A method, medium and terminal for identifying invalid triggering of respiratory support equipment

Abstract

The present invention is applicable to the technical field of medical equipment, and relates to a method, medium and terminal for identifying invalid triggers of respiratory support equipment, including: denoising the patient flow; judging whether the patient is in an exhalation state, if so, storing the patient flow during exhalation, and analyzing the patient flow during exhalation at the moment of inspiration; judging in real time whether the minimum patient flow needs to be updated from the first point of the patient's exhalation flow, if so, updating, and resetting the count CNT to 0, if not, performing a linear fitting on the N exhaled patient flow data, judging whether the linear coefficient of the fitting is less than 0, if so, adding 1 to the count CNT; after all patient flows are analyzed, judging whether the count CNT is greater than a preset threshold, if so, adding 1 to the invalid trigger asynchronous type. The present invention has a simple process, convenient operation, low resource occupation, and a wide range of application, and improves the invalid trigger identification efficiency of respiratory support equipment.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical equipment, and in particular relates to a method, medium and terminal for identifying invalid triggering of respiratory support equipment. Background Art

[0002] In mechanical ventilation, when the patient's breathing needs do not match the ventilator setting parameters, it is easy to cause human-machine asynchrony and other phenomena, resulting in poor mechanical ventilation effects and failure to achieve clinical treatment effects. Common types of human-machine asynchrony include double triggering, invalid triggering, premature switching, false triggering, etc., where invalid triggering events are defined as the user's inspiratory efforts, but the processed flow does not produce enough changes, or although changes occur, there are problems with the ventilator's judgment logic, resulting in the inability to judge the inhalation state, and the pressure cannot be switched from expiratory pressure to inspiratory pressure (such as Figure 2 ).

[0003] The patent with announcement number CN111563451B provides a method for identifying ineffective inspiratory efforts of mechanical ventilation based on multi-scale wavelet features, including the following steps: a. reading respiratory waveform data and preprocessing it. First, the exhalation start point is determined by finding the first zero-crossing point of the flow velocity waveform, and the point to the end of exhalation is considered to be the exhalation phase of the breath, and then the linear trend in the exhalation phase waveform is removed to eliminate the influence of data offset on the later calculation; b. performing N-layer decomposition of the exhalation phase flow velocity waveform by discrete wavelet transform; c. extracting features from the wavelet coefficients of each layer; d. selecting the best features using the sequence forward selection algorithm; e. classifying the best features using a support vector machine classifier, and then obtaining the classification result of human-machine asynchronous. The data processed by this patent is input into the support vector machine for training and prediction. Although the human-machine asynchronous is identified and classified, it needs to be connected to an independent server or other platform. Due to the limitation of hardware resources, the above scheme is difficult to implement in embedded software. There is also a method for identification based on respiratory cycle parameters in the prior art. This method requires the patient to maintain a basically consistent respiratory frequency, and the application scenario is limited.

[0004] Therefore, how to provide a method for identifying invalid triggers of respiratory support equipment that occupies less resources and has a wide range of applications, so as to improve the efficiency of identifying invalid triggers of respiratory support equipment, is an urgent problem to be solved by personnel in this technical field. Summary of the invention

[0005] In view of the deficiencies in the prior art, an object of the present invention is to provide a method for identifying invalid triggers of respiratory support equipment, so as to solve the problem that in the prior art, the efficiency of invalid trigger identification of respiratory support equipment is low due to limited resources and application scenarios; in addition, the present invention also provides an invalid trigger identification medium and terminal for respiratory support equipment.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for identifying invalid triggering of a respiratory support device, comprising the following steps:

[0008] S10, filter the patient flow and remove the noise; S20, determine whether the patient is in the exhalation state, if so, store the patient flow during exhalation, and execute step S30 to analyze the patient flow during exhalation at the moment of inspiration; S30, starting from the first point of the patient's exhalation flow, determine in real time whether the minimum patient flow needs to be updated, if so, update it, and reset the count CNT to 0, if not, perform a linear fitting on the N exhaled patient flow data, and determine whether the linear coefficient of the fitting is less than 0, if so, add 1 to the count CNT; S40, loop the steps S10 to S30 to make a judgment, and when all patient flow analyses are completed, determine whether the count CNT is greater than a preset threshold, if so, add 1 to the invalid trigger asynchronous type, if not, judge as normal or other.

[0009] Furthermore, in step S10, FIR low-pass filtering and one-dimensional Kalman filtering are used to remove noise.

[0010] Furthermore, in step S30, in a 100 Hz sampling system, the value of N is 20.

[0011] Furthermore, in step S30, the preset threshold is set according to the first 10 respiratory cycles, and the inspiratory drop time is set to be greater than one third of the total inspiratory time.

[0012] Furthermore, the number of cycles in step S40 is the difference between the number of flow rates and N.

[0013] In a second aspect, the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0014] In a third aspect, the present invention further provides an electronic terminal, comprising: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the method as described above.

[0015] Compared with the prior art, the respiratory support device invalid trigger identification method, medium and terminal provided by the present invention have at least the following beneficial effects:

[0016] In the prior art, when the patient's breathing needs do not match the ventilator setting parameters, it is easy to cause human-machine asynchrony and other phenomena, resulting in poor mechanical ventilation effects, failure to achieve clinical treatment effects, and low human-machine asynchrony recognition efficiency. The present invention has a simple process, convenient operation, low resource usage, and a wide range of applications. By analyzing relevant waveform features and using the coefficients of the sliding fitting equation to identify invalid triggers, the invalid trigger recognition efficiency of respiratory support equipment is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the scheme of the present invention, a brief introduction is given below to the figures required for use in the description of the embodiments. Obviously, the figures described below are some embodiments of the present invention. For ordinary technicians in this field, other figures can be obtained based on these figures without paying any creative work.

[0018] Figure 1 A flowchart of a method for identifying invalid triggering of a respiratory support device provided by an embodiment of the present invention;

[0019] Figure 2 This is the waveform diagram when the respiratory support device does not trigger an event. DETAILED DESCRIPTION

[0020] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. The preferred embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0022] The present invention provides a method for identifying invalid triggering of a respiratory support device, which is applied to the process of identifying human-machine asynchronous phenomena in the respiratory support device. The method for identifying invalid triggering of the respiratory support device includes the following steps:

[0023] S10, filter the patient flow and remove the noise; S20, determine whether the patient is in the exhalation state, if so, store the patient flow during exhalation, and execute step S30 to analyze the patient flow during exhalation at the moment of inspiration; S30, starting from the first point of the patient's exhalation flow, determine in real time whether the minimum patient flow needs to be updated, if so, update it, and reset the count CNT to 0, if not, perform a linear fitting on the N exhaled patient flow data, and determine whether the linear coefficient of the fitting is less than 0, if so, add 1 to the count CNT; S40, loop steps S10 to S30 to make a judgment, and when all patient flows are analyzed, determine whether the count CNT is greater than the preset threshold, if so, add 1 to the invalid trigger asynchronous type, if not, judge as normal or other.

[0024] The present invention has a simple process, convenient operation, small resource occupation, wide application range, and improves the invalid trigger recognition efficiency of respiratory support equipment.

[0025] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings.

[0026] The present invention provides an invalid trigger identification method for a respiratory support device, which is applied to the identification process of human-machine asynchronous phenomenon in the respiratory support device. After the normal switching of the untriggered event, there is a period of slow flow fluctuation in the exhalation stage, that is, the user himself generates inhalation, but the triggering condition cannot be met. Generally, the flow will slowly return to zero in the normal exhalation stage, and then enter the next trigger. In a normal exhalation cycle, the process of continuous flow decline generally does not occur. Therefore, the focus is on identifying the fluctuation characteristics of the exhalation stage, especially the process of patient flow decline. At the same time, it is also necessary to distinguish the fluctuations caused by other events. For example, early switching may also cause fluctuations under certain circumstances. The difficulty in identifying invalid triggers through waveform characteristics lies in how to distinguish the fluctuations caused by other abnormal situations (such as sudden changes in leakage) from the fluctuations caused by inhalation efforts in invalid triggering. Therefore, it is set to perform fluctuation identification only after the minimum value of the exhaled patient flow, and the span of the fluctuation needs to be determined based on the previous respiratory frequency, combined with Figure 1 and Figure 2 In this embodiment, the respiratory support device invalid trigger identification method includes the following steps:

[0027] S10, filtering the patient flow and removing noise;

[0028] Specifically, in this embodiment, noise above 5 Hz can be removed by using FIR low-pass filtering, one-dimensional Kalman filtering, etc.

[0029] S20, determining whether the patient is in an exhalation state, if so, storing the patient flow during exhalation, and executing step S30, analyzing the patient flow during exhalation at the inhalation moment (or in steps);

[0030] S30, starting from the first point of the patient's expiratory flow, determine in real time whether the minimum patient flow needs to be updated, if yes, update it and reset the count CNT to 0, if no, perform a linear term fitting on the N expiratory patient flow data, determine whether the linear term coefficient (i.e., slope) of the fitting is less than 0 (or a smaller value), if yes, add 1 to the count CNT;

[0031] Specifically, in this embodiment, the value of N needs to be adjusted according to the random noise of the system. Taking a 100 Hz sampling system as an example, if it is necessary to avoid misjudgment caused by noise within 5 Hz, the value of N should be more than 20 points. Of course, it cannot be too large, otherwise the fitting period will be too small and judgment cannot be made. In this embodiment, N is 20.

[0032] Furthermore, in this embodiment, if the minimum user flow needs to be updated, it is updated in real time, and the count CNT is reset to 0, and the first-order coefficient is counted again.

[0033] S40, looping the step S10 to the step S30 to make a judgment, after all the patient flow analysis is completed, judging whether the count CNT is greater than a preset threshold, if so, adding 1 to the invalid trigger asynchronous type, if not, judging as normal or others.

[0034] Specifically, in this embodiment, the number of cycles is the difference between the number of flow rates and N. The preset threshold can be set according to the first 10 respiratory cycles. Taking a 100 Hz sampling system as an example, if the average inspiratory time of the patient's first 10 respiratory cycles is 1.5 s, the inspiratory drop time can be set to be greater than one third of the total inspiratory time, that is, 50 cycles. The time of other respiratory cycles can be estimated in turn.

[0035] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, any one of the methods in the present embodiment is implemented.

[0036] An embodiment of the present invention further provides an electronic terminal, comprising: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any one of the methods in this embodiment.

[0037] The computer-readable storage medium in this embodiment can be understood by ordinary technicians in this field: all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0038] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used to communicate, and the processor and the transceiver are used to run computer programs so that the electronic terminal executes each step of the above method.

[0039] Compared with the prior art, the invalid trigger identification method, medium and terminal of the respiratory support device described in the above embodiments are easy to cause human-machine asynchrony and other phenomena when the patient's breathing demand does not match the ventilator setting parameters, resulting in poor mechanical ventilation effect, inability to achieve clinical treatment effect, and low human-machine asynchrony identification efficiency. The present invention has a simple process, convenient operation, low resource consumption, and a wide range of applications. By analyzing the relevant waveform characteristics and using the coefficients of the sliding fitting equation to identify invalid triggers, the invalid trigger identification efficiency of the respiratory support device is improved.

[0040] Obviously, the embodiments described above are only preferred embodiments of the present invention, rather than all embodiments. The preferred embodiments of the present invention are shown in the accompanying drawings, but they do not limit the patent scope of the present invention. The present invention can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive. Although the present invention has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific embodiments, or to perform equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of the present invention, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present invention.

Claims

1. A method for identifying invalid triggering of a respiratory support device, characterized in that: The following steps are involved: S10, filtering the patient flow and removing noise; S20, determining whether the patient is in an exhalation state, if so, storing the patient flow rate during exhalation, and executing step S30, analyzing the patient flow rate during exhalation at the moment of inspiration; S30, starting from the first point of the patient's expiratory flow, determine in real time whether the minimum patient flow needs to be updated, if so, update it and reset the count CNT to 0, if not, perform a linear fitting on the N expiratory patient flow data, and determine whether the linear coefficient of the fitting is less than 0, if so, add 1 to the count CNT; S40, looping the step S10 to the step S30 to make a judgment, after all the patient flow analysis is completed, judging whether the count CNT is greater than a preset threshold, if so, adding 1 to the invalid trigger asynchronous type, if not, judging as normal or others.

2. A method for identifying invalid triggering of a respiratory support device according to claim 1, characterized in that: In the step S10, FIR low-pass filtering and one-dimensional Kalman filtering are used to remove noise.

3. A method for identifying invalid triggering of a respiratory support device according to claim 1, characterized in that: In step S30, in a 100 Hz sampling system, the value of N is 20.

4. A method for identifying invalid triggering of a respiratory support device according to claim 1, characterized in that: In step S30, the preset threshold is set according to the first 10 respiratory cycles, and the inspiratory drop time is set to be greater than one third of the total inspiratory time.

5. A method for identifying invalid triggering of a respiratory support device according to claim 1, characterized in that: The number of cycles in step S40 is the difference between the number of flow rates and N.

6. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

7. An electronic terminal, characterized in that: include: Processor and memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the method according to any one of claims 1 to 5.

Images