Body temperature adjusting system based on digital twinning and adjusting method thereof

Abstract

The invention discloses a body temperature adjusting system based on digital twinning and an adjusting method thereof, and relates to the technical field of body temperature management. According to the system, multi-dimensional physiological data of a patient, operation related data, operating room environment data and heat preservation equipment operation state data are obtained in real time through a data acquisition module, a patient body temperature digital twin model is constructed, and the model is dynamically updated and calibrated in the operation process; the body temperature change trend of the patient is predicted based on the digital twinborn model, an individualized body temperature adjusting strategy is generated before the body temperature deviates from a preset safety threshold value, a plurality of devices such as body surface heating, infusion heating, flushing fluid heating and environment adjusting are coordinated through the cooperative control module for cooperative execution, and accurate regulation and control of the body temperature are achieved. Real-time mapping, predictive adjustment and closed-loop optimization of the body temperature of the patient can be achieved, the risk of low body temperature and excessive heat preservation in the perioperative period is effectively reduced, the safety and the intelligent level of body temperature management are improved, and good clinical application value is achieved.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of body temperature management, and more particularly, the present application relates to a body temperature regulation system based on digital twinning and a regulation method thereof. BACKGROUND

[0002] Perioperative hypothermia is a common complication in surgical operation, usually refers to the core body temperature of patients below 36℃. During the operation, due to the factors such as exposure of surgical incision, inhibition of body temperature regulation function by anesthetic drugs, infusion or flushing of low temperature liquid, and lower environmental temperature in the operating room, patients are prone to body temperature drop, which in turn increases the risk of postoperative infection, coagulopathy, cardiovascular burden and prolonged hospitalization time, and even endangers the life safety of patients.

[0003] At present, the regulation of body temperature of surgical patients in clinic mainly depends on passive heat preservation measures and active heat preservation equipment. Passive heat preservation methods such as covering heat preservation blanket have limited heat preservation capacity; active heat preservation equipment such as body surface warming blanket, infusion warmer and flushing liquid warmer can provide heat supply, but they mostly use fixed parameters or rely on the experience of medical staff for adjustment, and it is difficult to fine control according to the individual differences of different patients and surgical scenes. In addition, the existing body temperature monitoring methods are mostly single-point and intermittent monitoring, and there is a lag between body temperature perception and regulation, and there is a lack of prediction ability for body temperature change trend, and there is also a lack of unified cooperative control mechanism among different heat preservation equipment, and the overall body temperature management effect is still insufficient.

[0004] Digital twinning technology can realize real-time mapping, dynamic prediction and optimization control of state by constructing a virtual model of physical entity. If digital twinning technology is introduced into the field of body temperature management of surgical patients, a digital twinning model of patient body temperature is constructed, and the prediction and individualized regulation of body temperature change are realized combined with multi-source data, which is expected to solve the problems of individualization deficiency, response lag and poor multi-device cooperation in existing body temperature regulation technology.

[0005] Therefore, it is urgent to provide a surgical patient body temperature individualized regulation system and method based on digital twinning to at least solve some of the above problems. SUMMARY

[0006] A series of simplified concepts are introduced in the summary section, which will be further described in detail in the specific embodiment section. The summary section of the present application does not mean to attempt to limit the key features and essential technical features of the claimed technical solutions, and even less to determine the protection scope of the claimed technical solutions.

[0007] In a first aspect, the present invention proposes a body temperature regulation system based on digital twins, comprising: a data acquisition module, a digital twin modeling module, a body temperature prediction and strategy optimization module, a collaborative control module, an execution module, a visualization interaction module, and a data storage and traceability module; The aforementioned data acquisition module is used to collect multi-dimensional physiological data, surgery-related data, environmental data, and operational status data of the aforementioned execution module in real time. The aforementioned digital twin modeling module is used to construct a basic digital twin model of the patient's body temperature based on the initial data collected by the aforementioned data acquisition module, and to dynamically update and calibrate the basic digital twin model of the patient's body temperature based on the real-time data collected during the operation. The aforementioned body temperature prediction and strategy optimization module is used to predict the patient's body temperature change trend within a preset time period based on the real-time virtual mapping data output by the aforementioned digital twin modeling module, combined with a preset body temperature safety threshold, and to generate an individualized body temperature regulation strategy when the prediction results meet preset conditions. The aforementioned collaborative control module is used to convert the aforementioned individualized body temperature regulation strategy into control instructions for the aforementioned execution module, and to coordinate the processing of multiple control instructions. The aforementioned execution module is used to perform heating operations and / or environmental adjustment operations according to the aforementioned control commands; The aforementioned visual interactive module is used to display the patient's body temperature status, predicted trends, and the implementation of control measures; The aforementioned data storage and traceability module is used to store data related to body temperature regulation generated during the surgical procedure.

[0008] In one feasible implementation, the aforementioned multidimensional physiological data includes core body temperature, body surface temperature distribution, heart rate, blood pressure, respiratory rate, blood oxygen saturation, and metabolic rate. The above-mentioned surgical data includes surgical type, surgical incision location and size, operation time, intraoperative infusion rate and fluid temperature, and intraoperative irrigation fluid volume and temperature; The environmental data mentioned above includes operating room temperature, humidity, and airflow speed; The operating status data of the above-mentioned execution module includes the working mode, output power and running time of each insulation device.

[0009] In one feasible implementation, the data acquisition module includes multiple types of sensors, a surgical information input unit, an environmental monitoring unit, and an equipment status monitoring unit. The aforementioned types of sensors include implantable core body temperature sensors, array-type body surface temperature sensors, and physiological parameter monitors; The aforementioned surgical information entry unit is used for medical staff to enter or synchronously obtain surgical-related data from the hospital information system and / or surgical anesthesia system; The aforementioned environmental monitoring unit is used to collect the aforementioned environmental data in real time; The aforementioned equipment status monitoring unit is used to collect the operating parameters of each of the aforementioned insulation devices in real time.

[0010] In one feasible implementation, the above-mentioned patient body temperature digital twin model includes a patient individual characteristics sub-model, a body temperature conduction sub-model, an environmental influence sub-model, and a device function sub-model. The above patient individual characteristic sub-models are constructed based on patient age, gender, weight, height, underlying diseases, and body fat percentage; The above-mentioned body temperature conduction sub-model is constructed based on the biological heat conduction equation and is used to simulate the generation, conduction and dissipation of heat in the patient's body; The above environmental impact sub-model is used to describe the influence of operating room environmental parameters on changes in patient body temperature; The aforementioned device function sub-model is used to simulate the regulatory effect of each of the aforementioned execution modules on the patient's body temperature; The aforementioned digital twin modeling module uses a Kalman filter algorithm to dynamically calibrate the parameters of the aforementioned patient body temperature digital twin model.

[0011] In one feasible implementation, the above-mentioned body temperature prediction and strategy optimization module uses a long short-term memory network algorithm or a gated recurrent unit algorithm to predict the trend of changes in the patient's body temperature. The aforementioned individualized body temperature regulation strategy includes the selection of the working mode, output power adjustment, and runtime planning for each of the aforementioned execution modules; The aforementioned collaborative control module incorporates a conflict detection and coordination algorithm. When there are potential regulatory conflicts between the control commands of multiple execution modules, the algorithm prioritizes and adjusts the parameters of the control commands based on the patient's current body temperature status and predicted trends.

[0012] Secondly, the present invention also proposes a method for individualized body temperature regulation of surgical patients based on digital twins, used in the digital twin-based individualized body temperature regulation system for surgical patients described in the first aspect, comprising: Acquire patient individual characteristic data, preoperative basal body temperature data, surgical plan data, and initial operating room environment data, and use the acquired data as input data for model initialization; Input the above model initialization input data into the digital twin modeling module to construct the basic model of the patient's body temperature digital twin and complete the initial setting of the model parameters; During the surgery, the data acquisition module collects multi-dimensional physiological and environmental data of the patient in real time and forms a real-time data stream for model updates. The aforementioned real-time data stream is input into the aforementioned patient body temperature digital twin model, and the aforementioned patient body temperature digital twin model is dynamically updated and its parameters are calibrated to obtain real-time virtual mapping data reflecting the patient's current body temperature status. Based on the above real-time virtual mapping data, predict the patient's body temperature change trend within a preset time period in the future, and generate an individualized body temperature regulation strategy when the prediction results meet the preset body temperature regulation conditions. Based on the above individualized body temperature regulation strategy, control commands are generated for each heat preservation device, and the execution module is driven to complete the body temperature regulation operation after the control commands are coordinated by the collaborative control module. The patient's body temperature is continuously monitored based on the adjustment results of the execution module, and the monitoring results are fed back to the aforementioned digital twin model of the patient's body temperature to perform closed-loop optimization of the aforementioned individualized body temperature regulation strategy.

[0013] In one feasible implementation, the aforementioned model initialization input data is input into the digital twin modeling module to construct a basic digital twin model of the patient's body temperature and to complete the initial setting of model parameters, including: Based on the patient's age, gender, weight, height, underlying diseases, and body fat percentage, a sub-model of the patient's individual characteristics is constructed. A body temperature conduction sub-model was constructed based on the biological heat conduction equation to simulate the generation, conduction and dissipation of heat in the patient's body; Based on the initial environmental data of the operating room mentioned above, an environmental impact sub-model was constructed to describe the impact of environmental factors on changes in patient body temperature. Based on the heating characteristic parameters of each heat preservation device, a device action sub-model is constructed to describe the regulatory effect of different heat preservation devices on the patient's body temperature. The above-mentioned patient individual characteristic sub-model, body temperature conduction sub-model, environmental influence sub-model, and equipment function sub-model are combined to form the above-mentioned patient body temperature digital twin basic model, and the initial setting of model parameters is completed.

[0014] In one feasible implementation, the aforementioned data acquisition module collects multi-dimensional physiological and environmental data from patients in real time and forms a real-time data stream for model updates, including: Real-time collection of multi-dimensional physiological data from patients, including core body temperature, surface temperature distribution, heart rate, blood pressure, respiratory rate, and metabolic rate; Real-time acquisition of environmental data such as intraoperative infusion temperature, infusion rate, operating room temperature, humidity, and airflow speed; The collected multidimensional physiological data and environmental data are time-synchronized and formatted to generate a real-time data stream with timestamps, which serves as input data for dynamic model updates.

[0015] In one feasible implementation, the aforementioned real-time data stream is input into the patient's body temperature digital twin model, and the patient's body temperature digital twin model is dynamically updated and its parameters calibrated to obtain real-time virtual mapping data reflecting the patient's current body temperature status, including: The aforementioned real-time data stream is matched with the current model parameters of the aforementioned patient body temperature digital twin basic model; The deviation between the model output and the actual monitoring data is calculated based on the aforementioned real-time data stream. The Kalman filter algorithm was used to dynamically calibrate the model parameters of the above-mentioned digital twin model of patient body temperature; Real-time virtual mapping data corresponding to the patient's current body temperature status is generated based on the calibrated model parameters.

[0016] In one feasible implementation, the above-mentioned prediction of the patient's body temperature change trend within a preset time period based on the aforementioned real-time virtual mapping data, and the generation of an individualized body temperature regulation strategy when the prediction result meets preset body temperature regulation conditions, includes: The above real-time virtual mapping data is input into the body temperature prediction model to predict the patient's body temperature change trend within a preset time period. The predicted trend of body temperature change is compared with the preset body temperature safety threshold to determine whether the body temperature regulation triggering condition is met. When the above-mentioned thermoregulation triggering conditions are met, an individualized thermoregulation strategy is generated by combining the patient's individual characteristics data and surgical plan data; The aforementioned individualized body temperature regulation strategy involves jointly setting the operating parameters of surface heating devices, infusion heating devices, irrigation fluid heating devices, and operating room environment regulation devices.

[0017] In summary, this embodiment continuously and in real-time collects multi-dimensional physiological data, surgical data, environmental data, and operational status data of the temperature-maintaining equipment from the patient through a data acquisition module. This overcomes the limitations of existing technologies that rely on single-point, intermittent temperature monitoring, enabling the system to comprehensively and dynamically grasp the true state of the patient's temperature changes and their influencing factors, thereby improving the perception accuracy and timeliness of temperature management from the source. A digital twin modeling module is introduced to construct a digital twin model of body temperature in virtual space that corresponds one-to-one with the patient's actual body temperature state, and the model is continuously updated and dynamically calibrated based on real-time data during the surgery. Unlike the prior art, which only performs simple feedback adjustments based on the current measurement value, this embodiment can characterize the mechanism of patient temperature changes at the model level, achieving real-time virtual mapping and continuous tracking of body temperature status, providing a reliable model foundation for subsequent prediction and decision-making. Through the temperature prediction and strategy optimization module, based on the digital twin model, the trend of the patient's body temperature changes within a preset time period is predicted and analyzed, and individualized temperature regulation strategies are generated in advance by combining preset body temperature safety thresholds. This approach effectively overcomes the lack of predictive regulation mechanisms in existing technologies, transforming thermoregulation from a passive response to active intervention. It allows for proactive measures to be taken before a significant drop or rise in body temperature, thereby significantly reducing the risk of perioperative hypothermia or overheating. This embodiment utilizes a collaborative control module to coordinate and control various warming devices, including surface warming, intravenous fluid warming, irrigation fluid warming, and operating room environmental regulation, avoiding the problems of independent operation, mutual interference, or regulatory conflicts among multiple devices in the prior art. By coordinating and processing multiple control commands, the system can drive the execution modules to work collaboratively according to the overall optimal strategy, significantly improving the overall effectiveness and stability of thermoregulation. A visual interactive module allows medical staff to intuitively and in real-time monitor the patient's temperature status, predicted trends, and the operation of each device, enabling manual intervention when necessary. This balances automated regulation with clinical safety, improving the system's operability and reliability in actual surgical scenarios. This embodiment systematically stores data on the entire perioperative temperature regulation process through a data storage and traceability module. This not only supports the traceability analysis and quality assessment of postoperative temperature management effectiveness but also provides a data foundation for subsequent model optimization and clinical research, further enhancing the system's long-term application value. In summary, by combining digital twin modeling with predictive control, real-time sensing, trend prediction, individualized regulation, and multi-device collaborative control of surgical patients' body temperature are achieved. Compared to the background technology, this approach demonstrates significant advantages in accuracy, foresight, safety, and system synergy, and possesses promising clinical application prospects.

[0018] Other advantages, objectives and features of this application will be apparent in part from the description which follows, and in part from what those skilled in the art will understand through study and practice of this application. Attached Figure Description

[0019] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A structural schematic diagram of a body temperature regulation system based on digital twin provided for an embodiment of this application; Figure 2 This is a flowchart illustrating a body temperature regulation method based on digital twins, provided as an embodiment of this application. Detailed Implementation

[0020] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The technical solutions of the embodiments of this application will now be clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0021] Please see Figure 1 The present application provides a body temperature regulation system based on digital twin, which includes: a data acquisition module 10, a digital twin modeling module 20, a body temperature prediction and strategy optimization module 30, a collaborative control module 40, an execution module 50, a visualization interaction module 60, and a data storage and traceability module 70. The aforementioned data acquisition module 10 is used to collect multi-dimensional physiological data, surgery-related data, environmental data, and operational status data of the surgical patient in real time, as well as the aforementioned execution module 50. The aforementioned digital twin modeling module 20 is used to construct a basic digital twin model of the patient's body temperature based on the initial data collected by the aforementioned data acquisition module 10, and to dynamically update and calibrate the basic digital twin model of the patient's body temperature based on the real-time data collected during the operation. The aforementioned body temperature prediction and strategy optimization module 30 is used to predict the patient's body temperature change trend within a preset time period based on the real-time virtual mapping data output by the aforementioned digital twin modeling module 20, combined with a preset body temperature safety threshold, and to generate an individualized body temperature regulation strategy when the prediction result meets the preset conditions. The aforementioned collaborative control module 40 is used to convert the aforementioned individualized body temperature regulation strategy into control instructions for the aforementioned execution module 50, and to coordinate the processing of multiple control instructions. The aforementioned execution module 50 is used to perform heating operations and / or environmental adjustment operations according to the aforementioned control instructions; The aforementioned visualization and interaction module 60 is used to display the patient's body temperature status, predicted trends, and adjustment implementation status; The aforementioned data storage and traceability module 70 is used to store data related to body temperature regulation generated during the surgical procedure.

[0022] For example, the body temperature regulation system based on digital twin described in this embodiment adopts a modular architecture design, mainly including a data acquisition module 10, a digital twin modeling module 20, a body temperature prediction and strategy optimization module 30, a collaborative control module 40, an execution module 50, a visualization interaction module 60, and a data storage and traceability module 70. The modules work together through data and control commands to achieve real-time perception, virtual mapping, trend prediction, and individualized regulation of the patient's body temperature during the operation.

[0023] The data acquisition module 10, serving as the system's perception layer, is used to collect multi-source heterogeneous data related to patient temperature changes in real time before and during surgery. On one hand, this module acquires multi-dimensional physiological data of the patient in real time, including core body temperature, surface temperature distribution, and parameters reflecting the body's thermometabolic state such as heart rate, blood pressure, respiratory rate, blood oxygen saturation, and metabolic rate. On the other hand, this module simultaneously collects surgery-related data, such as surgery type, incision location and size, surgery duration, intraoperative infusion rate and fluid temperature, and irrigation fluid volume and temperature. It also acquires operating room environmental data, including ambient temperature, humidity, and airflow speed. Furthermore, the data acquisition module 10 is also used to collect operational status data of each temperature-regulating device in the execution module 50, such as operating mode, output power, and operating time, providing a complete data foundation for subsequent temperature regulation decisions.

[0024] The digital twin modeling module 20, as the core modeling unit of the system, is used to construct a basic digital twin model of the patient's body temperature based on the initial data collected preoperatively by the data acquisition module 10. During the surgery, this model is continuously updated and dynamically calibrated using real-time data. Through this module, the system constructs a digital twin body temperature model in virtual space that corresponds to the patient's actual body temperature state, enabling real-time mapping and continuous tracking of changes in the patient's body temperature. This provides reliable model support for the formulation of body temperature prediction and regulation strategies.

[0025] The body temperature prediction and strategy optimization module 30 is used to predict and analyze the patient's body temperature change trend within a preset time period based on the real-time virtual mapping data output by the digital twin modeling module 20 and in conjunction with preset body temperature safety thresholds. When the prediction results indicate that the patient's body temperature may be lower or higher than the safety threshold range, this module comprehensively considers the patient's individual characteristics and the current surgical scenario, and automatically generates an individualized body temperature regulation strategy that matches the patient's condition, so as to realize the transformation of body temperature regulation from "post-event response" to "pre-event intervention".

[0026] The collaborative control module 40 is used to further convert the individualized body temperature regulation strategy generated by the body temperature prediction and strategy optimization module 30 into specific control instructions for the execution module 50, and to coordinate multiple control instructions in a unified manner. Through this module, the problems of regulation conflict or insufficient coordination that may occur when multiple temperature-preserving devices are running simultaneously can be effectively avoided, thereby ensuring that the body temperature regulation strategy can be executed in an orderly manner according to the overall optimal plan.

[0027] The execution module 50 receives control commands output by the collaborative control module 40 and performs corresponding body temperature regulation operations accordingly. This module may include surface heating devices, infusion heating devices, irrigation fluid heating devices, and operating room environment regulation devices. By comprehensively regulating the patient's body surface, infused fluids, and surrounding environment, it achieves precise regulation of the patient's body temperature.

[0028] The visualization and interaction module 60 is used to present the patient's body temperature status, predicted temperature trend, and the operation status of each execution module to medical staff in an intuitive way, enabling them to monitor changes in the patient's body temperature and the system's adjustment process in real time. Simultaneously, this module supports manual intervention. When medical staff detect abnormalities or need to temporarily adjust the adjustment strategy, they can issue manual control commands through this module to intervene in the automatic adjustment process.

[0029] The data storage and traceability module 70 is used to uniformly store various types of data generated throughout the entire surgical process, including physiological data, surgical data, environmental data, model update data, regulation strategy data, and execution module operation data, thereby forming a complete perioperative thermoregulation data archive, providing data support for postoperative analysis, quality assessment, and model optimization.

[0030] In summary, this embodiment continuously and in real-time collects multi-dimensional physiological data, surgical data, environmental data, and operational status data of the temperature-maintaining equipment from the patient through a data acquisition module. This overcomes the limitations of existing technologies that rely on single-point, intermittent temperature monitoring, enabling the system to comprehensively and dynamically grasp the true state of the patient's temperature changes and their influencing factors, thereby improving the perception accuracy and timeliness of temperature management from the source. A digital twin modeling module is introduced to construct a digital twin model of body temperature in virtual space that corresponds one-to-one with the patient's actual body temperature state, and the model is continuously updated and dynamically calibrated based on real-time data during the surgery. Unlike the prior art, which only performs simple feedback adjustments based on the current measurement value, this embodiment can characterize the mechanism of patient temperature changes at the model level, achieving real-time virtual mapping and continuous tracking of body temperature status, providing a reliable model foundation for subsequent prediction and decision-making. Through the temperature prediction and strategy optimization module, based on the digital twin model, the trend of the patient's body temperature changes within a preset time period is predicted and analyzed, and individualized temperature regulation strategies are generated in advance by combining preset body temperature safety thresholds. This approach effectively overcomes the lack of predictive regulation mechanisms in existing technologies, transforming thermoregulation from a passive response to active intervention. It allows for proactive measures to be taken before a significant drop or rise in body temperature, thereby significantly reducing the risk of perioperative hypothermia or overheating. This embodiment utilizes a collaborative control module to coordinate and control various warming devices, including surface warming, intravenous fluid warming, irrigation fluid warming, and operating room environmental regulation, avoiding the problems of independent operation, mutual interference, or regulatory conflicts among multiple devices in the prior art. By coordinating and processing multiple control commands, the system can drive the execution modules to work collaboratively according to the overall optimal strategy, significantly improving the overall effectiveness and stability of thermoregulation. A visual interactive module allows medical staff to intuitively and in real-time monitor the patient's temperature status, predicted trends, and the operation of each device, enabling manual intervention when necessary. This balances automated regulation with clinical safety, improving the system's operability and reliability in actual surgical scenarios. This embodiment systematically stores data on the entire perioperative temperature regulation process through a data storage and traceability module. This not only supports the traceability analysis and quality assessment of postoperative temperature management effectiveness but also provides a data foundation for subsequent model optimization and clinical research, further enhancing the system's long-term application value. In summary, by combining digital twin modeling with predictive control, real-time sensing, trend prediction, individualized regulation, and multi-device collaborative control of surgical patients' body temperature are achieved. Compared to the background technology, this approach demonstrates significant advantages in accuracy, foresight, safety, and system synergy, and possesses promising clinical application prospects.

[0031] In one feasible implementation, the aforementioned multidimensional physiological data includes core body temperature, body surface temperature distribution, heart rate, blood pressure, respiratory rate, blood oxygen saturation, and metabolic rate. The above-mentioned surgical data includes surgical type, surgical incision location and size, operation time, intraoperative infusion rate and fluid temperature, and intraoperative irrigation fluid volume and temperature; The environmental data mentioned above includes operating room temperature, humidity, and airflow speed; The operating status data of the above-mentioned execution module includes the working mode, output power and running time of each insulation device.

[0032] For example, during operation, the system comprehensively collects and fuses multi-source information to achieve a complete characterization and precise regulation of the patient's body temperature status. Specifically, the multi-dimensional physiological data includes not only core body temperature, which reflects the patient's core thermal state, but also surface temperature distribution, which describes heat dissipation from the body surface. Furthermore, it combines parameters such as heart rate, blood pressure, respiratory rate, blood oxygen saturation, and metabolic rate to comprehensively characterize the patient's circulatory function, respiratory status, and energy metabolism level, thereby providing a more complete physiological basis for modeling the mechanism of body temperature changes.

[0033] At the same time, the system synchronously acquires surgery-related data that are highly correlated with changes in body temperature, such as the type of surgery, the location and size of the surgical incision, and the duration of the surgery, to reflect the impact of the surgical exposure range and duration on heat loss. By collecting information such as intraoperative infusion rate and fluid temperature, intraoperative irrigation fluid volume and temperature, it can accurately describe the risk of body temperature drop caused by low-temperature fluid input or irrigation operations, providing an important reference for the formulation of subsequent body temperature prediction and regulation strategies.

[0034] In addition, considering that the operating room environment has a continuous and significant impact on the patient's body temperature, this embodiment also includes environmental data such as operating room temperature, humidity, and airflow speed in the collection scope to characterize the impact of environmental conditions on the heat exchange process of the patient's body surface, so that the body temperature digital twin model can more realistically reflect the actual surgical scenario.

[0035] Building upon this foundation, the system also monitors the operational status data of the execution modules in real time, including parameters such as the working mode, output power, and runtime of each temperature-maintaining device. By correlating and analyzing the aforementioned operational status data with patient physiological data, surgical data, and environmental data, the system can accurately assess the actual effectiveness of current temperature regulation measures and provide a reliable basis for temperature prediction, strategy optimization, and closed-loop regulation, thereby achieving continuous monitoring and individualized precise control of the patient's body temperature during surgery.

[0036] In one feasible implementation, the data acquisition module 10 includes multiple types of sensors 101, a surgical information input unit 102, an environmental monitoring unit 103, and an equipment status monitoring unit 104. The aforementioned multi-type sensors 101 include implantable core body temperature sensors, array-type body surface temperature sensors, and physiological parameter monitors; The surgical information entry unit 102 is used for medical staff to enter or synchronously obtain surgical-related data from the hospital information system and / or surgical anesthesia system; The aforementioned environmental monitoring unit 103 is used to collect the aforementioned environmental data in real time; The aforementioned equipment status monitoring unit 104 is used to collect the operating parameters of each of the aforementioned insulation devices in real time.

[0037] For example, the data acquisition module 10, serving as the system's information sensing and data entry point, employs a multi-unit collaborative approach to comprehensively acquire information related to patient body temperature regulation. This data acquisition module 10 includes multiple types of sensors 101, a surgical information input unit 102, an environmental monitoring unit 103, and an equipment status monitoring unit 104. These units cooperate functionally and remain synchronized in time, providing a continuous and reliable data foundation for subsequent digital twin modeling and body temperature regulation decisions.

[0038] The multi-type sensors 101 are used to directly acquire the patient's physiological status information, specifically including an implantable core body temperature sensor, an array-type body surface temperature sensor, and a physiological parameter monitor. The implantable core body temperature sensor allows for continuous monitoring of the patient's core body temperature. The array-type body surface temperature sensor acquires temperature distribution data across different areas of the patient's body surface, reflecting heat dissipation characteristics. The physiological parameter monitor simultaneously collects vital signs such as heart rate and blood pressure, enabling the system to characterize the patient's thermometabolism and physiological state from multiple dimensions.

[0039] The surgical information entry unit 102 is used to acquire surgical information closely related to changes in body temperature. On the one hand, medical staff can manually enter information such as the type of surgery, incision location and size, and estimated surgery duration through this unit. On the other hand, this unit can also interface with the hospital information system and / or surgical anesthesia system to automatically and synchronously acquire relevant surgical data, thereby reducing the burden of manual data entry and improving data accuracy and consistency.

[0040] The environmental monitoring unit 103 is used to collect environmental data in the operating room in real time, including parameters such as ambient temperature, humidity, and airflow speed. By continuously monitoring the environmental conditions in the operating room, the system can accurately assess the impact of the external environment on the heat exchange process of the patient's body surface and incorporate this impact into the digital twin model of body temperature for comprehensive analysis.

[0041] The equipment status monitoring unit 104 is used to collect the operating parameters of each temperature-maintaining device in real time, including information such as working mode, output power, and operating time. Through continuous monitoring of the status of the above-mentioned equipment, the system can grasp the implementation status of the current body temperature regulation measures in real time and feed the relevant data back to the digital twin model and body temperature regulation control logic, so as to evaluate and optimize the regulation effect, thereby realizing closed-loop management of the patient's body temperature regulation process.

[0042] In one feasible implementation, the above-mentioned patient body temperature digital twin modeling module 20 includes a patient individual characteristic sub-model 201, a body temperature conduction sub-model 202, an environmental influence sub-model 203, and a device function sub-model 204. The aforementioned patient individual characteristic sub-model 201 is constructed based on the patient's age, gender, weight, height, underlying diseases, and body fat percentage; The aforementioned body temperature conduction sub-model 202 is constructed based on the biological heat conduction equation and is used to simulate the generation, conduction and dissipation of heat in the patient's body; The aforementioned environmental impact sub-model 203 is used to describe the influence of operating room environmental parameters on changes in patient body temperature; The aforementioned device function sub-model 204 is used to simulate the regulatory effect of each of the aforementioned execution modules 50 on the patient's body temperature; The aforementioned digital twin modeling module 20 dynamically calibrates the parameters of the aforementioned patient body temperature digital twin model using a Kalman filter algorithm.

[0043] For example, the patient body temperature digital twin modeling module 20 adopts a layered and decoupled modeling approach, which breaks down the key factors affecting changes in the patient's body temperature into multiple functionally distinct and interrelated sub-models, thereby constructing a digital twin body temperature model in virtual space that is highly consistent with the patient's actual body temperature state.

[0044] Specifically, the patient individual characteristics sub-model 201 is used to characterize the innate and baseline differences in thermoregulation ability among different patients. This sub-model is constructed based on individual characteristic parameters such as age, gender, weight, height, underlying diseases, and body fat percentage, and is used to reflect individual differences in metabolic level, heat generation capacity, and heat storage and dissipation characteristics, thus providing a foundation for individualized modeling of the digital twin model.

[0045] The body temperature conduction sub-model 202 is used to describe the dynamic changes in heat within a patient's body. This sub-model is constructed based on the biological heat conduction equation. By modeling the processes of heat generation within the body, heat conduction between tissues, and heat loss to the body surface and the external environment, it simulates the physical mechanism of changes in the patient's core body temperature and body surface temperature, thereby providing theoretical support for predicting the trend of body temperature changes.

[0046] The environmental impact sub-model 203 is used to describe the mechanism by which operating room environmental conditions affect changes in patient body temperature. By incorporating environmental parameters such as operating room temperature, humidity, and airflow velocity into this sub-model, the continuous effect of environmental factors on the heat exchange process on the patient's body surface can be reflected, enabling the digital twin model to realistically reproduce the characteristics of changes in patient body temperature under different operating room environmental conditions.

[0047] The equipment function sub-model 204 is used to simulate the effect of each execution module 50 on the patient's body temperature regulation. Based on the working mode, output power and corresponding heat input characteristics of different heating devices, this sub-model describes the impact of measures such as body surface heating, infusion heating, flushing fluid heating and environmental regulation on the patient's body temperature, thereby realizing a virtual simulation of the combined effect of multiple body temperature regulation methods.

[0048] After the aforementioned sub-models are constructed, the digital twin modeling module 20 dynamically calibrates the parameters of the patient's body temperature digital twin model using a Kalman filter algorithm. By comparing and analyzing the real-time collected patient physiological data with the model output results, the deviation of the model parameters is continuously corrected, enabling the virtual model to consistently match the patient's actual body temperature state. This achieves real-time virtual mapping and high-precision dynamic modeling of the patient's body temperature state, providing a reliable model foundation for subsequent body temperature prediction, strategy optimization, and closed-loop regulation.

[0049] In one feasible implementation, the above-mentioned body temperature prediction and strategy optimization module 30 uses a long short-term memory network algorithm or a gated recurrent unit algorithm to predict the trend of patient body temperature changes. The aforementioned individualized body temperature regulation strategy includes the selection of the working mode, output power adjustment, and runtime planning for each of the aforementioned execution modules 50; The aforementioned collaborative control module 40 has a built-in conflict detection and coordination algorithm. When there is a potential regulatory conflict between the control commands of multiple execution modules 50, the algorithm prioritizes and adjusts the parameters of the control commands based on the patient's current body temperature status and predicted trend.

[0050] For example, the body temperature prediction and strategy optimization module 30, as the system's intelligent decision-making unit, performs a forward-looking analysis of the future trend of the patient's body temperature based on the real-time virtual mapping data output by the patient's body temperature digital twin model. Specifically, this module uses a long short-term memory network algorithm or a gated recurrent unit algorithm to model the patient's body temperature time series data during surgery. By mining the temporal correlation between body temperature changes and the patient's physiological state, surgical progress, and environmental conditions, it can predict the trend of the patient's body temperature changes within a preset time period, thereby providing a predictive basis for body temperature regulation.

[0051] After obtaining the predicted trend of body temperature changes, the body temperature prediction and strategy optimization module 30 further combines the patient's current body temperature status, individual characteristics, and predicted trend to generate an individualized body temperature regulation strategy that matches the patient's status. This individualized body temperature regulation strategy does not independently control a single device, but rather comprehensively considers the synergistic effects of each execution module 50. It selects the operating modes of the surface heating device, infusion heating device, irrigation fluid heating device, and operating room environment regulation device, and plans their output power and operating time as a whole, thereby reducing energy consumption and avoiding excessive intervention while ensuring body temperature safety.

[0052] To ensure the safe and effective execution of the aforementioned individualized body temperature regulation strategy, this embodiment also utilizes a collaborative control module 40 to coordinate the multi-device regulation process. The collaborative control module 40 incorporates a conflict detection and coordination algorithm to perform logical verification and conflict judgment on the control commands of multiple execution modules 50 simultaneously participating in body temperature regulation. When potential conflicts are detected in the control commands of multiple execution modules 50 regarding regulation direction or intensity—for example, simultaneous occurrence of regulation combinations that may lead to overheating—the collaborative control module 40 prioritizes and adjusts the parameters of each control command based on the patient's current body temperature status and predicted temperature change trends, thereby forming a coordinated and consistent control scheme.

[0053] Through the combination of the above-mentioned body temperature prediction, strategy optimization and collaborative control mechanisms, this embodiment can realize a closed-loop control process from body temperature trend prediction to multi-device collaborative adjustment, so that body temperature regulation is transformed from traditional experience-based and passive control to active and individualized intelligent regulation based on digital twins and prediction models, thereby significantly improving the safety and precision of patient body temperature management during surgery.

[0054] The second aspect, such as Figure 2 As shown, the present invention also proposes a method for individualized body temperature regulation of surgical patients based on digital twins, used in the digital twin-based individualized body temperature regulation system for surgical patients described in the first aspect, comprising: S210. Acquire patient individual characteristic data, preoperative basal body temperature data, surgical plan data, and initial operating room environment data, and use the acquired data as input data for model initialization. S220. Input the above model initialization input data into the digital twin modeling module to construct the basic model of the patient's body temperature digital twin and complete the initial setting of the model parameters. S230. During the operation, the patient's multi-dimensional physiological data and environmental data are collected in real time based on the data acquisition module, and a real-time data stream is formed for model updates. S240. Input the above real-time data stream into the above patient body temperature digital twin model, and dynamically update and calibrate the parameters of the above patient body temperature digital twin model to obtain real-time virtual mapping data reflecting the patient's current body temperature status. S250. Based on the above real-time virtual mapping data, predict the patient's body temperature change trend within a preset time period in the future, and generate an individualized body temperature regulation strategy when the prediction result meets the preset body temperature regulation conditions. S260. Based on the above individualized body temperature regulation strategy, control instructions are generated for each heat preservation device, and the execution module is driven to complete the body temperature regulation operation after the control instructions are coordinated by the collaborative control module. S270. Based on the adjustment results of the execution module, the patient's body temperature is continuously monitored, and the monitoring results are fed back to the above-mentioned digital twin model of the patient's body temperature to perform closed-loop optimization of the above-mentioned individualized body temperature regulation strategy.

[0055] For example, the individualized temperature regulation method for surgical patients based on digital twin proposed in this invention uses the individualized temperature regulation system described in the first aspect as the implementation carrier. Through a closed-loop process of "data acquisition - digital twin modeling - temperature prediction - collaborative regulation - feedback optimization", it realizes continuous sensing, dynamic prediction and individualized regulation and control of the patient's body temperature during surgery.

[0056] Specifically, in step S210, the system first acquires the patient's individual characteristic data, preoperative basal body temperature data, surgical plan data, and initial operating room environment data during the preoperative stage, and uses these data as unified input data for model initialization. The patient's individual characteristic data reflects the differences in thermoregulation ability and thermometabolism levels among different patients; the preoperative basal body temperature data determines the initial body temperature state; the surgical plan data describes information such as the type of surgery, incision location, and expected surgery duration; and the initial operating room environment data characterizes the initial impact of the external environment on the patient's body temperature, thus providing a complete foundation for the subsequent construction of the digital twin model.

[0057] In step S220, the system inputs the aforementioned model initialization input data into the digital twin modeling module, constructs a basic digital twin model of the patient's body temperature in virtual space, and completes the initial setting of model parameters. Through this step, the system forms an initial digital twin model of body temperature that reflects the patient's individual characteristics, physiological state, and the influence of the surgical environment, laying the foundation for the dynamic simulation of intraoperative body temperature changes.

[0058] In step S230, after the surgery begins, the system continuously and in real-time collects the patient's multi-dimensional physiological data and environmental data through the data acquisition module, and organizes the collected data into a real-time data stream for model updates. The aforementioned multi-dimensional physiological data includes the patient's core body temperature, body surface temperature distribution, and vital sign parameters, while the environmental data includes operating room temperature, humidity, and airflow speed, thereby ensuring that the model input data can comprehensively reflect the actual influencing factors of the patient's body temperature changes.

[0059] In step S240, the system inputs the aforementioned real-time data stream into the patient's digital twin model of body temperature, dynamically updating and calibrating the model's parameters. By comparing and analyzing the model's output with the real-time monitoring data and continuously correcting the model parameters, the virtual model can maintain a high degree of consistency with the patient's current body temperature status, thereby generating virtual mapping data reflecting the patient's real-time body temperature status.

[0060] In step S250, the system predicts and analyzes the patient's body temperature change trend within a preset time period based on the aforementioned real-time virtual mapping data. When the prediction results indicate that the patient's body temperature may deviate from the preset safe temperature range, the system automatically generates an individualized body temperature regulation strategy that matches the patient's condition, taking into account the patient's individual characteristics and the current progress of the surgery, thus realizing the transformation of body temperature regulation from passive response to predictive intervention.

[0061] In step S260, the system generates control commands for each warming device based on the aforementioned individualized body temperature regulation strategy, and coordinates these control commands through a collaborative control module. By performing conflict detection and parameter adjustment on the control commands for multiple warming devices, the system ensures that each execution module can operate collaboratively according to the overall optimal regulation scheme, thereby driving the execution modules to complete the actual regulation operation of the patient's body temperature.

[0062] In step S270, while performing the body temperature regulation operation, the system continuously monitors the patient's body temperature and feeds the monitoring results back to the patient's digital twin model of body temperature. By incorporating the actual changes in body temperature after regulation into the model analysis again, closed-loop optimization of the individualized body temperature regulation strategy is achieved, enabling the system to continuously adjust the regulation strategy according to the real-time changes in the patient's body temperature, thereby maintaining the patient's body temperature within a safe and stable range throughout the entire surgical procedure.

[0063] In one feasible implementation, the aforementioned model initialization input data is input into the digital twin modeling module to construct a basic digital twin model of the patient's body temperature and to complete the initial setting of model parameters, including: Based on the patient's age, gender, weight, height, underlying diseases, and body fat percentage, a sub-model of the patient's individual characteristics is constructed. A body temperature conduction sub-model was constructed based on the biological heat conduction equation to simulate the generation, conduction and dissipation of heat in the patient's body; Based on the initial environmental data of the operating room mentioned above, an environmental impact sub-model was constructed to describe the impact of environmental factors on changes in patient body temperature. Based on the heating characteristic parameters of each heat preservation device, a device action sub-model is constructed to describe the regulatory effect of different heat preservation devices on the patient's body temperature. The above-mentioned patient individual characteristic sub-model, body temperature conduction sub-model, environmental influence sub-model, and equipment function sub-model are combined to form the above-mentioned patient body temperature digital twin basic model, and the initial setting of model parameters is completed.

[0064] For example, the construction and initialization of the patient's body temperature digital twin basic model is completed by multi-sub-model collaborative fusion to ensure that the virtual model can comprehensively and accurately reflect the mechanism of the patient's body temperature changes in the surgical scenario.

[0065] Specifically, firstly, based on individual characteristics such as age, gender, weight, height, underlying diseases, and body fat percentage, a sub-model of individual patient characteristics is constructed. This sub-model characterizes the differences among different patients in basal metabolic rate, thermogenic capacity, and body heat distribution characteristics, enabling the digital twin model to perform individualized modeling for different patients.

[0066] Based on this, a body temperature conduction sub-model was constructed. This sub-model is based on the biological heat conduction equation and is used to simulate the generation, conduction and dissipation of heat between different tissues in the patient's body, thereby describing the physical mechanism of changes in core body temperature and body surface temperature over time, and providing theoretical support for the accurate simulation of body temperature change trends.

[0067] The system constructs an environmental impact sub-model based on the initial environmental data of the operating room. By introducing environmental factors such as operating room temperature, humidity and airflow speed, it models the impact of the external environment on the heat exchange process of the patient's body surface, so that the digital twin model can truly reflect the changes in the patient's body temperature under different environmental conditions.

[0068] The system also constructs a sub-model of the device's function based on the heating characteristic parameters of each warming device. This sub-model describes the regulatory effects of different warming devices on patient body temperature, such as surface warming, infusion warming, flushing fluid warming, and environmental regulation. Through this sub-model, the effects of different devices on patient body temperature under different operating parameters can be simulated and evaluated.

[0069] After constructing the aforementioned sub-models, the patient individual characteristics sub-model, body temperature conduction sub-model, environmental influence sub-model, and equipment function sub-model are combined and fused to form a basic digital twin model of the patient's body temperature, and the model parameters are initially set. The basic digital twin model constructed in this way can accurately reflect the patient's initial body temperature status in the preoperative stage and provide a reliable model foundation for dynamic model updates, body temperature prediction, and the generation of individualized adjustment strategies during subsequent surgery.

[0070] In one feasible implementation, the aforementioned data acquisition module collects multi-dimensional physiological and environmental data from patients in real time and forms a real-time data stream for model updates, including: Real-time collection of multi-dimensional physiological data from patients, including core body temperature, surface temperature distribution, heart rate, blood pressure, respiratory rate, and metabolic rate; Real-time acquisition of environmental data such as intraoperative infusion temperature, infusion rate, operating room temperature, humidity, and airflow speed; The collected multidimensional physiological data and environmental data are time-synchronized and formatted to generate a real-time data stream with timestamps, which serves as input data for dynamic model updates.

[0071] For example, during the operation, the system continuously and in real time collects key data related to changes in the patient's body temperature through the data acquisition module, and forms a real-time data stream for updating the digital twin model to ensure the timeliness and consistency of the model input.

[0072] Specifically, the system first collects multi-dimensional physiological data from patients in real time, including core body temperature, which reflects the patient's core thermal state, and surface temperature distribution, which describes the heat dissipation characteristics of the body surface. Simultaneously, the system also collects vital signs parameters such as heart rate, blood pressure, respiratory rate, and metabolic rate to comprehensively reflect the patient's circulatory status, respiratory status, and energy metabolism level, thus providing a more comprehensive physiological background for the analysis of the mechanisms of body temperature changes.

[0073] While collecting physiological data, the system also acquires environmental data and intraoperative operational data that are closely related to changes in body temperature in real time. For example, by collecting intraoperative infusion temperature and infusion rate, the system can accurately reflect the impact of low temperature or high flow rate of fluids on the patient's body temperature; by collecting environmental parameters such as operating room temperature, humidity, and airflow speed, the system can characterize the continuous effect of external environmental conditions on the heat exchange process of the patient's body surface.

[0074] After completing the multi-source data acquisition, the system performs unified time synchronization and formatting on the collected multi-dimensional physiological and environmental data. By adding unified timestamps to various types of data and organizing them according to a preset data structure, a continuous and standardized real-time data stream is formed. This real-time data stream serves as input data for the dynamic updating and parameter calibration of the digital twin model, enabling the model to adjust in real time based on the latest patient status and environmental conditions, thereby achieving high-precision virtual mapping of the patient's body temperature status and subsequent predictive analysis.

[0075] In one feasible implementation, the aforementioned real-time data stream is input into the patient's body temperature digital twin model, and the patient's body temperature digital twin model is dynamically updated and its parameters calibrated to obtain real-time virtual mapping data reflecting the patient's current body temperature status, including: The aforementioned real-time data stream is matched with the current model parameters of the aforementioned patient body temperature digital twin basic model; The deviation between the model output and the actual monitoring data is calculated based on the aforementioned real-time data stream. The Kalman filter algorithm was used to dynamically calibrate the model parameters of the above-mentioned digital twin model of patient body temperature; Real-time virtual mapping data corresponding to the patient's current body temperature status is generated based on the calibrated model parameters.

[0076] For example, the patient's body temperature digital twin model is continuously updated and adaptively calibrated during surgery by introducing real-time data streams, thereby ensuring that the virtual model can always accurately reflect the patient's current body temperature status.

[0077] Specifically, the system first inputs the real-time data stream generated during real-time acquisition into the patient's digital twin model of body temperature, and then matches it with the current model parameters of the patient's basic digital twin model of body temperature. Through this matching process, the model can receive the latest patient physiological state and environmental information within the existing structure and parameter framework, providing a basis for subsequent error analysis and parameter correction.

[0078] Based on this, the system calculates the deviation between the output of the digital twin model and the actual monitored patient body temperature data using real-time data streams. By analyzing the differences between the model's predicted values ​​and the actual measured values, the system can identify the degree and trend of deviation in the model at the current moment, thus providing a quantitative basis for adjusting model parameters.

[0079] Subsequently, the system employs a Kalman filter algorithm to dynamically calibrate the model parameters of the patient's digital twin model of body temperature. By introducing the recursive estimation mechanism of the Kalman filter, the model parameters are smoothly corrected while considering measurement noise and model uncertainty, enabling the model to gradually approximate the true pattern of patient body temperature changes and avoiding drastic fluctuations in the model due to a single abnormal data point.

[0080] After parameter calibration, the system recalculates the model output based on the calibrated model parameters, generating real-time virtual mapping data corresponding to the patient's current body temperature status. This real-time virtual mapping data characterizes the patient's body temperature status in virtual space and serves as the core input for subsequent prediction of body temperature trends, generation of individualized body temperature regulation strategies, and closed-loop regulation control, thereby achieving high-precision, real-time digital twin mapping of the patient's body temperature status.

[0081] In one feasible implementation, the above-mentioned prediction of the patient's body temperature change trend within a preset time period based on the aforementioned real-time virtual mapping data, and the generation of an individualized body temperature regulation strategy when the prediction result meets preset body temperature regulation conditions, includes: The above real-time virtual mapping data is input into the body temperature prediction model to predict the patient's body temperature change trend within a preset time period. The predicted trend of body temperature change is compared with the preset body temperature safety threshold to determine whether the body temperature regulation triggering condition is met. When the above-mentioned thermoregulation triggering conditions are met, an individualized thermoregulation strategy is generated by combining the patient's individual characteristics data and surgical plan data; The aforementioned individualized body temperature regulation strategy involves jointly setting the operating parameters of surface heating devices, infusion heating devices, irrigation fluid heating devices, and operating room environment regulation devices.

[0082] For example, after completing the real-time digital twin mapping of the patient's body temperature status, the system further predicts and analyzes the future trend of the patient's body temperature based on the real-time virtual mapping data, thereby realizing the transformation of body temperature regulation from passive response to predictive intervention.

[0083] Specifically, the system first inputs the real-time virtual mapping data into the body temperature prediction model to predict the patient's body temperature change trend over a preset time period. By analyzing the characteristics of the body temperature time series, the body temperature prediction model can comprehensively consider the patient's current body temperature status, the rate of body temperature change, and related physiological and environmental factors to make a forward-looking estimate of the future trend of body temperature changes.

[0084] After obtaining the predicted body temperature trend, the system compares the predicted trend with a preset safe body temperature threshold to determine whether the patient's body temperature is at risk of deviating from the safe range. When the prediction result indicates that the patient's body temperature may be lower or higher than the safe body temperature threshold, the system determines that the body temperature regulation trigger condition is met, and thus enters the regulation strategy generation stage.

[0085] When the above-mentioned thermoregulation triggering conditions are met, the system comprehensively analyzes the thermoregulation needs by combining the patient's individual characteristic data and surgical plan data. By taking into account factors such as the patient's age, physical characteristics, underlying diseases, current surgical type, surgical progress, and expected duration, the system generates an individualized thermoregulation strategy that matches the patient's actual condition, in order to avoid the problems of insufficient or excessive heat preservation caused by uniform parameter adjustment.

[0086] The individualized body temperature regulation strategy is formulated using a multi-device joint regulation approach, specifically including the joint setting of operating parameters for surface heating devices, infusion heating devices, irrigation fluid heating devices, and operating room environment regulation devices. Through the coordinated configuration of multiple body temperature regulation methods, the system can achieve stable regulation of the patient's body temperature while ensuring body temperature safety, providing a clear control basis for the subsequent collaborative control and execution module's actual operation.

[0087] In one feasible implementation, the system software adopts a modular architecture design, corresponding to data acquisition, digital twin modeling, body temperature prediction and strategy optimization, collaborative control, visualization interaction, and data storage and traceability functional modules.

[0088] The data acquisition module software can be developed using the C# language to realize real-time acquisition, filtering and preprocessing, data format conversion and network transmission of multi-sensor data. The data is transmitted to the core processing unit through the TCP / IP protocol, and the data update frequency is 1 time / second.

[0089] The digital twin modeling module software can be developed using Python and employs an object-oriented approach to construct sub-models of individual patient characteristics, body temperature conduction, environmental influences, and equipment effects. The body temperature conduction sub-model is based on the Pennes biological heat conduction equation and solved numerically using the finite difference method. The model parameters are dynamically calibrated using a Kalman filter algorithm at a rate of one second per calibration cycle to ensure consistency between the virtual model and the patient's actual body temperature.

[0090] The body temperature prediction and strategy optimization module can implement a long short-term memory network model based on the TensorFlow framework. The model input includes the patient's core body temperature, body surface temperature distribution, metabolic rate, surgical progress, environmental parameters, and equipment operation data within the past 5 minutes. The output is the predicted body temperature values ​​for the next 10 minutes and 30 minutes. When the predicted body temperature exceeds the preset body temperature safety threshold range, the system calls the optimization model based on a genetic algorithm to generate an individualized body temperature regulation strategy.

[0091] The collaborative control module can be developed using Python. It incorporates a conflict detection algorithm based on rule-based reasoning and a coordination algorithm based on priority sorting to convert the regulation strategy into specific control instructions and send them to each execution module. When an equipment abnormality or fault is detected, a backup regulation strategy is automatically triggered.

[0092] The visualization and interaction module can be developed based on the Qt framework, supporting two-dimensional and three-dimensional visualization displays. The patient's digital twin model of body temperature presents the surface temperature distribution in three-dimensional form and supports manual intervention. The data storage and traceability module uses a MySQL database to store data related to the entire perioperative temperature regulation process.

[0093] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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 this application.

Claims

1. A digital twin-based individualized body temperature regulation system for surgical patients, characterized in that, include: The system includes a data acquisition module, a digital twin modeling module, a body temperature prediction and strategy optimization module, a collaborative control module, an execution module, a visualization and interaction module, and a data storage and traceability module. The data acquisition module is used to collect multi-dimensional physiological data, surgery-related data, environmental data, and the operating status data of the execution module in real time from the surgical patient. The digital twin modeling module is used to construct a basic digital twin model of the patient's body temperature based on the initial data collected by the data acquisition module, and to dynamically update and calibrate the basic digital twin model of the patient's body temperature based on the real-time data collected during the operation. The body temperature prediction and strategy optimization module is used to predict the patient's body temperature change trend within a preset time period based on the real-time virtual mapping data output by the digital twin modeling module and a preset body temperature safety threshold, and to generate an individualized body temperature regulation strategy when the prediction result meets the preset conditions. The collaborative control module is used to convert the individualized body temperature regulation strategy into control instructions for the execution module, and to coordinate the processing of multiple control instructions. The execution module is used to perform heating operations and / or environmental adjustment operations according to the control instructions; The visualization and interaction module is used to display the patient's body temperature status, predicted trends, and adjustment implementation status; The data storage and traceability module is used to store data related to body temperature regulation generated during the surgery.

2. The digital twin-based individualized body temperature regulation system for surgical patients according to claim 1, characterized in that, The multidimensional physiological data include core body temperature, body surface temperature distribution, heart rate, blood pressure, respiratory rate, blood oxygen saturation, and metabolic rate. The surgical data includes the type of surgery, the location and size of the surgical incision, the duration of the surgery, the intraoperative infusion rate and fluid temperature, and the volume and temperature of the intraoperative irrigation fluid. The environmental data includes operating room temperature, humidity, and airflow speed; The operating status data of the execution module includes the working mode, output power, and running time of each insulation device.

3. The individualized body temperature regulation system for surgical patients based on digital twins according to claim 1, characterized in that, The data acquisition module includes multiple types of sensors, a surgical information input unit, an environmental monitoring unit, and an equipment status monitoring unit; The various types of sensors include implantable core body temperature sensors, array-type body surface temperature sensors, and physiological parameter monitors. The surgical information input unit is used for medical staff to input surgical-related data or to synchronously obtain surgical data from the hospital information system and / or surgical anesthesia system. The environmental monitoring unit is used to collect the environmental data in real time; The equipment status monitoring unit is used to collect the operating parameters of each of the insulation devices in real time.

4. The individualized body temperature regulation system for surgical patients based on digital twins according to claim 1, characterized in that, The patient's body temperature digital twin model includes a patient individual characteristics sub-model, a body temperature conduction sub-model, an environmental influence sub-model, and a device function sub-model. The patient individual characteristic sub-model is constructed based on the patient's age, gender, weight, height, underlying diseases, and body fat percentage; The body temperature conduction sub-model is constructed based on the biological heat conduction equation and is used to simulate the generation, conduction and dissipation of heat in the patient's body; The environmental impact sub-model is used to describe the influence of operating room environmental parameters on changes in patient body temperature. The device function sub-model is used to simulate the regulatory effect of each of the execution modules on the patient's body temperature; The digital twin modeling module uses a Kalman filter algorithm to dynamically calibrate the parameters of the patient's body temperature digital twin model.

5. The individualized body temperature regulation system for surgical patients based on digital twins according to claim 1, characterized in that, The body temperature prediction and strategy optimization module uses a long short-term memory network algorithm or a gated recurrent unit algorithm to predict the trend of changes in the patient's body temperature. The individualized body temperature regulation strategy includes the selection of working mode, output power adjustment and runtime planning for each of the execution modules. The collaborative control module has a built-in conflict detection and coordination algorithm. When there is a potential regulatory conflict between the control commands of multiple execution modules, the control commands are prioritized and the parameters are adjusted based on the patient's current body temperature status and predicted trend.

6. A method for individualized body temperature regulation of surgical patients based on digital twins, used in the individualized body temperature regulation system for surgical patients based on digital twins as described in any one of claims 1 to 5, characterized in that, include: Acquire patient individual characteristic data, preoperative basal body temperature data, surgical plan data, and initial operating room environment data, and use the acquired data as input data for model initialization; The model initialization input data is input into the digital twin modeling module to construct the basic digital twin model of the patient's body temperature and complete the initial setting of the model parameters; During the surgery, the data acquisition module collects multi-dimensional physiological and environmental data of the patient in real time and forms a real-time data stream for model updates. The real-time data stream is input into the patient's body temperature digital twin model, and the patient's body temperature digital twin model is dynamically updated and its parameters are calibrated to obtain real-time virtual mapping data that reflects the patient's current body temperature status. Based on the real-time virtual mapping data, predict the patient's body temperature change trend within a preset time period in the future, and generate an individualized body temperature regulation strategy when the prediction result meets the preset body temperature regulation conditions. Based on the individualized body temperature regulation strategy, control commands are generated for each heat preservation device, and the execution module is driven to complete the body temperature regulation operation after the control commands are coordinated by the collaborative control module. The patient's body temperature is continuously monitored based on the adjustment results of the execution module, and the monitoring results are fed back to the patient's body temperature digital twin model to perform closed-loop optimization of the individualized body temperature regulation strategy.

7. The method according to claim 6, characterized in that, The process of inputting the model initialization input data into the digital twin modeling module to construct the basic digital twin model of the patient's body temperature and completing the initial setting of the model parameters includes: Based on the patient's individual characteristics data, such as age, gender, weight, height, underlying diseases, and body fat percentage, a sub-model of the patient's individual characteristics is constructed. A body temperature conduction sub-model was constructed based on the biological heat conduction equation to simulate the generation, conduction and dissipation of heat in the patient's body; An environmental impact sub-model is constructed based on the initial environmental data of the operating room to describe the impact of environmental factors on changes in patient body temperature. Based on the heating characteristic parameters of each heat preservation device, a device action sub-model is constructed to describe the regulatory effect of different heat preservation devices on the patient's body temperature. The patient's individual characteristics sub-model, the body temperature conduction sub-model, the environmental influence sub-model, and the equipment function sub-model are combined to form the basic digital twin model of the patient's body temperature, and the initial setting of the model parameters is completed.

8. The method according to claim 6, characterized in that, The method involves real-time acquisition of multi-dimensional physiological and environmental data from patients using a data acquisition module, forming a real-time data stream for model updates, including: Real-time collection of multi-dimensional physiological data from patients, including core body temperature, surface temperature distribution, heart rate, blood pressure, respiratory rate, and metabolic rate; Real-time acquisition of environmental data such as intraoperative infusion temperature, infusion rate, operating room temperature, humidity, and airflow speed; The collected multi-dimensional physiological data and environmental data are time-synchronized and formatted to generate a real-time data stream with timestamps, which serves as input data for dynamic model updates.

9. The method according to claim 6, characterized in that, The step of inputting the real-time data stream into the patient's body temperature digital twin model, and dynamically updating and calibrating the parameters of the patient's body temperature digital twin model to obtain real-time virtual mapping data reflecting the patient's current body temperature status includes: The real-time data stream is matched with the current model parameters of the patient's body temperature digital twin base model; The deviation between the model output and the actual monitoring data is calculated based on the real-time data stream. The Kalman filter algorithm was used to dynamically calibrate the model parameters of the patient's body temperature digital twin model; Real-time virtual mapping data corresponding to the patient's current body temperature status is generated based on the calibrated model parameters.

10. The method according to claim 6, characterized in that, The process of predicting the patient's body temperature change trend within a preset time period based on the real-time virtual mapping data, and generating an individualized body temperature regulation strategy when the prediction result meets preset body temperature regulation conditions, includes: The real-time virtual mapping data is input into the body temperature prediction model to predict the patient's body temperature change trend within a preset time period. The predicted trend of body temperature change is compared with the preset body temperature safety threshold to determine whether the body temperature regulation triggering condition is met. When the aforementioned body temperature regulation triggering conditions are met, an individualized body temperature regulation strategy is generated by combining the patient's individual characteristic data and surgical plan data; The individualized body temperature regulation strategy includes jointly setting the operating parameters of the body surface heating device, infusion heating device, irrigation fluid heating device, and operating room environment regulation device.

Images