CN113693608A - Detection method for diagnosing sleep disorder based on cloud platform - Google Patents
Detection method for diagnosing sleep disorder based on cloud platform Download PDFInfo
- Publication number
- CN113693608A CN113693608A CN202110893617.0A CN202110893617A CN113693608A CN 113693608 A CN113693608 A CN 113693608A CN 202110893617 A CN202110893617 A CN 202110893617A CN 113693608 A CN113693608 A CN 113693608A
- Authority
- CN
- China
- Prior art keywords
- sleep disorder
- detection method
- cloud platform
- sleep
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 208000019116 sleep disease Diseases 0.000 title claims abstract description 73
- 208000020685 sleep-wake disease Diseases 0.000 title claims abstract description 69
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000002372 labelling Methods 0.000 claims description 19
- 238000013527 convolutional neural network Methods 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 14
- 238000003745 diagnosis Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 abstract description 2
- 238000012216 screening Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000013461 design Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000002604 ultrasonography Methods 0.000 description 6
- 208000011338 SATB2 associated disease Diseases 0.000 description 4
- 208000013959 SATB2-associated syndrome Diseases 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 201000002859 sleep apnea Diseases 0.000 description 3
- 206010003119 arrhythmia Diseases 0.000 description 2
- 230000006793 arrhythmia Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000241 respiratory effect Effects 0.000 description 2
- 206010020591 Hypercapnia Diseases 0.000 description 1
- 206010021079 Hypopnoea Diseases 0.000 description 1
- 206010021143 Hypoxia Diseases 0.000 description 1
- 206010024642 Listless Diseases 0.000 description 1
- 208000032140 Sleepiness Diseases 0.000 description 1
- 206010041349 Somnolence Diseases 0.000 description 1
- 206010042434 Sudden death Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 208000035850 clinical syndrome Diseases 0.000 description 1
- 208000010877 cognitive disease Diseases 0.000 description 1
- 235000009508 confectionery Nutrition 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 208000018875 hypoxemia Diseases 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 208000017971 listlessness Diseases 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000004796 pathophysiological change Effects 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000004622 sleep time Effects 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 201000002931 third-degree atrioventricular block Diseases 0.000 description 1
- 208000003663 ventricular fibrillation Diseases 0.000 description 1
- 206010047302 ventricular tachycardia Diseases 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—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
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/352—Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/353—Detecting P-waves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/366—Detecting abnormal QRS complex, e.g. widening
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to a domain, in particular to a detection method for diagnosing sleep disorder based on a cloud platform, which comprises the following steps: the sleep disorder acquisition device comprises a GPU module and an electrocardio acquisition module; the electrocardio acquisition module is used for acquiring and the GPU module is used for carrying out certain operation to provide sleep disorder detection service, so that the sleep disorder detection time of a patient can be greatly shortened, and the patient only needs to be at home. Detection is not required to be carried out in a hospital, and early warning of early sleep disorder is facilitated; the method is convenient for the patient to screen the sleep disorder, does not need to go to a sleep disorder research center for sleep detection, and can be carried out at home; the sleep disorder early warning service is provided, and the patient can intervene if the patient quickly knows that the patient has the sleep disorder, and can directly go to a department of respiration for treatment.
Description
Technical Field
The invention relates to the technical field of medical instruments, and particularly provides a detection method for diagnosing sleep disorders based on a cloud platform.
Background
2019, the population of international sleep disorders has been growing, and it is necessary to count that more than thirty million americans suffer from sleep disorders each year, which may last for months to years, and that diagnosing sleep disorders requires extensive testing or examination by professionals to make a diagnosis. The sleep condition of China is not optimistic enough, according to the survey of 'Chinese sleep index in 2019' initiated by a pre-happiness company in 2019, the situation is not optimistic, 33.1 percent of the Chinese people sleep in a bitter region, 26.3 percent of the Chinese people sleep in a comfortable region, 16.1 percent of the Chinese people sleep in a fussy region, only 13.8 percent of the Chinese people sleep in a sweet region, the average sleep time after 70 and 80 is the least, the situation is also optimistic after 90 times of surfing by using a mobile phone, the Chinese people sleep after twenty three points at night often, and the situation is more chaotic when the Chinese people are younger. Sleep apnea syndrome is readily available to these people, and respiratory syndrome is more likely to occur in obese people.
Sleep apnea syndrome (Sleep apnea syndrome SAS) refers to a clinical syndrome in which a series of pathophysiological changes occur in an organism due to hypoxemia and hypercapnia caused by repeated review pauses and/or hypopnea in a Sleep state caused by various reasons. SAS can cause somnolence and listlessness in the daytime, leading to cognitive dysfunction, and complications of organs such as heart, lung, and cerebral vessels (e.g., various arrhythmias including malignant arrhythmia such as third-degree atrioventricular block, ventricular tachycardia, ventricular fibrillation), increase occupational risks in specific professions, and even cause sudden death at night. Although the clinical Polysomnography (PSG) is the gold standard for diagnosing SAS, the medical cost is increased due to the need of patients to stay in hospital, and hospital detection beds are limited, so that large-area screening of people cannot be performed. The technology for carrying out quantitative and qualitative primary screening on SAS patients has made remarkable progress, and the technologies are new functions added on the basis of detection on dynamic electrocardiograms.
Meanwhile, a sleep respiratory disease diagnosis and treatment center (hereinafter referred to as a sleep center) is visited on a certain monday, wherein a sleep medical technician is seen, three instruments are used according to the introduction of a doctor to the sleep center, other machines are not used outside the portable sleep respiratory monitor and the professional polysomnography, and the number of patients in the sleep center is three according to the observation, but the number of the patients is far more than three, and when the patients have severe sleep disorder, the patients need to sleep for three days in a hospital. Meanwhile, it is observed that data of the philips-brand polysomnography used in hospitals still need to be manually marked by a sleep medical technician, an event that the sleep record takes 24 minutes after 7 hours of light is calculated is already calculated, and the event which should be automatically completed needs to be used for 24 minutes, so that the operation is very inconvenient.
Disclosure of Invention
The invention aims to: aiming at the existing (the problem of the background technology).
In order to achieve the above purpose, the invention provides the following technical scheme:
a detection method for diagnosing sleep disorder based on a cloud platform is used for improving the problems.
The present application is specifically such that:
a sleep disorder diagnosis detection method based on a cloud platform comprises a GPU module and a sleep disorder acquisition device of an electrocardio acquisition module; acquiring through the electrocardio acquisition module and performing certain operation by using the GPU module to provide sleep disorder detection service;
as a preferred technical solution of the present application, the sleep disorder collecting device comprising a GPU module and an ecg collecting module according to claim 1 is characterized in that: the system is provided with a GPU module capable of carrying out deep learning operation and a collecting device capable of collecting twelve-lead electrocardiosignals. The GPU module is an NVIDIAJETSON NANO edge calculation module provided by Invland corporation, and the twelve-lead electrocardiosignal acquisition device consists of an ADS1298 acquisition chip, an STM32 module and an ESP32 module.
As a preferred technical solution of the present application, the sleep disorder collecting device comprising a GPU module and an ecg collecting module according to claim 1 is characterized in that: the operation module and the acquisition device can be connected by adopting an internal communication bus or can be connected by adopting WiFi and Bluetooth. The internal bus protocol can be selected as a serial port protocol and an SPI protocol, the external NVIDIA JETSON NANO adopts a WiFi and Bluetooth integrated network card to provide a WiFi and Bluetooth server, and the ESP32 module of the sleep disorder acquisition device of the electrocardio acquisition module is connected with the WiFi or Bluetooth.
As a preferred technical solution of the present application, the method for detecting sleep disorder based on cloud platform diagnosis according to claim 1 is characterized in that: the sleep disorder acquisition device comprising the GPU module and the electrocardio acquisition module can be used for forming a cloud computing platform to carry out computing, and the cloud computing platform is in an edge cloud computing state. When the edge computing state is calculated, the equipment can communicate with other similar equipment through a network, and mutually share the characteristics in the database to detect the sleep disorder.
As a preferred technical solution of the present application, the method for detecting sleep disorder based on cloud platform diagnosis according to claim 1 is characterized in that: the collected electrocardio data can also be sent to a special server built in a cloud computing center for calculation by using network connection. The dedicated server also comprises a GPU or TPU or a dedicated FPGA module so as to use the neural network for operation.
As a preferred technical solution of the present application, the method for detecting sleep disorder based on cloud platform diagnosis according to claim 1 is characterized in that: the detection method comprises three processes, namely a basic electrocardiosignal labeling process, an abnormal signal detection process during sleep and a sleep disorder detection process.
As a preferred technical solution of the present application, the cloud platform-based sleep disorder diagnosis detection method according to claim 6, is characterized in that: the basic electrocardiosignal labeling process is to perform PQRST labeling on the twelve-lead electrocardiosignal data, so that the subsequent analysis is facilitated.
The basic electrocardiosignal labeling process is the most basic part in the whole service, and provides the functions of labeling the electrocardiosignal types respectively and time sequences. The whole algorithm is to distinguish other points after searching for the R wave point by taking the binary tree as the bottom, and can consume more operation time for operation because the real-time monitoring is not realized.
The R wave point searching is the most basic design of the whole labeling service, the data level is different from the prior graphic analysis, in fact, the data is the sensitive core, the data transmitted by the system are Float values, corresponding standardization operation can be carried out, and then analysis is carried out. The R-wave point algorithm requires two steps to be performed to find the approximate mode, i.e. the sum of the most central means. The other is the kernel radius, which is a specific distance from the kernel of the tree, and this operation can be done when building a binary tree, with the sidebands having distance parameters.
Then, an accumulation algorithm is used for counting the distance from the farthest point of the edge, and then the corresponding leaf node is dyed with different colors and thrown to the corresponding mark sequence, so that the marking can be finished.
The cloud platform-based diagnostic sleep disorder detection method of claim 6, wherein: abnormal signal detection and sleep disorder detection during sleep are both realized by adopting the method that electrocardiosignals are hierarchically sliced, and then a U-NET convolutional neural network built based on a CNN technology is compared with data in an attached database to obtain a final result.
The abnormal signal detection during sleep is based on the result marked on the above, and then more professional analysis is carried out, the tree established by the previous service is utilized to analyze and discriminate the mark in the tree, for example, whether a QRS wave sequence exists after P wave, to judge whether heart rate abnormal conditions such as heart conduction blockage exist, and then other discrimination services are carried out.
Two modes are provided simultaneously, one mode is identified based on a traditional state machine mode, and the other mode is that the heart rate is made into a segmented image and then directly goes through a convolutional neural network for judgment. Both modes can operate, but without data enhancement, convolutional neural networks are generally less effective than traditional state machine modes.
The fast screening service for the sleep disorder in the electrocardio environment is a screening service for fast judging based on a convolutional neural network, classification operation is carried out on electrocardiosignal pictures of a certain jump by utilizing a pre-made model set about ECG judgment, picture marks are classified and concentrated after classification is finished, electrocardiosignals with the concentrated sleep disorder are counted, duration is counted, an interval is calculated as each jump has a fixed time length, and then a corresponding result is classified and thrown out according to the type of an occurred event.
Compared with the prior art, the invention has the beneficial effects that:
in the scheme of the application:
1. the sleep disorder detection time of the patient is greatly reduced, and the patient only needs to be at home. Detection is not required to be carried out in a hospital, and early warning of early sleep disorder is facilitated.
2. The method is convenient for the patient to screen the sleep disorder, does not need to go to a sleep disorder research center for sleep detection, and can be carried out at home.
3. The sleep disorder early warning service is provided, and the patient can intervene if the patient quickly knows that the patient has the sleep disorder, and can directly go to a department of respiration for treatment.
Description of the drawings:
FIG. 1 is a block diagram of the inside of the apparatus and a software configuration diagram;
FIG. 2 is a flowchart of the overall detection;
FIG. 3 is a basic ECG labeling flow chart;
FIG. 4 is a flow chart of abnormal signal labeling during sleep;
fig. 5 is a flow chart of sleep disorder detection.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments.
Thus, the following detailed description of the embodiments of the invention is not intended to limit the scope of the invention as claimed, but is merely representative of some embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments of the present invention and the features and technical solutions thereof may be combined with each other without conflict.
The embodiment provides a sleep disorder diagnosis detection method based on a cloud platform, which comprises a GPU module and a sleep disorder acquisition device of an electrocardio acquisition module; acquiring through the electrocardio acquisition module and performing certain operation by using the GPU module to provide sleep disorder detection service;
as a preferred technical solution of the present application, the sleep disorder collecting device comprising a GPU module and an ecg collecting module according to claim 1 is characterized in that: the system is provided with a GPU module capable of carrying out deep learning operation and a collecting device capable of collecting twelve-lead electrocardiosignals. The GPU module is selected from an NVIDIA JETSON NANO edge calculation module provided by Invland corporation, and the twelve-lead electrocardiosignal acquisition device consists of an ADS1298 acquisition chip, an STM32 module and an ESP32 module.
As a preferred technical solution of the present application, the sleep disorder collecting device comprising a GPU module and an ecg collecting module according to claim 1 is characterized in that: the operation module and the acquisition device can be connected by adopting an internal communication bus or can be connected by adopting WiFi and Bluetooth. The internal bus protocol can be selected as a serial port protocol and an SPI protocol, the external NVIDIA JETSON NANO adopts a WiFi and Bluetooth integrated network card to provide a WiFi and Bluetooth server, and the ESP32 module of the sleep disorder acquisition device of the electrocardio acquisition module is connected with the WiFi or Bluetooth.
As a preferred technical solution of the present application, the method for detecting sleep disorder based on cloud platform diagnosis according to claim 1 is characterized in that: the sleep disorder acquisition device comprising the GPU module and the electrocardio acquisition module can be used for forming a cloud computing platform to carry out computing, and the cloud computing platform is in an edge cloud computing state. When the edge computing state is calculated, the equipment can communicate with other similar equipment through a network, and mutually share the characteristics in the database to detect the sleep disorder.
As a preferred technical solution of the present application, the method for detecting sleep disorder based on cloud platform diagnosis according to claim 1 is characterized in that: the collected electrocardio data can also be sent to a special server built in a cloud computing center for calculation by using network connection. The dedicated server also comprises a GPU or TPU or a dedicated FPGA module so as to use the neural network for operation.
As a preferred technical solution of the present application, the method for detecting sleep disorder based on cloud platform diagnosis according to claim 1 is characterized in that: the detection method comprises three processes, namely a basic electrocardiosignal labeling process, an abnormal signal detection process during sleep and a sleep disorder detection process.
As a preferred technical solution of the present application, the cloud platform-based sleep disorder diagnosis detection method according to claim 6, is characterized in that: the basic electrocardiosignal labeling process is to perform PQRST labeling on the twelve-lead electrocardiosignal data, so that the subsequent analysis is facilitated.
The basic electrocardiosignal labeling process is the most basic part in the whole service, and provides the functions of labeling the electrocardiosignal types respectively and time sequences. The whole algorithm is to distinguish other points after searching for the R wave point by taking the binary tree as the bottom, and can consume more operation time for operation because the real-time monitoring is not realized.
The R wave point searching is the most basic design of the whole labeling service, the data level is different from the prior graphic analysis, in fact, the data is the sensitive core, the data transmitted by the system are Float values, corresponding standardization operation can be carried out, and then analysis is carried out. The R-wave point algorithm requires two steps to be performed to find the approximate mode, i.e. the sum of the most central means. The other is the kernel radius, which is a specific distance from the kernel of the tree, and this operation can be done when building a binary tree, with the sidebands having distance parameters.
Then, an accumulation algorithm is used for counting the distance from the farthest point of the edge, and then the corresponding leaf node is dyed with different colors and thrown to the corresponding mark sequence, so that the marking can be finished.
The cloud platform-based diagnostic sleep disorder detection method of claim 6, wherein: abnormal signal detection and sleep disorder detection during sleep are both realized by adopting the method that electrocardiosignals are hierarchically sliced, and then a U-NET convolutional neural network built based on a CNN technology is compared with data in an attached database to obtain a final result.
The abnormal signal detection during sleep is based on the result marked on the above, and then more professional analysis is carried out, the tree established by the previous service is utilized to analyze and discriminate the mark in the tree, for example, whether a QRS wave sequence exists after P wave, to judge whether heart rate abnormal conditions such as heart conduction blockage exist, and then other discrimination services are carried out.
Two modes are provided simultaneously, one mode is identified based on a traditional state machine mode, and the other mode is that the heart rate is made into a segmented image and then directly goes through a convolutional neural network for judgment. Both modes can operate, but without data enhancement, convolutional neural networks are generally less effective than traditional state machine modes.
The fast screening service for the sleep disorder in the electrocardio environment is a screening service for fast judging based on a convolutional neural network, classification operation is carried out on electrocardiosignal pictures of a certain jump by utilizing a pre-made model set about ECG judgment, picture marks are classified and concentrated after classification is finished, electrocardiosignals with the concentrated sleep disorder are counted, duration is counted, an interval is calculated as each jump has a fixed time length, and then a corresponding result is classified and thrown out according to the type of an occurred event.
Example 1
The user only has two points of requirements on the acquisition end, one is accurate in acquisition, the other is timely in data uploading, and the other is secondary requirements, such as humanized operation, simple use boundary and the like. In order to meet the accurate target of the user, a medical-grade electrocardio acquisition chip, namely ADS1298 is adopted in the system, the ADS1298 can acquire fine electrocardio signals, 2-12 times of method multiples can be configured to amplify the related signals, and then the converted data of each channel of 24 bits are converted into digital signals in an analog-to-digital mode to be output, so that the system is quite convenient. While ADS12988 can be easily configured into wilson center lead and goldberg lead modes to acquire relevant data.
The quasi-another aspect of the adoption lies in being used for gathering on the connector, generally adopt the DB15 interface of standard and professional electrocardio acquisition line to gather the operation, but the acquisition line is thick and big unchangeable operation again, consequently can adopt the interface that the computer is commonly used to carry out relevant operation, here owing to need extremely thick signal line, so only HDMI interface meets the requirements in the aspect of preventing two sides from inserting, if consider with the time advance can adopt Type-C interface, Type-C interface has two sides male characteristics, signal line one side is totally 12, as long as use 10 wherein just can accomplish relevant operation, make things convenient for the user to use. The original design adopts a computer interface, the portable acquisition conducting wires on the market are found to adopt 3.5mm earphone interfaces after later investigation, and meanwhile, a large amount of equipment adopts DB15 interfaces, so that the two different requirements are considered, the interface is firstly designed into a pin header style, and the subsequent convenient replacement is realized.
The scheme is that the data uploading is mainly in how the single-chip microcomputer processes, the scheme is that the data uploading is divided into two single-chip microcomputers for related operations, one single-chip microcomputer is specially responsible for data acquisition operation, the other single-chip microcomputer is responsible for data uploading operation, the simulation is that the operation is performed when a hospital performs color ultrasound examination, namely, the operation is performed by a doctor, a color ultrasound instrument and a computer for uploading reports, the doctor operates the color ultrasound instrument to acquire physiological information of a patient, the color ultrasound instrument transmits the data from the color ultrasound instrument to the computer for processing, and the processing computer transmits the data to an image center of the hospital through a network; the STM32 singlechip serves as the doctor, the ADS1298 chip is the color Doppler ultrasound instrument, and the STM32 singlechip only serves as the function of a data uploading person, so that the STM32 singlechip operates the ADS1298 chip to operate, the STM32 singlechip transmits data to the ESP32, the ESP32 serves as a processing computer to perform primary processing and then archive operation, and finally the data are uploaded to an upper computer to be stored. The original design is that ESP32 is adopted to issue a message with Topic as completeFile through MQTT protocol, the path of the file prepared by the ESP is told to an upper computer, and the upper computer downloads the related file through the path; ESP32 also issues a RawDataFile message through MQTT protocol for information sharing, and the design is found to be not feasible subsequently, so that the sharing service is changed to an SD card WEB server.
Example 2
The main program mainly has two responsibilities, one is used as a general dispatcher station to perform dispatching operation, the other is used as a Web server of detailed information to perform service display, and therefore, the ASP.Net Core technology is required to be used for development, the reason why Java is not selected is that the ASP.Net Core is uniform in language and is not disordered like Java, and the ASP.Net Core running platform virtual machines are all virtual machines which are debugged by professionals and are in an optimal state, so that the main program is convenient to use, and the problem of optimizing is not required to be considered like a Java virtual machine. Net Core can develop grammar profile faster than asp in terms of development efficiency.
The master dispatching console is responsible for dispatching data operation, mainly comprises functions of processing program registration, processing program dispatching, data arrangement and the like, is also responsible for maintaining the SQlite database, and is a master responsible person. The processing program registration mainly processes the registration of related programs, and each processing program is a basic Service, which comprises a basic electrocardiogram labeling Service, an abnormal heart rate detection Service, a sleep disorder rapid screening Service in an electrocardio environment and other series of services, and the services are represented by a data table SE _ ECG _ Service in an SQlite database.
Example 3
The basic electrocardiogram marking service is the most basic part of the whole service, and provides the functions of marking the types of electrocardiosignals respectively and time sequences. The whole algorithm is to distinguish other points after searching for the R wave point by taking the binary tree as the bottom, and can consume more operation time for operation because the real-time monitoring is not realized.
The R wave point searching is the most basic design of the whole labeling service, the data level is different from the prior graphic analysis, in fact, the data is the sensitive core, the data transmitted by the system are Float values, corresponding standardization operation can be carried out, and then analysis is carried out. The R-wave point algorithm requires two steps to be performed to find the approximate mode, i.e. the sum of the most central means. The other is the kernel radius, which is a specific distance from the kernel of the tree, and this operation can be done when building a binary tree, with the sidebands having distance parameters.
Then, an accumulation algorithm is used for counting the distance from the farthest point of the edge, and then the corresponding leaf node is dyed with different colors and thrown to the corresponding mark sequence, so that the marking can be finished.
Example 4
The abnormal heart rate detection service is based on the marked result and then performs more professional analysis, the tree established by the previous service is used for analyzing and screening the mark in the tree, for example, whether a P wave has a QRS wave sequence or not is judged to determine whether abnormal heart rate conditions such as heart conduction blockage exist, and then other identification services are performed.
Two modes are provided simultaneously, one mode is identified based on a traditional state machine mode, and the other mode is that the heart rate is made into a segmented image and then directly goes through a convolutional neural network for judgment. Both modes can operate, but without data enhancement, convolutional neural networks are generally less effective than traditional state machine modes.
Example 5
The fast screening service for the sleep disorder in the electrocardio environment is a screening service for fast judging based on a convolutional neural network, classification operation is carried out on electrocardiosignal pictures of a certain jump by utilizing a pre-made model set about ECG judgment, picture marks are classified and concentrated after classification is finished, electrocardiosignals with the concentrated sleep disorder are counted, duration is counted, an interval is calculated as each jump has a fixed time length, and then a corresponding result is classified and thrown out according to the type of an occurred event.
In the description of the present invention, it should be noted that the terms "upper", "lower", and the like refer to orientations or positional relationships based on those shown in the drawings, or orientations or positional relationships that are conventionally arranged when the products of the present invention are used, or orientations or positional relationships that are conventionally understood by those skilled in the art, and such terms are used for convenience of description and simplification of the description, and do not refer to or imply that the devices or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like are used merely to distinguish one description from another, and are not to be construed as indicating or implying relative importance.
The foregoing embodiments are merely illustrative of the principles and features of the present invention, which are intended to enable those skilled in the art to understand the disclosure and practice the invention accordingly.
The above embodiments are only used for illustrating the invention and not for limiting the technical solutions described in the invention, and although the present invention has been described in detail in the present specification with reference to the above embodiments, the present invention is not limited to the above embodiments, and therefore, any modification or equivalent replacement of the present invention is made; all such modifications and variations are intended to be included herein within the scope of this disclosure and the appended claims.
Claims (8)
1. A detection method for diagnosing sleep disorder based on a cloud platform is characterized in that: the sleep disorder acquisition device comprises a GPU module and an electrocardio acquisition module; the electrocardio acquisition module is used for acquiring and the GPU module is used for carrying out certain operation to provide sleep disorder detection service.
2. The cloud platform-based diagnostic sleep disorder detection method of claim 1, wherein: the sleep disorder acquisition device is provided with the GPU module capable of carrying out deep learning operation and the electrocardio acquisition device capable of acquiring twelve-lead electrocardiosignals.
3. The cloud platform-based sleep disorder diagnosis detection method of claim 2, wherein: the operation module in the GPU module and the electrocardio acquisition device can be connected by adopting an internal communication bus or connected by adopting WiFi and Bluetooth.
4. The cloud platform-based diagnostic sleep disorder detection method of claim 3, wherein: and forming a cloud computing platform by using the sleep disorder acquisition device to perform computing, wherein the cloud computing platform is an edge cloud computing state.
5. The cloud platform-based diagnostic sleep disorder detection method of claim 3, wherein: the collected electrocardio data are sent to a special server built in a cloud computing center for calculation by using network connection.
6. The cloud platform-based diagnostic sleep disorder detection method of claim 3, wherein: the detection method comprises three processes, namely a basic electrocardiosignal labeling process, an abnormal signal detection process during sleep and a sleep disorder detection process.
7. The cloud platform-based diagnostic sleep disorder detection method of claim 3, wherein: the basic electrocardiosignal labeling process is to perform PQRST labeling on the twelve-lead electrocardiosignal data, so that the subsequent analysis is facilitated.
8. The cloud platform-based diagnostic sleep disorder detection method of claim 3, wherein: the abnormal signal detection during sleeping and the sleep disorder detection are both realized by adopting a method that the electrocardiosignals are hierarchically sliced, and then a U-NET convolutional neural network built based on a CNN technology is compared with data in an attached database to obtain a final result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110893617.0A CN113693608A (en) | 2021-08-04 | 2021-08-04 | Detection method for diagnosing sleep disorder based on cloud platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110893617.0A CN113693608A (en) | 2021-08-04 | 2021-08-04 | Detection method for diagnosing sleep disorder based on cloud platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113693608A true CN113693608A (en) | 2021-11-26 |
Family
ID=78651637
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110893617.0A Pending CN113693608A (en) | 2021-08-04 | 2021-08-04 | Detection method for diagnosing sleep disorder based on cloud platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113693608A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107569212A (en) * | 2017-08-30 | 2018-01-12 | 上海市共进医疗科技有限公司 | A kind of equipment, system and method based on heart rate detection noctural sleep apnea syndrome |
CN109106350A (en) * | 2018-09-20 | 2019-01-01 | 中山大学 | The preliminary screening method of the Sleep Apnea-hypopnea Syndrome of low physiological stress |
US20190150772A1 (en) * | 2017-11-20 | 2019-05-23 | Kinpo Electronics, Inc. | Wearable device capable of detecting sleep apnea event and detection method thereof |
CN110151138A (en) * | 2019-05-29 | 2019-08-23 | 中山大学 | Sleep apnea segment detection method, equipment based on convolutional neural networks |
CN110916650A (en) * | 2019-12-30 | 2020-03-27 | 龙岩学院 | Wearable electrocardio monitoring facilities |
US20210186416A1 (en) * | 2019-12-23 | 2021-06-24 | Koninklijke Philips N.V. | Arrhythmic heartbeat resilient sleep apnea detection |
-
2021
- 2021-08-04 CN CN202110893617.0A patent/CN113693608A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107569212A (en) * | 2017-08-30 | 2018-01-12 | 上海市共进医疗科技有限公司 | A kind of equipment, system and method based on heart rate detection noctural sleep apnea syndrome |
US20190150772A1 (en) * | 2017-11-20 | 2019-05-23 | Kinpo Electronics, Inc. | Wearable device capable of detecting sleep apnea event and detection method thereof |
CN109106350A (en) * | 2018-09-20 | 2019-01-01 | 中山大学 | The preliminary screening method of the Sleep Apnea-hypopnea Syndrome of low physiological stress |
CN110151138A (en) * | 2019-05-29 | 2019-08-23 | 中山大学 | Sleep apnea segment detection method, equipment based on convolutional neural networks |
US20210186416A1 (en) * | 2019-12-23 | 2021-06-24 | Koninklijke Philips N.V. | Arrhythmic heartbeat resilient sleep apnea detection |
CN110916650A (en) * | 2019-12-30 | 2020-03-27 | 龙岩学院 | Wearable electrocardio monitoring facilities |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103678916B (en) | The universal method of the monitoring data of a kind of automatic collection monitor and device | |
CN206601705U (en) | A kind of medical treatment & health system based on Remote data service with analysis | |
CN110875092B (en) | Health big data service method and system based on remote fundus screening | |
RU2008107719A (en) | SYSTEM AND METHOD FOR CONTEXT-DEPENDENT DETECTION OF SERVICES FOR MOBILE MEDICAL DEVICES | |
US20130102856A1 (en) | Non-invasive detection of fetal or maternal illness | |
US20150164428A1 (en) | Method for Multi-Scale Quality Assessment for Variability Analysis | |
CN106108846A (en) | A kind of intelligent drug risk monitoring method and system | |
CN110664397A (en) | Real-time analysis, diagnosis and early warning cloud system for electrocardiogram data | |
Sulas et al. | A non-invasive multimodal foetal ECG–Doppler dataset for antenatal cardiology research | |
CN115862819A (en) | Medical image management method based on image processing | |
CN105740640A (en) | Comprehensive collecting and analyzing method for human body life parameters | |
CN205451067U (en) | Health detection of family and system of diagnosing | |
CN113693608A (en) | Detection method for diagnosing sleep disorder based on cloud platform | |
CN113288156B (en) | Method for generating electrocardiographic data of any lead visual angle | |
CN103366082A (en) | System and method of managing technician review of medical test data | |
CN207837532U (en) | The recognition of face detecting system of sleep-apnea | |
CN111938652A (en) | Application of artificial intelligence diagnosis mode in early diagnosis of bronchial asthma | |
US20230170087A1 (en) | Systems and methods for remote pregnancy monitoring and management | |
CN117316367B (en) | Intelligent diagnosis system based on AI | |
US12023165B2 (en) | Screening cardiac conditions using cardiac vibrational energy spectral heat maps | |
US20190150773A1 (en) | Continuous cardiac monitoring and real time episode detection system | |
US20230165506A1 (en) | Apparatus for non-invasive acquisition of maternal and/or fetal physiological signals | |
WO2022089289A1 (en) | Signal processing method and apparatus | |
TWM555707U (en) | Arrhythmia detecting apparatus and related system thereof | |
CN207323456U (en) | A kind of smart machine for leukaemic's health service |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211126 |