An intelligent surgical body position monitoring method and system for long-time surgery pressure injury prevention

Abstract

The application discloses a kind of intelligent operation body position monitoring method and system for long time operation pressure injury prevention, it is related to intelligent medical equipment and medical sensing monitoring technical field, for solving the problem of poor anti-interference and prone to body position displacement caused by blind decompression of traditional operation pressure sore prevention means.First, stress and temperature and humidity signals are acquired by sensor array and compensation calibration is carried out, environmental interference is eliminated to construct pressure distribution matrix;Subsequently, stress gradient is analyzed and time accumulation mapping is carried out relying on topological characteristics, and core high-risk site and load characteristics are accurately locked;Then, physiological and time sequence parameters of patient are fused to deduce tolerance baseline, and individualized bearing limit boundary is generated to realize dynamic early warning;Finally, the strategy of establishing support by using peripheral air bag progressive pre-inflation and center air bag servo unloading exhaust is adopted, which completely resolves concentrated stress while maintaining the absolute stability of operation body position, and constructs active protection closed-loop system.

Description

Technical Field

[0001] This invention relates to the field of intelligent medical equipment and medical sensing and monitoring technology, specifically to an intelligent surgical position monitoring method and system for preventing pressure injury during prolonged surgery. Background Technology

[0002] In prolonged surgical procedures such as those in burn wards, orthopedics, and spinal surgery, patients are under anesthesia and unable to adjust their posture or express pain or discomfort. When bony prominences are subjected to concentrated high-pressure loads for extended periods, the microcirculation of local tissues is severely impaired, leading to intraoperative pressure injuries. This significantly increases the risk of postoperative infection and the difficulty of recovery for patients.

[0003] Current methods for preventing pressure ulcers generally exhibit limitations due to their passive nature. Traditional positioning pads rely solely on the physical deformation of materials like gels or sponges to disperse pressure, failing to provide quantitative monitoring of contact surface stress. They heavily depend on medical staff manually adjusting the patient's position periodically, a human intervention method easily overlooked during busy surgical procedures, leaving local tissues continuously under dangerous pressure. Some non-contact monitoring solutions using optical cameras are severely obstructed by sterile drapes, blankets, and surgical instruments in actual surgical environments, leading to monitoring failure and extremely poor measurement accuracy. Furthermore, devices employing dense, flexible sensor matrices often have extremely complex circuitry, making them unable to withstand the repeated high-temperature, high-pressure sterilization environment of the operating room, easily causing structural damage. Simultaneously, these devices typically only display numerical values ​​and do not form a closed-loop linkage with the positioning pad's actuator; forced single-point decompression can easily disrupt the absolute stability of the surgical position. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an intelligent surgical position monitoring method and system for preventing pressure injuries during prolonged surgeries, thus solving the problems mentioned in the background.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent surgical positioning monitoring method for preventing pressure injuries during prolonged surgery, comprising the following steps: S1. Simultaneously acquiring contact surface force signals and microenvironment temperature and humidity signals through a biomimetic honeycomb flexible pressure sensor array within the positioning pad substrate; calling a preset temperature and humidity self-compensation algorithm to parse the microenvironment temperature and humidity signals into environmental compensation parameters; combining the environmental compensation parameters to perform baseline drift calibration on the contact surface force signals, and constructing a two-dimensional pressure distribution matrix; S2. Based on the hexagonal topological features of the biomimetic honeycomb flexible pressure sensor array, locking local pressure peak nodes in the two-dimensional pressure distribution matrix; analyzing the spatial stress gradient vectors between the local pressure peak nodes and adjacent nodes; and addressing abnormal stress concentration nodes... S3. Perform load accumulation mapping in the time dimension, outputting the coordinates of the core high-risk bony prominence and dynamic load accumulation characteristics; S4. Extract the tissue tolerance baseline model associated with the coordinates of the core high-risk bony prominence, collect the patient's physiological signs and surgical process time parameters as multimodal constraints, input them into the tissue tolerance baseline model for state evolution deduction, and generate individualized bearing limit boundaries; S5. When the dynamic load accumulation characteristics reach the individualized bearing limit boundary, map the controllable airbags in the central zone and the adjacent peripheral zone according to the coordinates of the core high-risk bony prominence, drive the micro air pump group to perform progressive pre-inflation of the controllable airbags in the adjacent peripheral zone, and after the support stress in the controllable airbags in the adjacent peripheral zone reaches the preset position maintenance standard, control the controllable airbags in the central zone to perform servo unloading and degassing actions.

[0006] Furthermore, the specific process of simultaneously acquiring the contact surface force signal and the microenvironment temperature and humidity signal through the biomimetic honeycomb flexible pressure sensor array within the body positioning pad substrate, and calling the preset temperature and humidity self-compensation algorithm to parse the microenvironment temperature and humidity signal into environmental compensation parameters is as follows: Separate the composite detection signal collected by the biomimetic honeycomb flexible pressure sensor array to obtain the contact surface force signal and the microenvironment temperature and humidity signal; decompose the microenvironment temperature and humidity signal to extract the temperature fluctuation feature vector and the humidity wetting feature vector, and input the temperature fluctuation feature vector and the humidity wetting feature vector into the preset substrate drift feature library for matching to obtain the thermal impedance compensation coefficient and the humidity-sensitive capacitance compensation coefficient; fuse the thermal impedance compensation coefficient and the humidity-sensitive capacitance compensation coefficient to generate the environmental compensation parameter.

[0007] Furthermore, the specific process of constructing a two-dimensional pressure distribution matrix by performing baseline drift calibration on the contact surface force signal in conjunction with environmental compensation parameters is as follows: the contact surface force signal is converted into an initial pressure amplitude sequence, and the initial pressure amplitude sequence is reverse-weighted and corrected by environmental compensation parameters to filter out thermal and moisture drift noise and generate the real contact surface pressure amplitude; the spatial physical coordinates of each sensing unit in the biomimetic honeycomb flexible pressure sensor array are extracted, and the real contact surface pressure amplitude is mapped to the corresponding spatial physical coordinates to construct a two-dimensional pressure distribution matrix.

[0008] Furthermore, based on the hexagonal topological features of the biomimetic cellular flexible pressure sensor array, the specific process of locking local pressure peak nodes in the two-dimensional pressure distribution matrix and analyzing the spatial stress gradient vectors between local pressure peak nodes and adjacent nodes is as follows: traverse the node pressure values ​​in the two-dimensional pressure distribution matrix, extract the nodes with extreme values ​​as local pressure peak nodes, and locate the six adjacent nodes physically bordering the local pressure peak nodes based on the hexagonal topological features; extract the neighborhood pressure values ​​of the six adjacent nodes and the stress difference features between the local pressure peak nodes and their neighborhood pressure values, and combine them with the physical border distance parameter to construct a six-dimensional spatial stress gradient vector pointing from the local pressure peak nodes to the six adjacent nodes.

[0009] Furthermore, the specific process of performing load accumulation mapping on abnormal stress concentration nodes in the time dimension and outputting the coordinates of the core high-risk bony protuberances and dynamic load accumulation features is as follows: extract the nodes where the magnitude of the vector in the six-dimensional spatial stress gradient vector exceeds the preset safety gradient and mark them as abnormal stress concentration nodes, and mark the spatial physical coordinates corresponding to the abnormal stress concentration nodes as the coordinates of the core high-risk bony protuberances; introduce time slice sequences to extract the pressure amplitude of the core high-risk bony protuberance coordinates in the continuous time slice sequence, perform discrete-time integral mapping on the pressure amplitude along the time slice sequence, and generate dynamic load accumulation features that characterize the continuous pressure state of the tissue.

[0010] Furthermore, the specific process of extracting the tissue tolerance baseline model associated with the coordinates of core high-risk bony prominences and collecting patient physiological parameters and surgical process time parameters as multimodal constraints is as follows: Anatomical partition nodes mapped by the coordinates of core high-risk bony prominences are extracted, and the inherent pressure benchmarks corresponding to the anatomical partition nodes under standard physiological conditions are retrieved to construct the tissue tolerance baseline model; core body temperature characteristic parameters and body mass index parameters are collected in real time to construct a set of physiological parameters, and the expected total intervention duration parameter and the current real-time running time scale are extracted to construct a set of surgical process time parameters; the physiological parameter set and the surgical process time parameter set are fused to generate multimodal constraints.

[0011] Furthermore, the specific process of inputting the tissue tolerance baseline model for state evolution deduction and generating individualized bearing limit boundaries is as follows: Analyze the multimodal constraints, obtain the physiological metabolic lag weights generated by the conversion of the physiological sign parameter set and the temporal compression attenuation weights generated by the conversion of the surgical process temporal parameter set; use the physiological metabolic lag weights and temporal compression attenuation weights as dynamic fine-tuning factors to perform nonlinear weighted mapping processing on the inherent pressure benchmark inside the tissue tolerance baseline model, and output the individualized bearing limit boundary characterizing the current critical state of tissue pressure.

[0012] Furthermore, when the dynamic load accumulation characteristics reach the individualized bearing limit boundary, the specific process of driving the micro-pump group to perform progressive pre-inflation of the adjacent peripheral zone controllable airbags based on the coordinate mapping of the core high-risk bony prominences to the central zone controllable airbags and the adjacent peripheral zone controllable airbags is as follows: When the dynamic load accumulation characteristics reach the individualized bearing limit boundary, the spatial matrix of the body positioning pad substrate corresponding to the coordinates of the core high-risk bony prominences is analyzed, and the physical address of the independent airbag directly below the spatial matrix is ​​marked as the central zone controllable airbag; the surrounding airbag group that is adjacent to the physical edge of the central zone controllable airbag is located and marked as the adjacent peripheral zone controllable airbags based on the hexagonal topological characteristics; the micro-pump group is controlled to input an inflation airflow in a stepped increasing mode to the adjacent peripheral zone controllable airbags to perform progressive pre-inflation.

[0013] Furthermore, after the support stress inside the controllable airbags of the adjacent outer zones reaches the preset body position maintenance standard, the specific process of controlling the controllable airbags of the central zone to perform servo unloading and exhaust actions is as follows: real-time air pressure closed-loop feedback signals of the controllable airbags of the adjacent outer zones are collected, and the stress distribution vector characterizing the spatial support stiffness in the real-time air pressure closed-loop feedback signals is extracted; when the stress distribution vector matches the preset body position maintenance standard, the micro air pump group is controlled to maintain the inflation pressure of the controllable airbags of the adjacent outer zones, and the proportional servo exhaust valve associated with the controllable airbags of the central zone is activated; a pulse width modulation duty cycle control signal is sent to the proportional servo exhaust valve to release the gas inside the controllable airbags of the central zone to perform servo unloading and exhaust actions.

[0014] An intelligent surgical positioning monitoring system for preventing pressure injuries during prolonged surgery, comprising: a signal processing module for simultaneously acquiring contact surface force signals and microenvironment temperature and humidity signals via a biomimetic honeycomb flexible pressure sensor array within a positioning pad substrate; calling a preset temperature and humidity self-compensation algorithm to parse the microenvironment temperature and humidity signals into environmental compensation parameters; combining the environmental compensation parameters to perform baseline drift calibration on the contact surface force signals; and constructing a two-dimensional pressure distribution matrix; and a stress analysis module for identifying local pressure peak nodes in the two-dimensional pressure distribution matrix based on the hexagonal topological features of the biomimetic honeycomb flexible pressure sensor array; analyzing the spatial stress gradient vectors between the local pressure peak nodes and adjacent nodes; and analyzing abnormal stress concentrations. The node performs load accumulation mapping in the time dimension, outputting the coordinates of the core high-risk bony prominence and dynamic load accumulation characteristics; the state inference module is used to extract the tissue tolerance baseline model associated with the coordinates of the core high-risk bony prominence, collect the patient's physiological signs parameters and surgical process time parameters as multimodal constraints, input the tissue tolerance baseline model to perform state evolution inference, and generate individualized bearing limit boundaries; the servo control module is used to drive the micro air pump group to perform progressive pre-inflation of the adjacent peripheral controllable airbags according to the coordinates of the core high-risk bony prominence mapping of the central zone controllable airbag and the adjacent peripheral zone controllable airbags when the dynamic load accumulation characteristics reach the individualized bearing limit boundary; after the support stress in the adjacent peripheral zone controllable airbags reaches the preset position maintenance standard, the central zone controllable airbag is controlled to perform servo unloading and degassing actions.

[0015] The present invention has the following beneficial effects:

[0016] (1) A smart surgical position monitoring method for preventing pressure injury during long-term surgery. The method acquires force signals and temperature and humidity signals synchronously through a sensor array in the positioning pad matrix and performs environmental compensation and baseline drift calibration, effectively eliminating the interference of the complex microenvironment of the operating room on the underlying physical signals. At the same time, based on the hexagonal topological features of the biomimetic cellular array, the method locks the local pressure peak nodes and analyzes the spatial stress gradient vector. The method performs load accumulation mapping on abnormal stress concentration nodes in the time dimension. From the dual interweaving of deep physical mechanics and time accumulation, the method accurately extracts the coordinates of the core high-risk bony prominences and the dynamic load accumulation features, completely changing the shortcomings of the traditional solution that only relies on passive physical deformation to disperse pressure.

[0017] (2) An intelligent surgical position monitoring system for preventing pressure injury during long-term surgery extracts a tissue tolerance baseline model and integrates the patient's individual physiological signs parameters with the surgical process time parameters for deduction. This breaks the limitations of the traditional single fixed alarm threshold and generates an individualized bearing limit boundary that characterizes the current critical state of tissue pressure, thus realizing a refined early warning that varies from person to person. On this basis, when the load reaches the limit boundary, the system drives the adjacent peripheral airbags to perform progressive pre-inflation based on the high-risk coordinates. After the position maintenance standard is reached, the control center airbag performs servo unloading and exhaust actions, which cleverly realizes the smooth dissipation of local concentrated stress to the surrounding healthy tissues. Under the premise of ensuring the absolute macroscopic stability of the surgical position, it completes automated active intervention.

[0018] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0019] Figure 1 This is a flowchart of an intelligent surgical position monitoring method for preventing pressure injury during prolonged surgery, according to the present invention.

[0020] Figure 2 This is a schematic diagram of dynamic load accumulation and the evolution of the bearing limit boundary.

[0021] Figure 3 This is a schematic diagram of the servo control for peripheral pre-inflation and central unloading.

[0022] Figure 4 This is a flowchart of an intelligent surgical position monitoring system for preventing pressure injury during prolonged surgery, as described in this invention. Detailed Implementation

[0023] This application provides an intelligent surgical position monitoring method and system for preventing pressure injuries during prolonged surgery. It solves the problems of delayed intraoperative intervention due to passive protection and poor equipment anti-interference capabilities in traditional pressure ulcer prevention methods, as well as the easy occurrence of patient displacement during surgery due to direct local decompression.

[0024] The overall approach of the scheme in this application embodiment is as follows: First, a biomimetic honeycomb flexible pressure sensor array is used to simultaneously acquire force signals and temperature and humidity signals, which are then analyzed into environmental compensation parameters. Baseline drift calibration is performed on the force signals to construct a two-dimensional pressure distribution matrix. Next, relying on the hexagonal topological features of the sensor array, local pressure peak nodes are locked in the matrix and the spatial stress gradient vector is analyzed. Load accumulation mapping in the time dimension is performed on abnormal stress concentration nodes to output the coordinates of the core high-risk bony prominences and dynamic load accumulation features. Subsequently, a tissue tolerance baseline model is extracted and fused with the patient's physiological signs and surgical timing parameters to generate an individualized bearing limit boundary. Finally, when the dynamic load reaches the bearing limit boundary, the surrounding airbags are precisely pre-inflated based on the core coordinates to establish flexible support. After the support stress reaches the standard, the central airbag is controlled to perform a servo unloading and degassing action, thereby completing the adaptive spatial load transfer while maintaining body position stability.

[0025] Please see Figure 1 This invention provides a technical solution: an intelligent surgical positioning monitoring method for preventing pressure injuries during prolonged surgery, comprising the following steps: S1. Simultaneously acquiring contact surface force signals and microenvironment temperature and humidity signals through a biomimetic honeycomb flexible pressure sensor array within the positioning pad substrate; calling a preset temperature and humidity self-compensation algorithm to parse the microenvironment temperature and humidity signals into environmental compensation parameters; combining the environmental compensation parameters to perform baseline drift calibration on the contact surface force signals, and constructing a two-dimensional pressure distribution matrix; S2. Based on the hexagonal topological features of the biomimetic honeycomb flexible pressure sensor array, locking local pressure peak nodes in the two-dimensional pressure distribution matrix; analyzing the spatial stress gradient vectors of local pressure peak nodes and adjacent nodes; and analyzing the time dimension of abnormal stress concentration nodes. S3. Perform load accumulation mapping and output the coordinates of the core high-risk bony prominence and dynamic load accumulation characteristics; S4. Extract the tissue tolerance baseline model associated with the coordinates of the core high-risk bony prominence, collect the patient's physiological signs and surgical process time parameters as multimodal constraints, input them into the tissue tolerance baseline model for state evolution deduction, and generate individualized bearing limit boundaries; S5. When the dynamic load accumulation characteristics reach the individualized bearing limit boundary, map the controllable airbags in the central zone and the adjacent peripheral zone according to the coordinates of the core high-risk bony prominence, drive the micro air pump group to perform progressive pre-inflation of the controllable airbags in the adjacent peripheral zone, and after the support stress in the controllable airbags in the adjacent peripheral zone reaches the preset position maintenance standard, control the controllable airbags in the central zone to perform servo unloading and degassing actions.

[0026] In this implementation scheme, the main function of step S1 is to accurately collect and calibrate underlying physical data in the complex operating room microenvironment. In this step, the biomimetic honeycomb flexible pressure sensor array refers to a thin-film sensor network arranged in a hexagonal topology. This structure can comprehensively cover key pressure areas such as the sacrum, coccyx, and scapula while significantly reducing the number of sensor nodes and wiring, giving it excellent flexibility and the ability to withstand the high temperature and high pressure sterilization of the operating room. Baseline drift calibration refers to the process of correcting the sensor zero-point measurement shift caused by intraoperative irrigation fluid immersion, disinfectant evaporation, or a sudden drop in patient body temperature, using synchronously collected temperature and humidity parameters for reverse physical parameter correction. The technical role of this step is to eliminate the physical interference of the harsh clinical microenvironment on electronic components at the source, ensuring that the final acquired two-dimensional pressure distribution matrix can accurately and faithfully reflect the actual force on the patient's skin contact surface.

[0027] The main function of step S2 is to accurately pinpoint the true high-risk compression origin based on the dual superposition of spatial physical distribution and temporal dimension. In this step, the spatial stress gradient vector refers not only to extracting the absolute pressure value of a single node, but also to using the hexagonal physical arrangement characteristics to calculate the force difference and direction between the central peak node and the six surrounding adjacent nodes, thereby quantifying the degree of physical tearing and concentrated compression experienced by the local skin tissue. Load accumulation mapping refers to performing discrete-time integration calculations on the continuous surgical time axis to comprehensively assess the damage risk caused by the duration of compression. The technical advantage of this step is that it abandons the crude judgment method of traditional equipment that only looks at the absolute value of instantaneous single-point pressure. Through spatial topological deduction and temporal accumulation analysis, it accurately outputs the coordinates of the core high-risk bony prominences and their true dynamic load accumulation characteristics, providing extremely precise target points for subsequent intervention.

[0028] The main function of step S3 is to integrate individual patient physiological differences with the characteristics of the current surgical procedure to establish a personalized dynamic early warning safety line. In this step, the tissue tolerance baseline model refers to the physical limit data framework that a specific bony prominence anatomical location can withstand compression under standard physiological conditions; the multimodal constraint conditions are injected into the model as fine-tuning factors, such as the patient's real-time core deep body temperature, body mass index, and estimated total surgical time. For example, when the patient is thin or under hypothermic anesthesia, their critical tolerance for capillary closure will decrease sharply. The technical significance of this step is that it breaks through the limitations of previous medical monitoring equipment that rigidly applied a single alarm value. Through the weighted evolution of multi-source parameters, it generates an individualized bearing limit boundary that perfectly matches the current real-time physiological state of the patient, realizing a leap from static alarm to dynamic and precise early warning.

[0029] The main function of step S4 is to perform physical load transfer and automated decompression while maintaining the absolute macroscopic stability of the patient's surgical position. In this step, progressive pre-inflation refers to the micro-pump assembly slowly injecting stepped airflow into the adjacent zone airbags around the high-risk coordinate, establishing a flexible support surface around the pressure origin. Servo unloading and venting refers to the precise release of the resident gas in the central high-risk airbag through the proportional venting valve at the hardware level after the supporting force of the peripheral airbags reaches the set standard and the spatial gravity is successfully distributed. The technical role of this step is to realize an automated closed loop from monitoring to physical intervention. Through this stepped control logic of first supporting the periphery and then unloading the center, the local peak pressure is smoothly dissipated to the surrounding healthy tissue, completely solving the core clinical pain point that direct in-situ deflating of traditional equipment will cause the patient's body to collapse and shift, thereby compromising the surgeon's surgical field of vision and operational precision.

[0030] Specifically, the process of simultaneously acquiring contact surface force signals and microenvironment temperature and humidity signals through a biomimetic honeycomb flexible pressure sensor array within the body positioning pad substrate, and then using a preset temperature and humidity self-compensation algorithm to parse the microenvironment temperature and humidity signals into environmental compensation parameters is as follows: Separate the composite detection signals collected by the biomimetic honeycomb flexible pressure sensor array to obtain contact surface force signals and microenvironment temperature and humidity signals; decompose the microenvironment temperature and humidity signals to extract temperature fluctuation feature vectors and humidity wetting feature vectors, and input these vectors into a preset substrate drift feature library for matching to obtain thermal impedance compensation coefficients and humidity-sensitive capacitance compensation coefficients; and fuse the thermal impedance compensation coefficients and humidity-sensitive capacitance compensation coefficients to generate environmental compensation parameters.

[0031] In this implementation scheme, due to the sweat produced on the patient's skin during prolonged surgery, which may be accompanied by the infiltration of surgical irrigation fluid or disinfectant, coupled with the interaction between patient body temperature fluctuations and the insulation measures of anesthesia equipment, the flexible pressure sensor within the positioning pad substrate will experience significant temperature and humidity impedance drift. Therefore, the system first separates the composite detection signal through hardware filtering and multi-channel demultiplexing technology, purifying the pure contact surface force signal and microenvironment temperature and humidity signal. Subsequently, the system performs time-domain and frequency-domain decomposition on the microenvironment temperature and humidity signal, extracting the temperature fluctuation feature vector reflecting the temperature change gradient and the humidity infiltration feature vector reflecting the moisture penetration depth. By inputting the above feature vectors into a pre-set substrate drift feature library, the system can match the electrical offset of the flexible substrate under the current thermodynamic and hydrodynamic state. To accurately quantify this offset, the system calculates the thermal impedance compensation coefficient and the humidity-sensitive capacitance compensation coefficient using the polynomial regression model built into the substrate drift feature library, and performs a fusion calculation to generate environmental compensation parameters. The specific fusion calculation logic satisfies the following formula: ; ; Where m represents the sensing node number in the biomimetic honeycomb flexible pressure sensor array; The dimension number represents the temperature fluctuation feature; A represents the total number of dimensions of the temperature fluctuation feature. The substrate sensitivity weight represents the temperature fluctuation characteristic of the a-th dimension; This represents the a-th dimension component in the temperature fluctuation feature vector corresponding to the m-th sensing node. This represents the inherent thermal baseline constant of the system; represents the thermal impedance compensation coefficient of the m-th sensing node; b represents the dimension number of the humidity wetting feature; B represents the total number of dimensions of the humidity wetting feature; The dielectric constant attenuation weight represents the b-th dimension of the humidity wetting characteristic; This represents the b-th dimension component in the humidity wetting feature vector corresponding to the m-th sensing node. This represents the baseline constant of the humidity-sensitive capacitance inherent in the system; This represents the humidity-sensitive capacitance compensation coefficient of the m-th sensing node; Indicates the thermal coupling weighting factor; This represents the humidity-sensitive coupling weighting factor; R represents the weighting factor for thermal and humidity cross-interference; R_m represents the final generated environmental compensation parameter corresponding to the m-th sensor node. The above weighting factors... , as well as The method for establishing this is as follows: During the factory calibration stage, the positioning pad substrate is placed in a multi-gradient temperature and humidity alternating test chamber. The true baseline drift impedance values ​​of the flexible sensor under different temperature and humidity combinations are collected. The true baseline drift impedance values ​​measured in the historical data are then solved using a multi-dimensional surface fitting method with the least squares approach. Through the above formula, the system not only considers the independent drift effects of temperature and humidity but also introduces a thermal-humidity cross-coupling term, thus accurately reproducing the comprehensive interference base of the complex surgical microenvironment on the underlying electrical components.

[0032] Specifically, the process of constructing a two-dimensional pressure distribution matrix by performing baseline drift calibration on the contact surface force signal in conjunction with environmental compensation parameters is as follows: the contact surface force signal is converted into an initial pressure amplitude sequence, and the initial pressure amplitude sequence is reverse-weighted and corrected by environmental compensation parameters to filter out thermal and moisture drift noise and generate the real contact surface pressure amplitude; the spatial physical coordinates of each sensing unit in the biomimetic honeycomb flexible pressure sensor array are extracted, and the real contact surface pressure amplitude is mapped to the corresponding spatial physical coordinates to construct a two-dimensional pressure distribution matrix.

[0033] In this implementation scheme, after obtaining accurate environmental compensation parameters, the system needs to correct distorted pressure data to accurately reflect the physical pressure state of the patient's bony prominence. The system first uses a high-precision analog-to-digital converter to convert the contact surface force signal into an initial pressure amplitude sequence. Because flexible materials typically exhibit micro-deformation of elastic modulus and increased background capacitance under high temperature and humidity conditions, directly measured pressure values ​​may be too high or too low. Therefore, the system uses environmental compensation parameters to perform inverse weighted correction on the initial pressure amplitude sequence, thoroughly filtering out thermal and humidity drift noise and restoring the true mechanical contact surface pressure amplitude. Next, given that the biomimetic honeycomb flexible pressure sensor array has a hexagonal non-orthogonal geometric arrangement, its directly output node values ​​cannot be directly identified and analyzed by conventional orthogonal image processing algorithms. The system must extract the absolute spatial physical coordinates of each sensing unit and map the true contact surface pressure amplitude to a standard two-dimensional orthogonal coordinate system using a spatial topological Gaussian interpolation algorithm, thereby constructing a continuous and high-resolution two-dimensional pressure distribution matrix. The specific inverse calibration and spatial mapping logic satisfies the following formula: ; Where c represents the physical index number of the force sensing unit; This represents the instantaneous amplitude value in the initial pressure amplitude sequence output by the c-th force sensing unit; This represents the environmental compensation parameter mapped to the c-th force sensing unit; This represents the zero-point drift reverse suppression coefficient; This represents the intrinsic response gain constant of the sensing material; This represents the gain drift coefficient caused by environmental interference. This represents the actual contact surface pressure amplitude of the c-th force sensing unit after filtering out thermal and moisture drift noise. The value represents the pressure pixel value at the normalized plane coordinate point (x, y) of the constructed two-dimensional pressure distribution matrix; C represents the total number of force sensing units participating in the mapping. This represents the horizontal spatial physical coordinates of the c-th force sensing unit on the two-dimensional plane projection; This represents the longitudinal spatial physical coordinates of the c-th force sensing unit on the two-dimensional plane projection; This represents the physical stress diffusion radius constant of the body positioning pad substrate material. The physical stress diffusion radius constant here... Primarily used to characterize the attenuation range of concentrated pressure spreading outwards from within the flexible pad, its value is pre-established through finite element stress simulation calculations based on the Young's modulus and thickness parameters of the silicone and sponge composite substrate of the positioning pad surface. Through this complete mathematical transformation process, the system effectively eliminates spurious high-pressure signals generated by the complex environmental variables of the operating room and smoothly transforms discrete biomimetic cellular topology nodes into an orthogonal force field with precise spatial continuity. This provides a high-fidelity underlying data foundation for subsequently accurately locating and tracing abnormal compression points at high-risk bony prominences in the time dimension.

[0034] Specifically, based on the hexagonal topological features of the biomimetic cellular flexible pressure sensor array, the process of locking local pressure peak nodes in the two-dimensional pressure distribution matrix and analyzing the spatial stress gradient vectors between local pressure peak nodes and adjacent nodes is as follows: traverse the node pressure values ​​in the two-dimensional pressure distribution matrix, extract the nodes with extreme values ​​as local pressure peak nodes, and locate the six adjacent nodes physically bordering the local pressure peak nodes based on the hexagonal topological features; extract the neighborhood pressure values ​​of the six adjacent nodes and the stress difference features between the local pressure peak nodes and their neighborhood pressure values, and combine these with the physical border distance parameter to construct a six-dimensional spatial stress gradient vector pointing from the local pressure peak nodes to the six adjacent nodes.

[0035] In this implementation scheme, after obtaining a high-precision two-dimensional pressure distribution matrix, the system needs to further quantify the shear damage force on the skin tissue. In clinical pathology, the fundamental cause of pressure injury at bony prominences lies not only in the absolute vertical compression, but also in the intense stress gradient formed between the local high-pressure area and the surrounding low-pressure area. This gradient generates transverse shear force, directly tearing the subcutaneous microvascular network. Therefore, the system traverses the two-dimensional pressure distribution matrix, extracts the local pressure peak node by comparing neighborhood extrema, and precisely locates six adjacent nodes directly bordering the peak node on the physical edge, strictly based on the hexagonal topological features of the biomimetic cellular sensor. To realistically recreate the three-dimensional mechanical tearing state spreading outward from the pressure origin, the system extracts the stress difference features of the neighborhood pressure values ​​between the local pressure peak node and adjacent nodes, and combines them with the physical border distance parameter to construct a six-dimensional spatial stress gradient vector that can comprehensively characterize the extremely unbalanced spatial force state. The calculation logic of the components in each direction of this vector satisfies the following formula: Where p represents the index number of the local pressure peak node; k represents the adjacent node number of the hexagonal topological edge and its value ranges from one to six; This represents the central absolute pressure value at the local pressure peak node; This represents the neighborhood pressure value of the k-th neighboring node; This parameter represents the physical boundary distance between the local pressure peak node and its kth adjacent node. The weights of the spatial anisotropy distribution in the direction of the kth adjacent node are represented. This represents the shear force coupling compensation coefficient of skin tissue; This represents the cosine of the material deformation angle between the local pressure peak node and the kth adjacent node. This represents the stress gradient component pointing to the k-th neighboring node. The resulting set is the six-dimensional spatial stress gradient vector pointing from the local pressure peak node to its six neighboring nodes. Among the parameters mentioned above, the spatial anisotropy distribution weights... and skin tissue shear coupling compensation coefficient The establishment method is as follows: During the system initialization phase, a universal testing machine is used to conduct multiaxial tensile tests on the silicone matrix of the positioning pad. The stress-strain-yield curves of the matrix material at six different physical orientations of the hexagon are recorded. The results are obtained by extracting the extreme values ​​of deformation resistance in each direction and performing normalization calculations. Through this calculation process, the system not only identifies where the pressure is greatest, but also accurately calculates the mechanical gradient distribution of the tearing force from that high-pressure point to the surrounding tissue, effectively avoiding the warning failure caused by the failure of traditional equipment to detect shear force.

[0036] Specifically, the process of performing load accumulation mapping on abnormal stress concentration nodes in the time dimension and outputting the coordinates of the core high-risk bony protuberances and dynamic load accumulation features is as follows: extract the nodes where the magnitude of the vector in the six-dimensional spatial stress gradient vector exceeds the preset safety gradient and mark them as abnormal stress concentration nodes, and mark the spatial physical coordinates corresponding to the abnormal stress concentration nodes as the coordinates of the core high-risk bony protuberances; introduce time slice sequences to extract the pressure amplitude of the core high-risk bony protuberance coordinates in the continuous time slice sequence, perform discrete-time integral mapping on the pressure amplitude along the time slice sequence, and generate dynamic load accumulation features that characterize the continuous pressure state of the tissue.

[0037] In this implementation scheme, after constructing the six-dimensional spatial stress gradient vector, the system needs to assess the overall destructiveness of this gradient vector and introduce a time dimension to quantify the actual cumulative process of ischemic injury. The system first calculates the characteristic modulus of the six-dimensional spatial stress gradient vector in Euclidean space to characterize the magnitude of the comprehensive shear destructive force in the region. When this characteristic modulus exceeds the preset safety gradient, the system marks the node containing it as an abnormal stress concentration node and locks its absolute spatial physical coordinates as the coordinates of the core high-risk bony prominence. The preset safety gradient is established by collecting the critical closure pressure physiological constant of the dermal capillaries under standard clinical anesthesia, dividing it by the minimum elastic deformation thickness of the flexible contact layer of the positioning pad, and deriving the critical mechanical gradient value that induces irreversible tissue ischemia. After identifying high-risk coordinates, given that pressure injury is a biochemical decay process resulting from the combined effects of pressure and duration of pressure, the system introduces a time-slice sequence with a fixed frequency. It extracts the pressure amplitude of the core high-risk bony prominence coordinates within continuous time slices and performs discrete-time integral mapping along the time axis to generate dynamic load accumulation characteristics that characterize the continuous pressure state of the tissue. The specific accumulation mapping calculation logic satisfies the following formula: ; ;in, The characteristic magnitude of the six-dimensional spatial stress gradient vector is represented; T represents the total number of extraction cycles of the continuous time slice sequence; t represents the current time slice step index. This represents the pressure amplitude at the core high-risk bony prominence coordinates within the t-th time slice; This indicates a penalty factor for blocking blood microcirculation; Indicates the cumulative index of tissue ischemic fatigue; Indicates the physical duration of a single time slice; This represents the dynamic load accumulation characteristics of the final generated core high-risk bony prominence coordinates over time. In the above integral calculation, the exponential term vividly recreates the nonlinear collapse process of human soft tissue tolerance under continuous ischemia; that is, the longer the compression time, the greater the damage increment per unit time. Through this step, the system transforms static physical space compression data into dynamic fatigue integrals that conform to the pathological ischemic necrosis patterns, providing the most crucial and scientific data basis for subsequently triggering precise automated unloading and venting actions.

[0038] Specifically, the process of extracting the tissue tolerance baseline model associated with the coordinates of core high-risk bony prominences and collecting patient physiological parameters and surgical process time-series parameters as multimodal constraints is as follows: Anatomical partition nodes mapped by the coordinates of core high-risk bony prominences are extracted, and the inherent pressure benchmarks corresponding to these anatomical partition nodes under standard physiological conditions are retrieved to construct the tissue tolerance baseline model; core body temperature characteristic parameters and body mass index parameters are collected in real time to construct a set of physiological parameters, and the expected total intervention duration parameter and the current real-time running time scale are extracted to construct a set of surgical process time-series parameters; the physiological parameter set and the surgical process time-series parameter set are fused to generate multimodal constraints.

[0039] In this implementation plan, due to natural differences in subcutaneous fat thickness and muscle distribution, the maximum compressive force that bony prominences in different parts of the human body can withstand varies significantly. Therefore, the system first maps the acquired coordinates of core high-risk bony prominences onto a pre-set three-dimensional digital anatomical atlas to locate specific anatomical partition nodes. It then retrieves the capillary critical closure pressure of these nodes under standard healthy conditions from a medical norm database as an inherent pressure-bearing benchmark, using this as the basis for constructing a static tissue tolerance baseline model. However, the standard static model cannot reflect the dynamic physiological changes of the patient during surgery. For example, hypothermia can lead to peripheral microvascular constriction, thereby drastically reducing local tissue perfusion, while excessively low or high body mass index can alter the physical buffering and stress attenuation capabilities of soft tissues. Therefore, the system collects core deep body temperature characteristic parameters and body mass index parameters output from monitoring equipment in real time, constructing a set of physiological sign parameters that reflect the individual's microcirculatory physiological state. Simultaneously, the overall surgical schedule and current surgical progress directly determine the expected exposure of subcutaneous soft tissues to pressure. The system extracts the expected total intervention duration parameter and the current real-time running time scale to construct a set of surgical progress time sequence parameters. To integrate the aforementioned multidimensional heterogeneous data into the computational framework, the system performs data fusion to generate multimodal constraints. The specific physiological characteristic mapping and temporal fusion logic satisfies the following formula: ; ;in, This represents the dimensionless physiological state characteristic value after the transformation of the set of physiological sign parameters; The coefficient representing the mapping correlation between body morphology and tissue buffering capacity; A parameter representing the patient's true body mass index; A baseline body mass index parameter representing healthy individuals; This represents the mapping correlation coefficient between core body temperature and microcirculation perfusion; This represents the temperature sensitivity constant for vasoconstriction; This represents the core deep body temperature characteristic parameters collected in real time; This represents the standard human core body temperature constant; This represents the relative time exposure feature value after the transformation of the surgical process time sequence parameter set; This represents the time penalty coefficient for tissue fatigue under stress; This indicates the current real-time running time scale; This indicates the parameter representing the expected total intervention duration. The vasoconstriction temperature sensitivity constant is located here. The method for establishing this is as follows: the peripheral blood perfusion index change rate is calculated by collecting and regressing data from a large number of historical surgical patients under different deep anesthesia hypothermia conditions. Through this step, the system successfully transforms complex clinical multi-source heterogeneous parameters into structured dimensionless characteristic values, providing a very complete basis for setting constraint boundaries for subsequent targeted adjustments and dynamic pressure alarm boundaries.

[0040] Please see Figure 2 Specifically, the process of inputting the tissue tolerance baseline model for state evolution deduction and generating individualized bearing limit boundaries is as follows: Analyze the multimodal constraints, obtain the physiological metabolic lag weights generated by the conversion of the physiological sign parameter set and the temporal compression attenuation weights generated by the conversion of the surgical process temporal parameter set; use the physiological metabolic lag weights and temporal compression attenuation weights as dynamic fine-tuning factors to perform nonlinear weighted mapping processing on the inherent pressure benchmark inside the tissue tolerance baseline model, and output the individualized bearing limit boundary that characterizes the current critical state of tissue pressure.

[0041] In this implementation scheme, after obtaining the structured multimodal constraints, the system needs to dynamically reshape the static tissue tolerance baseline model to achieve precise early warning and defense line settings tailored to each individual. Since the decline in the tolerance of human skin and subcutaneous tissue under prolonged pressure and ischemia is not a simple linear process, but rather exhibits a nonlinear pathological pattern of slow accumulation in the early stages and a precipitous decline in the later stages, the system first analyzes the input multimodal constraints, calculating the physiological metabolic lag weight, which characterizes the individual patient's cellular metabolic level and microcirculation recovery capacity, and the temporal compression attenuation weight, which characterizes the increased tissue elastic fatigue caused by prolonged pressure. Subsequently, the system uses the physiological metabolic lag weight and the temporal compression attenuation weight as dynamic fine-tuning factors, and employs a nonlinear dimensionality reduction penalty algorithm to perform nonlinear weighted mapping processing on the inherent pressure benchmark pre-stored within the tissue tolerance baseline model, thereby outputting an individualized bearing limit boundary that accurately characterizes the current critical state of tissue pressure. The specific nonlinear evolutionary calculation logic satisfies the following formula: ; ; ;in, This represents the physiological metabolic lag weight derived from physiological state characteristic values; This represents the physiological state regulation gain constant; This represents the basal metabolic hysteresis bias constant; This represents the temporal compression attenuation weight generated from the transformation of relative time exposure feature values; This indicates the temporal compression attenuation rate of the cartilage and fascia layers. This represents the individualized bearing limit boundary generated by the deduction, which characterizes the current critical state of the organization under pressure. This represents the anatomically inherent pressure benchmark pre-stored within the tissue tolerance baseline model; This refers to the tissue damage tolerance safety margin factor introduced to defend against sudden blood supply shortages. The tissue damage tolerance safety margin factor here... The establishment method is as follows: Statistically calculate the confidence intervals for intraoperative hypotension in historically high-risk patients under the same surgical type, and mathematically calibrate the variance of peripheral systolic blood pressure fluctuations at the corresponding confidence levels. Through this series of evolutionary deductions, the system perfectly solves the problems of delayed warnings or false alarms caused by the rigid application of absolute pressure fixed red lines in traditional operating room pressure ulcer monitoring equipment. When patients are in high-risk conditions such as hypothermia or significantly prolonged surgery time, the system adaptively lowers their individual bearing limit boundary, thereby guiding the airbag inflation / deflation hardware mechanism to intervene in advance and perform protective physical intervention actions, greatly improving the reliability and effectiveness of clinical intelligent pressure ulcer prevention and control.

[0042] Specifically, when the dynamic load accumulation characteristics reach the individualized bearing limit boundary, the process of driving the micro-pump group to perform progressive pre-inflation of the adjacent peripheral zone controllable airbags based on the coordinate mapping of the core high-risk bony prominences to the central zone controllable airbags and the adjacent peripheral zone controllable airbags is as follows: When the dynamic load accumulation characteristics reach the individualized bearing limit boundary, the spatial matrix of the body positioning pad substrate corresponding to the coordinates of the core high-risk bony prominences is analyzed, and the physical address of the independent airbag directly below the spatial matrix is ​​marked as the central zone controllable airbag; the surrounding airbag group that is adjacent to the physical edge of the central zone controllable airbag is located and marked as the adjacent peripheral zone controllable airbag based on the hexagonal topological characteristics; the micro-pump group is controlled to input an inflation airflow in a stepped increasing mode to the adjacent peripheral zone controllable airbags to perform progressive pre-inflation.

[0043] In this implementation scheme, during prolonged surgery, directly deflating the local airbag that triggers an overpressure alarm would cause the patient's area to instantly lose physical support and collapse downwards. This macroscopic displacement would severely impair the surgeon's surgical field of vision and precision. Therefore, when the dynamic load accumulation characteristics reach the individualized load-bearing limit boundary, the system first analyzes the spatial matrix of the positioning pad matrix corresponding to the coordinates of the core high-risk bony prominences to accurately locate the central controllable airbag requiring depressurization. Subsequently, strictly following the hexagonal topological characteristics of the sensor array, the system addresses and locks onto six surrounding airbag groups that are completely adjacent to the physical edge of the central airbag, marking them as adjacent peripheral controllable airbags. To establish lateral flexible support without altering the patient's three-dimensional spatial absolute coordinates, the system sends a variable frequency drive command to the micro-pump assembly, controlling its output to inflate in a stepped-increasing pattern. The variable frequency drive voltage calculation logic for this progressive pre-inflation process satisfies the following formula: Where n represents the step inflation step number; This represents the frequency converter drive voltage of the air pump at the nth inflation step. This indicates the base sustaining voltage for starting the miniature air pump unit; This indicates the rated maximum output voltage of the miniature air pump unit; Indicates the duration span of a single inflation step; This represents the inflation response time constant of the gas pipeline network; This represents the body shape matching coefficient, indicating the patient's physiological contours. The body shape matching coefficient here... The method for establishing the pressure distribution is as follows: After the patient initially lies on the positioning pad and anesthesia induction is completed, the system extracts the total area covered by non-zero pressure nodes in the initial two-dimensional pressure distribution matrix, calculates the ratio of this area to the overall physical sensor array area of ​​the positioning pad, and performs nonlinear normalization. By introducing an exponential asymptotic term and a body shape matching coefficient, the system ensures that the inflation speed of the surrounding airbags exhibits a smooth transition characteristic of being fast at first and then slowing down. This not only quickly establishes a preliminary flexible barrier against collapse but also perfectly conforms to the physiological contours of different patients, effectively avoiding secondary compression damage to surrounding healthy tissues caused by excessive inflation.

[0044] Please see Figure 3Specifically, after the support stress inside the controllable airbags of the adjacent outer zones reaches the preset body position maintenance standard, the specific process of controlling the controllable airbags of the central zone to perform servo unloading and exhaust actions is as follows: real-time air pressure closed-loop feedback signals of the controllable airbags of the adjacent outer zones are collected, and the stress distribution vector characterizing the spatial support stiffness in the real-time air pressure closed-loop feedback signals is extracted; when the stress distribution vector matches the preset body position maintenance standard, the micro air pump group is controlled to maintain the inflation pressure of the controllable airbags of the adjacent outer zones, and the proportional servo exhaust valve associated with the controllable airbag of the central zone is activated; a pulse width modulation duty cycle control signal is sent to the proportional servo exhaust valve to release the gas inside the controllable airbag of the central zone to perform servo unloading and exhaust actions.

[0045] In this implementation scheme, after the adjacent peripheral controllable airbags have completed progressive pre-inflation, the system needs to determine whether the side support structure has sufficient stiffness to distribute the central gravity. The system extracts a stress distribution vector characterizing the spatial support stiffness by collecting real-time closed-loop air pressure feedback signals at the airway nodes inside the peripheral airbags. When the characteristic parameters of this stress distribution vector match the preset body position maintenance standard, it indicates that the bearing platform around the pressure origin has been stably established. At this point, the system immediately freezes the inflation action of the micro-pump group on the adjacent peripheral controllable airbags to maintain the existing support air pressure, and simultaneously activates the proportional servo exhaust valve associated with the hardware layer of the central controllable airbag. To achieve smooth dissipation of localized concentrated stress, the system sends a pulse width modulation duty cycle control signal to the exhaust valve to slowly release the resident gas inside the central airbag. The specific pulse width modulation duty cycle calculation logic satisfies the following formula: ;in, This indicates the effective width of the pulse width modulation duty cycle signal sent to the proportional servo exhaust valve. This indicates the real-time residence pressure feedback value inside the controllable airbag in the central zone; This indicates the target safe atmospheric pressure reference value required by clinical pathology to relieve microvascular ischemia. This represents the spatial support stiffness assessment value formed by the controllable airbags of adjacent peripheral zones; This represents the differential pressure drive proportional coefficient; This represents the stiffness compensation coupling coefficient; This represents the mechanical dead zone bias constant of the proportional servo exhaust valve. The aforementioned differential pressure drive proportional coefficient... Coupling coefficient with stiffness compensation The method for establishing this system is as follows: During the equipment's factory calibration phase, a multi-degree-of-freedom robotic arm applies multi-gradient simulated human body loads to the flexible positioning pad. The smoothness curves of the proportional servo exhaust valve under different load weights and exhaust gas rates are recorded. A multiple linear regression algorithm is used to fit and optimize the massive amount of curve data. Through this calculation logic, the system achieves adaptive dynamic adjustment of the servo unloading action. Specifically, when the current air pressure is severely excessive, the exhaust speed is appropriately increased to rescue ischemic tissues, while when the external support stiffness is weak, the exhaust rate is adaptively suppressed to provide additional buffering. This control mechanism completely overcomes the intraoperative displacement defects caused by the direct and forceful in-situ exhaust of traditional equipment. While ensuring the absolute stability of the surgeon's surgical field, it perfectly realizes the active intervention and closed-loop release of spatial stress during long-term surgeries.

[0046] Please see Figure 4 A smart surgical positioning monitoring system for preventing pressure injuries during prolonged surgery includes: a signal processing module, used to simultaneously acquire contact surface force signals and microenvironment temperature and humidity signals through a biomimetic honeycomb flexible pressure sensor array within the positioning pad substrate; to call a preset temperature and humidity self-compensation algorithm to parse the microenvironment temperature and humidity signals into environmental compensation parameters; to perform baseline drift calibration on the contact surface force signals based on the environmental compensation parameters; and to construct a two-dimensional pressure distribution matrix; and a stress analysis module, used to locate local pressure peak nodes in the two-dimensional pressure distribution matrix based on the hexagonal topological features of the biomimetic honeycomb flexible pressure sensor array; to analyze the spatial stress gradient vectors between the local pressure peak nodes and adjacent nodes; and to perform load accumulation mapping on abnormal stress concentration nodes in the time dimension. The system outputs the coordinates of the core high-risk bony prominences and the dynamic load accumulation characteristics. A state deduction module extracts the tissue tolerance baseline model associated with the core high-risk bony prominence coordinates, collects patient physiological parameters and surgical procedure time parameters as multimodal constraints, inputs the tissue tolerance baseline model for state evolution deduction, and generates individualized load-bearing limit boundaries. A servo control module, when the dynamic load accumulation characteristics reach the individualized load-bearing limit boundary, maps the central zone controllable airbag and adjacent peripheral zone controllable airbags based on the core high-risk bony prominence coordinates, drives a micro-pump group to perform progressive pre-inflation of the adjacent peripheral zone controllable airbags, and controls the central zone controllable airbag to perform servo unloading and degassing actions after the support stress within the adjacent peripheral zone controllable airbags reaches the preset position maintenance standard.

[0047] In this implementation scheme, the signal processing module serves as the underlying data sensing and purification hub of the entire system. Its main function is to overcome the physical interference of the complex microenvironment of the operating room on electronic components. By synchronously acquiring force and temperature / humidity signals and using environmental compensation parameters to perform baseline drift calibration, this module can effectively eliminate spurious pressure drift noise caused by disinfectant penetration or body temperature fluctuations. This allows the system to construct a high-fidelity two-dimensional pressure distribution matrix that accurately reflects the actual pressure on the patient's bony prominences, laying a solid and reliable data foundation for subsequent precise risk monitoring and mechanical analysis. The stress analysis module is the core computational hub for identifying and locating tissue damage risks. Its main function is to upgrade from simple spatial pressure measurement to a comprehensive spatiotemporal pathological analysis. Relying on the hexagonal topological features of the underlying sensor array, this module can not only lock the local pressure peak but also accurately resolve the spatial stress gradient vector tearing towards surrounding tissues. Combined with the surgical time axis, it performs load accumulation mapping, scientifically and rigorously quantifying the actual degree of damage to local tissues caused by continuous ischemia and mechanical shearing. Finally, it outputs highly targeted coordinates and dynamic load accumulation characteristics of core high-risk bony prominences. The state simulation module serves as the decision-making center for precise and personalized medical early warning. Its main function is to overcome the limitations of traditional medical monitoring equipment that rigidly applies single alarm values. This module integrates the patient's real-time physiological parameters with the temporal parameters of the surgical process into multimodal constraints. It dynamically fine-tunes and simulates the state evolution of the static tissue tolerance baseline model, comprehensively considering the weakening effects of body temperature fluctuations, individual differences in physical condition, and the duration of surgery on microcirculation tolerance. This generates an individualized load-bearing limit boundary that perfectly matches the real-time physiological critical state of the specific patient. The servo control module is the automated execution terminal for completing intraoperative closed-loop protection and physical intervention. Its main function is to achieve adaptive spatial load transfer while maintaining the absolute stability of the patient's macroscopic surgical position. When the system determines that the load is approaching the limit boundary, the module accurately maps the bottom airbag according to the high-risk coordinates, and adopts a step-by-step control strategy of first driving the outer airbags to gradually pre-inflate to establish a flexible support wall on the side. After the support stiffness reaches the standard, the module controls the central high-risk airbag to execute servo unloading and degassing. This strategy not only completely resolves the local concentrated stress, but also effectively avoids the risk of patient collapse and displacement that is easily caused by traditional in-situ direct degassing.

[0048] In summary, this application has at least the following effects:

[0049] An intelligent surgical positioning monitoring method and system for preventing pressure injuries during prolonged surgery effectively eliminates interference from the complex surgical microenvironment on physical signals through an underlying biomimetic honeycomb flexible pressure sensor array and a temperature and humidity self-compensation mechanism, thereby acquiring high-fidelity pressure distribution data. It creatively integrates spatial stress gradient analysis and temporal load accumulation mapping to accurately pinpoint high-risk pressure origins. Simultaneously, the system combines the patient's multimodal physiological characteristics and surgical sequence features to deduce individualized load-bearing limit boundaries, breaking the limitations of traditional single fixed thresholds to achieve precise dynamic early warning. Based on this, the system employs a stepped closed-loop control strategy: progressive pre-inflation of adjacent airbags to establish flexible support, and servo-assisted unloading and degassing of the central high-risk airbag. This strategy completely resolves localized concentrated stress and actively intervenes in tissue ischemia crises while perfectly maintaining the macroscopic absolute stability of the patient's overall surgical position, avoiding body displacement and surgical field of view disruption caused by direct local deflation. Ultimately, it forms a complete active protection closed loop integrating high-interference-resistant monitoring, personalized intelligent early warning, and non-destructive smooth decompression.

[0050] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0051] This invention is described with reference to flowchart illustrations and / or block diagrams of systems, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0052] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0053] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0054] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0055] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A smart surgical position monitoring method for preventing pressure injury during prolonged surgery, characterized in that, Includes the following steps: S1. The contact surface force signal and micro-environment temperature and humidity signal are synchronously acquired by the biomimetic honeycomb flexible pressure sensor array in the body positioning pad matrix. The preset temperature and humidity self-compensation algorithm is called to parse the micro-environment temperature and humidity signal into environmental compensation parameters. The baseline drift calibration of the contact surface force signal is performed in combination with the environmental compensation parameters to construct a two-dimensional pressure distribution matrix. S2. Based on the hexagonal topological features of the biomimetic cellular flexible pressure sensor array, local pressure peak nodes are locked in the two-dimensional pressure distribution matrix, the spatial stress gradient vectors of local pressure peak nodes and adjacent nodes are analyzed, load accumulation mapping is performed on abnormal stress concentration nodes in the time dimension, and the coordinates of core high-risk bony protuberances and dynamic load accumulation features are output. S3. Extract the tissue tolerance baseline model associated with the coordinates of the core high-risk bony prominences, collect the patient's physiological signs parameters and the time sequence parameters of the surgical process as multimodal constraints, input them into the tissue tolerance baseline model to perform state evolution deduction, and generate individualized bearing limit boundaries; S4. When the dynamic load accumulation characteristics reach the individualized bearing limit boundary, the controllable airbags in the central zone and the adjacent peripheral zone are mapped according to the coordinates of the core high-risk bony prominences. The micro air pump group is driven to perform progressive pre-inflation of the controllable airbags in the adjacent peripheral zone. After the support stress in the controllable airbags in the adjacent peripheral zone reaches the preset body position maintenance standard, the controllable airbags in the central zone are controlled to perform servo unloading and exhaust actions.

2. The intelligent surgical position monitoring method for preventing pressure injury during prolonged surgery according to claim 1, characterized in that: The specific process of simultaneously acquiring the contact surface force signal and the microenvironment temperature and humidity signal through the biomimetic honeycomb flexible pressure sensor array within the body positioning pad substrate, and then calling the preset temperature and humidity self-compensation algorithm to parse the microenvironment temperature and humidity signal into environmental compensation parameters is as follows: The composite detection signals collected by the biomimetic honeycomb flexible pressure sensor array are separated to obtain the force signal on the contact surface and the temperature and humidity signal of the microenvironment; The temperature and humidity signals of the microenvironment are decomposed to extract the temperature fluctuation feature vector and the humidity wetting feature vector. The temperature fluctuation feature vector and the humidity wetting feature vector are then input into a pre-set substrate drift feature library for matching to obtain the thermal impedance compensation coefficient and the humidity-sensitive capacitance compensation coefficient. The environmental compensation parameter is generated by combining the thermal impedance compensation coefficient and the humidity-sensitive capacitance compensation coefficient.

3. The intelligent surgical position monitoring method for preventing pressure injury during prolonged surgery according to claim 1, characterized in that: the specific process of constructing a two-dimensional pressure distribution matrix by performing baseline drift calibration on the contact surface force signal in conjunction with environmental compensation parameters is as follows: The contact surface force signal is converted into an initial pressure amplitude sequence. The initial pressure amplitude sequence is then reverse-weighted and corrected using environmental compensation parameters to filter out thermal and moisture drift noise and generate the true contact surface pressure amplitude. The spatial physical coordinates of each sensing unit in the biomimetic honeycomb flexible pressure sensor array are extracted, and the pressure amplitude of the actual contact surface is mapped to the corresponding spatial physical coordinates to construct a two-dimensional pressure distribution matrix.

4. The intelligent surgical positioning monitoring method for preventing pressure injury during prolonged surgery according to claim 1, characterized in that: based on the hexagonal topological features of the biomimetic honeycomb flexible pressure sensor array, the local pressure peak node is locked in the two-dimensional pressure distribution matrix, and the specific process of analyzing the spatial stress gradient vector between the local pressure peak node and its adjacent nodes is as follows: Traverse the node pressure values ​​in the two-dimensional pressure distribution matrix, extract the nodes with extreme values ​​as local pressure peak nodes, and locate the six adjacent nodes that are physically adjacent to the local pressure peak nodes based on the hexagonal topological features. The stress difference features between the neighborhood pressure values ​​of six adjacent nodes and the local pressure peak node and the neighborhood pressure values ​​are extracted. Combined with the physical boundary distance parameter, a six-dimensional spatial stress gradient vector is constructed from the local pressure peak node to the six adjacent nodes.

5. The intelligent surgical positioning monitoring method for preventing pressure injury during prolonged surgery according to claim 1, characterized in that: the specific process of performing load accumulation mapping on abnormal stress concentration nodes in the time dimension and outputting the coordinates of core high-risk bony prominences and dynamic load accumulation features is as follows: The nodes where the magnitude of the vector in the six-dimensional spatial stress gradient vector exceeds the preset safety gradient are marked as abnormal stress concentration nodes, and the spatial physical coordinates corresponding to the abnormal stress concentration nodes are marked as the coordinates of the core high-risk bony protuberances. By introducing time slice sequences, the pressure amplitude of the core high-risk bony prominence coordinates within a continuous time slice sequence is extracted. Discrete-time integral mapping is then performed on the pressure amplitude along the time slice sequence to generate dynamic load accumulation features characterizing the continuous pressure state of the tissue.

6. The intelligent surgical positioning monitoring method for preventing pressure injury during prolonged surgery according to claim 1, characterized in that: the specific process of extracting the tissue tolerance baseline model associated with the coordinates of core high-risk bony prominences and collecting the patient's physiological signs parameters and the temporal parameters of the surgical process as multimodal constraints is as follows: Extract the anatomical partition nodes of the coordinate mapping of the core high-risk bony prominences, and retrieve the inherent pressure benchmarks corresponding to the anatomical partition nodes under standard physiological conditions to construct a tissue tolerance baseline model. Real-time acquisition of core body temperature characteristic parameters and body mass index parameters to construct a set of physiological sign parameters, and extraction of the expected total intervention duration parameter and the current real-time running time scale to construct a set of surgical process time sequence parameters; Multimodal constraints are generated by integrating the set of physiological signs parameters with the set of surgical procedure time parameters.

7. The intelligent surgical position monitoring method for preventing pressure injury during prolonged surgery according to claim 1, characterized in that: the specific process of inputting a tissue tolerance baseline model for state evolution deduction to generate an individualized bearing limit boundary is as follows: The multimodal constraints were analyzed to obtain the physiological metabolic lag weights generated by the conversion of the physiological sign parameter set and the temporal compression attenuation weights generated by the conversion of the surgical process temporal parameter set. Using physiological metabolic lag weights and temporal compression attenuation weights as dynamic fine-tuning factors, a nonlinear weighted mapping process is performed on the inherent pressure benchmark within the tissue tolerance baseline model to output an individualized bearing limit boundary that characterizes the current critical state of tissue pressure.

8. The intelligent surgical position monitoring method for preventing pressure injury during prolonged surgery according to claim 1, characterized in that: when the dynamic load accumulation characteristics reach the individualized bearing limit boundary, the specific process of driving the micro-pump group to perform progressive pre-inflation of the controllable airbags in the adjacent peripheral zones based on the coordinate mapping of the core high-risk bony prominences and the controllable airbags in the central zone is as follows: When the dynamic load accumulation characteristics reach the individualized bearing limit boundary, the spatial matrix of the body pad matrix corresponding to the coordinates of the core high-risk bony protuberance is analyzed, and the physical address of the independent airbag directly below the spatial matrix is ​​marked as the central zone controllable airbag. Based on the hexagonal topological features, the surrounding airbag group that is physically adjacent to the central partition controllable airbag is marked as the adjacent outer partition controllable airbag. The micro air pump unit is controlled to supply a stepped-increasing airflow to the controllable airbags in the adjacent peripheral zones to perform progressive pre-inflation.

9. The intelligent surgical position monitoring method for preventing pressure injury during prolonged surgery according to claim 1, characterized in that: after the support stress inside the controllable airbags of the adjacent peripheral zones reaches the preset position maintenance standard, the specific process of the controllable airbags of the control center zone performing servo unloading and degassing actions is as follows: Real-time air pressure closed-loop feedback signals of controllable airbags in adjacent peripheral zones are collected, and stress distribution vectors characterizing spatial support stiffness are extracted from the real-time air pressure closed-loop feedback signals. When the stress distribution vector matches the preset body position maintenance standard, the micro air pump group is controlled to maintain the inflation pressure of the controllable airbags in the adjacent peripheral zones, and the proportional servo exhaust valve associated with the controllable airbag in the central zone is activated. A pulse width modulation duty cycle control signal is sent to the proportional servo exhaust valve to release the gas inside the controllable airbag in the center zone and perform a servo unloading and exhaust action.

10. An intelligent surgical positioning monitoring system for preventing pressure injury during prolonged surgery, used to execute the intelligent surgical positioning monitoring method for preventing pressure injury during prolonged surgery as described in any one of claims 1-9, characterized in that, include: The signal processing module is used to simultaneously acquire the contact surface force signal and the micro-environment temperature and humidity signal through the biomimetic honeycomb flexible pressure sensor array in the body positioning pad matrix. It calls the preset temperature and humidity self-compensation algorithm to parse the micro-environment temperature and humidity signal into environmental compensation parameters. Combined with the environmental compensation parameters, it performs baseline drift calibration on the contact surface force signal and constructs a two-dimensional pressure distribution matrix. The stress analysis module is used to locate local pressure peak nodes in a two-dimensional pressure distribution matrix based on the hexagonal topological features of a biomimetic cellular flexible pressure sensor array, analyze the spatial stress gradient vector between the local pressure peak nodes and adjacent nodes, perform load accumulation mapping on abnormal stress concentration nodes in the time dimension, and output the coordinates of core high-risk bony prominences and dynamic load accumulation features. The state deduction module is used to extract the tissue tolerance baseline model associated with the coordinates of the core high-risk bony prominences, collect the patient's physiological signs parameters and surgical process time parameters as multimodal constraints, input the tissue tolerance baseline model to perform state evolution deduction, and generate individualized bearing limit boundaries. The servo control module is used to drive the micro air pump group to perform progressive pre-inflation of the controllable airbags in the adjacent peripheral zones based on the coordinate mapping of the central high-risk bony prominences and the controllable airbags in the adjacent peripheral zones when the dynamic load accumulation characteristics reach the individualized bearing limit boundary. After the support stress in the controllable airbags in the adjacent peripheral zones reaches the preset body position maintenance standard, the module controls the controllable airbags in the central zone to perform servo unloading and degassing actions.

Images