagnostic apparatus and generate sensor data related to the change of the position environment based on the detected position for a certain period of time.
- the position sensor 111 may be a global positioning system (GPS).
- the acceleration sensor 113 detects an acceleration change of the diagnostic device to generate sensor data. More specifically, the acceleration sensor 113 may detect a change in acceleration, vibration, shock, and the like of the diagnostic apparatus, and generate sensor data related to a change in acceleration or the like based on the detected change.
- the illuminance sensor 115 detects the brightness around the diagnostic device to generate sensor data. More specifically, the illuminance sensor 115 detects the brightness around the diagnostic apparatus and generates sensor data regarding the brightness based on the detected brightness.
- the acoustic sensor 117 detects sound around the diagnostic device to generate sensor data. More specifically, the acoustic sensor 117 may detect sound around the diagnostic apparatus and generate sensor data related to noise based on the detected sound. In addition, the acoustic sensor 117 detects a user's phone call voice and may generate sensor data based on the detected voice. In this case, the generated sensor data is used to generate habit data related to emotion through machine learning. Can be.
- the motion sensor 119 detects movement around the diagnostic device to generate sensor data. More specifically, the motion sensor 119 may detect the movement of the attention of the diagnostic apparatus, and detect the sensor data based on the detected movement.
- FIG. 4 is a block diagram illustrating a habit analysis unit according to an exemplary embodiment.
- the habit analysis unit 140 includes an input analysis module 141 and a log analysis module 143.
- the habit analyzing unit 140 analyzes the user's habits from behavior data such as sensor data detected by the sensor unit, data directly input by the user, or log data stored in the usage log to generate respective habit factors of the habit data.
- Habit analysis unit 140 may analyze the behavior data by machine learning technology.
- machine learning refers to a technique for analyzing new data based on properties that are already known through learning data.
- the habit data generated by the habit analysis unit 140 may be generated in a normalized form. In this case, normalization means correcting in consideration of environmental differences in order to be able to compare diagnosis data and habit data.
- each habit factor of habit data may be normalized to have a value between 0 and 1. Such normalization makes it easier to compare with the diagnostic data and facilitate the management of habit data.
- the habit analysis unit 140 may store the habit data generated every certain period.
- the habit analysis unit 140 may further have an input analysis module 141.
- the input analysis module 141 analyzes the data input from the user to generate habit data.
- the input analysis module 141 may generate the habit factor of the habit data related to the emotion of the user by analyzing the image data input through the camera with the voice input through the microphone.
- the input data may be a response to a preset query to collect the user's activity.
- the habit analysis unit 140 may further have a log analysis module 143.
- the log analysis module 143 analyzes log data stored in the usage log to generate habit data.
- the log analysis module 143 may generate habit data by analyzing log data such as a call history, a history of sending and receiving a history, an internet search history, an application usage history, and the like.
- the habit analyzer 140 may generate a habit factor of habit data related to movement by analyzing a distance traveled by the user for one day based on sensor data related to the position detected from the position sensor 111.
- the habit analysis unit 140 may generate sensory factors related to the acceleration change detected by the acceleration sensor 113 to generate habit factors of the habit data related to the exercise. More specifically, the habit analysis unit 140 analyzes the sensor data by machine learning technology to classify the acceleration data into a specific state (walking, running, standing), and the habit of the habit data related to the exercise based on the classified specific state. You can create arguments.
- the habit analyzer 140 may generate sensor data related to sleep by analyzing sensor data related to brightness detected by the illumination sensor 115.
- the habit analysis unit 140 analyzes the sensor data using a machine learning technique to classify the illumination data into a specific state (before sleep, during sleep, after waking up, etc.), and based on the classified specific state, habit data regarding the user's sleep Can create a habit factor.
- the habit analysis unit 140 analyzes sensor data related to the movement detected by the motion sensor 119 and sensor data related to the sound detected by the acoustic sensor 117 to determine the quality of sleep of the user.
- a habit factor of habit data can be generated.
- the habit analysis unit 140 may analyze a plurality of behavior data together to generate one factor of the habit data.
- the input analysis module 141 may generate a habit factor of habit data related to the user's diet by analyzing data on a meal amount, smoking amount, and drinking amount input by the user through a preset query. In addition, the input analysis module 141 may analyze the image data of the food photographed by the user with the camera and generate a habit factor of the habit data related to the user's diet.
- the log analysis module 143 analyzes the contents in the text message according to the machine learning technique to collect habit factors of the habit data related to the user's emotion, or analyzes the telephone call history to determine the habit factors of the habit data related to the social activity of the user. You can also collect.
- the log analysis module 143 may generate a habit factor of habit data related to a cognitive activity of the user by analyzing an internet search history or an application usage history.
- the log analysis module 143 may generate lifestyle data by analyzing payment information included in the text message.
- FIG. 5 is a block diagram illustrating a diagnosis unit according to an exemplary embodiment.
- the diagnosis unit 160 compares previously stored diagnostic data and habit data to diagnose a risk group. More specifically, the diagnosis unit 160 calculates a sum of difference values of each habit factor of the habit data and each habit factor of the diagnostic data, and if the sum of the calculated difference values of each habit factor is equal to or greater than a preset threshold, the risk group It can be diagnosed as On the other hand, the diagnosis unit 160 may exclude the habit factor having a null value in the calculation of the difference value. In addition, when there are a plurality of habit data of the user generated at each predetermined cycle, the diagnosis unit 160 may diagnose a risk group using an arithmetic mean.
- diagnosis unit 160 may further include a trend analysis module 161.
- the trend analysis module 161 may determine whether the difference value between the habit data and the diagnostic data is increasing. More specifically, the trend analysis module 161 determines whether the sum of the difference values between each habit factor of the habit data and each habit factor of the diagnostic data is increasing. In this case, the diagnosis unit 160 may diagnose the risk group when the sum of the difference values of the trend analysis module 161 is determined to increase.
- the diagnosis unit 160 may further include a correlation analysis module 163.
- the correlation analysis module 163 analyzes a correlation between each habit factor of habit data and each habit factor of habit data of a disease patient. In this case, the diagnosis unit 160 may diagnose a risk group when the analysis result of the correlation analysis module 163 is greater than or equal to a preset threshold. To analyze the correlation, the correlation analysis module 163 converts the change trend of each element of the plurality of habit data into a sequence form, and compares the converted sequence with the sequence representing the change trend of each element of the patient's habit data. Can be. In this case, the correlation analysis module 163 may analyze the correlation by regression analysis of the habit data of the user and the habit data of the patient.
- the diagnosis unit 160 may further include a search module 165.
- the search module 165 detects a user's profile and searches for diagnostic data matching the detected user's profile.
- the search module 165 detects a user profile such as age, gender, race, nationality, etc. of the diagnostic apparatus user, and detects diagnostic data that matches the detected profile.
- FIG. 6 is a block diagram illustrating a diagnostic management apparatus according to another embodiment.
- the diagnostic management apparatus 200 includes a communication manager 210, a habit manager 220, a diagnostic manager 230, and an action manager 240.
- the diagnostic management apparatus 200 of FIG. 6 generates habit data by analyzing behavior data received from the diagnostic apparatus.
- the diagnosis management apparatus 200 may diagnose a risk group based on habit data, and may also perform preventive measures when diagnosed as a risk group.
- the communication manager 210 transmits and receives data through a communication network.
- the communication manager 210 may receive behavior data from a diagnostic device connected to a communication network.
- the communication manager 210 may transmit various data to the diagnostic apparatus through a communication network.
- the habit manager 220 analyzes behavior data received through the communication manager 210 to generate habit data of the user.
- the habit management unit 220 generates individual habit factors of habit data by analyzing repetitive behaviors of the user based on behavior data such as sensor data detected by the sensor, data input from the user, or log data stored in the usage log. can do. Meanwhile, the habit manager 220 may store the generated habit data in the habit data storage unit.
- the diagnosis management unit 230 may diagnose whether the disease corresponds to a risk group of the disease based on the habit data. More specifically, the diagnosis management unit 230 may diagnose the diagnosis data and the habit data as being at risk of a disease when the difference value is greater than or equal to a preset criterion.
- the diagnostic data is habit data that is a criterion for determining a disease, and may be habit data of a normal person. Meanwhile, the diagnostic data may be stored in the diagnostic data storage 260.
- the action manager 240 performs various measures for disease prevention.
- the action manager 240 may provide the user with information about various diseases, such as a criterion for diagnosing a risk group, a cause of the disease, a method of preventing the disease, and a method of alleviating the progress of the disease.
- the information about the disease may be stored in the preventive measures storage unit 270.
- the action manager 240 may notify the registered guardian or medical staff whether the risk group of the disease is diagnosed.
- the habit data storage unit 250 stores habit data.
- the habit data is data about a habit of the user generated by analyzing the behavior data.
- One habit data may have a plurality of habit factors.
- One habit factor of habit data may be generated by analyzing a plurality of behavioral data.
- the habit data storage unit 250 may sequentially store the habit data generated for each preset period.
- the diagnostic data storage unit 260 stores diagnostic data.
- the diagnostic data refers to habit data that serves as a criterion for determining whether the disease corresponds to a risk group of a disease.
- the diagnostic data storage unit 260 may store a plurality of diagnostic data generated by reflecting a user profile.
- the diagnostic data storage unit 260 may store a plurality of diagnostic data generated by reflecting gender, age, race, and nationality.
- the diagnostic data may be a normal human habit.
- the diagnostic data storage unit 260 may further include a sequence showing a change trend of each element of the patient's habit data.
- the preventive measure storage unit 270 stores information related to various measures for preventing disease. More specifically, the preventive measure storage unit 270 may include information on the disease, and may store various information for notifying the medical staff or the guardian whether the risk group is diagnosed.
- FIG. 7 is a block diagram for explaining a habit managing unit according to another exemplary embodiment.
- the habit management unit 220 includes an input analysis module 221 and a log analysis module 223.
- the habit management unit 220 analyzes the habits of the user from the behavior data received from the diagnosis apparatus to generate each habit factor of the habit data.
- Habit manager 220 may analyze the behavior data by machine learning technology. At this time, the habit data may be generated in a normalized form.
- the habit management unit 220 may generate habit data by analyzing sensor data detected from one or more sensors received from the diagnosis apparatus.
- the sensor data detected from the sensor may vary depending on the type of sensor included in the diagnostic device.
- the habit management unit 220 may further have an input analysis module 221.
- the input analysis module 221 analyzes the data input from the user to generate habit data.
- the input analysis module 221 may generate a habit factor of habit data related to the emotion of the user by analyzing data of a voice format input through a microphone and data of an image shape input through a camera.
- the habit management unit 220 may further have a log analysis module 223.
- the log analysis module 223 analyzes log data stored in the usage log to generate habit data.
- the log analysis module 223 may generate habit data by analyzing log data such as a call history, a history of sending and receiving a history, an internet search history, an application usage history, and the like.
- the habit manager 220 may generate a factor of the habit data by analyzing the plurality of behavior data together.
- the habit analysis unit may analyze the behavior data at regular intervals and store the habit data in the habit data storage unit.
- FIG. 8 is a block diagram illustrating a diagnosis managing unit according to another exemplary embodiment.
- the diagnosis managing unit 230 compares previously stored diagnostic data and habit data to diagnose a risk group. More specifically, the diagnosis management unit 230 calculates a sum of difference values between each habit factor of the habit data and each habit factor of the diagnostic data, and if the sum of the calculated difference values of each habit factor is equal to or greater than a preset threshold, the risk group. It can be diagnosed with On the other hand, the diagnostic management unit 230 may exclude the null value in the calculation of the difference value of the habit factor. In addition, when there are a plurality of habit data of the user generated at each predetermined cycle, the diagnosis managing unit 230 may diagnose a risk group using an arithmetic mean.
- the diagnosis management unit 230 may further include a trend analysis module 231.
- the trend analysis module 231 may determine whether a difference value between the habit data and the diagnostic data is increasing. More specifically, the trend analysis module 231 determines whether the sum of the difference values between each habit factor of the habit data and each habit factor of the diagnostic data is increasing. In this case, the diagnosis management unit 230 may diagnose the risk group when the sum of the difference values of the trend analysis module 231 is determined to increase.
- the diagnosis unit 230 may further include a correlation analysis module 233.
- the correlation analysis module 233 analyzes a correlation between each habit factor of habit data and each habit factor of habit data of a disease patient. In this case, when the analysis result of the correlation analysis module 233 is greater than or equal to a preset threshold, the diagnosis management unit 230 may diagnose the risk group. To analyze the correlation, the correlation analysis module 233 converts the change trend of each element of the plurality of habit data into a sequence form, and compares the converted sequence with the sequence representing the change trend of each element of the patient's habit data. Can be. In this case, the correlation analysis module 233 may analyze the correlation by regression analysis of the habit data of the user and the habit data of the patient.
- the diagnostic manager 230 may further include a search module 235.
- the search module 235 detects a user's profile and searches for diagnostic data matching the detected user's profile.
- the search module 235 may detect a user profile such as age, gender, race, or nationality of the user of the diagnostic apparatus, and search the diagnostic data storage for diagnostic data corresponding to the detected user profile.
- FIG. 9 is a flowchart illustrating a diagnosis method using a habit, according to an exemplary embodiment.
- the diagnostic apparatus searches for diagnostic data matching a user profile.
- the diagnostic apparatus may extract a user profile to search for diagnostic data.
- the diagnostic apparatus may request the diagnosis management apparatus to search for diagnostic data matching the user profile, and receive the diagnosis data to be matched from the diagnostic management apparatus.
- the diagnostic data may be habit data of a normal person.
- diagnostic data may vary for different user profiles such as gender, age, race, nationality.
- the diagnosis apparatus may diagnose the risk group by comparing the habit data with the diagnosis data.
- the diagnosis apparatus compares the habit data with the diagnosis data to diagnose whether it corresponds to a risk group. More specifically, the diagnostic apparatus calculates a difference value between the habit data and the diagnostic data, and diagnoses that the difference corresponds to a risk group when the calculated difference value is greater than or equal to a preset threshold.
- the preset threshold may vary depending on the setting.
- FIG. 9 has been described with reference to a diagnosis apparatus, it should be understood that a diagnosis management apparatus may diagnose a disease in the same manner.
- FIG. 10 is a diagram for describing a method of generating habit data, according to an exemplary embodiment.
- FIG. 10A illustrates an example of a habit data generation method of a diagnostic apparatus.
- the diagnostic apparatus collects behavior data.
- the diagnostic apparatus may collect behavior data in various ways. More specifically, the diagnostic apparatus may collect sensor data detected by one or more sensors, input from a user, behavioral data, and log data regarding a user's history of use of the diagnostic device. In this case, the diagnostic apparatus may periodically detect the change of the sensor for collecting the behavior data, and may request the user to input a preset query.
- log data may be generated by monitoring a user's usage history of the corresponding function. For example, when the diagnostic apparatus is a smartphone, the diagnostic apparatus may collect a smartphone usage history such as a call history, a history of sending / receiving a user, an internet search history, an application usage history, and the like in the form of log data.
- the diagnostic apparatus determines whether a predetermined period is used. At this time, if the preset period has not reached, the diagnostic apparatus branches back to step S201 to collect behavior data. For example, if habit data is set to be generated at noon every day, the diagnostic device collects behavior data again when noon is reached.
- the branching to step S205 and the diagnostic apparatus may generate the habit data by analyzing the collected behavior data. More specifically, the diagnostic apparatus analyzes the user's habits from the collected behavioral data to generate each habit factor of the habit data.
- the diagnostic apparatus may analyze behavioral data using machine learning techniques, and habit data may be generated in a normalized form.
- the habit data is data about a habit of the user generated by analyzing the behavior data.
- One habit data may have a plurality of habit factors.
- One habit factor of habit data may be generated by analyzing a plurality of behavioral data.
- the habit data generated in step S205 is stored in step S207.
- the habit data may be stored in the diagnostic apparatus or in the diagnostic management apparatus.
- the diagnostic management apparatus receives behavior data at predetermined intervals from the diagnostic apparatus.
- the diagnostic management device may receive behavior data at a 24-hour period.
- the diagnostic management apparatus analyzes the received behavior data to generate habit data, and stores the habit data generated in step S213.
- FIG. 11 is a flowchart illustrating an embodiment of step S103 of FIG. 9.
- the diagnostic apparatus compares habit data with diagnostic data. More specifically, the diagnostic apparatus may calculate a difference value between each habit factor of the habit data and each factor of the diagnostic data, and obtain a sum of the calculated difference values of each factor. At this time, the diagnostic apparatus may exclude the habit factor of the habit data having a blank value from the calculation. In addition, when comparing the plurality of habit data and the diagnostic data, the diagnostic apparatus may calculate the sum of difference values of each habit factor using an arithmetic mean. For example, the diagnostic apparatus may calculate an average value of each habit factor of the plurality of habit data and then compare the average value with the diagnostic data. In addition, the diagnostic apparatus may compare each habit data with the diagnostic data, and obtain a sum of the average values of the compared results.
- the diagnosis apparatus diagnoses whether a disease risk group corresponds to the disease risk group based on the comparison result of operation S301. More specifically, the diagnostic apparatus diagnoses as a disease risk group if the sum of the difference values of each factor is greater than or equal to a predetermined threshold in step S301. In this case, the preset threshold may be changed.
- the diagnostic device may take preventive measures according to a predetermined procedure.
- the diagnostic apparatus may display information related to a disease or notify a medical staff or a guardian that a diagnosis of a dangerous group is made.
- the diagnosis apparatus may notify the medical staff of the habit data.
- step S103 of FIG. 12 is a view for explaining an embodiment of step S103 of FIG.
- the diagnosis apparatus in operation S301, the diagnosis apparatus generates comparison data 12 that calculates a difference between the habit elements of each habit data 10 and each habit element of the diagnostic data 11.
- the sum of the mean values of the elements of the comparison data 12 and the threshold may be compared to determine whether a disease risk group exists.
- FIGS. 11 and 12 have been described with reference to the diagnosis apparatus, it should be understood that the diagnosis management apparatus may diagnose the disease in the same manner.
- FIG. 13 is a flowchart illustrating another embodiment of step S103 of FIG. 9.
- the diagnostic apparatus loads stored habit data at predetermined intervals.
- the diagnostic device may load all habit data generated periodically once a day.
- the preset period may vary depending on the setting.
- the diagnostic apparatus calculates a difference value between the habit data and the diagnosis data, and stores the difference value of each factor calculated in step S403 in step S405.
- the diagnostic apparatus calculates a difference value between each habit factor and each habit factor of the diagnostic data to generate comparison data, and stores the generated comparison data.
- the diagnostic apparatus determines whether habit data of the next cycle exists. If the habit data of the next cycle exists, the diagnostic apparatus branches to step S403 to calculate a difference value between the habit data and the diagnostic data of the next cycle.
- the diagnostic apparatus branches to step S409 to determine whether the stored difference value is an increasing trend.
- the diagnostic apparatus may determine the increase trend only when the difference value is more than the preset threshold range. For example, if the threshold is increased by 0.3 for 3 days, the diagnostic apparatus may determine that the stored difference value increases when 0.9 (1.11-> 1.30-> 2.01) increases for 3 days.
- the diagnostic device in step S411 may take preventive measures according to a predetermined procedure.
- FIG. 13 has been described based on the diagnosis device, it should be understood that the diagnosis management device can diagnose the disease in the same manner.
- step S103 of FIG. 9 is a flowchart for explaining another embodiment of step S103 of FIG. 9.
- FIG. 15 is a view for explaining another embodiment of step S103 of FIG. 9.
- the diagnosis apparatus loads stored habit data at predetermined cycles. For example, the diagnostic device loads 30 habit data generated every day.
- the diagnostic apparatus converts the change of the habit data of the loaded habit data into a sequence 21 form.
- the diagnostic apparatus may convert 30 habit data generated every day into a sequence 21 of the form as shown in FIG. 15.
- the diagnostic apparatus derives a correlation coefficient 23 by analyzing a correlation between the converted sequence 21 and the sequence 22 indicating a change in each habit element of the patient's habit data.
- the diagnostic apparatus may additionally generate an unknown sequence value based on the rare analysis.
- the diagnostic apparatus determines whether the correlation coefficient 23 derived by analyzing the correlation is equal to or greater than a preset threshold. For example, when the threshold is 0.8 and the correlation coefficient is 0.862, the diagnostic apparatus may determine that the threshold is greater than or equal to the threshold.
- the diagnosis apparatus may diagnose that the disease is a risk group, and may take preventive measures according to a predetermined procedure.
- FIGS. 14 and 15 have been described based on the diagnosis device, it should be understood that the diagnosis management device may diagnose the disease in the same manner.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Child & Adolescent Psychology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Social Psychology (AREA)
- Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Developmental Disabilities (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Educational Technology (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Radar, Positioning & Navigation (AREA)
Abstract
Description
Claims (21)
- 하나 이상의 센서로부터 검출된 센서 데이터를 분석하여 사용자의 습관 데이터를 생성하는 습관 분석부; 및상기 생성된 습관 데이터와 정상인의 생활 습관 데이터인 진단용 데이터를 비교하여 질환의 위험군인지 진단하는 진단부; 를 포함하는 습관을 이용한 진단 장치.
- 제1항에 있어서,상기 습관 분석부는 사용 로그에 저장된 로그 데이터를 분석하여 상기 습관 데이터를 생성하는 로그 분석 모듈; 을 더 포함하는 습관을 이용한 진단 장치.
- 제1항에 있어서,상기 습관 분석부는 사용자로부터 입력된 데이터를 분석하여 상기 습관 데이터를 생성하는 입력 분석 모듈; 을 더 포함하는 습관을 이용한 진단 장치.
- 제1항에 있어서,상기 습관 분석부는 상기 습관 데이터를 정규화(Normalization)된 형태로 생성하는 습관을 이용한 진단 장치.
- 제1항에 있어서,상기 진단부는 사용자의 프로필에 매칭되는 상기 진단용 데이터를 검색하는 검색 모듈; 을 더 포함하는 것을 특징으로 하는 습관을 이용한 진단 장치.
- 제1항에 있어서,상기 진단부는 상기 습관 데이터와 상기 진단용 데이터의 차이 값이 기 설정된 임계치 이상이면 상기 질환의 위험군으로 진단하는 습관을 이용한 진단 장치.
- 제1항에 있어서,기 설정된 주기마다 생성된 상기 습관 데이터를 저장하기 위한 저장부; 를 더 포함하고,상기 진단부는 상기 저장된 습관 데이터와 상기 진단용 데이터의 차이 값이 증가하는 추세인지 판단하는 추이 분석 모듈;을 더 포함하고, 상기 차이 값이 증가하는 추세로 판단되면 상기 질환의 위험군으로 진단하는 습관을 이용한 진단 장치.
- 제1항에 있어서,기 설정된 주기마다 생성된 상기 습관 데이터를 저장하기 위한 저장부; 를 더 포함하고,상기 진단부는 상기 저장부에 저장된 습관 데이터의 변화 추이를 수열 형태로 변환하고, 상기 변환된 수열과 질환 환자의 습관 데이터의 변화 추이를 나타낸 수열간 상관 관계를 분석하는 상관 분석 모듈; 을 더 포함하고, 상기 상관 관계가 기 설정된 임계치 이상이면 상기 질환의 위험군으로 진단하는 습관을 이용한 진단 장치.
- 제1항에 있어서,상기 위험군에 해당하는 것으로 진단되면, 사용자에게 상기 질환에 관한 정보를 제공하거나, 의료진 또는 보호자에게 상기 위험군 진단을 통지하는 조치부; 를 더 포함하는 습관을 이용한 진단 장치.
- 진단 장치로부터 수신한 행동 데이터를 분석하여 사용자의 습관 데이터를 생성하는 습관 관리부; 및상기 생성된 습관 데이터와 정상인의 생활 습관 데이터인 진단용 데이터를 비교하여 질환의 위험군인지 진단하는 진단 관리부; 를 포함하는 습관을 이용한 진단 관리 장치.
- 제10항에 있어서,상기 진단 장치로부터 수신한 행동 데이터는 상기 진단 장치의 하나 이상의 센서를 통해 검출된 센서 데이터, 상기 진단 장치를 통해 사용자로부터 직접 입력 받은 데이터, 상기 진단 장치의 사용 로그에 저장된 로그 데이터 중 하나 이상인 습관을 이용한 진단 관리 장치.
- 제10항에 있어서,기 설정된 주기마다 생성된 상기 습관 데이터를 저장하기 위한 습관 데이터 저장부; 를 더 포함하고,상기 진단 관리부는 상기 습관 데이터 저장부에 저장된 습관 데이터와 상기 진단용 데이터의 차이 값이 증가하는 추세인지 판단하는 추이 분석 모듈; 을 더 포함하고, 상기 차이 값이 증가하는 추세로 판단되면 상기 질환의 위험군으로 진단하는 습관을 이용한 진단 관리 장치.
- 제10항에 있어서,기 설정된 주기마다 생성된 상기 습관 데이터를 저장하기 위한 습관 데이터 저장부; 를 더 포함하고,상기 진단 관리부는 상기 습관 데이터 저장부에 저장된 습관 데이터의 변화 추이를 수열 형태로 변환하고, 상기 변환된 수열과 질환 환자의 습관 데이터의 변화 추이를 나타낸 수열간 상관 관계를 분석하는 상관 분석 모듈; 을 더 포함하고, 상기 상관 관계가 기 설정된 임계치 이상이면 상기 질환의 위험군으로 진단하는 습관을 이용한 진단 관리 장치.
- 제10항에 있어서,상기 위험군으로 진단되면, 사용자에게 상기 질환에 관한 정보를 제공하거나, 의료진 또는 보호자에게 상기 위험군 진단을 통지하는 조치 관리부; 를 더 포함하는 것을 특징으로 하는 습관을 이용한 진단 관리 장치.
- 사용자의 프로필에 매칭되는 정상인의 생활 습관 데이터인 진단용 데이터를 검색하는 단계; 및상기 검색된 진단용 데이터와 습관 데이터를 비교하여 질환의 위험군에 해당하는지 진단하는 단계; 를 포함하는 습관을 이용한 진단 방법.
- 제15항에 있어서,행동 데이터를 기반으로 상기 습관 데이터를 생성하는 단계; 를 더 포함하고,상기 행동 데이터는 하나 이상의 센서를 통해 검출된 센서 데이터, 사용자로 입력 받은 데이터, 또는 사용 로그에 저장된 로그 데이터 중 하나 이상인 습관을 이용한 진단 방법.
- 제16항에 있어서,상기 습관 데이터를 생성하는 단계는 상기 습관 데이터를 정규화(Normalization)하는 단계;를 더 포함하는 습관을 이용한 진단 방법.
- 제15항에 있어서,상기 위험군인지 진단하는 단계는 상기 습관 데이터와 상기 진단용 데이터의 차이 값이 기 설정된 임계치 이상이면 상기 질환의 위험군에 해당하는 것으로 진단하는 습관을 이용한 진단 방법.
- 제15항에 있어서,상기 습관 데이터를 생성하는 단계는 기 설정된 주기마다 생성된 상기 습관 데이터를 저장하는 단계를 더 포함하고,상기 진단하는 단계는 상기 저장된 습관 데이터와 상기 진단용 데이터의 차이 값이 증가하는 추세인지 판단하는 단계; 를 더 포함하고, 상기 차이 값이 증가하는 추세인 경우 위험군에 해당하는 것으로 진단하는 습관을 이용한 진단 방법.
- 제15항에 있어서,상기 습관 데이터를 생성하는 단계는 기 설정된 주기마다 생성된 상기 습관 데이터를 저장하는 단계를 더 포함하고,상기 진단하는 단계는 상기 저장된 습관 데이터의 변화 추이를 수열 형태로 변환하는 단계; 및 상기 변환된 수열과 질환 환자의 생활 습관 데이터의 변화 추이를 나타내는 수열간 상관 관계를 분석하는 단계; 를 더 포함하고, 상기 상관 관계가 기 설정된 임계치 이상이면, 위험군으로 진단하는 습관을 이용한 진단 방법.
- 제15항에 있어서,상기 위험군으로 진단되면, 상기 진단 장치의 사용자에게 질환에 관한 정보를 제공하거나, 의료진 또는 보호자에게 위험군 진단을 통지하는 단계; 를 더 포함하는 습관을 이용한 습관을 이용한 진단 방법.
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP14827076.2A EP3023051A4 (en) | 2013-07-18 | 2014-06-12 | Diagnostic apparatus using habit, diagnosis management apparatus, and diagnostic method using same |
CN201480039931.0A CN105407794A (zh) | 2013-07-18 | 2014-06-12 | 利用习惯的诊断装置和诊断管理装置及利用其的诊断方法 |
JP2016527909A JP2016529606A (ja) | 2013-07-18 | 2014-06-12 | 習慣を用いた診断装置及び診断管理装置及び方法 |
US15/000,240 US20160128618A1 (en) | 2013-07-18 | 2016-01-19 | Diagnostic apparatus using habit, diagnosis management apparatus, and diagnostic method using same |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020130084994A KR20150010255A (ko) | 2013-07-18 | 2013-07-18 | 습관을 이용한 진단 장치 및 진단 관리 장치와 그를 이용한 진단 방법 |
KR10-2013-0084994 | 2013-07-18 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/000,240 Continuation US20160128618A1 (en) | 2013-07-18 | 2016-01-19 | Diagnostic apparatus using habit, diagnosis management apparatus, and diagnostic method using same |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015008936A1 true WO2015008936A1 (ko) | 2015-01-22 |
Family
ID=52346352
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2014/005162 WO2015008936A1 (ko) | 2013-07-18 | 2014-06-12 | 습관을 이용한 진단 장치 및 진단 관리 장치와 그를 이용한 진단 방법 |
Country Status (6)
Country | Link |
---|---|
US (1) | US20160128618A1 (ko) |
EP (1) | EP3023051A4 (ko) |
JP (1) | JP2016529606A (ko) |
KR (1) | KR20150010255A (ko) |
CN (1) | CN105407794A (ko) |
WO (1) | WO2015008936A1 (ko) |
Families Citing this family (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102011495B1 (ko) * | 2012-11-09 | 2019-08-16 | 삼성전자 주식회사 | 사용자의 심리 상태 판단 장치 및 방법 |
US8948783B2 (en) | 2013-06-28 | 2015-02-03 | Facebook, Inc. | User activity tracking system |
US9125015B2 (en) | 2013-06-28 | 2015-09-01 | Facebook, Inc. | User activity tracking system and device |
US11944466B2 (en) | 2013-10-10 | 2024-04-02 | Aura Home, Inc. | Method and apparatus for monitoring virus variant risk during an epidemic and pandemic |
US9498163B2 (en) | 2013-10-10 | 2016-11-22 | Pushd, Inc. | Automated location and activity aware medical monitoring |
US11013472B1 (en) | 2013-10-10 | 2021-05-25 | Aura Home, Inc. | Method and apparatus for epidemic and pandemic risk assessment |
US9472166B2 (en) | 2013-10-10 | 2016-10-18 | Pushd, Inc. | Automated personalized picture frame method |
US10820293B2 (en) | 2013-10-10 | 2020-10-27 | Aura Home, Inc. | Digital picture frame with improved display of community photographs |
US11350889B2 (en) | 2013-10-10 | 2022-06-07 | Aura Home, Inc. | Covid-19 risk and illness assessment method |
US11797599B2 (en) | 2013-10-10 | 2023-10-24 | Aura Home, Inc. | Trend detection in digital photo collections for digital picture frames |
US10824666B2 (en) | 2013-10-10 | 2020-11-03 | Aura Home, Inc. | Automated routing and display of community photographs in digital picture frames |
US10474407B2 (en) | 2013-10-10 | 2019-11-12 | Pushd, Inc. | Digital picture frame with automated interactions with viewer and viewer devices |
US20200089702A1 (en) | 2013-10-10 | 2020-03-19 | Pushd, Inc. | Digital picture frames and methods of photo sharing |
US10430986B2 (en) | 2013-10-10 | 2019-10-01 | Pushd, Inc. | Clustering photographs for display on a digital picture frame |
US11669562B2 (en) | 2013-10-10 | 2023-06-06 | Aura Home, Inc. | Method of clustering photos for digital picture frames with split screen display |
US10127829B1 (en) * | 2015-05-22 | 2018-11-13 | Michael Paul Maly | Method and system for calculating probabilities of causation of specified health conditions by foods |
US20210128831A1 (en) * | 2019-11-05 | 2021-05-06 | Insulet Corporation | Systems and methods for determining placement of wearable drug delivery devices |
KR102540657B1 (ko) | 2020-06-26 | 2023-06-08 | 주식회사 올리브헬스케어 | 행동 습관 개선을 제공하는 관리 시스템 |
WO2022107518A1 (ja) * | 2020-11-19 | 2022-05-27 | 株式会社Nttドコモ | 血液情報推定装置 |
US20220292534A1 (en) * | 2021-03-15 | 2022-09-15 | BJ Fogg, LLC | Comprehensive system of optimizing habit engagement |
KR20230112873A (ko) | 2022-01-21 | 2023-07-28 | 고현서 | 심리 프로파일에 따른 행동 습관 제공 방법, 서버, 저장 매체 및 디바이스 |
CN115101195B (zh) * | 2022-06-24 | 2023-04-07 | 曜立科技(北京)有限公司 | 一种辅助瓣膜病诊断决策的方法及系统 |
US11861259B1 (en) | 2023-03-06 | 2024-01-02 | Aura Home, Inc. | Conversational digital picture frame |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002143097A (ja) * | 2000-11-10 | 2002-05-21 | Kuniaki Otsuka | 疾病発症予知通報システム及び方法 |
JP2006026037A (ja) * | 2004-07-15 | 2006-02-02 | Hitachi Ltd | 健康管理支援システム |
US20110082711A1 (en) * | 2009-10-06 | 2011-04-07 | Masimo Laboratories, Inc. | Personal digital assistant or organizer for monitoring glucose levels |
KR20110043177A (ko) * | 2009-10-21 | 2011-04-27 | 아주대학교산학협력단 | 개인화 서비스 제공 스마트 디바이스 |
KR20110126646A (ko) * | 2009-02-06 | 2011-11-23 | 비안카메드 리미티드 | 만성 질환 모니터링용 장치, 시스템 및 방법 |
Family Cites Families (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6724887B1 (en) * | 2000-01-24 | 2004-04-20 | Verint Systems, Inc. | Method and system for analyzing customer communications with a contact center |
JP2003153868A (ja) * | 2001-11-20 | 2003-05-27 | Matsushita Electric Ind Co Ltd | 個人疾患検知システム、個人疾患検知方法、媒体、及びプログラム |
JP2003296575A (ja) * | 2002-04-02 | 2003-10-17 | Nippon Colin Co Ltd | 保険料更新方法および装置 |
JP3720346B2 (ja) * | 2004-03-30 | 2005-11-24 | シャープ株式会社 | 携帯情報処理装置 |
JP4585219B2 (ja) * | 2004-03-31 | 2010-11-24 | 株式会社東芝 | ヘルスケア情報提供システム、およびヘルスケア情報提供プログラム |
JP4795666B2 (ja) * | 2004-10-29 | 2011-10-19 | 株式会社東芝 | 健康管理支援装置および健康管理支援プログラム |
JP2006155411A (ja) * | 2004-11-30 | 2006-06-15 | Houken Corp | 治療予測モデル構築システム、治療予測モデル構築方法、治療予測モデル構築用プログラム、治療内容検証・提案システム、治療内容検証・提案方法、治療内容検証・提案用プログラム、健康管理データダウンロード方法、着脱可能な記憶メディア |
CN1716267A (zh) * | 2005-07-21 | 2006-01-04 | 高春平 | 个性化立体养生保健方法及装置 |
CN1723838A (zh) * | 2005-07-21 | 2006-01-25 | 高春平 | 个性化立体减肥的方法及装置 |
JP4848524B2 (ja) * | 2005-10-21 | 2011-12-28 | 国立大学法人山口大学 | 聴診心音信号の処理方法及び聴診装置 |
WO2007072816A1 (ja) * | 2005-12-19 | 2007-06-28 | Matsushita Electric Industrial Co., Ltd. | 生活習慣改善支援装置および生活習慣改善支援方法 |
US20070276197A1 (en) * | 2006-05-24 | 2007-11-29 | Lifescan, Inc. | Systems and methods for providing individualized disease management |
CN101295331A (zh) * | 2008-05-26 | 2008-10-29 | 上海健业文化传播有限公司 | 标准生活方式的实现方法 |
KR20110120962A (ko) * | 2009-02-23 | 2011-11-04 | 제네럴 일렉트릭 컴퍼니 | 포인트-어브-케어 인액티브 의료 시스템 및 방법 |
JP2010231308A (ja) * | 2009-03-26 | 2010-10-14 | Olympus Corp | 生活習慣病予防装置および生活習慣病予防プログラム |
CN102576375B (zh) * | 2009-05-29 | 2016-05-18 | 弗吉尼亚大学专利基金会 | 用于糖尿病的开环和闭环控制的系统协调器和模块化体系结构 |
US8303500B2 (en) * | 2009-08-21 | 2012-11-06 | Fazal Raheman | Prescription zero: a non-pharmaceutical prescription device for prescribing, administering, monitoring, measuring and motivating a therapeutic lifestyle regimen for prevention and treatment of chronic diseases |
CN102068260B (zh) * | 2009-11-25 | 2013-06-05 | 深圳市健康鼠科技有限公司 | 睡眠质量监测方法以及生活方式管理建议系统 |
EP2460464A1 (en) * | 2010-12-03 | 2012-06-06 | Koninklijke Philips Electronics N.V. | Sleep disturbance monitoring apparatus |
US20120197621A1 (en) * | 2011-01-31 | 2012-08-02 | Fujitsu Limited | Diagnosing Insulin Resistance |
CN102650994A (zh) * | 2011-02-24 | 2012-08-29 | 悦康健康管理顾问科技股份有限公司 | 人体状况的整合管理系统及其管理方法 |
JP5656723B2 (ja) * | 2011-04-12 | 2015-01-21 | 日本電信電話株式会社 | メンタルヘルス管理支援システム及びメンタルヘルス管理支援方法 |
CN102855372A (zh) * | 2011-07-01 | 2013-01-02 | 王国梁 | 生理状态、饮食及运动规划建议管理系统 |
CN102999686A (zh) * | 2011-09-19 | 2013-03-27 | 上海煜策信息科技有限公司 | 一种健康管理系统及其实现方法 |
CN103020408A (zh) * | 2011-09-23 | 2013-04-03 | 重庆市真源医药信息有限公司 | 慢性病健康管理非药物干预方法及系统 |
CN103186701B (zh) * | 2011-12-28 | 2016-08-10 | 中国移动通信集团公司 | 一种饮食习惯分析方法、系统和设备 |
CN102779225A (zh) * | 2012-03-20 | 2012-11-14 | 重庆市真源医药信息有限公司 | 全自动社区健康小屋一体化实施方案 |
CN102637291B (zh) * | 2012-04-16 | 2015-05-20 | 复旦大学附属中山医院 | 一种手机云加端物联网医学系统及采用该系统的方法 |
CN102920461A (zh) * | 2012-09-13 | 2013-02-13 | 中国计量学院 | 一种进食习惯监测装置 |
CN102930491A (zh) * | 2012-11-05 | 2013-02-13 | 苏州天奥体育科技有限公司 | 一种体重管理服务系统及方法 |
-
2013
- 2013-07-18 KR KR1020130084994A patent/KR20150010255A/ko not_active Application Discontinuation
-
2014
- 2014-06-12 EP EP14827076.2A patent/EP3023051A4/en not_active Withdrawn
- 2014-06-12 JP JP2016527909A patent/JP2016529606A/ja active Pending
- 2014-06-12 CN CN201480039931.0A patent/CN105407794A/zh active Pending
- 2014-06-12 WO PCT/KR2014/005162 patent/WO2015008936A1/ko active Application Filing
-
2016
- 2016-01-19 US US15/000,240 patent/US20160128618A1/en not_active Abandoned
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002143097A (ja) * | 2000-11-10 | 2002-05-21 | Kuniaki Otsuka | 疾病発症予知通報システム及び方法 |
JP2006026037A (ja) * | 2004-07-15 | 2006-02-02 | Hitachi Ltd | 健康管理支援システム |
KR20110126646A (ko) * | 2009-02-06 | 2011-11-23 | 비안카메드 리미티드 | 만성 질환 모니터링용 장치, 시스템 및 방법 |
US20110082711A1 (en) * | 2009-10-06 | 2011-04-07 | Masimo Laboratories, Inc. | Personal digital assistant or organizer for monitoring glucose levels |
KR20110043177A (ko) * | 2009-10-21 | 2011-04-27 | 아주대학교산학협력단 | 개인화 서비스 제공 스마트 디바이스 |
Also Published As
Publication number | Publication date |
---|---|
CN105407794A (zh) | 2016-03-16 |
EP3023051A1 (en) | 2016-05-25 |
KR20150010255A (ko) | 2015-01-28 |
US20160128618A1 (en) | 2016-05-12 |
JP2016529606A (ja) | 2016-09-23 |
EP3023051A4 (en) | 2017-03-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2015008936A1 (ko) | 습관을 이용한 진단 장치 및 진단 관리 장치와 그를 이용한 진단 방법 | |
WO2022169037A1 (ko) | 머신러닝에 기반하여 심리지표 데이터 및 신체지표 데이터를 학습함으로써 정신건강을 예측하고 정신건강 솔루션을 제공하는 방법 및 이를 이용한 정신건강 평가 장치 | |
WO2021015381A1 (en) | Pulmonary function estimation | |
WO2020080819A1 (ko) | 기계학습 알고리즘을 이용한 구강건강 예측장치 및 방법 | |
WO2015199296A1 (ko) | 응급 정신의학적 정신 상태 예측 모델 기반의 응급 원격정신의학 시스템 및 방법 | |
JP2009134590A (ja) | 行動識別システム、行動識別方法、最適センサ集合決定方法および最適パラメータ決定方法。 | |
WO2015046806A1 (ko) | 질병 관리 애플리케이션 제공 방법 및 이를 구현한 장치 | |
WO2018004111A1 (ko) | 사용자 단말, 서비스 제공장치, 스마트 체온계를 이용한 체온정보 수집 및 서비스 제공시스템, 이를 이용한 서비스 제공방법 | |
WO2020119118A1 (zh) | 异常数据的处理方法、装置、设备及计算机可读存储介质 | |
WO2019240343A1 (ko) | 사용자 상태에 따른 맞춤형 자기관리정보 제공시스템 | |
WO2022211385A1 (ko) | 질병 예측치의 분포를 이용한 건강관리 상담 시스템 | |
WO2013141667A1 (ko) | 일상 건강 정보 제공 시스템 및 일상 건강 정보 제공 방법 | |
WO2022114793A1 (ko) | 빅데이터 기반의 당뇨병 발병 위험도 예측 시스템, 예측 방법, 및 프로그램 | |
WO2017146512A1 (en) | Apparatus and method for detection of chronotropic incompetence | |
WO2022014798A1 (ko) | 고객 만족도 조사 수행 시스템 | |
WO2024063321A1 (ko) | 스마트 인솔 기반 부분 체중 부하 보행 가이드 제공 방법 및 그 시스템 | |
WO2019103188A1 (ko) | 뇌파 분석을 통한 외상성 뇌손상 평가 시스템 및 방법 | |
WO2023282451A1 (ko) | 내면 집중력 훈련 방법 및 장치 | |
WO2018034388A1 (ko) | 환자 안전을 위한 측위 기반의 환자 안전관리 시스템 | |
WO2022015010A1 (ko) | 음향 신호를 분석하여 기침을 계수하는 방법, 이를 수행하는 서버 및 비일시성의 컴퓨터 판독 가능 기록 매체 | |
WO2023106516A1 (ko) | 인공지능 콜을 이용한 질의응답 기반의 치매 검사 방법 및 서버 | |
WO2021241925A1 (ko) | 혈압 측정 방법 및 전자 장치 | |
WO2022169020A2 (ko) | Ppg 기반 스펙트로그램 및 cnn에 기반하는 통증 평가 방법 및 장치 | |
WO2023033434A1 (ko) | 안약 사용 지원 장치, 방법 및 기록매체 | |
WO2023210929A1 (ko) | 의료데이터 전송방법 및 시스템 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201480039931.0 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14827076 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2016527909 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2014827076 Country of ref document: EP |