Medium and long catheter puncture positioning and intelligent monitoring integrated system

Abstract

The invention discloses a medium and long catheter puncture positioning and intelligent monitoring integrated system which is characterized in that a preset puncture path of a medium and long catheter is output by constructing a catheter positioning model; simulating a medium and long catheter puncture positioning process according to a preset puncture path, analyzing performance index data under the same environmental parameters, extracting the performance index data to obtain key performance parameters of a puncture positioning effect, establishing an effect prediction model, and obtaining an effect prediction result by obtaining actual puncture positioning data. A fluctuation characteristic value about the effect prediction model is obtained to determine an adjustment strategy of puncture positioning, and the system is optimized; and the accuracy and precision of puncture positioning are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of medium-length catheter puncture, and in particular to a medium-length catheter puncture positioning and intelligent monitoring integrated system. Background Art

[0002] A medium-length catheter is a catheter that is placed from the antecubital fossa of the forearm until it reaches the proximal basilic vein, cephalic vein, or axillary vein, with the tip of the catheter located in the axilla or under the clavicle, but cannot reach the central vein.

[0003] However, the existing medium-length catheter puncture positioning system usually uses Seldinger or ultrasound guidance for puncture, which often has high operation requirements and complicated operation process, and lacks an intelligent positioning system, resulting in a low one-time puncture success rate, which increases the pain of patients; at the same time, different physical factors (such as: the curvature and size of the blood vessel) and physiological factors (such as: blood flow parameters) have a direct impact on the performance of puncture positioning, so it is necessary to adjust the positioning technology according to actual conditions; and the traditional medium-length catheter puncture positioning system often relies on experience judgment rather than precise calculation, which may lead to low accuracy and precision of the positioning effect, for example: not considering the blood flow parameters of the human body, which may lead to prediction deviation;

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to propose an integrated system for puncture positioning and intelligent monitoring of medium-length catheters, which solves the problems of low one-time puncture success rate and low accuracy and precision of puncture positioning effect.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an integrated system for puncture positioning and intelligent monitoring of medium-long catheters, including a model design unit, a comprehensive analysis unit and an optimization correction unit, wherein the model design unit, the comprehensive analysis unit and the optimization correction unit are signal-connected;

[0007] The model design unit constructs a catheter positioning model, generates and outputs the preset puncture path of the medium-length catheter to the comprehensive analysis unit;

[0008] The comprehensive analysis unit includes a puncture path analysis module and a positioning accuracy analysis module, and the puncture path analysis module and the positioning accuracy analysis module are signal-connected;

[0009] The puncture path analysis module simulates the puncture positioning process of a medium-length catheter according to the preset puncture path, and generates performance index data under different environmental parameters, and then extracts the performance index data to obtain the key performance parameters of the puncture positioning effect, and establishes an effect prediction model based on the key performance parameters; wherein the environmental parameters include blood flow parameters and vascular parameters;

[0010] The positioning accuracy analysis module obtains the actual puncture positioning data, substitutes the actual puncture positioning data into the effect prediction model, obtains the fluctuation characteristic value of the puncture positioning effect, and determines the puncture positioning effect according to the fluctuation characteristic value to determine the adjustment strategy of the puncture positioning, and generates an optimization signal and sends it to the optimization correction unit;

[0011] The optimization correction unit receives the optimization signal and adaptively adjusts the puncture positioning of the medium and long catheter to realize intelligent monitoring of the system.

[0012] Furthermore, the specific working process of generating key performance parameters is as follows:

[0013] Step A1, obtaining historical puncture positioning data through a preset puncture path, and determining typical values ​​and variation ranges under different environmental parameters;

[0014] Step A2, statistical information is collected based on historical puncture positioning data and environmental parameters are set, and a three-dimensional positioning model is established to simulate the puncture positioning behavior of a medium-length catheter;

[0015] Step A3, extracting the corresponding performance indicators of puncture positioning according to the simulation results, the performance indicators including the movement speed direction, the movement speed value and the acceleration value, and marking them as generated performance indicator data;

[0016] Step A4: verify the simulation results and adjust the model parameters according to the verification results.

[0017] Furthermore, the specific working process of step A2 is as follows:

[0018] Step A201, obtaining environmental parameters from historical puncture positioning data, the environmental parameters including blood flow parameters and blood vessel parameters, the blood flow parameters including blood pressure and blood flow velocity, which are marked as a1 and a2 respectively; the blood vessel parameters including the curvature and size of the blood vessel, which are marked as b1 and b2 respectively; and then processing and analyzing the environmental parameters by setting a parameter influence model to obtain an environmental influence coefficient HG;

[0019] Step A202, establish a three-dimensional positioning model, set up N2 simulation scenes according to the preset puncture path, analyze the impact of different environmental parameters on the puncture positioning effect; and then identify the environmental parameters with the most significant impact on the puncture positioning effect according to the generated environmental impact coefficient HG.

[0020] Furthermore, the specific working process of step A201 is as follows:

[0021] Step A201-1, constructing a parameter influence model: marking the input information as a parameter set Q0, the parameter set Q0 includes N0 element values, marking any element value as Xi, assigning corresponding weight factor coefficients to the N0 element values ​​respectively, the weight factor coefficient of the marked element value Xi is φi, and establishing a formula to output the influence coefficient Qyx of the parameter set Q;

[0022] Step A201-2, applying the parameter influence model: first, the blood flow parameters and the vascular parameters are respectively substituted into the reference numerical model, and the blood flow reference index set and the vascular reference index set are respectively output, and they are respectively substituted into the parameter influence model, and the blood flow influence coefficient XL and the vascular influence coefficient XG are respectively output;

[0023] First, a reference numerical model is constructed: the input information is marked as parameter Q1, which includes multiple data indicators, and any data indicator in parameter Q1 is marked as k, and the data value of the marked data indicator k is Lk, and the standard interval of the data indicator k is set to KZ [KZ1, KZ2]; then, the reference value Ck of the data indicator k is obtained by combining the data value Lk with the standard interval KZ; wherein, each data indicator k corresponds to a standard reference index Ck, and the standard reference index Ck is expressed as a normal reference index and an abnormal reference index;

[0024] Then apply the reference numerical model: mark the blood flow parameters as U1 = {blood pressure a1, blood flow velocity a2}, mark the blood vessel parameters as U2 = {curvature b1, size b2}, and substitute the U1 set into the reference numerical model, output the blood pressure reference value Ca1 and the blood flow velocity reference value Ca2, and integrate them into the blood flow reference index set, and substitute the U2 set into the reference numerical model, output the curvature reference value Cb1 and the size reference value Cb2, and integrate them into the blood vessel reference index set;

[0025] The blood flow influence coefficient XL is output by combining the blood pressure reference value Ca1 and the blood flow velocity reference value Ca2;

[0026] The blood vessel influence coefficient XG is output by combining the curvature reference value Cb1 and the size reference value Cb2;

[0027] A201-3, and then integrate the blood flow influence coefficient XL and the blood vessel influence coefficient XG into an influence coefficient set, and then substitute the influence coefficient set into the parameter analysis model to output the environmental influence coefficient HG.

[0028] Furthermore, in step 202, the specific working process of determining the environmental parameter with the most significant effect on puncture positioning is as follows:

[0029] Set a first threshold interval, a second threshold interval, and a third threshold interval, and compare and analyze the environmental impact coefficient HG with the preset first threshold interval, second threshold interval, and third threshold interval respectively:

[0030] When the environmental impact coefficient HG is in the first threshold interval, it is determined that the puncture positioning effect is good;

[0031] When the environmental impact coefficient HG is in the second threshold interval, it is determined that the puncture positioning effect is moderate;

[0032] When the environmental impact coefficient HG is in the third threshold interval, it is determined that the puncture positioning effect is poor; wherein the first threshold interval is smaller than the second threshold interval and smaller than the third threshold interval;

[0033] Then, through N2 simulation scenes, the best environmental parameters are recorded for the simulation scenes according to the preset puncture paths.

[0034] Furthermore, the specific working process of step A3 is as follows:

[0035] Step A301, extracting the position distribution data of the medium-length catheter through the three-dimensional positioning model and the preset puncture path, calculating the distance between two position points in adjacent time, obtaining the distance value dt between the two adjacent points, and then calculating the movement speed direction, movement speed value and acceleration value of the medium-length catheter for puncture positioning;

[0036] Step A302, by analyzing the performance indicators: first decompose the direction of the motion speed: take the vertical axis and the horizontal axis as the baseline, construct a two-dimensional plane, mark the angle between the motion speed direction and the horizontal baseline as the motion speed inclination angle θ; then mark the motion speed value as Vy, mark the acceleration value as ay, and obtain the kinetic energy evaluation coefficient Dp of the current medium-length catheter by combining the motion speed value Vy, the acceleration value ay and the motion speed inclination angle θ;

[0037] Step A304, by comparing the evaluation results under different environmental parameters, a report of performance indicator data is prepared.

[0038] Furthermore, the specific working process of establishing the effect prediction model based on key performance parameters is as follows:

[0039] Step B1, obtaining performance index data corresponding to puncture positioning under different environmental parameters, and then standardizing them so that the data range corresponding to the performance index data of each environmental parameter is [0, 1] or [-1, -1], and constructing a performance index data matrix X;

[0040] Step B2, calculate the covariance matrix based on the processed performance index data to obtain the matrix A covar ; Then for the matrix A covarPerform eigenvalue decomposition and record the eigenvector values ​​respectively, sort the eigencomponents in descending order, and select the largest j components as the principal component components to form the matrix Ank eigen , and construct a new feature space S0 at the same time; where j is a natural number greater than 1, and the component eigenvalue is greater than 1;

[0041] Step B3, combining features according to the feature space S0 to obtain a key performance feature set for predicting the puncture positioning effect, and constructing an effect prediction model according to the key performance feature set.

[0042] Furthermore, the specific working process of obtaining the fluctuation characteristic value is as follows:

[0043] Step C1, using the actual puncture location data as a training set, using the training set to train an effect prediction model, and determining the architecture of the effect prediction model; wherein the effect prediction model is a decision tree model, and the architecture includes the number of decision trees, the depth of the trees, and the minimum number of samples required for splitting nodes; and at the same time, the prediction ability of the trained decision tree model is tested by dividing the puncture location data into a validation set;

[0044] Step C2, based on the prediction results using the validation set, extract the accuracy, precision and recall of the model, and mark them as d1, d2 and d3 respectively, set the collection period Ta, and construct the monitoring vector <accuracy d1, precision d2, recall d3, time period Ta>, calculate the average value and fluctuation value under the period Ta, and mark the average value and fluctuation value corresponding to the accuracy d1 as da1 and db1 respectively, mark the average value and fluctuation value corresponding to the precision d2 as da2 and db2 respectively, and mark the average value and fluctuation value corresponding to the recall d3 as da3 and db3 respectively; wherein the fluctuation value represents the average value of the difference between the maximum and minimum values ​​of the period Ta data;

[0045] Then, the corresponding average value and fluctuation value are combined to generate the fluctuation characteristic value bd;

[0046] Step C3, set the fluctuation characteristic value threshold, and compare the fluctuation characteristic value bd with the preset fluctuation characteristic value threshold. When the fluctuation characteristic value bd exceeds the preset fluctuation characteristic value threshold, it is determined that the puncture positioning effect is unstable, and an early warning signal is generated and sent to the optimization correction unit for early warning; otherwise, the adjustment strategy of the puncture positioning is determined according to the fluctuation characteristic value and the performance index, and an optimization signal is generated and sent to the optimization correction unit.

[0047] Furthermore, when the optimization correction unit receives the optimization signal, it immediately edits and displays the text, and the text content is "The puncture positioning fluctuates, and positioning optimization is required."

[0048] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0049] The present invention comprises a model design unit, a comprehensive analysis unit and an optimization correction unit, and the model design unit, the comprehensive analysis unit and the optimization correction unit are connected by signals. First, a catheter positioning model is constructed to output a preset puncture path of a medium-length catheter. Then, the puncture positioning process of the medium-length catheter is simulated according to the preset puncture path, and performance index data under the same environmental parameters are analyzed. Then, the performance index data is extracted to obtain key performance parameters of the puncture positioning effect, and an effect prediction model is established. By acquiring actual puncture positioning data, a fluctuation characteristic value of the effect prediction model is obtained to determine the adjustment strategy of the puncture positioning, and the system is optimized. The accuracy and precision of the puncture positioning are ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 The schematic diagram of the structure of the present invention is shown. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] Embodiment 1:

[0053] like Figure 1 As shown, a medium-length catheter puncture positioning and intelligent monitoring integrated system includes a model design unit, a comprehensive analysis unit and an optimization correction unit, and the model design unit, the comprehensive analysis unit and the optimization correction unit are connected by signals;

[0054] The specific working steps are as follows:

[0055] S1, the model design unit constructs a catheter positioning model, generates and outputs the preset puncture path of the medium-length catheter to the comprehensive analysis unit;

[0056] S2, the comprehensive analysis unit includes a puncture path analysis module and a positioning accuracy analysis module, and the puncture path analysis module and the positioning accuracy analysis module are signal-connected;

[0057] S2-1, the puncture path analysis module simulates the puncture positioning process of a medium-length catheter according to a preset puncture path, and generates performance index data under different environmental parameters, and then extracts the performance index data to obtain key performance parameters of the puncture positioning effect, and establishes an effect prediction model based on the key performance parameters; wherein the environmental parameters include blood flow parameters and vascular parameters;

[0058] S2-11, wherein the specific working process of generating key performance parameters is as follows:

[0059] Step A1, obtaining historical puncture positioning data through a preset puncture path, and determining typical values ​​and variation ranges under different environmental parameters;

[0060] Step A2, statistical information is collected based on historical puncture positioning data and environmental parameters are set, and a three-dimensional positioning model is established to simulate the puncture positioning behavior of a medium-length catheter;

[0061] The specific working process is as follows:

[0062] Step A201, obtaining environmental parameters from historical puncture positioning data, the environmental parameters including blood flow parameters and blood vessel parameters, the blood flow parameters including blood pressure and blood flow velocity, which are marked as a1 and a2 respectively; the blood vessel parameters including the curvature and size of the blood vessel, which are marked as b1 and b2 respectively;

[0063] Then, by setting the parameter influence model, the environmental parameters are processed and analyzed to obtain the environmental influence coefficient HG; it should be noted that the blood flow parameters will affect the position and stability of the medium-length catheter in the blood vessel, and the blood vessel parameters will affect the placement and passage of the medium-length catheter; the above parameters are collected through integrated equipment, such as: collecting the curvature and size of the blood vessel through ultrasound imaging, and collecting blood pressure and blood flow velocity through laser Doppler equipment. The above equipment is adaptively installed and is not drawn in the figure;

[0064] The specific working process is as follows:

[0065] Step A201-1, construct parameter influence model: mark the input information as parameter set Q0, parameter set Q0 contains N0 element values, mark any element value as Xi, assign corresponding weight factor coefficients to N0 element values ​​respectively, the weight factor coefficient of the marked element value Xi is φi, and establish the formula: The influence coefficient Qyx of the output parameter set Q;

[0066] Step A201-2, applying the parameter influence model: first, the blood flow parameters and the vascular parameters are respectively substituted into the reference numerical model, and the blood flow reference index set and the vascular reference index set are respectively output, and they are respectively substituted into the parameter influence model, and the blood flow influence coefficient XL and the vascular influence coefficient XG are respectively output;

[0067] Step A201-21, first construct a reference numerical model: mark the input information as parameter Q1, parameter Q1 includes multiple data indicators, mark any data indicator in parameter Q1 as k, and mark the data value of data indicator k as Lk, set the standard interval of data indicator k as KZ[KZ1, KZ2]; then combine the data value Lk with the standard interval KZ to obtain the reference value Ck of data indicator k: Ck=(LK-KZ1)*(KZ2-Lk)+1; wherein each data indicator k corresponds to a standard reference index Ck, and the standard reference index Ck is expressed as a normal reference index and an abnormal reference index; it should be noted that when the data value Lk of data indicator k is within the standard interval KZ, the reference index Ck range is [0, 1], and the data indicator is determined to be normal; when the data value Lk of data indicator a is higher or lower than the standard interval KZ, the reference index Ck is greater than 1, and the data indicator is determined to be abnormal;

[0068] Step A201-22, reapply the reference numerical model: mark the blood flow parameters as U1 = {blood pressure a1, blood flow velocity a2}, mark the blood vessel parameters as U2 = {curvature b1, size b2}, and substitute the U1 set into the reference numerical model, output the blood pressure reference value Ca1 and the blood flow velocity reference value Ca2, and integrate them into a blood flow reference index set, and substitute the U2 set into the reference numerical model, output the curvature reference value Cb1 and the size reference value Cb2, and integrate them into a blood vessel reference index set;

[0069] The blood flow influence coefficient XL is output by combining the blood pressure reference value Ca1 and the blood flow velocity reference value Ca2: XL=Ca1*β1+Ca2*β2; wherein β1 and β2 are weight coefficients of the blood pressure reference value Ca1 and the blood flow velocity reference value Ca2, respectively, and both β1 and β2 are greater than 0; it should be noted that the larger the blood pressure reference value Ca1, the more abnormal the blood pressure is. When puncturing and positioning a medium-length catheter, a higher blood pressure may increase the tension of the blood vessel wall, increasing the risk of damaging the blood vessel during the puncture; while too low blood pressure may make the blood vessel difficult to penetrate, and increase the difficulty of puncture; the larger the blood flow velocity reference value Ca2, the more abnormal the blood flow velocity is. A higher blood flow velocity means that the fluid in the blood vessel flows more rapidly, which may increase the difficulty of catheter puncture and lead to inaccurate puncture positioning; based on the above reference values, the corresponding blood flow influence coefficient XL is larger;

[0070] The blood vessel influence coefficient XG is output by combining the curvature reference value Cb1 and the size reference value Cb2: XG = Cb1*β3+Cb2*β4; wherein β3 and β4 are weight coefficients of the curvature reference value Cb1 and the size reference value Cb2, respectively, and both β3 and β4 are greater than 0; it should be noted that the larger the curvature reference value Cb1, the more abnormal the curvature is judged to be. When the puncture positioning of a medium-length catheter is being performed, the resistance caused by the curvature of the blood vessel needs to be overcome when the catheter is advanced, and excessive curvature will cause difficulty in puncture; the larger the size reference value Cb2, the more abnormal the size value is judged to be, and a blood vessel with a smaller diameter may increase the difficulty of catheter puncture; based on the above reference values, the corresponding blood vessel influence coefficient XG is larger;

[0071] A201-3, and then integrate the blood flow influence coefficient XL and the blood vessel influence coefficient XG into an influence coefficient set, and then substitute the influence coefficient set into the parameter analysis model to output the environmental influence coefficient HG: HG = XL*γ1+XG*γ2; wherein γ1 and γ2 are weight coefficients of the blood flow influence coefficient XL and the blood vessel influence coefficient XG, respectively, and both γ1 and γ2 are greater than 0; it should be noted that, when the blood flow influence coefficient XL and the blood vessel influence coefficient XG are larger, the environmental influence coefficient HG is larger, and it is more difficult to determine the puncture positioning;

[0072] Step A202, establishing a three-dimensional positioning model, by setting N2 simulation scenes according to the preset puncture path, analyzing the influence of different environmental parameters on the puncture positioning effect; and then identifying the environmental parameter with the most significant effect on the puncture positioning effect according to the generated environmental influence coefficient HG;

[0073] Among them, the specific working process of determining the environmental parameters with the most significant effect on puncture positioning is as follows:

[0074] Set a first threshold interval, a second threshold interval, and a third threshold interval, and compare and analyze the environmental impact coefficient HG with the preset first threshold interval, second threshold interval, and third threshold interval respectively:

[0075] When the environmental impact coefficient HG is in the first threshold interval, it is determined that the puncture positioning effect is good;

[0076] When the environmental impact coefficient HG is in the second threshold interval, it is determined that the puncture positioning effect is moderate;

[0077] When the environmental impact coefficient HG is in the third threshold interval, it is determined that the puncture positioning effect is poor; wherein the first threshold interval is smaller than the second threshold interval and smaller than the third threshold interval;

[0078] Then, through N2 simulation scenes, the best environmental parameters are recorded for the simulation scenes according to the preset puncture paths;

[0079] Step A3, extracting the corresponding performance indicators of puncture positioning according to the simulation results, the performance indicators including the movement speed direction, the movement speed value and the acceleration value, and marking them as generated performance indicator data;

[0080] The specific working process is as follows:

[0081] Step A301, extracting the position distribution data of the medium-length catheter through the three-dimensional positioning model and the preset puncture path, calculating the distance between two position points in adjacent time, obtaining the distance value dt between the two adjacent points, and then calculating the movement speed direction, movement speed value and acceleration value of the medium-length catheter for puncture positioning;

[0082] Step A302, by analyzing the performance indicators: first decompose the direction of the motion speed: take the vertical axis and the horizontal axis as the baseline, construct a two-dimensional plane, and mark the angle between the motion speed direction and the horizontal baseline as the motion speed inclination angle θ; then mark the motion speed value as Vy, and mark the acceleration value as ay, and obtain the kinetic energy evaluation coefficient Dp of the current medium-length catheter by combining the motion speed value Vy, the acceleration value ay and the motion speed inclination angle θ: Dp = η1*Vy*cosθ+η2*ay; wherein η1 and η2 are weight coefficients of the motion speed value Vy and the acceleration value ay, respectively, and both η1 and η2 are greater than 0; it should be noted that the larger the motion speed value Vy and the acceleration value ay are, the larger the corresponding kinetic energy evaluation coefficient Dp is;

[0083] Step A304, formulating a report of performance indicator data by comparing evaluation results under different environmental parameters;

[0084] Step A4, verifying the simulation results and adjusting the model parameters according to the verification results;

[0085] S2-12, wherein the specific working process of establishing the effect prediction model based on the key performance parameters is as follows:

[0086] Step B1, obtaining performance index data corresponding to puncture positioning under different environmental parameters, and then standardizing them so that the data range corresponding to the performance index data of each environmental parameter is [0, 1] or [-1, -1], and constructing a performance index data matrix X;

[0087] Step B2, calculate the covariance matrix based on the processed performance index data to obtain the matrix A covar :

[0088]

[0089] X = m*ρ;

[0090] Among them, m is the number of observations of the actual puncture positioning data, X Tis the transpose of the performance index data matrix X, ρ represents the number of different performance indicators for analyzing the puncture positioning effect;

[0091] Then for the matrix A covar Perform eigenvalue decomposition and record the eigenvector values ​​respectively, sort the eigencomponents in descending order, and select the largest j components as the principal component components to form the matrix Ank eigen , and construct a new feature space S0 at the same time; where j is a natural number greater than 1, and the component eigenvalue is greater than 1;

[0092] Step B3, combining features according to the feature space S0 to obtain a key performance feature set for predicting the puncture positioning effect, and constructing an effect prediction model according to the key performance feature set;

[0093] S1-2, positioning accuracy analysis module, obtains actual puncture positioning data, substitutes the actual puncture positioning data into the effect prediction model, obtains the fluctuation characteristic value of the puncture positioning effect, and determines the puncture positioning effect according to the fluctuation characteristic value to determine the adjustment strategy of the puncture positioning, and generates an optimization signal and sends it to the optimization correction unit;

[0094] S1-21, wherein the specific working process of obtaining the fluctuation characteristic value is:

[0095] Step C1, using the actual puncture location data as a training set, using the training set to train an effect prediction model, and determining the architecture of the effect prediction model; wherein the effect prediction model is a decision tree model, and the architecture includes the number of decision trees, the depth of the trees, and the minimum number of samples required for splitting nodes; and at the same time, the prediction ability of the trained decision tree model is tested by dividing the puncture location data into a validation set;

[0096] Step C2, based on the prediction results using the validation set, extract the accuracy, precision and recall of the model, and mark them as d1, d2 and d3 respectively, set the collection period Ta, and construct the monitoring vector <accuracy d1, precision d2, recall d3, time period Ta>, calculate the average value and fluctuation value under the period Ta, and mark the average value and fluctuation value corresponding to the accuracy d1 as da1 and db1 respectively, mark the average value and fluctuation value corresponding to the precision d2 as da2 and db2 respectively, and mark the average value and fluctuation value corresponding to the recall d3 as da3 and db3 respectively; wherein the fluctuation value represents the average value of the difference between the maximum and minimum values ​​of the period Ta data;

[0097] Then, the corresponding average value and fluctuation value are combined to generate the fluctuation characteristic value bd: Among them, σ1, σ2 and σ3 are weight correction coefficients, and σ1, σ2 and σ3 are all greater than 0;

[0098] Step C3, setting a fluctuation characteristic value threshold, and comparing the fluctuation characteristic value bd with the preset fluctuation characteristic value threshold. When the fluctuation characteristic value bd exceeds the preset fluctuation characteristic value threshold, it is determined that the puncture positioning effect is unstable, and a warning signal is generated and sent to the optimization correction unit for warning; otherwise, the adjustment strategy of the puncture positioning is determined according to the fluctuation characteristic value and the performance index, and an optimization signal is generated and sent to the optimization correction unit;

[0099] S3, the optimization correction unit receives the optimization signal and adaptively adjusts the puncture positioning of the medium-length catheter to realize intelligent monitoring of the system;

[0100] When the optimization correction unit receives the optimization signal, it immediately edits and displays the text, the text content of which is "The puncture positioning fluctuates and positioning optimization is required"; for example: according to the predetermined objective function and constraints, the adjustment strategy of the puncture positioning is input into the optimization algorithm for optimization solution, and the puncture positioning of the medium and long catheter is intelligently adjusted according to the results of the optimization solution.

[0101] In summary of the above technical scheme: the present invention includes a model design unit, a comprehensive analysis unit and an optimization and correction unit, and the model design unit, the comprehensive analysis unit and the optimization and correction unit are connected by signals; first, by constructing a catheter positioning model, a preset puncture path of a medium-length catheter is output; then, the puncture positioning process of the medium-length catheter is simulated according to the preset puncture path, and the performance index data under the same environmental parameters are analyzed, and then the performance index data is extracted to obtain the key performance parameters of the puncture positioning effect, so as to establish an effect prediction model, and by obtaining the actual puncture positioning data, the fluctuation characteristic value of the effect prediction model is obtained to determine the adjustment strategy of the puncture positioning, and optimize the system; the accuracy and precision of the puncture positioning are ensured.

[0102] The size of the interval and threshold is set for the convenience of comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value;

[0103] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0104] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A medium-length catheter puncture positioning and intelligent monitoring integrated system, characterized by: It includes a model design unit, a comprehensive analysis unit and an optimization correction unit, and signals are connected among the model design unit, the comprehensive analysis unit and the optimization correction unit; The model design unit constructs a catheter positioning model, generates and outputs the preset puncture path of the medium-length catheter to the comprehensive analysis unit; The comprehensive analysis unit includes a puncture path analysis module and a positioning accuracy analysis module, and the puncture path analysis module and the positioning accuracy analysis module are signal-connected; The puncture path analysis module simulates the puncture positioning process of a medium-length catheter according to the preset puncture path, and generates performance index data under different environmental parameters, and then extracts the performance index data to obtain the key performance parameters of the puncture positioning effect, and establishes an effect prediction model based on the key performance parameters; wherein the environmental parameters include blood flow parameters and vascular parameters; The positioning accuracy analysis module obtains the actual puncture positioning data, substitutes the actual puncture positioning data into the effect prediction model, obtains the fluctuation characteristic value of the puncture positioning effect, and determines the puncture positioning effect according to the fluctuation characteristic value to determine the adjustment strategy of the puncture positioning, and generates an optimization signal and sends it to the optimization correction unit; The optimization correction unit receives the optimization signal and adaptively adjusts the puncture positioning of the medium and long catheter to realize intelligent monitoring of the system.

2. The integrated system for puncture positioning and intelligent monitoring of medium-length catheters according to claim 1, characterized in that: The specific working process of generating key performance parameters is as follows: Step A1, obtaining historical puncture positioning data through a preset puncture path, and determining typical values ​​and variation ranges under different environmental parameters; Step A2, statistical information is collected based on historical puncture positioning data and environmental parameters are set, and a three-dimensional positioning model is established to simulate the puncture positioning behavior of a medium-length catheter; Step A3, extracting the corresponding performance indicators of puncture positioning according to the simulation results, the performance indicators including the movement speed direction, the movement speed value and the acceleration value, and marking them as generated performance indicator data; Step A4: verify the simulation results and adjust the model parameters according to the verification results.

3. The integrated system for puncture positioning and intelligent monitoring of medium-long catheters according to claim 1, characterized in that: The specific working process of step A2 is: Step A201, obtaining environmental parameters from historical puncture positioning data, the environmental parameters including blood flow parameters and blood vessel parameters, the blood flow parameters including blood pressure and blood flow velocity, which are marked as a1 and a2 respectively; the blood vessel parameters including the curvature and size of the blood vessel, which are marked as b1 and b2 respectively; and then processing and analyzing the environmental parameters by setting a parameter influence model to obtain an environmental influence coefficient HG; Step A202, establish a three-dimensional positioning model, set up N2 simulation scenes according to the preset puncture path, analyze the impact of different environmental parameters on the puncture positioning effect; and then identify the environmental parameters with the most significant impact on the puncture positioning effect according to the generated environmental impact coefficient HG.

4. The integrated system for puncture positioning and intelligent monitoring of medium-length catheters according to claim 3 is characterized in that: The specific working process of step A201 is: Step A201-1, constructing a parameter influence model: marking the input information as a parameter set Q0, the parameter set Q0 includes N0 element values, marking any element value as Xi, assigning corresponding weight factor coefficients to the N0 element values ​​respectively, the weight factor coefficient of the marked element value Xi is φi, and establishing a formula to output the influence coefficient Qyx of the parameter set Q; Step A201-2, applying the parameter influence model: first, the blood flow parameters and the vascular parameters are respectively substituted into the reference numerical model, and the blood flow reference index set and the vascular reference index set are respectively output, and they are respectively substituted into the parameter influence model, and the blood flow influence coefficient XL and the vascular influence coefficient XG are respectively output; First, a reference numerical model is constructed: the input information is marked as parameter Q1, which includes multiple data indicators, and any data indicator in parameter Q1 is marked as k, and the data value of the marked data indicator k is Lk, and the standard interval of the data indicator k is set to KZ [KZ1, KZ2]; then, the reference value Ck of the data indicator k is obtained by combining the data value Lk with the standard interval KZ; wherein, each data indicator k corresponds to a standard reference index Ck, and the standard reference index Ck is expressed as a normal reference index and an abnormal reference index; Then apply the reference numerical model: mark the blood flow parameters as U1 = {blood pressure a1, blood flow velocity a2}, mark the blood vessel parameters as U2 = {curvature b1, size b2}, and substitute the U1 set into the reference numerical model, output the blood pressure reference value Ca1 and the blood flow velocity reference value Ca2, and integrate them into the blood flow reference index set, and substitute the U2 set into the reference numerical model, output the curvature reference value Cb1 and the size reference value Cb2, and integrate them into the blood vessel reference index set; The blood flow influence coefficient XL is output by combining the blood pressure reference value Ca1 and the blood flow velocity reference value Ca2; The blood vessel influence coefficient XG is output by combining the curvature reference value Cb1 and the size reference value Cb2; A201-3, and then integrate the blood flow influence coefficient XL and the blood vessel influence coefficient XG into an influence coefficient set, and then substitute the influence coefficient set into the parameter analysis model to output the environmental influence coefficient HG.

5. The integrated system for puncture positioning and intelligent monitoring of medium-length catheters according to claim 3 is characterized in that: In step 202, the specific working process of determining the environmental parameter with the most significant effect on puncture positioning is as follows: Set a first threshold interval, a second threshold interval, and a third threshold interval, and compare and analyze the environmental impact coefficient HG with the preset first threshold interval, second threshold interval, and third threshold interval respectively: When the environmental impact coefficient HG is in the first threshold interval, it is determined that the puncture positioning effect is good; When the environmental impact coefficient HG is in the second threshold range, it is determined that the puncture positioning effect is moderate; When the environmental impact coefficient HG is in the third threshold interval, it is determined that the puncture positioning effect is poor; wherein the first threshold interval is smaller than the second threshold interval and smaller than the third threshold interval; Then, through N2 simulation scenes, the best environmental parameters are recorded for the simulation scenes according to the preset puncture paths.

6. The integrated system for puncture positioning and intelligent monitoring of medium-length catheters according to claim 2, characterized in that: The specific working process of step A3 is: Step A301, extracting the position distribution data of the medium-length catheter through the three-dimensional positioning model and the preset puncture path, calculating the distance between two position points in adjacent time, obtaining the distance value dt between the two adjacent points, and then calculating the movement speed direction, movement speed value and acceleration value of the medium-length catheter for puncture positioning; Step A302, by analyzing the performance indicators: first decompose the direction of the motion speed: take the vertical axis and the horizontal axis as the baseline, construct a two-dimensional plane, mark the angle between the motion speed direction and the horizontal baseline as the motion speed inclination angle θ; then mark the motion speed value as Vy, mark the acceleration value as ay, and obtain the kinetic energy evaluation coefficient Dp of the current medium-length catheter by combining the motion speed value Vy, the acceleration value ay and the motion speed inclination angle θ; Step A304, by comparing the evaluation results under different environmental parameters, a report of performance indicator data is prepared.

7. The integrated system for puncture positioning and intelligent monitoring of medium-length catheters according to claim 1, characterized in that: The specific working process of establishing the effect prediction model based on key performance parameters is as follows: Step B1, obtaining performance index data corresponding to puncture positioning under different environmental parameters, and then standardizing them so that the data range corresponding to the performance index data of each environmental parameter is [0, 1] or [-1, -1], and constructing a performance index data matrix X; Step B2, calculate the covariance matrix based on the processed performance index data to obtain the matrix A covar ; Then for the matrix A covar Perform eigenvalue decomposition and record the eigenvector values ​​respectively, sort the eigencomponents in descending order, and select the largest j components as the principal component components to form the matrix Ank eigen , and construct a new feature space S0 at the same time; where j is a natural number greater than 1, and the component eigenvalue is greater than 1; Step B3, combining features according to the feature space S0 to obtain a key performance feature set for predicting the puncture positioning effect, and constructing an effect prediction model according to the key performance feature set.

8. The integrated system for puncture positioning and intelligent monitoring of medium-length catheters according to claim 1, characterized in that: The specific working process of obtaining the fluctuation characteristic value is: Step C1, using the actual puncture location data as a training set, using the training set to train an effect prediction model, and determining the architecture of the effect prediction model; wherein the effect prediction model is a decision tree model, and the architecture includes the number of decision trees, the depth of the trees, and the minimum number of samples required for splitting nodes; and at the same time, the prediction ability of the trained decision tree model is tested by dividing the puncture location data into a validation set; Step C2, based on the prediction results using the validation set, extract the accuracy, precision and recall of the model, and mark them as d1, d2 and d3 respectively, set the collection period Ta, and construct the monitoring vector <accuracy d1, precision d2, recall d3, time period Ta>, calculate the average value and fluctuation value under the period Ta, and mark the average value and fluctuation value corresponding to the accuracy d1 as da1 and db1 respectively, mark the average value and fluctuation value corresponding to the precision d2 as da2 and db2 respectively, and mark the average value and fluctuation value corresponding to the recall d3 as da3 and db3 respectively; wherein the fluctuation value represents the average value of the difference between the maximum and minimum values ​​of the period Ta data; Then, the corresponding average value and fluctuation value are combined to generate the fluctuation characteristic value bd; Step C3, set the fluctuation characteristic value threshold, and compare the fluctuation characteristic value bd with the preset fluctuation characteristic value threshold. When the fluctuation characteristic value bd exceeds the preset fluctuation characteristic value threshold, it is determined that the puncture positioning effect is unstable, and an early warning signal is generated and sent to the optimization correction unit for early warning; otherwise, the adjustment strategy of the puncture positioning is determined according to the fluctuation characteristic value and the performance index, and an optimization signal is generated and sent to the optimization correction unit.

9. The integrated system for puncture positioning and intelligent monitoring of medium-length catheters according to claim 1, characterized in that: When the optimization correction unit receives the optimization signal, it immediately edits and displays the text, and the text content is "The puncture positioning fluctuates and positioning optimization is required."

Images