CN110876621A - Sleep apnea syndrome detecting system based on neural network - Google Patents
Sleep apnea syndrome detecting system based on neural network Download PDFInfo
- Publication number
- CN110876621A CN110876621A CN201811059253.0A CN201811059253A CN110876621A CN 110876621 A CN110876621 A CN 110876621A CN 201811059253 A CN201811059253 A CN 201811059253A CN 110876621 A CN110876621 A CN 110876621A
- Authority
- CN
- China
- Prior art keywords
- module
- lstm
- neural network
- respiration
- detection 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
- 201000002859 sleep apnea Diseases 0.000 title claims abstract description 26
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 59
- 230000029058 respiratory gaseous exchange Effects 0.000 claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000003745 diagnosis Methods 0.000 claims abstract description 20
- 230000001133 acceleration Effects 0.000 claims abstract description 12
- 238000004891 communication Methods 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims description 13
- 210000001015 abdomen Anatomy 0.000 claims description 9
- 238000013500 data storage Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000003321 amplification Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000011897 real-time detection Methods 0.000 claims description 3
- 238000013145 classification model Methods 0.000 claims 3
- 230000005856 abnormality Effects 0.000 claims 1
- 238000003062 neural network model Methods 0.000 claims 1
- 230000000241 respiratory effect Effects 0.000 abstract description 16
- 238000007635 classification algorithm Methods 0.000 abstract 1
- 208000008784 apnea Diseases 0.000 description 11
- 210000000038 chest Anatomy 0.000 description 11
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 7
- 229910052760 oxygen Inorganic materials 0.000 description 7
- 239000001301 oxygen Substances 0.000 description 7
- 239000008280 blood Substances 0.000 description 6
- 210000004369 blood Anatomy 0.000 description 6
- 238000000034 method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 206010021079 Hypopnoea Diseases 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000000414 obstructive effect Effects 0.000 description 3
- 208000001797 obstructive sleep apnea Diseases 0.000 description 3
- 206010021133 Hypoventilation Diseases 0.000 description 2
- 230000003187 abdominal effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 210000000115 thoracic cavity Anatomy 0.000 description 2
- 206010003497 Asphyxia Diseases 0.000 description 1
- 206010006334 Breathing abnormalities Diseases 0.000 description 1
- 208000007590 Disorders of Excessive Somnolence Diseases 0.000 description 1
- 206010020591 Hypercapnia Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 208000006083 Hypokinesia Diseases 0.000 description 1
- 206010021143 Hypoxia Diseases 0.000 description 1
- 206010049976 Impatience Diseases 0.000 description 1
- 206010041235 Snoring Diseases 0.000 description 1
- 206010041349 Somnolence Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036996 cardiovascular health Effects 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 208000035850 clinical syndrome Diseases 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 208000018875 hypoxemia Diseases 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- WABPQHHGFIMREM-UHFFFAOYSA-N lead(0) Chemical compound [Pb] WABPQHHGFIMREM-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004796 pathophysiological change Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000004622 sleep time Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000011580 syndromic disease 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
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/0826—Detecting or evaluating apnoea events
-
- 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
- A61B5/113—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb occurring during breathing
-
- 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
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4818—Sleep apnoea
-
- 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
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Physiology (AREA)
- Cardiology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Pulmonology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a sleep apnea syndrome detection system based on LSTM neural network classification, which consists of a protection circuit, an impedance type respiration detection module, an electrocardiosignal detection module, an acceleration detection module, an oronasal respiration detection module, a signal self-coding module, an LSTM characteristic extraction module, sleep respiration detection equipment of a wireless communication module, LSTM neural network training equipment, processing and diagnosis equipment based on the LSTM neural network, a thermistor sensor for detecting oronasal respiration airflow, and a positive electrode and a negative electrode for detecting chest respiration and electrocardiogram signals of a human body. The device is simple and easy without hospitalization, and does not cause physiological and psychological burden. The device can detect the respiratory states of different parts of a human body in multiple directions, achieves the purpose of classifying and diagnosing the sleep apnea syndrome through an LSTM neural network classification algorithm, is simple to operate, and can be used at home.
Description
Technical Field
The invention relates to the field of wearable intelligent diagnosis equipment, in particular to a sleep apnea syndrome detection system.
Background
Among the snoring population, approximately 20% of people sleep often with suffocation symptoms, medically known as sleep apnea syndrome. Sleep Apnea Syndrome (SAS) refers to a clinical syndrome in which a series of pathophysiological changes occur in the body due to repeated intermittent hypoxemia and hypercapnia attacks caused by apnea and/or hypopnea in a sleep state caused by various reasons. Investigation shows that about 4000 million people currently suffer from the disease in China. People suffering from the disease are easy to have the symptoms of daytime sleepiness, personality impatience, hypodynamia, reduced working efficiency and the like, and are easy to have hypertension, coronary heart disease, cerebrovascular disease and the like. The continuous dynamic monitoring of the sleep physiological parameters has important significance for human health medical treatment and is an indispensable technical means for detecting respiratory events in sleep, and the detection of the respiratory events in sleep is an important basis for clinical diagnosis.
Apnea refers to the condition that the oral-nasal airflow stops completely for more than 10s in the sleep process; hypoventilation means that the respiratory airflow amplitude is reduced by more than 50% compared with the baseline level, and the blood oxygen saturation is reduced by 4% compared with the basic level; sleep Apnea Hypopnea Index (AHI) refers to the sum of the number of apneas and hypopneas per hour of sleep time.
According to the chest and abdomen movement condition during sleep apnea, sleep apnea is clinically divided into three types, ① obstructive type means that chest and abdomen type respiration still exists during apnea, which is most common, ② central type means that chest and abdomen type respiration disappears during apnea, and ③ mixed type means that central type apnea appears at the beginning and then obstructive type apnea appears during one-time apnea.
Currently, the commonly used method for detecting sleep apnea is to monitor a patient in a hospital with a Polysomnography (PSG) detector for multiple electrical conduction throughout the night. The PSG has more monitored physiological parameters, and is beneficial to the comprehensive judgment of doctors to give accurate diagnosis results. However, due to the fact that the PSG is provided with a plurality of sensors, the PSG is large in size and inconvenient to move, a patient needs to be monitored in hospital, and the sleep environment is changed and the monitoring equipment is affected, so that the sleep difficulty is caused, and the diagnosis accuracy is affected. And the monitoring equipment is expensive, complex to operate and difficult to popularize and apply in families. Most of the devices widely used at home today are used for measuring a single part, so that the breath of a human body cannot be comprehensively analyzed, and accurate positioning and diagnosis are difficult.
Patent CN201210010908 discloses a prescreening system for obstructive sleep apnea hypoventilation syndrome patients, which uses chest and abdomen straps to monitor the thoracoabdominal breathing movements. Patent CN201420109006 discloses a portable sleep apnea hypopnea syndrome screening device, which only uses a blood oxygen probe to measure pulse wave, blood oxygen value and pulse rate value, and judges whether the patient is a sleep apnea hypopnea syndrome patient and the severity degree through an oxygen desaturation index.
The prior art has the problems that the tightness degree of the binding band is required to be adjusted by a user by using the binding band, small breathing movement cannot be measured when the tightness degree is too large, discomfort of the user is caused when the tightness degree is too large, normal breathing movement is influenced, and the measurement precision is influenced; the blood oxygen probe cannot directly detect respiratory movement, and only when the respiratory pause time is long and the blood oxygen saturation is remarkably reduced, the respiratory pause event can be detected, and researches show that only a small part of respiratory pause events can cause the change of the blood oxygen saturation.
Disclosure of Invention
In order to solve the technical problems, the invention provides the following technical scheme:
a sleep apnea syndrome detection system based on an LSTM deep neural network is composed of a sensor group, sleep apnea detection equipment, a signal self-coding module, an LSTM feature extraction module, wireless communication equipment, LSTM neural network training equipment and processing diagnosis equipment based on the LSTM neural network; the sensor group comprises a positive electrode and a negative electrode which are used for sensing the chest respiration and electrocardiogram signals of a human body, and a thermistor sensor which is used for sensing the breathing airflow of the mouth and the nose; the sleep respiration detection device comprises a protection circuit, an impedance respiration detection module, an electrocardiosignal detection module, an acceleration detection module and an oral-nasal respiration detection module; the sleep respiration detection equipment is connected with the signal self-coding module, the signals are combined into a standard input format of an LSTM model through the LSTM feature extraction module after self-coding, and then the marked input is connected with the processing diagnosis equipment or the LSTM neural network training equipment through the wireless communication equipment; the processing and diagnosing device comprises a data processing module, a data storage and playback module, an LSTM-based real-time monitoring and abnormity alarming module and a diagnosing and reporting module.
A signal self-coding module and an LSTM characteristic extraction module in the processing equipment receive and process various signals sent by the detection equipment; the processed data is stored and replayed through a data storage and replay module, meanwhile, abnormal events of respiration and an electrocardiogram are detected and alarmed through a real-time detection and abnormity alarm module based on a trained LSTM neural network, and finally, the stored records are analyzed, diagnosed and a report is generated through a diagnosis and report module.
The electrocardiosignal detection module provides the electrocardiosignal amplification and filtering functions.
The acceleration sensor provides functions of a breathing state of the abdomen of a human body and a sleeping position state during sleeping, the breathing state of the abdomen is obtained through the numerical change of the acceleration sensor, and the position signal is collected and transmitted to the signal self-encoding module through the measurement of the gravity acceleration direction at regular time.
The positive electrode and the negative electrode are used for applying an excitation signal of the impedance type respiration detection module to a human body and simultaneously detecting a feedback signal to measure thoracic impedance to obtain a thoracic respiration signal; the positive electrode and the negative electrode are also used for sensing electrocardiosignals and outputting the electrocardiosignals to the electrocardiosignal detection module.
The thermistor respiratory flow detection module acquires respiratory signals by detecting the temperature changes of nasal information and oral respiratory airflow, amplifies and filters the acquired signals and reaches the signal self-coding module.
The processing and diagnosis equipment can be realized on the basis of any one of a smart phone, a tablet computer and a computer.
The device is simple and easy without hospitalization, and does not cause physiological and psychological burden. The device can detect the respiratory states of different parts of the human body in multiple directions simultaneously, achieves the purpose of classifying and diagnosing the sleep apnea syndrome, is simple to operate, and can be used at home.
Drawings
FIG. 1 is a drawing illustrating the inventor of the present invention
FIG. 2 is a block diagram of the architecture of the present invention
FIG. 3 functional block diagram of sleep apnea syndrome monitoring and classification diagnosis software process
Detailed Description
The invention aims to provide a method for detecting an apnea event in a human sleep state, classifying and diagnosing sleep apnea syndrome, evaluating cardiovascular health conditions and detecting a sleep position, which can be used for self-monitoring of sub-health people. The system comprises a wearable sensor group, a sleep respiration detection device and a processing diagnosis device. The system design can reduce the influence on the normal sleep of a human body as much as possible, and the functions of data storage, analysis, display, diagnosis and analysis and the like which need higher-performance hardware support can be designed based on the intelligent terminal equipment, so that the equipment cost is reduced to the greatest extent.
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without inventive step, are within the scope of the present invention.
As shown in fig. 1 and 2, the present system includes: the sleep respiration detection device comprises a sleep respiration detection device 1 comprising a protection circuit, an impedance respiration detection module, an electrocardiosignal detection module, an acceleration detection module, an oral-nasal respiration detection module, a signal self-coding module, an LSTM characteristic extraction module and a wireless communication module, a thermistor sensor 2 for detecting the respiratory airflow of the oral-nasal, a positive electrode 3 for detecting the chest respiration and electrocardiogram signals of a human body, a negative electrode 4, an LSTM neural network training device 5 and a processing diagnosis device 6 based on forward propagation of an LSTM neural network.
The positive electrode 3 and the negative electrode 4 are connected with the impedance respiration detection module and the electrocardiosignal detection module through the protection circuit; the thermistor sensor is connected with the mouth-nose respiration detection module; the impedance respiration detection module, the electrocardiosignal detection module, the acceleration detection module and the mouth-nose respiration detection module are respectively connected with the wireless communication module through the signal self-coding module and the LSTM characteristic extraction module; the wireless communication module is connected with the processing and diagnosis equipment 6; the processing and diagnosing device 6 comprises a data processing module, a data storage and playback module, an LSTM-based real-time monitoring and abnormity alarming module and a diagnosing and reporting module.
In the embodiment, the positive electrode 3 and the negative electrode 4 are respectively arranged on the left chest and the right chest of a human body and used for sensing chest respiration and electrocardiosignals; the positive electrode 3 and the negative electrode 4 apply an excitation signal of the impedance respiration detection module to a human body, and simultaneously detect a feedback signal to obtain a chest respiration signal; the positive electrode 3 and the negative electrode 4 are used for sensing electrocardiosignals and transmitting the electrocardiosignals to the electrocardiosignal detection module.
The electrocardiosignal detection module provides the electrocardiosignal amplification and filtering functions. The electrocardiosignals are induced by the electrocardio-electrode, reach the protection circuit through a lead wire, are amplified and filtered by the electrocardio-signal detection module, and reach the signal self-coding module.
The thermistor respiratory airflow detection module acquires respiratory signals by detecting the temperature changes of the nasal information and the oral respiratory airflow, amplifies and filters the acquired signals and reaches the signal self-coding module.
The thermistor sensor 3 is arranged at the mouth and the nose of a human body in the embodiment and used for detecting the breath airflow of the mouth and the nose and collecting temperature signals, then transmitting the related signals to the mouth and nose breath detection module and transmitting the signals to the signal self-coding module.
In this embodiment, the acceleration detection module is disposed in the sleep respiration detection device 1, and the sleep respiration detection device 1 is disposed on the abdomen of the human body. The abdominal respiration state is acquired through the numerical change of the acceleration sensor, and the body position signals are acquired and transmitted through the measurement of the gravity acceleration direction at regular time through the signal self-encoding module, so that the detection of the abdominal respiration signals and the sleeping body position of a human body is realized.
The signal self-coding module performs self-coding on the respiration, electrocardio and body position signals, converts the signals into an LSTM model standard input format through the LSTM feature extraction module, and sends the input format to the processing and diagnosis equipment 6 through the wireless communication module for further processing.
The LSTM neural network training device 5 labels the data stored in the data storage and playback module in the processing and diagnosis device 6, and stores the parameters of the successfully converged model by training the parameters of the LSTM model through back propagation, and calls the parameters when waiting for real-time monitoring.
The process diagnostic device 6 may be implemented based on (including but not limited to) a smart phone, tablet, computer or similar homemade device with computing capabilities.
The processing and diagnosing device 6 comprises a data processing module, a data storage and playback module, an LSTM-based real-time monitoring and abnormity alarming module and a diagnosing and reporting module, and can realize the functions of data processing, storage and playback of sleep physiological signals, sleep apnea, real-time detection and alarming, sleep apnea classification diagnosis and sleep position detection. In this embodiment, the monitoring is implemented in the form of monitoring software based on an intelligent terminal.
Fig. 3 is a schematic flow chart of an implementation of the monitoring software of the intelligent terminal.
The monitoring software pair first initializes the process diagnostic device, after which a function selection is made by the user. If the real-time monitoring is carried out, wireless communication is required to be established to receive data, and whether the electrocardiogram and the respiration are abnormal or not is judged through data processing and real-time analysis based on a trained LSTM model; if the electrocardio or breathing abnormality exists, the monitoring software can control the intelligent terminal to send out sound or vibration alarm and store the processed data; if the user selects the playback function, the monitoring software reads the stored records, performs electrocardiogram analysis, sleep position analysis and apnea statistical analysis, performs classified diagnosis by the aid of chest and abdomen movement conditions during apnea and LSTM classification judgment, judges whether the human sleep apnea is obstructive, central or mixed, and finally generates and displays a report.
Finally, it should be noted that the above-mentioned embodiments described with reference to the drawings are only preferred embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications or equivalent substitutions made based on the spirit of the present invention should be covered within the scope of the present invention.
Claims (7)
1. A sleep apnea syndrome detecting system based on neural network is composed of a sensor group, sleep apnea detecting equipment, a signal self-coding module, an LSTM characteristic extraction module, wireless communication equipment, LSTM neural network training equipment and processing diagnosis equipment based on LSTM neural network; the sensor group comprises a positive electrode and a negative electrode which are used for sensing the chest respiration and electrocardiogram signals of a human body, and a thermistor sensor which is used for sensing the breathing airflow of the mouth and the nose; the sleep respiration detection device comprises a protection circuit, an impedance respiration detection module, an electrocardiosignal detection module, an acceleration detection module and an oral-nasal respiration detection module; the sleep respiration detection equipment is connected with the signal self-coding module, the signals are combined into a standard input format of an LSTM model through the LSTM feature extraction module after self-coding, and then the marked input is connected with the LSTM neural network training equipment through the wireless communication equipment; the processing and diagnosing device comprises a data processing module, a data storage and playback module, an LSTM-based real-time monitoring and abnormity alarming module and a diagnosing and reporting module.
2. The system for detecting the sleep apnea syndrome based on the neural network as claimed in claim 1, wherein the signal self-coding module receives and self-codes various signals sent by the detection device, and then converts the signals into a standard input format of an LSTM model through the LSTM feature extraction module; the converted data is transmitted to a data storage and playback module of the processing and diagnosis device through the wireless communication device for storage and playback, real-time detection and abnormal alarming are carried out through a trained LSTM neural network, and finally the stored records are analyzed, diagnosed and reported through a diagnosis and reporting module to generate a report.
3. The system of claim 1, wherein the four signals of the impedance respiration detection module signal, the electrocardiograph detection module signal, the oronasal respiration detection module signal and the chest and abdomen acceleration detection module signal extracted by the sensor group and the sleep respiration detection device through amplification and filtering are sampled and self-encoded.
4. The sleep apnea syndrome detection system of claim 1, wherein the LSTM feature extraction module is capable of automatically combining the self-encoded signal data into a standard input format of an LSTM neural network model.
5. The system of claim 1, wherein the diagnostic device is trained to have a built-in LSTM classification model before performing real-time monitoring and alarming for abnormality, and the training of the LSTM classification model requires a large number of standard inputs labeled with classification results.
6. The system of claim 1, wherein the processing and diagnosing device based on the trained LSTM classification model is capable of receiving standard inputs provided by the LSTM feature extraction module via the wireless communication device to perform the classification and determination of the sleep apnea syndrome.
7. The system for detecting sleep apnea syndrome based on neural network as claimed in claim 1, wherein the processing and diagnosing device can be implemented based on any one of a smart phone, a tablet computer and a computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811059253.0A CN110876621A (en) | 2018-09-06 | 2018-09-06 | Sleep apnea syndrome detecting system based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811059253.0A CN110876621A (en) | 2018-09-06 | 2018-09-06 | Sleep apnea syndrome detecting system based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110876621A true CN110876621A (en) | 2020-03-13 |
Family
ID=69727266
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811059253.0A Pending CN110876621A (en) | 2018-09-06 | 2018-09-06 | Sleep apnea syndrome detecting system based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110876621A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111436939A (en) * | 2020-03-17 | 2020-07-24 | 佛山市台风网络科技有限公司 | Health monitoring method, system, computer equipment and readable storage medium |
| CN111466877A (en) * | 2020-03-31 | 2020-07-31 | 上海蠡图信息科技有限公司 | Oxygen reduction state prediction method based on L STM network |
| CN113180691A (en) * | 2020-12-28 | 2021-07-30 | 天津大学 | Three-channel sleep apnea and hypopnea syndrome recognition device |
| CN113243890A (en) * | 2021-05-10 | 2021-08-13 | 清华大学深圳国际研究生院 | Sleep apnea syndrome recognition device |
| CN113633260A (en) * | 2021-08-11 | 2021-11-12 | 广州医科大学附属第一医院（广州呼吸中心） | Multi-sleep monitoring method, monitor, computer device and readable storage medium |
-
2018
- 2018-09-06 CN CN201811059253.0A patent/CN110876621A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111436939A (en) * | 2020-03-17 | 2020-07-24 | 佛山市台风网络科技有限公司 | Health monitoring method, system, computer equipment and readable storage medium |
| CN111466877A (en) * | 2020-03-31 | 2020-07-31 | 上海蠡图信息科技有限公司 | Oxygen reduction state prediction method based on L STM network |
| CN111466877B (en) * | 2020-03-31 | 2023-12-01 | 上海蠡图信息科技有限公司 | LSTM network-based oxygen reduction state prediction method |
| CN113180691A (en) * | 2020-12-28 | 2021-07-30 | 天津大学 | Three-channel sleep apnea and hypopnea syndrome recognition device |
| CN113180691B (en) * | 2020-12-28 | 2022-10-21 | 天津大学 | Three-channel sleep apnea and hypopnea syndrome recognition device |
| CN113243890A (en) * | 2021-05-10 | 2021-08-13 | 清华大学深圳国际研究生院 | Sleep apnea syndrome recognition device |
| CN113633260A (en) * | 2021-08-11 | 2021-11-12 | 广州医科大学附属第一医院（广州呼吸中心） | Multi-sleep monitoring method, monitor, computer device and readable storage medium |
| CN113633260B (en) * | 2021-08-11 | 2024-03-12 | 广州医科大学附属第一医院（广州呼吸中心） | Polysomnography, computer equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104257353A (en) | Sleep apnea syndrome detecting system | |
| CN110876621A (en) | Sleep apnea syndrome detecting system based on neural network | |
| JP2021191502A (en) | Evaluation device | |
| CN107041730A (en) | A kind of contactless sleep monitoring device and its monitoring method | |
| CN107529991A (en) | For the heart of detection object and/or the equipment, system and method for respiratory disorder | |
| US10004452B2 (en) | System and methods for estimating respiratory airflow | |
| JP2000000214A (en) | Sleeping monitor device | |
| CN106175770B (en) | The judgement system of apnea during a kind of sleep | |
| CN105212899A (en) | Health sleep type remote monitoring service system | |
| CN101536904A (en) | Heart electricity-based sleep apnea detection device | |
| CN110811547A (en) | Multi-guide sleep monitor and sleep monitoring method | |
| KR20160084980A (en) | A real-time sleep monitoring system using a smartphone | |
| CN109171691A (en) | A kind of sleep-respiratory detection system and its detection method | |
| Jayarathna et al. | Polymer sensor embedded, IOT enabled t-shirt for long-term monitoring of sleep disordered breathing | |
| WO2017038966A1 (en) | Bio-information output device, bio-information output method and program | |
| Nassir et al. | Wireless body-area network for detection of sleep disorders | |
| US20210077013A1 (en) | System and method for digital monitoring of sleep apnea | |
| CN103637791A (en) | GSM network based remote electrocardiogram monitoring system | |
| CN111317476A (en) | Sleep apnea syndrome detection device based on respiratory airflow signal | |
| JP2001299712A (en) | Long-time biological monitor | |
| Heise et al. | Unobtrusively detecting apnea and hypopnea events via a hydraulic bed sensor | |
| CN108283490A (en) | Sleep-respiratory system and method | |
| CN113974613A (en) | Double sleep monitoring method based on enhanced ballistocardiogram | |
| KR20180065039A (en) | Smart phone ubiquitous healthcare diagnosis system using vital integrated communication module | |
| CN209032322U (en) | A kind of novel wearable obstructive sleep apnea syndrome early warning system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200313 |
|
| WD01 | Invention patent application deemed withdrawn after publication |