Cardiopulmonary resuscitation pressure feedback fracture early warning method and device

Abstract

This invention relates to the field of cardiopulmonary resuscitation (CPR) equipment with monitoring, control, and adjustment capabilities. It provides a method and device for CPR pressure feedback fracture early warning. The early warning method includes continuously collecting the compression depth and pressure at each compression during CPR; generating compression depth-pressure curves for each compression based on the compression depth and pressure; analyzing whether the most recent compression depth-pressure curve is abnormal; if the most recent compression depth-pressure curve is abnormal, indicating a fracture risk, a fracture risk alarm is triggered. The device includes a controller, a drive mechanism, and a compression head assembly; after determining the compression depth and pressure at the start of CPR, the controller controls the drive mechanism to operate and drive the compression head assembly to perform CPR compressions on the patient; and a fracture risk alarm is triggered during CPR. This invention can accurately adapt to different patients and mitigate risks.

Description

Technical Field

[0001] This invention relates to the field of cardiopulmonary resuscitation (CPR) equipment with monitoring, control, and regulation capabilities, and particularly to a method and device for CPR pressure feedback fracture early warning. Background Technology

[0002] Cardiopulmonary resuscitation (CPR) is the most commonly used and effective treatment for cardiac arrest patients. Animal experiments and clinical trials have shown that the quality of CPR significantly impacts survival rates and is one of the reasons for the large variability in survival rates of cardiac arrest events within the same emergency medical services system and between different systems. Data from studies by Hoke and Chamberlain between 1960 and 1999 found that conventional CPR resulted in rib fractures in at least one-third of patients and sternal fractures in at least one-fifth. A joint analysis of CPR-related injuries by Miller et al. showed that rib fractures accounted for 31.2% (987 / 3162) of all injuries, and sternal fractures accounted for 15.1% (501 / 3311). In a recent analysis of 2148 cardiac arrest deaths in Slovenia between 2004 and 2013, Kralj et al. found that 86% of male patients had one or more CPR-related skeletal injuries, compared to 91% of female patients. Numerous rib and sternal fractures can cause pain, impair breathing, lead to bronchopneumonia, puncture blood vessels, and cause organ bleeding.

[0003] Existing related technical solutions, such as CN 111947819 A - A method, device and feedback system for acquiring data during cardiopulmonary resuscitation (CPR), are mainly used to detect whether the compression parameters of the CPR machine are correct. They adjust the compression parameters by monitoring the state of the CPR process to achieve higher quality CPR. However, this only provides adjustment signals under ideal working conditions. In actual CPR, when a patient suffers a fracture and the equipment continues to compress without taking any measures, it will cause pain and respiratory depression, and in severe cases, bronchopneumonia, punctured blood vessels, and organ bleeding, posing a life-threatening risk. Current technology lacks an emergency mechanism for fracture situations and fails to provide appropriate medical solutions for patients. Furthermore, due to differences in age, physical condition, and lifestyle, the density and fragility of the thoracic bones vary among patients, resulting in differences in the compressibility of the thoracic bones. Current CPR equipment does not accurately assess or address these differences. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a cardiopulmonary resuscitation pressure feedback fracture early warning method, comprising the following steps:

[0005] During cardiopulmonary resuscitation, the depth and pressure of each compression are continuously recorded.

[0006] Based on the compression depth and pressure of each compression, a compression depth-pressure curve is generated for each compression, and the recent compression depth-pressure curve is analyzed to determine if there are any anomalies.

[0007] If the recent compression depth-compression pressure curve shows an abnormality, it indicates a risk of fracture, and a fracture risk alarm will be triggered.

[0008] Preferably, the method for analyzing whether there are any anomalies in the recent compression depth-compression pressure curve is as follows:

[0009] Calculate the non-overlapping degree of the compression depth-compression pressure curves for each two adjacent compressions. By comparing the non-overlapping degree of the two most recent compressions with other non-overlapping degrees, determine whether there is any abnormality in the most recent compression depth-compression pressure curve.

[0010] Preferably, the method for determining whether there are any anomalies in the most recent compression depth-compression pressure curve by comparing the degree of non-overlap includes:

[0011] Based on the pressure depth-pressure curve of two adjacent presses, take the pressure of two presses with the same pressure depth on the two curves respectively to obtain two sets of pressure data.

[0012] The sum of the square roots of the pressure differences at the same pressing depth is used to obtain the degree of non-overlap.

[0013] The non-overlapping degree of the two most recent presses is compared with the average of the non-overlapping degrees of a predetermined number of recent presses. If the non-overlapping degree of the two most recent presses is greater than the average, it indicates that there is an abnormality; otherwise, there is no abnormality.

[0014] Preferably, the method for analyzing whether there are any anomalies in the most recent press depth-press pressure curve is as follows:

[0015] The pressure depth-pressure curve of the most recent press is smoothed to obtain a smooth curve;

[0016] Construct a pressure function with pressure depth as the independent variable based on the smooth curve;

[0017] The second derivative of the pressure function is calculated, and the pressure depth of the most recent press is substituted into the solution to obtain the second derivative value of the pressure corresponding to each pressure depth point.

[0018] Compare the second derivative of the pressure value corresponding to each pressure depth point with the average value of the second derivative of the pressure value. If there is a pressure depth point whose ratio to the average value of the second derivative of the pressure value exceeds the safety threshold, it indicates that the most recent pressure depth-pressure curve is abnormal; otherwise, there is no abnormality.

[0019] Preferably, in step S100, the initial pressing depth and pressing force are determined by the following method:

[0020] Obtain the patient's basic information and images of the thoracic skeleton;

[0021] Image preprocessing is performed on the thoracic skeleton image to obtain the preprocessed thoracic skeleton image;

[0022] Feature data is extracted from the preprocessed thoracic skeleton image, and the feature data is input into a pre-trained compression model to output the first compression depth for the patient's cardiopulmonary resuscitation.

[0023] The correction factor is determined based on the patient's basic information. The preset standard compression pressure is then corrected based on the correction factor to obtain the first compression pressure.

[0024] When performing the first compression of cardiopulmonary resuscitation on a patient, the first compression depth and the first compression force should be selected as the compression control reference, and the first parameter and its corresponding measured value should be used as the starting compression depth and compression force.

[0025] Preferably, the pre-training process of the pressing model is as follows:

[0026] A cardiopulmonary resuscitation (CPR) database was constructed by collecting thoracic skeleton images and CPR data from previous patients. The thoracic skeleton images of each patient were preprocessed, and feature data were extracted to form a training set. CPR data of corresponding patients were selected to construct a validation set.

[0027] A basic model of cardiopulmonary resuscitation (CPR) compressions was constructed. The basic model was trained using a training set and validated using a validation set to obtain the optimized parameters of the basic model.

[0028] The basic pressing model is optimized by adjusting the parameters to obtain the pressing model.

[0029] The present invention also provides a cardiopulmonary resuscitation device, including a controller, a drive mechanism, and a compression head assembly;

[0030] The controller includes a compression parameter determination module and a fracture warning module. The compression parameter determination module is used to determine the compression depth and pressure at the start of cardiopulmonary resuscitation (CPR) based on the patient's basic information and thoracic skeleton image. The fracture warning module is used to issue a fracture risk alarm during CPR. The controller is used to implement CPR control based on the compression depth and pressure.

[0031] The drive mechanism is used to operate under the control of the controller and drive the press head assembly to perform the pressing motion;

[0032] The compression head assembly is used to perform compression movements for cardiopulmonary resuscitation on a patient, driven by a drive mechanism.

[0033] Preferably, the drive mechanism includes a rotary motion component, a transmission component, and a linear motion component;

[0034] The transmission assembly includes a driving pulley and a driven pulley, which are connected by a drive mechanism.

[0035] The rotary motion component includes a motor, and a drive pulley is fixedly connected to the output shaft of the motor;

[0036] The linear motion assembly includes a lead screw and nut assembly and a pressing push rod. The lead screw and nut assembly includes a lead screw and a lead screw nut that is threaded onto the lead screw. The pressing push rod is mounted on the lead screw and nut. A driven pulley is mounted on the lead screw. A pressing head assembly is mounted on the bottom of the pressing push rod.

[0037] Preferably, the pressing parameter determination module includes:

[0038] The information acquisition submodule is used to acquire the patient's basic information and thoracic skeleton images;

[0039] The preprocessing submodule is used to preprocess the thoracic skeleton image to obtain a preprocessed thoracic skeleton image.

[0040] The initial compression depth determination submodule is used to extract feature data from the preprocessed thoracic skeleton image, input the feature data into the pre-trained compression model, and output the first compression depth for the patient's cardiopulmonary resuscitation.

[0041] The compression pressure correction submodule is used to determine the correction coefficient based on the patient's basic information, and to correct the preset standard compression pressure according to the correction coefficient to obtain the first compression pressure;

[0042] The compression parameter determination submodule is used to select the first compression depth and the first compression force as the compression control reference when performing the first compression on the patient during the first compression of cardiopulmonary resuscitation, and to use the first parameter and the actual measured value of the other parameter as the starting compression depth and compression force.

[0043] Preferably, the fracture early warning module includes:

[0044] The compression parameter acquisition submodule includes a pressure sensor installed at the contact point between the compression head assembly and the patient's chest. The pressure sensor is used to continuously acquire the compression pressure for each compression during cardiopulmonary resuscitation. The compression parameter acquisition submodule also records the compression depth corresponding to the compression pressure. The compression depth is the compression stroke that the compression head assembly continues to travel downwards after contacting the patient.

[0045] The analysis submodule is used to generate a pressure depth-pressure curve for each press based on the pressure depth and pressure of each press, and to analyze whether there are any anomalies in the most recent pressure depth-pressure curve;

[0046] The risk warning submodule is used to issue a fracture risk alarm when there is an abnormality in the recent compression depth-compression pressure curve, indicating a risk of fracture.

[0047] The cardiopulmonary resuscitation (CPR) pressure feedback fracture early warning method and CPR device of the present invention continuously collects the compression depth and pressure of each compression, generating compression depth-pressure curves for each compression. Using the most recent compression depth-pressure curve as the primary analysis object, the method analyzes and evaluates whether there are any abnormalities. If an abnormality is found, indicating a fracture risk, a fracture risk alarm is triggered. In actual CPR, when the patient is at risk of fracture, the invention can promptly issue a warning, reminding medical personnel to take appropriate measures such as adjusting compression parameters (compression depth and pressure). This ensures that continuous compression does not cause fractures, patient pain, respiratory depression, bronchopneumonia, punctured blood vessels, or organ bleeding, thus avoiding life-threatening situations. Furthermore, it can accurately adapt to patients with different ages, physical conditions, and lifestyles, matching the compression parameters (compression depth and pressure) with the density, fragility, and pressure resistance of the patient's thoracic bones, improving the precision of compression parameter control and further mitigating risks.

[0048] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0049] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0050] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0051] Figure 1 This is a flowchart of a cardiopulmonary resuscitation pressure feedback fracture early warning method according to an embodiment of the present invention;

[0052] Figure 2 This is a flowchart illustrating whether there are any abnormalities in the compression depth-compression pressure curve of the most recent compression, as used in an embodiment of the cardiopulmonary resuscitation pressure feedback fracture early warning method of the present invention.

[0053] Figure 3 This is a schematic diagram showing the connection between the controller and the drive mechanism of a cardiopulmonary resuscitation device according to an embodiment of the present invention;

[0054] Figure 4 This is a frontal view of the initial state of the cardiopulmonary resuscitation device of the present invention used in a cardiopulmonary resuscitation embodiment;

[0055] Figure 5 This is a front view of the cardiopulmonary resuscitation device of the present invention in the compression state during a cardiopulmonary resuscitation embodiment.

[0056] Figure 6 This is a three-dimensional schematic diagram of the drive mechanism and compression head assembly used in an embodiment of the cardiopulmonary resuscitation device of the present invention.

[0057] Figure 7 Cross-sectional view of the drive mechanism and compression head assembly used in an embodiment of the cardiopulmonary resuscitation device of the present invention;

[0058] Figure 8 An exploded view of the drive mechanism and compression head assembly used in an embodiment of the cardiopulmonary resuscitation device of the present invention;

[0059] Figure 9 This is a schematic diagram showing the connection between the second drive mechanism and the compression head assembly used in an embodiment of the cardiopulmonary resuscitation device of the present invention;

[0060] Figure 10 This is a schematic diagram showing the connection between the third drive mechanism and the compression head assembly used in an embodiment of the cardiopulmonary resuscitation device of the present invention;

[0061] Figure 11 This is a schematic diagram of a curve with high overlap obtained by the non-overlapping degree analysis method of the compression depth-compression pressure curve in the embodiment of the cardiopulmonary resuscitation pressure feedback fracture early warning method of the present invention.

[0062] Figure 12 This is a schematic diagram of the non-overlap curve obtained by the non-overlap analysis method of the compression depth-compression pressure curve in the embodiment of the cardiopulmonary resuscitation pressure feedback fracture early warning method of the present invention.

[0063] Figure 13 This is a schematic diagram of the curve with no fracture risk and its second derivative line obtained by the second derivative analysis of the compression depth-compression pressure curve in an embodiment of the cardiopulmonary resuscitation pressure feedback fracture early warning method of the present invention.

[0064] Figure 14 This is a schematic diagram of the second derivative of the compression depth-compression pressure curve obtained by the second derivative analysis method of the cardiopulmonary resuscitation pressure feedback fracture early warning method of the present invention, which is used in an embodiment of the present invention.

[0065] Figure 15 This is a schematic diagram of the curve and its second derivative line of the type II fracture risk obtained by the second derivative analysis method of the compression depth-compression pressure curve used in the embodiment of the cardiopulmonary resuscitation pressure feedback fracture early warning method of the present invention.

[0066] Figure 16 The flowchart illustrates an application example of the cardiopulmonary resuscitation pressure feedback fracture early warning method of the present invention, which combines curve non-overlap analysis and second derivative analysis. Detailed Implementation

[0067] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0068] like Figure 1 As shown, this embodiment of the invention provides a method for early warning of fractures under cardiopulmonary resuscitation pressure feedback, including the following steps:

[0069] S100: During cardiopulmonary resuscitation, continuously collect the compression depth and compression force for each compression;

[0070] S200: Based on the compression depth and pressure of each compression, generate a compression depth-pressure curve for each compression and analyze whether there are any anomalies in the most recent compression depth-pressure curve;

[0071] S300: If the recent compression depth-compression pressure curve is abnormal, it indicates a risk of fracture, and a fracture risk alarm will be triggered.

[0072] The working principle and beneficial effects of the above technical solution are as follows: This solution continuously collects the compression depth and pressure during each compression, generating compression depth-pressure curves for each compression. The most recent compression depth-pressure curve is used as the primary analysis object. Analysis of this curve evaluates for any abnormalities. If an abnormality is found, indicating a fracture risk, a fracture risk alarm is triggered. In actual cardiopulmonary resuscitation (CPR), this solution can promptly issue warnings when a patient is at risk of fracture, reminding medical personnel to adjust compression parameters (compression depth and pressure) and take corresponding measures. This ensures that continuous compressions do not cause fractures, patient pain, respiratory depression, bronchopneumonia, puncture of blood vessels, or organ bleeding, thus avoiding life-threatening situations. Furthermore, it can accurately adapt to patients with different ages, physical conditions, and lifestyles, ensuring that the compression parameters (compression depth and pressure) match the density, fragility, and pressure resistance of the patient's thoracic bones, improving the precision of compression parameter control and further mitigating risks.

[0073] In one embodiment, in step S200, the method for analyzing whether there are any anomalies in the recent compression depth-compression pressure curve is as follows:

[0074] Calculate the non-overlapping degree of the compression depth-compression pressure curves for each two adjacent compressions, compare the non-overlapping degree of the two most recent compressions with the other non-overlapping degrees, and determine whether there is any abnormality in the most recent compression depth-compression pressure curve.

[0075] The working principle and beneficial effects of the above technical solution are as follows: This solution calculates the degree of non-overlap between adjacent curves, compares the non-overlap between the two most recent curves with other non-overlapping values, and determines whether there is an anomaly in the most recent compression depth-compression pressure curve. This allows for a quantitative analysis of the fracture risk during compression, avoids the influence of subjective factors, and improves the reliability of the analysis results. Figure 11 The curves from the two presses shown have a high degree of overlap, and the upper right portion of the curves also overlaps, indicating that there are no abnormalities. Figure 12 The curves for two compressions no longer overlap after reaching a certain compression depth, indicating a significant difference in the upper right portion of the curves, suggesting an abnormal situation. Additionally, during compressions, important CPR indicators such as blood saturation and end-tidal CO2 can be monitored simultaneously. This allows for early warning if monitoring results indicate a critical situation, and also enables the optimization and adjustment of CPR compression parameters (compression depth and pressure) based on the monitoring results.

[0076] In one embodiment, step S200 includes:

[0077] Based on the compression depth-compression pressure curve of two consecutive compressions, multiple compression pressures corresponding to the same compression depth are taken from both curves, resulting in two sets of compression pressure data, denoted as P. m-1 [n] and P m [n], where n represents the number of digits representing the pressure of the data set, and m-1 and m represent the sequence number of the number of presses, respectively;

[0078] Calculate the sum of the square roots of the pressure differences at the same pressing depth to obtain the degree of non-overlap. Let D[m] represent the curve change of the m-th pressing compared to the previous pressing (i.e. the m-1-th pressing).

[0079] The non-overlapping degree of the two most recent presses (e.g., D[m]) is compared with the average of a predetermined number of recent non-overlapping degrees (e.g., the five most recent presses: D[m], D[m-1], D[m-2], D[m-3], and D[m-4]) (denoted as E[k], where k represents the predetermined number of recent non-overlapping degrees). If the non-overlapping degree of the two most recent presses is greater than the average, i.e., D[m] > E[k], then there is an anomaly; otherwise, there is no anomaly.

[0080] The working principle and beneficial effects of the above technical solution are as follows: This solution provides a specific method for calculating the non-overlapping degree of adjacent curves, and further provides a specific method for comparing the non-overlapping degree of the two most recent curves with other non-overlapping degrees. This can accurately determine whether there is an abnormality, quantify the fracture risk during compression, avoid the influence of subjective factors, and improve the reliability of the analysis results. The number of recent non-overlapping degrees participating in the comparison can be set, which can control the amount of calculation and accelerate the calculation. On the other hand, using the recent non-overlapping degree obtained from recent compression data can improve the accuracy of the judgment.

[0081] In one embodiment, such as Figure 2 As shown, in step S200, the method for analyzing whether there are any anomalies in the most recent press depth-press pressure curve is as follows:

[0082] S210: Smooth the pressure depth-pressure curve of the most recent press to obtain a smooth curve;

[0083] S220: Construct a pressure function with pressure depth as the independent variable based on the smooth curve;

[0084] S230: Take the second derivative of the pressure function and substitute the pressure depth collected in the most recent press into the solution to obtain the second derivative value of the pressure corresponding to each pressure depth point;

[0085] S240: Compare the second derivative of the pressure value corresponding to each pressure depth point with the average value of the second derivative of the pressure value. If there is a pressure depth point whose ratio to the average value of the second derivative of the pressure value exceeds the safety threshold, it indicates that the most recent pressure depth-pressure curve is abnormal; otherwise, there is no abnormality.

[0086] The working principle and beneficial effects of the above technical solution are as follows: This solution provides another method for anomaly detection. By smoothing the curve and then constructing a corresponding function, the smoothing process ensures that the constructed function can be differentiated. Based on this, the second order of the function is calculated, and then the values ​​of the second derivative at each point corresponding to the compression depth are iterated. The ratio of the second derivative value at a single point to the average value of the second derivative values ​​at all points is calculated. If there is a point where the ratio is greater than the safety threshold, it indicates that the most recent compression depth-compression pressure curve is abnormal, i.e., there is a risk of fracture. Figure 13 The curve shown is the most recent press curve. The line corresponding to the second derivative of this curve function is basically horizontal. Figure 13 (where the x and y axes almost coincide) indicates a situation without anomalies; such as Figure 14 and Figure 15 The compression curves for the most recent compression under two different scenarios are shown respectively. Both curves have deviation points on the lines corresponding to the second derivative of the function, which are far from the horizontal level. That is, there are compression depth points where the ratio of the compression pressure to the average value of the second derivative of the compression pressure exceeds the safe threshold. Therefore, both scenarios are abnormal. This approach also achieves quantitative risk analysis, avoids the influence of subjective factors, and improves the reliability of the analysis results.

[0087] In one embodiment, in step S100, the initial pressing depth and pressing force are determined by the following method:

[0088] Obtain the patient's basic information and images of the thoracic skeleton;

[0089] Image preprocessing is performed on the thoracic skeleton image to obtain the preprocessed thoracic skeleton image;

[0090] Feature data is extracted from the preprocessed thoracic skeleton image, and the feature data is input into a pre-trained compression model to output the first compression depth for the patient's cardiopulmonary resuscitation.

[0091] The correction factor is determined based on the patient's basic information. The preset standard compression pressure is then corrected based on the correction factor to obtain the first compression pressure.

[0092] When performing the first compression of cardiopulmonary resuscitation on a patient, the first compression depth and the first compression force should be selected as the compression control reference, and the first parameter and its corresponding measured value should be used as the starting compression depth and compression force.

[0093] The working principle and beneficial effects of the above technical solution are as follows: This solution uses feature data extracted from the preprocessed image of the patient's thoracic skeleton to obtain the first compression depth for cardiopulmonary resuscitation using a compression model. This first compression depth reflects the compressive elasticity of the patient's thoracic skeleton, reducing the risk of fracture caused by the initial compression depth. In addition, a correction coefficient is determined based on the patient's basic information to correct the compression pressure. The resulting first compression pressure can also reduce the risk of fracture caused by the initial compression. Combining these two parameters, and considering that these two parameters may not correspond to each other for the patient (i.e., both parameters will not be reached simultaneously), the parameter that is reached first is used as the limiting parameter for stopping further compressions during the first compression. This further controls the risk, improves the safety of the initial compression, and compensates for the risk of delayed feedback warning. Combined with feedback warning, this further ensures the safety of cardiopulmonary resuscitation.

[0094] In one embodiment, the pre-training process of the press model is as follows:

[0095] A cardiopulmonary resuscitation (CPR) database was constructed by collecting thoracic skeleton images and CPR data from previous patients. The thoracic skeleton images of each patient were preprocessed, and feature data were extracted to form a training set. CPR data of corresponding patients were selected to construct a validation set.

[0096] A basic model of cardiopulmonary resuscitation (CPR) compressions was constructed. The basic model was trained using a training set and validated using a validation set to obtain the optimized parameters of the basic model.

[0097] The basic pressing model is optimized by adjusting the parameters to obtain the pressing model.

[0098] The working principle and beneficial effects of the above technical solution are as follows: This solution provides a pre-training method for a compression model that obtains the first compression depth based on the feature data of the patient's thoracic bone image. Feature data extracted from the thoracic bone images of previous patients and cardiopulmonary resuscitation data are used to form training sets and validation sets, respectively. The basic cardiopulmonary resuscitation compression model is trained and validated using the training set and validation set, and parameter tuning and optimization are performed to obtain a well-trained compression model. Through big data training and learning, the compression model can effectively control the fracture risk of compression.

[0099] In one embodiment, the first pressing pressure is obtained in the following manner:

[0100] The patient's basic information includes age and unhealthy lifestyle habits (smoking, drinking, and staying up late, etc.). An age coefficient is determined based on the patient's age. It can be selected from a pre-set age range and age coefficient comparison table. The older the age, the larger the age coefficient. Values ​​are assigned to each unhealthy lifestyle habit according to the set rules.

[0101] The correction factor is calculated using the following formula:

[0102]

[0103] In the above formula, ε represents the correction coefficient; A represents the pre-set adjustment factor, which can be set based on experimental data; e represents the natural constant; L represents the patient's age coefficient; T i This indicates the value assigned to the i-th unhealthy lifestyle habit of the patient;

[0104] The first pressing pressure is the product of the reciprocal of the correction factor and the preset standard pressing pressure.

[0105] The working principle and beneficial effects of the above technical solution are as follows: Based on the corresponding quantitative transformation of the patient's basic information such as age and unhealthy lifestyle habits, this solution calculates a correction coefficient that is adapted to the patient's basic information by constructing a correction coefficient calculation formula. This coefficient is then used to adjust the preset standard compression pressure, thereby making the obtained first compression pressure suitable for the patient and improving compression safety. Through this algorithm, the method can be flexibly applied to different patients and has higher safety for different patients.

[0106] The adjustment factor introduced in the above formula can be obtained by substituting the cardiopulmonary resuscitation data of each patient into the formula for reverse calculation. For the values ​​of each adjustment factor obtained after cardiopulmonary resuscitation data of different patients, the value conditions corresponding to the adjustment factor values ​​(patient basic information) are determined by statistical methods according to the basic information of different patients, and a adjustment factor value table is formed.

[0107] When using this method, the similarity between the patient's basic information and the values ​​in the value table is calculated. The similarity calculation formula is as follows:

[0108]

[0109] In the above formula, S j S represents the similarity between the basic information of the patient to be treated and the j-th value condition in the value table; S() represents the similarity function; ω k This represents the k-th parameter in the basic information of the patient to be treated; ω jk This represents the k-th parameter in the j-th value condition of the value table;

[0110] Based on the similarity of each value condition calculated, the adjustment factor value corresponding to the value condition with the highest similarity is selected for calculation, thereby further improving the safety of the first compression pressure for the corresponding patient.

[0111] like Figure 3-5 As shown, an embodiment of the present invention provides a cardiopulmonary resuscitation device, including a controller 1, a drive mechanism 2, and a compression head assembly 3;

[0112] The controller 1 includes a compression parameter determination module 11 and a fracture warning module 12. The compression parameter determination module 11 is used to determine the compression depth and compression pressure at the start of cardiopulmonary resuscitation (CPR) based on the patient's basic information and thoracic skeleton image. The fracture warning module 12 is used to issue a fracture risk alarm during CPR. The controller 1 is used to implement CPR control based on the compression depth and compression pressure.

[0113] The drive mechanism 2 is used to operate under the control of the controller 1 and drive the pressing head assembly 3 to perform pressing motion;

[0114] The compression head assembly 3 is used to perform compression movements for cardiopulmonary resuscitation on the patient under the drive mechanism 2.

[0115] The working principle and beneficial effects of the above technical solution are as follows: This solution determines the compression depth and pressure at the start of cardiopulmonary resuscitation (CPR) through the compression parameter determination module in the controller. The controller drive mechanism drives the compression head assembly to perform CPR compression movements on the patient. During compression, the aforementioned CPR pressure feedback fracture warning method is executed in conjunction with the fracture warning module. When this solution is used in actual CPR, if the patient is at risk of fracture, a timely warning can be issued, reminding medical personnel to take relevant countermeasures such as adjusting the compression parameters (compression depth and pressure). On the one hand, it ensures that continuous compression will not cause fractures, pain, respiratory depression, bronchopneumonia, puncture of blood vessels, or organ bleeding, thus avoiding life-threatening situations for the patient. On the other hand, it can accurately adapt to different patients with different ages, physical conditions, and lifestyles, so that the compression parameters (compression depth and pressure) match the density, fragility, and pressure resistance of the patient's thoracic bones, improving the accuracy of the control of the compression parameters (compression depth and pressure) and further mitigating risks.

[0116] In one embodiment, such as Figure 6-8 As shown, the drive mechanism 2 includes a rotary motion component 21, a transmission component 23, and a linear motion component 22;

[0117] The transmission assembly 23 includes a driving pulley 231 and a driven pulley 232; the driving pulley 231 and the driven pulley 232 mesh; or it may also include a synchronous belt 233, which meshes with the driving pulley 231 and the driven pulley 232 respectively;

[0118] The rotary motion assembly 21 includes a motor 211 and a motor mounting base 212. The motor 211 is fixed on the motor mounting base 212, and the drive pulley 231 is mounted on the output shaft of the motor 211 via a flat key 213.

[0119] The linear motion assembly 22 includes a pressure frame 221, a lead screw and nut assembly 222, a pressing push rod 224, and a push rod guide sleeve 225. The lead screw and nut assembly 222 includes a lead screw 2221 and a lead screw nut 2222 threadedly fitted onto the lead screw 2221. The lead screw 2221 of the lead screw and nut assembly 222 is installed inside the pressing frame 221 via a mating bearing 226. A driven pulley 232 is provided at the upper end of the lead screw 2221, and the bearing end... Cover 227 locks the outer ring of bearing 226 onto the inner ring of pressing frame 221 to prevent bearing 226 from moving up and down. Locking nut 228 locks lead screw 2221 onto the inner ring of bearing 226 to prevent lead screw 2221 from moving up and down. The portion of pressing push rod 224 located inside pressing frame 221 is installed on lead screw nut 2222. Push rod guide sleeve 225 is located at the bottom of pressing frame 221 and is sleeved on the pressing push rod. On rod 224, the lead screw 2221 rotates, driving the lead screw nut 2222 to move up and down linearly. The push rod guide sleeve 225 at the bottom of the pressing frame 221 guides the pressing push rod 224 on the lead screw nut 2222 to prevent it from oscillating. The pressing push rod 224 is equipped with an indicator 229 that indicates the pressing depth. The indicator 229 includes a scale 2291 and a slider 2292 with a pointer. The side of the pressing frame 221 has a vertical guide hole. The scale 2291 is installed along the vertical guide hole on the side of the pressing frame 221. The slider 2292 can move up and down in the vertical guide hole. The pointer on the slider 2292 indicates the corresponding scale value on the scale 2291 as the slider moves. The side of the slider 2292 away from the pointer is fixedly connected to the pressing push rod 224. Sensors can also be set on the scale 2291 and the pointer. The sensors are used to convert the pointer's indication data into an electrical signal and feed it back to the controller.

[0120] The press head assembly 3 is located at the bottom of the press push rod 224. The press head assembly 3 includes a press head support 31, a miniature cable chain 33, a press head guide sleeve 34, a press head 35, a baffle 36, and a buffer ring 37. The press head support 31 is fixed to the bottom of the press push rod 224. A pressure sensor 121 of the fracture warning module 12 is installed inside the press head support 31. The sensing cable 122 of the pressure sensor passes through the through hole on the press push rod 224 and is installed inside the miniature cable chain 33. The miniature cable chain 33 is located on the outer side of the press frame 221. As the pressing head assembly 3 moves up and down, the micro chain 33 drags up and down on the outer side of the pressing frame 221; the pressing head guide sleeve 34 is fixed to the lower end of the pressing head support 31, the pressing head 35 is sleeved on the pressing head guide sleeve 34 and limited by the baffle 36, the pressing head 35 can move up and down slightly on the pressing head guide sleeve 34, the pressing head 35 presses the patient's chest, the patient's sternum reacts to the pressing head 35 to transmit the pressing force to the pressure sensor 121, the buffer ring 37 is set between the pressure sensor 121 and the pressing head 35 to play a buffering role;

[0121] The transmission assembly 23 converts the rotational motion of the motor 211 into the linear motion of the lead screw nut 2222, thereby driving the compression head 35 to perform cardiopulmonary resuscitation compressions on the patient's chest.

[0122] The working principle and beneficial effects of the above technical solution are as follows: The CPR system with real-time feedback of compression pressure in this solution uses a servo motor capable of forward and reverse rotation. The drive mechanism employs a rotary motion component primarily powered by a motor, which is driven by pulleys (active and driven pulleys) and a synchronous belt in the transmission component. The linear motion component converts the rotary motion into linear motion, thereby driving the compression push rod in the linear motion component to push the compression head component, performing CPR compressions on the patient. Initially, the compression push rod is adjusted to a predetermined height, ensuring the bottom of the compression head component at the lower end of the push rod contacts the patient's chest skin. The compression depth of the compression head component can be precisely controlled by precisely controlling the forward and reverse rotation angles of the motor. During compression using the initial compression parameters, if a fracture warning module issues a risk warning, the controller reduces the forward and reverse rotation angles of the motor, thus reducing the compression depth of the compression head component and effectively preventing risks.

[0123] In one embodiment, such as Figure 9 As shown, the drive mechanism 2 includes a cylinder 24, a four-way valve 25, and an air pump 26; the two non-connected opposite interfaces of the four-way valve 25 are connected to the air inlet and air outlet of the air pump 26 respectively, and one of the interfaces of the four-way valve 25 is connected to the fixed cavity interface of the cylinder 24; the lower end of the moving part of the cylinder 24 is equipped with a pressing head assembly 3.

[0124] An infrared ranging sensor 123 is installed at the lower end of the fixed cavity of the cylinder 24. The infrared ranging sensor 123 is electrically connected to the controller 1. The infrared ranging sensor 123 is used to measure the pressing depth of the pressing head assembly 3.

[0125] The working principle and beneficial effects of the above technical solution are as follows: The driving mechanism of this solution uses a cylinder connected to an air pump as a power source. Through the reversing of the four-way valve, the cylinder is repeatedly filled and emptied. When filling, the pressing head assembly is pressed down to make the patient exhale. When emptying, the contraction of the pressing head assembly causes the patient's chest cavity to rebound, making the patient inhale. The driving mechanism can use the cylinder air pressure converted from the pressing pressure to calculate the air supply and suction volume provided by the air pump to the cylinder, thereby controlling the air pump and the four-way valve accordingly. A spring can be installed in the cylinder, with both ends of the spring fixedly connected to the top of the moving part of the cylinder and the top of the cylinder, respectively. When emptying, the tension of the spring further accelerates the contraction of the pressing head assembly.

[0126] In one embodiment, such as Figure 10 As shown, the drive mechanism 2 includes a pressure rod 27, a connecting rod assembly 28, and a motor 29; the connecting rod assembly 28 includes a first connecting rod 281 and a second connecting rod 282;

[0127] The first connecting rod 281 is provided with a first guide elongated hole and a second guide elongated hole, and the side of the second connecting rod 282 is provided with a toothed bar;

[0128] One end of the first link 281 is fixed, and the other end of the first link 281 is hinged to the second link 282 through the first guide elongated hole;

[0129] The output shaft of motor 29 is fixed with a gear, which meshes with the rack teeth on the side of the second connecting rod 282;

[0130] The top end of the pressure rod 27 is connected to the second guide hole of the first connecting rod 281 by a sliding pin. The sliding pin can move within the second guide hole. The bottom end of the pressure rod 27 is connected to the pressing head assembly 3.

[0131] An infrared distance sensor 123 is installed at the lower end of the linkage assembly 28. The infrared distance sensor 123 is electrically connected to the controller 1. The infrared distance sensor 123 is used to measure the pressing depth of the pressing head assembly 3.

[0132] The working principle and beneficial effects of the above technical solution are as follows: The drive mechanism of this solution uses a motor as a power source. Through the lever formed by the pressure rod and the connecting rod assembly, under the control of the forward and reverse rotation angle of the motor, the rotational motion is converted into linear reciprocating motion through the meshing of the gear and the rack on the side of the second connecting rod, thereby driving the up and down reciprocating motion of the compression head assembly to realize the cardiopulmonary resuscitation compression action.

[0133] In one embodiment, the press parameter determination module includes:

[0134] The information acquisition submodule is used to acquire the patient's basic information and thoracic skeleton images;

[0135] The preprocessing submodule is used to preprocess the thoracic skeleton image to obtain a preprocessed thoracic skeleton image.

[0136] The initial compression depth determination submodule is used to extract feature data from the preprocessed thoracic skeleton image, input the feature data into the pre-trained compression model, and output the first compression depth for the patient's cardiopulmonary resuscitation.

[0137] The compression pressure correction submodule is used to determine the correction coefficient based on the patient's basic information, and to correct the preset standard compression pressure according to the correction coefficient to obtain the first compression pressure;

[0138] The compression parameter determination submodule is used to select the first compression depth and the first compression force as the compression control reference when performing the first compression on the patient during the first compression of cardiopulmonary resuscitation, and to use the first parameter and the actual measured value of the other parameter as the starting compression depth and compression force.

[0139] The working principle and beneficial effects of the above technical solution are as follows: This solution acquires the patient's basic information and thoracic skeleton image through the information acquisition submodule. After preprocessing the thoracic skeleton image through the preprocessing submodule, the feature data extracted by the compression depth preliminary determination submodule are used to obtain the first compression depth for cardiopulmonary resuscitation using a compression model. This first compression depth can reflect the pressure-bearing elasticity of the patient's thoracic skeleton, reducing the risk of fracture caused by the initial compression depth. In addition, the compression pressure correction submodule determines the correction coefficient based on the patient's basic information to correct the compression pressure. The resulting first compression pressure can also reduce the risk of fracture caused by the initial compression. Combining these two parameters, considering that these two parameters may not correspond to each other for the patient (i.e., both parameters will not be reached simultaneously), when performing the first compression, the compression parameter determination submodule uses the first of the two as the limiting parameter for stopping further compression. This can further control the risk, improve the safety of the initial compression, and compensate for the risk of delayed feedback warning. Combined with feedback warning, this can further ensure the safety of cardiopulmonary resuscitation.

[0140] In one embodiment, the fracture early warning module includes:

[0141] The compression parameter acquisition submodule includes a pressure sensor installed at the contact point between the compression head assembly and the patient's chest. The pressure sensor is used to continuously acquire the compression pressure for each compression during cardiopulmonary resuscitation. The compression parameter acquisition submodule also records the compression depth corresponding to the compression pressure. The compression depth is the compression stroke that the compression head assembly continues to travel downwards after contacting the patient.

[0142] The analysis submodule is used to generate a pressure depth-pressure curve for each press based on the pressure depth and pressure of each press, and to analyze whether there are any anomalies in the most recent pressure depth-pressure curve;

[0143] The risk warning submodule is used to issue a fracture risk alarm when there is an abnormality in the recent compression depth-compression pressure curve, indicating a risk of fracture.

[0144] The working principle and beneficial effects of the above technical solution are as follows: This solution synchronously records compression pressure and compression depth through the compression parameter acquisition submodule, generates compression depth-compression pressure curves for each compression, analyzes whether there are any abnormalities in the most recent compression depth-compression pressure curves, can quantitatively analyze the fracture risk during compression, avoid the influence of subjective factors, and improve the reliability of the analysis results; In addition, during the compression process, important effective indicators of cardiopulmonary resuscitation, namely blood saturation and end-tidal CO2, can be monitored simultaneously. On the one hand, if the monitoring results show a critical situation, an early warning will be issued; on the other hand, the compression parameters (compression depth and compression pressure) of cardiopulmonary resuscitation can be optimized and adjusted based on the monitoring results.

[0145] Figure 16 The illustration shows an application embodiment of the present invention. In this embodiment, the cardiopulmonary resuscitation pressure feedback fracture early warning method simultaneously employs curve non-overlap analysis. Figure 16 The decision method 1) and second derivative analysis in the process ( Figure 16 Combine the judgment method 2 in the process.

[0146] Initially, the bottom of the compression head assembly is adjusted to contact the patient's chest skin. Based on the initial compression data (compression depth and / or compression pressure), the drive mechanism (such as the forward and reverse rotation angle of the motor) is precisely controlled to achieve precise control of the compression depth (and / or compression pressure). The reciprocating motion of the compression head assembly initiates CPR compressions on the patient. Medical personnel activate the "fracture risk warning" function on the device. During compressions using the initial parameters, the device continuously monitors the relationship between compression depth and pressure, and simultaneously uses judgment method 1 (curve non-overlap analysis) and judgment method 2 (second derivative analysis) to identify fracture risk.

[0147] Using method 1, the overlap between the most recent compression depth-pressure curve and previous curves is compared. An abnormal inconsistency within a short period may indicate a fracture. The specific process is as follows:

[0148] 1. Record the pressing process. The pressure value data (pressing pressure) groups P1[n] and P2n] with the pressing depth as the horizontal axis are the data of two consecutive pressing processes, where n = 1, 2, 3, ..., N, and N is the number of pressing data collections for a single press;

[0149] 2. Calculate the sum of the square roots of the difference (P1[n]-P2[n]) (n takes values ​​from 0 to N-1), and denote this value as D[2], which represents the curve change of the second pressing process compared to the first pressing process; similarly, calculate all D[n];

[0150] 3. Compare the most recent D[N] with the average value E[n] of several recent times in the D[n] sequence. Several recent times can be taken as 5 to 10 times. That is, if D[N]>k1*E[n], it indicates that the patient's chest cavity condition has changed suddenly, indicating the risk of fracture; k1 is the first alarm coefficient threshold.

[0151] Using judgment method 2, the smoothness of the depth-pressure curve of a single press is analyzed. Sudden changes in the force system composed of muscles and bones are more clearly reflected in the second derivative curve of the depth-pressure curve; the specific process is as follows:

[0152] 1. Use the pressing pressure sampling sequence P1[m] corresponding to the pressing depth of a single press, m=1,2,3,…,N,N is the number of pressing data collections for a single press, generate a smoothness curve with pressing depth as the abscissa, and generate the second derivative sequence S1[m] by taking the derivative of the smoothness curve.

[0153] 2. Compare the second derivative value S1[m] of each most recent compression depth sampling point with the average value eS1 of the second derivative value of the current sequence;

[0154] 3. When S1[m] > k2*eS1, it indicates a risk of fracture and an alarm is triggered; k2 is the second alarm coefficient threshold.

[0155] Figure 16The thresholds in the process include a deviation threshold for the non-overlapping degree from the average value and a safety threshold reflecting the deviation of the line point corresponding to the second derivative of the curve function. If the difference between the non-overlapping degree of the compression curves of the two most recent compressions and the average non-overlapping degree is greater than the deviation threshold, and / or, there is a compression depth point on the line point of the second derivative of the curve function corresponding to the most recent compression curve that exceeds the average value of the second derivative of the compression pressure by a proportion exceeding the safety threshold, then there is a risk of fracture. The fracture warning module will issue a fracture risk alarm. At this time, the device can adjust the compression parameters according to the settings (e.g., reduce the compression depth and reduce the compression pressure). Medical staff should pay more attention or take other effective measures. If adjusting the compression parameters or other measures are effective, the medical staff will clear the alarm and continue to perform cardiopulmonary resuscitation on the patient. When using this invention for cardiopulmonary resuscitation, a timely warning can be issued when a patient is at risk of fracture, prompting medical personnel to take appropriate measures such as adjusting compression parameters (compression depth and pressure). On the one hand, this ensures that continuous compressions will not cause fractures, pain, respiratory depression, bronchopneumonia, puncture of blood vessels, or organ bleeding, thus avoiding life-threatening situations for the patient. On the other hand, it can precisely adapt to different patients with varying ages, physical conditions, and lifestyles, matching the compression parameters (compression depth and pressure) to the density, fragility, and pressure resistance of the patient's thoracic bones, improving the accuracy of control over these parameters and further mitigating risks.

[0156] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A cardiopulmonary resuscitation device, characterized in that, Includes a controller, drive mechanism, and press head assembly; The controller includes a compression parameter determination module and a fracture warning module. The compression parameter determination module is used to determine the compression depth and pressure at the start of cardiopulmonary resuscitation based on the patient's basic information and thoracic skeleton image. The fracture warning module is used to issue a fracture risk alarm during the implementation of cardiopulmonary resuscitation. The controller is used to control cardiopulmonary resuscitation based on compression depth and pressure; The drive mechanism is used to operate under the control of the controller and drive the press head assembly to perform the pressing motion; The compression head assembly is used to perform compression movements for cardiopulmonary resuscitation on a patient, driven by a drive mechanism; The pressure parameter determination module includes: The information acquisition submodule is used to acquire the patient's basic information and thoracic skeleton images; The preprocessing submodule is used to preprocess the thoracic skeleton image to obtain a preprocessed thoracic skeleton image. The initial compression depth determination submodule is used to extract feature data from the preprocessed thoracic skeleton image, input the feature data into the pre-trained compression model, and output the first compression depth for the patient's cardiopulmonary resuscitation. The compression pressure correction submodule is used to determine the correction coefficient based on the patient's basic information, and to correct the preset standard compression pressure according to the correction coefficient to obtain the first compression pressure; The compression parameter determination submodule is used to select the first compression depth and the first compression force as the compression control reference when performing the first compression on the patient during the first compression of cardiopulmonary resuscitation, and to use the first parameter and the actual measured value of the other parameter as the starting compression depth and compression force. The fracture early warning module includes: The compression parameter acquisition submodule includes a pressure sensor, which is installed at the contact point between the compression head assembly and the patient's chest. The pressure sensor is used to continuously acquire the compression pressure for each compression during cardiopulmonary resuscitation. The compression parameter acquisition submodule also records the compression depth corresponding to the compression pressure. The analysis submodule is used to generate a pressure depth-pressure curve for each press based on the pressure depth and pressure of each press, and to analyze whether there are any anomalies in the most recent pressure depth-pressure curve; The risk warning submodule is used to issue a fracture risk alarm when there is an abnormality in the recent compression depth-compression pressure curve, indicating a risk of fracture.

2. The cardiopulmonary resuscitation device according to claim 1, characterized in that, The drive mechanism includes rotary motion components, transmission components, and linear motion components; The transmission assembly includes a driving pulley and a driven pulley, which are connected by a drive mechanism. The rotary motion component includes a motor, and a drive pulley is fixedly connected to the output shaft of the motor; The linear motion assembly includes a lead screw and nut assembly and a pressing push rod. The lead screw and nut assembly includes a lead screw and a lead screw nut that is threaded onto the lead screw. The pressing push rod is mounted on the lead screw and nut. A driven pulley is mounted on the lead screw. A pressing head assembly is mounted on the bottom of the pressing push rod.

3. The cardiopulmonary resuscitation device according to claim 1, characterized in that, The initial pressing depth determination submodule's processing procedure is as follows: Feature data is extracted from the preprocessed thoracic skeleton image, and the feature data is input into a pre-trained compression model to output the first compression depth for the patient's cardiopulmonary resuscitation. The correction factor is determined based on the patient's basic information. The preset standard compression pressure is then corrected based on the correction factor to obtain the first compression pressure. When performing the first compression of cardiopulmonary resuscitation on a patient, the first compression depth and the first compression force should be selected as the compression control reference, and the first parameter and its corresponding measured value should be used as the starting compression depth and compression force.

4. The cardiopulmonary resuscitation device according to claim 1, characterized in that, The pre-training process of the compression model used in the initial compression depth determination sub-module is as follows: A cardiopulmonary resuscitation (CPR) database was constructed by collecting thoracic skeleton images and CPR data from previous patients. The thoracic skeleton images of each patient were preprocessed, and feature data were extracted to form a training set. CPR data of corresponding patients were selected to construct a validation set. A basic model of cardiopulmonary resuscitation (CPR) compressions was constructed. The basic model was trained using a training set and validated using a validation set to obtain the optimized parameters of the basic model. The basic pressing model is optimized by adjusting the parameters to obtain the pressing model.

5. The cardiopulmonary resuscitation device according to claim 1, characterized in that, The analysis process of the analysis submodule includes: Calculate the degree of overlap of the compression depth-compression pressure curves for each two adjacent compressions. By comparing the degree of overlap of the two most recent compressions with other degree of overlap, determine whether there are any anomalies in the most recent compression depth-compression pressure curves; specifically: Based on the pressure depth-pressure curve of two adjacent presses, take the pressure of two presses with the same pressure depth on the two curves respectively to obtain two sets of pressure data. The sum of the square roots of the pressure differences at the same pressing depth is used to obtain the degree of non-overlap. The non-overlapping degree of the two most recent presses is compared with the average of the non-overlapping degrees of a predetermined number of recent presses. If the non-overlapping degree of the two most recent presses is greater than the average, it indicates that there is an abnormality; otherwise, there is no abnormality.

6. The cardiopulmonary resuscitation device according to claim 1 or 5, characterized in that, The analysis process of the analysis submodule also includes: The pressure depth-pressure curve of the most recent press is smoothed to obtain a smooth curve; Construct a pressure function with pressure depth as the independent variable based on the smooth curve; The second derivative of the pressure function is calculated, and the pressure depth of the most recent press is substituted into the solution to obtain the second derivative value of the pressure corresponding to each pressure depth point. Compare the second derivative of the pressure value corresponding to each pressure depth point with the average value of the second derivative of the pressure value. If there is a pressure depth point whose ratio to the average value of the second derivative of the pressure value exceeds the safety threshold, it indicates that the most recent pressure depth-pressure curve is abnormal; otherwise, there is no abnormality.

Images