An intelligent processing method and system for physiological data of patients with critical respiratory diseases

Abstract

The present invention discloses an intelligent processing method and system for the physiological data of a patient with a respiratory critical illness, including: decomposing the volume-time curve through an STL time series, obtaining the residual terms of the volume-time curve under abnormal fluctuations and without abnormal fluctuations, respectively, and then determining whether the current volume data is abnormal data; based on the residual value performance of the acquired abnormal data corresponding to the respiratory cycle on the airway pressure-time curve, obtaining the possibility of abnormal tidal volume caused by airway leakage; based on the possibility of abnormal data and the possibility of abnormal tidal volume caused by airway leakage, obtaining the abnormal degree of abnormal tidal volume data caused by airway leakage, and correcting the abnormal data according to the abnormal degree of abnormal tidal volume data caused by airway leakage. The present invention can accurately determine the possibility of abnormal data, and can also perform intelligent correction according to the abnormal degree, so as to obtain tidal volume data that is closer to reality.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and relates to an intelligent processing method and system for physiological data of patients with critical respiratory illness. Background Art

[0002] Critically ill respiratory patients are those whose oxygenation, ventilation or gas exchange capacity is significantly reduced due to severe respiratory dysfunction or acute respiratory failure. Critically ill respiratory patients need to closely monitor various physiological data, such as blood oxygen saturation, respiratory rate, tidal volume, airway pressure and other data. The monitoring of these data can not only help doctors evaluate the patient's current clinical status, but also effectively guide treatment decisions and adjust treatment strategies. Among them, in critically ill respiratory patients, especially those using mechanical ventilation, the monitoring of tidal volume is of vital importance, which can help doctors understand the patient's respiratory function, ventilation effect and lung condition.

[0003] At present, tidal volume monitoring for critically ill respiratory patients usually utilizes the built-in tidal volume monitoring system of the ventilator to monitor and calculate based on relevant sensors. However, during the use of the ventilator, airway leakage often occurs in the ventilator due to reasons such as unsealed endotracheal tube or pipe joints, leakage of endotracheal tube balloon, etc., resulting in the actual monitored and collected patient's lung breathing tidal volume data being lower than the actual tidal volume data. Especially in mechanical ventilation mode, leakage may mask the actual inadequate ventilation, affect the evaluation of ventilation effects, and prevent doctors from adjusting treatment strategies in a timely manner according to the patient's actual respiratory status. Therefore, timely identification and treatment of airway leakage is crucial for the management of critically ill patients. Summary of the invention

[0004] The purpose of the present invention is to solve the problem in the prior art that the ventilator has airway leakage due to unsealed and unstable trachea, resulting in inaccurate patient tidal volume monitoring data, and to provide an intelligent processing method and system for the physiological data of critically ill respiratory patients.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] An intelligent processing method for physiological data of a patient with a respiratory critical illness, comprising:

[0007] Collect lung gas volume data and airway pressure data of critically ill patients;

[0008] Based on the changing relationship between the patient's lung gas volume data, airway pressure data and time, a volume-time curve and an airway pressure-time curve are constructed respectively;

[0009] The volume-time curve is decomposed by STL time series to obtain the residual terms of the volume-time curve under abnormal fluctuation and without abnormal fluctuation respectively, and the possibility of each volume data being abnormal data is calculated based on the difference between the two, and then it is determined whether the current volume data is abnormal data; if so, proceed to the next step;

[0010] Decompose the airway pressure-time curve based on the STL time series decomposition algorithm to obtain the residual value on the airway pressure-time curve;

[0011] Based on the residual value of the acquired abnormal data corresponding to the respiratory cycle on the airway pressure-time curve, the possibility of abnormal tidal volume caused by airway leakage is obtained;

[0012] Based on the possibility of abnormal data and the possibility of abnormal tidal volume caused by airway leakage, the abnormal degree of abnormal tidal volume data caused by airway leakage is obtained, and the abnormal data is corrected according to the abnormal degree of abnormal tidal volume data caused by airway leakage to obtain real tidal volume data.

[0013] A further improvement of the present invention is:

[0014] Furthermore, based on the relationship between the patient's lung gas volume data, airway pressure data and time, a volume-time curve and an airway pressure-time curve are constructed, specifically:

[0015] When there is no abnormal airway leakage, the lung gas volume changes regularly and the volume-time curve is obtained; when airway leakage occurs, part of the gas leaks during the transmission process, and the actual gas delivered to the patient will be lower than the set value, and the stability of the delivery process will also be reduced, that is, the volume-time curve will show irregular fluctuations;

[0016] Under normal conditions, the patient's airway pressure rises steadily during the inhalation phase and gradually decreases to 0 during the exhalation phase. An airway pressure-time curve is constructed based on the patient's inhalation and exhalation phase data, and the inhalation and exhalation phases show a certain symmetry.

[0017] Furthermore, the volume-time curve is decomposed by STL time series to obtain the residual terms of the volume-time curve under abnormal fluctuation and without abnormal fluctuation, which are as follows:

[0018] Normal volume data changes periodically, while the irregular fluctuations of abnormal data will deviate from the original periodic law. Therefore, the volume-time curve is decomposed through STL time series to obtain the residual term of the curve:

[0019]

[0020] in, represents the original volume data, represents the trend term of volume data, represents the seasonal term of volume data, Residual term representing volume data;

[0021] The residual term of the volume-time curve without abnormal fluctuations is a stable curve basically consistent with the central axis; the central axis is a straight line with y=0; when abnormal fluctuations occur, the volume residual term at the moment of fluctuation deviates from the central axis, and the greater the degree of deviation, the more obvious the fluctuation, that is, the higher the degree of abnormality.

[0022] Furthermore, the possibility of each volume data being abnormal data is calculated based on the difference between the two, specifically:

[0023]

[0024] in, Indicates i The possibility that the volume data at a monitoring moment is abnormal data, Indicates i The residual value of volume data at each monitoring moment; Represents the residual value without fluctuation, that is, the central axis of the residual curve, where Indicates i The deviation degree of the volume data residual at each monitoring moment relative to the central axis. The greater the deviation degree, the higher the possibility that the corresponding volume data is abnormal data; represents the normalization function;

[0025] Determine whether the current volume data is abnormal data, specifically:

[0026] Based on the relationship between the probability of the abnormal data and the preset threshold, if the probability is greater than the set threshold, the current volume data is considered to be abnormal data.

[0027] Furthermore, the airway pressure-time curve is decomposed based on the STL time series decomposition algorithm to obtain the residual value on the airway pressure-time curve, specifically:

[0028] For abnormal data caused by airway leakage, the residual value of the airway pressure-time curve should change less, that is, the distance between the residual points is small; while for abnormal data caused by airway obstruction, the residual value of the airway pressure-time curve changes greatly in the period corresponding to the monitoring time;

[0029]

[0030] in, Represents the raw airway pressure data, Represents the trend term of airway pressure data, represents the seasonal term of the airway pressure data, Residual term representing the airway pressure data.

[0031] Furthermore, before obtaining the possibility of abnormal tidal volume caused by airway leakage, the method further includes: , divide the airway pressure-time curve into multiple respiratory cycles; obtain the corresponding respiratory cycle according to the corresponding monitoring time of the abnormal data; calculate the average distance between the residual values ​​of adjacent airway pressure data in the respiratory cycle corresponding to the abnormal data, the larger the average distance, the larger the fluctuation amplitude of the airway pressure in the respiratory cycle corresponding to the abnormal data, that is, the more likely the abnormal data is caused by airway obstruction; since the time interval of the monitoring data is consistent, the difference of the residual items represents the distance between the residual values.

[0032] Furthermore, based on the residual value of the acquired abnormal data corresponding to the respiratory cycle on the airway pressure-time curve, the possibility of abnormal tidal volume caused by airway leakage is obtained, specifically:

[0033]

[0034] in, Indicates i The abnormal data is the possibility of airway leakage. Indicates i The number of monitoring moments contained in the corresponding period of abnormal data, Indicates i The abnormal data corresponds to the j The residual value of airway pressure at each monitoring moment, Indicates i The difference between the residual values ​​of airway pressure at adjacent monitoring moments in the respiratory cycle corresponding to each abnormal data, that is, the distance between the residual values ​​of airway pressure at adjacent monitoring moments, Indicates i The average distance between the residual values ​​of airway pressure at adjacent monitoring moments in the respiratory cycle corresponding to the abnormal data is for The inverse of The smaller the time, the The larger the value is, the smaller the average distance of the residual values ​​is, and the more likely it is that the tidal volume data is abnormal due to airway leakage; Indicates i The abnormal data corresponds to the peak value of airway pressure during the respiratory cycle. Indicates i The peak value of airway pressure in the respiratory cycle before the abnormal data. Indicates i The peak value of airway pressure in the next respiratory cycle after abnormal data; Indicates i The difference between the peak value of airway pressure in the respiratory cycle and the peak value of airway pressure in the adjacent respiratory cycle corresponding to the abnormal data, that is, the consistency with the peak value of airway pressure in the adjacent respiratory cycle, It means that the smaller the difference in the peak values ​​of airway pressure between adjacent respiratory cycles, that is, the higher the consistency, the more likely the abnormal data is caused by airway leakage.

[0035] Further, based on the possibility of abnormal data and the possibility of abnormal tidal volume caused by airway leakage, the abnormal degree of abnormal tidal volume data caused by airway leakage is obtained, specifically:

[0036] The more serious the airway leakage is, the more unstable the gas transmission will be during the patient's breathing process, that is, the higher the degree of deviation of the tidal volume data from the original breathing pattern; the more serious the airway leakage is, the more obvious the abnormal characteristics of the airway leakage it exhibits, that is, the easier it is to be identified as a leakage abnormality; the higher the possibility that the tidal volume data is abnormal data, and the higher the possibility that it is caused by airway leakage, the higher the abnormal degree of the abnormal data;

[0037]

[0038] in, Indicates i The abnormality of the tidal volume data Indicates i The possibility that the data is abnormal data, Indicates i The first data is the possibility of abnormal tidal volume due to airway leak.

[0039] Furthermore, the abnormal data is corrected according to the abnormal degree of the abnormal tidal volume data caused by airway leakage to obtain the real tidal volume data, specifically:

[0040]

[0041] in, Indicates i The true value after correction of abnormal tidal volume data caused by airway leakage. Indicates i The abnormal tidal volume data monitoring value caused by airway leakage, Indicates i The degree of abnormality of the abnormal tidal volume data caused by airway leakage; It means that according to the degree of abnormality, the original tidal volume monitoring value is increased to correct the abnormally low tidal volume of the patient caused by airway leakage of the ventilator equipment, so as to obtain the real tidal volume data.

[0042] An intelligent processing system for physiological data of patients with critical respiratory diseases, characterized by comprising:

[0043] A collection module, which collects lung gas volume data and airway pressure data of patients with critical respiratory diseases;

[0044] A construction module, wherein the construction module constructs a volume-time curve and an airway pressure-time curve based on the relationship between the patient's lung gas volume data, airway pressure data and time;

[0045] A judgment module, wherein the judgment module decomposes the volume-time curve through the STL time series, obtains the residual terms of the volume-time curve under abnormal fluctuation and without abnormal fluctuation respectively, and calculates the possibility of each volume data being abnormal data based on the difference between the two, and then determines whether the current volume data is abnormal data; if so, proceeds to the next step;

[0046] A decomposition module, wherein the decomposition module decomposes the airway pressure-time curve based on the STL time series decomposition algorithm to obtain a residual value on the airway pressure-time curve;

[0047] An acquisition module, wherein the acquisition module acquires the possibility that the abnormal tidal volume is caused by airway leakage based on the residual value expression of the acquired abnormal data corresponding to the respiratory cycle on the airway pressure-time curve;

[0048] A correction module, wherein the correction module obtains the abnormality degree of the abnormal tidal volume data caused by airway leakage based on the possibility of abnormal data and the possibility of abnormal tidal volume caused by airway leakage, and corrects the abnormal data according to the abnormality degree of the abnormal tidal volume data caused by airway leakage to obtain real tidal volume data.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] The present invention comprehensively analyzes the patient's lung gas volume, airway pressure and time variation relationship, uses the STL time series decomposition method to accurately distinguish normal and abnormal fluctuations in the volume-time curve, and effectively identifies and evaluates the abnormality of tidal volume data. At the same time, combined with the residual analysis of the airway pressure-time curve, the diagnostic accuracy of abnormal tidal volume caused by airway leakage is further improved. The present invention can accurately determine the possibility of abnormal data, and can also perform intelligent corrections based on the degree of abnormality, thereby obtaining tidal volume data that is closer to reality. This not only optimizes the clinical decision-making process, but also provides patients with more accurate treatment plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 A schematic flow chart of the intelligent processing method for physiological data of critically ill respiratory patients of the present invention;

[0053] Figure 2 It is a structural schematic diagram of the intelligent processing system of physiological data of critically ill respiratory patients of the present invention;

[0054] Figure 3 is the volume-time curve;

[0055] Figure 4 It is a schematic diagram of the relationship between the volume residual term and the central axis at the moment of fluctuation when abnormal fluctuation occurs;

[0056] Figure 5 It is the airway pressure-time waveform. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0058] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0060] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0061] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0062] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0063] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0064] See also Figure 1 The present invention discloses an intelligent processing method for physiological data of patients with critical respiratory diseases, comprising:

[0065] S101, collects lung gas volume data and airway pressure data of patients with critical respiratory diseases;

[0066] S102, constructing a volume-time curve and an airway pressure-time curve respectively based on the relationship between the patient's lung gas volume data, airway pressure data and time;

[0067] When there is no abnormal airway leakage, the lung gas volume changes regularly and the volume-time curve is obtained; when airway leakage occurs, part of the gas leaks during the transmission process, and the actual gas delivered to the patient will be lower than the set value, and the stability of the delivery process will also be reduced, that is, the volume-time curve will show irregular fluctuations;

[0068] Under normal conditions, the patient's airway pressure rises steadily during the inhalation phase and gradually decreases to 0 during the exhalation phase. An airway pressure-time curve is constructed based on the patient's inhalation and exhalation phase data, and the inhalation and exhalation phases show a certain symmetry.

[0069] S103, decomposing the volume-time curve by STL time series, obtaining the residual terms of the volume-time curve under abnormal fluctuation and without abnormal fluctuation respectively, and calculating the possibility of each volume data being abnormal data based on the difference between the two, and then determining whether the current volume data is abnormal data; if so, proceeding to the next step;

[0070] The volume-time curve is decomposed by STL time series to obtain the residual terms of the volume-time curve under abnormal fluctuation and without abnormal fluctuation, specifically:

[0071] Normal volume data changes periodically, while the irregular fluctuations of abnormal data will deviate from the original periodic law. Therefore, the volume-time curve is decomposed through STL time series to obtain the residual term of the curve:

[0072]

[0073] in, represents the original volume data, represents the trend term of volume data, represents the seasonal term of volume data, Residual term representing volume data;

[0074] The residual term of the volume-time curve without abnormal fluctuations is a stable curve basically consistent with the central axis; the central axis is a straight line with y=0; when abnormal fluctuations occur, the volume residual term at the moment of fluctuation deviates from the central axis, and the greater the degree of deviation, the more obvious the fluctuation, that is, the higher the degree of abnormality.

[0075] The possibility of each volume data being abnormal data is calculated based on the difference between the two, specifically:

[0076]

[0077] in, Indicates i The possibility that the volume data at a monitoring moment is abnormal data, Indicates i The residual value of volume data at each monitoring moment; Represents the residual value without fluctuation, that is, the central axis of the residual curve, where Indicates i The deviation degree of the volume data residual at each monitoring moment relative to the central axis. The greater the deviation degree, the higher the possibility that the corresponding volume data is abnormal data; represents the normalization function;

[0078] Determine whether the current volume data is abnormal data, specifically:

[0079] Based on the relationship between the probability of the abnormal data and the preset threshold, if the probability is greater than the set threshold, the current volume data is considered to be abnormal data.

[0080] S104, decomposing the airway pressure-time curve based on the STL time series decomposition algorithm to obtain a residual value on the airway pressure-time curve;

[0081] For abnormal data caused by airway leakage, the residual value of the airway pressure-time curve should change less, that is, the distance between the residual points is small; while for abnormal data caused by airway obstruction, the residual value of the airway pressure-time curve changes greatly in the period corresponding to the monitoring time;

[0082]

[0083] in, Represents the raw airway pressure data, Represents the trend term of airway pressure data, represents the seasonal term of the airway pressure data, Residual term representing the airway pressure data.

[0084] Before obtaining the possibility of airway leak causing abnormal tidal volume, it also includes: seasonal items based on the patient's airway pressure data , divide the airway pressure-time curve into multiple respiratory cycles; obtain the corresponding respiratory cycle according to the corresponding monitoring time of the abnormal data; calculate the average distance between the residual values ​​of adjacent airway pressure data in the respiratory cycle corresponding to the abnormal data, the larger the average distance, the larger the fluctuation amplitude of the airway pressure in the respiratory cycle corresponding to the abnormal data, that is, the more likely the abnormal data is caused by airway obstruction; since the time interval of the monitoring data is consistent, the difference of the residual items represents the distance between the residual values.

[0085] S105, based on the residual value of the acquired abnormal data corresponding to the respiratory cycle on the airway pressure-time curve, the possibility of abnormal tidal volume caused by airway leakage is obtained;

[0086]

[0087] in, Indicates i The abnormal data is the possibility of airway leakage. Indicates i The number of monitoring moments contained in the corresponding period of abnormal data, Indicates i The abnormal data corresponds to the j The residual value of airway pressure at each monitoring moment, Indicates i The difference between the residual values ​​of airway pressure at adjacent monitoring moments in the respiratory cycle corresponding to each abnormal data, that is, the distance between the residual values ​​of airway pressure at adjacent monitoring moments, Indicates i The average distance between the residual values ​​of airway pressure at adjacent monitoring moments in the respiratory cycle corresponding to the abnormal data is for The inverse of The smaller the time, the The larger the value is, the smaller the average distance of the residual values ​​is, and the more likely it is that the tidal volume data is abnormal due to airway leakage; Indicates i The abnormal data corresponds to the peak value of airway pressure during the respiratory cycle. Indicates i The peak value of airway pressure in the respiratory cycle before the abnormal data. Indicates i The peak value of airway pressure in the next respiratory cycle after abnormal data; Indicates i The difference between the peak value of airway pressure in the respiratory cycle and the peak value of airway pressure in the adjacent respiratory cycle corresponding to the abnormal data, that is, the consistency with the peak value of airway pressure in the adjacent respiratory cycle, It means that the smaller the difference in the peak values ​​of airway pressure between adjacent respiratory cycles, that is, the higher the consistency, the more likely the abnormal data is caused by airway leakage.

[0088] S106, based on the possibility of abnormal data and the possibility of abnormal tidal volume caused by airway leakage, the abnormal degree of abnormal tidal volume data caused by airway leakage is obtained, and the abnormal data is corrected according to the abnormal degree of abnormal tidal volume data caused by airway leakage to obtain real tidal volume data.

[0089] The more serious the airway leakage is, the more unstable the gas transmission will be during the patient's breathing process, that is, the higher the degree of deviation of the tidal volume data from the original breathing pattern; the more serious the airway leakage is, the more obvious the abnormal characteristics of the airway leakage it exhibits, that is, the easier it is to be identified as a leakage abnormality; the higher the possibility that the tidal volume data is abnormal data, and the higher the possibility that it is caused by airway leakage, the higher the abnormal degree of the abnormal data;

[0090]

[0091] in, Indicates i The abnormality of the tidal volume data Indicates i The possibility that the data is abnormal data, Indicates i The first data is the possibility of abnormal tidal volume due to airway leak.

[0092] According to the abnormal degree of tidal volume abnormal data caused by airway leakage, the abnormal data is corrected to obtain the real tidal volume data, specifically:

[0093]

[0094] in, Indicates i The true value after correction of abnormal tidal volume data caused by airway leakage. Indicates i The abnormal tidal volume data monitoring value caused by airway leakage, Indicates i The degree of abnormality of the abnormal tidal volume data caused by airway leakage; It means that according to the degree of abnormality, the original tidal volume monitoring value is increased to correct the abnormally low tidal volume of the patient caused by airway leakage of the ventilator equipment, so as to obtain the real tidal volume data.

[0095] See also Figure 2 The present invention discloses an intelligent processing system for physiological data of patients with critical respiratory diseases, comprising:

[0096] A collection module, which collects lung gas volume data and airway pressure data of patients with critical respiratory diseases;

[0097] A construction module, wherein the construction module constructs a volume-time curve and an airway pressure-time curve based on the relationship between the patient's lung gas volume data, airway pressure data and time;

[0098] A judgment module, wherein the judgment module decomposes the volume-time curve through the STL time series, obtains the residual terms of the volume-time curve under abnormal fluctuation and without abnormal fluctuation respectively, and calculates the possibility of each volume data being abnormal data based on the difference between the two, and then determines whether the current volume data is abnormal data; if so, proceeds to the next step;

[0099] A decomposition module, wherein the decomposition module decomposes the airway pressure-time curve based on the STL time series decomposition algorithm to obtain a residual value on the airway pressure-time curve;

[0100] An acquisition module, wherein the acquisition module acquires the possibility that the abnormal tidal volume is caused by airway leakage based on the residual value expression of the acquired abnormal data corresponding to the respiratory cycle on the airway pressure-time curve;

[0101] A correction module, wherein the correction module obtains the abnormality degree of the abnormal tidal volume data caused by airway leakage based on the possibility of abnormal data and the possibility of abnormal tidal volume caused by airway leakage, and corrects the abnormal data according to the abnormality degree of the abnormal tidal volume data caused by airway leakage to obtain real tidal volume data.

[0102] Embodiment: The present invention discloses an intelligent processing method for physiological data of a patient with a critical respiratory disease, comprising:

[0103] Step 1: Use a ventilator to monitor the lung gas volume data and airway pressure data of critically ill patients.

[0104] Set various preset parameters of the ventilator, such as respiratory rate, minute ventilation, tidal volume, supply concentration, etc. Then connect the patient to the ventilator, and use the internal flow sensor, pressure sensor and tidal volume monitoring system of the ventilator to continuously monitor the patient's lung gas volume data (i.e. tidal volume data) and airway pressure data, and obtain the volume-time curve and pressure-time curve. Since the patient's state may change during the monitoring process, the accuracy of the obtained tidal volume data is analyzed and corrected every 10 minutes.

[0105] Step 2: Based on the residual distribution characteristics of the corresponding curves of the lung gas volume data and the airway pressure data, the abnormal data caused by airway leakage are identified and the degree of abnormality is calculated.

[0106] Under normal conditions, the patient's tidal volume data shows periodic regular changes, but when airway leakage is abnormal, the waveform formed by the tidal volume monitoring data will show irregular fluctuations. Therefore, the suspected abnormal airway leakage data can be identified by the deviation of the residual of the tidal volume data corresponding to the curve relative to the central axis. Because when the patient has airway obstruction, the tidal volume data will also show irregular fluctuations. In view of the patient's airway obstruction, it is necessary to take corresponding treatment measures for the patient in time, rather than just correcting the tidal volume data. Therefore, it is necessary to further distinguish the abnormal data caused by airway leakage. According to the difference in the performance of airway leakage and airway obstruction abnormalities in airway pressure data, they are distinguished by analyzing the distribution characteristics of the residual of the pressure-time curve. And according to the degree of deviation of the residual from the central axis, the degree of airway leakage abnormality is calculated.

[0107] Therefore, the present invention analyzes the residual distribution of the corresponding curves of the monitored tidal volume data and airway pressure data, and obtains the abnormal degree of the abnormal airway leakage data as follows:

[0108] Step 2.1: Identify abnormal tidal volume data based on the residual of the lung gas volume-time curve.

[0109] The patient's tidal volume data refers to the volume of gas inhaled or exhaled by the lungs during each normal breathing cycle, so it can be directly expressed by the lung gas volume data. When there is no abnormality such as airway leakage, the lung gas volume should show a periodic regular change, that is, the volume-time curve is as follows Figure 3 shown.

[0110] When the ventilator has airway leakage, part of the gas leaks out during the transmission process, and the gas actually delivered to the patient will be lower than the set value. The stability of the delivery process will also decrease, that is, the volume-time curve will show irregular fluctuations. Therefore, based on the irregular fluctuation data in the volume-time curve, the abnormal tidal volume data is identified.

[0111] Because normal volume data changes periodically, and the irregular fluctuations of abnormal data will deviate from the original periodic law, the volume-time curve is decomposed through STL time series to obtain the residual term of the curve:

[0112]

[0113] in, represents the original volume data, represents the trend term of volume data, represents the seasonal term of volume data, Represents the residual term of the volume data.

[0114] The residual term of the volume-time curve without abnormal fluctuations should be a stable curve that is basically consistent with the central axis (y=0). When abnormal fluctuations occur, the volume residual term at the time of fluctuation will deviate from the central axis. The greater the deviation, the more obvious the fluctuation, that is, the higher the abnormality. Figure 4 shown.

[0115] Therefore, the possibility that each volume data is abnormal data is calculated according to the degree of deviation of the residual term of each volume data relative to the central axis.

[0116]

[0117] in, Indicates i The possibility that the volume data at a monitoring moment is abnormal data, Indicates i The residual value of the volume data at each monitoring moment. Represents the residual value without fluctuation, that is, the central axis of the residual curve, where . Indicates i The greater the deviation, the higher the possibility that the corresponding volume data is abnormal data. Represents the normalization function.

[0118] Although the residual of the volume-time curve is always 0 under ideal conditions, the volume data may still have slight fluctuations under normal conditions due to the influence of the patient's spontaneous breathing. However, such slight fluctuations are not data abnormalities, that is, the volume data is still accurate. Therefore, it is stipulated here that when When i The volume data at each monitoring moment is abnormal data.

[0119] Step 2.2: According to the residual distribution of the abnormal tidal volume data on the airway pressure-time curve at the corresponding moment, the abnormal tidal volume data caused by airway leakage is obtained.

[0120] In addition to airway leakage, abnormal fluctuations in volume data (tidal volume) may also be caused by airway obstruction in the patient, which may cause irregular abnormal fluctuations in volume data. The airway obstruction data will be identified as abnormalities caused by ventilator airway leakage. Abnormal data caused by airway leakage can be corrected to obtain accurate patient tidal volume, while airway obstruction is data that reflects the patient's true breathing level and does not need to be corrected. Therefore, it is necessary to further analyze the abnormal data identified in step 1 to obtain abnormal data caused by airway leakage.

[0121] Because the abnormal manifestations of airway leakage and airway obstruction in the volume-time curve are similar, the airway pressure-time curve is analyzed here, and the abnormal data of airway leakage and airway obstruction are distinguished by combining the data distribution characteristics in the curve. Under normal conditions, the airway pressure of the patient rises steadily during the inspiration phase, and gradually decreases to 0 during the expiration phase. In the airway pressure-time waveform, the inspiration phase and the expiration phase show a certain symmetry, such as Figure 5 shown.

[0122] Airway leakage will cause the patient to inhale insufficiently and fail to reach the preset tidal volume, that is, the airway pressure rises slowly during the inhalation phase, and the airway pressure drops less during the exhalation phase, and may not be able to drop to 0, and the corresponding airway pressure-time curve will become flatter. Airway obstruction in patients will cause the airway pressure to rise rapidly during the inhalation phase, and even the peak value will be too high, and the fluctuation of the airway pressure-time curve will be more obvious. Therefore, for abnormal data caused by airway leakage, the residual value of the airway pressure-time curve should change less during the period of the monitoring time, that is, the distance between the residual points is small; while for abnormal data caused by airway obstruction, the residual value of the airway pressure-time curve changes more during the period of the corresponding monitoring time.

[0123] Therefore, the airway pressure-time curve is first decomposed using the STL time series decomposition algorithm:

[0124]

[0125] in, Represents the raw airway pressure data, Represents the trend term of airway pressure data, represents the seasonal term of the airway pressure data, Residual term representing the airway pressure data.

[0126] Seasonal terms based on patient airway pressure data , divide the airway pressure-time curve into multiple breathing cycles. According to the abnormal data obtained in step 1, the corresponding breathing cycle is obtained. Calculate the average distance between the residual values ​​of adjacent airway pressure data in the breathing cycle corresponding to the abnormal data. The larger the average distance, the greater the fluctuation amplitude of the airway pressure in the breathing cycle corresponding to the abnormal data, that is, the more likely the abnormal data is caused by airway obstruction. Since the time interval of the monitoring data is consistent, only the difference of the residual terms is used here to represent the distance between the residual values.

[0127] In addition, airway leakage is caused by loose installation of mechanical equipment, so the abnormal tidal volume data caused by leakage is consistent, that is, on the pressure-time curve, the residual values ​​of abnormal data in different cycles are relatively close. Airway obstruction is caused by obstruction of the patient's airway, resulting in poor breathing. In order to achieve more adequate breathing, patients often need to adjust their breathing depth. Therefore, on the pressure-time curve, the maximum residual values ​​in abnormal data of different cycles vary greatly, corresponding to different maximum breathing depths of patients. Since the peak airway pressure is the airway pressure value at the moment when the patient fully inhales, it can better reflect the patient's breathing state. Therefore, here we obtain the peak value of the airway pressure in the respiratory cycle corresponding to each abnormal data, as well as the peak value of the airway pressure in the two adjacent respiratory cycles. The closer the peak value corresponding to the abnormal data is to the peak value of the adjacent respiratory cycle, the more likely it is that the tidal volume abnormality is caused by airway leakage.

[0128] Therefore, the possibility that the abnormal tidal volume data is caused by airway leakage is calculated based on the residual value of the abnormal data corresponding to the respiratory cycle on the airway pressure-time curve.

[0129]

[0130] in, Indicates i The abnormal data is the possibility of airway leakage. Indicates i The number of monitoring moments contained in the corresponding period of abnormal data, Indicates i The abnormal data corresponds to the j The residual value of airway pressure at each monitoring moment, Indicates i The difference between the residual values ​​of airway pressure at adjacent monitoring moments in the respiratory cycle corresponding to each abnormal data, that is, the distance between the residual values ​​of airway pressure at adjacent monitoring moments, Indicates i The average distance between the residual values ​​of airway pressure at adjacent monitoring moments in the respiratory cycle corresponding to the abnormal data is for The inverse of The smaller the time, the The larger the value is, the smaller the average distance of the residual values ​​is, and the more likely it is that the tidal volume data is abnormal due to airway leakage. Indicates i The abnormal data corresponds to the peak value of airway pressure during the respiratory cycle. Indicates i The peak value of airway pressure in the respiratory cycle before the abnormal data. Indicates i The peak value of airway pressure in the breathing cycle after the abnormal data. Indicates i The difference between the peak value of airway pressure in the respiratory cycle and the peak value of airway pressure in the adjacent respiratory cycle corresponding to the abnormal data, that is, the consistency with the peak value of airway pressure in the adjacent respiratory cycle, It means that the smaller the difference in the peak values ​​of airway pressure between adjacent respiratory cycles, that is, the higher the consistency, the more likely the abnormal data is caused by airway leakage.

[0131] when When the abnormal tidal volume data is detected, it is considered that the abnormal tidal volume data is caused by airway leakage, that is, the abnormal data needs to be corrected.

[0132] Step 2.3: Calculate the degree of abnormality of the abnormal tidal volume data caused by airway leak.

[0133] The more serious the airway leakage, the more unstable the gas transmission during the patient's breathing process, that is, the higher the degree of deviation of the tidal volume data from the original breathing pattern. In addition, the more serious the airway leakage, the more obvious the abnormal characteristics of the airway leakage it exhibits, that is, the easier it is to be identified as a leakage abnormality. Therefore, according to the results obtained in step a and step b, the higher the possibility that the tidal volume data is abnormal data, and the higher the possibility that it is caused by airway leakage, the higher the degree of abnormality of the abnormal data.

[0134]

[0135] in, Indicates the abnormality of the i-th tidal volume data, Indicates the possibility that the i-th data is abnormal data, Indicates the possibility that the i-th data is abnormal tidal volume caused by airway leakage.

[0136] Step 3: Correct the abnormal data according to the abnormal degree of the abnormal tidal volume data caused by the airway leakage.

[0137] Since airway leakage may cause part of the gas to not be detected during the transmission process, the higher the abnormality of the abnormal tidal volume data caused by airway leakage, the lower the monitored value is than the true value. Therefore, according to the abnormality of the abnormal tidal volume data, the abnormal tidal volume data caused by airway leakage obtained in step S2 is corrected.

[0138]

[0139] in, represents the true value of the tidal volume abnormality data after correction caused by the i-th airway leak, represents the abnormal tidal volume data monitoring value caused by the i-th airway leakage, Indicates the abnormal degree of abnormal tidal volume data caused by the i-th airway leak. It means that according to the degree of abnormality, the original tidal volume monitoring value is increased to correct the abnormally low tidal volume of the patient caused by airway leakage of the ventilator equipment, so as to obtain the real tidal volume data.

[0140] Thus, the abnormal tidal volume data caused by airway leakage is corrected, and more accurate and intelligent tidal volume data is provided when doctors diagnose patients based on their respiratory signs.

[0141] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent processing method for physiological data of patients with critical respiratory diseases, characterized in that: include: Collect lung gas volume data and airway pressure data of critically ill patients; Based on the changing relationship between the patient's lung gas volume data, airway pressure data and time, a volume-time curve and an airway pressure-time curve are constructed respectively; The volume-time curve is decomposed by STL time series to obtain the residual terms of the volume-time curve under abnormal fluctuation and without abnormal fluctuation respectively, and the possibility of each volume data being abnormal data is calculated based on the difference between the two, so as to determine whether the current volume data is abnormal data; If yes, proceed to the next step; Decompose the airway pressure-time curve based on the STL time series decomposition algorithm to obtain the residual value on the airway pressure-time curve; Based on the residual value of the acquired abnormal data corresponding to the respiratory cycle on the airway pressure-time curve, the possibility of abnormal tidal volume caused by airway leakage is obtained; Based on the possibility of abnormal data and the possibility of abnormal tidal volume caused by airway leakage, the abnormal degree of abnormal tidal volume data caused by airway leakage is obtained, and the abnormal data is corrected according to the abnormal degree of abnormal tidal volume data caused by airway leakage to obtain real tidal volume data; The method of obtaining the abnormal degree of the abnormal tidal volume data caused by airway leakage based on the possibility of abnormal data and the possibility of abnormal tidal volume caused by airway leakage is specifically as follows: The more serious the airway leakage is, the more unstable the gas transmission will be during the patient's breathing process, that is, the higher the degree of deviation of the tidal volume data from the original breathing pattern; the more serious the airway leakage is, the more obvious the abnormal characteristics of the airway leakage it exhibits, that is, the easier it is to be identified as a leakage abnormality; the higher the possibility that the tidal volume data is abnormal data, and the higher the possibility that it is caused by airway leakage, the higher the abnormal degree of the abnormal data; in, Indicates i The degree of abnormality of the abnormal tidal volume data caused by airway leakage, Indicates i The possibility that the volume data at a monitoring moment is abnormal data, Indicates i The abnormal data is the possibility of abnormal tidal volume caused by airway leakage; The abnormal data is corrected according to the abnormal degree of the abnormal tidal volume data caused by airway leakage to obtain the real tidal volume data, specifically: in, Indicates i The true value after correction of abnormal tidal volume data caused by airway leakage. Indicates i The abnormal tidal volume data monitoring value caused by airway leakage, Indicates i The degree of abnormality of the abnormal tidal volume data caused by airway leakage; It means that according to the degree of abnormality, the original tidal volume monitoring value is increased to correct the abnormally low tidal volume of the patient caused by airway leakage of the ventilator equipment, so as to obtain the real tidal volume data.

2. The intelligent processing method for physiological data of critically ill respiratory patients according to claim 1 is characterized in that: Based on the relationship between the patient's lung gas volume data, airway pressure data and time, a volume-time curve and an airway pressure-time curve are constructed respectively, specifically: When there is no abnormal airway leakage, the lung gas volume changes regularly and the volume-time curve is obtained; when airway leakage occurs, part of the gas leaks during the transmission process, and the actual gas delivered to the patient will be lower than the set value, and the stability of the delivery process will also be reduced, that is, the volume-time curve will show irregular fluctuations; Under normal conditions, the patient's airway pressure rises steadily during the inhalation phase and gradually decreases to 0 during the exhalation phase. An airway pressure-time curve is constructed based on the patient's inhalation and exhalation phase data, and the inhalation and exhalation phases show a certain symmetry.

3. The intelligent processing method for physiological data of critically ill respiratory patients according to claim 2 is characterized in that: The volume-time curve is decomposed by STL time series to obtain the residual terms of the volume-time curve under abnormal fluctuation and without abnormal fluctuation, specifically: Normal volume data changes periodically, while the irregular fluctuations of abnormal data will deviate from the original periodic law. Therefore, the volume-time curve is decomposed through STL time series to obtain the residual term of the curve: in, represents the original volume data, represents the trend term of volume data, represents the seasonal term of volume data, Residual term representing volume data; The residual term of the volume-time curve without abnormal fluctuations is a stable curve basically consistent with the central axis; the central axis is a straight line with y=0; when abnormal fluctuations occur, the volume residual term at the moment of fluctuation deviates from the central axis, and the greater the degree of deviation, the more obvious the fluctuation, that is, the higher the degree of abnormality.

4. The intelligent processing method for physiological data of critically ill respiratory patients according to claim 3 is characterized in that: The possibility of each volume data being abnormal data is calculated based on the difference between the two, specifically: in, Indicates i The possibility that the volume data at a monitoring moment is abnormal data, Indicates i The residual value of volume data at each monitoring moment; Represents the residual value without fluctuation, that is, the central axis of the residual curve, where ; Indicates i The deviation degree of the volume data residual at each monitoring moment relative to the central axis. The greater the deviation degree, the higher the possibility that the corresponding volume data is abnormal data; represents the normalization function; Determine whether the current volume data is abnormal data, specifically: Based on the relationship between the probability of the abnormal data and the preset threshold, if the probability is greater than the set threshold, the current volume data is considered to be abnormal data.

5. The intelligent processing method for physiological data of critically ill respiratory patients according to claim 4 is characterized in that: The airway pressure-time curve is decomposed based on the STL time series decomposition algorithm to obtain the residual value on the airway pressure-time curve, specifically: For abnormal data caused by airway leakage, the residual value of the airway pressure-time curve should change less, that is, the distance between the residual points is small; while for abnormal data caused by airway obstruction, the residual value of the airway pressure-time curve changes greatly in the period corresponding to the monitoring time; in, Represents the raw airway pressure data, Represents the trend term of airway pressure data, represents the seasonal term of the airway pressure data, Residual term representing the airway pressure data.

6. The intelligent processing method for physiological data of critically ill respiratory patients according to claim 5 is characterized in that: Before obtaining the possibility of airway leak causing abnormal tidal volume, it also includes: seasonal items based on the patient's airway pressure data , divide the airway pressure-time curve into multiple respiratory cycles; obtain the corresponding respiratory cycle according to the corresponding monitoring time of the abnormal data; calculate the average distance between the residual values ​​of adjacent airway pressure data in the respiratory cycle corresponding to the abnormal data, the larger the average distance, the larger the fluctuation amplitude of the airway pressure in the respiratory cycle corresponding to the abnormal data, that is, the more likely the abnormal data is caused by airway obstruction; since the time interval of the monitoring data is consistent, the difference of the residual items represents the distance between the residual values.

7. The intelligent processing method for physiological data of critically ill respiratory patients according to claim 6 is characterized in that: The possibility of abnormal tidal volume caused by airway leakage is obtained based on the residual value of the acquired abnormal data corresponding to the respiratory cycle on the airway pressure-time curve, specifically: in, Indicates i The abnormal data is the possibility of abnormal tidal volume caused by airway leakage. Indicates i The number of monitoring moments contained in the corresponding period of abnormal data, Indicates i The abnormal data corresponds to the j The residual value of airway pressure at each monitoring moment, Indicates i The difference between the residual values ​​of airway pressure at adjacent monitoring moments in the respiratory cycle corresponding to each abnormal data, that is, the distance between the residual values ​​of airway pressure at adjacent monitoring moments, Indicates i The average distance between the residual values ​​of airway pressure at adjacent monitoring moments in the respiratory cycle corresponding to the abnormal data is for The inverse of The smaller the time, the The larger the value is, the smaller the average distance of the residual values ​​is, and the more likely it is that the tidal volume data is abnormal due to airway leakage; Indicates the peak value of airway pressure in the respiratory cycle corresponding to the i-th abnormal data, Indicates i The peak value of airway pressure in the respiratory cycle before the abnormal data. Indicates i The peak value of airway pressure in the next respiratory cycle after abnormal data; Indicates i The difference between the peak value of airway pressure in the respiratory cycle and the peak value of airway pressure in the adjacent respiratory cycle corresponding to the abnormal data, that is, the consistency with the peak value of airway pressure in the adjacent respiratory cycle, It means that the smaller the difference in the peak values ​​of airway pressure between adjacent respiratory cycles, that is, the higher the consistency, the more likely the abnormal data is caused by airway leakage.

8. An intelligent processing system for physiological data of patients with critical respiratory diseases, characterized in that: The intelligent processing method for physiological data of a patient with a critical respiratory disease as claimed in claim 1 comprises: A collection module, which collects lung gas volume data and airway pressure data of patients with critical respiratory diseases; A construction module, wherein the construction module constructs a volume-time curve and an airway pressure-time curve based on the relationship between the patient's lung gas volume data, airway pressure data and time; A judgment module, wherein the judgment module decomposes the volume-time curve through the STL time series, obtains the residual terms of the volume-time curve under abnormal fluctuation and without abnormal fluctuation respectively, and calculates the possibility of each volume data being abnormal data based on the difference between the two, and then determines whether the current volume data is abnormal data; if so, proceeds to the next step; A decomposition module, wherein the decomposition module decomposes the airway pressure-time curve based on the STL time series decomposition algorithm to obtain a residual value on the airway pressure-time curve; An acquisition module, wherein the acquisition module acquires the possibility of abnormal tidal volume caused by airway leakage based on the residual value performance of the acquired abnormal data corresponding to the respiratory cycle on the airway pressure-time curve; A correction module, wherein the correction module obtains the abnormality degree of the abnormal tidal volume data caused by airway leakage based on the possibility of abnormal data and the possibility of abnormal tidal volume caused by airway leakage, and corrects the abnormal data according to the abnormality degree of the abnormal tidal volume data caused by airway leakage to obtain real tidal volume data.

Images