CN117504074A - Breathing machine output pressure control method and system - Google Patents
Breathing machine output pressure control method and system Download PDFInfo
- Publication number
- CN117504074A CN117504074A CN202311552214.5A CN202311552214A CN117504074A CN 117504074 A CN117504074 A CN 117504074A CN 202311552214 A CN202311552214 A CN 202311552214A CN 117504074 A CN117504074 A CN 117504074A
- Authority
- CN
- China
- Prior art keywords
- sleep state
- respiratory
- output pressure
- fuzzy inference
- fuzzy
- 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
- 230000029058 respiratory gaseous exchange Effects 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 86
- 230000007958 sleep Effects 0.000 claims abstract description 189
- 230000000241 respiratory effect Effects 0.000 claims abstract description 111
- 238000005070 sampling Methods 0.000 claims abstract description 79
- 208000001797 obstructive sleep apnea Diseases 0.000 claims abstract description 68
- 230000004461 rapid eye movement Effects 0.000 claims description 26
- 230000001276 controlling effect Effects 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 18
- 208000008784 apnea Diseases 0.000 claims description 15
- 206010021079 Hypopnoea Diseases 0.000 claims description 14
- 230000008667 sleep stage Effects 0.000 claims description 12
- 238000009423 ventilation Methods 0.000 claims description 12
- 230000004424 eye movement Effects 0.000 claims description 11
- 230000003434 inspiratory effect Effects 0.000 claims description 10
- 230000036391 respiratory frequency Effects 0.000 claims description 10
- 230000036387 respiratory rate Effects 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 6
- 206010062519 Poor quality sleep Diseases 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 230000008093 supporting effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 13
- 230000006872 improvement Effects 0.000 description 13
- 230000008569 process Effects 0.000 description 10
- 230000037053 non-rapid eye movement Effects 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 7
- 238000011282 treatment Methods 0.000 description 6
- 230000000414 obstructive effect Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 210000002345 respiratory system Anatomy 0.000 description 4
- RZVAJINKPMORJF-UHFFFAOYSA-N Acetaminophen Chemical compound CC(=O)NC1=CC=C(O)C=C1 RZVAJINKPMORJF-UHFFFAOYSA-N 0.000 description 3
- 208000029618 autoimmune pulmonary alveolar proteinosis Diseases 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000003860 sleep quality Effects 0.000 description 3
- 230000035565 breathing frequency Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 201000002859 sleep apnea Diseases 0.000 description 2
- 208000019116 sleep disease Diseases 0.000 description 2
- 208000020685 sleep-wake disease Diseases 0.000 description 2
- 206010000125 Abnormal dreams Diseases 0.000 description 1
- 208000007590 Disorders of Excessive Somnolence Diseases 0.000 description 1
- 208000000059 Dyspnea Diseases 0.000 description 1
- 206010013975 Dyspnoeas Diseases 0.000 description 1
- 206010021143 Hypoxia Diseases 0.000 description 1
- 206010041349 Somnolence Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000037007 arousal Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000007177 brain activity Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 230000007954 hypoxia Effects 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 230000037152 sensory function Effects 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M16/00—Devices for influencing the respiratory system of patients by gas treatment, e.g. mouth-to-mouth respiration; Tracheal tubes
- A61M16/0003—Accessories therefor, e.g. sensors, vibrators, negative pressure
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M16/00—Devices for influencing the respiratory system of patients by gas treatment, e.g. mouth-to-mouth respiration; Tracheal tubes
- A61M16/021—Devices for influencing the respiratory system of patients by gas treatment, e.g. mouth-to-mouth respiration; Tracheal tubes operated by electrical means
- A61M16/022—Control means therefor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M16/00—Devices for influencing the respiratory system of patients by gas treatment, e.g. mouth-to-mouth respiration; Tracheal tubes
- A61M16/0003—Accessories therefor, e.g. sensors, vibrators, negative pressure
- A61M2016/0027—Accessories therefor, e.g. sensors, vibrators, negative pressure pressure meter
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M16/00—Devices for influencing the respiratory system of patients by gas treatment, e.g. mouth-to-mouth respiration; Tracheal tubes
- A61M16/0003—Accessories therefor, e.g. sensors, vibrators, negative pressure
- A61M2016/003—Accessories therefor, e.g. sensors, vibrators, negative pressure with a flowmeter
Landscapes
- Health & Medical Sciences (AREA)
- Emergency Medicine (AREA)
- Pulmonology (AREA)
- Engineering & Computer Science (AREA)
- Anesthesiology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Hematology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method and a system for controlling output pressure of a breathing machine, wherein the method comprises the following steps: acquiring and judging an obstructive sleep apnea event in a unit sampling period according to a respiratory signal in the unit sampling period; according to the respiratory signal, calculating to obtain a sleep state corresponding to the unit sampling period by adopting a fuzzy reasoning method; and determining a ventilator output pressure compensation amount corresponding to the sleep state according to the obstructive sleep apnea event and the sleep state, and adjusting and controlling the output of the corresponding ventilator pressure according to the ventilator output pressure compensation amount. The method can dynamically adjust the output pressure of the breathing machine according to different sleep states, adjust and control the corresponding pressure output of the breathing machine in real time, has strong self-adaptability, can improve more personalized and finer pressure adjustment of the breathing machine, fully plays the supporting role of the breathing machine, and realizes the automatic analysis and the intelligent degree of a breathing machine control system.
Description
Technical Field
The invention relates to the technical field of medical equipment, in particular to a method and a system for controlling output pressure of a breathing machine.
Background
Sleep is vital to human life and is an integral part of maintaining physical health. Generally, sleep of the human body is mainly divided into two stages: REM (Rapid Eye Movement ) and NREM (Non-rapid Eye Movement, non-rapid eye movement), which alternate overnight. However, many individuals experience respiratory-related problems during sleep, such as OSA (Obstructive Sleep Apnea, obstructive sleep apnea event), a common sleep disorder. OSA is mainly characterized by collapse of the upper airway, resulting in obstructed oronasal ventilation, reduced ventilation flow, and even complete interruption, which repeatedly occurs during the night, resulting in hypoxia and sleep structural disturbances, and thus causing symptoms such as daytime sleepiness.
Currently, OSA events occurring during sleep are addressed by PAP (Positive Airway Pressure Device, positive airway pressure), which maintains the patency of upper breathing by applying positive airway pressure, effectively preventing the user from blocking the upper airway during sleep, reducing the occurrence of obstructive apneic events, and thus improving the user's sleep quality. However, PAP is currently mainly used for detecting and helping sleep disorder users breathe smoothly, but monitoring of sleep stages cannot be performed, and dynamic adjustment of pressure of a breathing machine when obstructive sleep apnea events occur in different sleep stages reduces the adaptivity and accuracy of pressure adjustment, so that the adaptivity of the breathing machine is poor.
Disclosure of Invention
One of the purposes of the present invention is to provide a method for controlling output pressure of a ventilator, so as to solve the problem that in the prior art, the pressure of the ventilator cannot be dynamically adjusted according to the sleep state when the obstructive sleep apnea event occurs, so that the self-adaption of the ventilator is low.
It is an object of the present invention to provide a ventilator output pressure control system.
In order to achieve one of the above objects, the present invention provides a method for controlling output pressure of a ventilator, comprising: acquiring and judging an obstructive sleep apnea event in a unit sampling period according to a respiratory signal in the unit sampling period; according to the respiratory signal, calculating to obtain a sleep state corresponding to the unit sampling period by adopting a fuzzy reasoning method; and determining a ventilator output pressure compensation amount corresponding to the sleep state according to the obstructive sleep apnea event and the sleep state, and adjusting and controlling the output of the corresponding ventilator pressure according to the ventilator output pressure compensation amount.
As a further refinement of an embodiment of the present invention the respiration signal comprises at least one of a respiration flow signal, a respiration effort signal and a respiration pressure signal.
As a further improvement of an embodiment of the present invention, the sleep state includes at least one of an awake state, a fast eye movement state, a light sleep state, and a deep sleep state; wherein in the awake state, the respiratory signal has a higher respiratory frequency and a higher fluctuation amplitude; in the rapid eye movement state, the respiratory signal has a higher respiratory frequency and a lower fluctuation amplitude; in the shallow sleep state, the respiratory signal has a respiratory frequency and a fluctuation amplitude higher than those of the deep sleep state; in the deep sleep state, the respiration signal has a low respiration rate and a low fluctuation amplitude.
As a further improvement of an embodiment of the present invention, the "acquiring and determining, according to the respiratory signal in the unit sampling period, that the obstructive sleep apnea event occurs in the unit sampling period" specifically includes: acquiring and calculating to obtain a corresponding respiratory impedance value according to the pressure signal and the flow signal of the respiratory gas in the unit sampling period; judging whether the respiratory impedance value is larger than a preset respiratory impedance threshold value or not; if yes, judging that the obstructive sleep apnea event occurs in the unit sampling period.
As a further improvement of an embodiment of the present invention, the "calculating the sleep state corresponding to the unit sampling period by using a fuzzy inference method according to the respiratory signal" specifically includes: analyzing and extracting signal characteristics corresponding to the respiratory signals to obtain a plurality of respiratory characteristics; and performing fuzzy reasoning operation on the respiratory characteristics by adopting a fuzzy reasoning method, and determining the sleep state corresponding to the unit sampling period according to the reasoning operation result.
As a further improvement of an embodiment of the present invention, the respiratory characteristics include at least one of depth of breath, peak-to-average ratio, minute ventilation, respiratory rate, expiratory flow amplitude, inspiratory flow amplitude.
As a further improvement of an embodiment of the present invention, the "performing a fuzzy inference operation on the plurality of respiratory features using a fuzzy inference method" determining a sleep state corresponding to the unit sampling period according to a result of the fuzzy inference operation specifically includes: constructing a first fuzzy inference model, respectively inputting each respiratory feature into the first fuzzy inference model, and performing fuzzification operation on each respiratory feature by adopting a membership function to obtain a plurality of corresponding membership values; based on a Mamdani fuzzy reasoning algorithm, calculating to obtain a plurality of respiratory feature fuzzy sets according to the plurality of membership values and a preset fuzzy reasoning rule base; performing defuzzification operation on the respiratory feature fuzzy sets by adopting a gravity center method to obtain a first fuzzy reasoning coefficient; and determining a sleep state corresponding to the unit sampling period according to the first fuzzy inference coefficient.
As a further improvement of an embodiment of the present invention, the "determining the sleep state corresponding to the unit sampling period according to the first fuzzy inference coefficient" specifically includes: judging whether the first fuzzy inference coefficient is larger than or equal to a preset inference coefficient threshold value or not; if yes, judging that the sleep state corresponding to the unit sampling period is a first sleep state, and determining whether the first sleep state is a rapid eye movement state according to the first fuzzy inference coefficient and the plurality of breathing characteristics; if not, judging that the sleep state corresponding to the unit sampling period is a second sleep state, and determining whether the second sleep state is a shallow sleep state according to the first fuzzy inference coefficient and the plurality of respiratory characteristics; wherein the first sleep state includes at least one of an awake state and a fast eye movement state; the second sleep state includes at least one of a light sleep state and a deep sleep state.
As a further improvement of an embodiment of the present invention, the "determining whether the first sleep state is a fast eye movement state according to the first fuzzy inference coefficient and the plurality of respiratory features" specifically includes: constructing a second fuzzy inference model, taking the first fuzzy inference coefficient and a plurality of breathing characteristics as the input of the second fuzzy inference model, and executing fuzzy inference operation to obtain a second fuzzy inference coefficient; if the second fuzzy inference coefficient is greater than or equal to the preset inference coefficient threshold, judging that the first sleep state is a rapid eye movement state; and if the second fuzzy inference coefficient is smaller than the preset inference coefficient threshold value, judging that the first sleep state is an awake state.
As a further improvement of an embodiment of the present invention, the "determining whether the second sleep state is a shallow sleep state according to the second fuzzy inference coefficient and the plurality of respiratory features" specifically includes: constructing a third fuzzy inference model, taking the first fuzzy inference coefficient and a plurality of breathing characteristics as the input of the third fuzzy inference model, and executing fuzzy inference operation to obtain a third fuzzy inference coefficient; if the third fuzzy inference coefficient is greater than or equal to the preset inference coefficient threshold, judging that the second sleep state is a shallow sleep state; and if the third fuzzy inference coefficient is smaller than the preset inference coefficient threshold value, judging that the second sleep state is a deep sleep state.
As a further improvement of an embodiment of the present invention, the "determining the ventilator output pressure compensation amount corresponding to the sleep state according to the obstructive sleep apnea event and the sleep state" specifically includes: acquiring and counting a pause duration T of the obstructive sleep apnea event in a current unit sampling period; acquiring and according to the output pressure P and the maximum output pressure P of the breathing machine in the current unit sampling period max And an apnea-hypopnea index AHI corresponding to the current sleep state, calculating a corresponding ventilator output pressure adjustment parameter P PR The method comprises the steps of carrying out a first treatment on the surface of the Acquiring a Fuzzy inference coefficient Fuzzy in a current unit sampling period, and adjusting a parameter P according to the Fuzzy inference coefficient Fuzzy and the output pressure of the breathing machine PR Calculating to obtain the output pressure compensation quantity P of the breathing machine MI 。
As a further improvement of an embodiment of the present invention, the Fuzzy inference coefficient Fuzzy includes at least one of a first Fuzzy inference coefficient, a second Fuzzy inference coefficient and a third Fuzzy inference coefficient.
As a further improvement of one embodiment of the present invention, the "adjusting parameter P according to the ventilator output pressure PR And the Fuzzy inference coefficient Fuzzy is calculated to obtain the output pressure compensation quantity P of the breathing machine MI "specifically includes:
the output pressure compensation quantity P of the breathing machine MI The output pressure regulating parameter P of the breathing machine PR The ventilator output pressure P and the maximum output pressure P in the current sampling period max The pause duration T during which the obstructive sleep apnea event occurs, the apnea-hypopnea index AHI, and the Fuzzy inference coefficient Fuzzy at least satisfy:
P MI ＝a 1 *P PR +a 2 *Fuzzy
Wherein a is 1 Weights representing the ventilator output pressure adjustment parameters, a 2 Weights, x, representing different sleep states 1 Weights, x, representing the apnea-hypopnea index AHI 2 A weight, x, representing a pause duration T during which said obstructive sleep apnea event occurs 3 Weights representing the ventilator output pressure.
As a further improvement of an embodiment of the present invention, the "adjusting and controlling the output of the corresponding ventilator pressure according to the ventilator output pressure compensation amount" specifically includes: acquiring the output pressure P of the breathing machine in the current unit sampling period; controlling the positive airway pressure system to increase the pressure output of the breathing machine on the basis of the output pressure P of the breathing machine, wherein the pressure output is increased to be the output pressure compensation quantity P of the breathing machine corresponding to the current sleep state MI 。
As a further improvement of an embodiment of the present invention, the detection of obstructive sleep apnea events occurring in a unit sampling period and the recognition of sleep stages are both configured in real time.
To achieve one of the above objects, an embodiment of the present invention provides a ventilator output pressure control system, including: the method comprises the steps of realizing the output pressure control method of the breathing machine according to any one of the above steps when the processor executes the computer program.
Compared with the prior art, the embodiment of the invention has at least one of the following beneficial effects:
the invention adopts a control and adjustment method for the output pressure of the breathing machine, and determines the compensation quantity of the output pressure of the breathing machine by combining the double information of the obstructive apnea event and the sleep state, and can dynamically adjust the output pressure of the breathing machine according to different sleep states so as to realize personalized sleep apnea treatment and improve the self-adaptability. The respiratory signal is identified, so that the unobstructed degree of the airflow can be directly reflected, and the identification accuracy of obstructive sleep apnea events can be improved; meanwhile, the uncertainty and gradual change of the sleep state can be intuitively represented by adopting a fuzzy reasoning method, so that the overall sleep quality of a user is better estimated, the accuracy of sleep state detection is improved, a basis is provided for the dynamic adjustment of the output pressure of a subsequent breathing machine, and the accuracy and reliability of pressure adjustment are improved.
Drawings
Fig. 1 is a schematic view of a ventilator according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a ventilator output pressure control system in accordance with an embodiment of the present invention.
Fig. 3 is a schematic diagram showing steps of a method for controlling output pressure of a ventilator according to an embodiment of the present invention.
Fig. 4 is a schematic representation of respiratory signal fluctuations corresponding to NREM-OSA events and REM-OSA events in an embodiment of the present invention.
Fig. 5 is a schematic diagram showing a refinement step of step S1 of the ventilator output pressure control method according to an embodiment of the present invention.
Fig. 6 is a schematic diagram showing a refinement step of step S2 of the ventilator output pressure control method according to an embodiment of the present invention.
Fig. 7 is a schematic diagram showing a refinement step of step S22 of the ventilator output pressure control method according to an embodiment of the present invention.
Fig. 8 (a) is a schematic diagram of a fuzzy membership function based on a depth of breath characteristic in a method for ventilator output pressure control in accordance with an embodiment of the present invention.
Fig. 8 (b) is a schematic diagram of membership function based on peak-to-average ratio characteristics in a method for controlling output pressure of a ventilator according to an embodiment of the present invention.
FIG. 8 (c) is a graphical representation of membership functions based on minute ventilation characteristics in a ventilator output pressure control method in accordance with an embodiment of the present invention.
Fig. 8 (d) is a schematic diagram of a membership function based on respiratory rate characteristics in a method for controlling output pressure of a ventilator according to an embodiment of the present invention.
Fig. 8 (e) is a schematic diagram of membership function based on expiratory flow amplitude feature in a ventilator output pressure control method according to an embodiment of the present invention.
Fig. 8 (f) is a schematic diagram of membership function based on inspiratory flow amplitude characteristics in a ventilator output pressure control method according to an embodiment of the present invention.
Fig. 9 is a schematic diagram showing a refinement step of step S224 of the ventilator output pressure control method according to an embodiment of the present invention.
Fig. 10 is a schematic diagram showing sleep state classification results of a method for controlling output pressure of a ventilator according to an embodiment of the present invention.
Fig. 11 is a schematic diagram showing a refinement step of step S3 of the ventilator output pressure control method according to an embodiment of the present invention.
Fig. 12 is a flowchart of a preferred embodiment of a method for controlling output pressure of a ventilator according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to specific embodiments shown in the drawings. These embodiments are not intended to limit the invention and structural, methodological, or functional modifications of these embodiments that may be made by one of ordinary skill in the art are included within the scope of the invention.
It should be noted that the term "comprises," "comprising," or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. In the description of the embodiments of the present invention, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
During sleep stages, obstructive sleep apnea (Obstructive Sleep Apnea, OSA) events may occur, which tend to lead to sleep structural disturbances, thus causing health problems. The obstructive sleep apnea event may occur at different stages of sleep, with some obstructive sleep apnea users having a low overall apnea hypopnea index (Apnea Hypopnea Index, AHI) but high during rapid eye movement (Rapid Eye Movement, REM) of sleep, which presents difficulties for clinical treatment of the obstructive sleep apnea event, and thus accurate identification of obstructive sleep apnea events associated with different sleep states is of great importance for determining obstructive sleep apnea event types and formulating corresponding treatment strategies.
Based on this, the present invention provides a ventilator output pressure control system 100, as shown in fig. 1 and 2, for monitoring and acquiring respiration signals within a current unit sampling period by a plurality of sensors 200, respectively, wherein the respiration signals may include a respiration flow signal and a respiration pressure signal; determining the sleep state of the user in the current unit sampling period and the dynamic change condition of the output pressure compensation quantity of the breathing machine when an obstructive sleep apnea event occurs according to the breathing signal; and controlling a breathing machine pressure supporting module 500 in the breathing machine, taking the pressure value currently output by the breathing machine as a reference, improving the output pressure, and amplifying to obtain the output pressure compensation quantity of the breathing machine.
Wherein the flow monitoring and the pressure monitoring in fig. 1 can be respectively performed by the sensor 200 (including the flow sensor and the pressure sensor) in fig. 2; the memory device 300 may be used to store the respiratory flow signal and the pressure flow signal acquired by the sensor 200; the ventilator pressure control system 400 may obtain and calculate and control ventilator pressure output in different sleep states from the storage device 300 based on the respiratory flow signal and the pressure flow signal; the ventilator pressure support module 500 may be configured to output the ventilator output pressure calculated by the ventilator pressure control system 400 to the airway of the user.
In addition, the invention also provides a method for controlling the output pressure of the breathing machine, as shown in fig. 3, which specifically comprises the following steps:
step S1, acquiring and judging an obstructive sleep apnea event in a unit sampling period according to a respiratory signal in the unit sampling period;
step S2, calculating to obtain a sleep state corresponding to the unit sampling period by adopting a fuzzy reasoning method according to the respiratory signal;
and step S3, determining a ventilator output pressure compensation amount corresponding to the sleep state according to the obstructive sleep apnea event and the sleep state, and adjusting and controlling the output of the corresponding ventilator pressure according to the ventilator output pressure compensation amount.
Thus, by combining the double information of the obstructive apnea event and the sleep state, the output pressure compensation quantity of the breathing machine is determined, the output pressure adjustment of the personalized breathing machine can be realized, and the self-adaptability is improved; meanwhile, by adopting a fuzzy reasoning method, the uncertainty and the gradual change of the sleep stage can be intuitively mapped to the determined sleep state, and the accuracy and the reliability of sleep state detection are improved.
Wherein the respiratory signal may comprise at least one of a respiratory flow signal, a respiratory effort signal, and a respiratory pressure signal. With continued reference to fig. 2, when it is identified that an obstructive pause event occurs, the ventilator output pressure compensation amount in step S3 may be controlled by the ventilator pressure support module 500 on the ventilator to increase the pressure output of the ventilator based on the current ventilator output pressure, and the pressure output of the ventilator is increased to the ventilator output pressure compensation amount, so that the airway of the human body is smooth, and the obstructive pause event no longer occurs.
In addition, normal human sleep may undergo cycles of two periods, NREM (Non-Rapid Eye Movement ) and REM (Rapid Eye Movement, rapid eye movement), which may occur repeatedly throughout the night, each period having a duration of about 90 to 120 minutes. In particular, the NREM period may be further divided into a shallow sleep state and a deep sleep state.
In one embodiment, an obstructive sleep apnea event that occurs during NREM may be referred to as NREM-OSA; in another embodiment, an obstructive sleep apnea event that occurs during REM may be referred to as REM-OSA. As shown in fig. 4, the REM-OSA and NREM-OSA are two types of Obstructive Sleep Apnea (OSA) that are associated with different sleep stages, respectively, with different characteristics and clinical manifestations.
On the one hand, the weakening of upper airway muscle tone during REM results in a greater susceptibility of the upper airway to collapse; on the other hand, the EELV (End-Expiratory Lung Volume ) value decreases significantly during REM, so that the longitudinal traction force of the airway decreases or weakens, airway collapse easily occurs, and thus obstructive sleep apnea event easily occurs during REM, and the upper airway resistance is maximum at this stage, and thus the respiratory signal corresponding to REM-OSA fluctuates more than NREM-OSA.
Furthermore, in one embodiment, the sleep state may include an awake state in which its corresponding respiratory signal has a higher respiratory frequency and a higher fluctuation amplitude, and in which each region of the brain remains in a state in which thinking is active and sensory functions are normal; in one embodiment, the sleep states may include a rapid eye movement state in which their corresponding respiratory signals have a higher respiratory rate and lower fluctuation amplitude, which is accompanied by active brain activity, rapid eye movement, and a vivid dream; in one embodiment, the sleep state may include a deep sleep state in which its corresponding respiratory signal has a low respiratory frequency and a low fluctuation amplitude, and in which it is difficult to wake up by external disturbances. In one embodiment, the sleep state may include a shallow sleep state in which the respiration frequency and the fluctuation amplitude of the corresponding respiration signal are higher than those of the deep sleep state, in other words, the respiration frequency and the fluctuation amplitude of the shallow sleep state are lower, but are higher than those of the deep sleep state, and in this state, the micro-wake is easily caused by interference of external noise or the like.
As shown in fig. 5, in one embodiment, the following steps may be specifically included for step S1:
step S11, obtaining and calculating to obtain a corresponding respiratory impedance value according to the pressure signal and the flow signal of the respiratory gas in the unit sampling period;
step S12, judging whether the respiratory impedance value is larger than a preset respiratory impedance threshold value;
if yes, step S13 is skipped, and the obstructive sleep apnea event occurs in the unit sampling period is judged.
Therefore, the respiratory impedance is calculated only by using the pressure signal and the flow signal, the respiratory fluency can be quantitatively reflected, and whether the obstructive sleep apnea occurs or not can be accurately judged.
Wherein the respiratory impedance value refers to the extent to which airflow is impeded or restricted in the respiratory tract. When the respiratory tract is blocked or stenosed, resistance is encountered by the flow of air through the respiratory tract, resulting in dyspnea or non-smooth breathing. The obstructive sleep apnea is a sleep breathing disorder, which is manifested in that the respiratory tract is repeatedly blocked partially or completely during sleep, resulting in apnea or very shallow breathing, which may result in insufficient oxygen supply, affecting sleep quality. Thus, whether the airway of the user is blocked in the current sleep stage can be directly known by calculating the respiratory impedance value.
As shown in fig. 6, in one embodiment, for step S2, the present invention provides a refinement step, which may specifically include:
s21, analyzing and extracting signal characteristics corresponding to the respiratory signals to obtain a plurality of respiratory characteristics;
and S22, performing fuzzy reasoning operation on the respiratory characteristics by adopting a fuzzy reasoning method, and determining the sleep state corresponding to the unit sampling period according to the reasoning operation result.
Therefore, by adopting a fuzzy reasoning method suitable for processing the fuzzy uncertain breathing signals, the fuzzy uncertain breathing characteristics can be mapped to the determined sleep state, so that the judgment on the sleep state is more accurate and reliable.
It should be noted that, in the awake state and the fast eye movement state, and in the non-fast eye movement state (i.e., the shallow sleep state or the deep sleep state), the fluctuation amplitude of the respiratory signal and the respiratory fluctuation situation are greatly different. Based on this, signal features corresponding to the respiratory signal may be analyzed and extracted to enable classification of different sleep stages.
Specifically, in one embodiment, the respiratory feature may include depth of respiration. The depth of breath may be determined by monitoring the variability of the inspiratory flow and expiratory flow amplitude differences over a unit sampling period, and in particular by calculating the median or variance of the inspiratory flow and expiratory flow amplitude differences over a unit sampling period to determine the corresponding depth of breath.
In one embodiment, the respiratory characteristics may include peak-to-average ratio. The peak-to-average ratio can be calculated and determined by calculating and determining the variation of the ratio of the peak value of the inspiration flow to the average value of the inspiration flow in the unit sampling period, and when the fluctuation amplitude of the inspiration flow signal is large, the peak-to-average ratio is large, namely the period of time has large inspiration flow variability.
In one embodiment, the respiratory characteristics may include minute ventilation. The minute ventilation may be determined by calculating the variability of ventilation in a unit sampling period, and in particular by calculating the variance or entropy of ventilation in a unit sampling period to determine the minute ventilation.
In one embodiment, the respiratory characteristics may include respiratory rate. The respiratory rate may be determined by calculating the variability of the respiratory rate in unit sampling periods, and in particular by calculating the variance or entropy of the respiratory rate in unit sampling periods.
In one embodiment, the respiratory feature may include an expiratory flow amplitude. The expiratory flow amplitude may be determined by calculating the variability of the expiratory flow amplitude in a unit sampling period, in particular by calculating the variance or entropy of the expiratory flow amplitude in a unit sampling period.
In one embodiment, the respiratory feature may include an inspiratory flow amplitude. The inspiratory flow amplitude may be determined by calculating the variability of the inspiratory flow amplitude over a unit sampling period, and in particular by calculating the average or median of the inspiratory flow amplitude over a unit sampling period.
In a preferred embodiment, the above six embodiments may be used in combination, although other combinations are not excluded and may be freely adjusted according to the actual situation.
Furthermore, the essence of the fuzzy inference method is the computation process of mapping a given input space to a specific output space by means of fuzzy logic. In other words, the fuzzy reasoning method can design different fuzzy sets and fuzzy rules according to different input characteristics, so that corresponding reasoning is carried out according to different input characteristics, and an output value is obtained. In the invention, the score value or the probability value of different sleep states can be analytically inferred by adopting a fuzzy inference method, so that the sleep state can be determined.
Based on this, as shown in fig. 7, in one embodiment, the following steps may be specifically included for step S22:
Step S221, a first fuzzy inference model is built, each breathing characteristic is input into the first fuzzy inference model, and fuzzy operation is carried out on each breathing characteristic by adopting a membership function, so that a plurality of corresponding membership values are obtained;
step S222, calculating a plurality of respiratory feature fuzzy sets based on a Mamdani fuzzy reasoning algorithm according to the plurality of membership values and a preset fuzzy reasoning rule base;
step S223, performing defuzzification operation on the respiratory feature fuzzy sets by adopting a gravity center method to obtain a first fuzzy inference coefficient;
step S224, determining a sleep state corresponding to the unit sampling period according to the first fuzzy inference coefficient.
In this way, uncertainty and ambiguity in respiratory features can be mapped into specific language descriptions by adopting membership functions, then a Mamdani fuzzy reasoning algorithm is used for multi-rule reasoning to obtain corresponding fuzzy sets, and finally a gravity center method is used for defuzzification to determine a final sleep state, wherein the gravity center method can consider the overall features of the fuzzy sets, and the accuracy is higher.
Wherein the membership function may determine the degree of the appropriate fuzzy set to which the input data belongs. In one embodiment, the membership functions may be a combined membership function, such as a triangular membership function shown in formula (1) and a trapezoidal membership function shown in formula (2), where the combined membership functions may perform the blurring operation on the respiratory features respectively. Of course, the present invention does not exclude other membership functions, and can be freely selected according to actual requirements, and the present invention is not particularly limited.
In particular, the membership value in step S221 may be understood as the degree to which each respiratory feature belongs to a certain suitable fuzzy set, and may be specifically classified into three classes, low, medium and high. For each of the respiratory characteristics described above, different blur levels may be established according to different sleep state degrees, and reference may be made to membership functions corresponding to different respiratory characteristics as shown in fig. 8 (a) to 8 (f); wherein the corresponding output value is determined from the input value for each respiratory feature, the output value may comprise a plurality of values.
For example, referring to fig. 8 (a), assuming that the input value of the depth of breath is 3, the value is less than 5, and the corresponding output value is "low", so the depth of breath membership value is "low"; assuming an input value of 7.5 for depth of breath, the corresponding output value is "low, high", i.e. the depth of breath membership value is "low, high".
In addition, the Mamdani fuzzy inference algorithm is a decision method based on fuzzy inference. The preset fuzzy inference rule base can be built automatically according to experience and actual requirements, namely, all fuzzy rules are combined together, and the fuzzy rule base can be used for describing the relation between input variables and output variables. In the invention, when a fuzzy inference algorithm is executed on each respiratory feature, the respiratory feature can be used as input, and the inference can be performed according to a preset fuzzy inference rule base to obtain an inference result. Thus, the uncertainty and the ambiguity of the input data can be better processed by using the algorithm, the reasoning result is easy to explain, and no complex calculation process or intermediate steps exist, so that the algorithm has higher operation efficiency.
The gravity center method can convert a fuzzy set into a uniquely determined numerical value, and the method can fully consider the whole information of the fuzzy set, and has stable output value, namely, the first fuzzy inference coefficient can be output in the invention.
Further, as shown in fig. 9, in one embodiment, the following steps may be specifically included for step S224:
step S2241, judging whether the first fuzzy inference coefficient is larger than or equal to a preset inference coefficient threshold value;
if yes, step S2242A is skipped, the sleep state corresponding to the unit sampling period is judged to be a first sleep state, and whether the first sleep state is a rapid eye movement state is determined according to the first fuzzy inference coefficient and the plurality of respiratory characteristics;
if not, step S2242B is skipped, the sleep state corresponding to the unit sampling period is determined to be the second sleep state, and whether the second sleep state is the shallow sleep state is determined according to the first fuzzy inference coefficient and the plurality of respiratory characteristics.
Therefore, the corresponding relation between the reasoning coefficient and the sleep state is fully utilized, the reasoning coefficient threshold value is set for division, and different sleep sub-states are further subdivided, so that different sleep states can be effectively distinguished, and the judgment result is more accurate and reliable.
Wherein the first sleep state may include at least one of an awake state and a fast eye movement state; the second sleep state may include at least one of a light sleep state and a deep sleep state.
It should be noted that the first sleep state (i.e., NREM period) and the second sleep state (i.e., REM period) are easily distinguished by the fluctuation amplitude and frequency of the respiratory signal in the unit sampling period, because the fluctuation amplitude and frequency of the respiratory signal in the two periods are greatly different. And the sub-sleep state of the first sleep state or the second sleep state can be further judged on the basis of the first fuzzy inference coefficient.
Based on this, in one embodiment, for the "determine whether the first sleep state is a fast eye movement state according to the first fuzzy inference coefficient and the several respiratory characteristics" part in step S2242A may specifically include the following steps:
step S2242A1, constructing a second fuzzy inference model, taking the first fuzzy inference coefficient and a plurality of breathing characteristics as the input of the second fuzzy inference model, and executing fuzzy inference operation to obtain a second fuzzy inference coefficient;
step S2242A2, if the second fuzzy inference coefficient is greater than or equal to the preset inference coefficient threshold, determining that the first sleep state is a rapid eye movement state;
Step S2242A3, if the second fuzzy inference coefficient is smaller than the preset inference coefficient threshold, determining that the first sleep state is an awake state.
Therefore, the combination of the two fuzzy inference models is fully utilized, more complex reasoning and decision can be realized, and the judgment result is more accurate and reliable.
In another embodiment, for the "determining whether the second sleep state is a shallow sleep state according to the second fuzzy inference coefficient and the plurality of respiratory features" part in step S2242B may specifically include the following steps:
step S2242B1, a third fuzzy inference model is constructed, the first fuzzy inference coefficient and a plurality of breathing characteristics are used as the input of the third fuzzy inference model, and fuzzy inference operation is executed to obtain a third fuzzy inference coefficient;
step S2242B2, if the third fuzzy inference coefficient is greater than or equal to the preset inference coefficient threshold, determining that the second sleep state is a shallow sleep state;
step S2242B3, if the third fuzzy inference coefficient is smaller than the preset inference coefficient threshold, determining that the second sleep state is a deep sleep state.
Therefore, the combination of the two fuzzy inference models is fully utilized, more complex reasoning and decision can be realized, and the judgment result is more accurate and reliable.
Wherein the first fuzzy inference coefficient is used as an input parameter of the second fuzzy inference model and the third fuzzy inference model. In a preferred embodiment, the number of respiratory features corresponding to the second fuzzy inference model may include minute ventilation, respiratory rate, and the first fuzzy inference coefficient; the plurality of respiratory features corresponding to the third fuzzy inference model may include an inspiratory flow amplitude, an expiratory flow amplitude, and the first fuzzy inference coefficient.
The first fuzzy inference coefficient can be used for distinguishing a first sleep state and a second sleep state; the second fuzzy inference coefficient may be used to distinguish sub-states of the first sleep state, i.e., to distinguish rapid eye movement state REM from awake state; the third fuzzy inference coefficient may be used to distinguish sub-states of the second sleep state, i.e. to distinguish between a shallow sleep state and a deep sleep state.
In addition, steps S2242A1 to S2242A3 and steps S2242B1 to S2242B3 may be executed alternately, and the two may be executed in parallel or sequentially. Step S2242A2 may be performed after step S2242A3, and step S2242B2 may be performed after step S2242B 3.
In one embodiment, as shown in fig. 10, by adopting the first fuzzy inference model to the third fuzzy inference model, the whole sleep stage can be divided into different sleep states and continuous time lengths, so that whether the obstructive sleep apnea event occurs in the different sleep states can be monitored in real time later.
As shown in fig. 11, in one embodiment, for the "determining a ventilator output pressure compensation amount corresponding to the sleep state according to the obstructive sleep apnea event and the sleep state" portion of step S3, the present invention provides a refinement step, which may specifically include:
step S311, obtaining and counting a pause time T of the obstructive sleep apnea event in the current unit sampling period;
step S312, obtaining and based on the ventilator output pressure P and the maximum output pressure P in the current unit sampling period max And an apnea-hypopnea index AHI corresponding to the current sleep state, calculating a corresponding ventilator output pressure adjustment parameter P PR ；
Step S313, obtaining Fuzzy inference coefficient Fuzzy in the current unit sampling period, and adjusting parameter P according to the Fuzzy inference coefficient Fuzzy and the output pressure of the breathing machine PR Calculating to obtain the output pressure compensation quantity P of the breathing machine MI 。
Therefore, a plurality of parameters in the current unit sampling period are comprehensively considered, so that the output pressure compensation quantity of the breathing machine is more accurate and reasonable, the output pressure compensation quantity of the breathing machine can be dynamically adjusted by combining the reasoning coefficient corresponding to the current sleep state, the self-adaption is strong, the output pressure adjustment of the breathing machine which is more personalized and finer can be improved, and the automatic analysis and the intelligent degree of the breathing machine are realized.
Wherein, the output pressure P of the breathing machine refers to the treatment pressure of the current breathing machine output to the outside; the maximum output pressure P max Is the maximum output pressure provided by the breathing machine outwards; the apneic low ventilation Index AHI (Apnea-hyppnea Index) can be used to assess the severity of sleep Apnea, as determined by counting the total number of apneic and hypopneas events that occur per hour.
In addition, the Fuzzy inference coefficient Fuzzy may include at least one of a first Fuzzy inference coefficient, a second Fuzzy inference coefficient, and a third Fuzzy inference coefficient. Specifically, the first fuzzy inference model may output the first fuzzy inference coefficient; the second fuzzy inference model may output the second fuzzy inference coefficient; the third fuzzy inference model may output the third fuzzy inference coefficient.
Further, according to the sleep state of the obstructive sleep apnea event occurring in the current unit sampling period, determining the corresponding apnea-hypopnea index AHI, and further determining the corresponding output pressure adjustment parameter P of the breathing machine PR Corresponding output pressure compensation quantity P of the breathing machine MI The output pressure compensation quantity P of the breathing machine MI The output pressure regulating parameter P of the breathing machine PR The ventilator output pressure P and the maximum output pressure P in the current sampling period max The suspension period T during which the obstructive sleep apnea event occurs, the apnea-hypopnea index AHI, and the Fuzzy inference coefficient Fuzzy may satisfy at least the formula (3) and the formula (4):
P MI ＝a 1 *P PR +a 2 *Fuzzy (3)
wherein a is 1 Weights representing the ventilator output pressure adjustment parameters, a 2 Weights representing different sleep states，x 1 Representing the weight, x, associated with the apneic hypopneas index AHI 2 A weight, x, representing a pause duration T during which said obstructive sleep apnea event occurs 3 Weights representing the ventilator output pressure.
The Fuzzy inference coefficient Fuzzy can be dynamically adjusted according to the sleep state where the obstructive sleep apnea event occurs in the current unit sampling period. Specifically, in one embodiment, if the sleep state in which the obstructive sleep apnea event occurs in the current unit sampling period is a deep sleep state, the Fuzzy inference coefficient Fuzzy may be a third Fuzzy inference coefficient; in another embodiment, if the sleep state in which the obstructive sleep apnea event occurs in the current unit sampling period is a fast eye movement state, the Fuzzy inference coefficient Fuzzy may be a second Fuzzy inference coefficient.
Based on the output of the ventilator pressure adjusted according to the ventilator output pressure compensation amount in the current sleep state, the "output according to the ventilator output pressure compensation amount, adjust and control the corresponding ventilator pressure" in step S3 may specifically include the following steps:
step S321, obtaining the output pressure P of the breathing machine in the current unit sampling period;
step S322, controlling the positive airway pressure system to increase the pressure output of the ventilator based on the ventilator output pressure P, and increasing the output pressure compensation amount P of the ventilator corresponding to the current sleep state MI 。
Therefore, the pressure output result of the breathing machine in different sleep states can be dynamically adjusted according to the pressure of the current breathing machine, and the breathing machine has strong flexibility and good treatment effect.
Wherein the positive airway pressure (Positive Airway Pressure, PAP) system may include at least one of a continuous positive airway pressure (Continuous Positive Airway Pressure, CPAP) and an automatic positive airway pressure system (Auto Continuous Airway Pressure, APAP).
In particular, the CPAP system may be used as an effective means of treating obstructive sleep apnea events. The user is connected with a positive pressure air source by wearing a nose mask or a face mask, and the upper airway is supported and stabilized by controlling and adjusting the pressure output of the breathing machine, so that the upper airway occlusion is eliminated, and the obstructive sleep apnea event can be effectively eliminated; the APAP system may dynamically change the output pressure of the ventilator based on the current user's breathing data. Preferably, the PAP system may employ an APAP system. Further, the ventilator output pressure may be the pressure that the ventilator uses to input to the airway of the user to relieve or treat obstructive sleep apnea events.
It should be noted that, no matter which sleep state the user is in, the positive airway pressure system has an initial ventilator output pressure P, and the ventilator output pressure compensation amount P corresponds to the current sleep state MI May be attached to the initial ventilator output pressure P, generating a pressure such as P+P MI Is a ventilator output pressure. In addition, the treatment pressure of the breathing machine output by the positive airway pressure system is not always increased, and when the obstructive sleep apnea event is relieved under the action of the output pressure of the breathing machine, the breathing frequency to be measured tends to the normal breathing frequency, and the positive airway pressure system is controlled to reduce the output of the pressure of the breathing machine; when the respiratory frequency is normal, the positive airway pressure system is controlled to gradually reduce the output of the respirator pressure until the output pressure of the respirator is reduced to the minimum output pressure.
In addition, the dividing process of the sleep state and the identifying process of the obstructive sleep apnea event can be executed in parallel, or the dividing process of the sleep state can be executed first, and then whether the obstructive sleep apnea event occurs in each sleep state is identified based on the dividing result; the recognition process of the obstructive sleep apnea event can be executed first, and then the sleep state corresponding to the event can be determined. The present invention is not particularly limited in this regard.
The detection process of the occurrence of the obstructive sleep apnea event and the recognition process of the sleep stage in the unit sampling period are configured in real time. In other words, by continuously monitoring the respiratory signal, the sleep state is determined in real time and the OSA event is detected in real time by using the fuzzy inference method and the fuzzy inference model. Meanwhile, according to the detection result, the output pressure of the breathing machine is timely adjusted to ensure that a user obtains optimal breathing support, real-time and continuous monitoring and adjustment are realized, and the self-adaptability and the working efficiency of the breathing machine are improved.
The various embodiments, examples or specific examples provided herein may be combined with one another to ultimately form a plurality of preferred embodiments.
For example, fig. 12 shows a flowchart of a method for controlling output pressure of a ventilator according to a preferred embodiment. The processing of the preferred embodiment will be summarized below in connection with fig. 12.
In a unit sampling period, collecting a respiratory flow signal and a respiratory pressure signal through a sensor; and carrying out data processing on the acquired signal data, and calculating to obtain a plurality of respiratory characteristics.
And constructing and inputting the respiratory features into the first fuzzy inference model based on the first fuzzy inference model to perform fuzzy inference operation so as to distinguish and obtain a first sleep state and a second sleep state.
A second fuzzy inference model and a third fuzzy inference model are constructed, a first fuzzy inference coefficient and a corresponding breathing characteristic which are output by the first fuzzy inference model are respectively input into the second fuzzy inference model and the third fuzzy inference model, and a sub-sleep state (arousal and rapid eye movement) and a second fuzzy inference coefficient in a first sleep state, and a sub-sleep state (including shallow sleep and deep sleep) and a third fuzzy inference coefficient in a second sleep state are obtained through calculation.
And identifying whether obstructive sleep apnea events occur in different sleep states according to the respiratory signals, if so, calculating to obtain the output pressure compensation quantity of the breathing machine in different sleep states according to the first fuzzy inference coefficient or the second fuzzy inference coefficient or the third fuzzy inference coefficient, and further obtaining the corresponding output pressure of the breathing machine.
The invention also provides a ventilator output pressure control system, comprising: the method comprises the steps of realizing the output pressure control method of the breathing machine according to any one of the above steps when the processor executes the computer program.
In summary, according to the method for controlling the output pressure of the breathing machine, the breathing impedance value is calculated by acquiring and according to the breathing signals in the unit sampling period, so that the breathing smoothness degree can be quantitatively reflected, and whether obstructive sleep apnea occurs or not can be accurately judged; the uncertain respiratory characteristics or respiratory signals can be mapped to the determined sleep state by adopting a fuzzy reasoning method, so that the accuracy and the reliability are high; and finally, based on obstructive sleep apnea events generated in different sleep stages, the output pressure output of the corresponding breathing machine is adjusted and controlled in real time, so that the self-adaption is strong, the more personalized and finer adjustment of the output pressure of the breathing machine can be improved, the supporting effect of the breathing machine is fully exerted, and the automatic analysis and the intelligent degree of a breathing machine control system are realized.
It should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is for clarity only, and that the skilled artisan should recognize that the embodiments may be combined as appropriate to form other embodiments that will be understood by those skilled in the art.
The above list of detailed descriptions is only specific to practical embodiments of the present invention, and they are not intended to limit the scope of the present invention, and all equivalent embodiments or modifications that do not depart from the spirit of the present invention should be included in the scope of the present invention.
Claims (16)
1. A method of ventilator output pressure control, comprising:
acquiring and judging an obstructive sleep apnea event in a unit sampling period according to a respiratory signal in the unit sampling period;
according to the respiratory signal, calculating to obtain a sleep state corresponding to the unit sampling period by adopting a fuzzy reasoning method;
and determining a ventilator output pressure compensation amount corresponding to the sleep state according to the obstructive sleep apnea event and the sleep state, and adjusting and controlling the output of the corresponding ventilator pressure according to the ventilator output pressure compensation amount.
2. The ventilator output pressure control method of claim 1, wherein the respiratory signal comprises at least one of a respiratory flow signal, a respiratory effort signal, and a respiratory pressure signal.
3. The method of claim 1, wherein the sleep state comprises at least one of an awake state, a fast eye movement state, a light sleep state, and a deep sleep state; wherein in the awake state, the respiratory signal has a higher respiratory frequency and a higher fluctuation amplitude; in the rapid eye movement state, the respiratory signal has a higher respiratory frequency and a lower fluctuation amplitude; in the shallow sleep state, the respiratory signal has a respiratory frequency and a fluctuation amplitude higher than those of the deep sleep state; in the deep sleep state: the respiratory signal has a lower respiratory frequency and a lower fluctuation amplitude.
4. The method according to claim 1, wherein the step of acquiring and determining that the obstructive sleep apnea event occurs in the unit sampling period according to the respiratory signal in the unit sampling period comprises:
acquiring and calculating to obtain a corresponding respiratory impedance value according to the pressure signal and the flow signal of the respiratory gas in the unit sampling period;
judging whether the respiratory impedance value is larger than a preset respiratory impedance threshold value or not;
if yes, judging that the obstructive sleep apnea event occurs in the unit sampling period.
5. The method according to claim 1, wherein the calculating the sleep state corresponding to the unit sampling period according to the respiratory signal by using a fuzzy inference method specifically includes:
analyzing and extracting signal characteristics corresponding to the respiratory signals to obtain a plurality of respiratory characteristics;
and performing fuzzy reasoning operation on the respiratory characteristics by adopting a fuzzy reasoning method, and determining the sleep state corresponding to the unit sampling period according to the reasoning operation result.
6. The ventilator output pressure control method of claim 5, wherein the breathing characteristics comprise at least one of depth of breath, peak-to-average ratio, minute ventilation, respiratory rate, expiratory flow amplitude, inspiratory flow amplitude.
7. The method according to claim 5, wherein the step of performing a fuzzy inference operation on the plurality of respiratory features by using a fuzzy inference method, and determining the sleep state corresponding to the unit sampling period according to the result of the fuzzy inference operation, specifically comprises:
constructing a first fuzzy inference model, respectively inputting each respiratory feature into the first fuzzy inference model, and performing fuzzification operation on each respiratory feature by adopting a membership function to obtain a plurality of corresponding membership values;
based on a Mamdani fuzzy reasoning algorithm, calculating to obtain a plurality of respiratory feature fuzzy sets according to the plurality of membership values and a preset fuzzy reasoning rule base;
performing defuzzification operation on the respiratory feature fuzzy sets by adopting a gravity center method to obtain a first fuzzy reasoning coefficient;
and determining a sleep state corresponding to the unit sampling period according to the first fuzzy inference coefficient.
8. The method according to claim 7, wherein the determining the sleep state corresponding to the unit sampling period based on the first fuzzy inference coefficient specifically includes:
Judging whether the first fuzzy inference coefficient is larger than or equal to a preset inference coefficient threshold value or not;
if yes, judging that the sleep state corresponding to the unit sampling period is a first sleep state, and determining whether the first sleep state is a rapid eye movement state according to the first fuzzy inference coefficient and the plurality of breathing characteristics;
if not, judging that the sleep state corresponding to the unit sampling period is a second sleep state, and determining whether the second sleep state is a shallow sleep state according to the first fuzzy inference coefficient and the plurality of respiratory characteristics;
wherein the first sleep state includes at least one of an awake state and a fast eye movement state; the second sleep state includes at least one of a light sleep state and a deep sleep state.
9. The method of claim 8, wherein determining whether the first sleep state is a fast eye movement state based on the first fuzzy inference factor and the plurality of breathing characteristics comprises:
constructing a second fuzzy inference model, taking the first fuzzy inference coefficient and a plurality of breathing characteristics as the input of the second model inference model, and executing fuzzy inference operation to obtain a second fuzzy inference coefficient;
If the second fuzzy inference coefficient is greater than or equal to the preset inference coefficient threshold, judging that the first sleep state is a rapid eye movement state;
and if the second fuzzy inference coefficient is smaller than the preset inference coefficient threshold value, judging that the first sleep state is an awake state.
10. The method of claim 8, wherein determining whether the second sleep state is a shallow sleep state based on the second fuzzy inference factor and the plurality of breathing characteristics comprises:
constructing a third fuzzy inference model, taking the first fuzzy inference coefficient and a plurality of breathing characteristics as the input of the third fuzzy inference model, and executing fuzzy inference operation to obtain a third fuzzy inference coefficient;
if the third fuzzy inference coefficient is greater than or equal to the preset inference coefficient threshold, judging that the second sleep state is a shallow sleep state;
and if the third fuzzy inference coefficient is smaller than the preset inference coefficient threshold value, judging that the second sleep state is a deep sleep state.
11. The ventilator output pressure control method according to claim 1, wherein the determining a ventilator output pressure compensation amount corresponding to the sleep state based on the obstructive sleep apnea event and the sleep state specifically comprises:
Acquiring and counting a pause duration T of the obstructive sleep apnea event in a current unit sampling period;
acquiring and according to the output pressure P and the maximum output pressure P of the breathing machine in the current unit sampling period max And an apnea-hypopnea index AHI corresponding to the current sleep state, calculating a corresponding ventilator output pressure adjustment parameter P PR ；
Acquiring a Fuzzy inference coefficient Fuzzy in a current unit sampling period, and adjusting a parameter P according to the Fuzzy inference coefficient Fuzzy and the output pressure of the breathing machine PR Calculating to obtain the output pressure compensation quantity P of the breathing machine MI 。
12. The method of claim 11, wherein the Fuzzy inference factor Fuzzy zy comprises at least one of a first Fuzzy inference factor, a second Fuzzy inference factor, and a third Fuzzy inference factor.
13. The method according to claim 11, wherein the "adjusting the parameter P according to the Fuzzy inference coefficient Fuzzy and the ventilator output pressure" is performed PR Calculating to obtain the output pressure compensation quantity P of the breathing machine MI "specifically includes:
the output pressure compensation quantity P of the breathing machine MI The output pressure regulating parameter P of the breathing machine PR The ventilator output pressure P and the maximum output pressure P in the current sampling period max The pause duration T during which the obstructive sleep apnea event occurs, the apnea-hypopnea index AHI, and the Fuzzy inference coefficient Fuzzy at least satisfy:
P MI ＝a 1 *P PR +a 2 *Fuzzy
wherein a is 1 Weights representing the ventilator output pressure adjustment parameters, a 2 Weights, x, representing different sleep states 1 Weights, x, representing the apnea-hypopnea index AHI 2 A weight, x, representing a pause duration T during which said obstructive sleep apnea event occurs 3 Weights representing the ventilator output pressure.
14. The ventilator output pressure control method according to claim 1, wherein the "adjusting and controlling the output of the corresponding ventilator pressure according to the ventilator output pressure compensation amount" specifically includes:
acquiring the output pressure P of the breathing machine in the current unit sampling period;
controlling the positive airway pressure system to increase the pressure output of the breathing machine on the basis of the output pressure P of the breathing machine, wherein the increase is the output pressure compensation quantity of the breathing machine corresponding to the current sleep stateP MI 。
15. The method of claim 1, wherein the detection of obstructive sleep apnea events and the recognition of sleep stages in a unit sampling period are both configured in real time.
16. A ventilator output pressure control system, comprising:
a memory and a processor, said memory having a computer program executable on said processor, said processor implementing the steps of the ventilator output pressure control method of any of claims 1-15 when said computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311552214.5A CN117504074A (en) | 2023-11-21 | 2023-11-21 | Breathing machine output pressure control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311552214.5A CN117504074A (en) | 2023-11-21 | 2023-11-21 | Breathing machine output pressure control method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117504074A true CN117504074A (en) | 2024-02-06 |
Family
ID=89743492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311552214.5A Pending CN117504074A (en) | 2023-11-21 | 2023-11-21 | Breathing machine output pressure control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117504074A (en) |
-
2023
- 2023-11-21 CN CN202311552214.5A patent/CN117504074A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210085214A1 (en) | Detection of sleep condition | |
| JP7538200B2 (en) | Automatic control for flow restriction detection. | |
| JP5714903B2 (en) | Automated sleep phenotype | |
| JP4960964B2 (en) | Systems and methods for diagnosis and treatment of patient breathing patterns | |
| JP2011500110A5 (en) | ||
| CN117504074A (en) | Breathing machine output pressure control method and system | |
| AU2013267068B2 (en) | Detection of Sleep Condition | |
| EP4260798A1 (en) | Assessing sleep of a subject | |
| AU2015203494A1 (en) | Detection of Sleep Condition | |
| JP2020036949A (en) | Automated control for detection of flow limitation | |
| WO2023198499A1 (en) | Assessing sleep of a subject |
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 |