Intraoperative shoulder warm-keeping equipment and system based on intelligent temperature control and control method of intraoperative shoulder warm-keeping equipment and system

Abstract

According to the intraoperative shoulder warm keeping equipment and system based on intelligent temperature control and the control method of the intraoperative shoulder warm keeping equipment and system, the equipment is provided with a temperature sensor, a warm keeping device, an AI processing chip and the like, the AI processing chip can read an operation medical record file of an intraoperative patient, the compensation body temperature value Tcomp of the intraoperative patient and the operation medical record file are recognized based on an intraoperative AI machine algorithm model, and the temperature value Tcomp of the intraoperative patient is obtained. And predicting and outputting a corresponding intraoperative shoulder warm-keeping temperature value, carrying out temperature control dynamic adjustment, and running to the intraoperative shoulder warm-keeping temperature value. Therefore, parameters such as the room temperature and the body temperature of the patient in the operation can be combined, and the system comprehensively regulates and controls the temperature of the shoulder thermal clothes / equipment in the operation through parameter calculation and evaluation, so that the patient has targeted thermal regulation and control. Therefore, the low body temperature in the operation is prevented from influencing the healing of the incision after the operation and the recovery of the patient. Meanwhile, the defects that existing external warm keeping equipment does not make contact with the patient, and concentrated warm keeping cannot be achieved can be overcome.

Description

Technical Field

[0001] The present invention relates to the field of intelligent surgical care technology, and in particular to an intraoperative shoulder warming device based on intelligent temperature control, an intraoperative shoulder warming system based on intelligent temperature control, a control method thereof, an electronic device, and a computer-readable storage medium. Background Art

[0002] Intraoperative shoulder warming is used in scenarios such as low operating room environments, long surgeries (especially thoracic, abdominal, or lower body surgeries), elderly / pediatric / weak patients, decreased body temperature regulation ability after anesthesia, and shoulder exposure caused by special surgical positions. Its significance lies in reducing the occurrence of intraoperative hypothermia, reducing the risk of complications such as postoperative infection and coagulation abnormalities, maintaining stable physiological functions, and improving patient comfort and postoperative recovery quality. If warming equipment is not used during surgery, intraoperative hypothermia is likely to occur, affecting postoperative wound healing and patient recovery. For example, hypothermia caused by surgery (core body temperature below 36°C) is a common perioperative complication that may have multiple adverse effects on patients, as follows: 1. Effects on the cardiovascular system Arrhythmias: Hypothermia can increase myocardial sensitivity and induce ventricular arrhythmias (such as ventricular fibrillation), especially when the core body temperature is <32°C, the risk increases significantly.

[0003] Decreased myocardial contractility: Decreased cardiac output may lead to hypotension and tissue hypoperfusion.

[0004] Vasoconstriction: Peripheral vascular resistance increases, increasing the workload on the heart.

[0005] 2. Coagulation disorders Platelet function inhibition: For every 1°C decrease in body temperature, platelet function decreases by approximately 10%-20%, increasing the risk of intraoperative and postoperative bleeding.

[0006] Decreased thrombin activity: The coagulation cascade is slowed down and PT / APTT is prolonged, but laboratory tests may underestimate the actual bleeding risk due to standard 37°C testing.

[0007] 3. Delayed drug metabolism Slowed metabolism of anesthetic drugs: decreased liver enzyme activity prolongs the duration of action of drugs such as muscle relaxants and propofol, leading to delayed awakening.

[0008] Depth of anesthesia is difficult to assess: hypothermia may mask signs of shallow anesthesia.

[0009] 4. Increased risk of infection Immune function suppression: Neutrophil chemotaxis and phagocytosis are decreased, and the risk of surgical site infection (SSI) increases by 1.5-3 times.

[0010] Delayed wound healing: Hypothermia reduces subcutaneous oxygen partial pressure and affects collagen synthesis.

[0011] 5. Prolonged postoperative recovery Shivering: Increases oxygen consumption (up to 400%), increases the burden on the heart and lungs, and is especially detrimental to patients with coronary heart disease or COPD.

[0012] Prolonged hospital stay: Patients with hypothermia recover slowly after surgery, and their hospital stay may increase by 20%-40%.

[0013] etc.

[0014] The main preventive measures currently used in clinical practice to keep the shoulder warm during surgery are mainly to use heaters and liquid warmers, but this method can only adjust the room temperature and try to cover the patient with a blanket during surgery. Although these measures are simple, they also have the following application defects: The current clinical practice of preventing shoulder warming during surgery requires nurses to operate the device, which can easily lead to contact infection during surgery and increase the risk of infection. Adjusting the room temperature by adjusting the heater takes up the nurse's energy and prevents her from fully focusing on the surgical process. The existing control method is mainly based on room temperature adjustments, and does not integrate the patient's temperature during surgery for balanced control. The lack of attention to the patient's body temperature may cause the room temperature to not match the patient's physical needs. Summary of the Invention

[0015] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions: In one aspect, a shoulder warming device for intraoperative surgery based on intelligent temperature control is provided, the device comprising: At least one set of warming device to provide shoulder warming service during surgery; Body temperature sensor, used to monitor the patient's body temperature during surgery and provide real-time feedback to the MCU controller; Room temperature sensor, used to monitor room temperature data in the operating room and provide real-time feedback to the MCU controller; An MCU controller is configured to perform dynamic compensation calculation on the body temperature data based on the room temperature data, generate a compensated body temperature value Tcomp for the patient during surgery, and send the value to the AI ​​processing chip; The AI ​​processing chip is used to read the surgical medical records of the patient during surgery, identify the compensated body temperature value Tcomp and the surgical medical records of the patient during surgery based on the intraoperative AI machine algorithm model, predict and output the corresponding intraoperative shoulder warming temperature value and feed it back to the MCU controller; the MCU controller controls the warming device to dynamically adjust the temperature control to the intraoperative shoulder warming temperature value; Database, used to provide data storage services; Power supply, used for power supply; A wireless module is used to upload the intraoperative patient's body temperature data and the intraoperative shoulder warming temperature value to a backend server in real time for evaluation by anesthesiologists; The warming device, body temperature sensor, room temperature sensor, AI processing chip, database, power supply and wireless module are electrically connected to the MCU controller respectively.

[0016] Preferably, it is characterized in that the warming device comprises: Several thermal insulation components; A temperature control device, configured to respond to a temperature control instruction issued by the MCU controller and control the temperature of the warming component to achieve the intraoperative shoulder warming temperature value; The warming component is electrically connected to the temperature control device.

[0017] Preferably, it is characterized in that the calculation formula of the compensated body temperature value Tcomp is as follows: , in: T comp is the body temperature value after compensation; T raw The raw body temperature reading monitored by the body temperature sensor; T env The real-time ambient temperature of the operating room is monitored by the room temperature sensor; T ref is the standard reference room temperature (take 23°C); T body The current measured body temperature of the patient monitored by the body temperature sensor (the average value calculated after filtering); T target The preset target body temperature (usually set at 36.5-37°C); α is the room temperature influence coefficient (default is 0.15), which is calibrated through experiments; β is the sensitivity to body temperature deviation (default 0.8), which is dynamically adjusted according to the patient's condition; γ is the body temperature change rate weight (default 0.05), which is determined by the patient's metabolic model; is the room temperature compensation term, which is used to eliminate the sensor measurement deviation caused by ambient temperature fluctuations and uses the exponent e for attenuation correction; It is a dynamic response item used to capture the trend of body temperature changes and compensate for temperature changes caused by metabolism or infusion in advance.

[0018] Preferably, the method for generating the intraoperative AI machine algorithm model includes: Collecting intraoperative nursing big data of several patients undergoing surgery, including surgical medical records, room temperature data, body temperature data of the patients during surgery, and compensated body temperature Tcomp of the patients during surgery obtained by dynamically compensating the body temperature data based on the room temperature data; Perform feature engineering on the intraoperative nursing big data of each patient during surgery, extract the corresponding intraoperative nursing features, and annotate the intraoperative nursing features with the corresponding intraoperative shoulder warming temperature values; The intraoperative nursing features of each intraoperative patient after statistical annotation are formed into a feature set, which is divided into a training set and a validation set according to a preset ratio; The training set is input into the preset RF random forest model to perform feature classification training and generate the initial intraoperative AI machine algorithm model; The prediction performance of the intraoperative AI machine algorithm model was verified using a validation set: If the verification is successful, the intraoperative AI machine algorithm model is deployed and applied to the AI ​​processing chip; If the verification fails, repeat the above steps.

[0019] In another aspect, a shoulder warming system for surgery based on intelligent temperature control is provided, the system comprising: The aforementioned intraoperative shoulder warming device based on intelligent temperature control is used to upload the intraoperative patient's body temperature data and the intraoperative shoulder warming temperature value to the backend server in real time for evaluation by the anesthesiologist; The backend server is configured to transmit the surgical medical records of the intraoperative patient to the intraoperative shoulder warming device based on intelligent temperature control, which stores the records in its database; and, when the anesthesiologist assesses and finds that the intraoperative shoulder warming temperature value of the intraoperative patient does not match the surgical medical records, generate a corresponding temperature control correction instruction and transmit it to the intraoperative shoulder warming device based on intelligent temperature control; The intraoperative shoulder warming device based on intelligent temperature control receives the temperature control correction instruction through its wireless module and forwards it to the MCU controller, and the MCU controller responds to the temperature control correction instruction and controls the warming device to perform dynamic temperature control adjustment; The intraoperative shoulder warming device based on intelligent temperature control is communicatively connected to the background server.

[0020] On the other hand, a control method for an intraoperative shoulder warming system based on intelligent temperature control is also provided, comprising the following steps: System initialization; Activate the intelligent temperature-controlled shoulder warming device worn by the patient during surgery, and its wireless module begins to establish wireless communication with the backend server; The backend server responds to the communication request, establishes a communication channel, binds the device ID of the smart temperature-controlled intraoperative shoulder warming device worn by the patient during surgery to the patient's medical record number, and sends feedback to the smart temperature-controlled intraoperative shoulder warming device worn by the patient; After receiving feedback, the patient's intraoperative shoulder warming device, which is based on intelligent temperature control, begins to monitor and collect room temperature data in the operating room and the patient's body temperature data, and feeds it back to the MCU controller in real time; The MCU controller performs dynamic compensation calculation on the body temperature data based on the room temperature data, generates a compensated body temperature value Tcomp of the patient during surgery, and sends it to the AI ​​processing chip; The AI ​​processing chip reads the surgical medical records of the patient during surgery, identifies the compensated body temperature value Tcomp and the surgical medical records of the patient during surgery based on the intraoperative AI machine algorithm model, predicts and outputs the corresponding intraoperative shoulder warming temperature value and feeds it back to the MCU controller; the MCU controller controls the warming device to dynamically adjust the temperature control and operate to the intraoperative shoulder warming temperature value; The wireless module uploads the intraoperative patient's body temperature data and the intraoperative shoulder warming temperature value to the backend server in real time for evaluation by the anesthesiologist.

[0021] On the other hand, an electronic device is provided, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned intraoperative shoulder warming equipment, systems and control methods based on intelligent temperature control is implemented.

[0022] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned intraoperative shoulder warming equipment, systems and control methods based on intelligent temperature control.

[0023] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: The intraoperative shoulder warming device proposed in the present invention is equipped with a temperature sensor, a warming device, and an AI processing chip. The AI ​​processing chip can read the surgical medical records of the patient during surgery, identify the compensated body temperature value Tcomp and the surgical medical records of the patient during surgery based on the intraoperative AI machine algorithm model, predict and output the corresponding intraoperative shoulder warming temperature value and feed it back to the MCU controller; the MCU controller controls the warming device to dynamically adjust the temperature control and run to the intraoperative shoulder warming temperature value. Therefore, it is possible to combine parameters such as room temperature and intraoperative patient body temperature. After parameter calculation and evaluation, the system can comprehensively regulate the temperature of the intraoperative shoulder warming clothing / equipment, so that the patient has targeted warming regulation. In this way, hypothermia during surgery is avoided, which affects the postoperative incision healing and the patient's recovery. At the same time, it can solve the defects of existing external warming equipment that have no contact with the patient and cannot provide centralized warming.

[0024] This invention utilizes a technological pipeline combining dynamic body temperature compensation, random forest prediction, and closed-loop PID control to achieve precise and intelligent intraoperative shoulder warming. The hardware selection prioritizes both performance and medical compliance, and the software algorithm has undergone rigorous clinical validation, significantly reducing the incidence of hypothermia-related complications. In the future, transfer learning can be used to expand this intelligent temperature control approach to other surgical areas, such as the abdomen and lower extremities. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 This is a schematic diagram of the control system of an intraoperative shoulder warming device based on intelligent temperature control provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of a generation process of an intraoperative AI machine algorithm model provided by an embodiment of the present invention; Figure 3 This is a system block diagram provided by an embodiment of the present invention; Figure 4 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0028] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0029] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0030] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0031] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0032] The warming device of this embodiment can be a heating blanket, a warming sheet and other equipment, which is equipped with a temperature control module / device and a specific warming and heating component (for example, the warming device of CN215020267U can be referred to, but its control needs to be implemented in combination with the present invention). The temperature control module / device is controlled by the MCU controller of the present invention, and the intelligent strategy output by the corresponding AI processing chip (the recommended intraoperative shoulder warming temperature value) can be used.

[0033] The specific parameters such as the structure and size of the warming device for keeping the patient warm can be selected by the user.

[0034] The embodiment of the present invention provides a shoulder warming device based on intelligent temperature control during surgery. Figure 1 The control system of the shoulder warming device for intraoperative surgery based on intelligent temperature control is shown in the figure, and the device includes: At least one set of warming device to provide shoulder warming service during surgery; Body temperature sensor, used to monitor the patient's body temperature during surgery and provide real-time feedback to the MCU controller; Room temperature sensor, used to monitor room temperature data in the operating room and provide real-time feedback to the MCU controller; An MCU controller is configured to perform dynamic compensation calculation on the body temperature data based on the room temperature data, generate a compensated body temperature value Tcomp for the patient during surgery, and send the value to the AI ​​processing chip; The AI ​​processing chip is used to read the surgical medical records of the patient during surgery, identify the compensated body temperature value Tcomp and the surgical medical records of the patient during surgery based on the intraoperative AI machine algorithm model, predict and output the corresponding intraoperative shoulder warming temperature value and feed it back to the MCU controller; the MCU controller controls the warming device to dynamically adjust the temperature control to the intraoperative shoulder warming temperature value; Database, used to provide data storage services; Power supply, used for power supply; A wireless module is used to upload the intraoperative patient's body temperature data and the intraoperative shoulder warming temperature value to a backend server in real time for evaluation by anesthesiologists; The warming device, body temperature sensor, room temperature sensor, AI processing chip, database, power supply and wireless module are electrically connected to the MCU controller respectively.

[0035] The present invention can combine parameters such as room temperature and intraoperative patient body temperature. After parameter calculation and evaluation, the system comprehensively regulates the temperature of the shoulder warming equipment / device during surgery, so that the patient can have targeted warming regulation. In this way, hypothermia during surgery is avoided, which affects postoperative wound healing and patient recovery. The integrated device is equipped with room temperature and body temperature sensors, which can adjust the temperature during surgery in combination with the patient's body temperature. The body temperature data is dynamically compensated and calculated based on the room temperature data to generate a compensated body temperature value Tcomp for the patient during surgery, thereby avoiding the defects in patient warming regulation during surgery caused by single room temperature regulation. Temperature control is performed taking into account the patient's body temperature to avoid the temperature control result not meeting the patient's body temperature requirements.

[0036] Each hardware configuration can be configured by the user. This embodiment provides a specific device configuration as shown in Table 1 below:

[0037]

[0038]

[0039] Table 1 Hardware system composition and connection, refer to the attached Figure 1 The integrated installation structure and sealing process are not described in this embodiment, and this embodiment only describes its system application.

[0040] Preferably, it is characterized in that the warming device comprises: Several thermal insulation components; A temperature control device, configured to respond to a temperature control instruction issued by the MCU controller and control the temperature of the warming component to achieve the intraoperative shoulder warming temperature value; The warming component is electrically connected to the temperature control device.

[0041] The heating device can include multiple sets, each controlled by a temperature control device (thermostat or temperature control module). The specific understanding can be combined with existing temperature control equipment technology.

[0042] The calculation method of the sensed temperature of the present invention will be described below.

[0043] When the system is activated, the sensor collects data and the MCU performs signal processing (pre-processing steps such as filtering, amplification, noise reduction, and digital-to-analog conversion). Some system parameters / coefficients are pre-entered into the calculation formula.

[0044] Compensated body temperature value T comp The calculation of the temperature should eliminate the interference of the ambient temperature on the surface measurement, and adopt the piecewise linear compensation model (composed of the following sections: T raw 、 、 ) See the following description for details.

[0045] Preferably, it is characterized in that the calculation formula of the compensated body temperature value Tcomp is as follows: , in: T comp is the body temperature value after compensation; T raw The raw body temperature reading monitored by the body temperature sensor; T env The real-time ambient temperature of the operating room is monitored by the room temperature sensor; T ref The standard reference room temperature (23°C) can be referred to clinical specifications; T body The current measured body temperature of the patient monitored by the body temperature sensor (the average value calculated after filtering) can be sampled multiple times and then the average value is calculated; T target The target body temperature is set to 36.5-37°C, which is assessed and input by the anesthesiologist. α is the room temperature influence coefficient (default is 0.15), which is calibrated through experiments and can be obtained by experimental personnel; β is the sensitivity to body temperature deviation (default is 0.8), which is dynamically adjusted according to the patient's condition. The current patient's condition can be analyzed through a big data model, and then the corresponding β value can be output; γ is the weight of the body temperature change rate (default 0.05), which is determined by the patient's metabolic model and can be set by the attending physician based on the patient's metabolic data; is the room temperature compensation term, which is used to eliminate the sensor measurement deviation caused by ambient temperature fluctuations and uses the exponent e for attenuation correction; It is a dynamic response item used to capture the trend of body temperature changes and compensate for temperature changes caused by metabolism or infusion in advance.

[0046] After the system is activated, data collection begins; ‌Input preprocessing:‌ The body temperature signal is filtered by Kalman to eliminate motion artifacts; Room temperature data were smoothed using a sliding average (window 5 min); Dynamic adjustment of coefficients (pseudocode example): # Dynamically calculate the alpha coefficient (based on the patient's BMI and anesthesia depth) def calc_alpha(bmi, bis): return 0.1 + 0.05*(bmi-25) / 10 + 0.02*(40-bis) / 10 # bis: anesthesia depth index; Compensation execution logic (pseudo code example): import numpy as np def temp_compensation(T_raw, T_env, T_body_history, params): T_body = np.median(T_body_history[-3:]) # median filtering dT_body = (T_body_history[-1] - T_body_history[-3]) / 2 # differential approximation alpha = params['alpha'] * (1 - 0.2*(T_env - 23)) # Room temperature nonlinear correction comp = alpha*(T_env - 23)*np.exp(-0.8*abs(T_body-36.5)) comp += 0.05 * dT_body return T_raw + comp. The code implements real-time body temperature compensation, including adaptive correction of ambient temperature and response to rate of change.

[0047] The MCU can send the patient's compensated body temperature Tcomp during surgery to the AI ​​processing chip, which has an embedded intraoperative AI machine algorithm model.

[0048] The specific method of generating the model will be described below.

[0049] like Figure 2 As shown, preferably, the method for generating the intraoperative AI machine algorithm model includes: Collecting intraoperative nursing big data of several patients undergoing surgery, including surgical medical records, room temperature data, body temperature data of the patients during surgery, and compensated body temperature Tcomp of the patients during surgery obtained by dynamically compensating the body temperature data based on the room temperature data; Perform feature engineering on the intraoperative nursing big data of each patient during surgery, extract the corresponding intraoperative nursing features, and annotate the intraoperative nursing features with the corresponding intraoperative shoulder warming temperature values; The intraoperative nursing features of each intraoperative patient after statistical annotation are formed into a feature set, which is divided into a training set and a validation set according to a preset ratio; The training set is input into the preset RF random forest model to perform feature classification training and generate the initial intraoperative AI machine algorithm model; The prediction performance of the intraoperative AI machine algorithm model was verified using a validation set: If the verification is successful, the intraoperative AI machine algorithm model is deployed and applied to the AI ​​processing chip; If the verification fails, repeat the above steps.

[0050] 1. Training data preparation: ‌Input Features‌: Patient static characteristics: age, weight, BMI, ASA classification (anesthesia risk level); Surgical characteristics: structured data such as surgical type (laparotomy / laparoscopic), estimated duration, anesthesia method (general anesthesia / epidural), intraoperative blood loss, infusion volume, complications, etc. Dynamic data: body temperature T body , indoor temperature T env ; ‌Tag‌: Optimal shoulder warming temperature during surgery comp (Annotated by the optimal value manually set by the anesthesiologist in the historical nursing record).

[0051] 2. Feature Engineering Select appropriate special processing methods for feature extraction. For example, a statistical model can be used to calculate the patient's maximum body temperature at each time point, along with the room temperature at that time and the calculated compensation temperature Tcomp. This feature extraction process can be used to identify intraoperative nursing characteristics for the patient and use them for model training.

[0052] For room temperature data and body temperature data, please refer to the application solutions of the above sensors; Tcomp calculation: see the above calculation formula; Feature Engineering Framework: Time series features: Construct a sliding window (every 5 minutes) to extract the body temperature change rate, room temperature fluctuation entropy, and temperature change acceleration; Spatial characteristics: Calculate the temperature gradient in the surgical area (max(T1-T5)-min(T1-T5)); Interactive features: generate surgery duration × basal metabolic rate, infusion volume / weight × room temperature standard deviation; Compensation features: extract the area under the Tcomp curve (AUC) and the compensation temperature oscillation amplitude (ΔTcomp_max).

[0053] Other features can be determined by the user.

[0054] Labeling system: Grading labeling: Set the temperature based on the actual intraoperative shoulder warming temperature value used during surgery, and establish four-level labels (32°C / 34°C / 36°C / 38°C). The anesthesiologist can specifically label the intraoperative shoulder warming temperature value based on the above characteristics; Dynamic labeling: Mark the weighted warmth value for each 15-minute nursing period: Y=0.6, equipment set temperature +0.4, and the nurse adjusts the correction value for the number of times.

[0055] 3. Model Training The RF model is used for training (pseudo code example) as follows: from sklearn.ensemble (prepared dataset) import RandomForestRegressor (RF model); from sklearn.model_selection import train_test_split; # Data partition (8:2 ratio) X_train, X_val, y_train, y_val = train_test_split(features, labels, test_size=0.2, random_state=42); # Model parameter settings rf_model = RandomForestRegressor( n_estimators=200, # number of decision trees max_depth=8, # Maximum depth of a single tree min_samples_split=5, # Minimum number of samples for node splitting n_jobs=-1 # Use all CPU cores ) # Training process rf_model.fit(X_train, y_train) # Validation set evaluation val_pred = rf_model.predict(X_val) mae = np.mean(np.abs(val_pred - y_val)) print(f"Validation set MAE: {mae:.2f}℃") # Target MAE <0.5℃.

[0056] Model validation can be done using AOC or F1 score, etc. The user can re-build the test set to test and verify. The test is as follows: Test environment: Operating rooms in three tertiary hospitals, covering general surgery (laparoscopy) and orthopedics (open surgery) scenarios; Sample size: 200 patients undergoing general anesthesia (ASA physical status II-III) were randomly divided into the AI ​​group (n=100) and the conventional group (n=100, artificially controlled). The comparison of key indicators is shown in Table 2 below:

[0057] Table 2 The model performance is verified as follows: Prediction accuracy: MAE = 0.43°C (test set), with an error of < 0.5°C for 92% of cases; Real-time performance: The delay from data acquisition to temperature adjustment is ≤ 1.5 seconds.

[0058] 4. Model deployment optimization: Quantization Compression: Convert floating-point weights to INT8 format, reducing model size by 75%; Hardware acceleration: Jetson Nano's GPU accelerates inference speed, with a single prediction time of ≤50ms.

[0059] The specific installation is as follows: Compile the optimized model binary file into the chip instruction set; Framework integration (such as TensorFlow Lite and ONNX Runtime adaptation); Intermediate representation format conversion (such as ONNX, NNEF); Chip vendor-specific toolchain packaging (such as TensorRT and OpenVINO); Dynamic link library loads pre-trained model parameters; Customized operator library docking with chip computing units; Containerized deployment (Docker+FPGA heterogeneous architecture); Layered deployment of end-cloud collaborative inference architecture; Hardware accelerated instruction set microcode injection (CUDA / OpenCL kernels).

[0060] For details, refer to existing file burning or chip injection methods. Because the device communicates wirelessly with the backend, it can also be downloaded from the backend for the first time after the patient wears it, installing the model in the AI ​​processing chip. After backend testing, it can be put into use.

[0061] System control flow: ‌1. Initialization and device activation‌ Power on: Press the power button and the MCU completes self-test (sensor communication, heater resistance detection). Wireless pairing: The wireless module scans the Wi-Fi hotspot in the operating room (default SSID: OR_Server) and establishes an SSL encrypted channel. Medical record binding: The MCU sends the device ID (e.g., DEVID_001) to the backend server, which receives and stores the patient's medical record number (e.g., PID_202309001).

[0062] 2. Real-time temperature control logic (pseudo code example): The following steps are executed in a loop (period = 1 second): 1) Collecting data: Body temperature sensor reading T_body (DS18B20); Room temperature sensor reading T_room (SHT35); 2) Calculate the compensated body temperature T_comp (according to the calculation formula).

[0063] 3). AI predicts the set temperature T_set: The MCU sends [medical records, compensated body temperature value Tcomp] to the AI ​​processing chip via SPI; RF model reasoning → T_set (e.g., 37.8°C), the intraoperative shoulder warming temperature; 4). Temperature control execution: The MCU generates corresponding temperature control instructions based on the shoulder warming temperature value during surgery and controls the temperature control module to make adjustments.

[0064] 5). Data upload: Encapsulated data packet: {timestamp, body temperature data, intraoperative shoulder warming temperature value}; Push to the cloud server via MQTT protocol.

[0065] ‌3. Anesthesiologist intervention mechanism‌ Abnormal warning: When the AI-predicted shoulder warming temperature deviates by more than ±1.5°C from the historical setting in the patient's medical record, the system automatically triggers an alarm. Manual correction: The anesthesiologist enters the corrected intraoperative shoulder warming temperature value in the backend interface. The command is sent back to the device via HTTPS, and the MCU immediately switches to manual mode.

[0066] like Figure 3 As shown, on the other hand, a shoulder warming system based on intelligent temperature control during surgery is provided, the system comprising: The aforementioned intraoperative shoulder warming device based on intelligent temperature control is used to upload the intraoperative patient's body temperature data and the intraoperative shoulder warming temperature value to the backend server in real time for evaluation by the anesthesiologist; The backend server is configured to transmit the surgical medical records of the intraoperative patient to the intraoperative shoulder warming device based on intelligent temperature control, which stores the records in its database; and, when the anesthesiologist assesses and finds that the intraoperative shoulder warming temperature value of the intraoperative patient does not match the surgical medical records, generate a corresponding temperature control correction instruction and transmit it to the intraoperative shoulder warming device based on intelligent temperature control; The intraoperative shoulder warming device based on intelligent temperature control receives the temperature control correction instruction through its wireless module and forwards it to the MCU controller, and the MCU controller responds to the temperature control correction instruction and controls the warming device to perform dynamic temperature control adjustment; The intraoperative shoulder warming device based on intelligent temperature control is communicatively connected to the background server.

[0067] The above system can be understood in conjunction with the aforementioned devices. Anesthesiologists in the backend can view each patient's medical records and temperature control parameters in real time, and monitor whether the AI-recommended temperature meets the patient's condition. If it is found to be inconsistent with the patient's condition, they can intervene promptly and issue new temperature control instructions through the backend server to ensure safe temperature control operation.

[0068] On the other hand, a control method for an intraoperative shoulder warming system based on intelligent temperature control is also provided, comprising the following steps: System initialization; Activate the intelligent temperature-controlled shoulder warming device worn by the patient during surgery, and its wireless module begins to establish wireless communication with the backend server; The backend server responds to the communication request, establishes a communication channel, binds the device ID of the smart temperature-controlled intraoperative shoulder warming device worn by the patient during surgery to the patient's medical record number, and sends feedback to the smart temperature-controlled intraoperative shoulder warming device worn by the patient; After receiving feedback, the patient's intraoperative shoulder warming device, which is based on intelligent temperature control, begins to monitor and collect room temperature data in the operating room and the patient's body temperature data, and feeds it back to the MCU controller in real time; The MCU controller performs dynamic compensation calculation on the body temperature data based on the room temperature data, generates a compensated body temperature value Tcomp of the patient during surgery, and sends it to the AI ​​processing chip; The AI ​​processing chip reads the surgical medical records of the patient during surgery, identifies the compensated body temperature value Tcomp and the surgical medical records of the patient during surgery based on the intraoperative AI machine algorithm model, predicts and outputs the corresponding intraoperative shoulder warming temperature value and feeds it back to the MCU controller; the MCU controller controls the warming device to dynamically adjust the temperature control and operate to the intraoperative shoulder warming temperature value; The wireless module uploads the intraoperative patient's body temperature data and the intraoperative shoulder warming temperature value to the backend server in real time for evaluation by the anesthesiologist.

[0069] For details, please refer to the implementation description of the above systems and devices.

[0070] Figure 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, such as Figure 4 As shown, the electronic device 410 may include a first processor 2001 .

[0071] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0072] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0073] The following combination Figure 4 The components of the electronic device 410 are described in detail. The first processor 2001 is the control center of the electronic device 410 and can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs) or one or more field programmable gate arrays (FPGAs).

[0074] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0075] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 4 CPU0 and CPU1 are shown in FIG.

[0076] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 4 1 and 2. The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). A processor herein can refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0077] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled by the first processor 2001 for execution. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0078] Alternatively, the memory 2002 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001 or exist independently and accessed through the interface circuit ( Figure 4 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0079] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0080] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 4 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0081] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 4 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0082] It should be noted that Figure 4 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router. The actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0083] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the intraoperative shoulder warming equipment, system and control method based on intelligent temperature control described in the above method embodiment, and will not be repeated here.

[0084] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, etc.

[0085] It should also be understood that the memory in the embodiments of the present invention may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0086] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0087] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0088] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0089] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean 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.

[0090] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0091] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0092] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0093] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0094] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0095] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical disks.

[0096] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A shoulder warming device based on intelligent temperature control during surgery, characterized in that: The device comprises: At least one set of warming device to provide shoulder warming service during surgery; Body temperature sensor, used to monitor the patient's body temperature during surgery and provide real-time feedback to the MCU controller; Room temperature sensor, used to monitor room temperature data in the operating room and provide real-time feedback to the MCU controller; An MCU controller is configured to perform dynamic compensation calculation on the body temperature data based on the room temperature data, generate a compensated body temperature value Tcomp for the patient during surgery, and send the value to the AI ​​processing chip; The AI ​​processing chip is used to read the surgical medical records of the patient during surgery, identify the compensated body temperature value Tcomp and the surgical medical records of the patient during surgery based on the intraoperative AI machine algorithm model, predict and output the corresponding intraoperative shoulder warming temperature value and feed it back to the MCU controller; the MCU controller controls the warming device to dynamically adjust the temperature control to the intraoperative shoulder warming temperature value; Database, used to provide data storage services; Power supply, used for power supply; A wireless module is used to upload the intraoperative patient's body temperature data and the intraoperative shoulder warming temperature value to a backend server in real time for evaluation by anesthesiologists; The warming device, body temperature sensor, room temperature sensor, AI processing chip, database, power supply and wireless module are electrically connected to the MCU controller respectively.

2. The shoulder warming device based on intelligent temperature control during surgery according to claim 1 is characterized in that: The warming device comprises: Several thermal insulation components; A temperature control device, configured to respond to a temperature control instruction issued by the MCU controller and control the temperature of the warming component to achieve the intraoperative shoulder warming temperature value; The warming component is electrically connected to the temperature control device.

3. The shoulder warming device based on intelligent temperature control during surgery according to claim 1 is characterized in that: The calculation formula of the compensated body temperature value Tcomp is as follows: ， in: T comp is the body temperature value after compensation; T raw The raw body temperature reading monitored by the body temperature sensor; T env The real-time ambient temperature of the operating room is monitored by the room temperature sensor; T ref is the standard reference room temperature (take 23°C); T body The current measured body temperature of the patient monitored by the body temperature sensor (the average value calculated after filtering); T target The preset target body temperature (usually set at 36.5-37°C); α is the room temperature influence coefficient (default is 0.15), which is calibrated through experiments; β is the sensitivity to body temperature deviation (default 0.8), which is dynamically adjusted according to the patient's condition; γ is the body temperature change rate weight (default 0.05), which is determined by the patient's metabolic model; is the room temperature compensation term, which is used to eliminate the sensor measurement deviation caused by ambient temperature fluctuations and uses the exponent e for attenuation correction; It is a dynamic response item used to capture the trend of body temperature changes and compensate for temperature changes caused by metabolism or infusion in advance.

4. The shoulder warming device based on intelligent temperature control during surgery according to claim 1, characterized in that: The method for generating the intraoperative AI machine algorithm model includes: Collecting intraoperative nursing big data of several patients undergoing surgery, including surgical medical records, room temperature data, body temperature data of the patients during surgery, and compensated body temperature Tcomp of the patients during surgery obtained by dynamically compensating the body temperature data based on the room temperature data; Perform feature engineering on the intraoperative nursing big data of each patient during surgery, extract the corresponding intraoperative nursing features, and annotate the intraoperative nursing features with the corresponding intraoperative shoulder warming temperature values; The intraoperative nursing features of each intraoperative patient after statistical annotation are formed into a feature set, which is divided into a training set and a validation set according to a preset ratio; The training set is input into the preset RF random forest model to perform feature classification training and generate the initial intraoperative AI machine algorithm model; The prediction performance of the intraoperative AI machine algorithm model was verified using a validation set: If the verification is successful, the intraoperative AI machine algorithm model is deployed and applied to the AI ​​processing chip; If the verification fails, repeat the above steps.

5. A shoulder warming system during surgery based on intelligent temperature control, characterized in that: The system comprises: The intraoperative shoulder warming device based on intelligent temperature control according to any one of claims 1 to 4 is used to upload the intraoperative patient's body temperature data and the intraoperative shoulder warming temperature value to the backend server in real time for evaluation by the anesthesiologist; The backend server is configured to transmit the surgical medical records of the intraoperative patient to the intraoperative shoulder warming device based on intelligent temperature control, which stores the records in its database; and, when the anesthesiologist assesses and finds that the intraoperative shoulder warming temperature value of the intraoperative patient does not match the surgical medical records, generate a corresponding temperature control correction instruction and transmit it to the intraoperative shoulder warming device based on intelligent temperature control; The intraoperative shoulder warming device based on intelligent temperature control receives the temperature control correction instruction through its wireless module and forwards it to the MCU controller, and the MCU controller responds to the temperature control correction instruction and controls the warming device to perform dynamic temperature control adjustment; The intraoperative shoulder warming device based on intelligent temperature control is communicatively connected to the background server.

6. A control method for the intraoperative shoulder warming system based on intelligent temperature control according to claim 5, characterized in that: The steps include: System initialization; Activate the intelligent temperature-controlled shoulder warming device worn by the patient during surgery, and its wireless module begins to establish wireless communication with the backend server; The backend server responds to the communication request, establishes a communication channel, binds the device ID of the smart temperature-controlled intraoperative shoulder warming device worn by the patient during surgery to the patient's medical record number, and sends feedback to the smart temperature-controlled intraoperative shoulder warming device worn by the patient; After receiving feedback, the patient's intraoperative shoulder warming device, which is based on intelligent temperature control, begins to monitor and collect room temperature data in the operating room and the patient's body temperature data, and feeds it back to the MCU controller in real time; The MCU controller performs dynamic compensation calculation on the body temperature data based on the room temperature data, generates a compensated body temperature value Tcomp of the patient during surgery, and sends it to the AI ​​processing chip; The AI ​​processing chip reads the surgical medical records of the patient during surgery, identifies the patient's compensated body temperature value Tcomp and the surgical medical records based on the intraoperative AI machine algorithm model, predicts and outputs the corresponding intraoperative shoulder warming temperature value and feeds it back to the MCU controller; The MCU controller controls the warming device to dynamically adjust the temperature to the intraoperative shoulder warming temperature value; The wireless module uploads the intraoperative patient's body temperature data and the intraoperative shoulder warming temperature value to the backend server in real time for evaluation by the anesthesiologist.

7. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to claim 6 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, which can be called by a processor to execute the method according to claim 6.

Images