Automatic cough identification method and system for respiratory support equipment

Abstract

The invention discloses an automatic cough identification method for respiratory support equipment, which comprises the following steps of: setting an air leakage threshold, judging whether the air leakage at the current moment is less than the air leakage threshold, if so, executing the next step, otherwise, re-initializing; acquiring flow information of the current task, performing filtering processing to obtain filtering flow of the current task, and calculating a filtering flow difference value between the filtering flow of the current task and the filtering flow of the previous task; the filtering flow difference value and the pressure difference value are judged; if the filtering flow difference value is larger than the pressure difference, 1 is added to the counting value, and the next step is executed; and judging whether the flow waveform has a wave trough, if so, judging whether the counting value is greater than a counting threshold value, and judging whether the absolute value of the current task wave trough value is greater than the average value of the absolute values of the wave trough values of the first N respiratory cycles, and if so, marking the current timestamp as a cough time node. The technical problem that existing respiratory support equipment cannot automatically recognize the cough of a patient and perform early warning is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of respiratory support equipment, and in particular to a method and system for automatically identifying coughs of respiratory support equipment. Background Art

[0002] In modern clinical medicine, respiratory support equipment, as an effective means of artificially replacing the autonomous ventilation function, is widely used in respiratory failure caused by various reasons, anesthesia respiratory management during major surgery, respiratory support feeding and emergency resuscitation, and occupies a very important position in the field of modern medicine. Respiratory support equipment is a vital medical device that can prevent and treat respiratory failure, reduce complications, and save and prolong the life of patients. Respiratory support equipment is divided into two categories: invasive respiratory support equipment and respiratory support equipment. Invasive respiratory support equipment requires the establishment of artificial airways such as oral or nasal endotracheal intubation and tracheotomy tubes to ventilate patients through artificial airways; while respiratory support equipment usually uses masks to complete the function of mechanical ventilation. With the continuous development of medical device technology, users have higher and higher requirements for the intelligence of medical devices. When patients wear respiratory support equipment and cough, it may cause misjudgment of the triggering switch of the respiratory support equipment. In the dual-level pressure mode, it may cause discomfort to the patient, resulting in poor mechanical ventilation effect and failure to achieve the effect of clinical treatment. Therefore, it is urgent to propose a method and system for automatically identifying coughs in respiratory support equipment to solve the technical problem that existing respiratory support equipment cannot automatically identify patients' coughs and issue warnings. Summary of the invention

[0003] The main purpose of the present invention is to propose a method and system for automatically identifying coughs in respiratory support equipment, aiming to solve the technical problem that existing respiratory support equipment cannot automatically identify patient coughs and issue warnings.

[0004] To achieve the above object, the present invention provides a method for automatically identifying a cough of a respiratory support device, wherein the method for automatically identifying a cough of a respiratory support device comprises the following steps:

[0005] S1. Set the leakage threshold value, and determine whether the current leakage volume is less than the leakage threshold value. If so, execute step S2. Otherwise, re-initialize;

[0006] S2. Obtain the flow information of the current task and perform filtering processing to obtain the filtered flow of the current task, and calculate the filtered flow difference between the filtered flow of the current task and the filtered flow of the previous task;

[0007] S3, judging the size of the filtered flow difference and the pressure difference; if the filtered flow difference is greater than the pressure difference, the count value is increased by 1 and step S4 is executed; otherwise, the process returns to step S1;

[0008] S4. Determine whether a trough appears in the flow waveform. If so, determine whether the count value is greater than the count threshold, and determine whether the absolute value of the current task trough value is greater than the average of the absolute values ​​of the trough values ​​of the previous N respiratory cycles. If so, mark the current timestamp as a cough time node.

[0009] One of the preferred solutions, before step S1, further includes:

[0010] Set the task cycle and collect and process the data of the respiratory support equipment once every task cycle.

[0011] In one of the preferred solutions, the task period is 10 ms.

[0012] In one of the preferred solutions, the leakage threshold is 70 L / min.

[0013] One of the preferred solutions is that in step S2, the flow information obtained by the current task is filtered using FIR low-pass filtering and one-dimensional Kalman filtering methods.

[0014] In one of the preferred embodiments, the pressure difference is:

[0015] p=1.1*(inspiratory pressure-expiratory pressure)

[0016] Where p is the pressure difference of the respiratory support device.

[0017] In one of the preferred solutions, in step S4, it is determined whether the flow waveform has a trough, specifically:

[0018] If(Flow (NUM-2) -Flow (NUM-1) )*(Flow (NUM-1) -Flow (NUM) )<0, and Flow (NUM-1) -Flow (NUM) <0, it is determined that the flow waveform has a trough;

[0019] Among them, Flow( NUM-2) is the flow value at the time of task NUM-2, Flow (NUM) is the flow value at the time of the NUM task, Flow (NUM-1) It is the flow value at the time of NUM-1 task.

[0020] One of the preferred solutions is that in step S4, it is determined whether the absolute value of the current task trough value is greater than the average value of the absolute values ​​of the trough values ​​of the previous N respiratory cycles, specifically:

[0021] Determine whether the trough value at the current task moment is greater than the average of the absolute values ​​of the trough values ​​of the previous five respiratory cycles. If so, record and mark the current timestamp as the cough time node, count the number of coughs plus one, and set the count value to zero.

[0022] One of the preferred solutions, after step S4, further includes:

[0023] If coughing is detected, the first EPAP interval is maintained and an early warning is issued. If the first interval is reached, the switching between the inspiratory pressure and the expiratory pressure is restored to the normal setting.

[0024] A respiratory support device cough automatic recognition system, the respiratory support device cough automatic recognition system comprising a respiratory support device cough automatic recognition method as described above.

[0025] In the above technical solution of the present invention, the method for automatically identifying coughs in respiratory support equipment includes the following steps: S1, setting a leakage threshold, judging whether the leakage at the current moment is less than the leakage threshold, if so, executing step S2, otherwise, reinitializing; S2, obtaining the flow information of the current task and performing filtering processing to obtain the filtered flow of the current task, and calculating the filtered flow difference between the filtered flow of the current task and the filtered flow of the previous task; S3, judging the size of the filtered flow difference and the pressure difference; if the filtered flow difference is greater than the pressure difference, the count value is increased by 1, and step S4 is executed, otherwise, returning to step S1; S4, judging whether a trough appears in the flow waveform, if so, judging whether the count value is greater than the count threshold, and judging whether the absolute value of the trough value of the current task is greater than the average of the absolute values ​​of the trough values ​​of the previous N respiratory cycles, if so, marking the current timestamp as a cough time node. The present invention generates a cough when the patient breathes, and the cough will generate a large negative flow, and the generated flow changes at a fast rate. By judging the flow waveform of the respiratory support equipment, the technical problem that the existing respiratory support equipment cannot automatically identify the patient's cough and issue an early warning is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0027] Figure 1 This is a first schematic diagram of a method for automatically identifying coughs in a respiratory support device according to an embodiment of the present invention;

[0028] Figure 2This is a schematic diagram of flow fluctuation caused by a patient coughing according to an embodiment of the present invention.

[0029] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with the implementation methods and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. 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.

[0031] In addition, in the present invention, the descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0032] Furthermore, the technical solutions between the various embodiments of the present invention may be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in the field. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0033] See also Figure 1 According to one aspect of the present invention, the present invention provides a method for automatically identifying a cough of a respiratory support device, wherein the method for automatically identifying a cough of a respiratory support device comprises the following steps:

[0034] S1. Set the leakage threshold value, and determine whether the current leakage volume is less than the leakage threshold value. If so, execute step S2. Otherwise, re-initialize;

[0035] S2. Obtain the flow information of the current task and perform filtering processing to obtain the filtered flow of the current task, and calculate the filtered flow difference between the filtered flow of the current task and the filtered flow of the previous task;

[0036] S3, judging the size of the filtered flow difference and the pressure difference; if the filtered flow difference is greater than the pressure difference, the count value is increased by 1 and step S4 is executed; otherwise, the process returns to step S1;

[0037] S4. Determine whether a trough appears in the flow waveform. If so, determine whether the count value is greater than the count threshold, and determine whether the absolute value of the current task trough value is greater than the average of the absolute values ​​of the trough values ​​of the previous N respiratory cycles. If so, mark the current timestamp as a cough time node.

[0038] Specifically, in this embodiment, see Figure 2 , the horizontal axis is time (s), the vertical axis is flow (L / min), according to the analysis of user flow, when the patient coughs during breathing, the flow from the respiratory support device to the patient end is positive, the cough will produce a large negative flow, and the rate of change of the generated flow is fast, and the turning point of the cough identifies the number of times the cough occurs; before the step S1, it also includes: setting a task cycle, and collecting and processing data of the respiratory support device once every task cycle.

[0039] Specifically, in this embodiment, the task cycle is 10 ms, and data collection and data processing are performed every 10 ms, that is, 10 ms is one task cycle.

[0040] Specifically, in this embodiment, when the leakage of the respiratory support equipment is relatively large, it is easy to cause misjudgment of the event. Therefore, the range of the leakage must be limited in the implementation process. In the present invention, the leakage threshold is 70L / min. The present invention does not make a specific limitation and can be set according to needs. When the leakage is greater than the leakage threshold, no judgment is made, the relevant parameters are initialized, re-tested, and confirmation is made whether to end the treatment; if the leakage meets the conditions, the collected flow signal needs to be filtered, mainly to remove the noise in the flow signal.

[0041] Specifically, in this embodiment, in step S2, the flow information obtained by the current task is filtered using FIR low-pass filtering and one-dimensional Kalman filtering methods.

[0042] Specifically, in this embodiment, the pressure difference is:

[0043] p=1.1*(inspiratory pressure-expiratory pressure)

[0044] Where p is the pressure difference of the respiratory support device.

[0045] Specifically, in this embodiment, the step S4 determines whether the flow waveform has a trough, specifically: (NUM-2) -Flow (NUM-1) )*(Flow (NUM-1) -Flow (NUM) )<0,

[0046] And Flow( NUM-1) -Flow (NUM) <0, it is determined that the flow waveform has a trough;

[0047] Among them, Flow (NUM-2) is the flow value at the time of NUM-2 task, Flow (NUM)is the flow value at the time of the NUM task, Flow (NUM-1) It is the flow value at the time of NUM-1 task.

[0048] Specifically, in the present embodiment, the step S4 determines whether the absolute value of the current task trough value is greater than the average value of the absolute values ​​of the trough values ​​of the previous N respiratory cycles, specifically: determine whether the trough value at the current task moment is greater than the average value of the absolute values ​​of the trough values ​​of the previous five respiratory cycles; if the count value is greater than the count threshold, and the absolute value of the current trough value is greater than the average value of the absolute values ​​of the trough values ​​of the previous five respiratory cycles, then the current timestamp is recorded and marked as a cough time node, the number of coughs is counted plus one, and the count value is set to zero.

[0049] Specifically, in this embodiment, the counting threshold is 5, which is not specifically limited in the present invention and can be set as needed.

[0050] Specifically, in this embodiment, after step S4, it also includes: if a cough is detected, maintaining the first EPAP interval time and issuing an early warning, and if the first interval time is reached, restoring the normal setting of the switching of the inspiratory pressure and the expiratory pressure; by setting the first time interval and maintaining EPAP at the first time interval, the adverse effects caused by the false triggering of the respiratory support equipment can be prevented, while allowing the patient to recover properly.

[0051] Specifically, in this embodiment, the first time interval can be set to any time of 3s, 5s, and 10s, which is not specifically limited in the present invention and can be set according to needs.

[0052] According to another aspect of the present invention, the present invention provides a system for automatically identifying a cough of a respiratory support device, wherein the system for automatically identifying a cough of a respiratory support device comprises the method for automatically identifying a cough of a respiratory support device as described above.

[0053] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. All equivalent structural changes made using the contents of the present invention's specification and drawings, or directly / indirectly applied in other related technical fields, are included in the patent protection scope of the present invention.

Claims

1. A method for automatically identifying cough in respiratory support equipment, characterized in that: The following steps are involved: S1. Set the leakage threshold value, and determine whether the current leakage volume is less than the leakage threshold value. If so, execute step S2. Otherwise, re-initialize; S2. Obtain the flow information of the current task and perform filtering processing to obtain the filtered flow of the current task, and calculate the filtered flow difference between the filtered flow of the current task and the filtered flow of the previous task; S3, determining the magnitude of the filtered flow difference and the pressure difference; If the filtered flow difference is greater than the pressure difference, the count value is increased by 1 and step S4 is executed. Otherwise, the process returns to step S1. S4. Determine whether a trough appears in the flow waveform. If so, determine whether the count value is greater than the count threshold, and determine whether the absolute value of the current task trough value is greater than the average of the absolute values ​​of the trough values ​​of the previous N respiratory cycles. If so, mark the current timestamp as a cough time node.

2. A method for automatically identifying cough in respiratory support equipment according to claim 1, characterized in that: Before step S1, the method further includes: Set the task cycle and collect and process the data of the respiratory support equipment once every task cycle.

3. A method for automatically identifying cough in respiratory support equipment according to claim 2, characterized in that: The task period is 10 ms.

4. A method for automatically identifying cough in respiratory support equipment according to any one of claims 1 to 3, characterized in that: The leakage threshold is 70 L / min.

5. A method for automatically identifying cough in respiratory support equipment according to any one of claims 1 to 3, characterized in that: In step S2, the flow information obtained by the current task is filtered using FIR low-pass filtering and one-dimensional Kalman filtering methods.

6. A method for automatically identifying cough in respiratory support equipment according to any one of claims 1 to 3, characterized in that: The pressure difference is: p=1.1*(inspiratory pressure-expiratory pressure) Where p is the pressure difference of the respiratory support device.

7. A method for automatically identifying cough in respiratory support equipment according to any one of claims 1 to 3, characterized in that: In step S4, it is determined whether the flow waveform has a trough, specifically: If(Flow (NUM-2) -Flow (NUM-1) )*(Flow (NUM-1) -Flow (NUM) )<0, and Flow (NUM-1) -Flow (NUM) <0, it is determined that the flow waveform has a trough; Among them, Flow (NUM-2) is the flow value at the time of NUM-2 task, Flow (NUM) is the flow value at the time of the NUM task, Flow (NUM-1) It is the flow value at the time of NUM-1 task.

8. A method for automatically identifying cough in respiratory support equipment according to any one of claims 1 to 3, characterized in that: In step S4, it is determined whether the absolute value of the current task trough value is greater than the average value of the absolute values ​​of the trough values ​​of the previous N respiratory cycles, specifically: Determine whether the trough value at the current task moment is greater than the average of the absolute values ​​of the trough values ​​of the previous five respiratory cycles. If so, record and mark the current timestamp as the cough time node, count the number of coughs plus one, and set the count value to zero.

9. A method for automatically identifying cough in respiratory support equipment according to any one of claims 1 to 3, characterized in that: After step S4, the method further includes: If coughing is detected, the first EPAP interval is maintained and an early warning is issued. If the first interval is reached, the switching between the inspiratory pressure and the expiratory pressure is restored to the normal setting.

10. A respiratory support device cough automatic recognition system, characterized in that: The automatic cough recognition system for respiratory support equipment comprises an automatic cough recognition method for respiratory support equipment as described in any one of claims 1-9.

Images