Method and device for calculating blood temperature of patient in hemodialysis treatment

Abstract

The invention relates to a method and equipment for calculating the blood temperature of a patient in hemodialysis treatment, and the method comprises the following steps: obtaining geometric parameters and physical parameters of an extracorporeal circulation pipeline of hemodialysis, so as to establish a transient heat transfer model for representing the spatial-temporal dynamic change of the blood temperature in the extracorporeal circulation pipeline; acquiring operation parameters corresponding to the hemodialysis process, and constraining the transient heat transfer model by using the operation parameters to generate a constrained heat transfer model used for reflecting a heat exchange boundary condition in a real-time dialysis scene; carrying out numerical solution on the constrained heat transfer model so as to generate temperature field distribution data for representing the temperature of each part in the extracorporeal circulation pipeline under the preset dialysis duration; and extracting a temperature value corresponding to the position of the blood outlet of the extracorporeal circulation pipeline as the temperature of the blood outlet. The device has the advantage of better maintaining heat balance and safety of a patient in the treatment process.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of dialysis equipment, in particular to a method and device for calculating blood temperature of a patient during hemodialysis treatment. BACKGROUND

[0002] Hemodialysis is a routine medical method for purifying blood of patients with renal failure. As a life support technology, it simulates the function of the kidney by leading the patient's blood out of the body, removing accumulated metabolic waste and excess water in the blood, and returning the purified blood to the patient's body to maintain life activities.

[0003] During the hemodialysis treatment process, the extracorporeal circulation of blood is completed through a special pipeline system, which is usually referred to as an extracorporeal pipeline. After the blood is led out of the patient's body, it first flows through the arterial segment of the pipeline and enters the core purification device called a dialyzer. After completing the material exchange in the dialyzer, the clean blood returns to the patient's body through the venous segment of the pipeline. A standard dialysis treatment usually lasts for several hours, during which the blood will continuously flow in this extracorporeal pipeline.

[0004] When the blood flows in the extracorporeal pipeline, it exchanges heat with the pipeline wall, the dialyzer, and the surrounding air environment, which can cause the temperature of the blood returning to the body to change. This deviation in temperature can affect the patient's thermoregulatory system and overall hemodynamic stability. Clinical research and practice have shown that even a small, continuous temperature change can cause discomfort to the patient and even induce some adverse physiological reactions. SUMMARY

[0005] In order to better maintain the heat balance and safety of the patient during the treatment process, the present application provides a method and device for calculating blood temperature of a patient during hemodialysis treatment.

[0006] In a first aspect, the present application provides a method for calculating blood temperature of a patient during hemodialysis treatment, which adopts the following technical solution: A method for calculating blood temperature of a patient during hemodialysis treatment, comprising the following steps: S1. Obtain the geometric parameters and physical parameters of the extracorporeal pipeline of hemodialysis, and based on the geometric parameters and physical parameters, establish a transient heat transfer model for characterizing the spatio-temporal dynamic change of blood temperature in the extracorporeal pipeline; S2. Obtain the operating parameters corresponding to the hemodialysis process, and use the operating parameters to constrain the transient heat transfer model to generate a constrained heat transfer model reflecting the heat exchange boundary conditions corresponding to the real-time dialysis scene; S3. Numerically solving the constrained heat transfer model to generate a temperature field distribution data representing the temperature of each point in the extracorporeal circulation pipeline under a preset dialysis time; S4. Extracting a temperature value corresponding to the blood outlet position of the extracorporeal circulation pipeline from the temperature field distribution data as the blood outlet temperature.

[0007] By adopting the above technical solution, firstly, a transient heat transfer model representing the basic physical law is established, and then the general model is constrained by using the real-time acquired operating parameters to generate a constrained heat transfer model matched with a specific dialysis scene. Here, the universal model construction and the instant scene application are separated to form a two-stage determination method.

[0008] Specifically, the acquired operating parameters, such as the patient's body temperature and the dialysate temperature, are not substituted into a fixed calculation formula as variables. They are used to define the initial conditions and boundary conditions of the transient heat transfer model in this run. For example, the real-time body temperature of the patient defines the initial temperature of the blood entering the extracorporeal circulation pipeline, and the dialysate temperature establishes the key external environment of the heat exchange in the dialyzer region. In this way, the operating parameters directly limit the mathematical and physical boundaries of the model solution, so as to adjust and transform a general physical model into a constrained heat transfer model that can accurately describe the thermodynamic system of the current specific dialysis process.

[0009] Then, the constrained heat transfer model is numerically solved. Since the model has been accurately calibrated to the current real working state, the solving process is essentially a dynamic simulation of this specific dialysis process. The temperature field distribution data generated by the simulation can accurately reflect the temperature state of the blood at each point in the pipeline. Finally, the temperature value of the outlet position is extracted from this accurately simulated data to obtain an accurate blood outlet temperature prediction value.

[0010] Optionally, the transient heat transfer model is established based on a heat conduction partial differential equation, and the control equation of the heat conduction partial differential equation is: , wherein, is a heat capacity term, is a heat conduction term, is a convective heat transfer term, is an external heat exchange heat source term.

[0011] By adopting the technical scheme, the transient heat transfer model is specifically defined as a heat conduction partial differential equation including heat capacity, heat conduction and convection heat transfer terms, so that the model construction no longer depends on empirical formula or statistical fitting, and the output temperature field distribution data has high fidelity in theory and can accurately reflect the real physical process. Even if new equipment or unconventional operating parameters are not included in the existing database, the model can still effectively predict by solving the physical equation.

[0012] Optionally, the boundary condition for constraining the transient heat transfer model by the operating parameter comprises: At the blood inlet of the extracorporeal circulation pipeline, the inlet boundary condition is set as blood inlet temperature equal to the preset patient body temperature; In the dialyzer region of the extracorporeal circulation pipeline, the dialyzer membrane surface boundary condition is set as based on the convective heat transfer between blood and dialysate; In the non-dialyzer region of the extracorporeal circulation pipeline, the pipeline outer wall boundary condition is set as based on the convective heat transfer between the pipeline outer wall and the external environment; At the blood outlet of the extracorporeal circulation pipeline, the outlet boundary condition is set as a free outflow condition with zero temperature gradient.

[0013] Optionally, the geometric parameters, physical parameters and operating parameters include patient body temperature, dialysate temperature, environment temperature, blood physical parameters, flow rate parameters and geometric parameters of the extracorporeal circulation pipeline.

[0014] By adopting the technical scheme, the inlet boundary condition forcibly sets the temperature value of the numerical solver at the spatial starting point as the actual body temperature of the patient, providing a starting state conforming to the physiological actuality for the iterative calculation of the entire temperature field. The boundary conditions of the dialyzer and the non-dialyzer region do not directly set the temperature value, but dynamically calculate the heat flux through the interface according to the real-time temperature difference between the blood and the external environment during the solving process of the model. This calculated heat flux acts as a source term or sink term in the numerical algorithm, directly affecting the temperature change rate of the nodes near the boundary. The outlet boundary condition ensures that there is no non-physical heat backflow or divergence at the end of the calculation domain by specifying the temperature gradient at the outlet as zero.

[0015] By combining these boundary conditions, the method provides constraints for the transient heat transfer model, so that the model can start from a determined initial temperature, accurately account for heat loss caused by different mechanisms along the way, and finally obtain the outlet temperature in a stable numerical environment.

[0016] Optionally, the numerical solution of the constrained heat transfer model comprises spatial and temporal discretization of the constrained heat transfer model and iterative calculation.

[0017] By adopting the technical solution, the spatial discretization decomposes the continuous physical length of the extracorporeal circulation pipeline into a finite number of calculation nodes, and the time discretization divides the continuous dialysis time into a series of independent calculation time steps. Iterative calculation is the core process of solving the algebraic equation set and simulating the dynamic evolution of temperature over time. Since the temperature distribution at the current time depends on the state at the previous time, the calculation cannot be completed in one step and must be iterated through time stepping. The calculation process starts from the known initial temperature distribution. In the first time step, the equation set is solved to obtain the new temperature values at all spatial nodes. Then, this newly calculated temperature distribution is taken as the initial condition for the next time step, and the same solving process is repeated. Through this continuous iteration from one time step to the next, the method can calculate the evolution of the temperature field over the entire dialysis time.

[0018] Optionally, S2 comprises the following sub-steps: S21. Based on the real-time scenario corresponding to the hemodialysis process, determine the fusion scenario and the fusion weight, wherein the fusion scenario is characterized as a weighted combination of multiple standard scenarios, each standard scenario corresponding to a set of preset model parameters; the fusion weight is determined based on the degree of difference between the operating parameters and the reference parameters of each standard scenario; S22. Based on the fusion weight, fuse the multiple sets of preset model parameters corresponding to the multiple standard scenarios to obtain the operating parameters, wherein the fusion is based on a preset nonlinear weighting algorithm; S23. Based on the operating parameters, constrain the transient heat transfer model to construct a constrained heat transfer model reflecting the heat exchange boundary conditions under the real-time scenario.

[0019] Optionally, S21 comprises the following sub-steps: S211. Obtain and analyze the historical change data of the operating parameters within a preset time window to generate a change pattern feature; wherein the change pattern feature includes one or more features of the operating parameters in the first-order time derivative or the second-order time derivative; S212. Dynamically adjust the fusion weight according to the change pattern feature to obtain the final fusion weight.

[0020] Optionally, S212 comprises the following sub-steps: S2121. Pre-set a weight adjustment model, which is used to establish a mapping relationship between the change pattern feature and the weight adjustment coefficient; S2122. Input the change pattern feature into the weight adjustment model to calculate one or more weight adjustment coefficients for each standard scenario; S2123. Adjust the fusion weight using the weight adjustment coefficient to generate a final dynamically adjusted fusion weight.

[0021] Optionally, the standard scenario includes at least one of the following: a scenario in which only the ambient temperature deviates from the reference state, a scenario in which only the patient body temperature deviates from the reference state, or a scenario in which only the blood flow rate deviates from the reference state.

[0022] In a second aspect, the present application provides a computer device, which adopts the following technical solution: A computer device, comprising: one or more processors; a memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to: execute the above-mentioned method for calculating the blood temperature of a patient during hemodialysis treatment. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 A program block diagram of the method for calculating the blood temperature of a patient during hemodialysis treatment in an embodiment of the present application is shown.

[0024] Figure 2 A program block diagram of the S2 sub-step in an embodiment of the present application is shown.

[0025] Figure 3 A schematic diagram of the computer device in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] The present application will be further described below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.

[0027] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the inventive concept. As part of the description, some of the diagrams in the present disclosure are represented in block diagram form to avoid obscuring the disclosed principles. Some features of the actual implementation can not be described in detail for the sake of clarity. Also, the language used in the present disclosure has been principally selected for readability and instructional purposes and can not have been selected to delineate or circumscribe the inventive subject matter, resort to the claims being necessary to determine such

[0028] The terms "a," "an," and "the" are not intended to refer to only a singular entity, but include the general class of which a specific example can be used for illustration. The terms "a" and "an" are used interchangeably herein with the term "one or more" to mean that a number of an introduced functional entity can be used therewith. The use of the term "or" means any one of the alternatives, as well as any combination of the alternatives, including all combinations, unless the alternatives are expressly indicated to be mutually exclusive. The phrase "at least one of' followed by a list of two or more items means any of the items in the list alone or any combination of the items in the list. The phrase "at least one of' does not mean all of the items in the list.

[0029] In a scenario where hemodialysis treatment is required, hemodialysis is a conventional medical procedure used to purify the blood of patients with kidney failure. The process works by drawing a patient's blood out of the body, through an extracorporeal tubing system to mimic the function of the kidneys. During extracorporeal circulation, the blood first enters a core purification device known as a dialyzer, where metabolic waste and excess water accumulated in the blood are removed. After the purification process is complete, the clean blood is then fed back into the patient's body through the tubing to sustain their life activities. A standard dialysis treatment usually takes several hours, during which the blood is continuously circulated in the extracorporeal tubing system.

[0030] During the process of blood flowing in the extracorporeal circuit, heat exchange inevitably occurs due to the temperature difference between the blood and the wall of the circuit, the dialyzer and the surrounding environment. This usually manifests as heat loss of the blood, resulting in the blood returning to the patient's body at a lower temperature than the patient's core body temperature. This deviation in temperature directly affects the patient's thermoregulatory system and hemodynamic stability. Long-term extracorporeal heat loss, even if the magnitude is small, can cause the patient to shiver, feel uncomfortable, and in some cases, affect the stability of the cardiovascular system.

[0031] Therefore, with reference to Figure 1 The present application discloses a method for calculating the blood temperature of a patient during hemodialysis treatment, comprising the following steps S1-S4.

[0032] S1. Obtain the geometric parameters and physical parameters of the extracorporeal circuit of hemodialysis, and based on the geometric parameters and physical parameters, establish a transient heat transfer model for characterizing the spatio-temporal dynamic changes of blood temperature in the extracorporeal circuit.

[0033] During hemodialysis, blood is taken out of the body through an extracorporeal circuit. The circuit is composed of an arterial segment circuit, a dialyzer and a venous segment circuit. The working principle is that the blood first flows through the arterial segment circuit into the dialyzer, where purification is completed, and then returns to the patient's body through the venous segment circuit, forming a closed system for blood flow.

[0034] In order to accurately describe the physical characteristics of this closed system, the inherent geometric parameters and physical parameters need to be obtained first. The geometric parameters mainly describe the macroscopic physical dimensions of the extracorporeal circuit, such as the total length, inner diameter, outer diameter and wall thickness of the circuit. These parameters determine the flow distance of the blood in the circuit and the surface area for heat exchange with the outside world, thereby affecting the spatial distribution of blood temperature. The physical parameters describe the thermodynamic properties of the various materials that make up the system, such as the thermal conductivity of the circuit material, the density, specific heat capacity and thermal conductivity of the blood itself. These parameters determine the rate of heat transfer between different media and the ease of temperature change of the blood itself.

[0035] The transient heat transfer model regards temperature as a function of both spatial position and time, and integrates the above-mentioned geometric parameters and physical parameters into a unified system through mathematical methods, so as to calculate the temperature of the blood at any position in the extracorporeal circuit at any time during dialysis. This representation captures the dynamic evolution of temperature, rather than a static final value, to facilitate subsequent accurate calculations.

[0036] Optionally, in an embodiment, the transient heat transfer model is established based on a heat conduction partial differential equation, and the control equation of the heat conduction partial differential equation is: ; wherein, is the heat capacity term, is the heat conduction term, is the convection heat transfer term, is the external heat exchange source term.

[0037] The heat conduction partial differential equation is a basic physical equation describing the spatiotemporal evolution of heat transfer and temperature distribution in a physical system, which is essentially a mathematical expression of energy conservation analysis in a micro-volume. The heat capacity term on the left side of the equation, wherein p is the fluid density, is the specific heat capacity of the fluid, is the rate of change of temperature with respect to time, which collectively represents the rate of energy absorbed or released by the unit volume of fluid due to its temperature change. The heat conduction term on the right side of the equation, wherein k is the thermal conductivity of the fluid, is the temperature gradient, which describes the conduction and diffusion of heat within the fluid medium due to temperature difference. The convection heat transfer term, wherein v is the fluid velocity vector, describes the process of heat being carried and transported by the macroscopic movement of the fluid. The external heat exchange source term Q represents the net rate of heat exchange between the system and the external environment.

[0038] In the extracorporeal circulation process of hemodialysis, blood as a fluid, its thermodynamic behavior conforms to the physical laws described by the heat conduction partial differential equation. The flow of blood in the pipeline corresponds to the convection heat transfer process in the equation. Blood itself as a medium, the heat transfer within it due to temperature difference, corresponds to the heat conduction process. When flowing through the dialyzer and the pipeline exposed to the environment, the heat exchange between blood and dialysate and surrounding air corresponds to the external heat exchange source term. Therefore, using this equation can represent the spatiotemporal dynamic changes of blood in the extracorporeal circulation process caused by the combined action of multiple physical mechanisms.

[0039] S2. Obtain operating parameters corresponding to the hemodialysis process, and constrain the transient heat transfer model using the operating parameters to generate a constrained heat transfer model reflecting the heat exchange boundary conditions in the real-time dialysis scenario.

[0040] The operating parameters of a hemodialysis process are a set of variable physical quantities used to describe the real-time working condition during a single dialysis treatment. These parameters mainly include the patient's body temperature, the dialysis machine's set parameters such as blood flow rate and dialysate temperature, and the treatment environment's parameters such as ambient temperature. Each operating parameter has a direct impact on the extracorporeal blood temperature. For example, the patient's body temperature determines the initial thermal state of the blood leaving the body; the blood flow rate affects the residence time of the blood in the circuit, thus changing the total amount of heat exchange with the outside world; the dialysate temperature and the ambient temperature constitute the main external heat source or heat sink for the dialyzer region and the circuit exposure region, respectively.

[0041] The constraint of the transient heat transfer model using these operating parameters is achieved by converting these parameter values into the initial conditions and boundary conditions necessary for solving the model. This process is not simply substituting the parameters as variables into a fixed formula, but using them as mathematical and physical boundaries that define the physical model in this specific run. For example, the acquired real-time body temperature of the patient is set as the initial temperature value of the model at the inlet position of the circuit; the dialysate temperature and the ambient temperature are used to calculate the heat flux density when the dialyzer region and the circuit outer wall exchange heat with the outside through convection.

[0042] The generation process of the constrained heat transfer model takes the general transient heat transfer model and a set of operating parameters acquired at the current time as inputs. Its internal running mechanism is to map and assign each operating parameter to the boundary condition term in the model one by one, thereby converting a universal physical equation into a math model with completely determined boundaries that can accurately describe the thermodynamic system of the current specific dialysis process. The output of this process is the constrained heat transfer model.

[0043] Optionally, in some embodiments, the boundary conditions used to constrain the transient heat transfer model using the operating parameters include a-d.

[0044] a. At the blood inlet of the extracorporeal circuit, set the inlet boundary condition as the blood inlet temperature equal to the preset patient body temperature; b. In the dialyzer region of the extracorporeal circuit, set the dialyzer membrane surface boundary condition based on the convective heat exchange between blood and dialysate; c. In the non-dialyzer region of the extracorporeal circuit, set the circuit outer wall boundary condition based on the convective heat exchange between the circuit outer wall and the external environment; d. At the blood outlet of the extracorporeal circuit, set the outlet boundary condition as the free outflow condition with zero temperature gradient.

[0045] These boundary conditions provide constraints for the transient heat transfer model. Specifically, the inlet boundary condition forces the temperature value at the spatial origin of the numerical solver to be the actual body temperature of the patient, providing a physiologically realistic starting state for the iterative computation of the entire temperature field. For example, if the acquired body temperature of the patient is 36.8 degrees Celsius, then the temperature value of the model at the location of the tubing inlet is fixed to 36.8 degrees Celsius. The boundary conditions for the dialyzer and non-dialyzer regions do not directly set temperature values, but rather, during the solution process of the model, the heat flux across the interface is dynamically calculated based on the real-time temperature difference between the blood and the outside world. This calculated heat flux acts as a source or sink term in the numerical algorithm, directly affecting the rate of temperature change of the nodes near the boundary. For example, in the dialyzer region, the model continuously calculates the heat exchange rate based on the difference between the current temperature of the blood and the set dialysate temperature of 36.5 degrees Celsius. The outlet boundary condition ensures the stability of the numerical solution by specifying that the temperature gradient at the outlet is zero, preventing non-physical heat backflow or divergence at the end of the computational domain.

[0046] In the process of hemodialysis, the operating parameters involved can be divided into fixed parameters and variable parameters. The reason for this division is that the external environment and the state of the human body can actually change during the several-hour-long dialysis process, and these changes will continuously affect the constrained heat transfer model. For example, the environmental temperature in the treatment room can fluctuate periodically due to the start and stop of the air conditioning system, and the body temperature of the patient can also change slightly due to physiological regulation. When the environmental temperature decreases, the heat exchange rate described by the tubing outer wall boundary condition will increase, resulting in increased heat dissipation of the blood; when the patient's body temperature rises, the initial temperature value set by the inlet boundary condition will also increase accordingly, thereby changing the temperature distribution benchmark within the entire tubing.

[0047] Therefore, in different specific embodiments, the processing method of the operating parameters can be different. For some devices with limited computing power, or in application scenarios that do not require high-precision temperature prediction, the operating parameters can be treated as fixed parameters. At this time, the method acquires all operating parameters at one time at the beginning of dialysis, such as reading from standard values preset in a database or manually input values, and uses this set of fixed parameters to constrain the model once. When the computing power is sufficient, the operating parameters can be dynamically adjusted according to the changes in the external environment and the state of the human body. In this implementation, the method periodically or in real time acquires the latest parameter values from devices such as sensors, and continuously updates the constrained heat transfer model with these dynamically changing parameters. That is, at this time, the operating parameters acquired are dynamically adjusted for the real-time hemodialysis process to achieve higher-precision temperature prediction.

[0048] As an example, in a certain optional embodiment, with reference to Figure 2S2 comprises sub-steps S21-S23.

[0049] S21. Based on the real-time scenario corresponding to the hemodialysis process, determine a fusion scenario and a fusion weight, wherein the fusion scenario is characterized as a weighted combination of multiple standard scenarios, each of which corresponds to a set of preset model parameters; the fusion weight is determined based on the degree of difference between the operating parameters and the reference parameters of each standard scenario.

[0050] In this embodiment, in order to cope with the dynamic changes of operating parameters, the method first needs to determine the real-time scenario corresponding to the hemodialysis process. The real-time scenario here is a multi-dimensional state composed of all relevant operating parameters at the current time. In order to effectively model this complex multi-dimensional state, this method introduces the concept of standard scenario. A standard scenario refers to a kind of idealized scene in which only a single influencing factor deviates from a preset reference state, while all other factors remain in the reference state. For example, a reference state can be set with an environmental temperature of 24 degrees Celsius, a patient temperature of 36.8 degrees Celsius, and a blood flow rate of 300 milliliters per minute. Based on this, a standard scenario can be a low-temperature environment scenario in which only the environmental temperature deviates to 18 degrees Celsius, while other parameters remain unchanged. Similarly, a high-temperature sign scenario can be set in which only the patient temperature deviates to 37.5 degrees Celsius.

[0051] Each of these standard scenarios corresponds to a set of optimized model parameters in advance. This set of parameters can be obtained through the aforementioned experimental calibration or simulation calculation. For example, if a set of parameters consists of four dimensions, then (baseline value 1, baseline value 2, baseline value 3, change value A) and (baseline value 1, baseline value 2, baseline value 3, change value B) represent two standard scenarios of the fourth influencing factor in different states, respectively, each of which has a set of exclusive preset model parameters.

[0052] The actual dialysis process is usually a complex situation where multiple influencing factors deviate from the baseline state simultaneously. This complex situation is defined as a fusion scenario. The fusion scenario is mathematically characterized as the superposition of multiple different standard scenarios. The preset parameters of different standard scenarios are superimposed into the final model parameters used in the fusion scenario through different fusion weights. This method based on scenario decomposition and fusion is fundamentally different from the simple lookup table method that may be used in some prior art. The lookup table method may attempt to enumerate all combinations of environmental and physical data and statically correspond a weight to each. One disadvantage of this approach is that it ignores the parameter change process, i.e., the history of previous changes actually affects subsequent parameter adjustments. The lookup table method can also obtain the parameter change amount at adjacent times, but this change amount is a simultaneous change of multiple parameters, which will confuse the continuous influence of a single influencing factor, and the subsequent steps of the present application solve this problem.

[0053] Optionally, in some embodiments, the types of standard scenarios include at least one of the following: a scenario where only the environmental temperature deviates from the baseline state, a scenario where only the patient's body temperature deviates from the baseline state, or a scenario where only the blood flow rate deviates from the baseline state. In other embodiments, the types of standard scenarios can be further expanded, for example, by adding a scenario where only the environmental humidity deviates from the baseline state, or a scenario where only the patient's hematocrit deviates from the baseline state. As the number of types of standard scenarios increases, the model can perform more detailed and comprehensive decomposition of the real-time scenario. This correspondingly requires the input end of the system to obtain more dimensional operating parameters, and at the same time, the internal operation process of the system when determining the weights and fusing the parameters will also increase the computational load due to the need to process more baseline cases, thereby balancing the accuracy of the model and the computational cost.

[0054] Optionally, in some embodiments, the S21 includes the following sub-steps S211-S212.

[0055] S211. Obtain and analyze the historical change data of the operating parameters within a preset time window to generate a change pattern feature; wherein the change pattern feature includes at least one or more features of the operating parameters in the first-order time derivative or the second-order time derivative.

[0056] S212. Dynamically adjust the fusion weight according to the change pattern feature to obtain the final fusion weight.

[0057] During dialysis, the operating parameters are not isolated point-in-time data, but rather historical changes within a preset time window, forming an inherently correlated time series. Analyzing this series can reveal recent patterns of parameter change. These patterns are qualitative descriptions of the dynamic behavior of the parameters; for example, a patient's body temperature may exhibit a pattern of sustained, slow rise, or the ambient temperature may show a pattern of rapid decline followed by stabilization.

[0058] To apply these change patterns to computation, they need to be quantified into specific change pattern features. As disclosed in this embodiment, the change pattern features include at least one or more features of the operating parameters on the first or second time derivative. The first time derivative characterizes the instantaneous rate of change of the parameter; its sign and magnitude correspond to whether the parameter is increasing or decreasing, and the speed of change, respectively. The second time derivative characterizes the acceleration of the parameter change, distinguishing whether the change is accelerating, decelerating, or trending towards stability. By calculating these derivative values, the qualitative change patterns can be transformed into a set of precise numerical features that can be used by the algorithm.

[0059] The fusion weights are dynamically adjusted based on the changing pattern characteristics. This adjustment process does not directly replace the initial fusion weights calculated based on the current parameter values, but rather modifies them. For example, suppose the current ambient temperature is still within the normal range, but its changing pattern characteristics show a large negative first derivative, indicating a rapid decrease. In this case, the dynamic adjustment mechanism will proactively increase the fusion weights corresponding to the standard low-temperature environment scenario and correspondingly decrease the weights of other scenarios. In this way, the model can respond to upcoming state changes in advance, rather than passively waiting for parameter values ​​to reach a certain threshold before adjusting, thus enabling the final generated model parameters to better track and adapt to the dynamic evolution of the system.

[0060] Optionally, in one embodiment, S212 includes the following sub-steps S2121-S2123.

[0061] S2121. A weight adjustment model is preset, which is used to establish the mapping relationship between the change pattern features and the weight adjustment coefficients.

[0062] S2122. Input the change pattern features into the weight adjustment model to calculate one or more weight adjustment coefficients for each of the standard scenarios.

[0063] S2123. The fusion weights are corrected using the weight adjustment coefficients to generate the final dynamically adjusted fusion weights.

[0064] In this embodiment, the input to the preset weight adjustment model is the quantized change pattern feature generated in S211. Specifically, this is a feature vector composed of multiple numerical values, such as the first and second time derivatives of the patient's body temperature and the first and second time derivatives of the ambient temperature. The output of the model is a weight adjustment coefficient vector, the dimension of which corresponds to the number of standard scenarios. Each coefficient is used to adjust the fusion weight of a specific standard scenario.

[0065] The weight adjustment model is trained on a training set containing a large amount of historical dialysis data. This training set consists of numerous training samples, each containing an input feature vector and a corresponding target output vector. The input feature vector is a pattern of change calculated from real data from a specific historical dialysis process. The corresponding target output vector, i.e., the true weight adjustment coefficients, is obtained through offline optimization analysis. Specifically, for this historical data period, a set of weight adjustment coefficients is found through repeated trials to ensure that the temperature prediction model at that time produces results closest to the actual observations, and this optimal set of coefficients is used as the target output for that training sample.

[0066] The training process involves continuously feeding the model with input feature vectors from the training set and comparing its output with the corresponding target output. Based on the error between the two, optimization algorithms such as gradient descent are used to iteratively adjust the model's internal parameters until the model can output a set of weight adjustment coefficients that are sufficiently close to the target optimum for any given change pattern feature. For example, structurally, this weight adjustment model can be a feedforward neural network containing an input layer that matches the dimension of the change pattern feature, one or more hidden layers for learning complex nonlinear relationships, and an output layer that matches the number of standard scenarios.

[0067] The process of correcting the fusion weights using the aforementioned weight adjustment coefficient is a dynamic optimization of the initial weights calculated based on the current parameter values. For example, if the initial fusion weight for a standard scenario of hypothermic patient signs calculated based on the current operating parameters is 0.2, and the weight adjustment model calculates a weight adjustment coefficient of 1.4 for this scenario based on the monitored pattern of rapid decrease in patient body temperature, then the correction process can be performed by multiplying the initial weight by the adjustment coefficient, i.e., 0.2 * 1.4, thereby generating a final dynamically adjusted fusion weight of 0.28. This corrected weight allows the model to predictively strengthen its response to the trend of decreasing patient body temperature.

[0068] S22. Based on the fusion weights, the preset model parameters corresponding to the multiple standard scenarios are fused to obtain the running parameters, wherein the fusion is performed based on a preset nonlinear weighting algorithm.

[0069] This step, based on the dynamically determined fusion weights from previous steps, combines the independent preset model parameters corresponding to multiple standard scenarios to generate a set of final operating parameters that can represent the current complex real-time scenario. The fusion process here involves weighting the preset parameters of each standard scenario according to their corresponding fusion weight values. For example, if the system determines that the current real-time scenario is a combination of 70% of the baseline scenario and 30% of the low-temperature environment scenario, then the final generated operating parameters will be primarily determined by the preset parameters of the baseline scenario, and will be influenced by the corresponding parameters of the low-temperature environment scenario.

[0070] In a preferred embodiment, the fusion is performed based on a preset nonlinear weighted algorithm. The nonlinear weighted algorithm refers to the fact that the final generated operating parameters are not a simple linear weighted sum of the parameters of each standard scenario. The reason for using a nonlinear algorithm is that in physical reality, different influencing factors may have synergistic or antagonistic coupling effects. For example, when high blood flow rate and low temperature occur simultaneously, the impact on total heat loss may be greater than the sum of the effects of these two factors acting independently. A specific embodiment of the nonlinear weighted algorithm can be a small feedforward neural network, whose input is the fusion weight vector and the parameter matrix of each standard scenario. Through its internal nonlinear activation function, it outputs the final operating parameters after complex coupling calculations. Another embodiment can be a system based on fuzzy logic rules, which uses a series of "if-then" rules to describe the parameter changes under different scenario combinations, thereby achieving nonlinear fusion.

[0071] Of course, in some other embodiments, a preset linear weighting method can also be used for fusion. The advantage of this method is that its calculation process is simple, the computing power requirements of the device are low, and the results have good interpretability, that is, the contribution of each standard scenario to the final parameters is proportional to its weight.

[0072] Since the fusion weights are continuously and dynamically adjusted based on real-time data and changing patterns, the parameter fusion process in this step is also a continuous process. At each calculation time step of dialysis treatment, the system performs a parameter fusion calculation to generate a set of operating parameters that precisely match the fusion weights at that moment.

[0073] S23. Constrain the transient heat transfer model based on the operating parameters to construct a constrained heat transfer model that reflects the boundary conditions of heat exchange in real-time scenarios.

[0074] The core task of this step is to apply real-time constraints to a general transient heat transfer model based on the dynamically generated and continuously changing operating parameters from the previous steps. Since the operating parameters are dynamically changing, directly and abruptly substituting new parameter values ​​into the model at each calculation moment would cause discontinuous jumps in the boundary conditions over time. This contradicts the nature of temperature as a continuous physical quantity and may lead to oscillations or divergences in the numerical solution process. To prevent such non-physical abrupt changes in the calculation results, this embodiment employs a smooth-transition constraint mechanism.

[0075] The process of constraining the model may specifically include the following steps S231-S233.

[0076] S231. The system receives a set of the latest operating parameters generated by S22 at the current calculation moment.

[0077] S232. The system compares the latest operating parameters with the old parameters used in the previous calculation time step, and within the current calculation time step, establishes a smooth transition function, such as a linear interpolation function, for each changing operating parameter. This function ensures that the parameter values ​​change continuously from the beginning to the end of the current time step.

[0078] S233. Substitute these time-dependent transition functions, rather than static values, into the corresponding boundary conditions of the transient heat transfer model to complete the dynamic constraints on the model.

[0079] Through the above steps, a concrete example of a constrained heat transfer model can be generated. This model is a complete, ready-to-solve initial boundary value problem. It consists of two parts: first, the transient heat transfer model body established in step S1 with invariant form; and second, the set of boundary conditions that have been fully instantiated. For example, the previously abstract inlet boundary condition "the blood inlet temperature is equal to the preset patient body temperature" is concretized in this constrained model into a specific mathematical function, such as T(x=0,t)=f_body(t), where f_body(t) is a specific interpolation function that describes the smooth change of the patient's body temperature within this computation time step.

[0080] S3. Numerically solve the constrained heat transfer model to generate temperature field distribution data characterizing the temperature at various points inside the extracorporeal circulation pipeline under a preset dialysis duration.

[0081] The process of numerically solving the constrained heat transfer model is to transform a physical problem that is continuous in time and space into a discrete computational process that can be executed by a computing device. This solution process may specifically include the following steps S31-S35.

[0082] S31. Perform spatial and temporal discretization. Spatial discretization decomposes the continuous physical length of the extracorporeal circulation tubing into a finite number of discrete spatial nodes, while temporal discretization divides the preset total dialysis duration into a series of discrete time steps.

[0083] S32. Set initial conditions. At time zero, when the calculation begins, initialize the temperature values ​​at all spatial nodes to a known state, typically the patient's body temperature.

[0084] S33. Perform iterative calculations over time. Starting from the initial moment, within the first time step, solve for the new temperature values ​​of all spatial nodes at the end of the time step based on the algebraic equations transformed by the constrained heat transfer model.

[0085] S34. Use this newly calculated temperature distribution as the initial condition for the next time step, and repeat the same solution process.

[0086] S35. Continue the iterative process, advancing step by step until the preset total dialysis time is calculated.

[0087] Through the above solution process, a temperature field distribution data is finally generated. This data is one or more data structures that store the temperature value corresponding to each spatial node at the end of dialysis. For example, if the tubing is discretized into N nodes along its length, the generated temperature field distribution data can be a one-dimensional array containing N elements. A specific example of this array could be: [36.80, 36.78, 36.75, ..., 36.55, ..., 36.42], where the first element, 36.80 degrees Celsius, corresponds to the temperature of the tubing inlet node, the last element, 36.42 degrees Celsius, corresponds to the temperature of the tubing outlet node, and the middle elements correspond to the temperatures of the intermediate nodes within the tubing. This data visually presents the complete spatial distribution of blood temperature along the tubing from inlet to outlet at the end of dialysis.

[0088] S4. Extract the temperature value corresponding to the blood outlet position of the extracorporeal circulation tubing from the temperature field distribution data, and use it as the blood outlet temperature.

[0089] Extracting the temperature value corresponding to the blood outlet location from the temperature field distribution data is a direct data query operation. In S3, the continuous space of the extracorporeal circulation tubing is discretized into a series of ordered spatial nodes, and the generated temperature field distribution data is a set of data storing the temperature values ​​corresponding to these nodes one-to-one at the end of dialysis. Since the blood outlet location corresponds to the last calculation node in the spatial discretization process, the extraction operation involves locating and reading the temperature value corresponding to the last node from this data set.

[0090] The reason for using the method of first calculating the complete temperature field distribution data and then extracting the outlet temperature value from it, rather than directly calculating only the temperature at the outlet, is that in this model, the temperature at any point in the pipeline is the cumulative result of the heat exchange history of all upstream points. During the numerical solution process, the temperature value of each spatial node depends on the temperature value of its adjacent node as the calculation input. This computational dependency constitutes a complete chain from the pipeline inlet to the outlet.

[0091] Therefore, to obtain an accurate outlet temperature, the temperature evolution must be calculated node by node along the entire pipeline length, starting from the inlet. Only by fully simulating the transfer and distribution of heat throughout the entire spatial domain can the final outlet temperature be guaranteed.

[0092] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0093] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database contains data related to a method for calculating patient blood temperature during hemodialysis treatment. The network interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a method for calculating patient blood temperature during hemodialysis treatment.

[0094] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0095] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for calculating the blood temperature of a patient during hemodialysis treatment, characterized in that, Includes the following steps: S1. Obtain the geometric and physical parameters of the extracorporeal circulation tubing for hemodialysis, and based on the geometric and physical parameters, establish a transient heat transfer model to characterize the spatiotemporal dynamic changes of blood temperature within the extracorporeal circulation tubing; S2. Obtain the operating parameters corresponding to the hemodialysis process, and use the operating parameters to constrain the transient heat transfer model to generate a constrained heat transfer model that reflects the heat exchange boundary conditions in the real-time dialysis scenario. S3. Numerically solve the constrained heat transfer model to generate temperature field distribution data characterizing the temperature at various points inside the extracorporeal circulation pipeline under a preset dialysis duration; S4. Extract the temperature value corresponding to the blood outlet position of the extracorporeal circulation tubing from the temperature field distribution data, and use it as the blood outlet temperature.

2. The method for calculating patient blood temperature during hemodialysis treatment according to claim 1, characterized in that, The transient heat transfer model is established based on the partial differential equation of heat conduction, and the governing equation of the partial differential equation of heat conduction is: ， in, For heat capacity, For heat conduction, For convective heat transfer, This refers to the heat source for external heat exchange.

3. The method for calculating patient blood temperature during hemodialysis treatment according to claim 2, characterized in that, The boundary conditions used to constrain the transient heat transfer model using the operating parameters include: At the blood inlet of the extracorporeal circulation tubing, the inlet boundary condition is set to be that the blood inlet temperature is equal to the preset patient body temperature; In the dialyzer region of the extracorporeal circulation tubing, the boundary conditions on the dialyzer membrane surface are set to be based on convective heat transfer between blood and dialysate. In the non-dialyzer region of the extracorporeal circulation tubing, the boundary conditions of the tubing outer wall are set to be based on convective heat transfer between the tubing outer wall and the external environment; At the blood outlet of the extracorporeal circulation tubing, the outlet boundary condition is set to a free outflow condition with zero temperature gradient.

4. The method for calculating patient blood temperature during hemodialysis treatment according to claim 3, characterized in that, The geometric parameters, physical parameters, and operational parameters include: patient body temperature, dialysate temperature, ambient temperature, blood physical parameters, flow rate parameters, and geometric parameters of the extracorporeal circulation tubing.

5. The method for calculating patient blood temperature during hemodialysis treatment according to claim 4, characterized in that, The numerical solution of the constrained heat transfer model includes spatially and temporally discretizing the constrained heat transfer model and performing iterative calculations.

6. The method for calculating patient blood temperature during hemodialysis treatment according to claim 1, characterized in that, S2 includes the following sub-steps: S21. Based on the real-time scenario corresponding to the hemodialysis process, determine the fusion scenario and fusion weight, wherein the fusion scenario is characterized as a weighted combination of multiple standard scenarios, and each standard scenario corresponds to a set of preset model parameters; the fusion weight is determined based on the degree of difference between the operating parameters and the benchmark parameters of each standard scenario. S22. Based on the fusion weights, the preset model parameters corresponding to the multiple standard scenarios are fused to obtain the running parameters, wherein the fusion is performed based on a preset nonlinear weighting algorithm; S23. Constrain the transient heat transfer model based on the operating parameters to construct a constrained heat transfer model that reflects the boundary conditions of heat exchange in real-time scenarios.

7. The method for calculating patient blood temperature during hemodialysis treatment according to claim 6, characterized in that, S21 includes the following sub-steps: S211. Acquire and analyze historical change data of the operating parameters within a preset time window to generate a change pattern feature; wherein, the change pattern feature includes at least one or more features of the operating parameters on the first or second time derivative; S212. The fusion weights are dynamically adjusted according to the characteristics of the change pattern to obtain the final fusion weights.

8. The method for calculating patient blood temperature during hemodialysis treatment according to claim 7, characterized in that, S212 includes the following sub-steps: S2121. A weight adjustment model is preset, wherein the weight adjustment model is used to establish a mapping relationship between the change pattern features and the weight adjustment coefficients; S2122. Input the change pattern features into the weight adjustment model to calculate one or more weight adjustment coefficients for each of the standard scenarios; S2123. The fusion weights are corrected using the weight adjustment coefficients to generate the final dynamically adjusted fusion weights.

9. The method for calculating patient blood temperature during hemodialysis treatment according to claim 1, characterized in that, The standard scenario includes at least one of the following: a scenario in which only the ambient temperature deviates from the baseline, a scenario in which only the patient's body temperature deviates from the baseline, or a scenario in which only the blood flow rate deviates from the baseline.

10. A computer device, characterized in that, It includes: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to: perform a method for calculating a patient's blood temperature during hemodialysis treatment according to any one of claims 1 to 9.

Images