Inspection and testing-based method and apparatus for ventilation detection in patients with myasthenia

Abstract

The present invention relates to an inspection and testing-based apparatus for ventilation detection in patients with myasthenia. The apparatus comprises: a muscle strength monitoring module, which comprises an electromyographic sensor for collecting electromyographic signals and calculating a muscle strength index; a respiration monitoring module, which is connected to a mechanical ventilation device, and configured for acquiring respiration frequency, tidal volume, and inhalation time parameters of a patient; a blood detection module, which is configured for collecting a blood sample of the patient, and detecting a level of an inflammatory factor and a level of an anti-acetylcholine receptor antibody in blood; and a control module, which is configured for receiving muscle strength index data, respiration parameter change trend data, and blood detection data. When the muscle strength index is lower than a preset first threshold, a respiration parameter change trend is inconsistent with a preset mode, and when the level of the inflammatory factor or the level of the anti-acetylcholine receptor antibody in the blood is higher than a preset second threshold, it is determined that patient-ventilator asynchrony exists during ventilation.

Description

A method and device for detecting ventilation in patients with myasthenia gravis based on laboratory tests. Technical Field

[0001] This invention relates to the field of medical testing equipment technology, specifically to a ventilation detection method and device for patients with myasthenia gravis, and more particularly to a ventilation detection method and device for myasthenia gravis patients based on laboratory testing. Background Technology

[0002] Acquired myasthenia gravis is an autoimmune disease that primarily affects the function of the neuromuscular junction. The cause of acquired myasthenia gravis is that the body's immune system mistakenly attacks the acetylcholine receptors at the neuromuscular junction, preventing nerves from effectively transmitting signals to the muscles. The main symptoms of acquired myasthenia gravis include: muscle weakness, especially in the eye and facial muscles; ptosis (drooping eyelids); diplopia (double vision); dysphagia (difficulty swallowing); and dyspnea (difficulty breathing). Current diagnostic methods for acquired myasthenia gravis include: physical examination; blood tests (antibody testing); neurophysiological examination; and drug testing (such as the Nestin test). Traditional diagnostic methods rely on clinical assessment and electrophysiological testing, which are often time-consuming and somewhat invasive.

[0003] CN115177291A provides a method for identifying acquired myasthenia gravis in intensive care units (ICUs), comprising: acquiring muscle ultrasound data, medical text data, and clinical examination data of a patient; and, based on the muscle ultrasound data, the medical text data, and the clinical examination data, identifying the patient's acquired myasthenia gravis condition through a pre-defined multi-interactive memory network. This technical solution can identify the condition and severity of acquired myasthenia gravis in ICUs without causing muscle trauma.

[0004] The neurophysiological examination methods for acquired myasthenia gravis mentioned above have the following limitations, such as insufficient sensitivity (e.g., the repetitive nerve stimulation (RNS) test has low sensitivity in patients with ocular myasthenia gravis, which may lead to false negative results), low specificity, strong operation dependence, poor patient tolerance, and high equipment requirements). Existing methods for assessing motor function in acquired myasthenia gravis also suffer from limitations such as high subjectivity, lack of standardization, limited testing time, difficulty in quantifying disease severity and its impact on patients' quality of life, and insufficient sensitivity.

[0005] Myasthenia gravis affects the transmission of signals between nerves and muscles, leading to abnormal fatigue and weakness of skeletal muscles. This disease typically affects the extraocular muscles, facial muscles, throat muscles, and muscles of the limbs. When myasthenia gravis progresses to a more severe stage, it can affect the muscles that control breathing. This condition is called "myasthenic crisis" or "respiratory muscle weakness," an acute complication of myasthenia gravis. When respiratory muscles are affected, patients may experience difficulty breathing, and in severe cases, may be unable to breathe spontaneously, requiring emergency medical intervention, such as mechanical ventilation. Because myasthenia gravis is a neuromuscular junction disease, patients may exhibit varying degrees of neuromuscular weakness, which can affect their need for ventilator support. Myasthenia gravis patients are more prone to patient-ventilator asynchrony when using ventilators, i.e., a mismatch between the patient's spontaneous breathing and the assistance provided by the ventilator. This can cause discomfort and even worsen breathing difficulties. Currently, there is a lack of detection devices in the technology to assess the spontaneous breathing status of myasthenia gravis patients and whether their spontaneous breathing is matched with the assistance provided by the ventilator. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this application provides a ventilation detection method for patients with myasthenia gravis, applied to a respiratory support system, comprising: monitoring the muscle activity of the swallowing muscles and the muscle activity of the proximal limbs of the patient with myasthenia gravis; obtaining muscle strength data of the patient with myasthenia gravis based on the monitoring data of the swallowing muscle activity and the monitoring data of the proximal limb muscle activity; detecting the respiratory rate, tidal volume per respiratory cycle, and inspiratory time per respiratory cycle when the patient with myasthenia gravis is under mechanical ventilation; acquiring the trends of the changes in respiratory rate, tidal volume per respiratory cycle, and inspiratory time over time; and determining that human-ventilator resistance exists during mechanical ventilation of the patient with myasthenia gravis when the muscle strength data of the patient with myasthenia gravis is lower than a preset muscle strength threshold, and the trends of the changes in respiratory rate, tidal volume per respiratory cycle, and inspiratory time over time are inconsistent with the trends of the corresponding pre-stored parameters.

[0007] According to a preferred embodiment, obtaining muscle strength data of a patient with myasthenia gravis based on monitoring data of swallowing muscle activity and monitoring data of proximal limb muscle activity includes: collecting muscle strength data of a first time period when the patient performs a first standardized action as reference muscle strength data; collecting muscle strength data of a second time period after the patient performs the first standardized action for a preset time period; and analyzing muscle strength fluctuations based on the muscle strength data of the second time period and the reference muscle strength data.

[0008] According to a preferred embodiment, the first standardized action is swallowing and / or raising the arm.

[0009] According to a preferred embodiment, after determining that human-ventilator resistance exists during mechanical ventilation in a patient with myasthenia gravis, the method further includes: determining the type of human-ventilator resistance based on the changing trends of respiratory rate, tidal volume per respiratory cycle, and inspiratory time over time.

[0010] According to a preferred embodiment, if an increase in respiratory rate is accompanied by fluctuations in tidal volume waveform, it is determined that the ventilator failed to deliver air effectively.

[0011] According to a preferred embodiment, if an increase in respiratory rate is accompanied by an increase in inspiratory time, it is determined that the ventilator is not delivering enough gas.

[0012] According to a preferred embodiment, if the tidal volume is lower than a preset tidal volume threshold, the inspiratory time is shorter than a preset inspiratory time threshold, and the respiratory rate increases, then it is determined that the ventilator has premature expiratory triggering.

[0013] The ventilation detection method described in this application can, based on the disease characteristics of myasthenia gravis patients, and considering the changes in tidal volume, respiratory rate, and inspiratory time during mechanically assisted breathing, determine the presence and type of patient-ventilator resistance. This method helps ventilators promptly detect and adjust for patient-ventilator resistance when providing mechanical ventilation to myasthenia gravis patients.

[0014] This application also provides a ventilation detection device for patients with myasthenia gravis. The device includes: a muscle strength monitoring module configured to monitor the muscle activity of the swallowing muscles and the muscle activity of the proximal limbs of the patient with myasthenia gravis, and to obtain muscle strength data of the patient with myasthenia gravis based on the monitoring data of the swallowing muscle activity and the monitoring data of the proximal limb muscle activity; and a respiratory monitoring module configured to detect the respiratory rate, tidal volume per respiratory cycle, and inspiratory time per respiratory cycle when the patient with myasthenia gravis is receiving mechanical ventilation, and to obtain the respiratory rate, tidal volume per respiratory cycle, and inspiratory time over time. The control module, connected to the muscle strength monitoring module and the respiratory monitoring module, is configured to acquire muscle strength data of patients with myasthenia gravis from the muscle strength monitoring module and acquire the trends of respiratory rate, tidal volume and inspiratory time of patients with myasthenia gravis over time from the respiratory monitoring module. Specifically, when the muscle strength data of patients with myasthenia gravis is lower than the preset muscle strength threshold, and the trends of respiratory rate, tidal volume and inspiratory time over time are inconsistent with the trends of the corresponding pre-stored parameters, it is determined that there is human-ventilator resistance during mechanical ventilation of patients with myasthenia gravis.

[0015] According to a preferred embodiment, the control module is further configured to: if the respiratory rate increases and is accompanied by fluctuations in the tidal volume waveform, determine that there is a failure to effectively trigger the ventilator to deliver air.

[0016] According to a preferred embodiment, the control module is further configured to determine that the ventilator is not delivering enough gas if the respiratory rate increases and the inspiratory time increases.

[0017] This application further provides a system for monitoring a patient's muscle activity and maintaining the muscle strength of the patient's respiratory muscles, especially the diaphragm, using a wearable device. The system is capable of analyzing muscle strength data in real time to predict the risk of acquired myasthenia gravis and stimulating the patient's diaphragm with vibration, compression, electric shock, and / or infrared stimulation based on the detection results.

[0018] This application provides a respiratory support system for patients with acquired myasthenia gravis, including the aforementioned ventilation detection device. The system further includes: a chest support assembly comprising a first actuator configured to make external mechanical contact with the patient's chest and a first control unit signal-connected to the first actuator; and an abdominal support assembly comprising a second actuator configured to make external mechanical contact with the patient's abdomen and a second control unit signal-connected to the second actuator; wherein the first control unit and the second control unit are configured to cooperate with each other based on the patient's muscle strength data to provide mechanical and / or electrical stimulation to the patient's chest and abdomen, respectively, to assist the patient's breathing.

[0019] According to a preferred embodiment, the system further includes: a first sensor configured to monitor muscle activity of the swallowing muscles; a second sensor configured to monitor muscle activity of the proximal limb; and a data processing unit that receives detection data of muscle activity from the first sensor and / or the second sensor and calculates muscle strength data.

[0020] According to a preferred embodiment, the data processing unit is configured to collect muscle strength data of a first time period when the patient performs a first standardized action using a first sensor and / or a second sensor as reference muscle strength data, and to collect muscle strength data of a second time period after the patient performs the first standardized action using the first sensor and / or the second sensor for a preset time period to analyze muscle strength fluctuations.

[0021] According to a preferred embodiment, the first standardized action includes, but is not limited to, swallowing and / or raising the arm, with the proximal end of the limb being the patient's arm. The second sensor is configured to detect the motion acceleration of the patient's arm and the equivalent mass of the patient's arm. The data processing unit calculates muscle strength data of the user's arm during muscle activity based on the motion acceleration of the patient's arm detected by the second sensor and the equivalent mass of the patient's arm.

[0022] According to a preferred embodiment, the system further includes a sensing component configured to measure the movement of the patient's respiratory muscles to collect movement information, and to determine the movement state of the patient's respiratory muscles based on the collected movement information.

[0023] According to a preferred embodiment, the first control unit and the second control unit are configured to control the first actuator and the second actuator respectively to provide mechanical and / or electrical stimulation to the patient's chest and abdomen in accordance with the patient's motion state.

[0024] According to a preferred embodiment, the first actuator includes: an adjustable chest band that can surround the chest cavity, a first electrode disposed on the chest band for stimulating the pectoralis major muscle, a second electrode disposed on the chest band for stimulating the intercostal muscles, and an inflatable and deflated first mechanical airbag disposed on the chest band at corresponding positions on both sides of the chest cavity.

[0025] According to a preferred embodiment, the second actuator includes: an adjustable abdominal band that can surround the abdominal cavity, a third electrode disposed on the abdominal band for stimulating the rectus abdominis muscle, a fourth electrode disposed on the abdominal band for stimulating the external oblique muscle, and an inflatable second mechanical airbag disposed on the abdominal band at a position corresponding to the anterior side of the abdomen.

[0026] According to a preferred embodiment, the first and second actuators are configured to assist the patient in inhalation in the following manner: the first electrode activates the pectoralis major muscle to assist in lifting the thoracic cavity; the second electrode activates the intercostal muscles to help expand the thoracic cavity; the third and fourth electrodes activate the rectus abdominis and external oblique muscles, respectively, to assist in abdominal muscle contraction and descent of the diaphragm; the first mechanical airbags on both sides of the thoracic cavity inflate to assist in outward expansion of the thoracic cavity; the second mechanical airbag on the anterior side of the abdomen contracts to assist in descent of the diaphragm; the combined action of electrical stimulation and mechanical assistance increases the thoracic cavity volume, reduces intrathoracic pressure, and promotes air entry into the lungs.

[0027] According to a preferred embodiment, the first and second actuators are configured to assist the patient's exhalation in the following manner: the stimulation intensity of the first and second electrodes is reduced, allowing the thoracic cavity to naturally recoil; the stimulation intensity of the third and fourth electrodes is increased, assisting abdominal muscle contraction, compressing the abdominal cavity, and pushing the diaphragm upward; the first mechanical airbags on both sides of the thoracic cavity begin to deflate, allowing the thoracic cavity to recoil; the second mechanical airbag on the anterior side of the abdomen is inflated, assisting in compressing the abdominal cavity; the electrical stimulation and mechanical assistance work together to increase the intrathoracic pressure, pushing air out of the lungs.

[0028] The technical effects of the respiratory support system for patients with acquired myasthenia gravis in this application include: real-time monitoring and early warning. Through wearable devices, the system monitors swallowing muscles and proximal limb muscle activity in real time, enabling timely detection of subtle changes in muscle strength. By comparing muscle strength data from different time periods, the system can identify abnormal fluctuations in muscle strength early, providing a basis for early intervention. The system establishes personalized baseline data by collecting muscle strength data from patients performing standardized movements as a reference. This approach considers individual differences and improves the accuracy and specificity of the assessment, specifically in the following aspects: First, dynamic assessment: By comparing muscle strength data from different time periods, the system can dynamically assess the patient's muscle status, reflecting disease progression or improvement. Second, respiratory function protection: The system pays special attention to diaphragmatic function, one of the most dangerous complications in patients with acquired myasthenia gravis. Through the respiratory support unit, the system can actively maintain diaphragmatic strength, reducing the risk of respiratory failure. Through multimodal intervention, the respiratory support unit provides multiple stimulation modes, allowing the selection of the most suitable intervention mode based on the patient's specific condition. Non-invasive monitoring using wearable devices reduces disruption to the patient's daily life and improves patient compliance. The continuity and objectivity of the data are guaranteed because the system provides continuous and objective data, overcoming the shortcomings of traditional assessment methods, such as strong subjectivity and limited time points. Utilizing predictive analytics, by analyzing muscle strength fluctuation patterns, the system has the potential to predict the onset or exacerbation of acquired myasthenia gravis, supporting clinical decision-making. It also expands the possibilities for remote monitoring, providing the technological foundation for such monitoring, enabling medical teams to monitor patient conditions in real time and adjust treatment plans accordingly. Furthermore, it enables rehabilitation guidance; the data collected by the system can be used to guide patient rehabilitation training and help develop personalized rehabilitation plans. In summary, through real-time, objective, and continuous monitoring and timely intervention, this system has the potential to significantly improve the management of acquired myasthenia gravis, improve patient prognosis, and enhance quality of life. It provides an innovative and comprehensive solution for the diagnosis, treatment, and rehabilitation of acquired myasthenia gravis.

[0029] According to a preferred embodiment, the first sensor is a flexible sensor that is attached to a first region of the patient's swallowing muscle skin surface, which generates a first signal reflecting the strain change state of the first region and a second signal characterizing the curvature change state of the first region based on the deformation of the first region.

[0030] According to a preferred embodiment, the first sensor includes a strain sensing unit and an optical sensing unit. The strain sensing unit receives a first signal based on the deformation of a first region. The optical sensing unit receives a second signal based on the deformation of the first region.

[0031] According to a preferred embodiment, the data processing unit acquires muscle strength data of the patient's swallowing muscles based on a first signal and a second signal collected by a first sensor.

[0032] According to a preferred embodiment, the data processing unit further includes: a data receiving module for receiving muscle activity detection data from a first sensor and a second sensor; a data analysis module for calculating muscle strength data based on the received muscle activity detection data, analyzing the fluctuation of muscle strength using a predetermined algorithm model, and outputting a risk assessment result for acquired myasthenia gravis; and a user interface for displaying the analyzed risk assessment result and recommendations.

[0033] According to a preferred embodiment, the preset time period is adjusted based on the patient's muscle strength data in the first time period, historical muscle strength data, and / or medical orders.

[0034] According to a preferred embodiment, the data analysis module is configured with a machine learning algorithm to learn and adapt to the muscle strength fluctuation characteristics of individual patients and update the algorithm model over time. The data analysis module is also configured with an anomaly detection algorithm to detect and label outliers in the muscle strength data. Furthermore, the data analysis module is configured with a trend analysis algorithm to identify long-term trends and short-term fluctuations from muscle strength data over consecutive time periods to aid in assessing the progression of myasthenia gravis.

[0035] This application also relates to a ventilation detection device for patients with myasthenia gravis based on testing, comprising: a muscle strength monitoring module, including electromyography (EMG) sensors attached to the surface of the patient's swallowing muscles and proximal limb muscles for collecting EMG signals and calculating a muscle strength index; a respiratory monitoring module, connected to a mechanical ventilation device, for acquiring the patient's respiratory rate, tidal volume, and inspiratory time parameters, and analyzing the trend of parameter changes over time; a blood detection module, for collecting blood samples from the patient and detecting the levels of inflammatory factors and anti-acetylcholine receptor antibodies in the blood; and a control module, connected to the muscle strength monitoring module, respiratory monitoring module, and blood detection module respectively, for receiving muscle strength index data, respiratory parameter change trend data, and blood detection data; when the muscle strength index is lower than a preset first threshold, the respiratory parameter change trend is inconsistent with a preset mode, and the levels of inflammatory factors or anti-acetylcholine receptor antibodies in the blood are higher than a preset second threshold, it is determined that human-ventilator resistance exists during ventilation.

[0036] According to a preferred embodiment, the muscle strength monitoring module acquires electromyographic signals of the swallowing muscle group by means of electromyographic electrodes placed on the suprahyoid muscle group, with the proximal limb muscle being the middle of the deltoid muscle; the muscle strength index is the standardized root mean square electromyographic signal intensity.

[0037] According to a preferred embodiment, the inflammatory factors detected by the blood testing module also include interleukin-6, pH value, oxygen partial pressure and carbon dioxide partial pressure, as well as muscle damage markers, including creatine kinase and lactate dehydrogenase.

[0038] According to a preferred embodiment, when the control module detects a risk of human-ventilator resistance, it automatically adjusts the ventilation support mode, including switching from pressure control to volume control or bilevel ventilation mode, or adjusting the inspiratory pressure, positive end-expiratory pressure, and inspiratory-expiratory ratio to improve ventilation synchrony and patient comfort.

[0039] According to a preferred embodiment, the ventilation detection device further includes a human-machine interface module, configured to display the data collected by each module, the judgment results of the control module, and the adjustment results of ventilation parameters, and to receive input or confirmation of ventilation parameters from medical personnel; the human-machine interface module is configured to display the trend of muscle strength index, respiratory parameter curve, blood test index results, and the judgment results of the control module in graphical or numerical form, and to provide ventilation parameter adjustment suggestions, supporting medical personnel to manually adjust or confirm automatic adjustment operations.

[0040] This ventilation detection device improves the accuracy of judgment through multi-dimensional data fusion assessment. It not only relies on muscle strength and respiratory mechanics data, but also combines blood test results to comprehensively assess the condition of patients with myasthenia gravis, thereby improving the scientific nature and precision of ventilation strategies. Attached Figure Description

[0041] Figure 1 is a schematic flowchart of the ventilation detection method for patients with myasthenia gravis provided by the present invention;

[0042] Figure 2 is a schematic diagram of the module structure of the ventilation detection device for patients with myasthenia gravis provided by the present invention.

[0043] Figure 3 is a waveform diagram illustrating an example of "failure to effectively trigger ventilator delivery" provided in an embodiment of the present invention;

[0044] Figure 4 is a waveform diagram illustrating an example of "insufficient gas delivery by the ventilator" provided in an embodiment of the present invention;

[0045] Figure 5 is a waveform diagram illustrating an example of "pre-expiratory triggering" provided in an embodiment of the present invention;

[0046] Figure 6 is a schematic diagram of the system structure of the respiratory support system for patients with acquired myasthenia gravis provided by the present invention;

[0047] Figure 7 is a flowchart of the algorithm for acquired myasthenia gravis in patients provided by the present invention;

[0048] Figure 8 is a structural diagram of a respiratory support system for patients with acquired myasthenia gravis according to an embodiment of the present invention;

[0049] Figure 9 is a control flowchart of the inspiratory phase of an embodiment of the respiratory support system for patients with acquired myasthenia gravis of the present invention.

[0050] Figure 10 is a control flowchart of the expiratory phase of an embodiment of the respiratory support system for patients with acquired myasthenia gravis of the present invention.

[0051] List of reference numerals: 100: Chest assist assembly; 110: First actuator; 120: First control unit; 200: Abdominal assist assembly; 210: 220: Second actuator; 111: Chest strap; 112: First electrode; 113: Second electrode; 114: First mechanical airbag; 211: Abdominal strap; 212: Third electrode; 213: Fourth electrode; 214: Second mechanical airbag; 130: Wearable device; 131: First sensor; 132: Communication module; 133: Second sensor; 134: EMG sensor; 140: Data processing unit; 141: Data receiving module; 142: Data caching module; 143: Data analysis module; 144: Processor; 145: Memory; 146: Storage device; 150: User interface; 151: Mobile application; 152: Web interface; 153: Risk assessment and management plan module; 154: Educational resources and support materials; 160: Cloud storage server. Detailed Implementation

[0052] The following is a detailed explanation with reference to the accompanying drawings.

[0053] Myasthenia gravis is a chronic autoimmune disease that affects signal transmission between nerves and muscles, leading to abnormal fatigue and weakness of skeletal muscles. This disease typically affects the extraocular muscles, facial muscles, throat muscles, and muscles of the limbs. In some cases, myasthenia gravis can affect the muscles that control breathing, especially when the disease progresses to a more severe stage. This condition is called "myasthenic crisis" or "respiratory muscle weakness," and is an acute complication of myasthenia gravis. When respiratory muscles are affected, patients may experience difficulty breathing, and in severe cases, may be unable to breathe independently, requiring emergency medical intervention, such as mechanical ventilation.

[0054] For patients with myasthenia gravis using mechanical ventilation, there are some specific requirements and precautions compared to ordinary patients. Because myasthenia gravis is a neuromuscular junction disease, patients may exhibit varying degrees of neuromuscular weakness, which can affect their need for ventilator support. Therefore, frequent assessments of the patient's neuromuscular status, including muscle strength, respiratory depth, and rate, are necessary to adjust ventilator settings promptly. Using quantitative neuromuscular transmission tests (such as single-fiber electromyography or repetitive nerve stimulation tests) can help better understand the state of neuromuscular function, thereby guiding treatment decisions.

[0055] The inventors discovered in their research that during mechanical ventilation in patients with myasthenia gravis, the severity of myasthenia gravis varies among patients, leading to significant differences in muscle strength, especially in respiratory muscles. Since ventilator operating parameters are often set based on physician experience, patient-ventilator aversion frequently occurs due to mismatches between ventilator settings and patient needs. This can result in ineffective ventilator delivery, insufficient gas delivery, or premature expiratory triggering. This situation is even more common in myasthenia gravis patients with unstable muscle strength and significant inter-individual differences in muscle strength.

[0056] This application provides a ventilation detection method for patients with myasthenia gravis, applied to respiratory support systems, especially mechanical ventilation support systems, as shown in Figure 1. The method includes: monitoring the muscle activity of the swallowing muscles and the muscle activity of the proximal limbs in patients with myasthenia gravis; obtaining muscle strength data of patients with myasthenia gravis based on the monitoring data of the swallowing muscle activity and the muscle activity of the proximal limbs; detecting respiratory rate, tidal volume per respiratory cycle, and inspiratory time per respiratory cycle while providing mechanical ventilation to patients with myasthenia gravis; acquiring the trends of respiratory rate, tidal volume per respiratory cycle, and inspiratory time over time; and determining patient-ventilator resistance during mechanical ventilation when the muscle strength data of patients with myasthenia gravis is lower than a preset muscle strength threshold, and the trends of respiratory rate, tidal volume per respiratory cycle, and inspiratory time over time are inconsistent with the trends of the corresponding pre-stored parameters.

[0057] Tidal volume (VT): The amount of air that enters or leaves the lungs with each breath, usually expressed in milliliters (mL). The standard tidal volume for adults is 5-8 mL / kg of ideal body weight. Respiratory rate (RR): The number of breaths per minute, used to control minute ventilation (MV), which is the total amount of gas entering or leaving the lungs in one minute. The common respiratory rate range for adults is 10-20 breaths per minute. Inspiratory time (Ti): The duration of the inspiratory phase of each breath. The choice of inspiratory time affects the I:E ratio and overall breathing pattern.

[0058] This application provides a ventilation monitoring method for patients with myasthenia gravis, aiming to assess the occurrence of patient-ventilator resistance in real time by monitoring the changes in muscle activity and ventilation parameters, and to issue an alarm promptly when resistance occurs. Swallowing muscles are one of the most commonly affected sites in myasthenia gravis patients; monitoring their activity can reflect the neuromuscular functional state, especially when respiratory muscles are involved. Preferably, surface electromyography (sEMG) sensors are attached to the patient's larynx or neck to monitor the electrical activity of swallowing muscles (such as the cricopharynx and suprahyoid muscles). These sensors can capture the electrical signals generated during muscle contraction, thereby quantifying muscle strength. For example, signal processing algorithms (such as filtering, denoising, and feature extraction) can be used to convert the raw EMG signals into muscle strength data. Commonly used indicators include maximum RMS signal intensity and mean frequency (MNF).

[0059] Proximal limb muscles (such as shoulder girdle muscles and hip muscles) often share similar neural innervation pathways with respiratory muscles; therefore, changes in their muscle strength can indirectly reflect the state of the respiratory muscles. Surface electromyography (sEMG) sensors are preferably used, attached to the patient's scapular region, quadriceps femoris, etc., to monitor the electrical activity of proximal limb muscles. Similar to swallowing muscles, signal processing algorithms convert the electromyographic signals into muscle strength data.

[0060] Preferably, based on clinical experience, muscle strength in patients with myasthenia gravis typically declines gradually as the disease progresses. To establish a reasonable threshold, baseline measurements can be taken upon patient admission to record their normal muscle strength levels. Subsequently, the threshold is dynamically adjusted according to changes in the patient's condition. For example, for healthy adults, the maximum RMS signal intensity of the swallowing muscles is typically between 50-100 μV, and the RMS value of proximal limb muscles is between 100-300 μV. For example, when a patient's muscle strength decreases to less than 50% of the baseline value, it may indicate significant neuromuscular dysfunction and a high risk of respiratory failure. For example, if a patient's swallowing muscle RMS value drops below 25 μV, or the proximal limb muscle RMS value drops below 150 μV, an alarm is triggered, indicating the need for further evaluation of respiratory support.

[0061] The inventors discovered in their research that the assessment of patient-ventilator resistance (PVR) varies among myasthenia gravis patients with different levels of muscle strength, and the potential consequences of PVR also differ. When muscle strength is relatively high, patients can maintain normal physiological activities through a combination of spontaneous breathing and mechanical ventilation; mild PVR generally does not significantly affect normal breathing. However, when muscle strength is severely reduced, PVR can cause serious harm to the patient. According to one specific implementation, the muscle strength threshold is 30%, 50%, or 70% of the baseline value. Medical institutions or testing device manufacturers can set corresponding pre-stored respiratory rates, tidal volume, and inspiratory time trends for each respiratory cycle based on different muscle strength ranges. They can also set personalized pre-stored respiratory rates, tidal volume, and inspiratory time trends for each respiratory cycle based on the patient's condition to more accurately determine whether PVR has occurred and assess its potential physiological impact on the patient.

[0062] Preferably, obtaining muscle strength data for patients with myasthenia gravis based on monitoring data of swallowing muscle activity and monitoring data of proximal limb muscle activity includes: collecting muscle strength data for a first time period when the patient performs the first standardized action as reference muscle strength data; collecting muscle strength data for a second time period after the patient performs the first standardized action within a preset time period; and analyzing muscle strength fluctuations based on the muscle strength data for the second time period and the reference muscle strength data.

[0063] Preferably, the first standardized action is swallowing and / or raising the arm.

[0064] Preferably, after determining that human-ventilator resistance exists during mechanical ventilation in patients with myasthenia gravis, the method further includes: determining the type of human-ventilator resistance based on the changing trends of respiratory rate, tidal volume per respiratory cycle, and inspiratory time over time.

[0065] Preferably, as shown in Figure 3, if the respiratory rate increases and the tidal volume waveform fluctuates, it is determined that the ventilator failed to deliver air effectively.

[0066] Preferably, as shown in Figure 4, if an increase in respiratory rate is accompanied by an increase in inspiratory time, it is determined that the gas delivery of the ventilator is insufficient. The inspiratory time can be characterized by the pressure change in the ventilator airway.

[0067] Preferably, as shown in Figure 5, if the tidal volume is lower than the preset tidal volume threshold, the inspiratory time is shorter than the preset inspiratory time threshold, and the respiratory rate increases, it is determined that the ventilator has premature expiratory triggering. The inspiratory time can be characterized by the pressure change in the ventilator airway.

[0068] For assessing patient-ventilator resistance in patients with myasthenia gravis using mechanical ventilation, considering the unique pathological characteristics of the neuromuscular junction in these patients, selecting appropriate ventilation parameters is crucial for accurately determining patient-ventilator resistance. Based on the clinical characteristics and mechanical ventilation needs of patients with myasthenia gravis, this application provides a method for monitoring and evaluating patient-ventilator resistance and its type using muscle strength, tidal volume (VT), respiratory rate (RR), and inspiratory time (Ti).

[0069] Patients with myasthenia gravis may have weak respiratory muscles, resulting in smaller or unstable tidal volumes. Monitoring changes in tidal volume can identify whether a patient is attempting to increase inspiratory effort but is failing to effectively trigger mechanical ventilation. During disease exacerbations, patients with myasthenia gravis may exhibit an increased respiratory rate. If the respiratory rate is significantly higher than the set value, or if frequent spontaneous breathing attempts occur, this may indicate that the patient is struggling to overcome the limitations of the ventilator settings. Inspiratory time reflects the duration of the inspiratory phase in each breath. Due to respiratory muscle weakness, patients with myasthenia gravis may prolong inspiratory time to obtain sufficient air. If an abnormally prolonged inspiratory time is observed, or if it does not match the set inspiratory-expiratory ratio, it may indicate patient-ventilator resistance.

[0070] Preferably, during mechanical ventilation of the user, data of the above three ventilation parameters are collected in real time, and waveforms showing changes over time are generated. The waveform trends of the acquired tidal volume, respiratory rate, and inspiratory time are analyzed, with a focus on whether these parameters show regular abnormal fluctuations or deviate from the expected pattern.

[0071] Preferably, the determination method includes:

[0072] Baseline establishment: First, establish the normal range or baseline waveform for each ventilation parameter based on the patient's baseline condition and current treatment regimen. This can be accomplished through data collection during the initial stable phase.

[0073] Real-time comparison: Compare the waveforms of ventilation parameters monitored in real time with the baseline waveforms. If the waveforms of tidal volume, respiratory rate, or inspiratory time show a significant trend different from the baseline, such as: tidal volume being too small or too large, accompanied by a significant increase in respiratory rate; respiratory rate frequently exceeding the set value, accompanied by short and irregular inspiratory attempts; or abnormally prolonged inspiratory time, leading to an imbalance between inspiratory and expiratory ratios, these situations may indicate the occurrence of patient-ventilator resistance.

[0074] Confirming human-machine resistance: When multiple parameters show abnormal trends simultaneously, it can be more confidently determined that human-machine resistance exists.

[0075] Preferably, the human-ventilator resistance type, including ineffective inspiratory triggering and premature expiratory triggering, is determined by monitoring and analyzing tidal volume, respiratory rate, and inspiratory time using the following method.

[0076] Ineffective inspiratory triggering refers to a patient's attempt to initiate a breath, but failure to trigger mechanical ventilation, resulting in an unresponsive respiratory effort. Preferably, ineffective inspiratory triggering is confirmed through tidal volume (VT) waveform analysis and respiratory rate (RR) waveform analysis. Monitoring the tidal volume waveform observes for minute fluctuations (typically less than 20% of the set tidal volume). These minute fluctuations may represent the patient's spontaneous breathing effort, but due to insufficient trigger sensitivity or improper ventilator settings, they fail to effectively trigger ventilation. If the respiratory rate waveform shows frequent, short inspiratory attempts, and the tidal volume does not significantly increase after each attempt, it suggests possible ineffective inspiratory triggering. More preferably, the airway pressure waveform can also be additionally examined for negative pressure peaks (i.e., negative pressure generated during patient inspiration) that are not followed by positive pressure ventilation. This indicates that the patient attempted to inhale but failed to trigger the ventilator.

[0077] Premature expiratory cyclic off (PEO) refers to the ventilator switching to the expiratory phase too early, before the inspiratory phase has ended, resulting in insufficient tidal volume for the patient and impaired gas exchange. Monitor the tidal volume waveform to observe if the tidal volume is significantly lower than the set value. If the tidal volume is frequently lower than expected, it suggests possible premature expiratory cyclic off. More preferably, examine the airway flow waveform, especially at the end of the inspiratory phase, to observe if the flow rate drops to baseline prematurely. This indicates that the ventilator has switched to the expiratory phase too early, resulting in insufficient inspiratory time. Observe the airway pressure waveform, especially at the end of the inspiratory phase, to observe if the pressure drops prematurely. If the inspiratory pressure is not maintained for a sufficient time, it suggests premature expiratory cyclic off.

[0078] Preferably, the patient's respiratory rate is monitored in real time using a flow sensor or pressure sensor built into the ventilator. Respiratory rate is typically expressed as breaths per minute (breaths / minute). Under normal circumstances, the respiratory rate of a MG patient should be maintained between 10 and 20 breaths per minute. If the respiratory rate suddenly increases to above 25 breaths per minute and persists for more than 30 seconds, it may indicate that the patient is struggling to overcome the limitations of the ventilator settings. Tidal volume is also monitored in real time for each respiratory cycle using a flow sensor built into the ventilator. Under normal circumstances, the tidal volume of a MG patient should be maintained between 400 and 600 mL. If the tidal volume drops significantly to below 300 mL, accompanied by an increase in respiratory rate, it may indicate that the patient is failing to effectively trigger ventilator delivery, and there is a risk of ineffective inspiration triggering.

[0079] The ventilation detection method described in this application can, based on the disease characteristics of myasthenia gravis patients, and considering the changes in tidal volume, respiratory rate, and inspiratory time during mechanically assisted breathing, determine the presence and type of patient-ventilator resistance. This method helps ventilators promptly detect and adjust for patient-ventilator resistance when providing mechanical ventilation to myasthenia gravis patients.

[0080] This application also provides a ventilation detection device for patients with myasthenia gravis, as shown in Figure 2. The device includes: a muscle strength monitoring module configured to monitor the muscle activity of the swallowing muscles and the muscle activity of the proximal limbs of patients with myasthenia gravis, and to obtain muscle strength data of patients with myasthenia gravis based on the monitoring data of the swallowing muscle activity and the monitoring data of the proximal limb muscle activity; and a respiratory monitoring module configured to detect the respiratory rate, tidal volume per respiratory cycle, and inspiratory time per respiratory cycle when mechanical ventilation is provided to patients with myasthenia gravis, and to obtain the respiratory rate, tidal volume per respiratory cycle, and inspiratory time as the respiratory rate changes with the respiratory cycle. The control module, connected to the muscle strength monitoring module and the respiratory monitoring module, is configured to acquire muscle strength data of myasthenia gravis (MG) patients from the muscle strength monitoring module and respiratory rate, tidal volume per respiratory cycle, and inspiratory time from the respiratory monitoring module over time. Specifically, if the muscle strength data of an MG patient is lower than a preset muscle strength threshold, and the trends of respiratory rate, tidal volume per respiratory cycle, and inspiratory time over time are inconsistent with the trends of the corresponding pre-stored parameters, patient-ventilator resistance is identified during mechanical ventilation. The inspiratory time of each respiratory cycle is monitored in real time using a flow sensor built into the ventilator. Under normal circumstances, the inspiratory time of MG patients should be maintained between 0.8 and 1.2 seconds. If the inspiratory time is significantly prolonged to more than 1.5 seconds or shortened to less than 0.6 seconds, it may indicate a risk of delayed or premature expiratory triggering.

[0081] Preferably, when a patient's muscle strength data (such as the RMS values ​​of swallowing muscles and proximal limb muscles) are lower than a preset muscle strength threshold, it indicates significant neuromuscular dysfunction and a potential risk of respiratory muscle weakness. Simultaneously, if the trends of respiratory rate, tidal volume, and inspiratory time over time are inconsistent with the pre-stored trends of their corresponding parameters, the possibility of patient-ventilator resistance is further confirmed. Specifically, if a patient's muscle strength data is lower than the threshold (e.g., swallowing muscle RMS < 25 μV, proximal limb muscle RMS < 150 μV), and the respiratory rate suddenly increases to above 25 breaths / min, the tidal volume decreases to below 300 mL, and the inspiratory time prolongs to above 1.5 seconds, the system will determine that patient-ventilator resistance exists and issue an alarm. If the patient's muscle strength data is lower than the threshold, but the trends of the ventilation parameters are consistent with the pre-stored trends (e.g., respiratory rate stabilizes at 12-16 breaths / min, tidal volume stabilizes at 450-550 mL, and inspiratory time stabilizes at 1.0 second), then it is considered that there is no significant patient-ventilator resistance, and monitoring continues.

[0082] Preferably, when a patient's muscle strength data is close to the threshold (e.g., swallowing muscle RMS < 30 μV, proximal limb muscle RMS < 180 μV), but ventilation parameters have not yet shown significant abnormalities, healthcare professionals should closely monitor the patient's condition. When a patient's muscle strength data is below the threshold and ventilation parameters show abnormal changes, healthcare professionals should immediately check the ventilator settings and take appropriate measures (e.g., adjust trigger sensitivity, increase PEEP, etc.). When a patient's muscle strength data is far below the threshold (e.g., swallowing muscle RMS < 20 μV, proximal limb muscle RMS < 120 μV), and ventilation parameters are severely abnormal, healthcare professionals should prepare for emergency intubation or adjust the ventilation mode. Based on the test results, healthcare professionals can adjust the ventilator settings, such as trigger sensitivity, inspiratory time, and ventilation mode, to improve patient-ventilator synchrony. If necessary, combine this with other clinical interventions, such as drug therapy and psychological support, to comprehensively improve the patient's ventilation status.

[0083] The above technical solutions enable more precise identification and management of patient-ventilator asynchrony in myasthenia gravis patients during mechanical ventilation. This approach not only relies on traditional ventilation parameters (such as respiratory rate, tidal volume, and inspiratory time) but also incorporates the patient's muscle strength data, providing a more comprehensive assessment. Considering the specific pathological characteristics of MG patients and their needs for mechanical ventilation, this application provides a safe and effective ventilation management method to ensure optimal respiratory support for myasthenia gravis patients.

[0084] According to a preferred embodiment, the control module is further configured to: if the respiratory rate increases and is accompanied by fluctuations in the tidal volume waveform, determine that there is a failure to effectively trigger the ventilator to deliver air.

[0085] According to a preferred embodiment, the control module is further configured to determine that the ventilator is not delivering enough gas if the respiratory rate increases and the inspiratory time increases.

[0086] This application provides a respiratory support system for patients with acquired myasthenia gravis. Preferably, the respiratory support system includes the aforementioned ventilation detection device. As shown in FIG8, the system further includes: a chest assist assembly 100, including a first actuator 110 configured to make external mechanical contact with the patient's chest and a first control unit 120 signal-connected to the first actuator 110; and an abdominal assist assembly 200, including a second actuator 210 configured to make external mechanical contact with the patient's abdomen and a second control unit 220 signal-connected to the second actuator 210; wherein the first control unit 120 and the second control unit 220 are configured to cooperate with each other based on the patient's muscle strength data to control the first actuator 110 and the second actuator 210 to provide mechanical and / or electrical stimulation to the patient's chest and abdomen to assist the patient's breathing.

[0087] Based on this system, the following variable is first defined: F c (t): Chest muscle strength as a function of time; F a (t): Abdominal muscle strength as a function of time; S c (t): The intensity of the stimulus applied by the chest actuator as a function of time; S a R(t): The intensity of the stimulus applied by the abdominal actuator as a function of time; R(t): The patient's respiratory function index as a function of time.

[0088] This system can be described by the following mathematical model. The control equation for the chest support component is: S c (t)=f c (F c (t)). The control equation for the abdominal assist component is: S a (t)=f a (F a (t)). The equation for improving respiratory function is: R(t) = g(F c (t),F a (t),S c (t),S a (t)). Where, f c f a and g are nonlinear functions determined using clinical data and machine learning algorithms.

[0089] According to one specific implementation, the following linear model is used for processing: S c (t)=k c ·(F c max-Fc (t)); S a (t)=k a ·(F a max-F a (t)); R(t) = w c ·F c (t)+w a ·F a (t)+v c ·S c (t)+v a ·S a (t).

[0090] Where, k c k a It is the control gain coefficient, F c max, F a max represents the maximum muscle strength of the chest and abdominal muscles in a healthy person, respectively. w c w a v c v a It is the weighting coefficient.

[0091] Specifically, the clinical data sample of 10 patients is provided in Table 1 below.

[0092] Table 1

[0093] Table 1 lists the clinical data of 10 patients, recording their serial number, age, sex, myasthenia gravis status, chest muscle strength, abdominal muscle strength, intensity of chest stimulation, intensity of abdominal stimulation, tidal volume, respiratory rate, and blood oxygen saturation. Chest muscle strength, abdominal muscle strength, intensity of chest stimulation, and intensity of abdominal stimulation are standardized scores normalized to 0–100. c This can be determined by establishing a mapping from chest muscle strength to chest stimulation intensity. a The value of g can be determined by establishing a mapping from abdominal muscle strength to abdominal stimulation intensity. g can be determined by establishing mappings from (chest muscle strength, abdominal muscle strength, chest stimulation intensity, abdominal stimulation intensity) to (tidal volume, respiratory rate, blood oxygen saturation).

[0094] Preferably, as shown in FIG8, the first actuator 110 includes: an adjustable chest band 111 that can wrap around the chest cavity; a first electrode 112 disposed on the chest band 111 for stimulating the pectoralis major muscle; a second electrode 113 disposed on the chest band 111 for stimulating the intercostal muscles; and an inflatable and deflated first mechanical airbag 114 disposed on the chest band 111 at positions corresponding to both sides of the chest cavity. Specifically, the chest band 111 is made of an elastic fabric, such as a blend of nylon and spandex, and is configured with an elastic buckle system, with a chest circumference ranging from 70 to 130 cm. The first electrode 112 is a surface electrode made of a flexible conductive material, such as conductive silicone, and is elliptical in shape with a major axis of 8 cm and a minor axis of 5 cm. It is disposed on the inner side of the chest band 111 at the position corresponding to the pectoralis major muscle and is connected to the first control unit 120 via a flexible printed circuit. The second electrode 113 is made of flexible conductive material and is a strip-shaped electrode, approximately 15cm long and 2cm wide. It is positioned inside the chest band 111, arranged along the ribcage, and connected to the first control unit 120 via a flexible printed circuit. The first mechanical airbag 114 is made of medical-grade silicone and is circular in diameter, approximately 10cm in diameter. Its thickness can expand from 0.5cm to 3cm. It is embedded in the chest band structure on both sides of the chest band 111 and is inflated and deflated via a flexible tube connected to a micro electric pump. A pressure sensor can also be integrated into the first mechanical airbag for real-time pressure monitoring.

[0095] Preferably, as shown in Figure 8, the second actuator 210 includes: an adjustable abdominal band 211 that can wrap around the abdominal cavity; a third electrode 212 disposed on the abdominal band 211 for stimulating the rectus abdominis muscle; a fourth electrode 213 disposed on the abdominal band 211 for stimulating the external oblique muscle; and an inflatable second mechanical airbag 214 disposed on the abdominal band 211 at a position corresponding to the anterior side of the abdomen. The abdominal band 211 is made of breathable elastic fabric, approximately 20 cm wide, with an abdominal circumference of approximately 60–120 cm. The third electrode 212 is a rectangular surface electrode, 10 cm long and 5 cm wide, disposed on the inner side of the abdominal band 211 at a position corresponding to the rectus abdominis muscle, and connected to the second control unit 220 via a flexible printed circuit. The fourth electrode 213 is a fan-shaped surface electrode, approximately 15 cm in arc length and approximately 5 cm at its widest point, disposed on the inner side of the abdominal band 211 at a position corresponding to the external oblique muscle, and connected to the second control unit 220 via a flexible printed circuit. The second mechanical airbag 214 is made of medical-grade silicone and is elliptical in shape with a major axis of 20cm and a minor axis of 15cm. Its thickness can expand from 1cm to 5cm, and it is embedded in the abdominal band structure at a corresponding position on the front of the abdomen. Inflation and deflation are achieved by connecting a tubing to a miniature electric pump. Preferably, the first mechanical airbag uses the same electric pump as the second mechanical airbag. A pressure sensor can also be integrated into the second mechanical airbag for real-time pressure monitoring.

[0096] The first control unit 120 and the second control unit 220 may employ a low-power microcontroller (such as an ARM Cortex-M4) with an electrical stimulation module, a programmable current source with an output range of 0–100mA and an adjustable frequency (1–100Hz); an airbag control module, a PWM-controlled electric pump drive circuit; a communication interface: a Bluetooth Low Energy (BLE) module for communicating with the main controller; and a sensor interface: which can be used to connect an electromyography (EMG) sensor and a pressure sensor.

[0097] Preferably, as shown in Figures 9 and 10, the first actuator 110 and the second actuator 210 are configured to assist the patient's breathing in the following manner: During inhalation: The first electrode 112 activates the pectoralis major muscle to assist in lifting the thorax; the second electrode 113 activates the intercostal muscles to help expand the thoracic cavity; the third electrode 212 and the fourth electrode 213 respectively mildly activate the rectus abdominis and external oblique muscles, assisting in abdominal muscle contraction and causing the diaphragm to descend. The first mechanical air bladders 114 on both sides of the thoracic cavity inflate, assisting in the outward expansion of the thorax; the mechanical air bladder on the anterior side of the abdomen contracts, assisting in the descent of the diaphragm. The combined action of electrical stimulation and mechanical assistance increases the thoracic cavity volume, reduces intrathoracic pressure, and promotes air entry into the lungs, as shown in Figure 9. During exhalation: The stimulation intensity of the first electrode 112 and the second electrode 113 decreases, allowing the thorax to naturally recoil. The stimulation intensity of the third electrode 212 and the fourth electrode 213 increases, assisting in abdominal muscle contraction, compressing the abdominal cavity, and pushing the diaphragm upward. The first mechanical airbags 114 on both sides of the chest cavity begin to deflate, allowing the thoracic cavity to recoil. The second mechanical airbag 214 on the anterior side of the abdomen inflates, assisting in the compression of the abdominal cavity. The combination of electrical stimulation and mechanical assistance increases the intrathoracic pressure, propelling air out of the lungs, as shown in Figure 10.

[0098] Through this precisely coordinated approach, the device can mimic the respiratory muscle movement patterns of healthy individuals, providing comprehensive respiratory assistance to patients with myasthenia gravis. This method not only improves respiratory function but may also help maintain and train these muscles, potentially having a positive impact on the patient's long-term recovery.

[0099] According to one specific implementation, the electrode stimulation parameters for the inhalation and exhalation phases are shown in Tables 2 and 3 below:

[0100] Table 2: Inhalation phase (duration 1-2 seconds)

[0101] Table 3: Exhalation phase (duration 2-3 seconds)

[0102] Preferably, the first mechanical airbag has a maximum capacity of 500 ml per side, an inflation rate of 250–350 ml / s during inhalation, and a deflation rate of 150–250 ml / s during exhalation. The second mechanical airbag has a maximum capacity of 1000 ml, an inflation rate of 300–400 ml / s during inhalation, and a deflation rate of 200–300 ml / s during exhalation.

[0103] Preferably, the electrical stimulation intensity of the electrode can be adjusted according to the patient's blood oxygen saturation. According to one specific embodiment, I2 = I1 × (1 + k × (D - SpO2)), where I2 is the base electrical stimulation intensity, as listed in Tables 2 and 3, I1 is the electrode electrical stimulation intensity adjusted according to the patient's blood oxygen saturation, SpO2 is the current blood oxygen saturation percentage monitored in real time, k is an adjustment coefficient, typically 0.02, and D represents the target blood sample saturation value, a constant, usually set to 95–98.

[0104] According to one specific implementation, the stimulation intensity of the first, second, third, and fourth electrodes is set based on the patient's measured muscle strength, blood oxygen saturation, respiratory rate, and tidal volume.

[0105] Preferably,

[0106] Where I represents the stimulus intensity, M represents the standardized muscle strength test value, ranging from 0 to 100, O represents blood oxygen saturation, ranging from 0 to 100, R represents respiratory rate, ranging from 12 to 20 breaths / minute, and V represents tidal volume, typically ranging from 4 to 8 ml / kg body weight. w1, w2, w3, and w4 are parameters set based on the patient's individualized clinical data. According to one specific implementation method, based on statistical calculations of clinical data measurements from the test patients, w1, w2, w3, and w4 are set to 0.3, 0.3, 0.2, and 0.2 for the first electrode, respectively; w1, w2, w3, and w4 are set to 0.3, 0.25, 0.25, and 0.2 for the second electrode, respectively; w1, w2, w3, and w4 are set to 0.2, 0.3, 0.22, and 0.28 for the third electrode, respectively; and w1, w2, w3, and w4 are set to 0.24, 0.28, 0.22, and 0.26 for the fourth electrode.

[0107] Preferably, the volumes of the first mechanical cuff 114 and the second mechanical cuff 214 can be adjusted according to the patient's vital capacity (VC). The maximum volume of the first mechanical cuff = 0.15 × VC; the maximum volume of the second mechanical cuff = 0.3 × VC; where VC is the patient's vital capacity (ml). Preferably, the upper limit of the electrical stimulation intensity of the electrodes is 50 mA. The maximum assisted respiratory rate is set to 20 breaths / minute. An alarm is triggered when SpO2 is below 90% or when no effective breathing is detected for 30 consecutive seconds.

[0108] According to a preferred embodiment, the respiratory support system for patients with acquired myasthenia gravis further includes a first monitoring unit for monitoring the patient's thoracic volume, a second monitoring unit for monitoring the patient's abdominal volume, a third monitoring unit for acquiring the patient's intrathoracic pressure gradient ΔPt, and a fourth monitoring unit for acquiring the patient's intraperitoneal pressure gradient ΔPa. The first control unit 120 and the second control unit 220 are configured to adjust the real-time electrical stimulation intensity of the first, second, third, and fourth electrodes based on changes in the patient's thoracic volume acquired by the first monitoring unit, changes in the patient's abdominal volume acquired by the second monitoring unit, changes in the patient's intrathoracic pressure acquired by the third monitoring unit, and changes in the patient's intraperitoneal pressure acquired by the fourth monitoring unit.

[0109] Specifically, the first monitoring unit is a chest circumference measuring resistance band integrated within the chest band 111, which can measure changes in the patient's chest circumference in real time through resistance changes, thereby calculating changes in the patient's thoracic cavity volume. The second monitoring unit is an abdominal circumference measuring resistance band integrated within the abdominal band 211, which can measure changes in the patient's abdominal circumference in real time through resistance changes, thereby calculating changes in the patient's abdominal cavity volume. The third monitoring unit can be an intrathoracic pressure monitor with multiple pressure measuring points to monitor different locations within the thoracic cavity. The fourth monitoring unit can be an intra-abdominal pressure monitor with multiple pressure measuring points to monitor intra-abdominal pressure at different locations.

[0110] Preferably, the first monitoring unit, the second monitoring unit, the third monitoring unit, and the fourth monitoring unit are respectively signal-connected to the first control unit 120 and the second control unit 220. Specifically, the first monitoring unit, the second monitoring unit, the third monitoring unit, and the fourth monitoring unit are respectively signal-connected to the first control unit 120 and the second control unit 220 via wireless communication modules. The wireless communication module supports at least one communication mode selected from GPRS, 3G, 4G, 5G, Wi-Fi, Zigbee, and LoRa.

[0111] Specifically, the first control unit 120 and the second control unit 220 are configured to calculate the rate of change of the patient's thoracic volume ΔVt based on the patient's thoracic volume collected by the first monitoring unit, calculate the rate of change of the patient's abdominal volume ΔVa based on the patient's abdominal volume collected by the second monitoring unit, and calculate the volume phase difference θv based on the patient's thoracic volume changing with time t and the patient's abdominal volume changing with time t.

[0112] According to one specific implementation, the first control unit 120 and the second control unit 220 are configured to calculate the patient's Thoracoabdominal Respiratory Dynamics Synchronization Index (TRKSI) based on the patient's rate of change of thoracic volume ΔVt, rate of change of abdominal volume ΔVa, volume phase difference θv, intrathoracic pressure gradient ΔPt, and intraperitoneal pressure gradient ΔPa. The TRKSI is defined as: TRKSI = (VCC × PBF × VPCI × PCF × KER_normalized) × 100.

[0113] Where VCC is the volumetric compatibility factor, PBF is the pressure balance factor, VPCI is the volume-pressure coupling index, PCF is the phase compensation factor, KER is the kinetic efficiency ratio, and KER_normalized is the normalized kinetic efficiency ratio.

[0114] The formula for calculating the volumetric compatibility factor (VCC) is:

[0115] The formula for calculating the pressure balance factor (PBF) is as follows:

[0116] The formula for calculating the volumetric-pressure coupling index (VPCI) is as follows:

[0117] The formula for calculating the phase compensation factor (PCF) is as follows:

[0118] The formula for calculating the kinetic efficiency ratio (KER) is:

[0119] The normalized kinetic efficiency ratio KER_normalized is:

[0120] TRKSI can be further normalized to ensure that its value is between 0 and 100.

[0121] The TRKSI normalization formula is:

[0122] TRKSI=max(min(TRKSI,100),0).

[0123] The volume coordination coefficient assesses the matching degree of changes in thoracic and abdominal volume, incorporating a cosine function correction for phase difference, with a value ranging from 0 to 1. The pressure balance factor reflects the balance of thoracic and abdominal pressure gradients, employing an exponential function to ensure sensitivity; the smaller the pressure difference, the closer this coefficient is to 1. The volume-pressure coupling index assesses the matching degree between volume changes and pressure changes. The phase compensation coefficient specifically handles the influence of phase difference, reaching a maximum value of 1 when the phase difference is 0. The kinetic efficiency ratio assesses the efficiency of volume changes and pressure changes, using a sigmoid function for normalization to avoid the influence of outliers. The TRKSI can be used to quantitatively assess respiratory coordination, facilitating long-term monitoring and comparison of patients' respiratory stability and recovery status, and guiding respiratory training and treatment.

[0124] According to one specific implementation, a respiratory support system for patients with acquired myasthenia gravis is configured to execute a TRKSI-based adaptive electrical stimulation control scheme. First, basic parameters for electromyography (EMG) signal acquisition are set: sampling frequency 2000 Hz, resolution 16 bits, signal-to-noise ratio greater than 60 dB, and common-mode inhibition ratio greater than 100 dB. The first electrode is placed in the 3rd–5th intercostal spaces, the second electrode in the 3rd–7th intercostal spaces, the third electrode 5 cm above and below the umbilicus, and the fourth electrode below the 8th–9th costal margin. Basic parameters for electrode stimulation are: pulse width 200–400 μs, frequency 20–50 Hz, intensity 10–40 mA, rise time 0.5–1 s, duration 1–2 s, and stimulation interval 2–4 s.

[0125] Specifically, the first electrode has an initial intensity of 20 mA, a frequency of 35 Hz, and a pulse width of 300 μs. The second electrode has an initial intensity of 15 mA, a frequency of 40 Hz, and a pulse width of 250 μs. The third electrode has an initial intensity of 25 mA, a frequency of 30 Hz, and a pulse width of 350 μs. The fourth electrode has an initial intensity of 22 mA, a frequency of 32 Hz, and a pulse width of 325 μs.

[0126] Furthermore, for example, the training set listed in Table 4 below can be used to train an intelligent regulation mechanism for adjusting electrode stimulation parameters based on TRKSI. This regulation mechanism can be personalized and adjusted according to the patient's specific physiological state in clinical applications. The following training set serves as an example of feedback regulation based on TRKSI. According to one specific implementation, the stimulation intensity and frequency of the first, second, third, and fourth electrodes are adjusted in a manner that keeps TRKSI greater than or equal to 80, preferably greater than or equal to 90.

[0127] Table 4

[0128] Table 4 provides an example training set for training techniques based on TRKSI to adjust electrode stimulation parameters. This set includes TRKSI values ​​and corresponding first, second, third, and fourth electrode adjustment values. By training and implementing the feedback adjustment mechanism using this training set, the patient's respiratory status can be assessed over the long term using TRKSI parameters that objectively reflect respiratory coordination. This allows for the adjustment of electrode stimulation parameters in the respiratory support system, achieving better assisted breathing results.

[0129] Preferably, the system further includes: a first sensor 131 configured to monitor the muscle activity of the swallowing muscles; a second sensor 133 configured to monitor the muscle activity of the proximal limb; and a data processing unit 140, which receives the detection data of muscle activity from the first sensor 131 and / or the second sensor 133 and calculates the muscle strength data.

[0130] Preferably, the data processing unit 140 is configured to collect muscle strength data for a first time period during which the patient performs a first standardized action using the first sensor 131 and / or the second sensor 133 as reference muscle strength data, and to analyze muscle strength fluctuations by collecting muscle strength data for a second time period after the patient performs the first standardized action using the first sensor 131 and / or the second sensor 133 for a preset time period. Preferably, the first standardized action includes, but is not limited to, swallowing and / or arm raising, with the proximal end of the limb being the patient's arm. The second sensor 133 is configured to detect the motion acceleration and equivalent mass of the patient's arm, and the data processing unit 140 calculates muscle strength data of the user's arm during muscle activity based on the motion acceleration and equivalent mass of the patient's arm detected by the second sensor 133. Preferably, the system further includes a sensing component configured to measure the movement of the patient's respiratory muscles to collect movement information, and to determine the movement state of the patient's respiratory muscles based on the collected movement information.

[0131] Preferably, the first control unit 120 and the second control unit 220 are configured to control the first actuator 110 and the second actuator 210 to provide mechanical and / or electrical stimulation to the patient's chest and abdomen, respectively, based on the patient's movement state. Preferably, the electrodes are configured to adjust the intensity of the electrical stimulation sequentially based on the detected muscle strength fluctuation rate and the real-time detected blood oxygen saturation. According to another specific embodiment, the system is configured to preferentially use a control method that adjusts the intensity of the electrode electrical stimulation based on the real-time detected blood oxygen saturation when the detected blood oxygen saturation is below 95%. When the detected blood oxygen saturation is above 95%, a control method that adjusts the intensity of the electrode electrical stimulation based on the detected muscle strength fluctuation rate is preferred. This control strategy cleverly balances the patient's immediate safety needs (by monitoring blood oxygen saturation) and long-term therapeutic effects (by monitoring muscle strength). This balance is particularly important for the management of patients with chronic diseases. By adjusting treatment parameters in real time, the system can provide customized treatment according to each patient's real-time condition. The system can not only cope with acute situations (such as a sudden drop in blood oxygen) but also prevent potential problems (such as over-fatigue) by monitoring muscle status. This preventative approach may significantly reduce the risk of complications.

[0132] Long-term use of this system will accumulate a wealth of valuable data, which can be used to further optimize treatment strategies and may even provide new insights into research on related diseases. By optimizing stimulation intensity and frequency, the system may significantly improve patient comfort and quality of life, which is crucial for patients using respiratory support devices long-term. This control strategy demonstrates how to integrate multiple physiological parameters into an intelligent decision-making system, providing inspiration for the design of other medical devices.

[0133] Preferably, the first actuator 110 is configured to apply vibration along the patient's intercostal spaces to enhance the inspiratory process. Preferably, the first actuator 110 is configured to apply pressure to the pectoralis major and pectoralis minor muscles to enhance the expiratory process. Preferably, the second actuator 210 is configured to apply pressure or vibration to the external and internal oblique muscles on the patient's abdominal side. Preferably, the second actuator 210 is configured to apply circumferential pressure or vibration to the transverse abdominis muscle in the patient's lumbar region.

[0134] Preferably, for the intercostal muscles, a small vibrating device can be used to stimulate along the intercostal spaces. This helps enhance the inspiratory process. For the pectoralis major and pectoralis minor muscles, a larger vibrating pad or pressure pad can be used to cover the entire front of the chest. This helps enhance the expiratory process. For the rectus abdominis muscle, a band vibrator or pressure band can be used to stimulate from below the sternum to above the pubis. For the external and internal oblique muscles, an oblique stimulation band can be used on the side of the abdomen. Stimulation of the transverse abdominis muscle can be achieved by using a wraparound stimulation band around the waist.

[0135] Preferably, a pattern of alternating stimulation of the chest and abdomen is designed to mimic the rhythm of natural breathing. For example, first stimulate the chest muscles for 1-2 seconds (mimicking inhalation), then stimulate the abdominal muscles for 2-3 seconds (mimicking exhalation). Start with low intensity and low frequency, gradually increasing to a level that the patient can comfortably tolerate. The frequency can start at 12-20 breaths per minute, mimicking a normal breathing rate.

[0136] This system can analyze muscle strength data in real time to predict the risk of acquired myasthenia gravis and stimulate the patient's diaphragm with vibration and compression based on the detection results. As shown in Figure 6, this application provides a life support system for acquired myasthenia gravis. The system includes: a first sensor 131 configured to monitor the muscle activity of the swallowing muscles; a second sensor 133 configured to monitor the muscle activity of the proximal limbs; a data processing unit 140 that receives the detection data of muscle activity from the first sensor 131 and / or the second sensor 133 and calculates the muscle strength data; and a respiratory assistance unit configured to assist the patient's breathing through vibration, compression, electric shock, and / or infrared. The data processing unit 140 is configured to collect muscle strength data of the patient during a first time period when performing a first standardized action using the first sensor 131 and / or the second sensor 133 as reference muscle strength data, and to collect muscle strength data of the patient during a second time period after performing the first standardized action using the first sensor 131 and / or the second sensor 133 for a preset time period to analyze muscle strength fluctuations. The respiratory assistance unit stimulates the patient's diaphragm based on the muscle strength fluctuations to maintain the patient's diaphragm strength.

[0137] Preferably, the first sensor 131 and the second sensor 133 are configured in the wearable device. The data processing unit 140 is in data communication with the first sensor 131 and the second sensor 133. The data processing unit 140 divides and analyzes the data from the first sensor 131 and the second sensor 133 according to time. Preferably, the system further includes a user interface 150 for displaying the myasthenia gravis condition and risk assessment results. Preferably, the wearable device further includes at least one electromyography (EMG) sensor 134 for monitoring and analyzing comprehensive muscle activity. The sensors transmit data to the data processing unit 140 via a wireless protocol. Preferably, the data processing unit 140 further includes: a set of advanced data processing algorithms for extracting and analyzing key features in the sensor data; a set of machine learning and deep learning algorithms for refining the prediction model and enhancing system performance. Preferably, the user interface 150 includes: a mobile application 151 or a web interface 152 allowing patient access and interaction; a personalized risk assessment and management plan module 153 customized according to the individual needs and conditions of the patient; and educational resources and support materials 154 designed to provide patients with knowledge and self-management strategies.

[0138] The interaction between the data processing unit 140 and the wearable device 130 is optimized as follows: data transmission and communication protocols to ensure real-time transmission and processing of muscle strength data; secure data encryption and authentication mechanisms to protect patient privacy and data integrity; and data synchronization and integration functions with the cloud storage server 160 for data backup and remote access.

[0139] Preferably, the system further includes enhanced connectivity to the cloud storage server 160, including: robust data security measures such as access control, data encryption, and regular security audits; scalable storage capacity to accommodate the growth of patient data; and data analytics tools for extracting valuable insights from accumulated patient data to facilitate system improvement and myasthenia gravis research.

[0140] The specific algorithm for myasthenia gravis evaluation involved in this application is shown in Figure 7, and is explained in detail below:

[0141] The symbol is defined as: (t) i ): The i-th time period; (x i (x): Muscle strength data for the i-th time period; (R1): Standardized muscle strength data set for the first time period; (x i,p ): Muscle strength data associated with the p-th data point in R1 during the i-th time period.

[0142] The specific judgment process is as follows:

[0143] 1. Standardize the first time period data

[0144] The muscle strength data (x1) from the first time period were standardized to obtain the standardized set (R1):

[0145] in, It is the mean of (x1). That is the standard deviation.

[0146] 2. Calculate muscle strength fluctuations

[0147] For each subsequent time period (t) i (i>1), calculate its muscle strength data x i Differences from the corresponding data in R1:

[0148] [d i =x i,p -R1].

[0149] 3. Diagnosing acquired myasthenia gravis

[0150] If |d i If the threshold τ is exceeded, it is determined that there is acquired myasthenia gravis during that period.

[0151] The threshold can be adjusted based on clinical experience or the patient's personal historical data. Simultaneously, data noise, individual patient differences, and combined analysis of data from multiple muscle groups should be considered to optimize the accuracy of the judgment.

[0152] Specifically, the clinical test data of several patients are listed in Table 5 below.

[0153] Table 5

[0154] Table 5 lists the clinical test data of the two patients, including the corresponding swallowing muscle EMG data, arm acceleration data, measured arm equivalent mass, calculated muscle strength data, respiratory rate and tidal volume data at the corresponding time points (T0 and T1) for patients 1 and 2, respectively, when they performed swallowing or arm raising movements. Swallowing muscle strength is approximately linearly correlated with EMG signal intensity and can be calculated using the following formula: F swallow =k s ×EMG signal ;

[0155] Among them, F swall ow is the calculated swallowing muscle strength (unit: N), k s This is the proportionality coefficient (unit: N / μV), which needs to be determined through calibration. (EMG) signal It is the measured electromyography signal intensity (unit: μV).

[0156] According to one specific embodiment, swallowing muscle strength is measured using a surface electromyography (EMG) sensor, i.e., an EMG sensor 134, to record the amplitude and frequency of electromyographic signals during swallowing. The measurement parameters for arm muscle strength are the arm's acceleration *a* and the arm's equivalent mass *m*. Muscle strength *F* = *m* × *a*, where *F* is the muscle strength (Newtons, N), *m* is the arm's equivalent mass (kilograms, kg), and *a* is the arm's acceleration (meters per second). 2 m / s 2 ).

[0157] The testing process is as follows: First time period (reference data collection): Standardized movements (such as swallowing or raising an arm) are performed, and muscle strength data is recorded as a reference. Second time period (fluctuation analysis): After a preset time period, the standardized movements are performed again, muscle strength data is recorded, and compared with the reference data to analyze strength fluctuations. Strength fluctuations are characterized using a calculated strength fluctuation rate R. R = (F... 第二时段 -F 第一时 段 ) / F 第一时段 ×100%. Where R represents the force fluctuation rate, F 第二时段 F represents the muscle strength measured in the second time period. 第一 时段 This indicates the muscle strength measured in the first time period.

[0158] The relationship between electrical stimulation intensity and muscle strength variability is: I 调整后 =I 基础 ×(1-k×R); where, I 基础 This refers to the baseline intensity of electrical stimulation, as listed in Tables 2 and 3, I. 调整后 It is the intensity of electrode electrical stimulation adjusted according to the patient's strength fluctuation rate. R represents the strength fluctuation rate, and k is the adjustment coefficient, with a value range of 0.1 to 0.3.

[0159] Preferably, the second actuator 210 is an abdominal pressure device that receives information from the data processing unit 140 regarding the fluctuations in the patient's swallowing muscles and proximal upper limb muscle strength, and applies pressure to the patient's abdomen in a biomimetic breathing motion to maintain the patient's diaphragm and lung mobility. Preferably, the pressure pattern and force are also set in relation to the patient's intra-abdominal pressure. The patient's intra-abdominal pressure can be provided by an intra-abdominal pressure detection device.

[0160] For example, in muscle strength fluctuation detection, the system detected a 15% decrease in the patient's swallowing muscle strength within 10 minutes (from an initial 100N to 85N). Simultaneously, the proximal upper limb muscle strength decreased by 20% within 15 minutes (from an initial 150N to 120N). Based on this data, the abdominal pressure device was activated, initiating biomimetic breathing-like compressions of the patient's abdomen. The initial compression rate was set to 12 compressions per minute, mimicking a normal breathing rate. The initial compression depth was set to 2 cm to simulate mild breathing. The intra-abdominal pressure detection device measured the patient's baseline intra-abdominal pressure at 8 mmHg. The system was set to allow intra-abdominal pressure fluctuations of 6–10 mmHg during normal breathing. If the intra-abdominal pressure dropped to 5 mmHg, the system increased the compression pressure to a depth of 3 cm and the frequency to 14 compressions per minute. If the intra-abdominal pressure rose to 12 mmHg, the system decreased the compression pressure to a depth of 1.5 cm and the frequency to 10 compressions per minute. The system assesses muscle strength and intra-abdominal pressure every 5 minutes, dynamically adjusting compression parameters. If muscle strength recovers to more than 95% of its initial value within 15 minutes (swallowing muscle strength to 95N, proximal upper limb muscle strength to 142.5N), the system gradually reduces compression intensity and frequency. The system is set to a maximum compression depth of 4cm to prevent pressure on internal organs. The maximum compression rate is limited to 20 compressions per minute to avoid hyperventilation. Based on the patient's height, weight, and vital capacity, the system can be personalized with initial parameters. For example, for a patient who is 170cm tall and weighs 65kg, the initial compression depth might be set to 2.2cm. Through this precise, personalized, and dynamic adjustment, the respiratory support system can more effectively maintain the patient's diaphragmatic function and respiratory capacity while reducing the risk of complications.

[0161] According to one embodiment, the data processing unit 140 is configured to control the actuator to perform variable-frequency vibrations with a non-constant frequency within an operating frequency range of 5Hz to 1000Hz during a given time interval, to assist in maintaining the strength of the patient's diaphragm muscles. For example, the actuator specifications are: weight: 50 grams, dimensions: 5cm × 3cm × 1cm, maximum output power: 2 watts. Vibration frequency range: minimum frequency: 5Hz, maximum frequency: 1000Hz, frequency adjustment accuracy: 1Hz. Vibration modes include: Low frequency band (5Hz–50Hz): starting frequency: 10Hz, lasting 5 seconds, gradually increasing to 30Hz, lasting 10 seconds, decreasing to 20Hz, lasting 5 seconds. Mid-frequency band (51Hz–500Hz): starting from 100Hz, increasing by 50Hz every 2 seconds until reaching 300Hz, maintaining at 300Hz for 5 seconds, then decreasing by 100Hz every 3 seconds until returning to 100Hz. High-frequency band (501Hz–1000Hz): Start at 600Hz, rapidly increase to 900Hz (within 1 second), maintain at 900Hz for 2 seconds, slowly decrease to 700Hz (within 3 seconds), and repeat this cycle 3 times. Time interval settings: Total treatment time: 15 minutes, low-frequency band: 5 minutes, mid-frequency band: 7 minutes, high-frequency band: 3 minutes. Preferably, the system assesses the patient's diaphragmatic electromyography (EMG) signal every 30 seconds. If the EMG signal intensity decreases by more than 10%, the system increases the vibration intensity and duration. For example, if a decrease in EMG signal is detected in the mid-frequency band, the system may increase the maintenance time of 300Hz from 5 seconds to 8 seconds. The system can adjust the vibration intensity based on the patient's weight and muscle condition. For example, for a patient weighing 60kg, the initial vibration intensity may be set to 1.5 watts, and for a patient weighing 80kg, the initial vibration intensity may be set to 1.8 watts. Continuous high-frequency vibration (>800Hz) should not exceed 30 seconds. Every 5 minutes of treatment, the system pauses for 30 seconds to prevent muscle fatigue. If the patient reports discomfort (via button or voice command), the system immediately reduces the frequency by 50%. If discomfort persists, the system gradually reduces the frequency. Through this precise, dynamic vibration stimulation, the respiratory assist system effectively maintains and stimulates the patient's diaphragmatic muscle strength while providing a personalized and safe treatment plan. This approach may help prevent respiratory function decline in patients with acquired myasthenia gravis and improve their quality of life.

[0162] Preferably, the second actuator 210 further includes a band of at least two vibration modules, which are externally applied to the user's abdominal region to stimulate the diaphragm, thereby enhancing lung function. Preferably, the first sensor 131 is a flexible sensor attached to a first region of the patient's swallowing muscles' skin surface, which generates a first signal reflecting the strain change state of the first region and a second signal characterizing the curvature change state of the first region based on the deformation of the first region. Preferably, the first sensor 131 includes a strain sensing unit and an optical sensing unit. The strain sensing unit generates the first signal based on the deformation of the first region. The optical sensing unit generates the second signal based on the deformation of the first region. Preferably, the data processing unit 140 acquires muscle strength data of the patient's swallowing muscles based on the first and second signals collected by the first sensor 131.

[0163] Preferably, a flexible material (such as polydimethylsiloxane PDMS) is used to fabricate the sensor substrate, ensuring a close fit to the skin and without affecting swallowing movements. The strain sensing unit is made of nanomaterials such as graphene or carbon nanotubes, exhibiting high sensitivity and good flexibility. The optical sensing unit can employ fiber optic grating (FBG) technology, enabling precise measurement of minute curvature changes. The sensor surface is coated with a biocompatible material to reduce skin irritation. The sensor closely conforms to the surface of the swallowing muscles, accurately capturing muscle movement. The flexible design does not affect the patient's normal swallowing, improving comfort during long-term monitoring. The strain sensing unit measures muscle deformation through resistance changes and converts them into an electrical signal output. The optical sensing unit measures curvature using the phase change of light waves in an optical fiber and converts it into an optical signal output. A high-precision analog-to-digital converter (ADC) is used to convert the analog signal into a digital signal. A low-noise amplification circuit is designed to improve signal quality. In this way, strain and curvature information can be acquired simultaneously, comprehensively reflecting the movement state of the swallowing muscles. A high sampling rate (e.g., 1000Hz) can capture rapid swallowing movements. Digital filtering algorithms (such as Butterworth filters) are used to remove environmental noise and baseline drift. Machine learning algorithms (such as Support Vector Machines (SVMs) or deep neural networks) are applied to extract features from the raw signal. Strain and curvature data are converted into muscle strength data to build mathematical models for real-time data processing and provide immediate feedback. In this way, the muscle strength of the swallowing muscles can be accurately estimated, providing an objective basis for clinical assessment.

[0164] Preferably, the data processing unit 140 further includes: a data receiving module 141 for receiving muscle activity detection data from the first sensor 131 and the second sensor 133; a data analysis module 143 for calculating muscle strength data based on the received muscle activity detection data, analyzing the fluctuation of muscle strength using a predetermined algorithm model, and outputting a risk assessment result for acquired myasthenia gravis; and a user interface 150 for displaying the analyzed risk assessment result and recommendations.

[0165] Preferably, the data processing unit 140 is connected to the wearable device to receive muscle strength data from the first sensor 131 and / or the second sensor 133, and analyze the data to predict the risk of acquired myasthenia gravis; wherein the muscle strength data is divided into multiple time periods, specifically: muscle strength data in the first time period, i.e., reference muscle strength data collected when the patient performs the first standardized movement; and muscle strength data in the second time period, i.e., muscle strength data collected after a preset time period following the patient's performance of the first standardized movement, used to predict muscle strength fluctuations.

[0166] In this way, the wearable device integrates a first sensor 131 and a second sensor 133 for collecting muscle strength data. A data processing unit 140 wirelessly connects to the wearable device to receive and analyze the muscle strength data. In the first time period: the patient performs a first standardized action (such as a grip strength test or swallowing test), and reference muscle strength data is collected. In the second time period: the patient performs the same action again within a preset time period (such as 30 minutes) after performing the first standardized action, and muscle strength data for prediction is collected. The data processing unit 140 first performs data preprocessing, filtering and denoising the raw sensor data, then extracts key features from the processed data, such as peak strength, duration, and decay rate. Next, it compares the muscle strength data from the first and second time periods, calculates the percentage change in strength, and finally performs a risk assessment. Based on the data comparison results, a machine learning algorithm (such as a support vector machine or random forest) is used to predict the risk of acquired myasthenia gravis and outputs a stimulation mode according to a preset model, activating the corresponding respiratory assist device. The stimulation mode includes selections for compression, vibration, electric shock, or infrared stimulation, as well as specific setting parameters for each mode. This technical solution, by comparing changes in muscle strength over a short period, can identify potential risks of acquired myasthenia gravis early, gaining valuable time for clinical intervention. Utilizing a wearable device 130 for detection reduces discomfort associated with traditional examination methods and improves patient compliance. This non-invasive wearable device enables 24-hour continuous monitoring, providing a comprehensive understanding of changes in the patient's muscle strength. Considering individual differences, the system can perform customized risk assessments based on the patient's individual baseline data. Data can be transmitted to medical institutions in real time, facilitating remote monitoring of patient conditions and timely adjustments to treatment plans by physicians. This technical solution is suitable for data accumulation and analysis; long-term data collection will contribute to in-depth research into the pathogenesis and influencing factors of acquired myasthenia gravis. Standardized data collection and analysis processes reduce subjective judgment errors, improving the objectivity and accuracy of diagnosis. Early warning and timely intervention may reduce the occurrence of serious complications, thereby lowering overall medical costs. This acquired myasthenia gravis risk prediction system based on wearable device 130 and data analysis, along with a respiratory / life support system, can significantly improve the prevention, diagnosis, and rehabilitation of acquired myasthenia gravis, providing patients with better medical care.

[0167] Preferably, the wearable device further includes a communication module 132 for wirelessly transmitting muscle strength data collected by the first sensor 131 and the second sensor 133 to the data processing unit 140. Preferably, the preset time period is adjusted based on the patient's muscle strength data for a first time period, historical muscle strength data, and / or medical orders. Preferably, the data processing unit 140 further communicates with a cloud storage server 160 to transmit the analyzed muscle strength variability data and risk assessment results to the cloud storage server 160 for storage; to receive historical data from the cloud storage server 160 to assist in the analysis and judgment of current data and improve the accuracy of prediction; and to allow authorized medical personnel to access the patient's historical and current muscle strength data for remote diagnosis and treatment planning. Preferably, the communication module 132 supports at least one wireless communication technology, including but not limited to Bluetooth, Wi-Fi, NFC, or cellular network technology. Preferably, the user interface 150 is a touch screen for providing interactive operation, guiding the patient to complete standardized movements through the user interface 150, and displaying muscle strength data and assessment results in real time.

[0168] Preferably, the data receiving module 141 and the data analysis module 143 are embedded software modules running on the hardware platform of the data processing unit 140, wherein the hardware platform of the data processing unit 140 includes, but is not limited to, a processor 144, a memory 145, and a storage device 146. Preferably, the data processing unit 140 is further configured with a data caching module 142 for temporarily storing real-time muscle strength data received from the wearable device, ensuring that data is not lost when the wireless network is unstable or interrupted. Preferably, the data analysis module 143 is configured with a machine learning algorithm to learn and adapt to the muscle strength fluctuation characteristics of individual patients and update the algorithm model over time. The data analysis module 143 is configured with an anomaly detection algorithm for detecting and marking anomalies in the muscle strength data. The data analysis module 143 is also configured with a trend analysis algorithm for identifying long-term trends and short-term fluctuations from muscle strength data over continuous time periods to assist in assessing the progression of myasthenia gravis.

[0169] According to another preferred embodiment, in clinical scenarios where patients with myasthenia gravis experience respiratory muscle weakness and require mechanical ventilation, existing technologies rely solely on muscle activity and respiratory mechanics parameters to determine the presence of patient-ventilator resistance or poor ventilation, lacking the ability to dynamically assess the patient's overall pathophysiological state, particularly lacking the integration and utilization of blood indicators reflecting disease activity or inflammatory status. Therefore, it is impossible to accurately determine the patient's disease progression trend or achieve individualized, adaptive adjustments to ventilation parameters. This embodiment provides a ventilation detection method and device for myasthenia gravis patients based on laboratory tests, aiming to solve the above problems. By integrating muscle strength, respiratory mechanics parameters, and blood test indicators, it achieves a comprehensive assessment of the patient's condition and enables adaptive adjustment of mechanical ventilation parameters accordingly.

[0170] According to a preferred embodiment, a ventilation detection device for patients with myasthenia gravis based on test results is provided. The device includes a muscle strength monitoring module configured to monitor the muscle activity of the swallowing muscles in patients with myasthenia gravis; monitor the muscle activity of proximal limb muscles (such as the deltoid and quadriceps femoris) in patients with myasthenia gravis; and calculate a muscle strength index based on the activity data of the swallowing muscles and proximal limb muscles to assess the patient's muscle strength status. The ventilation detection device also includes a respiratory monitoring module configured to detect the respiratory rate of patients with myasthenia gravis during mechanical ventilation; detect the tidal volume and inspiratory time of each respiratory cycle; obtain trend data of the above parameters over time; and determine whether there is respiratory drive instability or poor patient-ventilator synchrony. The ventilation monitoring device also includes a blood testing module, configured to obtain blood samples from patients with myasthenia gravis; detect multiple key indicators in the blood reflecting the degree of disease activity, including but not limited to: anti-acetylcholine receptor antibody (AChR Ab) levels; concentrations of inflammatory factors such as interleukin-6 (IL-6); blood oxygen saturation (SpO2); arterial blood gas analysis (including pH, PaO2, PaCO2); muscle damage markers such as creatine kinase (CK) and lactate dehydrogenase (LDH); and upload the test results to the control module for comprehensive analysis. The ventilation detection device also includes a control module, which is signal-connected to the muscle strength monitoring module, respiratory monitoring module, and blood detection module. It is configured to acquire muscle strength index from the muscle strength monitoring module; acquire trend data of respiratory rate, tidal volume, and inspiratory time from the respiratory monitoring module; acquire the patient's blood test indicators from the blood detection module; establish a myasthenia gravis condition assessment model based on the above multimodal data to identify whether the patient's condition is worsening, ventilation demand is increasing, or patient-ventilator incoordination is occurring; when the muscle strength index is below a preset threshold, and the respiratory parameter trends are inconsistent with the preset model trends, combined with elevated levels of inflammatory factors or antibodies in the blood, it determines that patient-ventilator resistance exists during ventilator support; and based on the comprehensive assessment results, dynamically adjust the ventilation support mode (such as pressure control, volume control, bilevel mode, etc.) and parameters (such as inspiratory pressure, positive end-expiratory pressure PEEP, IPR ratio, etc.). Preferably, the ventilation detection device also includes a human-machine interaction module, configured to: display the current patient's muscle status, respiratory status, and blood indicators to medical staff; provide ventilation parameter suggestions or automatic adjustment reminders; and receive manual adjustment input or confirmation from medical staff.

[0171] According to another specific implementation, a ventilation monitoring method for patients with myasthenia gravis based on laboratory tests is provided, including the following steps: 1. Real-time acquisition of patient physiological data: Electromyography (EMG) sensors are used to collect EMG signals from swallowing muscles and proximal limb muscle groups; respiratory rate, tidal volume, and inspiratory time are recorded using respiratory monitoring equipment; relevant biomarkers in blood samples are analyzed using blood testing equipment. 2. Feature extraction and fusion analysis of the collected data: Muscle strength index is calculated based on EMG signals; trends in respiratory parameter changes are analyzed to determine whether respiratory muscle fatigue or patient-ventilator incoordination occurs; inflammatory factors and antibody levels from blood test results are cross-analyzed with muscle-respiratory data to assess the patient's ventilation needs and disease activity. 3. Construction of a multi-parameter comprehensive assessment model: A comprehensive scoring system is established using machine learning or rule-based models to output a comprehensive assessment value of the patient's ventilation stability, muscle function status, and disease activity. 4. Automated adjustment of ventilation parameters: If the comprehensive assessment value exceeds a set threshold, the mechanical ventilation mode and parameters are automatically adjusted to optimize ventilation support; if there is a risk of patient-ventilator resistance, medical staff are prompted to intervene or change the ventilation strategy. V. Feedback and Recording: Provide real-time feedback on patient status and ventilation adjustment results; record changes in ventilation parameters and disease progression trends for clinical decision-making reference.

[0172] Patients with myasthenia gravis are prone to respiratory muscle weakness and ventilatory dysfunction when their condition worsens due to neuromuscular junction dysfunction. By simultaneously collecting multi-dimensional data on patients' muscle strength, respiratory mechanics, and blood biomarkers, and making comprehensive judgments based on a multi-parameter fusion assessment model, adverse conditions during ventilatory support, such as patient-ventilator asynchrony, disease deterioration, or insufficient ventilatory support, can be identified earlier and more accurately. Based on this, dynamically optimizing mechanical ventilation modes and parameters can improve ventilation efficiency, reduce the incidence of complications, and achieve intelligent management of myasthenia gravis patients.

[0173] Compared with existing technologies, this embodiment has the following beneficial effects: Multi-dimensional data fusion assessment improves judgment accuracy; it not only relies on muscle strength and respiratory mechanics data but also combines blood test results to comprehensively assess the condition of myasthenia gravis patients, improving the scientific nature and precision of ventilation strategies; Dynamic adjustment of ventilation parameters enables individualized treatment; Based on real-time detection data and condition assessment, it automatically adjusts ventilation modes and parameters to achieve individualized, adaptive ventilation support, improving patient comfort and ventilation effectiveness; Early warning of patient-ventilator incompatibility and changes in condition can identify risks such as patient-ventilator asynchrony and insufficient ventilation support in advance, allowing for timely intervention and preventing further aggravation of respiratory muscle fatigue; Improved efficiency and safety in intensive care management, facilitating early identification and management of myasthenic crisis, and reducing ICU stay and mortality.

[0174] Specifically, the muscle strength monitoring module is constructed as follows: Surface electromyography (EMG) sensors (such as the MyoMVC system from Noraxon, USA) are attached to the patient's suprahyoid muscles (representing the swallowing muscles) and the middle deltoid muscle (representing the proximal limb muscles), respectively. The sampling frequency is set to 1000Hz, the sampling duration is 10 seconds / sample, and samples are collected every 5 minutes. The obtained raw EMG signals are filtered by a bandpass filter (filtering range 20–500Hz) to remove interference, and the EMG energy value for each sampling time is calculated by rectification and RMS (root mean square). After standardization of the EMG energy values ​​(using the EMG energy at the maximum voluntary contraction of a healthy adult subject as 100%), the Muscle Strength Index (MSI) of each muscle group is obtained. If the swallowing muscle MSI is below 30% of the standardized value for two consecutive times, and the deltoid MSI is below 40% of the standardized value, a "significant decrease in muscle strength" signal is output and sent to the control module.

[0175] The respiratory monitoring module uses invasive mechanical ventilation equipment (such as...) The Evita Infinity V500 provides ventilatory support to the patient, set to pressure control mode (PCV). Initial parameters are set as follows: inspiratory pressure (Pinsp) of 18 cmH2O, positive end-expiratory pressure (PEEP) of 5 cmH2O, I:E ratio of 1:2, and respiratory rate of 14 breaths / minute. The respiratory monitoring module acquires respiratory waveforms and parameter data from the ventilation device, collecting respiratory cycle data every 10 seconds and calculating the following parameters: respiratory rate (RR, breaths / minute); tidal volume per breath (Vt, mL / kg); inspiratory time per breath (Ti, seconds); and mean airway pressure (Pmean). Trend analysis is performed every 5 minutes: if Vt decreases by more than 10% and Ti fluctuates by more than ±15% in two consecutive measurements, the respiratory parameters are considered unstable, indicating insufficient ventilatory support or patient-ventilator asynchrony. This analysis result is transmitted to the control module.

[0176] The blood testing module is configured to collect venous blood samples from patients via an indwelling central venous catheter, every 12 hours (7:00 AM and 10:00 PM); the blood samples are sent to an ICU bedside blood gas analyzer (such as Abbott i-STAT) for rapid blood gas analysis (pH, PaO2, PaCO2, SpO2); another venous blood sample is sent to the laboratory for immunological testing: AChR antibody titer (using radioimmunoassay); IL-6 concentration (using ELISA); creatine kinase (CK) activity (using an automated biochemical analyzer); when the IL-6 concentration exceeds 15 pg / mL, the AChR antibody titer is higher than 2.0 nmol / L, or the CK activity increases to above 300 U / L, the patient is determined to be in a state of active immune inflammation or muscle damage, and an abnormal signal is sent to the control module.

[0177] The control module receives data from the muscle strength monitoring module, respiratory monitoring module, and blood detection module, and performs the following judgments and processing: (1) Initial state (Baseline): Muscle strength indicators are within the normal range, respiratory parameters are stable, and blood detection indicators are normal; keep the current ventilation parameters unchanged and continue monitoring. (2) If muscle strength decreases, breathing becomes unstable, and blood indicators increase, for example, in the muscle strength index, the electromyography index of the swallowing muscle is less than 30%, and the electromyography index of the deltoid muscle is less than 40%; in the respiratory parameters, Vt decreases by more than or equal to 10%, and Ti fluctuates by ±15%; in the blood detection parameter, IL-6 exceeds 15 pg / mL, then it is judged that there is a lack of synchronization between the human and the machine; the inflammatory response worsens, indicating that the condition is deteriorating; the control module calls the ventilation adjustment strategy, for example, switching the ventilation mode from pressure control (PCV) to pressure support (PSV) + control command ventilation (CMV). Combined mode; increase inspiratory pressure from 18cmH2O to 20cmH2O; increase positive end-expiratory pressure (PEEP) from 5cmH2O to 6cmH2O; adjust the inspiratory-to-expiratory ratio from 1:2 to 1:1.8 to prolong expiratory time; send a prompt message to the human-machine interface: "Human-machine asynchrony and decreased muscle strength have been detected. Please check the intubation depth and sedation status." (3) If a single or partial indicator is abnormal, such as only: elevated blood IL-6 or decreased swallowing muscle electromyography signal, a warning signal will be issued but the ventilation parameters will not be changed. Only the medical staff will be reminded to strengthen observation. (4) Ventilation effect feedback and recording: the control module outputs a comprehensive report every hour, including the data collected by each module; the control logic judgment process; ventilation parameter adjustment records; all data are uploaded to the electronic medical record system through the hospital information system (HIS) for doctors to access and review.

[0178] Specifically, the human-machine interface module includes a touch-screen LCD display, installed on the mechanical ventilation device. The display interface shows real-time electromyographic energy trends of the swallowing and deltoid muscles, respiratory parameter change curves (Vt, RR, Ti), blood IL-6 and AChR antibody values, as well as ventilation modes and parameter adjustment records. It supports medical staff to manually override the automatic adjustment logic and input new ventilation target parameters. After each ventilation parameter adjustment, the system automatically records the operator and the reason for the modification for clinical quality control.

[0179] Each module is connected via RS485 communication protocol to achieve high-speed data transmission; the control module adopts an embedded industrial computer (such as Advantech UNO-2484G); the data acquisition cycle is controlled by a timer with an accuracy of ±1ms; all sensors, acquisition devices and ventilation equipment have CE certification and medical-grade protection level (IP44); the system supports UPS uninterruptible power supply to ensure that data is not lost in the event of a sudden power outage.

[0180] According to a specific case, Patient A is a 42-year-old woman who has been diagnosed with myasthenia gravis for 6 years. She was admitted to the ICU due to dysphagia and respiratory muscle weakness and was managed using the ventilation detection device described in this embodiment. Day 1, 7:00 AM: Swallowing muscle electromyography index was 85%, deltoid muscle was 90%; respiratory parameters were normal; IL-6 was 8 pg / mL; ventilation mode was maintained at PCV, parameters remained unchanged. Day 2, 2:00 PM: Muscle strength decreased, swallowing muscle decreased to 28%, deltoid muscle to 38%; respiratory rate increased from 14 to 20 breaths / min, Vt decreased by 12%; IL-6 increased to 22 pg / mL; the control module detected a patient-ventilator asynchrony and initiated ventilation parameter adjustment; ventilation mode was switched to PSV+CMV; after receiving the alarm, medical staff administered gamma globulin to the patient. Day 3, 7:00 AM: IL-6 decreased to 10 pg / mL, muscle strength index recovered; respiratory parameters tended to stabilize; the control module returned to the initial ventilation mode; on the 5th day after the condition stabilized, the patient was successfully weaned off the ventilator and extubated.

[0181] It should be noted that the specific embodiments described above are exemplary. Those skilled in the art can devise various solutions inspired by the disclosure of this invention, and these solutions all fall within the scope of this invention and its protection. Those skilled in the art should understand that this specification and its accompanying drawings are illustrative and not intended to limit the scope of the claims. The scope of protection of this invention is defined by the claims and their equivalents. This specification contains multiple inventive concepts; terms such as "preferredly," "according to a preferred embodiment," or "optionally" indicate that the corresponding paragraph discloses an independent concept. The applicant reserves the right to file divisional applications based on each inventive concept.

Claims

1. A ventilation detection device for a myasthenia gravis patient, characterized by, The device comprises: a muscle strength monitoring module configured to monitor muscle activity of a swallowing muscle and muscle activity of a proximal limb of a myasthenia gravis patient, and obtain muscle strength data of the myasthenia gravis patient according to the monitoring data of the muscle activity of the swallowing muscle and the monitoring data of the muscle activity of the proximal limb; a respiration monitoring module configured to detect respiratory frequency, tidal volume of each respiratory cycle and inspiratory time of each respiratory cycle in the case of mechanical assisted ventilation of the myasthenia gravis patient, and obtain the change trend of the respiratory frequency, the tidal volume of each respiratory cycle and the inspiratory time over time; a control module in signal connection with the muscle strength monitoring module and the respiration monitoring module, configured to obtain the muscle strength data of the myasthenia gravis patient from the muscle strength monitoring module, and obtain the change trend of the respiratory frequency, the tidal volume of each respiratory cycle and the inspiratory time of the myasthenia gravis patient over time from the respiration monitoring module, wherein when the muscle strength data of the myasthenia gravis patient is lower than a preset muscle strength threshold, and the change trend of the respiratory frequency, the tidal volume of each respiratory cycle and the inspiratory time over time is inconsistent with the change trend of the corresponding parameters stored in advance, it is determined that there is human-machine resistance in the mechanical assisted ventilation of the myasthenia gravis patient.

2. The ventilation detection device for a myasthenia gravis patient according to claim 1, characterized by, The control module is further configured to: if the increase of the respiratory frequency is accompanied by fluctuation of the tidal volume waveform, it is determined that the ventilator gas delivery is not triggered effectively.

3. The ventilation detection device for a myasthenia gravis patient according to claim 1, characterized by, The control module is further configured to: if the increase of the respiratory frequency is accompanied by the increase of the inspiratory time, it is determined that the ventilator gas delivery is insufficient.

4. A method for ventilation detection for a myasthenia gravis patient, applied to a breathing assistance system, characterized in that, The method comprises: monitoring muscle activity of a swallowing muscle and muscle activity of a proximal limb of a myasthenia gravis patient; obtaining muscle strength data of the myasthenia gravis patient according to the monitoring data of the muscle activity of the swallowing muscle and the monitoring data of the muscle activity of the proximal limb; detecting respiratory frequency, tidal volume of each respiratory cycle and inspiratory time of each respiratory cycle in the case of mechanical assisted ventilation of the myasthenia gravis patient; obtaining the change trend of the respiratory frequency, the tidal volume of each respiratory cycle and the inspiratory time over time; when the muscle strength data of the myasthenia gravis patient is lower than a preset muscle strength threshold, and the change trend of the respiratory frequency, the tidal volume of each respiratory cycle and the inspiratory time over time is inconsistent with the change trend of the corresponding parameters stored in advance, it is determined that there is human-machine resistance in the mechanical assisted ventilation of the myasthenia gravis patient.

5. The method for detecting ventilation in a patient with myasthenia gravis according to claim 4, wherein Obtaining muscle strength data of the myasthenia gravis patient according to the monitoring data of the muscle activity of the swallowing muscle and the monitoring data of the muscle activity of the proximal limb comprises: collecting muscle strength data of a first period when the patient performs a first standardized action as reference muscle strength data; collecting muscle strength data of a second period in a preset time period after the patient performs the first standardized action; analyzing muscle strength fluctuation according to the muscle strength data of the second period and the reference muscle strength data.

6. The method for detecting ventilation in a patient with myasthenia gravis according to claim 5, wherein, The first standardized action is swallowing and / or arm lifting action.

7. The method of claim 4, wherein the method is for a patient with myasthenia gravis. After determining that there is human-machine resistance in the mechanical assisted ventilation of the myasthenia gravis, the method further comprises: judging the type of human-machine resistance according to the change trend of the respiratory frequency, the tidal volume of each respiratory cycle and the inspiratory over time.

8. The method for detecting ventilation in a patient with myasthenia gravis according to claim 7, wherein, If the respiratory rate increases with fluctuations in the tidal volume waveform, it is determined that the ventilator gas delivery is not being effectively triggered.

9. The method for detecting ventilation in a patient with myasthenia gravis according to claim 7, wherein, If the respiratory rate increases with an increase in the inspiratory time, it is determined that the ventilator gas delivery is insufficient.

10. The method of claim 7, wherein the method is for a patient with myasthenia gravis. If the tidal volume is lower than a preset tidal volume threshold, the inspiratory time is shorter than a preset inspiratory time threshold, and the respiratory rate increases, it is determined that the ventilator has an early exhalation trigger.

11. A ventilation detection device for detecting a muscle weakness patient based on inspection detection, characterized by, The application comprises: a muscle strength monitoring module comprising electromyographic sensors attached to the swallowing muscle groups and the proximal limb muscle surface of the patient, for collecting electromyographic signals and calculating a muscle strength index; a respiration monitoring module connected to a mechanical ventilation device, for obtaining the respiratory rate, tidal volume, and inspiratory time parameters of the patient, and analyzing the trends of the parameters over time; a blood detection module for collecting a blood sample of the patient and detecting the levels of inflammatory factors and anti-acetylcholine receptor antibodies in the blood; a control module connected to the muscle strength monitoring module, the respiration monitoring module, and the blood detection module, for receiving muscle strength index data, respiration parameter trend data, and blood detection data; When the muscle strength index is lower than a preset first threshold, the respiration parameter trend is inconsistent with a preset pattern, and the levels of inflammatory factors or anti-acetylcholine receptor antibodies in the blood are higher than a preset second threshold, it is determined that there is a patient-ventilator asynchrony during ventilation.

12. The ventilation detection device of claim 11, wherein, The electromyographic signal collection of the swallowing muscle groups by the muscle strength monitoring module is achieved through electromyographic electrodes arranged in the suprahyoid muscle group, and the proximal limb muscle is the middle deltoid muscle; the muscle strength index is the standardized root mean square electromyographic signal intensity.

13. The ventilation detection device of claim 12, wherein, The inflammatory factors detected by the blood detection module also include interleukin-6, pH, oxygen partial pressure, and carbon dioxide partial pressure, as well as muscle injury markers, wherein the muscle injury markers include creatine kinase and lactate dehydrogenase.

14. The ventilation detection device of claim 13, wherein, When the control module identifies the patient-ventilator asynchrony risk, it automatically adjusts the ventilation support mode, including switching from pressure control to volume control or bi-level ventilation mode, or adjusting the inspiratory pressure, positive end-expiratory pressure, and inspiratory-expiratory ratio to improve ventilation synchrony and patient comfort.

15. The ventilation detection device of claim 14, wherein, The ventilation detection device further comprises a human-computer interaction module configured to display the data collected by each module, the judgment results of the control module, and the ventilation parameter adjustment results, and to receive the input or confirmation of the medical staff on the ventilation parameters; the human-computer interaction module is configured to display the muscle strength index trend, the respiration parameter curve, the blood detection index results, and the judgment results of the control module in the form of graphs or numerical values, and to provide ventilation parameter adjustment suggestions to support manual adjustment or confirmation of automatic adjustment operations by medical staff.

Images