Catheter intervention operation dynamic correction system based on multi-mode feedback

Abstract

The invention relates to the technical field of catheter intervention data processing, in particular to a catheter intervention operation dynamic correction system based on multi-modal feedback. The whole catheter intervention operation process is monitored in real time through multiple dimensions, multi-modal monitoring data are obtained, a dynamic, accurate and visual bacteria distribution probability field is generated in combination with catheter movement data and operation space data, track key feature points are extracted in combination with operation behavior data, and the accuracy and accuracy of the bacteria distribution probability field are improved. Key links are focused to evaluate a catheter pollution probability value, a plurality of catheter intervention paths are planned in combination with catheter performance data, and an infection risk predicted value of each catheter intervention path is calculated through the pollution probability value, so that an optimal correction path is screened out, an operation direction is defined, and the operation efficiency is improved. And finally, based on the optimal correction path and catheter performance data, generating a multi-mode operation feedback instruction containing vision, touch and hearing, so that the catheter can be prevented from entering a high-infection risk area, the occurrence probability of CRBSI is reduced, and the safety and success rate of operation are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of catheter intervention data processing, in particular to a catheter intervention operation dynamic correction system based on multi-modal feedback. BACKGROUND

[0002] The peripherally inserted central catheter (PICC) refers to the central venous catheter through the basilic vein, cephalic vein or elbow median vein puncture, reaching the central venous catheter at the junction of the upper vena cava and atrium, compared with other venous catheters, the PICC catheter has many advantages, but catheter-related bloodstream infections (CRBSI) still occur in the clinical use process, CRBSI refers to the bloodstream infection of the patient during the indwelling intravascular catheter or within 48 hours after the catheter is removed, and the main cause of CRBSI is that the pathogen migrates to the blood through the catheter surface or lumen to cause infection.

[0003] At present, the prevention and control measures of catheter-related bloodstream infection mainly depend on the sterile operation specification of medical personnel, however, in the actual operation process, due to the fatigue, distraction and other factors of medical personnel, there are still some operation errors, which lead to non-standard sterile operation and further cause CRBSI, and the existing monitoring means is mainly post-tracing or regular inspection, which is difficult to find and correct the problems in the catheter intervention operation in time. SUMMARY

[0004] The main purpose of the present application is to provide a catheter intervention operation dynamic correction system based on multi-modal feedback, which aims to solve the technical problems in the prior art.

[0005] The present application provides a catheter intervention operation dynamic correction system based on multi-modal feedback, comprising: A first acquisition module is used for acquiring multi-modal monitoring data according to an intelligent monitoring device, wherein the multi-modal monitoring data includes catheter motion data, catheter performance data, operation space data and operation behavior data; A second acquisition module is used for acquiring the bacterial distribution probability field of the intervention operation space according to the catheter motion data and the operation space data; An extraction module is used for acquiring a plurality of trajectory key feature points according to the bacterial distribution probability field and the operation behavior data; A third acquisition module is used for acquiring a catheter pollution probability value according to the trajectory key feature points and the catheter motion data; A fourth acquisition module is used for acquiring a catheter intervention path set according to the bacterial distribution probability field and the catheter performance data, wherein the catheter intervention path set includes a plurality of catheter intervention paths, and acquiring an infection risk prediction value of each catheter intervention path according to the catheter pollution probability value; The fifth acquisition module is configured to acquire an optimal correction path according to the infection risk prediction value and the catheter intervention path set, and acquire an operation feedback instruction according to the optimal correction path and the catheter performance data.

[0006] Preferably, the second acquisition module is specifically configured to: acquire catheter contamination path information according to the catheter motion data and the operation space data; acquire contamination source information according to the catheter contamination path information, wherein the contamination source information includes a bacterial concentration, a bacterial diffusion coefficient and a specific bacterial growth rate; acquire a convective transport rate according to a fluid flow rate of an intervention operation space and the bacterial concentration according to the fluid flow rate and the bacterial concentration; acquire a random diffusion rate according to the bacterial concentration and the bacterial diffusion coefficient, and acquire a source term release rate according to the specific bacterial growth rate and the bacterial concentration; acquire a bacterial distribution probability field according to the random diffusion rate, the convective transport rate and the source term release rate.

[0007] Preferably, the extraction module is specifically configured to: acquire real-time operation data and historical operation data according to the operation behavior data, wherein the real-time operation data includes a real-time operation motion speed and a real-time operation direction change rate; acquire catheter spatial coordinates and catheter attitude angle data according to the catheter motion data, and acquire a catheter three-dimensional motion trajectory according to the catheter spatial coordinates and the catheter attitude angle data; acquire a trajectory-probability field mapping grid according to the catheter three-dimensional motion trajectory and the bacterial distribution probability field; acquire trajectory feature judgment data according to the historical operation data, wherein the trajectory feature judgment data includes a motion speed threshold and a direction change rate threshold; screen the catheter three-dimensional motion trajectory according to the operation motion speed and the motion speed threshold to obtain a plurality of primary constraint feature points, and screen a plurality of the primary constraint feature points according to the operation direction change rate and the direction change rate threshold to obtain a plurality of trajectory key feature points.

[0008] Preferably, the third acquisition module is specifically configured to: acquire a corresponding key grid cell according to each of the trajectory key feature points and the trajectory-probability field mapping grid, and acquire a feature point contamination probability value corresponding to each of the trajectory key feature points according to each of the key grid cells; According to the trajectory key feature point, a plurality of key directed edges are acquired, and according to each feature point pollution probability value and the key directed edge, a corresponding average pollution probability value is acquired; According to the catheter motion data, a plurality of directed edge residence time lengths are acquired, and according to a plurality of the directed edge residence time lengths, a path residence time length is acquired. According to the average pollution probability value and the directed edge residence time length, a catheter pollution probability value is acquired.

[0009] Preferably, the fourth acquisition module is specifically used for: According to the catheter motion data, a catheter front end real-time coordinate is acquired, and according to the catheter front end real-time coordinate and the catheter performance data, a catheter reachable area is acquired. According to the bacterial distribution probability field and the catheter reachable area, a passable area is acquired. A catheter target point coordinate is acquired, and according to the catheter target point coordinate, a catheter front end real-time coordinate and a passable area, a plurality of catheter intervention paths are acquired. An immune state evaluation value of the host is acquired, and according to the immune state evaluation value, an immune suppression coefficient is acquired. According to the operation behavior data, an operation compliance score value is acquired, and according to the operation compliance score value, an operation compliance reduction and exemption coefficient is acquired. According to the catheter pollution probability value, the immune state evaluation value, the immune suppression coefficient, the operation compliance score value and the operation compliance reduction and exemption coefficient, an infection risk prediction value is acquired.

[0010] Preferably, the fifth acquisition module is specifically used for: According to the optimal correction path, a key node coordinate and a path curvature feature are acquired, and according to the key node coordinate and the path curvature feature, a correction direction vector is acquired. According to the catheter performance data, a catheter maximum propulsion speed and a catheter minimum turning radius are acquired, and according to the catheter maximum propulsion speed, the catheter minimum turning radius and the correction direction vector, a motion constraint vector is acquired. According to the motion constraint vector, AR guide information is acquired, and according to the AR guide information, visual feedback instructions are acquired. According to the motion constraint vector, a correction intensity value is acquired, and according to the correction intensity value, tactile feedback instructions are acquired. According to the operation state information of the smart bracelet sensor, visual feedback instructions and tactile feedback instructions, speech feedback instructions are acquired.

[0011] The application also provides a computer device comprising a memory and a processor, the memory storing a computer program, and the electronic device further comprising the above-mentioned catheter intervention operation dynamic correction system based on multi-modal feedback.

[0012] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and the electronic device further includes the above-mentioned dynamic correction system for catheter interventional procedures based on multimodal feedback.

[0013] The beneficial effects of this invention are as follows: This invention uses camera equipment and a smart bracelet to monitor the entire process of catheter intervention in real time, collecting multimodal monitoring data and monitoring the operation from multiple dimensions. Specifically, the system integrates catheter motion data and operation space data, uses mathematical models to simulate bacterial distribution, and generates a dynamic, accurate, and visualized bacterial distribution probability field. Then, the system combines the bacterial distribution probability field with operation behavior data, extracts key trajectory feature points, and evaluates the catheter contamination probability value by focusing on key links. At the same time, combining the bacterial distribution probability field and catheter performance data, multiple catheter intervention paths are planned, and the infection risk prediction value of each catheter intervention path is calculated based on the contamination probability value. This allows for the selection of the optimal correction path and clarification of the operation direction. Finally, based on the optimal correction path and catheter performance data, the system generates multimodal operation feedback instructions including visual, tactile, and auditory senses. By efficiently transmitting information through multiple senses, this invention aims to achieve the processing and analysis of data related to catheter intervention operations to assist in optimizing the operation process. Attached Figure Description

[0014] Figure 1 This is a flowchart illustrating the functions performed by each module in a system flow according to an embodiment of the present invention.

[0015] Figure 2 This is a schematic diagram of the system structure according to an embodiment of the present invention.

[0016] Figure 3 This is a schematic diagram of the internal structure of a computer device according to an embodiment of this application.

[0017] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] like Figures 1-3 As shown, this application provides a dynamic correction system for catheter interventional procedures based on multimodal feedback. See also... Figure 1 In this dynamic correction system, The first acquisition module is used to execute step S1, specifically to acquire multimodal monitoring data based on the intelligent monitoring device, wherein the multimodal monitoring data includes catheter motion data, catheter performance data, operating space data, and operating behavior data; a second obtaining module, configured to perform step S2, and specifically configured to obtain a bacteria distribution probability field of an interventional operation space according to the catheter motion data and the operation space data; an extraction module, configured to perform step S3, and specifically configured to obtain a plurality of trajectory key feature points according to the bacteria distribution probability field and the operation behavior data; a third obtaining module, configured to perform step S4, and specifically configured to obtain a catheter contamination probability value according to the trajectory key feature points and the catheter motion data; a fourth obtaining module, configured to perform step S5, and specifically configured to obtain a catheter interventional path set according to the bacteria distribution probability field and the catheter performance data, wherein the catheter interventional path set includes a plurality of catheter interventional paths, and to obtain an infection risk prediction value of each of the catheter interventional paths according to the catheter contamination probability value; a fifth obtaining module, configured to perform step S6, and specifically configured to obtain an optimal correction path according to the infection risk prediction value and the catheter interventional path set, and to obtain an operation feedback instruction according to the optimal correction path and the catheter performance data.

[0020] As the function of each module described above, the peripherally inserted central catheter (PICC) refers to the central venous catheter through the basilic vein, cephalic vein or median cubital vein puncture, through the axillary vein to the junction of the superior vena cava and atrium, compared with other venous catheters, the PICC catheter has many advantages, but in the process of clinical use, catheter-related bloodstream infection (CRBSI) may still occur, CRBSI refers to the bloodstream infection occurring during the indwelling of the intravascular catheter or within 48 hours after the catheter is removed, and the main cause of CRBSI is that the pathogen migrates to the blood through the surface or lumen of the catheter to cause infection. At present, the prevention and control measures of catheter-related bloodstream infection mainly depend on the sterile operation specification of medical staff, however, in the actual operation process, due to the fatigue, distraction and other factors of medical staff, there are still some operation errors, which lead to non-standard sterile operation and further cause CRBSI, and the existing monitoring means is mainly post-tracing or regular inspection, which is difficult to find and correct the problems in the catheter intervention operation in time. In the present application, the whole process of catheter intervention operation of medical staff is monitored in real time through the intelligent monitoring devices such as camera equipment and smart bracelet, and multi-modal monitoring data is obtained, wherein the multi-modal monitoring data refers to the data set collected by various types of monitoring devices (such as camera equipment, sensors, etc.) and reflecting the multi-dimensional information in the catheter intervention operation process, the multi-modal monitoring data includes catheter motion data, catheter performance data, operation space data and operation behavior data, wherein the catheter motion data refers to the data directly describing the dynamic characteristics of the catheter in the intervention operation process, including the position, moving track, speed, direction and other physical motion parameters of the catheter, the catheter performance data refers to the data reflecting the physical properties and functional state of the catheter itself, including the catheter diameter, minimum turning radius and maximum pushing speed, the operation space data refers to the spatial characteristic data describing the environment of the catheter intervention operation, including the geometric structure of the operation area, environmental parameters (such as temperature, humidity) and the like, and the operation behavior data refers to the data recording the behavior characteristics of medical staff in the catheter intervention operation, such as hand movement track, operation force, contact frequency, sterile operation compliance and the like, through these monitoring data, the catheter intervention operation of medical staff can be monitored in real time from multiple dimensions, different types of data complement each other, so that the understanding of the operation process is more comprehensive and in-depth, thereby providing rich and basic data support for subsequent comprehensive and accurate analysis of the operation process and evaluation of the infection risk, the catheter motion data reflects the activity track of the catheter in the operation space, and the operation space data describes the specific environment of the operation space, after the catheter motion to the non-sterile area, the catheter will contact the infection source, thereby causing the spread and transmission of bacteria, by combining the catheter motion data and the operation space data, the distribution of bacteria in the intervention operation space can be simulated by using a mathematical model, and a bacteria distribution probability field is obtained, wherein the bacteria distribution probability field refers to the probability density field of the bacteria distribution in the intervention operation space obtained by calculation.The probability field can reflect the dynamic changes of the bacteria distribution in the operation process in real time, has strong timeliness and accuracy, and the establishment of the bacteria distribution probability field can quantify and visualize the abstract bacteria distribution, so that the medical staff can more intuitively understand the infection risk distribution in the operation space, which helps them to plan the path of the catheter in advance in the subsequent operation process and avoid high-risk areas, thereby reducing the possibility of infection. The bacteria distribution probability field provides distribution information of infection risk in the operation space, and the operation behavior data records the specific actions and behaviors of the medical staff in the operation process. By combining the two, the trajectory key feature points can be obtained, wherein the trajectory key feature points refer to key operation nodes highly related to infection risk, corresponding to behaviors or positions in the operation trajectory that are prone to cause bacterial contamination. Determining the trajectory key feature points can focus on the key links in the operation process. By combining the trajectory key feature points and the catheter movement data, the pollution risk of the catheter can be more targetedly evaluated, and the catheter pollution probability value is obtained, wherein the catheter pollution probability value refers to the possibility value of the catheter being contaminated by bacteria in the operation process calculated by the probability model. Since the bacteria distribution probability field provides distribution information of infection risk in the operation space, and the catheter performance data limits the path range that the catheter can pass through, a plurality of possible catheter intervention paths can be planned by combining the bacteria distribution probability field and the catheter performance data to form a catheter intervention path set, wherein the catheter intervention path is a potential movement path of the catheter from outside the body to the target position (such as a blood vessel or an organ). Then, the infection risk of each catheter intervention path is predicted by combining the catheter pollution probability value calculated in the foregoing to obtain an infection risk prediction value of each path, wherein the infection risk prediction value is a quantitative prediction value of the risk of each catheter intervention path possibly causing CRBSI. Then, the plurality of catheter intervention paths in the catheter intervention path set are sorted according to the infection risk prediction value, and the path with the lowest infection risk prediction value, i.e. the optimal correction path, is selected. The optimal correction path provides a clear target and direction for the catheter intervention operation, reducing the blindness of the operation. Then, the optimal correction path and the catheter performance data are combined to generate an operation feedback instruction, wherein the operation feedback instruction is a multi-modal instruction for guiding the medical staff to adjust the operation behavior. The operation feedback instruction includes visual feedback instructions (such as displaying the operation direction and precautions on the display screen), tactile feedback instructions (such as vibration prompts of the bracelet), and auditory feedback instructions (such as voice prompts). Through the multi-modal operation feedback instruction, information can be conveyed to the medical staff from different sensory channels, improving the efficiency and accuracy of information transmission, so as to respond to unexpected situations in time and avoid the catheter entering a high infection risk area, thereby reducing the probability of catheter-related bloodstream infection (CRBSI) and improving the safety and success rate of the operation.

[0021] In an embodiment, the second acquisition module is specifically configured to: The first obtaining unit is configured to perform step S21, and specifically configured to obtain catheter contamination path information according to the catheter motion data and the operation space data; The second obtaining unit is configured to perform step S22, and specifically configured to obtain contamination source information according to the catheter contamination path information, wherein the contamination source information includes a bacterial concentration, a bacterial diffusion coefficient and a bacterial specific growth rate; The third obtaining unit is configured to perform step S23, and specifically configured to obtain a fluid flow rate of the intervention operation space according to the air flow sensor, and obtain a convective transport rate according to the fluid flow rate and the bacterial concentration; The fourth obtaining unit is configured to perform step S24, and specifically configured to obtain a random diffusion rate according to the bacterial concentration and the bacterial diffusion coefficient, and obtain a source term release rate according to the bacterial specific growth rate and the bacterial concentration; The calculation unit is configured to perform step S25, and specifically configured to calculate a bacterial distribution probability field according to the random diffusion rate, the convective transport rate and the source term release rate, wherein a calculation formula of the bacterial existence probability is: ; wherein P represents a function of the bacterial existence probability, represents a spatial point a bacterial existence probability at a sampling time t, t represents the sampling time, represents the random diffusion rate, represents a convective transport rate at the sampling time t, represents a gradient of the probability function P, represents a source term release rate at the sampling time t.

[0022] According to the functions of the above units, the application identifies a catheter pollution path information that the catheter may contact or pass through in the operation process by analyzing catheter motion data (such as a moving track, a speed, and a direction) and operation space data (such as a geometry and a position of an operation area), wherein the catheter pollution path information refers to information of a potential pollution area or path that the catheter may contact or pass through due to a motion track, an operation mode, or environmental contact in the catheter intervention operation process, then acquires pollution source information according to the catheter pollution path information, wherein the pollution source information refers to a set of key parameters of pollution source characteristics in the intervention operation space, including a bacterial concentration, a bacterial diffusion coefficient, and a bacterial specific growth rate, wherein the bacterial concentration refers to a number of bacteria in a unit volume, reflecting an initial pollution intensity of the pollution source, the bacterial diffusion coefficient refers to an ability of bacteria to diffuse in a medium (such as air) due to random motion, and the bacterial specific growth rate refers to a relative growth rate of the number of bacteria per unit time, reflecting a propagation speed of the bacteria in a suitable environment, through which the characteristics of the pollution source can be comprehensively described to provide core input parameters for subsequent analysis of the transport and propagation of bacteria in space, then acquires a convective transport rate by multiplying a fluid flow rate and the bacterial concentration, wherein the fluid flow rate refers to a flow speed of fluid (such as air) in the intervention operation space, and the convective transport rate refers to a speed of bacteria migration with the flow due to fluid flow, and acquires a random diffusion rate by substituting the bacterial concentration gradient and the bacterial diffusion coefficient into Fick's first law, wherein the random diffusion rate refers to a speed of bacteria diffusion in the medium due to random motion, and acquires a source term release rate by multiplying the bacterial specific growth rate and the bacterial concentration, wherein the source term release rate refers to a pollution release speed caused by the propagation of the bacteria, through which the dynamic distribution law of the bacteria in space is fully described, and finally, the bacteria existence probability of any point in the operation space at any time is calculated by integrating the random diffusion rate, the convective transport rate, and the source term release rate through a formula, to form a visual bacteria distribution probability field, through which a real-time pollution map is provided for the subsequent steps to ensure the timeliness and accuracy of the correction strategy.

[0023] In one embodiment, the extraction module is specifically used for: The first acquisition unit is used to perform step S31 and is specifically used for acquiring real-time operation data and historical operation data according to the operation behavior data, wherein the real-time operation data includes a real-time operation motion speed and a real-time operation direction change rate. The second acquisition unit is used to perform step S32 and is specifically used for acquiring catheter space coordinates and catheter attitude angle data according to the catheter motion data, and acquiring a catheter three-dimensional motion track according to the catheter space coordinates and the catheter attitude angle data. The third acquisition unit is configured to perform step S33, and specifically configured to acquire a trajectory-probability field mapping grid according to the catheter three-dimensional motion trajectory and the bacteria distribution probability field; The fourth acquisition unit is configured to perform step S34, and specifically configured to acquire trajectory feature judgment data according to the historical operation data, wherein the trajectory feature judgment data includes a motion speed threshold and a direction change rate threshold; The screening unit is configured to perform step S35, and specifically configured to screen the catheter three-dimensional motion trajectory according to the operation motion speed and the motion speed threshold to obtain a plurality of primary constraint feature points, and screen a plurality of the primary constraint feature points according to the operation direction change rate and the direction change rate threshold to obtain a plurality of trajectory key feature points.

[0024] As the function of each unit described above, the present application can analyze the operation behavior more comprehensively by acquiring real-time operation data and historical operation data, wherein the real-time operation data refers to dynamic data reflecting the current catheter intervention operation collected in real time, and the real-time operation data includes real-time operation movement speed and real-time operation direction change rate, wherein the real-time operation movement speed refers to the displacement amount of the catheter in a unit time during the operation process, which reflects the speed rhythm of the operation and is a key indicator for measuring the stability or aggressiveness of the operation, and the real-time operation direction change rate refers to the change frequency of the catheter travel direction during the operation process, which is used to evaluate the steering frequency or path tortuosity of the operation and can assist in judging whether the operation has abnormal fluctuations, and these data can help to understand the operation state in real time, and the historical operation data refers to the recorded data accumulated in the past operations of the same type, then the catheter spatial coordinates and catheter attitude angle data are acquired according to the catheter movement data, wherein the catheter spatial coordinates refer to the position coordinates of the catheter tip in the three-dimensional space, which is used to accurately position the catheter, and the catheter attitude angle data refers to the angle parameters (such as pitch angle, yaw angle, roll angle) describing the orientation and attitude of the catheter, which reflects the inclination and rotation state of the catheter, and through the catheter spatial coordinates and the catheter attitude angle data, the movement trajectory of the catheter in the entire operation process can be accurately depicted to form a catheter three-dimensional movement trajectory, then the catheter three-dimensional movement trajectory is spatially coupled with the bacteria distribution probability field, and each point on the trajectory is assigned a corresponding bacteria probability value through grid division to form a trajectory-probability field mapping grid, which can clearly show the bacteria existence probability corresponding to each point on the catheter movement trajectory, then the trajectory feature judgment data are acquired according to the historical operation data, wherein the trajectory feature judgment data refer to standard parameters for judging the trajectory features, including movement speed threshold and direction change rate threshold, then the points with operation movement speed greater than the movement speed threshold are selected from the catheter three-dimensional movement trajectory to obtain a plurality of primary constraint feature points, wherein the primary constraint feature points refer to the feature points with movement speed deviating from the normal range in the catheter three-dimensional movement trajectory, and then the points with operation direction change rate greater than the direction change rate threshold are selected from the primary constraint feature points to obtain a plurality of trajectory key feature points, which represent the positions with high risk in the operation process, through the two-step screening, the range of attention is gradually reduced, the accuracy of screening is improved, and the key feature points with real risk characteristics are selected from a large number of movement trajectory points, so that the subsequent analysis and processing are more efficient.

[0025] In one embodiment, the third acquisition module is specifically configured to: The first obtaining unit is configured to perform step S41, and specifically configured to obtain a corresponding key grid cell according to each trajectory key feature point and the trajectory-probability field mapping grid, and obtain a feature point pollution probability value corresponding to each trajectory key feature point according to each key grid cell; The second obtaining unit is configured to perform step S42, and specifically configured to obtain a plurality of key directed edges according to the trajectory key feature points, and obtain a corresponding average pollution probability value according to each feature point pollution probability value and the key directed edge; The third obtaining unit is configured to perform step S43, and specifically configured to obtain a plurality of directed edge residence time lengths according to the catheter motion data, and obtain a path residence time length according to the plurality of directed edge residence time lengths; The fourth obtaining unit is configured to perform step S44, and specifically configured to obtain a catheter pollution probability value according to the average pollution probability value and the directed edge residence time length.

[0026] According to the functions of the above units, the present application matches the trajectory key feature points to the corresponding grid cells in the trajectory-probability field mapping grid to obtain key grid cells, wherein the key grid cell refers to the grid cell directly corresponding to the spatial position of the trajectory key feature point in the trajectory-probability field mapping grid, then obtains the feature point pollution probability value according to the bacterial distribution values of the eight vertices corresponding to the key grid cell, thereby establishing the direct correlation between the medical staff operation trajectory and the bacterial pollution risk, wherein the feature point pollution probability value refers to the possibility of the catheter contacting bacteria at the position of the feature point, then connects the adjacent trajectory key feature points as key directed edges, wherein the key directed edge refers to the directed line segment connected by two adjacent trajectory key feature points, representing a continuous motion path of the catheter in the operation process, containing definite motion direction and spatial trajectory information, and the average pollution probability value of each edge is obtained by averaging processing to eliminate accidental errors of a single feature point, wherein the average pollution probability value refers to the average pollution probability value corresponding to each key directed edge, then the directed edge residence time length of the catheter on each key directed edge is obtained based on the catheter motion data, wherein the directed edge residence time length is the actual residence time of the catheter when passing through a key directed edge, and the path residence time length is obtained by accumulating a plurality of directed edge residence time lengths, wherein the path residence time length is the total time required for the catheter to pass through all key directed edges, and the residence time length reflects the degree of caution of the operation, thereby providing a behavioral basis for risk assessment.

[0027] Finally, the catheter pollution probability value is obtained by the formula wherein, is the catheter pollution probability value, is the number of key directed edges, is the serial number of the key directed edge, It refers to the first The average contamination probability value of a key directed edge. This refers to the catheter passing through the first... The dwell time of a key directed edge. This refers to the duration of the path stay.

[0028] The above calculation formula is based on the time-weighted risk integral principle, which couples the spatial contamination probability with the time exposure factor. It quantifies the overall contamination risk during catheter operation by weighted averaging. The obtained catheter contamination probability value transforms the potential risk of catheter contact with bacteria into a specific value, which intuitively reflects the possibility of catheter contamination.

[0029] In one embodiment, the fourth acquisition module is specifically used for: The first acquisition unit is used to execute step S51, specifically to acquire the real-time coordinates of the catheter tip based on the catheter motion data, and to acquire the reachable area of ​​the catheter based on the real-time coordinates of the catheter tip and the catheter performance data. The second acquisition unit is used to execute step S52, specifically to acquire a passable area based on the bacterial distribution probability field and the duct reachable area. The third acquisition unit is used to execute step S53, specifically to acquire the coordinates of the catheter target point, and to acquire multiple catheter intervention paths based on the coordinates of the catheter target point, the real-time coordinates of the catheter tip, and the passable area. The fourth acquisition unit is used to execute step S54, specifically to acquire the host's immune status assessment value and acquire the immunosuppression coefficient based on the immune status assessment value. The fifth acquisition unit is used to execute step S55, specifically to acquire an operation compliance score value based on the operation behavior data, and to acquire an operation compliance reduction coefficient based on the operation compliance score value; The calculation unit is used to execute step S56, specifically to calculate the predicted infection risk value based on the catheter contamination probability value, immune status assessment value, immunosuppression coefficient, operation compliance score value, and operation compliance reduction coefficient, wherein the formula for calculating the predicted infection risk value is: ; in, Indicates elapsed time The estimated risk of infection Indicates time The risk value of medical device contamination Indicates the host immunosuppression coefficient. Indicates the host's immune value. This indicates the compliance reduction factor for operations. This indicates the operational compliance score.

[0030] As described above, this invention, by acquiring the real-time coordinates of the catheter tip, can clearly determine the current position of the catheter tip. The real-time coordinates refer to the three-dimensional spatial coordinates of the catheter tip obtained through real-time tracking. Then, combined with catheter performance data (such as bending radius, length, and maneuverability), the spatial range that the catheter can reach in its current state is obtained, thus obtaining the catheter-accessible area. This avoids "virtual paths" that deviate from the catheter's physical performance, ensuring the feasibility of path planning. Next, based on the bacterial distribution probability field, the operation area is divided into high-contamination risk areas, medium-contamination risk areas, and low-contamination risk areas. Then, high-contamination risk areas are removed from the catheter-accessible area, resulting in a passable area. By prioritizing low-risk paths within the limits of the catheter's physical performance, the problem of a sudden increase in operational difficulty due to blindly avoiding obstacles can be effectively avoided. Then, using the catheter target point coordinates as the endpoint (the coordinates of the catheter within the patient's body) and combining them with the real-time coordinates of the catheter tip as the starting point, multiple catheter intervention paths are generated within the passable area using the Dijkstra algorithm, resulting in a catheter intervention path set. Finally, the host's immune status assessment value and immunosuppression coefficient are obtained. This refers to a quantitative value of the strength of the host's immune function, comprehensively assessed through physiological indicators (such as white blood cell count, immunoglobulin level, and inflammatory factor concentration) and medical history information. The immunosuppression coefficient is a value used to quantify the degree of suppression of the host's immune function. The acquired data can fully consider the impact of the patient's own immune status on infection risk. Furthermore, the analysis of procedural data yields a procedural compliance score and a procedural compliance reduction coefficient. The procedural compliance score is a quantitative value obtained through a scoring system based on the degree to which the physician follows aseptic procedures (such as disinfection procedures, catheter indwelling time, and hand hygiene practices) during the procedure. The procedural compliance reduction coefficient is a numerical value used to quantify the reduction effect of compliant procedures on infection risk. These two data points fully consider the impact of procedural behavior on infection risk. Finally, the predicted infection risk is calculated based on the catheter contamination probability value, immune status assessment value, immunosuppression coefficient, procedural compliance score, and procedural compliance reduction coefficient. The above calculation formula is based on a multivariate risk weighted model based on the principles of infection epidemiology. Instrument contamination, host immunity, and procedural compliance are independent variables, corresponding to the three elements of the infection chain: "source of infection," "susceptible population," and "transmission route," respectively. The formula uses "..." This indicates that a higher catheter contamination probability value means a higher risk of carrying pathogens, directly increasing the probability of infection. " The lower the host immune status assessment value, the higher the susceptibility to infection. " The higher the operational compliance score (e.g., strict adherence to aseptic techniques and shortened operation time), the lower the risk of infection. Furthermore, the predicted risk of infection changes continuously over time and can be used for real-time intraoperative early warning.

[0031] In one embodiment, the fifth acquisition module is specifically configured to: The first acquisition unit is configured to perform step S61, and specifically configured to acquire key node coordinates and path curvature characteristics according to the optimal correction path, and acquire a correction direction vector according to the key node coordinates and the path curvature characteristics; The second acquisition unit is configured to perform step S62, and specifically configured to acquire a maximum propelling speed of the catheter and a minimum turning radius of the catheter according to the catheter performance data, and acquire a motion constraint vector according to the maximum propelling speed of the catheter, the minimum turning radius of the catheter, and the correction direction vector; The third acquisition unit is configured to perform step S63, and specifically configured to acquire AR guide information according to the motion constraint vector, and acquire visual feedback instructions according to the AR guide information; The fourth acquisition unit is configured to perform step S64, and specifically configured to acquire a correction intensity value according to the motion constraint vector, and acquire tactile feedback instructions according to the correction intensity value; The fifth acquisition unit is configured to perform step S65, and specifically configured to acquire operation state information according to the smart bracelet sensor, and acquire voice feedback instructions according to the operation state information, the visual feedback instructions, and the tactile feedback instructions.

[0032] As the function of each unit described above, the present application extracts the key node coordinates and path curvature features in the optimal correction path to quantify the spatial form and motion trend of the path, wherein the key node coordinates refer to the coordinate points with key spatial features in the optimal correction path, and the path curvature features refer to the bending degree and direction change characteristics of the optimal correction path, then the correction direction vector is obtained based on the key node coordinates and the path curvature features, wherein the correction direction vector refers to the vector parameter calculated based on the key node coordinates and the path curvature features, indicating the direction and angle that the front end of the catheter needs to adjust, then the maximum pushing speed of the catheter and the minimum turning radius of the catheter are obtained, wherein the maximum pushing speed of the catheter refers to the upper limit of the safe pushing speed determined by the physical performance of the catheter, which is used to limit the pushing speed of the catheter in the path, and the minimum turning radius of the catheter refers to the minimum curvature radius that the catheter can complete the turning in the curved path, which can measure the flexibility of the catheter, and is used to judge whether the curve in the path is within the allowable range of the instrument performance, then the motion constraint vector is obtained in combination with the above data, wherein the motion constraint vector refers to the multi-dimensional constraint condition formed by the correction direction vector, the maximum pushing speed of the catheter, the minimum turning radius and other parameters, which usually represents the allowed motion direction, speed range and turning amplitude in the form of a vector, and the motion constraint vector ensures that the catheter motion not only conforms to the path planning, but also does not exceed the performance boundary of the instrument, then based on the motion constraint vector, AR guidance information (such as virtual path projection, speed prompt arrow, safety area boundary) is generated and superimposed in the catheter intervention operation space through the AR device, then the correction intensity value is obtained according to the motion constraint vector, wherein the correction intensity value refers to the physical adjustment parameter obtained according to the motion constraint vector, indicating the magnitude of the force required to complete the direction or speed correction of the catheter, such as pushing force and rotating torque, and the abstract constraint condition can be converted into a perceptible physical parameter through the correction intensity value, and a tactile feedback instruction is output through a force feedback device (such as a smart bracelet), wherein the tactile feedback instruction refers to a physical perception signal output through the force feedback device, such as vibration, resistance change, force feedback pulse, etc., and through the tactile feedback instruction, the doctor can perceive the operation error and adjustment requirement through the hand touch, at the same time, the operation state information is obtained, wherein the operation state information refers to the information related to the execution of the visual feedback instruction and the tactile feedback instruction by the medical staff, and the speech feedback instruction is obtained in combination with the visual feedback instruction and the tactile feedback instruction, wherein the speech feedback instruction refers to the operation points prompted in real time through speech, such as “please reduce the pushing speed” and “the current path deviates”, so that full-range information coverage can be realized through the auditory channel, especially when the doctor's line of sight is limited or attention is distracted, timely reminders are provided to reduce the risk of human error, and through the above dynamic adjustment feedback strategy, the demand for operation correction in the catheter intervention operation process can be effectively met.

[0033] The application further provides a computer device comprising a memory and a processor, the memory storing a computer program, and the electronic device further comprises the catheter intervention operation dynamic correction system based on multi-modal feedback.

[0034] The application further provides a computer readable storage medium storing a computer program, and the electronic device further comprises the catheter intervention operation dynamic correction system based on multi-modal feedback.

[0035] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment system can be completed by a computer program instructing related hardware, and the computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments can be included. Any reference to memory, storage, database or other medium provided by the present application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM) and the like.

[0036] It should be noted that in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusions, so that processes, devices, articles or methods including a series of elements not only include those elements, but also include other elements not explicitly listed, or include elements inherent to such processes, devices, articles or methods. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, device, article or method including the element.

[0037] The above description is only preferred embodiments of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation using the content of the present application specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A dynamic correction system for catheter interventional procedures based on multimodal feedback, characterized in that, include: The first acquisition module is used to acquire multimodal monitoring data from the intelligent monitoring device, wherein the multimodal monitoring data includes catheter motion data, catheter performance data, operating space data, and operating behavior data; The second acquisition module is used to acquire the bacterial distribution probability field of the interventional operation space based on the catheter movement data and the operation space data. The extraction module is used to obtain multiple key trajectory feature points based on the bacterial distribution probability field and the operational behavior data; The third acquisition module is used to acquire the catheter contamination probability value based on the trajectory key feature points and the catheter motion data; The fourth acquisition module is used to acquire a set of catheter intervention paths based on the bacterial distribution probability field and the catheter performance data, wherein the set of catheter intervention paths includes multiple catheter intervention paths, and the infection risk prediction value of each catheter intervention path is acquired based on the catheter contamination probability value. The fifth acquisition module is used to acquire the optimal correction path based on the predicted infection risk value and the catheter intervention path set, and to acquire operation feedback instructions based on the optimal correction path and the catheter performance data.

2. The catheter intervention operation dynamic correction system based on multimodal feedback according to claim 1, characterized in that, The second acquisition module is specifically used for: The catheter contamination path information is obtained based on the catheter movement data and the operating space data; Based on the catheter contamination path information, contamination source information is obtained, wherein the contamination source information includes bacterial concentration, bacterial diffusion coefficient, and bacterial specific growth rate; The fluid velocity in the interventional operating space is obtained based on the airflow sensor, and the convective transport rate is obtained based on the fluid velocity and the bacterial concentration. The random diffusion rate is obtained based on the bacterial concentration and the bacterial diffusion coefficient, and the source term release rate is obtained based on the bacterial specific growth rate and the bacterial concentration. The bacterial distribution probability field is obtained based on the random diffusion rate, convective transport rate, and source term release rate.

3. The catheter intervention operation dynamic correction system based on multimodal feedback according to claim 1, characterized in that, The extraction module is specifically used for: Real-time operation data and historical operation data are obtained based on the operation behavior data, wherein the real-time operation data includes real-time operation speed and real-time operation direction change rate; Based on the catheter motion data, obtain the catheter spatial coordinates and catheter attitude angle data, and obtain the catheter three-dimensional motion trajectory based on the catheter spatial coordinates and catheter attitude angle data; The trajectory-probability field mapping grid is obtained based on the three-dimensional motion trajectory of the catheter and the bacterial distribution probability field. Trajectory feature determination data is obtained based on the historical operation data, wherein the trajectory feature determination data includes a motion speed threshold and a direction change rate threshold; The three-dimensional motion trajectory of the catheter is filtered according to the operation motion speed and the motion speed threshold to obtain multiple primary constraint feature points. Then, the multiple primary constraint feature points are filtered according to the operation direction change rate and the direction change rate threshold to obtain multiple trajectory key feature points.

4. The catheter intervention operation dynamic correction system based on multimodal feedback according to claim 3, characterized in that, The third acquisition module is specifically used for: Based on each of the trajectory key feature points and the trajectory-probability field mapping grid, obtain the corresponding key grid cell, and based on each key grid cell, obtain the feature point contamination probability value corresponding to each trajectory key feature point; Multiple key directed edges are obtained based on the key feature points of the trajectory, and the corresponding average contamination probability value is obtained based on the contamination probability value of each feature point and the key directed edge. The dwell time of multiple directed edges is obtained based on the duct motion data, and the dwell time of the path is obtained based on the dwell time of multiple directed edges. The conduit contamination probability value is obtained based on the average contamination probability value and the directed edge dwell time.

5. The catheter intervention operation dynamic correction system based on multimodal feedback according to claim 1, characterized in that, The fourth acquisition module is specifically used for: The real-time coordinates of the catheter tip are obtained based on the catheter motion data, and the reachable area of ​​the catheter is obtained based on the real-time coordinates of the catheter tip and the catheter performance data. The passable area is obtained based on the bacterial distribution probability field and the reachable area of ​​the duct. Obtain the target point coordinates of the catheter, and obtain multiple catheter intervention paths based on the target point coordinates, the real-time coordinates of the catheter tip, and the passable area; Obtain the host's immune status assessment value, and obtain the immunosuppression coefficient based on the immune status assessment value; An operation compliance score is obtained based on the operation behavior data, and an operation compliance reduction coefficient is obtained based on the operation compliance score. The predicted infection risk value is obtained based on the catheter contamination probability value, immune status assessment value, immunosuppression coefficient, operation compliance score value, and operation compliance reduction coefficient.

6. The catheter intervention operation dynamic correction system based on multimodal feedback according to claim 1, characterized in that, The fifth acquisition module is specifically used for: The key node coordinates and path curvature features are obtained based on the optimal correction path, and the correction direction vector is obtained based on the key node coordinates and path curvature features. The maximum advancement speed and minimum turning radius of the catheter are obtained based on the catheter performance data, and the motion constraint vector is obtained based on the maximum advancement speed, minimum turning radius of the catheter, and correction direction vector. AR guidance information is obtained based on the motion constraint vector, and visual feedback instructions are obtained based on the AR guidance information; The correction intensity value is obtained based on the motion constraint vector, and the tactile feedback command is obtained based on the correction intensity value; The smart bracelet obtains operation status information based on its sensors, and obtains voice feedback commands based on the operation status information, visual feedback commands, and tactile feedback commands.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, The electronic device further includes the catheter intervention operation dynamic correction system based on multimodal feedback as described in any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The electronic device further includes the catheter intervention operation dynamic correction system based on multimodal feedback as described in any one of claims 1 to 6.

Images