Slow-release drug delivery catheter

Abstract

The invention relates to a sustained-release administration catheter which comprises a catheter body, an upper port, a lower port, an air bag, an administration pump and a controller, local anesthetics are continuously administered through sustained-release micropores, surface anesthesia of tracheal catheters, urethral catheters or various drainage tubes is implemented, adverse reactions such as catheter drawing stimulation or burning pain of patients are relieved, and the sustained-release administration catheter is suitable for clinical application. Wherein the controller comprises a parameter real-time collection module which is used for acquiring physiological parameters such as the body temperature, the heart rate and the blood pressure of a patient through a temperature sensor and an electrocardiograph monitor, and a data processing module processes the data through a filter and a moving average method and evaluates the anesthesia state of the patient through standardization, feature extraction and a neural network algorithm. The anesthesia scheme generation module is used for generating a personalized anesthesia scheme by utilizing a self-adaptive control model according to an evaluation result and controlling the continuous administration module to inject anesthetics at a set rate, and the feedback adjustment module is used for dynamically adjusting the administration rate and dosage of the anesthetics according to real-time physiological parameters so as to ensure an optimal anesthesia state.

Description

Technical Field

[0001] The invention relates to the field of medical devices, in particular to a sustained-release drug delivery catheter. Background Art

[0002] When patients with general anesthesia and intubation wake up from anesthesia, they are prone to severe choking, increased blood pressure, increased heart rate, and increased intracranial pressure due to stimulation of the airway, urethra, or intestinal mucosa by the drug delivery catheter. The stress response during extubation in patients with hypertension is more likely to cause hypertension and induce serious complications, such as angina pectoris and myocardial infarction. During extubation of intracranial surgery patients, due to the recovery of the protective reflex of the upper airway, it is easy to have increased intracranial pressure and even intracranial hemorrhage, which threatens the patient's life.

[0003] The above discomfort reactions are generally eliminated by early tube removal, but this will increase the risk of patients in another way. At present, patients are usually kept asleep by continuous injection of sedatives, so that they can tolerate the tube; but the patient's long sleep state is not conducive to recovery, and the stimulation of the drug delivery catheter to the trachea or urethra will increase respiratory secretions and increase the chance of lung infection or urinary tract infection. Summary of the invention

[0004] The object of the present invention is to provide a sustained-release drug delivery catheter to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a sustained-release drug delivery catheter, comprising a tube body, an upper port, a lower port, an airbag, a drug delivery pump and a controller, wherein the upper port and the lower port are respectively arranged at both ends of the tube body, an airbag is installed on the surface of the tube body near the upper port, a temperature sensor is installed on one side of the airbag, an inflation tube and a sustained-release drug delivery tube are respectively connected to the surface of the tube body near the upper port, an inflation head is connected to one end of the inflation tube, a connecting tube is connected to one end of the sustained-release drug delivery tube, a filter head is installed at one end of the connecting tube, a delivery tube is connected to one end of the filter head, a chuck is installed on the surface of the delivery tube, one end of the delivery tube is connected to the output end of the drug delivery pump, a medicine box is connected to the input end of the drug delivery pump, a controller is installed on the surface of the drug delivery pump, a plurality of connecting grooves are evenly opened on the surface of one end of the tube body near the lower port, a drug delivery tube is installed inside the connecting groove, and a plurality of sustained-release micropores are evenly opened on the surface of the drug delivery tube; Specifically, a plurality of sustained-release micropores are provided on the wall of the drug delivery tube, and one end of the delivery tube is connected to the output end of the drug delivery pump. The local anesthetic can be added to the drug box connected to the drug delivery pump, and slowly released by the sustained-release micropores through the drug delivery tube, thereby implementing continuous surface anesthesia on the contact surface of the tube body, so that the patient can tolerate the catheter body and reduce adverse reactions. A medical hydrophilic coating is applied near the lower port surface and the airbag surface at one end of the tube body, and an anesthetic film is covered near the lower port surface and the airbag surface at one end of the tube body, wherein the surface of the anesthetic film alternately arranges two types of anesthetics, namely, acute-release anesthetics and sustained-release anesthetics, and a medical hydrophilic coating is applied to the lower port surface. Acute-release anesthetics can quickly achieve anesthesia to relieve the pain during intubation; sustained-release anesthetics are slowly released, and after the acute-release anesthetics are released, the maintenance time of the anesthetics is extended.

[0006] The controller is provided with a parameter real-time collection module, a data processing module, an anesthesia scheme generation module, a continuous drug delivery module and a feedback adjustment module. The parameter real-time collection module is used to obtain the real-time physiological parameters of the patient's body temperature, heart rate and blood pressure through a temperature sensor and an electrocardiogram monitor; the data processing module inputs the physiological parameters monitored by the parameter real-time collection module into the central control system, and analyzes the patient's condition through an algorithm; the anesthesia scheme generation module generates a personalized anesthesia scheme, including drug delivery rate and dosage, based on the analysis results of the data processing module, and the central control system generates a personalized anesthesia scheme; the continuous drug delivery module controls the drug delivery pump to continuously inject the anesthetic in the medicine box into the drug delivery tube at a set rate according to the scheme generated by the anesthesia scheme generation module, and delivers it into the patient's body through the sustained-release micropores; the feedback adjustment module dynamically adjusts the drug delivery rate and dosage of the anesthetic according to the physiological parameters monitored in real time by the central control system to ensure that the patient is in the best anesthesia state during the entire tracheal intubation process.

[0007] Preferably, the inflation tube is communicated with the airbag.

[0008] Preferably, the sustained-release drug delivery tube is connected to the connecting catheter via a threaded connector, and the sustained-release drug delivery tube is communicated with the drug delivery tube.

[0009] Preferably, the specific data processing steps of the data processing module are as follows: Step 1: First, filter the real-time physiological parameters of body temperature, heart rate, and blood pressure collected in the real-time collection module to eliminate the high-frequency noise in the signal, and use the moving average method to smooth the denoised data to improve the accuracy and reliability of the data; Step 2: Standardize the data processed in step 1, convert the data of different units and magnitudes into a unified format, specifically standardize the data to a distribution with a mean of 0 and a standard deviation of 1, and obtain preprocessed data; Step 3: Extract key features from the pre-processed data in step 2, including heart rate variability, temperature trend, and blood pressure fluctuation. The processing is as follows: Heart rate variability: HRV is calculated using both time domain and frequency domain methods. The time domain method is standard deviation SDNN:

[0010] in, is the time interval between adjacent heart beats, is the average time interval; Temperature change trend: calculate the slope of the temperature within the preset time. , slope It is expressed as:

[0011] Blood pressure fluctuation: The characteristics of blood pressure signal are extracted by wavelet transform. , wavelet transform It is expressed as:

[0012] in, is the wavelet function, and are the scale and displacement parameters respectively; Step 4: Use a neural network machine learning algorithm to analyze the feature parameters extracted in step 3 to evaluate the patient's current anesthesia state.

[0013] Preferably, the specific steps of using a neural network machine learning algorithm to analyze the characteristic parameters extracted in step 3 in step 4 are as follows: Step 41: Input feature parameters: Heart Rate Variability: ;Body temperature change trend: ; Blood pressure fluctuations ; Then the input vector of the input layer is: ; Step 42, select a number of hidden layers, each layer contains a number of neurons, and the input layer passes to the hidden layer as:

[0014] in, is a weight matrix, reflecting the importance and connection of each input feature; is the bias vector, used to adjust the output of the model; The output layer receives the output of the hidden layer and generates the final prediction result. The hidden layer passes it to the output layer as:

[0015] in, is a weight vector that specifies the influence of the hidden layer output on the final result; is a bias scalar used to further adjust the final output; Step 43: The neural network outputs the patient's current anesthesia status assessment result based on the input features and the trained weights and biases. .

[0016] Preferably, the anesthesia scheme generation module generates a personalized anesthesia scheme based on the analysis results of the data processing module, and the central control system generates an anesthesia scheme, wherein an adaptive control model is specifically used to generate the anesthesia scheme, and the specific implementation steps are as follows: Step S1, model identification: determine the adaptive control model: assume that the anesthesia effect index The change of is expressed by the following difference equation:

[0017] in, Indicates time Anesthesia effect index at the time of Indicates time The drug administration rate at are the adaptive control model parameters, Indicator of anesthetic effect Anesthetic effect on future moments The influence coefficient of Indicates drug delivery rate Anesthetic effect on future moments The influence coefficient of represents a constant term; Step S2: Parameter estimation: Use recursive least squares method to estimate model parameters using real-time data and , specifically: Positioning error: ; in, is the model's prediction: ; Recursive formula for updating parameters: ; The parameter vector is: ; Gain vector: ; State vector: Covariance matrix update: ,in Indicates time The covariance matrix at each moment is used for gain calculation in the recursive least squares method; Initial conditions: ; Step S3, control law design: according to the parameters estimated in step S2 and , design an adaptive control law to generate the drug delivery rate , to achieve optimal control of the patient's anesthetic state; specific expected anesthetic effect indicators , design the control law:

[0018] in, represents the control gain, which is set according to the control strategy; represents a compensation signal, which is used to further adjust the drug delivery rate; Specifically, the design of compensation signal: Assume error , compensation signal Designed for: ; The final control law is: .

[0019] Compared with the prior art, the present invention has the following beneficial effects: Compared with the drug-adding endotracheal tube, the present invention does not require temporary drug addition, can ensure constant anesthetic release at the optimal drug administration time point, make the drug efficacy more stable, and can completely control the choking reaction; the present invention controls the design of the drug administration pump through the controller provided, can avoid the situation that the medical staff forgets to administer the drug due to negligence, and avoids the temporary drug administration when the choking reaction is serious, which aggravates the choking reaction; The present invention can monitor the patient's physiological parameters in real time, and dynamically adjust the administration rate and dosage of anesthetics according to feedback information, so as to ensure that the patient is in a safe state during the entire anesthesia process and avoid the risks caused by over-anesthesia or under-anesthesia; it can provide individualized anesthesia plans according to the specific physiological parameters and anesthesia state of each patient, improve the anesthesia effect, and enable the patient to always maintain the best anesthesia depth and comfort during the operation; at the same time, the application of the advanced control algorithm of adaptive control makes the administration rate and dosage of anesthetics more accurate, and reduces the usage and side effects of anesthetics; The present invention can record and analyze a large amount of anesthesia process data, provide valuable data support for clinical research and improvement of anesthesia plans, and promote continuous improvement of anesthesia management; at the same time, the automated feedback adjustment system reduces the workload of anesthesiologists, allowing them to focus on more complex and urgent clinical decisions and optimize the workflow and efficiency of the operating room. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1It is a schematic diagram of the overall structure of the present invention; Figure 2 This is a schematic diagram of the enlarged structure of the drug delivery tube of the present invention; Figure 3 It is a schematic diagram of the structure of the controller system of the present invention; Figure 4 It is a schematic diagram of the working process of the data processing module of the present invention; Figure 5 A schematic diagram of anesthesia scheme flow chart is generated for the adaptive control model of the present invention.

[0021] In the figure: 1. tube body; 2. upper port; 3. lower port; 4. air bag; 5. drug delivery pump; 6. controller; 7. inflation tube; 8. inflation head; 9. sustained-release drug delivery tube; 10. threaded connector; 11. connecting catheter; 12. filter head; 13. delivery tube; 14. chuck; 15. medicine box; 16. temperature sensor; 17. connecting slot; 18. drug delivery tube; 19. sustained-release micropores. DETAILED DESCRIPTION

[0022] 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.

[0023] In the description of the present invention, it should be noted that the terms "vertical", "up", "down", "horizontal", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0024] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] Example 1 In order to be able to continuously perform surface anesthesia on the oral and pharyngeal surface mucosa that the endotracheal tube contacts when using the endotracheal tube, reduce patient discomfort and various adverse reactions caused thereby, and reduce accidents caused thereby, the multifunctional endotracheal tube for sustained-release drug delivery for endotracheal tube, please refer to Figure 1-2 The present invention provides a technical solution: a sustained-release drug delivery catheter, comprising a tube body 1, an upper port 2, a lower port 3, an air bag 4, a drug delivery pump 5 and a controller 6, wherein the upper port 2 and the lower port 3 are respectively arranged at both ends of the tube body 1, an air bag 4 is installed on one end of the surface of the tube body 1 near the upper port 2, a temperature sensor 16 is installed on one side of the surface of the air bag 4, an inflation tube 7 and a sustained-release drug delivery tube 9 are respectively connected at the surface of the tube body 1 near the upper port 2, wherein the inner diameter of the sustained-release drug delivery tube 9 is very small, much smaller than the inner diameter of the connecting tube 11, and its inner diameter size is about the same as that of a hair In other words, one end of the inflation tube 7 is connected to an inflation head 8, and the inflation head 8 is connected to the inflation tube 7 through a threaded connector 10, and the inflation tube 7 is connected to the airbag 4. One end of the sustained-release drug delivery tube 9 is connected to a connecting catheter 11, and the sustained-release drug delivery tube 9 is connected to the connecting catheter 11 through a threaded connector 10, and the sustained-release drug delivery tube 9 is connected to the drug delivery tube 18. Since the inner diameter of the sustained-release drug delivery tube 9 is very small, it is very easy to be blocked by impurities in the drug solution. In order to avoid the slow-release drug delivery tube 9 from being blocked and unable to deliver the drug normally, the connecting catheter 11 can also be provided with the following Figure 1 The filter head 12 shown in the figure has a delivery tube 13 connected to one end of the filter head 12, a chuck 14 is installed on the surface of the delivery tube 13, one end of the delivery tube 13 is connected to the output end of the dosing pump 5, and the input end of the dosing pump 5 is connected to a medicine box 15, wherein the medicine box 15 connected to the dosing pump 5 is filled with anesthetics of suitable concentration, such as 1% lidocaine, 0.3% ropivacaine, etc., and a controller 6 is installed on the surface of the dosing pump 5. A plurality of connecting passages are evenly opened on the surface of the tube body 1 near the lower opening 3. Groove 17, connected through groove 17 is installed with drug delivery tube 18, and several slow-release micropores 19 are evenly opened on the surface of drug delivery tube 18. Anesthetics in medicine box 15 are released from slow-release micropores 19 and contact with the mucous membrane of oral pharynx and throat, so as to implement anesthesia on the surface of the sticky tracheal tube membrane contacting the head section of tube body 1, so as to prevent the upward conduction of harmful nerve impulses, improve the patient's comfort, and be able to tolerate the existence of tracheal tube body 1, reduce resistance, vomiting, cardiovascular reaction and local friction damage. In order to ensure the uniform release of local anesthetics, the aperture of several slow-release micropores 19 of drug delivery tube 18 should be small and evenly distributed.

[0026] The surface of the lower port 3 and the airbag 4 is coated with a medical hydrophilic coating. On the one hand, the super-slippery characteristics of the hydrophilic coating are used to reduce the friction of the endotracheal tube body 1 when it is inserted into the patient's oral and pharyngeal cavity, thereby reducing damage; on the other hand, the hydrophilic coating endotracheal tube has a super strong affinity for liquid, which promotes the drug solution released by the sustained-release micropores 21 to quickly and evenly diffuse to the entire circumferential surface of the endotracheal tube at the head section of the tube body 1.

[0027] Example 2 See also Figure 3-5 , the controller 6 is provided with a parameter real-time collection module, a data processing module, an anesthesia scheme generation module, a continuous drug administration module and a feedback adjustment module; The parameter real-time collection module is used to obtain the patient's real-time physiological parameters of body temperature, heart rate, and blood pressure through the temperature sensor 16 and the ECG monitor; The data processing module inputs the physiological parameters monitored by the real-time parameter collection module into the central control system and analyzes the patient's condition through algorithms; The specific data processing steps of the data processing module are as follows: Step 1: First, filter the real-time physiological parameters of body temperature, heart rate, and blood pressure collected in the real-time collection module to eliminate the high-frequency noise in the signal, and use the moving average method to smooth the denoised data to improve the accuracy and reliability of the data; Step 2: Standardize the data processed in step 1, convert the data of different units and magnitudes into a unified format, specifically standardize the data to a distribution with a mean of 0 and a standard deviation of 1, and obtain preprocessed data; Step 3: Extract key features from the pre-processed data in step 2, including heart rate variability, temperature trend, and blood pressure fluctuation. The processing is as follows: Heart rate variability: HRV is calculated using both time domain and frequency domain methods. The time domain method is standard deviation SDNN:

[0028] in, is the time interval between adjacent heart beats, is the average time interval; Temperature change trend: calculate the slope of the temperature within the preset time. , slope It is expressed as:

[0029] Blood pressure fluctuation: The characteristics of blood pressure signal are extracted by wavelet transform. , wavelet transform It is expressed as:

[0030] in, is the wavelet function, and are the scale and displacement parameters respectively; Step 4: Use a neural network machine learning algorithm to analyze the feature parameters extracted in step 3 to evaluate the patient's current anesthesia state.

[0031] The specific steps of using the neural network machine learning algorithm in step 4 to analyze the feature parameters extracted in step 3 are as follows: Step 41: Input feature parameters: Heart Rate Variability: ;Body temperature change trend: ; Blood pressure fluctuations ; Then the input vector of the input layer is: ; Step 42, select a number of hidden layers, each layer contains a number of neurons, and the input layer passes to the hidden layer as:

[0032] in, is a weight matrix, reflecting the importance and connection of each input feature; is the bias vector, used to adjust the output of the model; The output layer receives the output of the hidden layer and generates the final prediction result. The hidden layer passes it to the output layer as:

[0033] in, is a weight vector that specifies the influence of the hidden layer output on the final result; is a bias scalar used to further adjust the final output; Step 43: The neural network outputs the patient's current anesthesia status assessment result based on the input features and the trained weights and biases. .

[0034] Through the above steps and algorithms, the neural network can effectively evaluate the patient's anesthetic status during tracheal intubation and dynamically adjust the administration rate and dosage of anesthetics based on the evaluation results.

[0035] The anesthesia plan generation module generates a personalized anesthesia plan, including the drug administration rate and dosage, based on the analysis results of the data processing module. The anesthesia plan generation module generates a personalized anesthesia plan based on the analysis results of the data processing module. The central control system uses an adaptive control model to generate anesthesia plans. The specific implementation steps are as follows: Step S1, model identification: determine the adaptive control model: assume that the anesthesia effect index The change of is expressed by the following difference equation:

[0036] in, Indicates time Anesthesia effect index at the time of Indicates time The drug administration rate at are the adaptive control model parameters, Indicator of anesthetic effect Anesthetic effect on future moments The influence coefficient of Indicates drug delivery rate Anesthetic effect on future moments The influence coefficient of represents a constant term; Step S2: Parameter estimation: Use recursive least squares method to estimate model parameters using real-time data and , specifically: Positioning error: ; in, is the model's prediction: ; Recursive formula for updating parameters: ; The parameter vector is: ; Gain vector: ; State vector: Covariance matrix update: ,in Indicates time The covariance matrix at each moment is used for gain calculation in the recursive least squares method; Initial conditions: ; Step S3, control law design: according to the parameters estimated in step S2 and , design an adaptive control law to generate the drug delivery rate , to achieve optimal control of the patient's anesthetic state; specific expected anesthetic effect indicators , design the control law:

[0037] in, represents the control gain, which is set according to the control strategy; represents a compensation signal, which is used to further adjust the drug delivery rate; Specifically, the design of compensation signal: Assume error , compensation signal Designed for: ; The final control law is: .

[0038] Through the above steps, the adaptive control model can dynamically generate and adjust the anesthesia plan according to the anesthesia status evaluation results output by the neural network to ensure the safety and comfort of the patient during tracheal intubation.

[0039] The continuous drug delivery module controls the drug delivery pump 5 to continuously inject the anesthetic in the drug box 15 into the drug delivery tube 18 at a set rate according to the plan generated by the anesthesia plan generation module, and then delivers the anesthetic into the patient's body through the slow-release micropores 19; The feedback adjustment module dynamically adjusts the administration rate and dosage of anesthetics according to the physiological parameters monitored in real time by the central control system to ensure that the patient is in the best anesthesia state during the entire tracheal intubation process. The specific process of the feedback adjustment module includes the following steps: A. Real-time monitoring of physiological parameters: First, through the real-time parameter collection module, the temperature sensor 16 and the ECG monitor obtain the patient's real-time physiological parameters of body temperature, heart rate, and blood pressure; B. Data processing and analysis: The monitored physiological parameters are preprocessed and analyzed by the data processing module, and the current anesthesia state is evaluated by using the neural network algorithm, and the anesthesia state evaluation result is output. The specific processing steps are described in detail above; C. Adjust the control strategy: According to the evaluation results, dynamically adjust the anesthetic drug administration strategy. This step mainly depends on the control algorithm, specifically adaptive control, including the following: Adaptive Control The adaptive control algorithm automatically adjusts the control parameters according to real-time data to adapt to the dynamic changes of the system. The steps include: Error calculation: calculate the error between the current anesthesia effect and the expected effect; Parameter estimation: Use real-time data to update neural network algorithm model parameters; Control law adjustment: According to the error and updated neural network algorithm model parameters, the control law is adjusted to generate a new drug delivery rate; D. Dynamically adjust the drug administration rate and dosage: According to the adjusted control strategy, the control parameters of the drug administration pump 5, that is, the drug administration rate and dosage of the anesthetic, are changed in real time to ensure that the patient's physiological parameters remain within a safe range and the anesthesia state is at an optimal level; E. Continuous feedback and optimization: Feedback adjustment is a continuous process. The real-time parameter collection module continuously monitors physiological parameters, evaluates the anesthesia state, and adjusts the control strategy based on the feedback information. This closed-loop control system ensures the effectiveness and reliability of real-time adjustment.

[0040] Through the above feedback adjustment process, the anesthesia process can be effectively managed and regulated to ensure the safety and comfort of the patient during endotracheal intubation.

[0041] Compared with the drug-adding endotracheal tube, the present invention does not require temporary drug addition, can ensure constant anesthetic release at the optimal drug administration time point, make the drug efficacy more stable, and can completely control the choking reaction; the present invention controls the design of the drug administration pump through the controller provided, can avoid the situation that the medical staff forgets to administer the drug due to negligence, and avoids the temporary drug administration when the choking reaction is serious, which aggravates the choking reaction; The present invention can monitor the patient's physiological parameters in real time, and dynamically adjust the administration rate and dosage of anesthetics according to feedback information, so as to ensure that the patient is in a safe state during the entire anesthesia process and avoid the risks caused by over-anesthesia or under-anesthesia; it can provide individualized anesthesia plans according to the specific physiological parameters and anesthesia state of each patient, improve the anesthesia effect, and enable the patient to always maintain the best anesthesia depth and comfort during the operation; at the same time, the application of the advanced control algorithm of adaptive control makes the administration rate and dosage of anesthetics more accurate, and reduces the usage and side effects of anesthetics; The present invention can record and analyze a large amount of anesthesia process data, provide valuable data support for clinical research and improvement of anesthesia plans, and promote continuous improvement of anesthesia management; at the same time, the automated feedback adjustment system reduces the workload of anesthesiologists, allowing them to focus on more complex and urgent clinical decisions and optimize the workflow and efficiency of the operating room.

[0042] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A sustained-release drug delivery catheter, comprising a tube body (1), an upper opening (2), a lower opening (3), an air bag (4), a drug delivery pump (5) and a controller (6), characterized in that: The two ends of the tube body (1) are respectively provided with an upper opening (2) and a lower opening (3); an air bag (4) is installed on the surface of the tube body (1) at one end close to the upper opening (2); a temperature sensor (16) is installed on one side of the surface of the air bag (4); an inflation tube (7) and a sustained-release drug delivery tube (9) are respectively connected to the surface of the tube body (1) close to the upper opening (2); one end of the inflation tube (7) is connected to an inflation head (8); one end of the sustained-release drug delivery tube (9) is connected to a connecting conduit (11); one end of the connecting conduit (11) is installed with a filter head (12); the filter head One end of the tube body (12) is connected to a delivery tube (13), a chuck (14) is installed on the surface of the delivery tube (13), one end of the delivery tube (13) is connected to the output end of the drug delivery pump (5), the input end of the drug delivery pump (5) is connected to a medicine box (15), a controller (6) is installed on the surface of the drug delivery pump (5), one end of the tube body (1) is evenly provided with a plurality of connecting grooves (17) on the surface near the lower opening (3), a drug delivery tube (18) is installed inside the connecting groove (17), and a plurality of sustained-release micropores (19) are evenly provided on the surface of the drug delivery tube (18).

2. A sustained-release drug delivery catheter according to claim 1, characterized in that: The inflation tube (7) is in communication with the air bag (4).

3. A sustained-release drug delivery catheter according to claim 1, characterized in that: The sustained-release drug delivery tube (9) is connected to the connecting conduit (11) via a threaded connector (10), and the sustained-release drug delivery tube (9) is in communication with the drug delivery tube (18).

4. A sustained-release drug delivery catheter according to claim 1, characterized in that: A medical hydrophilic coating is applied on the surface of one end of the tube body (1) close to the lower opening (3) and the surface of the air bag (4).

5. The sustained-release drug delivery catheter according to claim 1, characterized in that: The controller (6) is provided with a parameter real-time collection module, a data processing module, an anesthetic scheme generation module, a continuous drug delivery module and a feedback adjustment module. The parameter real-time collection module is used to obtain the real-time physiological parameters of the patient's body temperature, heart rate and blood pressure through a temperature sensor (16) and an electrocardiogram monitor; the data processing module inputs the physiological parameters monitored by the parameter real-time collection module into the central control system and analyzes the patient's condition through an algorithm; the anesthetic scheme generation module generates a personalized anesthetic scheme, including a drug delivery rate and dosage, based on the analysis results of the data processing module; the continuous drug delivery module controls the drug delivery pump (5) to continuously inject the anesthetic in the drug box (15) into the drug delivery tube (18) at a set rate according to the scheme generated by the anesthetic scheme generation module, and then delivers the anesthetic into the patient's body through the sustained-release micropores (19); the feedback adjustment module dynamically adjusts the drug delivery rate and dosage of the anesthetic according to the physiological parameters monitored in real time by the central control system to ensure that the patient is in the best anesthetic state during the entire tracheal intubation process.

6. A sustained-release drug delivery catheter according to claim 5, characterized in that: The specific data processing steps of the data processing module are as follows: Step 1: First, filter the real-time physiological parameters of body temperature, heart rate, and blood pressure collected in the real-time collection module to eliminate the high-frequency noise in the signal, and use the moving average method to smooth the denoised data to improve the accuracy and reliability of the data; Step 2: Standardize the data processed in step 1, convert the data of different units and magnitudes into a unified format, specifically standardize the data to a distribution with a mean of 0 and a standard deviation of 1, and obtain preprocessed data; Step 3: Extract key features from the pre-processed data in step 2, including heart rate variability, temperature change trend, and blood pressure fluctuation. The processing is as follows: Heart rate variability: HRV is calculated using both time domain and frequency domain methods. The time domain method is standard deviation SDNN: in, is the time interval between adjacent heart beats, is the average time interval; Temperature change trend: calculate the slope of the temperature within the preset time. , slope It is expressed as: Blood pressure fluctuation: The characteristics of blood pressure signal are extracted by wavelet transform. , wavelet transform It is expressed as: in, is the wavelet function, and are the scale and displacement parameters respectively; Step 4: Use a neural network machine learning algorithm to analyze the feature parameters extracted in step 3 to evaluate the patient's current anesthesia state.

7. A sustained-release drug delivery catheter according to claim 6, characterized in that: The specific steps of using the neural network machine learning algorithm to analyze the characteristic parameters extracted in step 3 in step 4 are as follows: Step 41: Input feature parameters: Heart Rate Variability: ;Body temperature change trend: ; Blood pressure fluctuations ; Then the input vector of the input layer is: ; Step 42, select a number of hidden layers, each layer contains a number of neurons, and the input layer passes to the hidden layer as: in, is a weight matrix, reflecting the importance and connection of each input feature; is the bias vector, used to adjust the output of the model; The output layer receives the output of the hidden layer and generates the final prediction result. The hidden layer passes it to the output layer as: in, is a weight vector that specifies the influence of the hidden layer output on the final result; is a bias scalar used to further adjust the final output; Step 43: The neural network outputs the patient's current anesthesia status assessment result based on the input features and the trained weights and biases. .

8. The sustained-release drug delivery catheter according to claim 5, characterized in that: The anesthesia scheme generation module generates a personalized anesthesia scheme based on the analysis results of the data processing module, and the central control system generates an anesthesia scheme, wherein an adaptive control model is specifically used to generate the anesthesia scheme, and the specific implementation steps are as follows: Step S1, model identification: determine the adaptive control model: assume that the anesthesia effect index The change of is expressed by the following difference equation: in, Indicates time Anesthesia effect index at the time of Indicates time The drug administration rate at are the adaptive control model parameters, Indicator of anesthetic effect Anesthetic effect on future moments The influence coefficient of Indicates drug delivery rate Anesthetic effect on future moments The influence coefficient of represents a constant term; Step S2: Parameter estimation: Use recursive least squares method to estimate model parameters using real-time data and , specifically: Positioning error: ; in, is the model's prediction: ; Recursive formula for updating parameters: ; The parameter vector is: ; Gain vector: ; State vector: Covariance matrix update: ,in Indicates time The covariance matrix at each moment is used for gain calculation in the recursive least squares method; Initial conditions: ; Step S3, control law design: according to the parameters estimated in step S2 and , design an adaptive control law to generate the drug delivery rate , to achieve optimal control of the patient's anesthetic state; specific expected anesthetic effect indicators , design the control law: in, represents the control gain, which is set according to the control strategy; represents a compensation signal, which is used to further adjust the drug delivery rate; Specifically, the design of compensation signal: Assume error , compensation signal Designed for: ; The final control law is: .

Images