Skin failure monitoring and early warning management system for critically ill patients

Abstract

The present invention relates to the field of early warning management technology, and specifically, to a monitoring and early warning management system for skin failure in critically ill patients. It includes: a skin data processing unit for obtaining a three-dimensional anatomical structure image of a patient's skin through computer tomography and magnetic resonance imaging, and generating a three-dimensional digital model of the patient's skin tissue; a biomechanical modeling unit for establishing a constitutive model of the skin tissue based on the data provided by the three-dimensional digital model of the patient's skin tissue and in combination with the patient's tissue characteristic data collected in advance based on clinical experiments; a risk assessment and early warning unit for assessing the patient's skin failure risk. The system can improve the system's assessment accuracy of skin failure risk, more effectively identify those areas that are vulnerable to damage, and take preventive measures in a timely manner to avoid nursing errors or delays caused by ignoring individual differences in patients, thereby improving treatment effects and patient safety.

Description

Technical Field

[0001] The present invention relates to the technical field of early warning management, and in particular to a skin failure monitoring and early warning management system for critically ill patients. Background Art

[0002] Critically ill patients in the intensive care unit (ICU) are prone to acute skin failure (ASF) due to complex conditions, unstable hemodynamics, and multiple complications. Acute skin failure refers to the process in which the skin, as the largest organ in the human body, undergoes necrosis of the skin and / or subcutaneous tissue due to low perfusion. Its pathological changes are mainly manifested as low perfusion of skin blood flow, which is often secondary to myocardial infarction, stroke, sepsis, trauma, and postoperative complications.

[0003] In the ICU, when patients are in critical condition, blood will be supplied to vital organs first, resulting in hypoperfusion of skin tissue. In addition, ICU patients are often accompanied by factors such as impaired nutritional status, mechanical ventilation, hemodynamic instability, organ failure, peripheral vascular disease, use of vasoactive drugs, and medical intervention (such as immobilization, surgery), which will increase the risk of acute skin failure.

[0004] However, acute skin failure is not given enough attention in clinical work. Medical staff have limited knowledge of it and are prone to confuse it with pressure injury, leading to missed diagnosis and misdiagnosis. In addition, existing monitoring equipment is inconvenient in adjusting the monitoring position and is difficult to meet clinical needs. Therefore, it is of great clinical significance to develop a management system that can effectively monitor and warn the risk of skin failure in critically ill patients. Summary of the invention

[0005] The purpose of the present invention is to provide a skin failure monitoring, early warning and management system for critically ill patients, so as to solve the problem that the traditional biomechanical model proposed in the above background technology cannot effectively simulate the cumulative damage to skin tissue caused by long-term stress and deformation history, ignores the individual differences of patients' skin, and leads to inaccurate skin failure risk assessment for some patients.

[0006] To achieve the above object, the present invention provides a monitoring and early warning management system for skin failure in critically ill patients, comprising:

[0007] A skin data processing unit, the skin data processing unit is used to obtain a three-dimensional anatomical structure image of the patient's skin through computer tomography and magnetic resonance imaging, and pre-process the acquired three-dimensional anatomical structure image, and segment and reconstruct the pre-processed three-dimensional anatomical structure image using a deep learning image segmentation method, and finally generate a three-dimensional digital model of the patient's skin tissue; the skin tissue includes a skin surface layer, a subcutaneous fat layer, and muscle tissue;

[0008] Among them, the skin data processing unit includes an acquisition processing module, a tissue recognition module and a three-dimensional reconstruction module;

[0009] A biomechanical modeling unit, the biomechanical modeling unit is used to establish a constitutive model of the skin tissue according to data provided by a three-dimensional digital model of the patient's skin tissue and in combination with the patient's tissue characteristic data collected in advance according to clinical experiments; the constitutive model of the skin tissue includes a hyperelastic model of the skin surface layer, a viscoelastic model of the subcutaneous fat layer, and an active contraction model of the muscle tissue, and the environmental force is introduced into the hyperelastic model of the skin surface layer for optimization, the influence factor of fat density is introduced into the process of establishing the viscoelastic model of the subcutaneous fat layer for optimization, and the influence of fatigue degree is introduced into the process of establishing the active contraction model of the muscle tissue for optimization;

[0010] Among them, the biomechanical modeling unit includes a surface modeling module, a fat layer modeling module and a muscle modeling module;

[0011] A risk assessment and early warning unit is used to jointly assess the patient's skin failure risk based on the strain energy density of the skin surface under external force obtained by the hyperelastic model of the skin surface, the latency of skin tissue damage obtained by the viscoelastic model of the subcutaneous fat layer, and the ischemic threshold obtained by the active contraction model of the muscle tissue.

[0012] As a further improvement of the technical solution, in the skin data processing unit:

[0013] The acquisition and processing module is used to obtain a three-dimensional anatomical structure image of the patient's skin through a computer tomography and magnetic resonance imaging device, and to pre-process the three-dimensional anatomical image;

[0014] The tissue recognition module is used to segment the 3D anatomical structure image into multiple slices using an image segmentation algorithm, and then extract different tissues from the multiple slices according to the density of the tissues, and use a deep learning image segmentation method to identify and classify different tissues;

[0015] The 3D reconstruction module is used to generate a volume model of each tissue of the patient based on the classified tissues, and to convert each tissue into a 3D digital model by extracting and reconstructing the tissue surface;

[0016] The three-dimensional digital model provides the biomechanical modeling unit with tissue morphology data, volume data, the position of each point on the tissue surface, and the connection relationship between tissues.

[0017] As a further improvement of the present technical solution, the tissue characteristic data includes tissue elastic modulus and physical properties, tissue thickness and density distribution, inter-tissue contact and interaction, force boundary conditions and external load data.

[0018] As a further improvement of the technical solution, in the biomechanical modeling unit:

[0019] The surface modeling module is used to establish a hyperelastic model of the skin surface, simulate the strain energy density of the skin surface under the action of external forces, and introduce environmental forces into the hyperelastic model of the skin surface for optimization;

[0020] The fat layer modeling module is used to establish a viscoelastic model of the subcutaneous fat layer, simulate the mechanical response of the subcutaneous fat layer under external force, introduce the influencing factor of fat density to optimize the process of establishing the viscoelastic model of the subcutaneous fat layer, and predict the latent period of skin tissue damage by combining the energy dissipation rate of the subcutaneous fat layer with the results of the viscoelastic model;

[0021] The muscle modeling module is used to establish an active contraction model of muscle tissue, and use the results of the active contraction model to obtain the ischemic threshold. In the process of establishing the active contraction model of muscle tissue, the influence of fatigue degree is introduced for optimization.

[0022] As a further improvement of the technical solution, the specific steps of the surface modeling module to establish the hyperelastic model of the skin surface are as follows:

[0023] ;

[0024] in, is the strain energy density of the skin surface under the action of external force; is the total strain energy; is the nonlinear index; is the elastic modulus constant of the skin material; is the elongation factor of the skin surface along the first principal axis during deformation; is the elongation factor of the skin surface along the second principal axis during deformation; is the elongation factor of the skin surface along the third principal axis during deformation; The degree of skin damage of the patient; is the change factor of the patient's skin volume; ;

[0025] When the patient's skin surface comes into contact with external objects, shear force occurs. When the skin is subjected to the shear force generated by contact with external objects for a long time, skin failure is accelerated. Therefore, environmental forces are introduced into the hyperelastic model of the skin surface for optimization. After optimization, the specific results are as follows:

[0026] ;

[0027] in, is the strain energy density of the optimized skin surface under the action of external force; It is the number of contact surfaces between the patient's skin surface and external objects; ; is the coefficient of friction between the skin and the contact surface; is the normal force on the contact surface; The skin surface and external objects Shear force applied during contact; is the shear modulus of the skin.

[0028] As a further improvement of the technical solution, the specific steps of the fat layer modeling module to establish the viscoelastic model of the subcutaneous fat layer are as follows:

[0029] ;

[0030] in, is the stress of the subcutaneous fat layer; is the elastic modulus of the subcutaneous fat layer; is the strain of the subcutaneous fat layer; is the viscosity coefficient of the subcutaneous fat layer;

[0031] Different patients have different skin thickness and fat. Patients with different thicknesses of fat layers have different stress resistance, which in turn affects the stress distribution of the subcutaneous fat layer of different patients. Therefore, in the process of establishing the viscoelastic model of the subcutaneous fat layer, the influencing factor of fat density is introduced for optimization. After optimization, the specific results are:

[0032] ;

[0033] in, is the elastic modulus of the subcutaneous fat layer after the fat density is introduced; is the elastic modulus of the standard fat layer; is the density of the current fat layer; is the density of the standard fat layer; is the thickness of the skin; is the standard skin thickness; is the influence factor of thickness change on elastic modulus; is the sensitivity index of elastic modulus to changes in fat density;

[0034] ;

[0035] in, is the viscosity coefficient of the subcutaneous fat layer after the fat density is introduced; is the viscosity coefficient of the standard fat layer; is a constant that controls the effect of fat density on the viscosity coefficient;

[0036] ;

[0037] in, is the stress of the subcutaneous fat layer after the fat density is introduced.

[0038] As a further improvement of the technical solution, the fat layer modeling module predicts the latent period of tissue damage by the energy dissipation rate of the subcutaneous fat layer, and the specific steps are as follows:

[0039] ;

[0040] in, is the energy dissipation rate; is the strain rate of the subcutaneous fat layer;

[0041] ;

[0042] in, is the growth rate of the injury; is the damage time scale constant; is the stress threshold at which damage begins to occur; is the index of damage evolution; is the standard energy value; is the sensitivity factor of damage evolution to energy dissipation rate;

[0043] Integrate the growth rate of the damage to obtain the cumulative damage of the skin under long-term stress and the latency of injury :

[0044] ;

[0045] in, For the skin in time Cumulative damage over time; is the damage growth rate; for a specific moment;

[0046] Once the accumulated damage reaches a certain critical value , then it is determined that the skin tissue is damaged:

[0047] ;

[0048] in, It is the incubation period of skin tissue damage; is the critical damage value.

[0049] As a further improvement of the technical solution, the specific steps of modeling the muscle modeling module are as follows:

[0050] ;

[0051] in, The contraction force of the muscle; is the maximum contraction force of the muscle; is the contraction speed of the muscle; is the maximum contraction speed of the muscle; is the passive elastic force of the muscle;

[0052] When critically ill patients are bedridden for a long time, their muscles are in a state of low activity and excessive tension for a long time. The active contraction model cannot simulate the muscle mechanical attenuation caused by long-term stress. Therefore, the influence of fatigue degree is introduced in the process of establishing the active contraction model of muscle tissue for optimization. The optimization is as follows:

[0053] ;

[0054] in, For optimized muscle contraction force; is the decay rate of the fatigue factor; Fatigue time.

[0055] As a further improvement of the technical solution, the muscle modeling module uses the model output result to correct the ischemic threshold, and the specific steps are as follows:

[0056] ;

[0057] in, is the ischemic threshold; is the basic ischemic threshold; Correction factor for blood flow supply; is the correction factor for lactate concentration; is the basal lactate concentration; is the lactate concentration; is the correction factor for the strength of muscle contraction; An index that controls the effect of blood flow supply on ischemic threshold; It is an index to control the effect of lactate concentration on ischemic threshold; It is an index that controls the effect of muscle contractility on ischemic threshold.

[0058] As a further improvement of the technical solution, the risk assessment and early warning unit assesses the patient's skin failure risk in the following specific steps:

[0059] Assess your patient's risk of skin failure:

[0060] ;

[0061] in, is the skin failure risk value; is a function related to the incubation period; is a correction function related to the ischemic threshold;

[0062] Based on the results of the risk value, set different levels of risk thresholds and early warning methods for different risk levels;

[0063] Different levels of risk thresholds include the first risk threshold and the second risk threshold risk ;

[0064] if , a low risk warning signal is generated; if and A medium risk warning signal is generated; if , a high-risk warning signal is generated.

[0065] Compared with the prior art, the present invention has the following beneficial effects:

[0066] In the skin failure monitoring and early warning management system for critically ill patients, the shear force between the skin surface and external objects, the impact of fatigue time on muscles, and the impact of fat density on the elastic modulus and viscosity coefficient of the subcutaneous fat layer are taken into account in the process of modeling each tissue, so as to achieve model optimization. This can improve the system's assessment accuracy of skin failure risks, more effectively identify those areas that are vulnerable to damage, and take preventive measures in a timely manner to avoid nursing errors or delays caused by ignoring individual differences among patients, thereby improving treatment outcomes and patient safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is the overall flow chart of the present invention;

[0068] The meaning of each number in the figure is:

[0069] 1. Skin data processing unit; 11. Acquisition and processing module; 12. Tissue identification module; 13. Three-dimensional reconstruction module; 2. Biomechanical modeling unit; 21. Surface modeling module; 22. Fat layer modeling module; 23. Muscle modeling module; 3. Risk assessment and early warning unit. DETAILED DESCRIPTION

[0070] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0071] See also Figure 1As shown, a skin failure monitoring and early warning management system for critically ill patients is provided, including a skin data processing unit 1, a biomechanical modeling unit 2 and a risk assessment and early warning unit 3;

[0072] The skin data processing unit 1 is used to obtain a three-dimensional anatomical structure image of the patient's skin through computer tomography and magnetic resonance imaging, and pre-process the acquired three-dimensional anatomical structure image, and use a deep learning image segmentation method to segment and reconstruct the pre-processed three-dimensional anatomical structure image, and finally generate a three-dimensional digital model of the patient's skin tissue; the skin tissue includes the skin surface, subcutaneous fat layer and muscle tissue; computer tomography provides high-precision soft and hard tissue contrast, and can clearly display the structure of bones and skin; magnetic resonance imaging provides higher soft tissue resolution, especially for the fat and muscle layers under the skin.

[0073] The skin data processing unit 1 includes a collection and processing module 11, a tissue identification module 12 and a three-dimensional reconstruction module 13;

[0074] The acquisition and processing module 11 is used to obtain a three-dimensional anatomical structure image of the patient's skin through a computer tomography and magnetic resonance imaging device, and pre-process the three-dimensional anatomical image; including using a Gaussian filtering method to reduce noise in the image, and then using non-local mean denoising to reduce detail noise in the image;

[0075] The tissue recognition module 12 is used to segment the three-dimensional anatomical structure image into multiple slices using a 3D convolutional neural network. The 3D convolutional neural network uses a three-dimensional convolution kernel to perform feature extraction in the spatial domain, which can better capture the structural features in the three-dimensional space, and then extract different tissues from the multiple slices according to the density of the tissue, and use a deep learning image segmentation method to identify and classify different tissues;

[0076] The three-dimensional reconstruction module 13 is used to generate a volume model of each tissue of the patient according to the classified tissues, and convert each tissue into a three-dimensional digital model by extracting and reconstructing the tissue surface. The three-dimensional digital model provides the biomechanical modeling unit 2 with tissue morphology data, volume data, normal vectors and curvatures of each point on the tissue surface, and connection relationships between tissues;

[0077] The biomechanical modeling unit 2 is used to establish a constitutive model of the skin tissue according to the data provided by the three-dimensional digital model of the patient's skin tissue and in combination with the patient's tissue characteristic data collected in advance according to clinical experiments; the constitutive model of the skin tissue includes a hyperelastic model of the skin surface layer, a viscoelastic model of the subcutaneous fat layer, and an active contraction model of the muscle tissue, and introduces environmental forces to optimize the hyperelastic model of the skin surface layer, introduces the influence factor of fat density to optimize the process of establishing the viscoelastic model of the subcutaneous fat layer, and introduces the influence of fatigue degree to optimize the process of establishing the active contraction model of the muscle tissue;

[0078] The biomechanical modeling unit 2 includes a surface modeling module 21, a fat layer modeling module 22 and a muscle modeling module 23;

[0079] Tissue property data include tissue elastic modulus and physical properties, tissue thickness and density distribution, intertissue contacts and interactions, force boundary conditions and external loading data;

[0080] Biomechanical Modelling Unit 2:

[0081] The surface modeling module 21 is used to establish a hyperelastic model of the skin surface, simulate the strain energy density of the skin surface under the action of external force, and introduce environmental forces into the establishment of the hyperelastic model of the skin surface for optimization;

[0082] The specific steps of the surface modeling module 21 to establish the hyperelastic model of the skin surface are as follows:

[0083] ;

[0084] in, It is the strain energy density of the skin surface under the action of external force, which is the energy stored in the skin tissue during deformation; is the total strain energy; is a nonlinear index that controls the stress-strain relationship of the material when it is deformed greatly. Since the deformation of the skin may show strong nonlinear characteristics, It is used to adjust the response of different deformation modes (stretching, compression, etc.) In critically ill patients, the elastic properties of the skin may change due to failure or tissue damage, affecting the value of the nonlinear index; is the elastic modulus constant of the skin material, which indicates the stiffness of the materials in each layer of the skin surface. In the scenario of the skin of critically ill patients, this value may be related to factors such as skin aging, health status, and degree of failure; is the elongation factor of the skin surface along the first principal axis during deformation; is the elongation factor of the skin surface along the second principal axis during deformation; is the elongation factor of the skin surface along the third principal axis during deformation; these elongation factors describe the degree of elongation or compression of the skin in each principal axis direction; The degree of skin damage of the patient. As the external force on the skin increases, The gradual increase indicates that the mechanical properties of the skin are gradually deteriorating. For critically ill patients, skin damage may be related to factors such as pressure ulcers and skin failure. The increase in means that the stiffness of the skin decreases and the strength of the material decreases; The factor for the change in the patient's skin volume is that the degree of volume change may be greater in failed skin, especially when the skin is edematous or has a morphological change due to pressure; ;

[0085] When the patient's skin surface comes into contact with external objects, shear force occurs. When the skin is subjected to the shear force generated by contact with external objects for a long time, skin failure is accelerated. Therefore, environmental forces are introduced into the hyperelastic model of the skin surface for optimization. After optimization, the specific results are as follows:

[0086] ;

[0087] in, is the strain energy density of the optimized skin surface under the action of external force; It is the number of contact surfaces between the patient's skin surface and external objects; ; The friction coefficient between the skin and the contact surface, which usually depends on factors such as the wetness of the skin and the roughness of the contact surface. It can be obtained through experiments or clinical data; is the normal force of the contact surface, that is, the vertical force between the skin and the external object. It is determined by the local pressure on the surface of the skin, the patient's position, and the pressure distribution of the external object; The surface of the skin and external objects Shear force during contact, which is often generated by friction and causes the skin to deform at the contact site, increasing the skin's stress response; is the shear modulus of the skin, which is the resistance of the skin material to shear deformation. This value will be different in different skin conditions (such as healthy skin, damaged skin, moist or dry skin);

[0088] The optimized model takes into account the friction and shear force between the skin surface and external objects, making the model more accurately reflect the stress and strain that the skin may face in the actual clinical environment. According to the shear force generated by different contact surfaces, each contact surface can be calculated and accumulated separately to simulate the long-term effects of friction and shear force on the skin.

[0089] The fat layer modeling module 22 is used to establish a viscoelastic model of the subcutaneous fat layer, simulate the mechanical response of the subcutaneous fat layer under the action of external force, introduce the influencing factor of fat density to optimize the process of establishing the viscoelastic model of the subcutaneous fat layer, and predict the latent period of skin tissue damage by combining the energy dissipation rate of the subcutaneous fat layer with the results of the viscoelastic model;

[0090] The specific steps of the fat layer modeling module 22 to establish the viscoelastic model of the subcutaneous fat layer are as follows:

[0091] ;

[0092] in, is the stress of the subcutaneous fat layer; is the elastic modulus of the subcutaneous fat layer; is the strain of the subcutaneous fat layer; is the viscosity coefficient of the subcutaneous fat layer;

[0093] Different patients have different skin thickness and fat. Patients with different thicknesses of fat layers have different stress resistance, which in turn affects the stress distribution of the subcutaneous fat layer of different patients. Therefore, in the process of establishing the viscoelastic model of the subcutaneous fat layer, the influencing factor of fat density is introduced for optimization. After optimization, the specific results are:

[0094] ;

[0095] in, is the elastic modulus of the subcutaneous fat layer after the fat density is introduced; is the elastic modulus of the standard fat layer; is the density of the current fat layer; It is the density of the standard fat layer, usually based on the value measured in a healthy and non-debilitated state; is the thickness of the skin; is the standard skin thickness, usually the skin thickness in a healthy state; is the influence factor of thickness change on elastic modulus; It is the sensitivity index of elastic modulus to fat density changes, indicating the degree of influence of fat density changes on elastic modulus, usually obtained by fitting experimental data;

[0096] ;

[0097] in, is the viscosity coefficient of the subcutaneous fat layer after the fat density is introduced; is the viscosity coefficient of the standard fat layer, usually based on the value measured in a healthy, non-depleted state; It is a constant that controls the effect of fat density on the viscosity coefficient. It indicates the response degree of fat density change to the viscosity coefficient and is usually obtained by fitting experimental data.

[0098] ;

[0099] in, is the stress of the subcutaneous fat layer after the fat density is introduced;

[0100] The above-mentioned optimization of the effect of fat density on the elastic modulus and viscosity coefficient of the subcutaneous fat layer can more accurately reflect the true physical properties of the patient's skin layer, especially when there are differences in skin thickness and fat layer density. This optimization method enables the model to provide personalized stress and damage predictions based on the physiological differences of different individuals, thereby improving the system's assessment accuracy of skin failure risk. By accurately calculating the stress distribution of the subcutaneous fat layer, it is possible to more effectively identify those areas that are vulnerable to damage, and take preventive measures in a timely manner to avoid nursing errors or delays caused by ignoring individual differences in patients, thereby improving treatment outcomes and patient safety.

[0101] The fat layer modeling module 22 predicts the latent period of tissue damage by the energy dissipation rate of the subcutaneous fat layer. The specific steps are as follows:

[0102] ;

[0103] in, is the energy dissipation rate, which indicates the energy converted into heat energy per unit time; is the strain rate of the subcutaneous fat layer, which describes the deformation rate of the skin under force;

[0104] Damage evolution can be described by the energy-based damage accumulation equation. Under long-term stress conditions, the damage accumulation of the skin is closely related to the energy dissipation rate and stress history. According to the existing damage evolution theory, the damage rate can be calculated by the following equation:

[0105] ;

[0106] in, is the growth rate of the injury; is the damage time scale constant, which determines the time response of damage evolution; It is the stress threshold at which damage begins to occur, indicating that when the effective stress exceeds this value, the skin will begin to accumulate damage; is the index of damage evolution; is the standard energy value, based on the energy dissipation characteristics of the skin in a healthy state; is the sensitivity factor of damage evolution to energy dissipation rate, reflecting the influence of energy dissipation on damage;

[0107] Integrate the growth rate of the damage to obtain the cumulative damage of the skin under long-term stress and the latency of injury :

[0108] ;

[0109] in, For the skin in time Cumulative damage over time; is the damage growth rate; is a specific moment; this formula calculates the total amount of damage to the skin under long-term stress. By integrating the damage growth rate, the skin damage over time can be obtained. As external stress continues to act, skin damage gradually accumulates until it reaches a certain threshold;

[0110] Once the accumulated damage reaches a certain critical value , then it is determined that the skin tissue is damaged:

[0111] ;

[0112] in, The incubation period of skin tissue damage indicates the time required for the cumulative damage to reach the critical value after the skin is subjected to external stress. The incubation period is the time interval before the skin is predicted to have obvious damage (such as deep tissue damage or ulcers); It is the critical damage value, which means that when the damage reaches a certain threshold, the degree of skin damage becomes significant and may cause deep tissue damage or pressure ulcers. This critical value is usually determined by factors such as biomechanical properties and skin health status;

[0113] By calculating the inverse of the damage growth rate at each moment in the damage growth process and integrating it, the time when the damage accumulation reaches the critical value, that is, the incubation period, is obtained. The damage latent period is an important indicator for evaluating the early signs of skin damage and is used to predict when the skin may suffer significant damage.

[0114] The muscle modeling module 23 is used to establish an active contraction model of muscle tissue, and obtain the ischemic threshold using the result of the active contraction model, and introduce the influence of fatigue degree to optimize the process of establishing the active contraction model of muscle tissue;

[0115] The specific steps of modeling in muscle modeling module 23 are as follows:

[0116] ;

[0117] in, The contraction force of the muscle indicates the actual strength of the muscle under force. In skin monitoring of critically ill patients, the contraction force of the muscle is closely related to the pressure on the skin tissue. Excessive muscle contraction may cause the skin to bear greater pressure, which in turn affects the skin damage. The maximum contraction force of the muscle, which indicates the force that the muscle can generate at maximum strength. During skin monitoring of critically ill patients, changes in the maximum contraction force of the muscle may affect local blood flow and tissue oxygen supply, thereby affecting skin damage; The contraction speed of the muscle (contraction speed refers to the speed of muscle contraction). In critically ill patients, the contraction speed of the muscle can reflect the patient's motor ability and muscle condition. Rapid contraction may generate greater force and increase the risk of skin tissue compression; The maximum contraction speed of the muscle indicates the fastest contraction speed that the muscle can reach. In the case of critically ill patients, changes in muscle contraction speed may affect the pressure of the muscle on the skin, thereby affecting the stress on the skin; is the passive elastic force of the muscle (passive elastic force refers to the force generated by the inherent elasticity of the muscle when the muscle is not actively contracted);

[0118] When critically ill patients are bedridden for a long time, their muscles are in a state of low activity and excessive tension for a long time. The active contraction model cannot simulate the muscle mechanical attenuation caused by long-term stress. Therefore, the influence of fatigue degree is introduced in the process of establishing the active contraction model of muscle tissue for optimization. The optimization is as follows:

[0119] ;

[0120] in, For optimized muscle contraction force; The decay rate of the fatigue factor controls the degree of influence of fatigue on muscle contraction force, which usually depends on the fatigue rate of the muscle and the endurance characteristics of the tissue; The fatigue time is the time when the muscle is under continuous work or high-intensity load;

[0121] After the fatigue time factor is introduced, the contraction force will gradually decrease with time, reflecting the decline of muscles under long-term continuous exercise or high-intensity load. This optimization model can more accurately simulate the changes in contraction force of muscles in actual applications, especially during long-term exercise, strain or fatigue.

[0122] The muscle modeling module 23 uses the model output result to correct the ischemic threshold, and the specific steps are as follows:

[0123] The ischemic threshold refers to the minimum level at which the blood supply to a tissue or organ is insufficient to meet its oxygen and nutrient needs under certain physiological or pathological conditions. Exceeding this threshold will lead to tissue ischemia, which will cause abnormal cell metabolism, lactic acid accumulation and tissue damage. In simple terms, the ischemic threshold is the critical point at which tissues begin to experience oxygen deficiency. Beyond this point, the function and health of the tissue will be affected.

[0124] ;

[0125] in, is the ischemic threshold; is the basic ischemic threshold, the ischemic threshold under normal conditions; Correction factor for blood flow supply; is the correction factor for lactate concentration; is the basal lactate concentration, usually the lactate concentration in a non-ischemic state; is the lactate concentration, which reflects the metabolic state of the muscle; is the correction factor for the strength of muscle contraction; An index that controls the effect of blood flow supply on ischemic threshold; It is an index to control the effect of lactate concentration on ischemic threshold; It is an index to control the effect of muscle contractility on ischemic threshold;

[0126] The risk assessment and early warning unit 3 is used to assess the patient's skin failure risk based on the strain energy density of the skin surface layer under the action of external force obtained by the hyperelastic model of the skin surface layer, the latent period of skin tissue damage obtained by the viscoelastic model of the subcutaneous fat layer, and the ischemic threshold obtained by the active contraction model of the muscle tissue;

[0127] Risk Assessment and Early Warning Unit 3 assesses the patient's risk of skin failure as follows:

[0128] Assess your patient's risk of skin failure:

[0129] ;

[0130] in, is the skin failure risk value; is a function related to the incubation period, which indicates the effect of the incubation period of tissue damage on the risk of skin failure. The functional form can be modeled based on the relationship between the incubation period and failure. is a correction function related to the ischemic threshold, indicating the effect of the ischemic threshold on the risk of skin failure;

[0131] Based on the results of the risk value, set different levels of risk thresholds and early warning methods for different risk levels;

[0132] Different levels of risk thresholds include the first risk threshold and the second risk threshold risk ;

[0133] if , a low-risk warning signal is generated, no warning is needed, continue to regularly check and monitor the patient's skin condition; maintain appropriate humidity and temperature conditions, and prevent prolonged pressure; if and A medium-risk warning signal is generated, and the system issues a warning, prompting medical staff to strengthen monitoring and care, and regularly assess skin conditions; consider adjusting the patient's position to reduce local pressure; use pressure distribution pads or other auxiliary equipment; if , a high-risk warning signal is generated and the system issues an emergency alarm, requiring medical staff to take emergency measures, perform medical intervention immediately, adjust the patient's position, ensure local blood flow; use special skin care products to prevent further skin damage; perform physical therapy on severely exhausted skin to avoid further deterioration.

[0134] The risk assessment and early warning unit 3 can realize dynamic monitoring and early warning of patients' skin failure, and guide clinical decision-making through a graded early warning mechanism, ensuring that patients can receive timely intervention before failure occurs, significantly improving the accuracy of clinical treatment and nursing effects.

[0135] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only preferred examples of the present invention, and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. A skin failure monitoring and early warning management system for critically ill patients, characterized in that: include: A skin data processing unit, the skin data processing unit is used to obtain a three-dimensional anatomical structure image of the patient's skin, pre-process the acquired three-dimensional anatomical structure image, and generate a three-dimensional digital model of the patient's skin tissue using a deep learning image segmentation method; Skin tissue includes the surface layer of skin, subcutaneous fat layer and muscle tissue; Among them, the skin data processing unit includes an acquisition processing module, a tissue recognition module and a three-dimensional reconstruction module; A biomechanical modeling unit, wherein the biomechanical modeling unit is used to establish a constitutive model of the skin tissue according to data provided by a three-dimensional digital model of the patient's skin tissue and in combination with the collected patient tissue characteristic data; the constitutive model of the skin tissue includes a hyperelastic model of the skin surface layer, a viscoelastic model of the subcutaneous fat layer, and an active contraction model of the muscle tissue, and the environmental force is introduced into the hyperelastic model of the skin surface layer for optimization, the influence factor of fat density is introduced into the process of establishing the viscoelastic model of the subcutaneous fat layer for optimization, and the influence of fatigue degree is introduced into the process of establishing the active contraction model of the muscle tissue for optimization; Among them, the biomechanical modeling unit includes a surface modeling module, a fat layer modeling module and a muscle modeling module; A risk assessment and early warning unit is used to jointly assess the patient's skin failure risk based on the strain energy density of the skin surface under external force obtained by the hyperelastic model of the skin surface, the latency of skin tissue damage obtained by the viscoelastic model of the subcutaneous fat layer, and the ischemic threshold obtained by the active contraction model of the muscle tissue.

2. The skin failure monitoring and early warning management system for critically ill patients according to claim 1 is characterized in that: In the skin data processing unit: The acquisition and processing module is used to obtain a three-dimensional anatomical structure image of the patient's skin through a computer tomography and magnetic resonance imaging device, and to pre-process the three-dimensional anatomical image; The tissue recognition module is used to segment the 3D anatomical structure image into multiple slices using an image segmentation algorithm, and then extract different tissues from the multiple slices according to the density of the tissues, and use a deep learning image segmentation method to identify and classify different tissues; The 3D reconstruction module is used to generate a volume model of each tissue of the patient based on the classified tissues, and to convert each tissue into a 3D digital model by extracting and reconstructing the tissue surface; The three-dimensional digital model provides the biomechanical modeling unit with tissue morphology data, volume data, the position of each point on the tissue surface, and the connection relationship between tissues.

3. The skin failure monitoring and early warning management system for critically ill patients according to claim 2 is characterized by: The tissue characteristic data include tissue elastic modulus and physical properties, tissue thickness and density distribution, inter-tissue contact and interaction, force boundary conditions and external load data.

4. The skin failure monitoring and early warning management system for critically ill patients according to claim 3 is characterized in that: In the biomechanical modeling unit: The surface modeling module is used to establish a hyperelastic model of the skin surface and simulate the strain energy density of the skin surface under the action of external forces; The fat layer modeling module is used to establish a viscoelastic model of the subcutaneous fat layer, simulate the mechanical response of the subcutaneous fat layer under external force, introduce the influencing factor of fat density to optimize the process of establishing the viscoelastic model of the subcutaneous fat layer, and predict the latent period of skin tissue damage by combining the energy dissipation rate of the subcutaneous fat layer with the results of the viscoelastic model; The muscle modeling module is used to establish an active contraction model of muscle tissue and obtain the ischemic threshold using the results of the active contraction model.

5. The critically ill patient skin failure monitoring and early warning management system according to claim 4 is characterized in that: The specific steps of the surface modeling module to establish the hyperelastic model of the skin surface are as follows: ； in, is the strain energy density of the skin surface under the action of external force; is the total strain energy; is the nonlinear index; is the elastic modulus constant of the skin material; is the elongation factor of the skin surface along the first principal axis during deformation; is the elongation factor of the skin surface along the second principal axis during deformation; is the elongation factor of the skin surface along the third principal axis during deformation; The degree of skin damage of the patient; is the change factor of the patient's skin volume; ; When the patient's skin surface comes into contact with external objects, shear force occurs. When the skin is subjected to the shear force generated by contact with external objects for a long time, skin failure is accelerated. Therefore, environmental forces are introduced into the hyperelastic model of the skin surface for optimization. After optimization, the specific results are as follows: ； in, is the strain energy density of the optimized skin surface under the action of external force; It is the number of contact surfaces between the patient's skin surface and external objects; ; is the coefficient of friction between the skin and the contact surface; is the normal force on the contact surface; The skin surface and external objects Shear force applied during contact; is the shear modulus of the skin.

6. The critically ill patient skin failure monitoring and early warning management system according to claim 5, characterized in that: The specific steps of the fat layer modeling module to establish the viscoelastic model of the subcutaneous fat layer are as follows: ； in, is the stress of the subcutaneous fat layer; is the elastic modulus of the subcutaneous fat layer; is the strain of the subcutaneous fat layer; is the viscosity coefficient of the subcutaneous fat layer; Different patients have different skin thickness and fat. Patients with different thicknesses of fat layers have different stress resistance, which in turn affects the stress distribution of the subcutaneous fat layer of different patients. Therefore, in the process of establishing the viscoelastic model of the subcutaneous fat layer, the influencing factor of fat density is introduced for optimization. After optimization, the specific results are: ； in, is the elastic modulus of the subcutaneous fat layer after the fat density is introduced; is the elastic modulus of the standard fat layer; is the density of the current fat layer; is the density of the standard fat layer; is the thickness of the skin; is the standard skin thickness; is the influence factor of thickness change on elastic modulus; is the sensitivity index of elastic modulus to changes in fat density; ； in, is the viscosity coefficient of the subcutaneous fat layer after the fat density is introduced; is the viscosity coefficient of the standard fat layer; is a constant that controls the effect of fat density on the viscosity coefficient; ； in, is the stress of the subcutaneous fat layer after the fat density is introduced.

7. The skin failure monitoring and early warning management system for critically ill patients according to claim 6 is characterized by: The fat layer modeling module predicts the latent period of tissue damage by the energy dissipation rate of the subcutaneous fat layer, and the specific steps are as follows: ； in, is the energy dissipation rate; is the strain rate of the subcutaneous fat layer; ； in, is the growth rate of the injury; is the damage time scale constant; is the stress threshold at which damage begins to occur; is the index of damage evolution; is the standard energy value; is the sensitivity factor of damage evolution to energy dissipation rate; Integrate the growth rate of the damage to obtain the cumulative damage of the skin under long-term stress and the latency of injury : ； in, For the skin in time Cumulative damage over time; is the damage growth rate; for a specific moment; When the accumulated damage reaches a certain critical value When the skin tissue is damaged: ； in, It is the incubation period of skin tissue damage; is the critical damage value.

8. The critically ill patient skin failure monitoring and early warning management system according to claim 7, characterized in that: The specific steps of modeling the muscle modeling module are as follows: ； in, The contraction force of the muscle; is the maximum contraction force of the muscle; is the contraction speed of the muscle; is the maximum contraction speed of the muscle; is the passive elastic force of the muscle; When critically ill patients are bedridden for a long time, their muscles are in a state of low activity and excessive tension for a long time. The active contraction model cannot simulate the muscle mechanical attenuation caused by long-term stress. Therefore, the influence of fatigue degree is introduced in the process of establishing the active contraction model of muscle tissue for optimization. The optimization is as follows: ； in, For optimized muscle contraction force; is the decay rate of fatigue factor; Fatigue time.

9. The skin failure monitoring and early warning management system for critically ill patients according to claim 8, characterized in that: The muscle modeling module uses the model output results to correct the ischemic threshold, and the specific steps are as follows: ； in, is the ischemic threshold; is the basic ischemic threshold; Correction factor for blood flow supply; is the correction factor for lactate concentration; is the basal lactate concentration; is the lactate concentration; is the correction factor for the strength of muscle contraction; An index that controls the effect of blood flow supply on ischemic threshold; It is an index to control the effect of lactate concentration on ischemic threshold; It is an index that controls the effect of muscle contractility on ischemic threshold.

10. The skin failure monitoring and early warning management system for critically ill patients according to claim 9, characterized in that: The specific steps of the risk assessment and early warning unit for assessing the patient's skin failure risk are as follows: Assess your patient's risk of skin failure: ； in, is the skin failure risk value; is a function related to the incubation period; is a correction function related to the ischemic threshold; Based on the results of the risk value, set different levels of risk thresholds and early warning methods for different risk levels; Different levels of risk thresholds include the first risk threshold and the second risk threshold risk ; if , a low risk warning signal is generated; if and A medium risk warning signal is generated; if , a high-risk warning signal is generated.

Images