Artificial Intelligence Dynamic Assessment Method and System for Constructing a Mouse Model of Multiple Injuries

Abstract

This invention discloses an artificial intelligence-based method and system for constructing a mouse model of multiple injuries, belonging to the technical field of injury models. The method includes: applying controlled impact to the mouse's cranium to induce brain injury, and introducing controlled trauma to the chest and abdomen to simulate thoracic and abdominal cavity injuries; monitoring the physiological parameters of the injured mouse in real time using a sensing device, and collecting physiological data reflecting the impact of cranial and thoracic abdominal injuries; inputting the physiological data into an artificial intelligence algorithm model to assess the severity of the injuries in real time and generate corresponding assessment results; using the assessment results to classify the severity of the injuries, and establishing a corresponding mouse model of multiple injuries to the cranium and chest / abdomen. The technical solution of this application achieves accurate simulation and graded assessment of injuries to multiple sites in mice. Through real-time monitoring of multimodal physiological parameters and dynamic analysis using artificial intelligence, it effectively supports the exploration of multiple injury mechanisms and the verification of intervention strategies.

Description

Technical Field

[0001] This invention relates to the technical field of injury models, and in particular to an artificial intelligence-based method and system for constructing a mouse model of multiple injuries for dynamic evaluation. Background Technology

[0002] With the high incidence of multiple injuries in trauma research and their complex physiological cascade responses, establishing scientific, controllable, and dynamically assessable animal models has become an urgent need for basic and translational research. In practical applications, traumatic brain injury combined with thoracic and abdominal injuries is often accompanied by multiple systemic imbalances, such as autonomic nervous system dysfunction, circulatory and respiratory dysfunction. The early mortality risk in individuals with severe traumatic brain injury is highly correlated with multiple parameters such as lactate levels, base excess, and injury scores, which places higher demands on the dynamic grading of experimental animal models and the scientific determination of critical time windows. Traditional single injury models are no longer sufficient to reflect the complex evolution and cascade mechanisms of multiple injuries in the physiological process.

[0003] Currently, existing animal model technologies suffer from three main problems. First, the controllability of injury is limited. Traditional methods such as free-fall impact and liver / spleen puncture rely solely on mechanical parameters to determine injury intensity, failing to establish a linear correlation between physiological responses and input parameters. This leads to inaccurate model grading and poor repeatability. Brain and thoracic / abdominal injuries are often induced separately, neglecting the essential characteristics of multiple injuries in terms of cross-compartmental biomechanical responses and physiological coupling. Second, dynamic monitoring and multimodal integration mechanisms are lacking. Existing models often rely on endpoint behavioral tests (such as the water maze and rotarod test) or single physiological parameters, making it difficult to achieve real-time continuous monitoring of key signals such as intracranial pressure, blood pressure, and respiratory rate. This results in missed opportunities for critical processes such as shock compensation and secondary brain injury. Furthermore, behavioral and tissue indicators are influenced by subjective interpretation, making it difficult to quantify complex injury dynamics. Third, there are significant deficiencies in cross-system interactive modeling and individualized adaptation. Traditional finite element models and stress wave propagation simulations are mostly applied to large individuals, with limited accuracy in simulating individual structural differences and cross-compartmental mechanical coupling in mice, making it difficult to achieve cascade responses and accurate modeling of multiple injuries.

[0004] While artificial intelligence (AI) technology has already assisted decision-making in some areas, dynamic, real-time intelligent grading in animal models remains a gap. Existing scoring systems or decision-making models based on static data are mostly used for single-instance risk prediction, lacking the ability to fuse dynamic physiological signals and incremental learning. Issues such as inconsistent multi-center data standards and insufficient model generalization ability limit the high versatility and consistency of intelligent grading tools in animal experiments. Current technologies urgently need breakthroughs in areas such as damage controllability, dynamic monitoring, multimodal data fusion, cross-system interaction, and intelligent grading. How to properly address these issues has become a pressing issue for the industry. Summary of the Invention

[0005] This invention provides an artificial intelligence-based method and system for constructing a mouse model of multiple injuries, which improves the controllability and scientific rigor of the mouse model of multiple injuries, realizes intelligent and standardized injury grading, and is helpful for mechanism research and verification of intervention effects.

[0006] According to a first aspect of the present invention, an artificial intelligence dynamic assessment method for constructing a mouse multiple injury model is provided, the method comprising:

[0007] Controlled impacts were applied to the cranium of mice to induce brain damage, and controlled trauma was introduced into the chest and abdomen to simulate thoracic and abdominal injuries.

[0008] The physiological parameters of the injured mice are monitored in real time by a sensing device, and physiological data reflecting the effects of brain and chest and abdominal injuries are collected. The physiological parameters include one or more of intracranial pressure, blood pressure and respiratory rate.

[0009] The physiological data is input into an artificial intelligence algorithm model for time-series analysis and cross-system data fusion to assess the severity of injury in the injured mouse in real time and generate corresponding assessment results.

[0010] The assessment results were used to classify the severity of the injury, and a corresponding mouse model of multiple injuries to the brain and chest and abdomen was established accordingly.

[0011] In one embodiment, the controlled impact to the mouse cranium to cause brain injury includes:

[0012] A pressure sensor was implanted in the cranial cavity of a mouse to monitor intracranial pressure in real time.

[0013] The impact force is adjusted based on the feedback of intracranial pressure to achieve a predetermined degree of traumatic brain injury.

[0014] In one embodiment, the introduction of controlled trauma to the chest and abdomen to simulate pleural and abdominal injuries includes:

[0015] A miniature hydraulic puncture needle was inserted into the thoracic or abdominal cavity of a mouse to puncture internal organs and induce bleeding.

[0016] The micro-flow pump linked to the puncture needle dynamically adjusts the bleeding rate according to the mouse's blood pressure changes, thereby simulating an uncontrolled hemorrhagic shock process.

[0017] In one embodiment, the real-time monitoring of the physiological parameters of the injured mouse includes:

[0018] A fiber optic intracranial pressure sensor was implanted in the cranial cavity of a mouse to monitor changes in intracranial pressure.

[0019] Flexible strain sensors were implanted in the thoracic cavity or chest wall of mice to monitor respiratory rate and determine the status of hemopneumothorax.

[0020] A miniature ultrasound probe was implanted in the peritoneal cavity of a mouse to monitor the amount of bleeding in the peritoneal cavity;

[0021] Microneedle-type blood lactate sensors were implanted in mice to monitor systemic metabolic disorders.

[0022] In one embodiment, it also includes:

[0023] The intracranial pressure, respiratory rate, bleeding volume, and blood lactate collected by the sensors are input into the artificial intelligence model as multimodal time-series data;

[0024] The time-series data were analyzed using a recurrent neural network to identify the correlations between key events and different physiological parameters during the injury process;

[0025] Output real-time updated severity scores for multiple injuries and / or early warning signals.

[0026] In one embodiment, it also includes:

[0027] Before injury, mice were subjected to miniature CT scans to obtain individual anatomical atlases of mice, including skull thickness, brain volume, and thoracic structure.

[0028] The impact location and angle of the traumatic brain injury are adjusted based on the anatomical atlas to reduce the injury dispersion caused by individual differences.

[0029] The propagation path of mechanical stress from the thoracic cavity to the brain is simulated using a finite element model, and the parameters of thoracic and abdominal injuries are calibrated accordingly to achieve the predetermined degree of secondary brain injury.

[0030] According to a second aspect of the present invention, an artificial intelligence dynamic assessment system for constructing a mouse multiple injury model is provided, comprising:

[0031] The injury module is used to apply controlled impacts to the brain of mice to cause brain damage and to introduce controlled trauma to the chest and abdomen to simulate thoracic and abdominal injuries.

[0032] The monitoring module is used to monitor the physiological parameters of the injured mouse in real time through a sensing device and to collect physiological data reflecting the effects of brain and chest and abdominal injuries. The physiological parameters include one or more of intracranial pressure, blood pressure and respiratory rate.

[0033] The analysis module is used to input the physiological data into an artificial intelligence algorithm model, perform time-series analysis and cross-system data fusion, assess the severity of the injury in the injured mouse in real time, and generate corresponding assessment results.

[0034] The grading module is used to grade the severity of the injury based on the assessment results, and to establish a corresponding mouse model of multiple injuries to the brain and chest and abdomen.

[0035] In one embodiment, the damage module, the monitoring module, the analysis module, and the grading module are controlled to execute any of the above-described methods for constructing a mouse multiple injury model using artificial intelligence dynamic assessment.

[0036] According to a third aspect of the present invention, an electronic device is provided, comprising: a communication interface, a processor, and a memory;

[0037] The memory is used to store program instructions, which, when executed by the processor that is connected to the memory via the communication interface, implement any of the above-described methods for constructing a dynamic evaluation mouse multiple injury model using artificial intelligence.

[0038] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a computer (e.g., a processor in the computer), implement any of the above-described methods for constructing a mouse multiple injury model for dynamic evaluation of artificial intelligence.

[0039] In summary, this invention provides a method and system for constructing a mouse model of multiple injuries using artificial intelligence for dynamic assessment. The method includes: applying controlled impact to the mouse's cranium to induce brain injury, and introducing controlled trauma to the chest and abdomen to simulate thoracic and abdominal cavity injuries; monitoring the physiological parameters of the injured mouse in real time using a sensing device, and collecting physiological data reflecting the effects of cranial and thoracic abdominal injuries, including one or more of intracranial pressure, blood pressure, and respiratory rate; inputting the physiological data into an artificial intelligence algorithm model for time-series analysis and cross-system data fusion, assessing the severity of the injury in the injured mouse in real time and generating corresponding assessment results; using the assessment results to classify the severity of the injury, and establishing a corresponding mouse model of multiple injuries to the cranium and chest / abdomen based on this classification. The technical solution of this application, through controlled injury and real-time multimodal physiological monitoring, achieves controllable and highly repeatable classification of the mouse model of multiple injuries to the cranium and chest / abdomen. Combining artificial intelligence algorithms with dynamic assessment of continuous physiological data can accurately reflect changes in injury severity, achieving intelligent and standardized classification evaluation. This approach overcomes the limitations of traditional models in terms of damage controllability, dynamic monitoring, and single evaluation methods.

[0040] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and drawings.

[0041] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0042] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0043] Figure 1 A flowchart of an artificial intelligence-based method for constructing a mouse model for dynamic evaluation of multiple injuries is provided as an embodiment of the present invention;

[0044] Figure 2 A flowchart of another method for constructing a mouse multiple injury model for dynamic evaluation using artificial intelligence, provided as an embodiment of the present invention;

[0045] Figure 3 A flowchart of another method for constructing a mouse multiple injury model for dynamic evaluation using artificial intelligence, provided as an embodiment of the present invention;

[0046] Figure 4 A flowchart of another method for constructing a mouse multiple injury model for dynamic evaluation using artificial intelligence, provided as an embodiment of the present invention;

[0047] Figure 5 A flowchart of another method for constructing a mouse multiple injury model for dynamic evaluation using artificial intelligence, provided as an embodiment of the present invention;

[0048] Figure 6 A flowchart of another method for constructing a mouse multiple injury model for dynamic evaluation using artificial intelligence, provided as an embodiment of the present invention;

[0049] Figure 7 A structural diagram of an artificial intelligence dynamic assessment mouse multiple injury model construction system provided for embodiments of the present invention;

[0050] Figure 8 This is a structural diagram of an electronic device provided as an embodiment of the present invention. Detailed Implementation

[0051] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0052] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0053] like Figure 1 As shown, this invention provides a method for constructing an artificial intelligence-based dynamic assessment model of multiple injuries in mice. This method includes:

[0054] In step S11, a controlled impact is applied to the mouse cranium to cause brain injury, and a controlled trauma is introduced in the chest and abdomen to simulate thoracic and abdominal cavity injuries.

[0055] In step S12, the physiological parameters of the injured mouse are monitored in real time by a sensing device, and physiological data reflecting the effects of brain and chest and abdomen injuries are collected. The physiological parameters include one or more of intracranial pressure, blood pressure and respiratory rate.

[0056] In step S13, the physiological data is input into an artificial intelligence algorithm model for time-series analysis and cross-system data fusion to assess the severity of injury in the injured mouse in real time and generate corresponding assessment results.

[0057] In step S14, the evaluation results are used to classify the severity of the injury, and a corresponding mouse model of multiple injuries to the brain and chest and abdomen is established accordingly.

[0058] In one embodiment, a closed-loop feedback control modeling platform for multiple injuries is established. The damage level is precisely controlled through mechanical feedback. Combined with multiple types of implantable physiological sensors and artificial intelligence algorithms, the multiple injury process is collected, analyzed, and graded in real time, providing a high-fidelity and highly universal experimental basis for mechanism research and intervention strategy verification.

[0059] This study aims to construct a mouse model of multiple injuries involving the cranium and chest / abdomen, achieving a closed-loop integration of injury-inducing manipulation and damage assessment. Starting with controlled impacts to the mouse cranium to induce brain injury, and introducing controlled trauma to the chest and abdomen to simulate thoracic and abdominal injuries, this approach differs from traditional single-site injury methods by simultaneously introducing controlled injuries at multiple sites on the same animal, thus more closely resembling clinical scenarios of multiple injuries. The use of controlled mechanical injury methods allows for precise damage energy management targeting the cranium and chest / abdomen, avoiding the randomness of injury outcomes caused by experimental conditions and individual animal differences, and improving the grading consistency and reproducibility of the experimental model.

[0060] The physiological parameters of the injured mice were monitored in real time using a sensing device, and physiological data reflecting the effects of intracranial and thoracic-abdominal injuries were collected. These physiological parameters included one or more of intracranial pressure, blood pressure, and respiratory rate, enabling multimodal and real-time acquisition of physiological signals. By implanting or attaching highly sensitive sensors into the mice, physiological data could be dynamically acquired throughout the entire process following injury induction. These physiological parameters not only reflected the initial effects of the injury but also allowed for real-time tracking of the body's adaptive response to combined injuries and the physiological cascade process.

[0061] The physiological data is input into an artificial intelligence algorithm model for time-series analysis and cross-system data fusion, enabling real-time assessment of the severity of injury in the injured mice and generating corresponding evaluation results. Through deep learning, feature extraction, and fusion of multimodal time-series physiological data, the model surpasses manual threshold interpretation, achieving automatic identification of injury severity, trend prediction, and early warning. Time-series analysis ensures the model's sensitivity to dynamic evolution processes, while cross-system data fusion enhances the understanding of pathological correlations and interactions among multiple organs.

[0062] The assessment results were used to grade the severity of injuries, and a corresponding mouse model of multiple injuries to the brain and chest / abdomen was established accordingly. The grading results generated by artificial intelligence can accurately distinguish the differences in the degree of injury, development trend, and prognostic risk among individuals with multiple injuries, forming a quantifiable and comparable multi-level injury model. This not only allows for model customization to meet different experimental needs but also realizes the objective grading of animal models, moving beyond subjective experience-based interpretation.

[0063] The system integrates a multi-chamber coupled injury module. In the reconstruction of craniocerebral injuries, an electromagnetically driven impactor is used, enabling real-time monitoring of intracranial pressure (ICP) via pressure sensors and dynamic adjustment of the impact force (range 0.5–2.5 J). This ensures a linear relationship between the degree of injury (mild, moderate, severe) and the input energy, solving the technical challenge of nonlinear correspondence between mechanical parameters and the actual degree of brain tissue damage in traditional gravity-based free-fall models. For chest and abdominal injuries, the system integrates a miniature hydraulic puncture needle. Based on real-time monitoring of blood pressure (BP) and blood lactate levels, it dynamically adjusts the liver and spleen puncture depth (0.1–1.0 mm) and blood loss rate (5–20 μL / min), accurately simulating the physiological process of uncontrollable hemorrhagic shock. This surpasses the limitations of previous fixed-parameter models in terms of dynamic controllability of injury and model realism.

[0064] In terms of modeling stress transmission and pathological mechanisms across chambers, the scheme introduces a miniature pressure wave generator implanted in the thoracic cavity, which can release controllable shock waves with frequencies of 10–50 Hz. Based on a finite element simulation model, the propagation path of stress between the cranium and the thoracic and abdominal cavities is pre-calculated. Through the principle of mechanical coupling, the cascade effect of secondary craniocerebral injury caused by thoracic injury can be quantified.

[0065] By performing a miniature CT scan on the mouse before surgery, three-dimensional anatomical atlases such as skull thickness, brain volume, and thoracic cavity structure can be obtained. Based on this, the impact position and angle can be dynamically adjusted with an adjustment accuracy of ±2°, significantly reducing the damage dispersion caused by anatomical differences.

[0066] Before model construction, a mini-CT scanner was used to perform a comprehensive scan of each mouse to obtain a three-dimensional anatomical atlas, including skull thickness, brain volume, and thoracic cavity structure. Based on the above individualized three-dimensional atlas, the researchers were able to dynamically adjust the impact position and angle at the time of injury, with an adjustment accuracy of ±2°, which significantly reduced the dispersion of injury distribution caused by individual anatomical variations in mice.

[0067] A dynamic monitoring system was constructed, and an implantable multimodal sensor array was used to collect key physiological parameters in mice in real time and at high frequency, covering 12 dimensions such as intracranial pressure, blood lactate, and respiratory rate. The sampling frequency reached 100Hz. The implantable multimodal sensor array is shown in Table 1 below.

[0068] Table 1

[0069]

[0070] The collected multimodal time-series data are processed by a dynamic adaptive artificial intelligence evaluation engine. Short-term memory networks (LSTM) are used to identify key time-window events such as short-term intracranial pressure spikes and blood lactate inflection points after injury. Graph neural networks (GNNs) further analyze the causal relationships between various systems, outputting a dynamic score for multiple injuries in real time. The stages of the dynamic model construction process are shown in Table 2 below.

[0071]

[0072] In cross-system interactive modeling, a multi-scale finite element simulation engine based on individual CT data was introduced to construct a three-dimensional finite element mesh of the cranium-thoracic abdomen, simulating the propagation of shock waves among cerebrospinal fluid, lung parenchyma, and abdominal organs, and calculating the distribution of local strain energy density (SED). Microdialysis technology was used to monitor brain tissue GFAP and serum Tau protein levels, establishing a quantitative relationship between SED and biochemical damage markers, achieving dual coupling modeling of biomechanics and biochemistry. Furthermore, optogenetic stimulation of the dorsal nucleus of the vagus nerve enabled controllable induction of autonomic dysfunction, simulating the multi-system pathological progression and cascade reactions after multiple injuries.

[0073] A federated learning and adaptive control platform was built, with a multi-center data lake architecture supporting local training of AI sub-models in different laboratories and improving model generalization ability through cloud parameter aggregation. A neurofunctional-behavioral quantitative description system was established through multimodal data standardization, and multiple methods such as gait analysis and cognitive assessment were used to comprehensively characterize animal models with multiple injuries. The system incorporates a dynamic adaptation algorithm that can automatically adjust injury parameters or implement simulated resuscitation operations based on MDSS scores and blood lactate levels, achieving closed-loop dynamic optimization throughout the entire process.

[0074] To verify the controllability of the injury, this technical solution designed a comparative experiment on the linear relationship of traumatic brain injury. Specifically, C57BL / 6 mice were used as experimental subjects (n=20 per group). Traumatic brain injury was induced using both a traditional gravity-induced fall model (grouped by the product of weight and fall height, gcf) and the electromagnetically driven impactor proposed in this solution (with real-time calibration combined with pressure feedback). The impact energy was set to increase in a gradient within the range of 1.0–2.0 J. A systematic evaluation of the relationship between tissue damage and input energy under the two injury methods was conducted, and the results are shown in Table 3 below.

[0075] Table 3

[0076]

[0077] To verify the dynamic simulation capability of thoracic and abdominal blood loss, a comparative experimental design was adopted. One group used traditional liver and spleen puncture with a fixed blood loss of 0.5 mL; the other group used the hydraulic puncture needle of this technology, dynamically adjusting the blood loss rate (5–20 μL / min) based on real-time monitoring of the blood pressure drop slope. The results showed that when predicting the irreversible shock point, the survival rate of the traditional model with blood lactate > 5 mmol / L as the cutoff was only 40% (with a false positive rate as high as 60%), while the survival rate of the dynamic blood loss group in this patented model increased to 85%, demonstrating that the real-time regulation mechanism can effectively avoid excessive blood loss.

[0078] To construct an efficient dynamic monitoring system, this technical solution employs a multimodal implantable sensor network to achieve high-precision, real-time monitoring of key physiological parameters in mice. The implantable sensors possess high sensitivity and accuracy, continuously capturing multidimensional physiological signals such as intracranial pressure, blood pressure, and respiratory rate. The accuracy of the implantable sensors is shown in Table 4 below.

[0079] Table 4

[0080]

[0081] For the grading and evaluation of multiple injuries, the proposed solution established a dynamic MDSS scoring model. The training dataset consisted of 120 mice from three laboratories (including five strains such as C57BL / 6 and BALB / c), while the test set consisted of 30 mice from an independent center. Through systematic training and independent validation using large-sample data from multiple centers, the model's performance across strains and experimental scenarios was comprehensively evaluated. The performance comparison is shown in Table 5 below.

[0082] Table 5

[0083]

[0084] The technical solution in this embodiment achieves controlled and highly reproducible grading of a mouse model of multiple injuries to the brain and chest / abdomen through controlled injury and real-time multimodal physiological monitoring. Combining artificial intelligence algorithms with dynamic evaluation of continuous physiological data accurately reflects changes in injury severity, enabling intelligent and standardized grading assessment. This solution overcomes the limitations of traditional models in terms of injury controllability, dynamic monitoring, and single evaluation methods, improving the model's physiological relevance and scientific rigor.

[0085] In one embodiment, such as Figure 2 As shown, step S11 includes the following steps S21-S22:

[0086] In step S21, a pressure sensor is implanted in the mouse's cranial cavity to monitor intracranial pressure in real time;

[0087] In step S22, the force of the impact device is adjusted according to the feedback of the intracranial pressure to achieve the predetermined degree of traumatic brain injury.

[0088] In one embodiment, a real-time feedback mechanism for injury controllability and physiological parameters was constructed during the establishment of a mouse model of traumatic brain injury. By implanting pressure sensors into the mouse cranial cavity, intracranial pressure can be dynamically and accurately monitored. Compared with traditional animal models that rely on mechanical parameters (such as weight, drop height, etc.) or endpoint behavioral evaluations, this mechanism can reflect the actual stress and degree of damage to brain tissue during injury in real time. The force of the impact device is adjusted based on the real-time monitoring results of intracranial pressure to achieve predetermined control over the degree of traumatic brain injury. The physiological-mechanical closed-loop regulation mechanism achieves dynamic matching between injury input parameters and physiological responses, overcoming the problem of nonlinear correlation between mechanical injury parameters and actual tissue damage. Through feedback adjustment, the degree of injury can be fine-tuned in real time during the experiment, improving the consistency of injury grading among multiple groups of animals.

[0089] In one embodiment, such as Figure 3 As shown, step S11 further includes the following steps S31-S32:

[0090] In step S31, a miniature hydraulic puncture needle is inserted into the thoracic or abdominal cavity of the mouse to puncture internal organs and induce bleeding;

[0091] In step S32, the bleeding rate is dynamically adjusted by a micro-flow pump linked to the puncture needle according to the mouse's blood pressure changes, thereby simulating an uncontrolled hemorrhagic shock process.

[0092] In one embodiment, a dynamic simulation of pathological changes in the thoracic and abdominal cavities in a multiple injury model was designed based on the construction process of thoracic and abdominal injuries in mice. By inserting a miniature hydraulic puncture needle into the thoracic or abdominal cavity of the mouse, precise mechanical damage and hemorrhage induction in specific organs (such as the liver and spleen) can be achieved. This is more controllable than traditional mechanical puncture or tissue cutting, and helps to standardize the extent and location of injury. The precise implementation of mechanical injury provides a stable foundation for the real-time acquisition and dynamic control of subsequent physiological parameters. Based on the design of a feedback closed loop that dynamically adjusts the bleeding rate according to blood pressure changes, the bleeding rate can be finely adjusted in real time according to the blood pressure level monitored by the mouse, thereby accurately simulating the complex pathological process of uncontrollable hemorrhagic shock in clinical practice. This mechanism effectively overcomes the problems of fixed blood loss, simple shock process, and lack of dynamic regulation in previous animal models, and achieves a high degree of coupling between injury and physiological response.

[0093] In one embodiment, such as Figure 4 As shown, step S12 includes the following steps S41-S44:

[0094] In step S41, an optical fiber intracranial pressure sensor is implanted into the cranial cavity of the mouse to monitor changes in intracranial pressure.

[0095] In step S42, a flexible strain sensor is implanted in the thoracic cavity or chest wall of the mouse to monitor respiratory rate and determine the status of hemopneumothorax.

[0096] In step S43, a miniature ultrasound probe is implanted into the peritoneal cavity of the mouse to monitor the amount of bleeding in the peritoneal cavity;

[0097] In step S44, a microneedle-type blood lactate sensor is implanted in the mouse to monitor systemic metabolic disorders.

[0098] In one embodiment, multiple types of implantable physiological sensors were introduced during the construction of a mouse model of multiple brain injuries, enabling real-time, multi-dimensional monitoring of key physiological parameters. By implanting fiber optic intracranial pressure sensors into the mouse cranial cavity, intracranial pressure changes can be continuously and dynamically acquired, providing objective data for assessing the degree of brain injury and subsequent regulation. Compared with traditional methods relying on endpoint behavioral or single-point pathological analysis, this approach enhances the sensitivity to the development of traumatic brain injury and helps capture real-time signals of key pathological stages such as cerebral edema and secondary brain injury.

[0099] Flexible strain sensors in the thoracic cavity or chest wall are used to monitor respiratory rate in real time and can assist in the assessment of important thoracic pathological conditions such as hemopneumothorax. Miniature ultrasound probes deployed in the abdominal cavity can non-invasively and dynamically monitor changes in intra-abdominal hemorrhage, providing high-resolution quantitative data for assessing abdominal organ damage and blood loss. Microneedle-type blood lactate sensors can reflect the body's systemic metabolic level and oxygenation status in real time, serving as an important indicator for monitoring the progression of multiple traumatic shock. The introduction of these highly integrated, multimodal sensing methods enriches the dimensions and depth of model data. It overcomes the limitations of previous single or intermittent monitoring techniques, achieving full-process, closed-loop acquisition of physiological information from multiple systems. Through these sensor networks, the complex responses and cascading changes of various tissues and organs after mouse injury can be captured in a timely manner.

[0100] In one embodiment, such as Figure 5 As shown, it also includes the following steps S51-S53:

[0101] In step S51, the intracranial pressure, respiratory rate, bleeding volume, and blood lactate collected by the sensor are input into the artificial intelligence model as multimodal time-series data;

[0102] In step S52, the time-series data is analyzed using a recurrent neural network to identify the correlation between key events and different physiological parameters during the injury process;

[0103] In step S53, the severity score of multiple injuries and / or early warning signals are output in real time.

[0104] In one embodiment, the construction and evaluation process of animal models of multiple injuries integrates an intelligent processing and analysis mechanism for multimodal time-series data, demonstrating data-driven scientific grading and early warning capabilities. By inputting multiple key physiological parameters such as intracranial pressure, respiratory rate, hemorrhage volume, and blood lactate collected by sensors into the artificial intelligence model in the form of time-series data, a solid foundation is laid for continuous monitoring and dynamic analysis of the entire process of multiple injuries. Unlike traditional evaluation models that rely solely on single or endpoint data, this approach achieves full-dimensional information capture of the entire process of injury occurrence, development, and recovery, ensuring the real-time nature of model evaluation.

[0105] At the data processing level, deep learning methods such as recurrent neural networks (RNNs) were introduced to analyze multimodal time-series data. RNNs excel at processing time-series information, automatically uncovering potential connections and patterns of change among various physiological parameters at different time points, enabling dynamic identification of key events in the injury process (such as brain herniation, circulatory imbalance, and metabolic deterioration). RNNs possess memory and recursive capabilities, allowing them to integrate historical information from multiple parameters and analyze the interactions between different systems (such as the nervous, circulatory, and metabolic systems), thereby revealing the systemic pathological coupling mechanisms under complex multiple injury models. The system outputs real-time scores and / or early warning signals based on the severity of multiple injuries, achieving intelligent and standardized dynamic hierarchical management. The scoring system automatically adjusts the model's grading standards based on changes in physiological parameters, promptly reflecting individual differences in injury and progression trends. The early warning mechanism issues signals before critical changes in injury, organically combining multimodal physiological data, deep learning algorithms, and an intelligent scoring system to establish a closed-loop platform spanning the entire process of injury, monitoring, assessment, and early warning.

[0106] In one embodiment, such as Figure 6 As shown, it also includes the following steps S61-S63:

[0107] In step S61, a miniature CT scan is performed on the mouse before injury to obtain an individual anatomical atlas of the mouse, including skull thickness, brain volume and thoracic cavity structure.

[0108] In step S62, the impact position and angle of the traumatic brain injury are adjusted based on the anatomical atlas to reduce the injury dispersion caused by individual differences.

[0109] In step S63, the propagation path of mechanical stress in the thoracic cavity to the brain is simulated by a finite element model, and the parameters of the chest and abdominal injury are calibrated accordingly to achieve the predetermined degree of secondary brain injury.

[0110] In one embodiment, an integrated mechanism of individualized anatomical information and biomechanical simulation was introduced into the construction process of a mouse multiple injury model to further improve the accuracy of model grading and the reproducibility of experimental results. By performing miniature CT scans on mice before injury, detailed anatomical data such as individual skull thickness, brain volume, and thoracic cavity structure were obtained, effectively solving the problem of high dispersion in injury manifestations caused by large individual anatomical differences in traditional models.

[0111] With the support of anatomical atlases, the impact location and angle of craniocerebral injury are adjusted based on individual anatomical characteristics. Precise matching not only significantly reduces injury deviations caused by differences in anatomical structures between different experimental animals, but also provides strong support for graded modeling and reproducible experiments. The propagation path of intrathoracic mechanical stress to the cranium is simulated using a finite element model, and relevant parameters of thoracic and abdominal injuries are calibrated accordingly to achieve precise control over the predetermined degree of secondary craniocerebral injury. Finite element simulation can reveal the propagation and energy distribution patterns of stress waves under different anatomical structures and stress conditions, thus providing theoretical support for the mechanical control and parameter setting of multiple injury models. The closed-loop process of physical simulation-physiological feedback-parameter calibration enables multiple injury models to possess a high degree of refinement and controllability in damage control, cross-compartmental coupling, and mechanism research.

[0112] In one embodiment, Figure 7 This is a block diagram illustrating an artificial intelligence-based dynamic assessment system for constructing a mouse model of multiple injuries, according to an exemplary embodiment. Figure 7 As shown, the AI-based dynamic assessment system for constructing a mouse multiple injury model includes an injury module 71, a monitoring module 72, an analysis module 73, and a grading module 74.

[0113] The injury module 71 is used to apply controlled impacts to the brain of mice to cause brain damage and to introduce controlled trauma to the chest and abdomen to simulate chest and abdominal cavity injuries.

[0114] The monitoring module 72 is used to monitor the physiological parameters of the injured mouse in real time through a sensing device, and to collect physiological data reflecting the effects of brain and chest and abdominal injuries. The physiological parameters include one or more of intracranial pressure, blood pressure and respiratory rate.

[0115] The analysis module 73 is used to input the physiological data into an artificial intelligence algorithm model, perform time-series analysis and cross-system data fusion, assess the severity of the injury in the injured mouse in real time, and generate corresponding assessment results.

[0116] The grading module 74 is used to grade the severity of the injury based on the assessment results, and to establish a corresponding mouse model of multiple injuries to the brain and chest and abdomen.

[0117] The damage module 71, monitoring module 72, analysis module 73, and grading module 74 included in the block diagram of the AI ​​dynamic assessment mouse multiple injury model construction system are controlled to execute the AI ​​dynamic assessment mouse multiple injury model construction method described in any of the above embodiments.

[0118] like Figure 8 As shown, the present invention provides an electronic device 800, which includes: a communication interface, a processor 801, and a memory 802;

[0119] The memory 802 stores program instructions. When executed by the processor 801, which is connected to the memory 802 via the communication interface, the program instructions apply controlled impacts to the mouse's cranium to cause brain injury and introduce controlled trauma to the chest and abdomen to simulate thoracic and abdominal injuries. The physiological parameters of the injured mouse are monitored in real time using a sensing device, and physiological data reflecting the effects of cranial and thoracic / abdominal injuries are collected. These physiological parameters include one or more of intracranial pressure, blood pressure, and respiratory rate. The physiological data is input into an artificial intelligence algorithm model for time-series analysis and cross-system data fusion to assess the severity of the injury in the mouse in real time and generate corresponding assessment results. The assessment results are used to classify the severity of the injury and establish a corresponding mouse model of cranial and thoracic / abdominal multiple injuries.

[0120] This invention provides a computer-readable storage medium storing computer program instructions. When executed by a processor, the computer program instructions apply controlled impacts to the brain of a mouse to cause brain injury and introduce controlled trauma to the chest and abdomen to simulate thoracic and abdominal injuries. The physiological parameters of the injured mouse are monitored in real time using a sensing device, and physiological data reflecting the effects of brain and chest / abdominal injuries are collected. These physiological parameters include one or more of intracranial pressure, blood pressure, and respiratory rate. The physiological data is input into an artificial intelligence algorithm model for time-series analysis and cross-system data fusion to assess the severity of the injury in the mouse in real time and generate corresponding assessment results. The assessment results are used to classify the severity of the injury and establish a corresponding mouse model of brain injury combined with multiple chest and abdominal injuries.

[0121] It should be understood that the specific features, operations, and details described above regarding the method of the present invention can also be similarly applied to the apparatus and system of the present invention, or vice versa. Furthermore, each step of the method of the present invention described above can be performed by a corresponding component or unit of the apparatus or system of the present invention.

[0122] It should be understood that the various modules / units of the device of the present invention can be implemented wholly or partially through software, hardware, firmware, or a combination thereof. Each module / unit can be embedded in the processor of a computer device in hardware or firmware form or independent of the processor, or it can be stored in the memory of a computer device in software form for the processor to call to execute the operation of each module / unit. Each module / unit can be implemented as an independent component or module, or two or more modules / units can be implemented as a single component or module.

[0123] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores computer instructions executable by the processor, which, when executed by the processor, instruct the processor to perform steps of the methods of embodiments of the present invention. The computer device can be broadly categorized as a server, terminal, or any other electronic device with the necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, memory, network interface, communication interface, etc., connected via a system bus. The processor of the computer device can be used to provide the necessary computing, processing, and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system, computer programs, etc. The internal memory can provide an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface and communication interface of the computer device can be used to connect and communicate with external devices via a network. When the computer program is executed by the processor, it performs the steps of the methods of the present invention.

[0124] This invention can be implemented as a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, causes the steps of the methods of embodiments of the invention to be performed. In one embodiment, the computer program is distributed across multiple network-coupled computer devices or processors, such that the computer program is stored, accessed, and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, may be executed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations may be executed by one or more computer devices or processors, and one or more other method steps / operations may be executed by one or more other computer devices or processors. One or more computer devices or processors may execute a single method step / operation, or execute two or more method steps / operations.

[0125] It will be understood by those skilled in the art that the method steps of the present invention can be performed by a computer program instructing related hardware, such as a computer device or processor. The computer program may be stored in a non-transitory computer-readable storage medium, and its execution causes the steps of the present invention to be performed. Depending on the context, any references herein to memory, storage, databases, or other media may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0126] The technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification, provided that such combination does not contain contradictions.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing an artificial intelligence dynamic evaluation mouse polytrauma model, characterized in that, include: Based on mice that have undergone sensor implantation, the implantation sites of the sensor include the brain and the chest and abdomen. The mice have suffered brain damage due to impact to the skull and controlled trauma to the chest and abdomen. The physiological parameters of the injured mice are monitored in real time by a sensing device, and physiological data reflecting the effects of brain and chest and abdomen injuries are collected. The physiological parameters include one or more of intracranial pressure, blood pressure and respiratory rate. The physiological data is input into an artificial intelligence algorithm model for time-series analysis and cross-system data fusion to assess the severity of injury in the injured mouse in real time and generate corresponding assessment results. The assessment results were used to classify the severity of the injury, and a corresponding mouse model of multiple injuries to the brain and chest and abdomen was established accordingly. Also includes: Before injury, mice were subjected to miniature CT scans to obtain individual anatomical atlases of mice, including skull thickness, brain volume, and thoracic structure. The impact location and angle of the traumatic brain injury are adjusted based on the anatomical atlas to reduce the injury dispersion caused by individual differences. The propagation path of mechanical stress from the thoracic cavity to the brain is simulated using a finite element model, and the parameters of thoracic and abdominal injuries are calibrated accordingly to achieve the predetermined degree of secondary brain injury.

2. The method for constructing a mouse model for dynamic evaluation of multiple injuries using artificial intelligence as described in claim 1, characterized in that, Also includes: The intracranial pressure, respiratory rate, bleeding volume, and blood lactate collected by the sensing device are input into the artificial intelligence model as multimodal time-series data. The time-series data were analyzed using a recurrent neural network to identify the correlations between key events and different physiological parameters during the injury process; Output real-time updated severity scores for multiple injuries and / or early warning signals.

3. An artificial intelligence-based dynamic assessment system for constructing a mouse model of multiple injuries, characterized in that, include: A monitoring module is used to monitor the physiological parameters of mice that have undergone sensor implantation, with the implantation sites including the cranium and chest / abdomen. The mice have suffered brain damage due to impact to the skull and controlled trauma to the chest / abdomen. The module collects physiological data reflecting the effects of cranial and chest / abdomen injuries in real time through the sensor. The physiological parameters include one or more of intracranial pressure, blood pressure, and respiratory rate. The analysis module is used to input the physiological data into an artificial intelligence algorithm model, perform time-series analysis and cross-system data fusion, assess the severity of the injury in the injured mouse in real time, and generate corresponding assessment results. The grading module is used to grade the severity of the injury based on the assessment results, and to establish a corresponding mouse model of multiple injuries to the brain and chest and abdomen. The system is also used to perform a miniature CT scan on mice before injury to obtain an individual anatomical atlas of the mice, including skull thickness, brain volume, and thoracic cavity structure; and to adjust the impact position and angle of the craniocerebral injury based on the anatomical atlas to reduce the injury dispersion caused by individual differences. The propagation path of mechanical stress from the thoracic cavity to the brain is simulated using a finite element model, and the parameters of thoracic and abdominal injuries are calibrated accordingly to achieve the predetermined degree of secondary brain injury.

4. The artificial intelligence dynamic evaluation mouse multiple injury model construction system as described in claim 3, characterized in that: The monitoring module, the analysis module, and the grading module are controlled to execute the artificial intelligence dynamic assessment method for constructing a mouse multiple injury model as described in claim 2.

5. An electronic device, characterized in that, include: Communication interface, processor, memory; The memory is used to store program instructions, which, when executed by the processor that is connected to the memory via the communication interface, enable the electronic device to implement the artificial intelligence dynamic assessment mouse multiple injury model construction method according to any one of claims 1 to 2.

6. A computer-readable storage medium having program instructions stored thereon, characterized in that, When the program instructions are executed by a computer, the computer enables the computer to implement the artificial intelligence dynamic assessment method for constructing a mouse multiple injury model as described in any one of claims 1 to 2.

Images