Pain perception adaptive analgesic drug automatic control device
Through the pain-aware automatic control device of automatic analgesic drugs, the use of data collection and status prediction technology to adjust the drug dosage in real time, solving the problems of poor treatment effects and side effects in existing pain management methods, realizing personalized and safe , efficient pain management.
Patent Information
- Application Number
- CN202311355736.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-19
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2043-10-19
AI Technical Summary
Existing pain management methods rely on the clinical experience of doctors and subjective patient reports, and the inability to adjust the dose of drugs in real time, resulting in poor treatment effects or side effects, and lack of personalized treatment.
Using pain awareness-adaptive automatic control device, the patient's physiological data is monitored in real time through data collection, status prediction and drug regulation and transmission parts, establish status space and drug model, and automatically adjust the dose of analgesic drugs according to the patient's physiology. Personalized regulation of status and pain levels.
It realizes personalized, safe and efficient pain management, improves treatment effect and patient quality of life, reduces unnecessary side effects and abuse of drugs, and ensures real-time and accuracy of pain management.
Smart Images

Figure CN117219226B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of drug delivery, and in particular relates to an automatic control device for analgesic drugs with self-adaptation to pain perception. Background Art
[0002] Pain management has always been an important challenge in the medical field. Patients may experience pain for various reasons, including postoperative pain, traumatic pain, cancer-related pain, and chronic pain caused by chronic diseases. In order to relieve patients' pain, the medical community has adopted a variety of treatment methods, including the use of analgesics. However, there are still some problems with existing pain management methods, which may cause discomfort to patients and poor treatment effects.
[0003] Existing pain management methods mainly rely on the clinical experience of doctors and the subjective reports of patients. Doctors usually decide on treatment plans, including drug selection and dosage, based on the patient's medical history, symptoms and pain level. This approach has some obvious limitations: Pain is a subjective feeling, and patients' subjective reports may be affected by emotions, cultural background and psychological factors, so they may not be accurate enough. Existing methods usually apply treatment plans to patients once and for all, without considering changes in the patient's physiological state and pain level. The abuse and dependence of analgesics have attracted widespread attention. Existing methods have failed to effectively address this problem. Even after the start of treatment, the patient's physiological state and pain level may change. However, existing methods are usually unable to adjust the drug dosage in real time, which may result in poor analgesia or unnecessary side effects of the drug. The physiological state and response vary greatly between patients, but existing methods often adopt a "one size fits all" approach and fail to provide personalized treatment. Summary of the invention
[0004] The main purpose of the present invention is to provide an automatic analgesic drug control device that is adaptive to pain perception. The present invention adopts adaptive analgesic treatment technology, and through real-time monitoring of patient physiological data, state prediction and personalized drug control, it realizes personalized, safe and efficient pain management, thereby improving the treatment effect and the quality of life of patients.
[0005] In order to solve the above problems, the technical solution of the present invention is achieved as follows:
[0006] Provided is a pain perception adaptive analgesic drug automatic control device, the device comprising: a data acquisition part, a state prediction part and a drug control delivery part; the data acquisition part is configured to acquire the patient's physiological data within a set time period, and calculate the pain level corresponding to the physiological data at each moment based on the physiological data; the state prediction part is configured to establish the patient's state space based on the physiological data, each state in the state space corresponds to the pain level at a moment, construct a state transition probability matrix between states in the state space, define the initial state probability distribution, observation model and observation probability distribution, calculate the forward probability and backward probability, perform state prediction based on the forward probability and backward probability, and obtain the state prediction result; the drug control delivery part is configured to deliver the analgesic drug of the dose corresponding to the probability state prediction result to the patient based on the state prediction result, and during the delivery process, send a control instruction to the data acquisition part to acquire the patient's real-time physiological data, and adjust the dose of the analgesic drug delivered to the patient according to the real-time physiological data.
[0007] Furthermore, the physiological data or real-time physiological data collected by the data collection part at least include: body temperature, heart rate, respiratory rate, blood pressure and analgesic drug concentration.
[0008] Furthermore, the state prediction part is based on physiological data to establish the patient's state space as:
[0009] ;
[0010] in represents the state space; Represents at the moment Status; The total number of moments in the set time period;
[0011] The constructed state transition probability matrix is ; Each element in the state transition probability matrix is:
[0012] ;
[0013] in Represents the state Transfer to state probability; and All are subscripts, with a value range of 1 to integer;
[0014] The initial state probability distribution is defined as:
[0015] ;
[0016] in Indicates at time When the status is probability;
[0017] The observation model is defined as:
[0018] ;
[0019] in represents the set of observations, Represents at the moment Observed value of
[0020] The observation probability is defined using the following formula:
[0021] ;
[0022] in, is the observation probability distribution, indicating that in a given state Observed to Observed The probability of Representation status The mean vector of the multidimensional Gaussian distribution under ; Representation status The covariance matrix of the multidimensional Gaussian distribution under , is its inverse matrix; is the covariance matrix The determinant of , which represents the uncertainty of the observations.
[0023] Furthermore, the state prediction part uses the following formula to calculate the forward probability:
[0024] ;
[0025] in, Indicates at time In state The forward probability of Indicates at time In state The forward probability of .
[0026] Furthermore, the state prediction part uses the following formula to calculate the backward probability:
[0027] ;
[0028] in, Indicates at time In state The backward probability of Indicates at time In state The backward probability of .
[0029] Furthermore, the state prediction part uses the following formula to perform state prediction based on the forward probability and the backward probability to obtain a state prediction result:
[0030] ;
[0031] Indicates at time In state The state prediction results.
[0032] Furthermore, the method for adjusting the dosage of the analgesic drug delivered to the patient according to the real-time physiological data by the drug regulation and delivery part includes: constructing a diffusion model, a release model and a metabolism model of the analgesic drug in the patient's body; setting an objective function based on the diffusion model, the release model and the metabolism model, wherein the optimization goal of the objective function is to minimize the dosage of the analgesic drug that eventually enters the patient's body while ensuring that the patient's pain level is reduced to below a set threshold; setting a time at which Real-time physiological data is collected at the same time, and the dose of analgesic delivered to the patient is based on the state prediction results. ; According to the pain level corresponding to the real-time physiological data, the dosage of analgesic drugs delivered to the patient at each moment is calculated through the constraints of the objective function. ; At each moment, deliver to the patient Dosage of analgesics.
[0033] Furthermore, the diffusion model is expressed using the following formula:
[0034] ;
[0035] in, is the diffusion coefficient, is the Laplace operator, is the nonlinear diffusion coefficient; is time; the release model is expressed using the following formula:
[0036] ;
[0037] in, is the release rate; is the surface area of the analgesic drug; is the saturated solubility, which is the set value; is the rate of dissolution of the analgesic drug;
[0038] The drug metabolism model is expressed using the following formula:
[0039] ;
[0040] in, is the metabolic rate; is the maximum metabolic rate, which is the set value; is the Michaelis constant.
[0041] Furthermore, the objective function is expressed using the following formula:
[0042] ;
[0043] in, is the objective function; the total time spent delivering analgesic medication to the patient;
[0044] The constraints are:
[0045] ;
[0046] in, The pain level corresponding to the real-time physiological data; is the set threshold.
[0047] Furthermore, based on the physiological data or real-time physiological data, the formula for calculating the pain level corresponding to the physiological data at each moment is:
[0048] ;
[0049] in, is the pain level; It is the difference between body temperature and standard value, in degrees Celsius; It is the difference between the heart rate and the standard value; It is the difference between the respiratory rate and the standard value of the respiratory rate; It is the difference between blood pressure and standard blood pressure value, in units of: The concentration of analgesic drugs is: ; and are weight coefficients, which are set values.
[0050] The pain perception adaptive analgesic automatic control device of the present invention has the following beneficial effects: In the present invention, the state prediction part establishes a state space by collecting and analyzing the patient's physiological data, in which each state corresponds to the pain level at a moment. This state space also includes a state transition probability matrix between states, an observation model and an observation probability distribution. This complex mathematical model provides a scientific basis for treatment. The function of the state prediction part is to monitor the patient's physiological state in real time and adjust the drug dosage according to the state prediction results. This means that treatment is no longer a one-time solution, but is adjusted according to the actual needs of the patient. The accuracy and real-time nature of state prediction help to provide personalized pain management to the greatest extent, ensuring that each patient obtains the best treatment effect. The drug control delivery part of the present invention delivers analgesic drugs of a dose corresponding to the state prediction results to the patient based on the state prediction results. During the delivery process, it also sends control instructions to the data acquisition part to collect the patient's real-time physiological data, and then adjusts the drug dosage according to these real-time data. The function of this part is to convert the theory of state prediction into actual treatment actions. By continuously monitoring the patient's physiological data, it can respond immediately when the pain level changes. This means that patients do not have to wait for the pain to intensify before they can get effective treatment, nor do they have to worry about overdose or underdose. The optimization of the drug regulation and delivery part improves the effectiveness and safety of treatment. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 A schematic diagram of the structure of a pain perception adaptive analgesic drug automatic control device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0052] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.
[0053] The following are detailed descriptions of each.
[0054] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein.
[0055] Example 1: Reference Figure 1 , a pain perception adaptive analgesic drug automatic control device, the device includes: a data acquisition part, a state prediction part and a drug control delivery part; the data acquisition part is configured to collect the patient's physiological data within a set time period, and calculate the pain level corresponding to the physiological data at each moment based on the physiological data; the state prediction part is configured to establish the patient's state space based on the physiological data, each state in the state space corresponds to the pain level at a moment, construct a state transition probability matrix between states in the state space, define the initial state probability distribution, observation model and observation probability distribution, calculate the forward probability and backward probability, perform state prediction based on the forward probability and backward probability, and obtain the state prediction result; the drug control delivery part is configured to deliver the analgesic drug of the dose corresponding to the probability state prediction result to the patient based on the state prediction result, and during the delivery process, send a control instruction to the data acquisition part to collect the patient's real-time physiological data, and adjust the dose of the analgesic drug delivered to the patient according to the real-time physiological data.
[0056] Specifically, first, the state prediction part uses the patient's physiological data to build a state space. The state space is a mathematical model that represents different states or situations. Here, each state represents the pain level at a specific moment. This establishment process can use statistical methods or machine learning techniques to map physiological data to pain levels. Once the state space is established, the state transition probability matrix is constructed next. This matrix describes the probability of the pain level transitioning from one state to another at different moments. These probabilities can be calculated based on historical data or model assumptions. The state transition probability matrix can help the system understand the relationship and transformation rules between different states. In order to connect physiological data with the state space, it is necessary to define an observation model and an observation probability distribution. The observation model describes the probability of observing specific physiological data in a given state. The observation probability distribution represents the probability distribution of physiological data in different states. In order to perform state prediction, the forward probability and backward probability calculation methods are used. The forward probability calculates the probability that the patient is in different states at the current moment given the observation data. The backward probability calculates the probability that the patient is in different states at the future moment given the observation data. Based on the calculation results of the forward probability and backward probability, the system can perform state prediction. This means that the system can estimate the pain level at future moments based on known physiological data and the state-space model. This prediction can be used to decide whether the dosage of analgesic medication needs to be adjusted.
[0057] By predicting the patient's pain level, the system can provide personalized treatment, ensuring that the patient receives the appropriate dose of analgesics at different times. This helps to minimize pain relief while minimizing the adverse effects of the medication. Because the state prediction is based on real-time physiological data, the system can automatically adjust the treatment strategy at any time. This means that if the patient's pain level suddenly increases, the system can respond quickly and provide more analgesics. By accurately predicting the patient's pain level, the system can reduce unnecessary medication use. This is very important to avoid drug abuse and dependence problems.
[0058] Embodiment 2: The physiological data or real-time physiological data collected by the data collection part at least include: body temperature, heart rate, respiratory rate, blood pressure and analgesic drug concentration.
[0059] Specifically, body temperature is a key indicator of a patient's physiological state. Abnormal body temperature can indicate fever or other health problems, which may lead to changes in pain levels. By monitoring body temperature, the system can detect potential problems in a timely manner and adjust treatment strategies accordingly. Heart rate is the number of times the heart beats per minute. A changing heart rate may reflect the patient's pain state because pain can cause the heart rate to increase. Monitoring heart rate helps determine the degree of pain and the physiological impact of pain on the patient. Respiratory rate indicates the number of breaths per minute. Pain can cause breathing to become faster or slower, so monitoring respiratory rate can provide information about the degree of pain. It also helps identify possible breathing-related problems. Blood pressure is the pressure of blood in blood vessels. Pain can cause blood pressure to rise or fall, which is crucial to understanding the patient's pain state and systemic response. Both high and low blood pressure can affect pain perception and processing. Monitoring the concentration of analgesic drugs is very important because it directly affects the effectiveness and safety of treatment. Ensuring that the appropriate drug concentration level is maintained helps avoid excessive or insufficient analgesia, thereby providing optimal pain management.
[0060] Embodiment 3: The state prediction part is based on physiological data, and the state space of the patient is established as:
[0061] ;
[0062] in represents the state space; Represents at the moment Status; The total number of moments in the set time period;
[0063] The constructed state transition probability matrix is ; Each element in the state transition probability matrix is:
[0064] ;
[0065] in Represents the state Transfer to state probability; and All are subscripts, with a value range of 1 to integer;
[0066] The initial state probability distribution is defined as:
[0067] ;
[0068] in Indicates at time When the status is probability;
[0069] The observation model is defined as:
[0070] ;
[0071] in represents the set of observations, Represents at the moment Observed value of
[0072] The observation probability is defined using the following formula:
[0073] ;
[0074] in, is the observation probability distribution, indicating that in a given state Observed to Observed The probability of Representation status The mean vector of the multidimensional Gaussian distribution under ; Representation status The covariance matrix of the multidimensional Gaussian distribution under , is its inverse matrix; is the covariance matrix The determinant of , which represents the uncertainty of the observations.
[0075] Specifically, in this embodiment, the state space It is a collection of multiple states, used to represent the patient at different times Each state in the state space is Corresponding to the pain level at a specific moment. In this way, the system can model the patient's state discretely for subsequent state prediction and analgesic drug regulation. State transition probability matrix Used to describe a state from Transfer to another state The probability of . Each element of this matrix Indicates that at the time Next, from the state Transfer to state This is a key mathematical tool for establishing relationships between states and predicting changes in the patient's state. Describes the moment Patients are in different states The probability distribution of . It represents the system's estimate of the patient's initial state. This is very important for the initial state prediction.
[0076] Observation Model Include Observations , these observations represent different The observation model is used to transform the state and observations connected so that the system can update its state predictions based on observations. Describes the given state Observed value Here, a multidimensional Gaussian distribution is used to model the observed probability distribution, including the mean vector and the covariance matrix The observation probability distribution is used to evaluate the likelihood of observations under different states, thus providing important information for state prediction.
[0077] The observation probability formula uses a multidimensional Gaussian distribution to model the observation probability. The multidimensional Gaussian distribution is a commonly used probability distribution used to describe the joint probability distribution of multiple continuous random variables. Here, the observation value is regarded as a multidimensional random variable. The observation probability formula includes two key parameters, namely the mean vector and the covariance matrix The mean vector Indicates in status The covariance matrix is the average of the observations under It represents the uncertainty and correlation of the observations, and describes the covariance between the observations. The core of the observation probability formula is the probability density function of the Gaussian distribution. The Gaussian distribution function measures the observed values. In a given state Specifically, it calculates the deviation of the observations from the mean vector and takes into account the effect of the covariance matrix.
[0078] The observation probability formula converts the observed value With status By calculating the observation probability, the system can evaluate the likelihood of observing actual data in a given state. This helps determine the likelihood of the observation corresponding to the current state. The observation probability formula is used to update the state prediction. In the process of state prediction, the state is first predicted based on the previous state and the state transition probability. Then, the observation probability formula is used to correct the state prediction based on the actual observation value, thereby providing a more accurate state estimate. Covariance matrix It plays a key role in the probability of observation. It reflects the uncertainty and correlation of the observations. If the elements of the covariance matrix are large, it means that the uncertainty of the observations is high, and the system will be more relaxed in estimating the observations. On the contrary, smaller covariance matrix elements indicate that the estimation of the observations is more precise.
[0079] Embodiment 4: The state prediction part uses the following formula to calculate the forward probability:
[0080] ;
[0081] in, Indicates at time In state The forward probability of Indicates at time In state The forward probability of .
[0082] Specifically, the forward probability can be estimated at the current moment by considering the observed value and the state transition probability. The forward probability formula takes into account the probability of each possible state. This helps the system update its estimate of the patient's state to make it more accurate. The forward probability calculation is recursive, and the forward probability at each moment depends on the forward probability at the previous moment. This allows the system to continuously make state estimates based on new observations and achieve real-time state predictions. The forward probability formula takes into account the observation probability and state transition probability to more comprehensively estimate the patient's state. The observation probability represents the likelihood of observing actual data in a given state, while the state transition probability represents the transition relationship between states.
[0083] Embodiment 5: The state prediction part uses the following formula to calculate the backward probability:
[0084] ;
[0085] in, Indicates at time In state The backward probability of Indicates at time In state The backward probability of .
[0086] Specifically, the backward probability can be estimated at the current time by considering the observed value, state transition probability and backward probability. The backward probability formula takes into account the observation probability, state transition probability, and backward probability to estimate the patient's state more comprehensively. The observation probability represents the likelihood of observing actual data in a given state, the state transition probability represents the conversion relationship between states, and the backward probability takes into account information from future moments.
[0087] Embodiment 6: The state prediction part uses the following formula to perform state prediction based on the forward probability and the backward probability to obtain a state prediction result:
[0088] ;
[0089] Indicates at time In state The state prediction results.
[0090] Specifically, the forward probability represents the known observation value In the case of This is calculated by the forward algorithm in the state prediction part. The backward probability represents the probability of In the case of This is calculated by the backward algorithm in the state prediction part. State prediction result It is at the moment In state The state prediction result is that during the entire time period, the system is in the state probability.
[0091] The core idea of the formula is to use the forward probability and the backward probability to estimate the In state The probability of is achieved by the following steps: First, the forward probability With backward probability Multiply, so that the time can be taken into account The observation data of the whole time period and the observation data of the state This product is then normalized with the sum of the products of the forward and backward probabilities of all possible states to ensure that the state prediction result is a probability distribution whose sum is 1. The numerator in the formula Reflects at the moment In state The denominator of the comprehensive probability is a normalization factor that ensures the probabilistic nature of the state prediction results. This formula is based on Bayes' theorem and combines the forward and backward probabilities to estimate the state at time The probability of being in different states provides a probabilistic estimate of the patient's state.
[0092] Example 7: The method for adjusting the dosage of the analgesic drug delivered to the patient according to the real-time physiological data by the drug regulation delivery part includes: constructing a diffusion model, a release model and a metabolism model of the analgesic drug in the patient's body; setting an objective function based on the diffusion model, the release model and the metabolism model, wherein the optimization goal of the objective function is to minimize the dosage of the analgesic drug that eventually enters the patient's body while ensuring that the patient's pain level is reduced to below a set threshold; setting at time Real-time physiological data is collected at the same time, and the dose of analgesic delivered to the patient is based on the state prediction results. ; According to the pain level corresponding to the real-time physiological data, the dosage of analgesic drugs delivered to the patient at each moment is calculated through the constraints of the objective function. ; At each moment, deliver to the patient Dosage of analgesics.
[0093] Specifically, first, mathematical models of drug diffusion, release, and metabolism in patients were established. These models describe the behavior of drugs in patients, including the rate of drug diffusion, the rate of release from the releaser, and the metabolic rate of the drug. These models are built on knowledge of physiology and pharmacology to understand and predict the behavior of drugs in patients. Next, an objective function was set to achieve two key goals. The main goal of this objective function is to minimize the total dose of analgesics that ultimately enter the patient's body. This is for the sake of drug safety and patient comfort, in order to minimize the side effects and adverse reactions of the drug. The optimization goal is to minimize the drug dose while ensuring that the patient's pain level is reduced below the set threshold. This means that the system is looking for an optimal dose adjustment strategy to minimize drug use while maintaining effective pain management. At each moment , collects real-time patient physiological data, including body temperature, heart rate, respiratory rate, blood pressure, etc., as well as data related to drug concentration. Then, based on the previous state prediction results and real-time data, calculates the dose of analgesic drugs that should be delivered to the patient at each moment Finally, the calculated dose of analgesic medication to the patient. When the system is running, it will ensure that the constraints set by the objective function are met. These constraints include reducing the pain level below the set threshold and minimizing the total dose. Based on mathematical modeling and optimization technology, it makes full use of the patient's real-time physiological data and continuously adjusts the drug dosage to ensure that the pain is effectively managed while minimizing the total dose of analgesics that ultimately enter the patient's body. This method helps to personalize the patient's pain management, improve treatment effectiveness, and reduce potential drug side effects.
[0094] Embodiment 8: The diffusion model is expressed using the following formula:
[0095] ;
[0096] in, is the diffusion coefficient, is the Laplace operator, is the nonlinear diffusion coefficient; For time;
[0097] : This is the drug concentration Over time The rate of change indicates the rate of change of the drug over time.
[0098] : Diffusion coefficient is used to describe the speed at which drugs diffuse in tissues. It reflects how fast drug molecules spread in tissues and is usually related to tissue properties and temperature.
[0099] : Laplace operator applied to concentration , represents the spatial gradient of concentration and is used to describe the distribution and changes of drugs in space.
[0100] : Nonlinear diffusion coefficient, which represents the nonlinear relationship between the square of drug concentration and the drug concentration itself. It reflects the slowdown of drug diffusion at high concentrations.
[0101] The principle of the diffusion model is based on Fick's second diffusion law, which describes the diffusion process of solutes in space. The model assumes that the diffusion rate of drugs in tissues is affected by two factors: the diffusion term ( ): This section describes the diffusion due to concentration gradient. The drug will flow from areas of high concentration to areas of low concentration as a result of the natural diffusion phenomenon. Diffusion coefficient Determines the speed of this process, the larger indicates faster diffusion. Nonlinear ( ): This term takes into account the interaction between drug molecules at high concentrations. When the drug concentration is high, the interaction will cause the diffusion rate to slow down, which is a characteristic of nonlinear diffusion.
[0102] Diffusion models are used to describe how drugs spread in tissues and help understand how the concentration distribution of drugs in tissues changes over time and space. This is important for predicting the distribution and concentration distribution of drugs in patients and can be used to develop appropriate treatment plans.
[0103] The release model is expressed using the following formula:
[0104] ;
[0105] in, is the release rate; is the surface area of the analgesic drug; is the saturated solubility, which is the set value; is the rate of dissolution of the analgesic drug;
[0106] Release item ( ) This section describes the diffusion of the drug due to concentration differences. The drug will flow from an area of high concentration (inside the releaser) to an area of low concentration (in the external environment or target tissue), following Fick's law of diffusion. Diffusion coefficient Determines the diffusion rate, drug surface area and concentration differences It is also an influencing factor.
[0107] Dissolved Item ( ): This term takes into account the rate at which the drug dissolves from the solid state (drug in the releaser) into the solution (releasable form). The drug is continuously dissolving in the releaser, and this rate is determined by the drug dissolution rate control.
[0108] Release models are used to describe the release rate of a drug from a release device. This helps understand how a drug is released from a given release device or dosage form into the patient's body, thereby affecting the concentration changes of the drug.
[0109] The drug metabolism model is expressed using the following formula:
[0110] ;
[0111] in, is the metabolic rate; is the maximum metabolic rate, which is the set value; is the Michaelis constant.
[0112] Specifically, the metabolic model assumes that drug metabolism is caused by biochemical reactions catalyzed by enzymes. These enzymes can accelerate the conversion of drug molecules into metabolites. The metabolic model uses Michaelis-Menten kinetics, which is a common model for describing the rate of enzyme-catalyzed reactions. It means that under enzyme saturation conditions, the enzyme system can metabolize the drug at the maximum rate. Is a constant that represents the value of drug concentration at half-saturation metabolic rate. Depends on drug concentration and these two parameters.
[0113] Embodiment 9: The objective function is expressed using the following formula:
[0114] ;
[0115] in, is the objective function; the total time spent delivering analgesic medication to the patient;
[0116] The constraints are:
[0117] ;
[0118] in, The pain level corresponding to the real-time physiological data; is the set threshold.
[0119] The integral term in the objective function represents the total cost of the system. By minimizing this cost, we can reduce the overall cost of treatment, for example by reducing the amount of drug used. The set threshold is not exceeded. This ensures that the patient's pain management is not sacrificed during the optimization process. distribution, we can find the best treatment strategy under the premise of satisfying the constraints so that the patient's pain can be effectively controlled.
[0120] Indicates at different times The dose of drug delivered to the patient. This part is the adjustable parameter of the objective function, that is, the optimization problem needs to find the optimal Distributed to minimize the cost. Diffusion term describes the diffusion of drugs in tissues, where is the diffusion coefficient, Represents the gradient of drug concentration. This part represents the distribution and changes of drugs in tissues. Its goal is to make the drugs evenly distributed in the target tissues to ensure effective treatment. Nonlinear diffusion term Represents the nonlinear relationship between the square of the drug concentration and the drug concentration itself. is the nonlinear diffusion coefficient, indicating that the drug diffusion rate slows down at high concentrations. The goal of this part is to keep the drug concentration within a controllable range to prevent adverse reactions caused by excessive concentrations. ) table represents the rate at which the drug is released from the releaser. This item represents the drug administration rate, and its goal is to control the drug release rate according to the system demand. Indicates the metabolic rate of the drug in the body. This item indicates the effect of in vivo metabolism on drug concentration, and its goal is to match the metabolic rate of the drug in the body with the therapeutic needs.
[0121] Embodiment 10: Based on physiological data or real-time physiological data, the formula for calculating the pain level corresponding to the physiological data at each moment is:
[0122] ;
[0123] in, is the pain level; It is the difference between body temperature and standard value, in degrees Celsius; It is the difference between the heart rate and the standard heart rate value; It is the difference between the respiratory rate and the standard value of the respiratory rate; It is the difference between blood pressure and standard blood pressure value, in units of: The concentration of analgesic drugs is: ; and are weight coefficients, which are set values.
[0124] The present invention realizes personalized pain management by monitoring the patient's physiological state and automatically adjusting the dosage of analgesics to ensure that the patient obtains the best pain relief effect and minimizes unnecessary use of drugs and potential adverse reactions. It combines the principles of medicine, biology, mathematical modeling and automated control to provide patients with a safer and more effective pain management strategy. In addition, this device can reduce the workload of medical staff and improve the efficiency and quality of treatment.
[0125] : The difference between the body temperature and the standard value, in degrees Celsius. Body temperature is a basic physiological parameter and is closely related to the health of the human body. If the body temperature deviates significantly from the standard value, it may indicate a potential physiological problem. In this formula, we use the weight coefficient This means that the degree to which different body temperature changes affect pain levels can be adjusted by adjusting value to control.
[0126] : The difference between the heart rate and the standard heart rate. Heart rate refers to the number of heart beats per minute, and its changes may be related to pain. In this formula, we use the weight system To adjust the effect of heart rate on pain level. The effect of different heart rate changes on pain level can be adjusted to control the value.
[0127] : The difference between the respiratory rate and the standard value of the respiratory rate. The respiratory rate refers to the number of breaths per minute, which may also be related to pain perception. In this formula, we use the weight coefficient To adjust the effect of breathing rate on pain level. The effect of different breathing rate changes on pain level can be adjusted to control the value.
[0128] : The difference between blood pressure and standard blood pressure, measured in millimeters of mercury (mmHg). Blood pressure is a key physiological indicator that reflects the state of the circulatory system. In this formula, we use the weight coefficient To adjust the effect of blood pressure on pain level. The effect of different blood pressure changes on pain level can be adjusted to control the value.
[0129] : Analgesic concentration in milligrams per liter (mg / L). Analgesics are drugs used to relieve pain, and their concentration may affect the sensation of pain. In this formula, the concentration of analgesics is expressed as a negative number This means that the higher the concentration of analgesic medication, the lower its effect on pain ratings. This is because the presence of analgesic medication generally reduces the sensation of pain.
[0130] The differences in these physiological parameters are multiplied by the corresponding weight coefficients, and then the absolute value of the result is taken. Next, all these terms are added together and the contribution of the analgesic concentration is subtracted. The final value $P(C)$ can be used to estimate a person's pain level. The higher this value, the higher the pain level, and vice versa. In general, this formula provides a way to estimate pain levels by monitoring multiple physiological parameters. It allows doctors or patients to have a more comprehensive understanding of the pain condition and helps to develop a more effective treatment plan. Importantly, the weight coefficients in the formula , , , and It can be adjusted according to actual conditions to suit different pain assessment needs and drug treatment plans. This method can be used in clinical practice to more accurately assess and manage the conditions of patients with pain.
[0131] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. Automatic control device for analgesic drugs with adaptive pain perception, It is characterized in that The device comprises: a data acquisition part, a state prediction part and a drug regulation and delivery part; the data acquisition part is configured to acquire the physiological data of the patient within a set time period, and calculate the pain level corresponding to the physiological data at each moment based on the physiological data; the state prediction part is configured to establish the patient's state space based on the physiological data, each state in the state space corresponds to the pain level at a moment, construct a state transition probability matrix between states in the state space, define the initial state probability distribution, the observation model and the observation probability distribution, calculate the forward probability and the backward probability, and perform state prediction based on the forward probability and the backward probability to obtain the state prediction result; the drug regulation and delivery part is configured to Based on the state prediction result, an analgesic drug of a dose corresponding to the state prediction result is delivered to the patient. During the delivery process, a control instruction is sent to the data acquisition part to collect the patient's real-time physiological data, and the dose of the analgesic drug delivered to the patient is adjusted according to the real-time physiological data; the method for the drug regulation and delivery part to adjust the dose of the analgesic drug delivered to the patient according to the real-time physiological data includes: constructing a diffusion model, a release model and a metabolic model of the analgesic drug in the patient's body; setting an objective function based on the diffusion model, the release model and the metabolic model, and the optimization goal of the objective function is: to minimize the dose of the analgesic drug that finally enters the patient's body, while ensuring that the patient's pain level is reduced to below the set threshold; setting at time Real-time physiological data is collected at the same time, and the dose of analgesic delivered to the patient is based on the state prediction results. ; According to the pain level corresponding to the real-time physiological data, the dosage of analgesic drugs delivered to the patient at each moment is calculated through the constraints of the objective function. ; At each moment, deliver to the patient dose of analgesics; The diffusion model is expressed using the following formula: ; in, is the diffusion coefficient, is the Laplace operator, is the nonlinear diffusion coefficient; is time; the release model is expressed using the following formula: ; in, is the release rate; is the surface area of the analgesic drug; is the saturated solubility, which is the set value; is the rate of dissolution of the analgesic drug; The drug metabolism model is expressed using the following formula: ; in, is the metabolic rate; is the maximum metabolic rate, which is the set value; is the Michaelis constant.
2. The pain perception adaptive analgesic drug automatic control device according to claim 1, It is characterized in that The physiological data or real-time physiological data collected by the data collection part at least include: body temperature, heart rate, respiratory rate, blood pressure and analgesic drug concentration.
3. The pain perception adaptive analgesic drug automatic control device as claimed in claim 2, It is characterized in that The state prediction part is based on physiological data, and the patient's state space is established as: ; in represents the state space; Represents at the moment Status; The total number of moments in the set time period; The constructed state transition probability matrix is ; Each element in the state transition probability matrix is: ; in Represents the state Transfer to state probability; and All are subscripts, with a value range of 1 to integer; The initial state probability distribution is defined as: ; in Indicates at time When the status is probability; The observation model is defined as: ; in represents the set of observations, Represents at the moment Observed value of The observation probability is defined using the following formula: ; in, is the observation probability distribution, indicating that in a given state Observed value The probability of Representation status The mean vector of the multidimensional Gaussian distribution under ; Representation status The covariance matrix of the multidimensional Gaussian distribution under , is its inverse matrix; is the covariance matrix The determinant of , which represents the uncertainty of the observations.
4. The pain perception adaptive analgesic drug automatic control device according to claim 3, It is characterized in that The state prediction part uses the following formula to calculate the forward probability: ; in, Indicates at time In state The forward probability of Indicates at time In state The forward probability of .
5. The pain perception adaptive analgesic drug automatic control device according to claim 4, It is characterized in that The state prediction part uses the following formula to calculate the backward probability: ; in, Indicates at time In state The backward probability of Indicates at time In state The backward probability of .
6. The pain perception adaptive analgesic drug automatic control device according to claim 5, It is characterized in that The state prediction part uses the following formula to perform state prediction based on the forward probability and the backward probability to obtain the state prediction result: ; Indicates at time In state The state prediction results.
7. The pain perception adaptive analgesic drug automatic control device according to claim 6, It is characterized in that The objective function is expressed using the following formula: ; in, is the objective function; the total time spent delivering analgesic medication to the patient; The constraints are: ; in, The pain level corresponding to the real-time physiological data; is the set threshold.
8. The pain perception adaptive analgesic drug automatic control device according to claim 7, It is characterized in that Based on physiological data or real-time physiological data, the formula for calculating the pain level corresponding to the physiological data at each moment is: ; in, is the pain level; It is the difference between body temperature and standard value, in degrees Celsius; It is the difference between the heart rate and the standard value; It is the difference between the respiratory rate and the standard value of the respiratory rate; It is the difference between blood pressure and standard blood pressure value, in units of: The concentration of analgesic drugs is: ; and are weight coefficients, which are set values.
Citation Information
Patent Citations
Intelligent analgesia management device
CN111696644A
Real-time pain detection and pain management system
CN114786564A
Drug relocation method for predicting new coronavirus adapted drug
CN114913916A
Chronic pain feature recognition system based on M-N + model
CN115862844A
Method for generating and using analgesia prediction model of analgesia pump
CN116543866A
