Self-adaptive incision zero-compression temperature-adjustable ice pillow system used after severe craniocerebral operation

Abstract

The invention relates to the technical field of medical instruments, and discloses a severe craniocerebral postoperative self-adaptive incision zero-compression temperature-adjustable ice pillow system, a temperature sensing unit of the system collects incision and ice pillow temperature data, and an initial temperature regulation threshold is determined through a self-adaptive algorithm; the pressure monitoring unit respectively determines initial zero compression parameters in the double monitoring periods and dynamically corrects the parameters according to body position changes; the regulation and control execution unit determines a temperature correction coefficient by calculating the comprehensive matching degree of the incision contact pressure and historical body position data and combining a matching degree threshold value and an intelligent learning algorithm; and the control center completes temperature regulation and control based on the corrected zero compression parameter. The system can realize accurate self-adaptive temperature adjustment in a zero-compression state of the incision according to individual physiological characteristics, operation types and body position changes of patients, effectively improves the safety and effectiveness of intensive craniocerebral postoperative incision nursing, reduces the risk of complications, and is suitable for clinical postoperative nursing scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to an adaptive incision zero-compression and temperature-adjustable ice pillow system after severe craniocerebral surgery. Background Art

[0002] In the field of postoperative care for critical cranial surgery, the quality of wound care directly impacts the patient's recovery process and complication rate. Traditional ice pillow devices face numerous technical bottlenecks in their application. Temperature control methods often use preset fixed values, failing to account for individual patient physiological characteristics (such as age, surgery type, and ability to regulate body temperature) and differences in postoperative recovery stages. This results in variable hypothermia treatment effectiveness. Some patients may be at risk of frostbite due to excessively low temperatures, or ineffectively control wound inflammation due to insufficient temperatures.

[0003] Existing ice pillows lack a dynamic monitoring mechanism for incision pressure management. When the patient's position changes (such as turning over or lying on the side), the contact pressure between the ice pillow and the incision will change accordingly. Traditional devices cannot perceive changes in vertical contact pressure, horizontal sliding friction, and dynamic pressure fluctuation values ​​in real time, which can easily cause excessive local pressure on the incision, affect blood circulation in the wound, and may even cause secondary injury.

[0004] The lack of matching analysis between historical body position data and real-time pressure data prevents the ice pillow from adaptively adjusting parameters based on the pressure distribution characteristics of the patient's different body positions, making it difficult to achieve the goal of true "zero pressure" care. Furthermore, traditional systems lack a neural network-based intelligent learning model, making it impossible to improve the prediction accuracy of the temperature correction coefficient through historical data training. This results in temperature control lagging behind the patient's actual needs, reducing the level of intelligence and personalization of postoperative care. Summary of the Invention

[0005] The purpose of the present invention is to provide an adaptive incision zero-compression and temperature-adjustable ice pillow system for post-surgery of severe craniotomy to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an adaptive incision zero-compression and temperature-adjustable ice pillow system for severe craniocerebral surgery, the system comprising: The temperature sensing unit is used to collect the patient's postoperative incision area temperature data and the ice pillow's basic temperature data, determine the initial temperature control threshold, and generate temperature control instructions based on an adaptive algorithm; The pressure monitoring unit is configured to collect incision contact pressure data and determine an initial zero-compression parameter during a first monitoring period after the ice pillow is activated; and is further configured to collect real-time patient position change data during a second monitoring period and compare it with historical position data, and determine whether to modify the initial zero-compression parameter based on the comparison result; a control execution unit, configured to, when determining to correct the initial zero compression parameter, calculate a comprehensive matching degree based on the incision contact pressure data and the historical body position data, compare the comprehensive matching degree with a matching degree threshold, and determine a temperature correction coefficient based on the comprehensive matching degree; when the comprehensive matching degree is greater than the matching degree threshold, determine the temperature correction coefficient based on the historical body position data; when the comprehensive matching degree is less than or equal to the matching degree threshold, determine the temperature correction coefficient through an intelligent learning algorithm; The control center is configured to correct the initial zero pressure parameter according to the temperature correction coefficient, and complete the ice pillow temperature control with the corrected final zero pressure parameter.

[0007] Preferably, the incision contact pressure data includes vertical contact pressure, horizontal sliding friction and dynamic pressure fluctuation value.

[0008] Preferably, determining the initial temperature control threshold includes: The patient's individual physiological characteristic data is collected and combined with the surgery type data, and the adaptive algorithm is used to analyze the tolerance differences of different patients to different temperatures, so as to determine the initial temperature control thresholds for different surgery types.

[0009] Preferably, after the ice pillow is activated, when collecting incision contact pressure data and determining the initial zero pressure parameter within the first monitoring cycle, the initial zero pressure parameter is obtained by weighted calculation combining the basic zero pressure threshold and the real-time contact pressure data.

[0010] Preferably, during the second monitoring period, the real-time body position change data of the patient is collected and compared with the historical body position data, and when determining whether to modify the initial zero compression parameter according to the comparison result, the method includes: When the historical body position data has the same features as the real-time body position change data, the initial zero compression parameter is not corrected; When the historical body position data does not contain the same features as those in the real-time body position change data, the initial zero compression parameter is modified.

[0011] Preferably, when determining to modify the initial zero pressure parameter, calculating the comprehensive matching degree based on the incision contact pressure data and the historical body position data includes: The comprehensive matching degree is obtained by weighted calculation based on the preset weight coefficients through the matching degree between the historical value and the real-time value of the vertical contact pressure, the matching degree between the historical value and the real-time value of the horizontal sliding friction, and the matching degree between the historical value and the real-time value of the dynamic pressure fluctuation value.

[0012] Preferably, when determining the temperature correction coefficient based on the comprehensive matching degree, it includes: Comparing the comprehensive matching degree with a preset matching degree threshold, and determining a temperature correction coefficient based on the comparison result; When data exists in the historical body position data and the comprehensive matching degree is greater than the matching degree threshold, determining the temperature correction coefficient according to the historical body position data; When there is no data in the historical body position data whose comprehensive matching degree is greater than the matching degree threshold, the temperature correction coefficient is determined according to an intelligent learning algorithm.

[0013] Preferably, when determining the temperature correction coefficient based on the historical body position data, the method includes: When there is only one data in the historical body position data whose comprehensive matching degree is greater than the matching degree threshold, the historical temperature correction coefficient corresponding to the data is used as the temperature correction coefficient; When there is more than one data in the historical body position data whose comprehensive matching degree is greater than the matching degree threshold, the average of the historical temperature correction coefficients corresponding to the respective data is used as the temperature correction coefficient.

[0014] Preferably, when determining the temperature correction coefficient according to an intelligent learning algorithm, the method includes: establishing a training data set based on the incision contact pressure data, the patient position change data, and the historical temperature correction coefficient; using a neural network model to learn the relationship between the initial zero compression parameter and the patient position change data through the training data set to predict the final zero compression parameter; and adjusting the model parameters using a parameter optimization algorithm; After the training is completed, the incision contact pressure data and the patient position change data are input into the trained neural network model to obtain the temperature correction coefficient; The initial zero pressure parameter is corrected according to the temperature correction coefficient.

[0015] Preferably, the matching threshold is dynamically adjusted according to the patient's age, degree of surgical trauma, and physiological characteristic data of the postoperative recovery stage, and the adjustment is based on the matching distribution pattern of patients with the same characteristics in historical data.

[0016] Compared with the prior art, the present invention has the following beneficial effects: This adaptive, zero-compression, temperature-adjustable ice pillow system for critical craniotomy surgery achieves precision and intelligent upgrades in postoperative care through the collaborative operation of multiple units and the integration of intelligent algorithms. The temperature sensing unit collects real-time temperature data for the incision area and the base temperature of the ice pillow. Based on the patient's individual physiological characteristics and the type of surgery, an adaptive algorithm analyzes the differences in temperature tolerance among different patients and accurately determines the initial temperature control threshold. This avoids the risk of frostbite or insufficient cooling caused by fixed temperature settings, thereby improving the safety and effectiveness of hypothermia therapy.

[0017] After the ice pillow is activated, the pressure monitoring unit first collects incision contact pressure data through the first monitoring cycle, and obtains the initial zero-compression parameter by weighted calculation based on the basic zero-compression threshold and real-time pressure data to ensure that the incision is not compressed in the initial state; in the second monitoring cycle, by comparing the real-time body position data with the historical body position data, it dynamically determines whether to correct the zero-compression parameter. When the patient's body position changes and the pressure distribution changes, the system can respond in time to avoid local compression injuries caused by body position changes. During the parameter correction process, the control execution unit calculates the comprehensive matching degree by weighting the matching degree of historical and real-time data of vertical contact pressure, horizontal sliding friction and dynamic pressure fluctuation values. According to the comparison result of the matching degree and the threshold, the temperature correction coefficient is flexibly determined by historical data mapping or intelligent learning algorithm: when the comprehensive matching degree is greater than the threshold, the temperature correction coefficient corresponding to the historical body position is directly called to improve the control efficiency; when the matching degree is insufficient, the incision pressure, body position change and historical correction coefficient are trained and learned through the neural network model to predict the optimal temperature correction coefficient to ensure that the temperature can still be accurately controlled under complex body position changes. The control center completes temperature control based on the corrected zero-pressure parameters, realizing coordinated adaptive management of "pressure-temperature".

[0018] The matching threshold can be dynamically adjusted according to the patient's age, degree of surgical trauma, and physiological characteristics of the postoperative recovery stage, enabling the system to adapt to the personalized needs of different patients, effectively reducing the incidence of complications such as incision edema and infection, shortening the patient's recovery period, and at the same time improving the automation and intelligence level of the nursing process and reducing the workload of medical staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a working principle diagram of the adaptive incision zero-compression and temperature-adjustable ice pillow system after severe craniocerebral surgery according to the present invention; Figure 2 Design drawings for body position data comparison and correction; Figure 3 Design drawings for determining correction factors for historical data; Figure 4 This is a design diagram of the intelligent learning algorithm. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] See also Figures 1-4The present invention relates to an adaptive incision zero-compression, temperature-adjustable ice pillow system for severe craniotomy. The system comprises a temperature sensing unit, a pressure monitoring unit, a control execution unit, and a control center. The specific implementation scheme is as follows: The temperature sensing unit is used to collect the patient's postoperative incision area temperature data and the ice pillow basic temperature data, determine the initial temperature control threshold, and generate temperature control instructions based on an adaptive algorithm.

[0022] After the ice pillow is activated, the pressure monitoring unit collects incision contact pressure data and determines the initial zero compression parameters during the first monitoring cycle; it also collects the patient's real-time body position change data during the second monitoring cycle and compares it with the historical body position data, and determines whether to correct the initial zero compression parameters based on the comparison results.

[0023] The control execution unit is used to calculate the comprehensive matching degree based on the incision contact pressure data and the historical body position data when it is determined that the initial zero compression parameters need to be corrected, compare the comprehensive matching degree with the matching degree threshold, and determine the temperature correction coefficient based on the comprehensive matching degree; when the comprehensive matching degree is greater than the matching degree threshold, determine the temperature correction coefficient based on the historical body position data; when the comprehensive matching degree is less than or equal to the matching degree threshold, determine the temperature correction coefficient through the intelligent learning algorithm.

[0024] The control center corrects the initial zero pressure parameters according to the temperature correction coefficient and completes the ice pillow temperature control with the corrected final zero pressure parameters.

[0025] Example 1: The incision contact pressure data includes vertical contact pressure, horizontal sliding friction and dynamic pressure fluctuation value. Among them, the collection of vertical contact pressure relies on the pressure sensor array set on the contact surface between the ice pillow and the incision. The pressure sensor array is composed of a plurality of evenly distributed micro pressure sensors, and each sensor is small in size to avoid causing additional pressure on the incision. These sensors can sense the vertical pressure of the ice pillow on the incision area in real time, and convert the collected pressure signal into an electrical signal, and transmit it to the signal processing module of the system. By analyzing and calculating these electrical signals, the specific value of the vertical contact pressure can be obtained, thereby reflecting the vertical pressure of the ice pillow on the incision. For example, when the patient's head moves slightly on the ice pillow, the pressure sensor array can capture the change in vertical pressure in time and convert it into fluctuation data of vertical contact pressure.

[0026] Horizontal sliding friction is monitored by a friction sensor. The friction sensor is installed on the contact surface between the ice pillow and the incision. Its design principle is that the generation of friction will cause deformation of the sensor's internal structure, thereby generating a corresponding electrical signal. When the patient's position changes, such as when the head turns to one side, relative sliding will occur between the incision and the ice pillow. At this time, the friction sensor will sense the friction generated by this sliding and convert it into an electrical signal to transmit to the system. The system processes and analyzes this electrical signal to obtain information such as the magnitude and direction of the horizontal sliding friction, thereby reflecting the friction between the incision and the ice pillow when the patient's position changes. For example, when the patient turns over, the sliding of the head on the ice pillow will cause a change in the horizontal sliding friction. The friction sensor can accurately monitor this change and feedback it to the system.

[0027] The dynamic pressure fluctuation value is recorded by the pressure sensor in real time as the dynamic change data of pressure. The pressure sensor used here has a high sampling frequency and can quickly capture instantaneous changes in pressure. When the patient uses the ice pillow, the pressure on the incision area will fluctuate dynamically due to physiological activities such as breathing and heartbeat, as well as possible fine-tuning of body position. The pressure sensor collects these fluctuating pressure data in real time and transmits it to the system's storage and analysis module. The system processes this data, removes noise interference, and obtains dynamic pressure fluctuation values ​​to reflect the changes in pressure over time. For example, when the patient breathes, the rise and fall of the chest will be transmitted to the head through the body, causing the pressure of the ice pillow on the incision to fluctuate slightly, and the pressure sensor can record these fluctuation data in a timely manner.

[0028] The integration of three types of data, namely vertical contact pressure, horizontal sliding friction and dynamic pressure fluctuation value, can more comprehensively reflect the pressure situation of the incision. The system will integrate and analyze these three types of data, and evaluate the pressure state of the incision by establishing a corresponding mathematical model. For example, when the vertical contact pressure exceeds a certain threshold, the horizontal sliding friction is also large, and the dynamic pressure fluctuation value changes frequently, the system can determine that the incision may be improperly compressed and needs to be adjusted accordingly. Through the comprehensive analysis of these three types of data, a more accurate and comprehensive basis can be provided for the subsequent determination and correction of zero compression parameters, ensuring that the ice pillow always maintains zero compression on the incision during use, thereby promoting the patient's postoperative recovery.

[0029] In actual application, the surface material of the ice pillow in contact with the incision is selected to be soft and elastic to cooperate with the work of the pressure sensor array and friction sensor, while reducing irritation to the incision. The layout density of the pressure sensor array is reasonably designed based on clinical experience and the size of the ice pillow to ensure that the vertical contact pressure data can be fully and accurately collected. The installation position of the friction sensor is optimized to ensure that it can sensitively monitor the friction generated by the relative sliding between the incision and the ice pillow. The sampling frequency of the pressure sensor is set according to the characteristics of the dynamic change of pressure to ensure that the dynamic pressure fluctuation value can be accurately recorded.

[0030] The system processes and stores the collected data on vertical contact pressure, horizontal sliding friction, and dynamic pressure fluctuations in real time for subsequent analysis and reference. During processing, filtering algorithms and other techniques are used to remove noise from the data, improving its accuracy and reliability. The system also compares and analyzes this data with historical data to better understand the changing trends in the incision's pressure state, providing a more scientific basis for subsequent parameter adjustments.

[0031] To ensure the proper functioning of various sensors, the system also incorporates sensor fault detection and alarm functionality. If a sensor malfunctions, the system promptly detects it and issues an alarm, alerting staff to repair or replace it, ensuring the accuracy and reliability of incision contact pressure data collection. The sensor selection and installation process fully considers the unique characteristics of the medical environment, ensuring compliance with medical hygiene standards, good biocompatibility, and disinfection resistance, facilitating routine cleaning and disinfection to prevent cross-infection.

[0032] Through the accurate collection and comprehensive analysis of three types of incision contact pressure data, namely vertical contact pressure, horizontal sliding friction and dynamic pressure fluctuation value, the system can more comprehensively and meticulously understand the pressure conditions of the incision during the use of the ice pillow, providing a solid data foundation for realizing the functions of adaptive incision zero compression and adjustable temperature, thereby better meeting the nursing needs of patients after severe craniocerebral surgery and promoting their recovery.

[0033] Example 2: When determining the initial temperature control threshold, the system needs to collect individual patient physiological characteristic data and combine it with the surgical type data, analyze the tolerance differences of different patients to different temperatures through an adaptive algorithm, and then determine the initial temperature control threshold for different surgical types. Among them, the collection of individual patient physiological characteristic data covers multiple dimensions, such as age information, which can be obtained through patient medical records or admission registration information. Patients of different age groups have different body temperature regulation abilities. For example, the basal metabolic rate of the elderly is lower, and their tolerance to low temperatures may be relatively weak; data related to body temperature regulation ability can be obtained through preoperative monitoring and recording of patient temperature changes, including the patient's temperature fluctuation range at rest, the reaction speed to changes in ambient temperature, etc.; basal metabolic rate data can be estimated by indirect calorimetry or using a formula, such as combining parameters such as the patient's height, weight, age and gender. Patients with a higher basal metabolic rate may produce more heat at the same temperature and have different tolerance to low temperatures.

[0034] Surgical type data collection includes the surgical site. For example, surgeries in different intracranial regions may have different temperature sensitivities. Frontal lobe surgery and brainstem surgery may have different levels of trauma and postoperative recovery requirements. The degree of surgical trauma can be measured by indicators such as duration, incision size, and the extent of tissue damage. More invasive surgeries may lead to a greater risk of postoperative temperature regulation disorders and a narrower temperature tolerance range. The system inputs these collected individual patient physiological characteristics and surgical type data into the adaptive algorithm module.

[0035] The adaptive algorithm follows a specific logic in its data analysis process. First, the patient's individual physiological characteristic data is standardized to eliminate the impact of the dimensions between different indicators and make the data comparable. For example, data such as age and basal metabolic rate are converted into standard scores so that the algorithm can perform unified analysis. Then, based on the surgical type data, feature vectors for different surgical types are established, such as quantifying factors such as the surgical site and degree of trauma into corresponding numerical features. Next, the algorithm uses cluster analysis methods in machine learning to divide patients with similar physiological characteristics and surgical types into different groups, and analyzes the differences in each group's tolerance to different temperatures.

[0036] Taking age and degree of surgical trauma as an example, for young patients with less surgical trauma, the algorithm may find that this group has a relatively strong tolerance for lower temperatures. Therefore, when determining the initial temperature control threshold, the lower limit can be set relatively low. However, for elderly patients with more surgical trauma, due to their weaker body temperature regulation ability, the algorithm will correspondingly raise the lower limit of the initial temperature control threshold to avoid the adverse effects of low temperatures on patients. During the analysis process, the algorithm also considers the correlation between various data indicators, such as the possible positive correlation between basal metabolic rate and body temperature regulation ability. Through multivariate statistical analysis methods, it comprehensively evaluates the influence of various factors on patients' temperature tolerance.

[0037] When determining the initial temperature control threshold for different types of surgeries, the system refers to a large amount of historical clinical data. These historical data include records of the effects of using ice pillows for temperature control on different patients after undergoing various types of cranial surgeries, as well as the corresponding temperature parameter settings. The algorithm matches the current patient's data with historical data, finds similar cases, analyzes the effective temperature control threshold range in historical cases, and adjusts it based on the individual differences of the current patient. For example, for a certain common type of cranial tumor resection, historical data shows that most patients recover well when the temperature control threshold is 18-22°C, but if the current patient is older and has a lower basal metabolic rate, the algorithm will appropriately increase the lower limit within the historical threshold range and adjust the initial temperature control threshold to 20-24°C.

[0038] To enable the adaptive algorithm to continuously optimize and improve analytical accuracy, the system also features self-learning capabilities. As new clinical data is continuously input, the algorithm automatically updates model parameters and adjusts the weighting of different factors to accommodate a more diverse patient population and surgical type. For example, as more data on the temperature tolerance of pediatric patients undergoing craniotomy is accumulated, the algorithm will develop a more precise analytical model for this population, ensuring that the initial temperature control threshold is more consistent with the physiological characteristics of pediatric patients.

[0039] In practice, the system generates a personalized initial temperature control threshold report for each patient. This report details the patient's individual physiological characteristics, surgical procedure type, algorithm analysis process, and the final temperature threshold range. Based on this report and the patient's real-time condition, medical staff can further adjust the ice pillow's temperature setting to ensure that temperature control achieves the therapeutic goal of reducing local incision metabolism and alleviating cerebral edema without causing adverse reactions to the patient due to excessively low or high temperatures.

[0040] The system also incorporates a data verification mechanism. Once the algorithm determines the initial temperature control threshold, it compares it to a preset safe temperature range. This range is based on medical standards and clinical experience. For example, the ice pillow's temperature should generally be controlled between 15°C and 30°C to avoid freezing or losing its cooling effect. If the algorithm-determined threshold exceeds the safe range, the system automatically issues an alert and prompts medical staff to intervene and make adjustments.

[0041] Through comprehensive collection of individual patient physiological characteristics and surgical type data, combined with in-depth analysis of adaptive algorithms, the system can accurately determine the initial temperature control threshold for each critically ill patient after craniocerebral surgery, achieve personalized temperature control, improve the safety and effectiveness of ice pillow use, and provide better care support for patients' postoperative recovery.

[0042] Example 3: After the ice pillow is activated, when the incision contact pressure data is collected and the initial zero pressure parameter is determined during the first monitoring cycle, the initial zero pressure parameter is obtained by weighted calculation combining the basic zero pressure threshold and the real-time contact pressure data. Among them, the basic zero pressure threshold is a standard value pre-set by the system based on a large amount of clinical data. The establishment of this standard value is based on a statistical analysis of the incision pressure tolerance of patients with different body shapes and different surgical types. For example, based on the common physiological characteristics of patients after severe craniocerebral surgery, by collecting the incision pressure data of patients when using ice pillows in multi-center clinical studies, the pressure range that does not cause pressure on the incision and can ensure effective contact of the ice pillow is screened out, and then the specific numerical range of the basic zero pressure threshold is determined.

[0043] The collection of real-time contact pressure data relies on a sensor array mounted on the contact surface of the ice pillow. During the first monitoring period after the ice pillow is activated (typically the first 30 minutes to one hour after the ice pillow begins operating), the sensor array continuously collects incision contact pressure data, including vertical contact pressure, horizontal sliding friction, and dynamic pressure fluctuations. This data is transmitted via a real-time transmission module to the system's data processing unit, which filters and denoises the raw data, eliminating outliers caused by slight patient movement or external interference to ensure data accuracy.

[0044] During the weighted calculation process, the basic zero-compression threshold and real-time contact pressure data are assigned different weight coefficients. The setting of the weight coefficient follows the principle of clinical priority. That is, when there is a deviation between the real-time contact pressure data and the basic zero-compression threshold, the weight ratio is automatically adjusted according to the degree of deviation. For example, if the real-time vertical contact pressure data shows that the current pressure is close to the upper limit of the basic zero-compression threshold, the system will automatically increase the weight of the real-time data, making the calculation result more inclined to adjust the initial zero-compression parameters according to the real-time pressure situation to avoid compression on the incision.

[0045] During specific implementation, the system first converts the basic zero-compression threshold into the corresponding pressure parameter baseline value, and at the same time, normalizes the real-time contact pressure data and converts it into a value with the same dimension as the baseline value. Then, according to the preset weight distribution rules, the baseline value and the standardized real-time data are weighted and summed. For example, the weight of the basic zero-compression threshold is set to 40%, and the weight of the real-time contact pressure data is set to 60%. Then, the initial zero-compression parameter = basic zero-compression threshold × 40% + real-time contact pressure data × 60%. The weight ratio can be dynamically adjusted according to the individual differences of the patient. For example, for patients with larger surgical incisions, the system will automatically increase the weight of the real-time data to more accurately match the patient's current incision pressure requirements.

[0046] During the first monitoring cycle, the system collects and dynamically analyzes real-time contact pressure data at high frequency. For example, every five minutes, a weighted calculation is performed on the collected data to generate a new candidate value for the initial zero-compression parameter, which is then compared with the previous calculation result. If the deviation between the two results is within a preset allowable range (e.g., ±5%), the current initial zero-compression parameter is considered stable. If the deviation exceeds the threshold, data collection continues and the weight coefficient is adjusted until the calculated result stabilizes. This dynamic adjustment mechanism ensures that the initial zero-compression parameter can adapt to changes in patient position or fluctuations in physiological status during the initial activation of the ice pillow.

[0047] The system also features abnormal data identification. When real-time contact pressure data shows an abnormality, such as a sudden increase or decrease, the system automatically triggers a review mechanism. By cross-verifying data from multiple sensors, the system determines whether the abnormality is caused by a sensor failure or a sudden patient condition (such as a sudden turn). If a sensor failure is confirmed, a backup sensor is activated to continue collecting data. If the abnormality is determined to be a transient pressure fluctuation caused by a change in patient position, the abnormal data is ignored to avoid interference with the calculation of the initial zero pressure parameters.

[0048] In clinical applications, medical staff can view the basic zero-compression threshold, real-time contact pressure data, and detailed parameters of the weighted calculation process through the system's human-computer interaction interface. The interface will dynamically display the generation process of the initial zero-compression parameters in the form of charts, including the pressure data change trend at each time point, the weight coefficient adjustment, etc., to facilitate real-time monitoring and intervention by medical staff. For example, when the initial zero-compression parameters calculated by the system are close to the preset safety pressure upper limit, the interface will issue an early warning prompt to remind medical staff to check the patient's position or the placement of the ice pillow.

[0049] To validate the rationale of the weighted calculation method, the system underwent extensive simulation experiments and clinical pre-tests during its development phase. The simulations used a pressure simulator to simulate different incision pressure scenarios, verifying the matching of the weighted calculation results with actual pressure requirements. The clinical pre-tests compared the clinical effects of the initial zero-compression parameters generated by the weighted calculation with those of traditional fixed parameters on patients with different types of critical craniotomy surgery. Feedback from medical staff and patients was collected, and the weight coefficient settings and calculation logic were continuously optimized.

[0050] It is worth noting that the weighted calculation of the initial zero-compression parameters is not completed in one go, but is continuously iterated and optimized during the first monitoring cycle. As the monitoring time progresses, the system collects more and more real-time contact pressure data, and the weighted calculation results will become more and more in line with the patient's actual needs. At the end of the monitoring cycle, the system will store the finalized initial zero-compression parameters in the patient's personalized data file as the baseline value for parameter correction in the subsequent second monitoring cycle.

[0051] By weighting the basic zero-compression threshold and real-time contact pressure data, the system can quickly generate initial zero-compression parameters that meet the patient's individual characteristics at the initial stage of ice pillow activation. It not only utilizes the statistical laws of historical clinical data, but also combines the patient's real-time pressure conditions to achieve personalized and dynamic setting of zero-compression parameters, laying a solid foundation for subsequent adaptive regulation.

[0052] Example 4: During the second monitoring cycle, the system needs to collect the patient's real-time body position change data and compare it with the historical body position data, and determine whether to correct the initial zero compression parameters based on the comparison results. The collection of the patient's real-time body position change data depends on the body position sensors arranged inside the ice pillow and on specific parts of the patient's body. The ice pillow usually has multiple miniature tilt sensors embedded inside it to monitor the angle changes caused by the movement of the patient's head; the sensors on the patient's body can be adhesive acceleration sensors fixed to the shoulders, back and other parts to capture the acceleration signals generated by body movement in real time. These sensors continuously collect data at a set sampling frequency (e.g., 10 times per second) to ensure that subtle changes in the patient's body position can be captured.

[0053] Historical body position data is stored in the system's database, which records all patient position changes from the initial use of the ice pillow to the present, including characteristic parameters such as the timestamp, angle offset, and acceleration peak of each position change. For example, the patient's turning over, head rotation, and other body position change data during the first monitoring cycle will be fully recorded to form a personalized historical body position feature library. At the beginning of the second monitoring cycle, the system automatically retrieves the historical body position data that matches the current monitoring time window as a comparison benchmark.

[0054] The body position data comparison process is based on feature extraction and pattern matching algorithms. The system preprocesses the real-time body position change data, using filtering algorithms to remove high-frequency noise and retain valid features reflecting body position changes, such as maximum tilt angle, duration of position change, and acceleration curve. For example, if a patient's head turns to the right, the real-time data will record the angle range, rotation speed, and acceleration changes, forming a set of feature vectors.

[0055] The system calculates similarity between this set of feature vectors and feature vectors in historical body position data. Similarity calculations can use methods such as Euclidean distance and cosine similarity to measure the degree of match between real-time features and historical features. For example, if the real-time head turn angle is 30 degrees and the turn duration is 2 seconds, and the historical data contains a record of a head turn of 28 degrees to the right for 1.9 seconds, if the distance between the feature vectors of the two in multidimensional space is less than a preset threshold, then the features are considered to be identical.

[0056] If historical position data shares characteristics with real-time position change data, the system determines that the current position change is a common movement the patient has already made and does not modify the initial zero-compression parameters. For example, if the patient has repeatedly turned their head at similar angles and speeds during the first monitoring cycle, the pressure distribution patterns corresponding to these position changes are stored in the historical data. The system assumes that the current movement will not have a new impact on the incision pressure and therefore maintains the initial zero-compression parameters unchanged.

[0057] When the historical body position data does not contain the same features as the real-time body position change data, the system determines that a new body position change pattern has occurred, which may have an unknown impact on the incision pressure distribution. In this case, the initial zero compression parameters need to be corrected. For example, during the second monitoring cycle, the patient's body rolls to the left for the first time. The historical data lacks the body position features corresponding to this movement. The system cannot use the historical data to predict the incision pressure under this position, so the parameter correction process is triggered.

[0058] In practical applications, the definition of posture features needs to take into account both accuracy and inclusiveness. The system will set a tolerance range for feature matching based on clinical experience, such as allowing posture changes within an angle deviation of ±5 degrees and a time deviation of ±0.5 seconds to be considered the same feature. This setting can not only avoid misjudgments due to subtle differences, but also ensure timely response to significantly different posture changes. For example, if the patient's head turns twice at angles of 30 degrees and 32 degrees respectively, they can be considered the same feature within the tolerance range, while a turn of 45 degrees is considered a new feature.

[0059] The system's posture data comparison module also has self-learning capabilities, continuously updating its historical posture feature library over time. When new posture change features are identified, the system automatically incorporates them into the historical data and recalculates the frequency and distribution of each feature. For example, as patients gradually increase their activity during postoperative recovery, resulting in more diverse posture changes, the system will dynamically adjust the feature matching threshold to adapt to the patient's posture change trends during the recovery phase.

[0060] Medical staff can view the comparison results and feature matching details of body position changes through the system interface. The interface displays a timeline showing the real-time body position change curve and the historical curve as an overlay comparison, with different colors marking areas with high matching and new feature areas. When the system determines that the initial zero compression parameters need to be corrected, a prompt will pop up on the interface, explaining the reason for the correction (such as "New body position feature detected: 45-degree turn to the left") and displaying a comparison chart of the relevant real-time body position data and historical data.

[0061] To validate the effectiveness of the body position matching algorithm, the system underwent extensive simulation testing and clinical sample validation during the design phase. Simulation testing used a robotic arm to simulate various body position changes, generating standard body position data to test the system's feature extraction and matching accuracy. Clinical validation involved manually labeling the types of position changes in patients at different postoperative stages, and comparing the system's matching results with manual judgment. The reliability of the matching results was improved by continuously optimizing algorithm parameters, such as adjusting the dimension of the feature vector and optimizing the similarity calculation method.

[0062] During the second monitoring cycle, the monitoring and comparison of body position changes is a continuous and dynamic process. The system updates the comparison results based on real-time data. For example, if a patient undergoes multiple similar body position changes within a short period of time, the system gradually increases the matching confidence of this feature, reducing the computational complexity for subsequent comparisons of similar movements. This dynamic optimization mechanism improves the system's response speed while reducing computing resource consumption.

[0063] It's important to note that the collection and processing of posture change data must comply with medical data privacy standards. The system anonymizes the raw sensor data to remove any identifiable information and employs encrypted transmission and storage technologies to ensure data security. In clinical use, medical staff only have access to posture analysis results relevant to patient treatment and cannot access personal privacy information contained in the raw sensor data.

[0064] By comparing and analyzing real-time body position change data with historical data, the system can accurately identify the patient's body position change pattern and determine whether the zero-compression parameters need to be adjusted. This system achieves an adaptive response to ice pillow pressure regulation, avoids the risk of incision compression caused by body position changes, and provides safer and more comfortable nursing support for patients undergoing critical craniotomy. For example, when a patient changes from a supine position to a lateral position, if this position change is recorded in the historical data, the system maintains the original parameters; if it is a new position, the system initiates the parameter correction process and recalculates the zero-compression parameters suitable for the lateral position, ensuring that the incision is always in a zero-compression state.

[0065] Example 5: When it is determined that the initial zero compression parameters need to be corrected, the system needs to calculate the comprehensive matching degree based on the incision contact pressure data and the historical body position data. The comprehensive matching degree is calculated by weighting the matching degree between the historical value and the real-time value of the vertical contact pressure, the matching degree between the historical value and the real-time value of the horizontal sliding friction, and the matching degree between the historical value and the real-time value of the dynamic pressure fluctuation value according to the preset weight coefficient. Taking the patient's position change from supine to left lateral position as an example, the system first retrieves the historical vertical contact pressure value, horizontal sliding friction value, and dynamic pressure fluctuation value corresponding to the left lateral position in the patient's historical body position data, and simultaneously collects the real-time data of the vertical contact pressure, horizontal sliding friction, and dynamic pressure fluctuation value after the current real-time body position change.

[0066] When calculating the matching degree of vertical contact pressure, the system will perform a difference analysis between the historical value and the real-time value. For example, the historical vertical contact pressure in the left lateral decubitus position is 12 mmHg, and the real-time value is 14 mmHg, with a difference of 2 mmHg. The system converts the difference into a matching percentage based on the preset mapping relationship between the difference and the matching degree. For example, a difference of 2 mmHg corresponds to a matching degree of 85%. The matching degree analysis of horizontal sliding friction is similar. Assuming that the historical horizontal sliding friction is 5 mN and the real-time value is 7 mN, a difference of 2 mN corresponds to a matching degree of 78%. The historical data of the dynamic pressure fluctuation value is a fluctuation range of ±3 mmHg in the left lateral decubitus position, and a real-time fluctuation range of ±4 mmHg. The system determines the matching degree by calculating the overlap of the fluctuation range. For example, a coincidence of 70% corresponds to a matching degree of 70%.

[0067] Preset weighting factors are set based on the importance of each pressure data point to the incision. For example, vertical contact pressure has the greatest impact on the incision, with a weighting factor of 0.5; horizontal sliding friction has the second greatest impact, with a weighting factor of 0.3; and dynamic pressure fluctuation value weighting factor of 0.2. The overall matching degree is calculated as follows: vertical contact pressure matching degree × 0.5 + horizontal sliding friction matching degree × 0.3 + dynamic pressure fluctuation matching degree × 0.2, which is 85% × 0.5 + 78% × 0.3 + 70% × 0.2 = 42.5% + 23.4% + 14% = 79.9%.

[0068] In actual application, the preset weight coefficients can be fine-tuned based on individual patient differences. For example, for patients with larger surgical incisions, horizontal sliding friction may have a greater impact on incision healing. The system will automatically adjust the weight coefficient of horizontal sliding friction to 0.4, the vertical contact pressure weight to 0.4, and the dynamic pressure fluctuation value weight to 0.2. The adjustment is based on the patient's surgical type data and postoperative recovery stage characteristics. For example, the incision of a craniotomy patient is more sensitive to horizontal friction. The system triggers adaptive adjustment of the weight coefficient by reading the surgical information in the patient's medical record.

[0069] The retrieval range of historical body position data is based on the principles of time correlation and body position similarity. The system will prioritize retrieving historical data closest to the current body position change. For example, if a patient is in the left lateral decubitus position on the third day after surgery, the system will first search for historical data on the left lateral decubitus position from the second to the third day after surgery. If there is insufficient data within this time period, the search range will be expanded to the first day after surgery. In terms of body position similarity, for body position changes with similar angles, such as left lateral decubitus position at 30 degrees and left lateral decubitus position at 40 degrees, the system will regard them as similar body positions and include them in the historical data comparison range to increase the probability of data matching.

[0070] When a patient changes position, such as from supine to semi-sitting, there may not be a completely matching position record in the historical position data. In this case, the system will search for historical data of similar positions for comparison. For example, the semi-sitting position and the supine position with the head raised at 30 degrees have some overlapping features. The system will extract the historical values ​​of vertical contact pressure and horizontal sliding friction when the patient is supine with the head raised at 30 degrees, and calculate the matching degree with the real-time data of the semi-sitting position. Although the two are not completely consistent, the analysis of the overlapping features can still provide a comprehensive matching degree with reference value.

[0071] The system automatically adjusts the frequency of real-time pressure data collection based on the magnitude of position changes. When a patient undergoes a significant position change, such as suddenly rising from a supine position, the system increases the pressure data collection frequency from 1 to 5 times per second to ensure that instantaneous peaks and fluctuations in pressure are captured, preventing missed data from affecting the matching calculation. When the patient's position is relatively stable, the collection frequency returns to normal to conserve system resources.

[0072] The calculated comprehensive matching degree is displayed in real time on the system interface as a progress bar or percentage, allowing medical staff to intuitively understand the degree of match between current pressure data and historical data. When the comprehensive matching degree exceeds a preset matching degree threshold (e.g., 80%), the system determines that the current pressure state is similar to the historical state and determines the temperature correction coefficient based on the historical data. When the matching degree falls below the threshold, the intelligent learning algorithm is activated to determine the coefficient.

[0073] During the clinical validation phase, the system collected and analyzed body position change and pressure data from a large number of patients. For example, the system monitored the left lateral decubitus position of 100 critically ill patients undergoing craniotomy and calculated their overall matching degree. It was found that 70 of these patients had an overall matching degree exceeding 80%, and similar body position records existed in their historical data. However, 30 patients had a matching degree below 80%, primarily those in the early postoperative period or with complications, whose body position change characteristics differed significantly from historical data. Through analysis of these actual cases, the system continuously optimized the matching degree calculation model and weight coefficient settings to improve the accuracy of the overall matching degree calculation.

[0074] It's worth noting that when historical values ​​for a certain type of pressure data are missing, the system automatically adjusts the weighting. For example, if a patient's historical data lacks records of dynamic pressure fluctuations, the system will temporarily set the weight coefficient for the dynamic pressure fluctuations to 0 and calculate the overall matching degree based solely on the matching degree between vertical contact pressure and horizontal sliding friction, thus avoiding calculation errors caused by missing data. The system will also mark the missing data and prioritize its collection in subsequent monitoring to complete the patient's historical data archive.

[0075] By performing multi-dimensional matching calculations on historical data and real-time data of vertical contact pressure, horizontal sliding friction, and dynamic pressure fluctuation values, and combining them with weighted processing using preset weight coefficients, the system can accurately assess the degree of similarity between the current pressure state and the historical situation, providing a scientific basis for determining the temperature correction coefficient, and ensuring that when the patient's position changes, the temperature control parameters of the ice pillow can be reasonably corrected according to the pressure changes, maintaining the zero-compression state of the incision and a suitable temperature environment.

[0076] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0077] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An adaptive incision zero-compression and temperature-adjustable ice pillow system for severe craniotomy, characterized by: include: The temperature sensing unit is used to collect the patient's postoperative incision area temperature data and the ice pillow's basic temperature data, determine the initial temperature control threshold, and generate temperature control instructions based on an adaptive algorithm; The pressure monitoring unit is configured to collect incision contact pressure data and determine an initial zero-compression parameter during a first monitoring period after the ice pillow is activated; and is further configured to collect real-time patient position change data during a second monitoring period and compare it with historical position data, and determine whether to modify the initial zero-compression parameter based on the comparison result; a control execution unit, configured to, when determining to correct the initial zero compression parameter, calculate a comprehensive matching degree based on the incision contact pressure data and the historical body position data, compare the comprehensive matching degree with a matching degree threshold, and determine a temperature correction coefficient based on the comprehensive matching degree; When the comprehensive matching degree is greater than the matching degree threshold, determining the temperature correction coefficient according to the historical body position data; When the comprehensive matching degree is less than or equal to the matching degree threshold, determining the temperature correction coefficient by an intelligent learning algorithm; The control center is configured to correct the initial zero pressure parameter according to the temperature correction coefficient, and complete the ice pillow temperature control with the corrected final zero pressure parameter.

2. The adaptive incision zero-compression and temperature-adjustable ice pillow system for severe craniocerebral surgery according to claim 1 is characterized in that: The incision contact pressure data includes vertical contact pressure, horizontal sliding friction and dynamic pressure fluctuation value.

3. The adaptive incision zero-compression and temperature-adjustable ice pillow system for severe craniocerebral surgery according to claim 2 is characterized in that: Determining the initial temperature control threshold includes: The patient's individual physiological characteristic data is collected and combined with the surgery type data, and the adaptive algorithm is used to analyze the tolerance differences of different patients to different temperatures, so as to determine the initial temperature control thresholds for different surgery types.

4. The adaptive incision zero-compression and temperature-adjustable ice pillow system for severe craniocerebral surgery according to claim 3 is characterized in that: After the ice pillow is activated, when collecting incision contact pressure data and determining the initial zero pressure parameter in the first monitoring cycle, the initial zero pressure parameter is obtained by weighted calculation combining the basic zero pressure threshold and the real-time contact pressure data.

5. The adaptive incision zero-compression and temperature-adjustable ice pillow system for severe craniocerebral surgery according to claim 4 is characterized in that: In the second monitoring period, the real-time body position change data of the patient is collected and compared with the historical body position data, and whether the initial zero compression parameter is to be corrected is determined according to the comparison result, including: When the historical body position data has the same features as the real-time body position change data, the initial zero compression parameter is not corrected; When the historical body position data does not contain the same features as those in the real-time body position change data, the initial zero compression parameter is modified.

6. The adaptive incision zero-compression and temperature-adjustable ice pillow system for severe craniocerebral surgery according to claim 5 is characterized in that: When it is determined that the initial zero compression parameter is to be corrected, the comprehensive matching degree is calculated according to the incision contact pressure data and the historical body position data, including: The comprehensive matching degree is obtained by weighted calculation based on the preset weight coefficients through the matching degree between the historical value and the real-time value of the vertical contact pressure, the matching degree between the historical value and the real-time value of the horizontal sliding friction, and the matching degree between the historical value and the real-time value of the dynamic pressure fluctuation value.

7. The adaptive incision zero-compression and temperature-adjustable ice pillow system for severe craniocerebral surgery according to claim 6 is characterized in that: When determining the temperature correction coefficient based on the comprehensive matching degree, it includes: Comparing the comprehensive matching degree with a preset matching degree threshold, and determining a temperature correction coefficient based on the comparison result; When data exists in the historical body position data and the comprehensive matching degree is greater than the matching degree threshold, determining the temperature correction coefficient according to the historical body position data; When there is no data in the historical body position data whose comprehensive matching degree is greater than the matching degree threshold, the temperature correction coefficient is determined according to an intelligent learning algorithm.

8. The adaptive incision zero-compression and temperature-adjustable ice pillow system for severe craniocerebral surgery according to claim 7 is characterized in that: Determining the temperature correction coefficient based on the historical body position data includes: When there is only one data in the historical body position data whose comprehensive matching degree is greater than the matching degree threshold, the historical temperature correction coefficient corresponding to the data is used as the temperature correction coefficient; When there is more than one data in the historical body position data whose comprehensive matching degree is greater than the matching degree threshold, the average of the historical temperature correction coefficients corresponding to the respective data is used as the temperature correction coefficient.

9. The adaptive incision zero-compression and temperature-adjustable ice pillow system for severe craniocerebral surgery according to claim 8, characterized in that: When determining the temperature correction coefficient according to the intelligent learning algorithm, it includes: establishing a training data set based on the incision contact pressure data, the patient position change data, and the historical temperature correction coefficient; using a neural network model to learn the relationship between the initial zero compression parameter and the patient position change data through the training data set to predict the final zero compression parameter; and adjusting the model parameters using a parameter optimization algorithm; After the training is completed, the incision contact pressure data and the patient position change data are input into the trained neural network model to obtain the temperature correction coefficient; The initial zero pressure parameter is corrected according to the temperature correction coefficient.

10. The adaptive incision zero-compression and temperature-adjustable ice pillow system for severe craniocerebral surgery according to claim 7, characterized in that: The matching threshold is dynamically adjusted according to the patient's age, degree of surgical trauma, and physiological characteristic data of the postoperative recovery stage, and the adjustment is based on the matching distribution pattern of patients with the same characteristics in historical data.

Images