A remote control method for an ECMO device

Abstract

The present invention proposes a remote control method for an ECMO device, which relates to the technical field of medical devices, and includes: collecting sensor data of the ECMO device in real time; encrypting the sensor data collected in real time and remotely transmitting it to a central data device for feature parameter extraction; obtaining the feature parameters extracted in the second step, and calculating the first feature parameter and the second feature parameter related to blood oxygen saturation by calculating the cross-correlation coefficient and the level coefficient; the central processor constructs a parameter relationship model according to the first feature parameter and the second feature parameter calculated in the third step, and calculates the new flow rate that the blood pump needs to adjust; based on the calculated new flow rate that the blood pump needs to adjust, using a mapping control algorithm to obtain the adjustment amount of the motor speed.

Description

Technical Field

[0001] The present invention proposes a remote control method for an ECMO device, which relates to the technical field of medical devices. Background Art

[0002] Modern ECMO devices are becoming more and more intelligent and automated, equipped with precise sensors and advanced control systems, and can monitor and adjust various parameters in real time, such as blood flow rate, oxygen concentration, temperature, etc. This provides a basis for remote control, enabling remote operators to accurately grasp the operating status of the device and conduct effective control.

[0003] With the wide coverage of high-speed wireless networks such as 4G and 5G and fiber optic networks, the data transmission speed and stability have been greatly improved, making it possible to transmit a large amount of data required for remote control of ECMO devices in real time. The development of the Internet of Things technology enables various devices to be interconnected through the network. The ECMO device can be used as a terminal device in the Internet of Things and is connected to the remote control platform through sensors and communication modules to realize real-time monitoring of the device status and transmission of remote control instructions.

[0004] Through remote control, the need for on-site operation by professionals can be reduced, and the labor cost and transportation cost can be lowered. At the same time, remote monitoring can also detect device failures in a timely manner and perform remote maintenance, reducing device downtime, improving device utilization rate, and further reducing medical costs. The remote control technology helps to integrate the ECMO device resources within the region, realizing centralized management and allocation of the devices. According to the needs of patients, the device can be remotely dispatched to different medical institutions, improving the use efficiency of the device and optimizing the allocation of medical resources. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention proposes a remote control method for an ECMO device, which includes the following steps:

[0006] Step 1: Real-time collect the sensor data of the ECMO device;

[0007] Step 2: Encrypt the real-time collected sensor data and remotely transmit it to the central data unit for feature parameter extraction;

[0008] Step 3: Obtain the feature parameters extracted in Step 2, and calculate the first feature parameter and the second feature parameter related to blood oxygen saturation by calculating the cross-correlation coefficient and the level coefficient;

[0009] Step 4: The central processor constructs a parameter relationship model according to the first feature parameter and the second feature parameter calculated in Step 3, and calculates the new flow rate that the blood pump needs to adjust;

[0010] Step Five: Based on the newly calculated flow rate that the blood pump needs to be adjusted, use the mapping control algorithm to obtain the adjustment amount of the motor speed.

[0011] In the preferred embodiment, in Step Three, obtain the characteristic parameters extracted in Step Two. Let the I-th characteristic parameter to be calculated in the t time period be T I (t), the blood oxygen saturation signal be V(t), and their discrete sequences be T I [i] and V[i] (i = 1, 2,..., N),

[0012] Calculate the means of the discrete sequences of the characteristic parameter and the blood oxygen saturation signal and

[0013]

[0014] The I-th characteristic parameter to be calculated is T I (t) and the cross-correlation coefficient C I with the blood oxygen saturation signal V(t) is calculated as follows:

[0015]

[0016] Select the characteristic parameter corresponding to the maximum cross-correlation coefficient C I as the first characteristic parameter related to blood oxygen saturation.

[0017] In the preferred embodiment, calculate the second characteristic parameter with the greatest correlation with the first characteristic parameter. Let the first characteristic parameter be X and the alternative characteristic parameter be Y. Sort the J measurement values of the first characteristic parameter X and the alternative characteristic parameter Y in ascending order respectively, and calculate the difference d j ,

[0018] d j = |X j - Y j |;

[0019] where X j , Y j are the measurement values of the first characteristic parameter and the alternative characteristic parameter at the position of the sequence number j respectively;

[0020] Calculate the level coefficient r s of the first characteristic parameter X and the alternative characteristic parameter Y according to the formula:

[0021]

[0022] where α is an adjustment parameter, and select the alternative characteristic parameter with the maximum r s as the second characteristic parameter.

[0023] In a preferred embodiment, in step four, taking pulse pressure as the first characteristic parameter and blood pump flow rate as the second characteristic parameter, the venous pressure P v , arterial pressure P a and the pulse pressure-flow relationship model between the blood pump flow rate Q is:

[0024] Q = k1 - k2P v - k3P a ;

[0025] where k1 is the basic flow coefficient, and k2 and k3 are the adjustment coefficients of the pulse pressure-flow relationship model;

[0026] When the venous pressure increases by ΔP v , the first blood pump flow rate adjustment amount ΔQ v is:

[0027] ΔQ v = - k2ΔP v

[0028] The first new blood pump flow rate Q n-v after adjustment is:

[0029] Q n-v = Q - ΔQ v = k1 - k2(P v + ΔP v ) - k3P a

[0030] When the arterial pressure increases by ΔP a , the second blood pump flow rate adjustment amount ΔQ a is:

[0031] ΔQ a = - k3ΔP a

[0032] The second new blood pump flow rate Q n-a after adjustment is:

[0033] Q n-a = Q - ΔQ a = k1 - k2P v - k3(P a + ΔP a )

[0034] Considering the simultaneous changes in venous pressure and arterial pressure, the total blood pump flow rate adjustment amount ΔQ is:

[0035] ΔQ = - k2ΔP v - k3ΔP a

[0036] The new blood pump flow rate Q that needs to be adjustedn is:

[0037] Q n = k1 - k2(P v + ΔP v ) - k3(P a + ΔP a ).

[0038] In a preferred embodiment, in the fifth step, let the blood pump flow deviation in the t period be Q'(t), the motor speed adjustment amount be Y, and Q1, Q2, and Q3 be the upper, middle, and lower boundary values of the deviation determined according to the actual situation:

[0039]

[0040] where a is the lower limit of the motor speed, b is the upper limit of the motor speed, and n represents the motor grade parameter.

[0041] In a preferred embodiment, in the fifth step, through the calculated new flow rate Q of the blood pump to be adjusted n , the valve opening rate L of the blood pump is calculated:

[0042]

[0043] where L is the valve opening rate, ρ is the blood flow density, q is the blood pump flow coefficient, P1 is the blood flow pressure value inside the blood pump pipeline, and P m is the blood flow pressure value at the outlet of the blood pump valve.

[0044] In a preferred embodiment, in the second step, the sending end of the ECMO device uses a hash algorithm to perform a hash operation on the real-time collected sensor data set, generating a hash value with a fixed length. The data set to be transmitted and the generated hash value are transmitted to the central processor through the network. The central processor uses the same hash algorithm as the sending end of the ECMO device to perform a re-hash operation on the received data set, generating a new hash value. If it is exactly the same as the hash value sent by the sending end of the ECMO device, it indicates that the data set has not been tampered with during the transmission process.

[0045] In a preferred embodiment, in the second step, the central data unit performs noise filtering on the received data set. For low-frequency blood flow pseudo-signals, an adaptive filtering algorithm is used. For medium-frequency noise generated by the operation of the device, a Butterworth band-stop filter is used to remove it; high-frequency electromagnetic interference is intercepted by a low-pass filter.

[0046] Compared with the prior art, the present invention has the following beneficial technical effects:

[0047] Precise Monitoring and Adjustment: By collecting sensor data of the ECMO device in real time, performing encrypted transmission, and extracting characteristic parameters, it is possible to comprehensively and timely grasp the operating status of the device and the physiological information of the patient. On this basis, the characteristic parameters most relevant to blood oxygen saturation are accurately calculated, and then the new flow rate that the blood pump needs to be adjusted and the adjustment amount of the motor speed are obtained, realizing precise control of the device, which helps to maintain the blood oxygen balance in the patient's body, reduce the risk of complications caused by problems such as insufficient oxygen supply or over-perfusion, and improve the safety and effectiveness of patient treatment.

[0048] Reducing Human Error: Traditional manual adjustment often relies on the experience and regular observation of medical staff, with certain subjectivity and lag. This method makes automatic adjustments based on real-time data and precise calculations, reducing errors in human judgment and operation, and ensuring that patients are always in a relatively ideal treatment state.

[0049] Optimizing Blood Pump Flow Control: This method calculates the new flow rate of the blood pump based on the characteristic parameters most relevant to blood oxygen saturation and the parameter relationship model, making the flow rate adjustment of the blood pump more scientific and reasonable, avoiding the inefficiency problems brought by traditional fixed flow rate models or blind adjustments, improving the accuracy and effectiveness of the blood pump's support for the patient's blood circulation, and enhancing the overall operating efficiency of the ECMO device.

[0050] Improving the Degree of Device Automation: Using the mapping control algorithm to obtain the adjustment amount of the motor speed, an automated process from data collection to final device parameter adjustment is realized, reducing the links of manual intervention, improving the response speed and degree of automation of the device, enabling the ECMO device to more quickly adapt to changes in the patient's physiological state, and enhancing the working efficiency of the device.

[0051] Encrypted Data Transmission: Encryption processing is carried out during the remote transmission of sensor data to the central data device, effectively preventing data from being stolen, tampered with, or leaked during transmission, ensuring the privacy of patients and the security of device operation data, and meeting the strict requirements of medical data security.

[0052] Decision-making Basis Based on Big Data Analysis: Through the collection of a large amount of sensor data, extraction of characteristic parameters, and data analysis means such as calculating cross-correlation coefficients, a more scientific and reliable decision-making basis is provided for the adjustment of the blood pump flow rate and motor speed, avoiding the limitations of single data points or empirical judgments, and improving the accuracy and reliability of control decisions. Description of the Drawings

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0054] Figure 1 Flowchart of the remote control method for the ECMO device of the present invention;

[0055] Figure 2 Schematic diagram of blood pump flow monitoring of the present invention;

[0056] Figure 3 Comparison chart of the controlled flow after the mapping control algorithm of the present invention and the flow control of actual operation. Detailed implementation manners

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0058] In the drawings of the specific embodiments of the present invention, to better and more clearly describe the working principles of the components in the system and show the connection relationships of the various parts of the device, only the relative positional relationships between the components are clearly distinguished, and it does not constitute a limitation on the signal transmission direction, connection sequence, and the sizes, dimensions, and shapes of the various parts of the structure within the component or structure.

[0059] As Figure 1 shown, it is a flowchart of the remote control method for the ECMO device of the present invention. The remote control method for the ECMO device includes the following steps:

[0060] Step 1: Real-time collect the sensor data of the ECMO device.

[0061] Sensors are selected to be highly accurate, highly sensitive, and capable of adapting to the complex environment of the extracorporeal membrane oxygenation (ECMO) pipeline. For example, for blood flow measurement, an ultrasonic Doppler flow sensor is used and installed at the position close to the inlet and outlet blood vessels of the extracorporeal membrane oxygenation to ensure accurate capture of blood flow velocity changes. The pressure sensor is selected as a semiconductor piezoresistive sensor and installed at key positions before and after the blood pump and inside the oxygenator to reflect the blood flow pressure situation in real time. The temperature sensor uses a thermistor sensor and is evenly distributed on the surface of the pipeline and the oxygenator, close to the blood flow area, to accurately obtain blood temperature information.

[0062] Preferably, calibrate each sensor. Test it in a simulated ECMO circulation device using a simulated blood sample with known standard values, and adjust the sensor parameters to ensure that its measurement error is controlled within a very small range.

[0063] When the ECMO device starts running, synchronously activate the sensor acquisition program. Set the data acquisition frequency. To ensure data real-time performance without overly increasing the system burden, the sensor data is acquired every 20 milliseconds. Preferably, the acquired data is immediately marked with a timestamp for subsequent sequential processing and analysis to ensure the timeliness and coherence of the data.

[0064] Step 2: Encrypt the sensor data acquired in real time and remotely transmit it to the central data unit for feature parameter extraction.

[0065] S21: Encrypt the sensor data acquired in real time and remotely transmit it to the central processor.

[0066] ECMO device sender operation:

[0067] Sensor data preparation: At the ECMO device end, collect the sensor data to be transmitted, including key data such as vital sign data and device operation parameters, and organize these key data into a complete data set.

[0068] Select a hash algorithm: According to the data security requirements and system support situation, select a suitable hash algorithm, such as MD5, SHA-1, SHA-256, etc. Preferably, use SHA-256 as the hash algorithm, which has high security.

[0069] Generate a hash value: Use the selected hash algorithm to perform a hash operation on the complete data set to generate a hash value with a fixed length. This hash value is the unique identifier of the data and represents the security features of the data in the complete data set.

[0070] Transmit the data set and the hash value: Transmit the data set to be transmitted and the generated hash value to the central processor through the network. Preferably, add the hash value as a part of the data set to the data packet, or specifically set a field in the data transmission protocol to transmit the hash value.

[0071] Central processor operation:

[0072] The central processor receives the data set and the hash value. After receiving the data set and the hash value transmitted from the ECMO device sender end, the central processor separates them and obtains the received data set and the hash value respectively.

[0073] Re - hashing operation: Use the same hashing algorithm as the sending end of the ECMO device to perform a re - hashing operation on the received data set, generating a new hash value.

[0074] Compare hash values: Compare the hash value regenerated by the central processing unit with the hash value sent by the sending end of the ECMO device. If the two hash values are exactly the same, it indicates that the data set has not been tampered with during transmission, and the data set is complete and reliable, and subsequent processing and control calculations can be performed.

[0075] S22. The central data unit performs signal filtering, enhancement, and feature signal extraction on the data.

[0076] Use the Fast Fourier Transform (FFT) algorithm to perform spectral analysis on the collected original signal, and identify noise components such as pseudo - signals (irregular low - frequency fluctuations) caused by equipment operation, electromagnetic interference, and the instability of blood flow itself. For different frequency - band noises, corresponding filtering methods are used for noise filtering. For low - frequency blood - flow pseudo - signals, an adaptive filtering algorithm is used to dynamically adjust the filter parameters according to the real - time blood - flow characteristics; for medium - frequency noise generated by equipment operation, a Butterworth band - stop filter is used to accurately remove it; high - frequency electromagnetic interference is intercepted by a low - pass filter. After filtering, the signal is subjected to residual analysis to ensure that the noise residue is lower than the set threshold, such as less than 5% of the total signal strength.

[0077] Perform multi - scale decomposition on the filtered signal through wavelet transform to amplify weak but key feature signals, such as the subtle fluctuations of the pressure signal caused by small changes in blood flow. Among the decomposed multi - scale components, extract feature parameters potentially associated with blood oxygen saturation, such as pulse - pressure signal, blood - pump flow signal, temperature signal, blood - flow velocity, etc., to prepare a sufficient and high - quality data feature set for subsequent modeling.

[0078] Step three: Obtain the feature parameters extracted in step two, and calculate the first feature parameter and the second feature parameter related to blood oxygen saturation by calculating the cross - correlation coefficient and the level coefficient.

[0079] Obtain the feature parameters extracted in step two. Let the I - th feature parameter to be calculated be T I (t), the blood oxygen saturation signal is V(t), and their discrete sequences are T I [i] and V[i] (i = 1, 2, …, N), where N is the number of discretizations.

[0080] First, calculate the means of T I [i] and V[i]:

[0081]

[0082] The I - th feature parameter to be calculated is T I(t) and the cross - correlation coefficient C of the blood oxygen saturation signal V(t) I The calculation formula is:

[0083]

[0084] Select the cross - correlation coefficient C I The corresponding characteristic parameter when it is the largest is used as the first characteristic parameter related to blood oxygen saturation.

[0085] Calculate the second characteristic parameter with the largest correlation with the first characteristic parameter. Let the first characteristic parameter be X and the alternative characteristic parameter be Y. The J - th measured values of the first characteristic parameter X and the alternative characteristic parameter Y are sorted in ascending order respectively to obtain the corresponding sorting serial numbers j, and then paired. Calculate the difference d of each pair of measured values at the serial number j j :

[0086] d j =|X j -Y j |;

[0087] Among them, X j and Y j are respectively the measured value of the first characteristic parameter and the measured value of the alternative characteristic parameter at the position of the serial number j.

[0088] Calculate the level coefficient r of the first characteristic parameter X and the alternative characteristic parameter Y according to the formula s :

[0089]

[0090] Among them, α is an adjustment parameter. When r s is greater than the threshold, it indicates that there is a strong correlation between the first characteristic parameter X and the alternative characteristic parameter Y.

[0091] Select the alternative characteristic parameter with the largest level coefficient r s as the second characteristic parameter.

[0092] Step 4: The central processing unit constructs a parameter relationship model according to the first characteristic parameter and the second characteristic parameter calculated in Step 3, and calculates the new flow rate that the blood pump needs to adjust.

[0093] In this embodiment, taking the pulse pressure as the first characteristic parameter and the blood pump flow rate as the second characteristic parameter as an example for illustration.

[0094] S31: Construct a pulse pressure - flow rate relationship model.

[0095] The venous pressure P v and the arterial pressure P a The pulse pressure - flow rate relationship model between and the blood pump flow rate Q is expressed as:

[0096] Q = k1 - k2P v - k3P a ;

[0097] Where k1 is the basic flow coefficient, which depends on factors such as the patient's basic physiological needs and the initial settings of the ECMO device; k2 and k3 are the adjustment coefficients of the pulse pressure-flow relationship model, which are determined by fitting experimental data or based on clinical experience.

[0098] S32: Blood pump flow adjustment calculation

[0099] When the venous pressure increases by ΔP v To maintain an appropriate flow rate, the first blood pump flow adjustment amount ΔQ v is calculated according to the following formula:

[0100] ΔQ v = - k2ΔP v

[0101] The adjusted first new blood pump flow Q n-v is:

[0102] Q n-v = Q - ΔQ v = k1 - k2(P v + ΔP v ) - k3P a

[0103] Similarly, when the arterial pressure increases by ΔP a the second blood pump flow adjustment amount ΔQ a is:

[0104] ΔQ a = - k3ΔP a

[0105] The adjusted second new blood pump flow Q n-a is:

[0106] Q n-a = Q - ΔQ a = k1 - k2P v - k3(P a + ΔP a )

[0107] Considering the simultaneous changes in venous pressure and arterial pressure, the total flow adjustment amount ΔQ is:

[0108] ΔQ = - k2ΔP v - k3ΔP a

[0109] The new blood pump flow Q that needs to be adjusted n is:

[0110] Q n = k1 - k2(P v + ΔP v ) - k3(P a + ΔP a )。

[0111] As shown Figure 2 in the figure, the blood pump flow is monitored. Once an increase in venous pressure is detected, it means that the blood return is blocked, and then the flow of the roller blood pump needs to be reduced to prevent venous congestion; if the arterial pressure increases, it indicates an increase in perfusion resistance, and the blood pump flow also needs to be appropriately reduced to avoid damage to blood vessels and organs caused by excessive pressure.

[0112] Step Five: Using the calculated new flow rate that the blood pump needs to adjust, and by means of the mapping control algorithm, obtain the motor speed adjustment amount.

[0113] The central processor continuously compares the current actual flow rate (fed back by the flow monitoring module built in the blood pump and also accessed through the analog input port to the processor) with the new flow rate. If there is a deviation, with the help of the mapping control algorithm, quickly calculate the compensation amount and drive the blood pump to adjust. For example, if the actual flow rate is low, immediately increase the motor power to increase the roller speed until the actual flow rate stabilizes near the target value, with the error controlled within ±0.1 L / min, achieving high-precision constant flow perfusion.

[0114] The mapping control algorithm specifically includes the following calculation steps:

[0115] Let the flow deviation in the t time period be Q′(t), and the motor speed adjustment amount be Y; Q1, Q2, Q3 are the upper, middle, and lower boundary values of the deviation determined according to the actual situation:

[0116]

[0117] Among them, a is the lower limit of the motor speed, b is the upper limit of the motor speed, and n represents the motor grade parameter.

[0118] The mapping control algorithm has good adaptability to the nonlinearity and uncertainty of the system. Since in the ECMO system, the relationship between the flow rate and various physiological parameters and equipment characteristics is complex and may change over time, the mapping control algorithm can handle this situation well.

[0119] In the actual application process, in some experimental ECMO flow control studies, the mapping control algorithm is used to cope with the different flow rate requirements of patients in different physiological states (such as blood pressure fluctuations, changes in blood viscosity, etc.). By continuously optimizing the upper, middle, and lower boundary values of the deviation, stable flow control can be achieved to a certain extent, reducing the flow control error caused by individual differences and complex physiological changes.

[0120] Embodiment 2

[0121] The hydraulic performance of the blood pump is also affected by the valve opening rate. Increasing the number of blades can improve the pressure supply capacity of the blood pump. However, when the number of blades is too large, it may increase the flow resistance of the fluid, resulting in a decrease in the efficiency of the blood pump. Therefore, the adjustment of the valve opening rate needs to balance the flow rate and efficiency to achieve the best hydraulic performance. The change of the valve opening rate will also affect the hemodynamics inside the blood pump, including the flow velocity distribution, pressure distribution, etc. These factors jointly determine the performance and safety of the blood pump

[0122] Therefore, in this embodiment, the control of the valve opening rate is mainly considered. In step five of Embodiment 1, based on the newly calculated flow rate Q that the blood pump needs to adjust n , the valve opening rate of the blood pump is calculated. The valve opening rate L of the blood pump can be specifically expressed by the following formula:

[0123]

[0124] where L is the valve opening rate, ρ is the blood flow density, q is the blood pump flow coefficient, P1 is the blood flow pressure value inside the blood pump pipeline, and P m is the blood flow pressure value at the outlet of the blood pump valve.

[0125] In a preferred embodiment, to avoid too high or too low pressure at the outlet of the blood pump, the adjustment of the valve opening rate should be carried out as slowly as possible. Slow adjustment can make the blood flow change gradually, reducing the generation of pressure waves and the possibility of pressure mutations. For example, the method of gradually increasing or decreasing the valve opening can be adopted. After each adjustment, wait for a period of time to observe the change of the pressure in the pipeline, and ensure that the pressure is stable within the safe range before proceeding to the next adjustment.

[0126] During the process of adjusting the valve opening rate, it is necessary to monitor the pressure at key positions in the pipeline in real time. The real-time acquisition of pressure data can be achieved by installing pressure sensors. According to the pressure monitoring data, a feedback mechanism is established. If the pressure approaches the alarm value, stop or reverse the adjustment of the valve opening rate in time to prevent the pressure from being too high or too low.

[0127] As Figure 3 shown, the comparison chart of the controlled flow rate and the actually operated flow rate control after adopting the mapping control algorithm of this embodiment. As the number of feedback samples increases, the calculated flow rate belongs to the flow rate data that matches the actual operation.

[0128] In one embodiment, a computer device is also provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0129] In one embodiment, a computer-readable storage medium is provided, storing a computer program which, when executed by a processor, implements the steps in the above method embodiments.

[0130] In one embodiment, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to execute the steps in the above method embodiments.

[0131] Those skilled in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the above method embodiments. Among them, any reference to a memory, a database, or other media used in the embodiments provided in the present application may include at least one of non-volatile and volatile memories. The databases involved in the embodiments provided in the present application may include at least one of relational databases and non-relational databases. Non-relational databases may include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in the present application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0132] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0133] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A remote control method for an ECMO device, characterized in that, It includes the following steps: Step 1: Collect the sensor data of the ECMO device in real time; Step 2: Encrypt the sensor data collected in real time and remotely transmit it to the central data processor for feature parameter extraction; Step 3: Obtain the feature parameters extracted in Step 2, and calculate the first feature parameter and the second feature parameter related to blood oxygen saturation by calculating the cross-correlation coefficient and the level coefficient; Step 4: The central processor constructs a parameter relationship model based on the first feature parameter and the second feature parameter calculated in Step 3, and calculates the new flow rate that the blood pump needs to adjust; Step 5: Based on the calculated new flow rate that the blood pump needs to adjust, use the mapping control algorithm to obtain the motor speed adjustment amount.

2. The remote control method of the ECMO device according to claim 1, characterized in that, In the third step, obtain the feature parameters extracted in the second step. Let the $I$-th feature parameter to be calculated at time period $t$ be $T$ I (t), the blood oxygen saturation signal is $V(t)$, and their discrete sequences are $T$ I [i] and $V[i]$, where $i = 1, 2, \ldots, N$. Calculate the mean value of the discrete sequence of the characteristic parameter and the blood oxygen saturation signal and The first characteristic parameter to be calculated is T I (t) and the cross-correlation coefficient C of the blood oxygen saturation signal V(t) I The calculation formula is: Select the cross-correlation coefficient C I The characteristic parameter corresponding to the maximum value is used as the first characteristic parameter related to blood oxygen saturation.

3. The remote control method of the ECMO device according to claim 2, characterized in that, Calculate the second characteristic parameter that has the greatest correlation with the first characteristic parameter. Let the first characteristic parameter be X and the alternative characteristic parameters be Y. Sort the J measured values of the first characteristic parameter being X and the alternative characteristic parameters being Y in ascending order respectively, and calculate the difference d of each pair of measured values with serial number j j , d j = |X j - Y j |; Among them, X j , Y j are respectively the measured value of the first characteristic parameter and the measured value of the alternative characteristic parameter at the position of serial number j; Calculate the level coefficient r of the first characteristic parameter X and the alternative characteristic parameter Y according to the formula s : where α is an adjustment parameter, and r s The largest alternative characteristic parameter is selected as the second characteristic parameter.

4. The remote control method of the ECMO device according to claim 1, characterized in that, In the fourth step, using the pulse pressure as the first characteristic parameter and the blood pump flow rate as the second characteristic parameter, the venous pressure P v , arterial pressure P a The pulse pressure-flow relationship model between and the blood pump flow rate Q is: Q = k1 - k2P v - k3P a ; Among them, k1 is the basic flow coefficient, and k2 and k3 are the adjustment coefficients of the pulse pressure-flow relationship model; When the venous pressure increases by ΔP v the first flow rate adjustment amount ΔQ of the blood pump v is: ΔQ v = -k2ΔP v The adjusted first new flow rate Q of the blood pump n-v is as follows: Q n-v = Q - ΔQ v = k1 - k2(P v + ΔP v ) - k3P a When the arterial pressure increases by ΔP a the second blood pump flow rate adjustment amount ΔQ a is: ΔQ a = -k3ΔP a The adjusted second new flow rate Q of the blood pump n-a is as follows: Q n-a = Q - ΔQ a = k1 - k2P v - k3(P a + ΔP a ) Considering the simultaneous changes in venous pressure and arterial pressure, the total flow adjustment amount ΔQ of the blood pump is: ΔQ = -k2ΔP v -k3ΔP a New flow rate Q to be adjusted for the blood pump n is: Q n = k1 - k2(P v + ΔP v ) - k3(P a + ΔP a )。 5. The remote control method of the ECMO device according to claim 3, characterized in that, In Step 5, let the blood pump flow deviation at time t be Q′(t), the motor speed adjustment amount be Y, and Q1, Q2, and Q3 be the upper, middle, and lower boundary values of the deviation determined according to the actual situation: Among them, a is the lower limit of the motor speed, b is the upper limit of the motor speed, and n represents the motor grade parameter.

6. The remote control method of the ECMO device according to claim 3, characterized in that, In the fifth step, according to the newly calculated flow rate Q that the blood pump needs to be adjusted n , the valve opening rate L of the blood pump is calculated as follows: Among them, L is the valve opening rate, ρ is the blood flow density, q is the blood pump flow coefficient, P1 is the blood flow pressure value inside the blood pump pipeline, and P m is the blood flow pressure value at the outlet of the blood pump valve.

7. The remote control method of the ECMO device according to claim 1, wherein, In Step 2, the sending end of the ECMO device uses the hash algorithm to perform a hash operation on the sensor data set collected in real time, generates a hash value with a fixed length, and transmits the data set to be transmitted and the generated hash value to the central processor through the network. The central processor uses the same hash algorithm as the sending end of the ECMO device to perform a second hash operation on the received data set, generates a new hash value. If it is exactly the same as the hash value sent by the sending end of the ECMO device, it means that the data set has not been tampered with during the transmission process.

8. The remote control method of the ECMO device according to claim 1, characterized in that, In Step 2, the central data processor filters the noise of the received data set. For low-frequency blood flow pseudo-signals, an adaptive filtering algorithm is used. For the intermediate-frequency noise generated by the operation of the device, a Butterworth band-stop filter is used to remove it; High-frequency electromagnetic interference is intercepted by a low-pass filter.

Images