AI-based mouse craniocerebral thoracico-abdominal combined injury dynamic model preparation method and system

Abstract

The invention discloses a preparation method and system of a mouse craniocerebral thoracico-abdominal combined injury dynamic model based on AI, and belongs to the technical field of biomechanical injury. The method comprises the steps that impact is applied to a mouse skull, and the impact is conducted along an organ synergistic conduction chain so as to induce the craniocerebral thoracico-abdominal combined injury of the mouse; in the impact applying process, multi-modal physiological data are synchronously collected; and inputting the collected multi-modal physiological data into an AI analysis model, analyzing the injury mechanism of the craniocerebral thoracic-abdominal combined injury, and establishing a dynamic model based on an analysis result. According to the technical scheme provided by the invention, high-simulation modeling of multi-organ cascade injury is realized by constructing the organ synergistic conduction chain from the brain to the thoracic cavity; in combination with multi-modal physiological data synchronous acquisition and an AI analysis model, injury time sequence characteristics can be accurately extracted, a causal path of a local injury initiation system response is established, and the precision and practicability of compound injury mechanism prediction are improved.

Description

Technical Field

[0001] This invention relates to the technical field of biomechanical injury, and in particular to an AI-based method and system for preparing a dynamic model of combined craniocerebral, thoracic and abdominal injuries in mice. Background Technology

[0002] In the field of biomechanical injury research, constructing high-precision complex injury models is a crucial foundation for studying the interactive mechanisms of multi-organ injuries. Among these, craniocerebral, thoracic, and abdominal complex injuries, as a typical type of systemic trauma, involve a cascade of physiological processes, including autonomic dysfunction triggered by brain tissue damage, respiratory regulation disorders, and the release of inflammatory factors. Currently widely used models, such as the explosive shock wave method, the pneumatic impact method, and the free-fall method, suffer from significant controllability and repeatability issues. For example, an impact angle deviation exceeding 2° can lead to differences in organ damage severity in mice exceeding 30%, while conventional mechanical actuation methods, such as the Harvard PAPM model, exhibit impact force errors as high as ±15%, poor repeatability, and a coefficient of variation reaching 28%. Furthermore, traditional models are mostly single-point sensing structures, capable of collecting only local pressure or motion signals, making it difficult to achieve simultaneous monitoring of cross-organ parameters such as electroencephalogram (EEG), blood oxygenation, and thoracic pressure.

[0003] In terms of injury mechanism analysis, existing finite element simulations (such as the Johns Hopkins FEA model) can numerically simulate tissue deformation caused by impact, but they rely on simplified geometric modeling, making it difficult to accurately predict microscopic injury processes such as axonal fracture, and they fail to effectively integrate biochemical response information (such as changes in the inflammatory factor IL-6). While multimodal data fusion platforms have introduced synchronous acquisition approaches to achieve cross-modal alignment of data such as EEG, pressure, and blood oxygenation, and have preliminarily established injury causal chains (such as "traumatic brain injury - autonomic nervous system dysfunction - pleural pressure change"), they still suffer from insufficient biological adaptation. For example, industrial-grade sampling cycles cannot meet the millisecond-level requirements of physiological signals, and there is a lack of dynamic calibration mechanisms for sensor drift and physiological interference. Therefore, there is an urgent need for an integrated small animal complex injury modeling method with impact controllability, multi-organ coupling response capability, cross-modal data synchronization, and AI mechanism analysis capabilities to improve the physiological realism and predictive ability of experimental models. Summary of the Invention

[0004] This invention provides a method and system for preparing a dynamic model of combined craniocerebral, thoracic and abdominal injuries in mice based on AI, which can realize multi-organ collaborative injury modeling and AI mechanism prediction, improve the accuracy of injury reproduction and physiological reasoning ability, and enhance the reliability of model extrapolation.

[0005] According to a first aspect of the present invention, a method for preparing an AI-based dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice is provided, the method comprising: An impact was applied to the skull of a mouse, causing the impact to be transmitted along the organ-coordinated conduction chain to induce a combined craniocerebral, thoracic, and abdominal injury in the mouse. The organ-coordinated conduction chain was transmitted sequentially through the skull, cerebrospinal fluid, spinal cord, and diaphragm to the thoracic cavity. During the application of the impact, multimodal physiological data are collected simultaneously, including one or more of the following: electroencephalogram (EEG) signals, intrathoracic pressure signals, and blood oxygenation signals. The collected multimodal physiological data are input into the AI ​​analysis model to analyze the injury mechanism of the combined craniocerebral, thoracic and abdominal injuries, and a dynamic model is established based on the analysis results.

[0006] In one embodiment, applying an impact to the mouse skull to conduct the impact along the organ-co-transmission chain includes: The electromagnetic coil is controlled to generate a pulsed magnetic field, which simultaneously drives the pneumatic cavity to release compressed gas, generating a directional impact. The output direction of the impact is adjusted in real time based on the feedback signal from the gyroscope, so that the impact is transmitted along the organ-coordinated conduction chain.

[0007] In one embodiment, the synchronous acquisition of multimodal physiological data includes one or more of electroencephalogram (EEG) signals, intrathoracic pressure signals, and blood oxygenation signals, including: The system uses a flexible implantable sensor array to acquire real-time signals of intracranial pressure changes, pleural gas pressure fluctuations, and blood oxygen concentration. The brain, chest, and blood data are processed synchronously across channels using a millisecond-level timestamp protocol to form multimodal physiological data with a unified time reference.

[0008] In one embodiment, the real-time acquisition of intracranial pressure changes and pleural gas pressure fluctuations via a flexible implantable sensor array includes: Nanoprobes based on the principle of plasmon resonance were implanted in the brain parenchyma of mice to obtain intracranial pressure signals that reflect changes in local tissue elasticity. A fiber optic sensor network is deployed in the chest and abdomen region to collect stress response and pleural gas pressure fluctuations in three-dimensional space.

[0009] In one embodiment, inputting the collected multimodal physiological data into the AI ​​analysis model includes: Extract temporal variation features from electroencephalogram (EEG), intrathoracic pressure (IP), and blood oxygenation (BO) signals; Based on the temporal variation characteristics, a multidimensional feature vector representing the response relationship between organs is constructed; Based on the multidimensional feature vector, an AI analysis model generates causal correlation outputs for predicting the evolution of damage mechanisms.

[0010] In one embodiment, it also includes: The causal correlation output includes a dynamic path diagram that starts from changes in local shear stress in the cranium and sequentially correlates the release of inflammatory factors, abnormal autonomic nerve function, and disordered regulation of intrathoracic pressure. This path is used to assist in establishing a mathematical model of the mechanism of cross-organ injury propagation.

[0011] According to a second aspect of the present invention, an AI-based dynamic model preparation system for combined craniocerebral, thoracic, and abdominal injuries in mice is provided, comprising: An impact module is used to apply an impact to the skull of a mouse, so that the impact is transmitted along the organ-coordinated conduction chain to induce a combined craniocerebral, thoracic and abdominal injury in the mouse. The organ-coordinated conduction chain is transmitted sequentially through the skull, cerebrospinal fluid, spinal cord and diaphragm to the thoracic cavity. The acquisition module is used to simultaneously acquire multimodal physiological data during the application of impact, including one or more of electroencephalogram (EEG) signals, intrathoracic pressure signals, and blood oxygenation signals. The analysis module is used to input the collected multimodal physiological data into the AI ​​analysis model to analyze the injury mechanism of the combined craniocerebral, thoracic and abdominal injuries, and to establish a dynamic model based on the analysis results.

[0012] In one embodiment, the impact module, the acquisition module, and the analysis module are controlled to execute any of the above-described AI-based methods for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice.

[0013] According to a third aspect of the present invention, an electronic device is provided, comprising: a communication interface, a processor, and a memory; The memory is used to store program instructions, which, when executed by the processor connected to the memory via the communication interface, implement any of the above-described AI-based methods for preparing dynamic models of combined craniocerebral, thoracic, and abdominal injuries in mice.

[0014] 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 a computer), implement any of the above-described methods for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice based on AI.

[0015] In summary, this invention provides an AI-based method and system for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice. The method includes: applying an impact to the skull of a mouse, causing the impact to be conducted along the organ-coordinated conduction chain to induce combined craniocerebral, thoracic, and abdominal injuries in the mouse. The organ-coordinated conduction chain is conducted sequentially through the skull, cerebrospinal fluid, spinal cord, and diaphragm to the thoracic cavity. During the application of the impact, multimodal physiological data are simultaneously collected, including one or more of electroencephalogram (EEG) signals, thoracic pressure signals, and blood oxygenation signals. The collected multimodal physiological data are input into an AI analysis model to analyze the injury mechanism of the combined craniocerebral, thoracic, and abdominal injuries, and a dynamic model is established based on the analysis results. The technical solution of this application realizes the organ-coordinated injury path from the skull to the thoracic cavity through a simulated explosion three-dimensional vector impact mechanism, which solves the problems of uncontrollable impact and fragmented organ response in existing complex injury models; it introduces a multimodal physiological sensor array and synchronous acquisition mechanism to improve the alignment accuracy of cross-organ data; and it integrates an AI analysis model to realize dynamic modeling of the causal chain between local injury and systemic physiological response, which significantly enhances the accuracy and interpretability of injury mechanism prediction and improves the extrapolation value of animal models in clinical mechanism research.

[0016] 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.

[0017] 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

[0018] 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.

[0019] Figure 1 A flowchart illustrating an AI-based method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice, provided as an embodiment of the present invention; Figure 2 A flowchart illustrating another AI-based method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice, provided as an embodiment of the present invention; Figure 3 A flowchart illustrating another AI-based method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice, provided as an embodiment of the present invention; Figure 4A flowchart illustrating another AI-based method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice, provided as an embodiment of the present invention; Figure 5 A flowchart illustrating another AI-based method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice, provided as an embodiment of the present invention; Figure 6 A structural diagram of an AI-based dynamic model preparation system for combined craniocerebral, thoracic, and abdominal injuries in mice, provided for an embodiment of the present invention; Figure 7 This is a structural diagram of an electronic device provided as an embodiment of the present invention. Detailed Implementation

[0020] 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.

[0021] 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.

[0022] like Figure 1 As shown, this invention provides an AI-based method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice. This AI-based method includes: In step S11, an impact is applied to the skull of a mouse, causing the impact to be transmitted along the organ-coordinated conduction chain to induce a combined craniocerebral, thoracic, and abdominal injury in the mouse. The organ-coordinated conduction chain is transmitted sequentially through the skull, cerebrospinal fluid, spinal cord, and diaphragm to the thoracic cavity. In step S12, during the application of the impact, multimodal physiological data are collected simultaneously, including one or more of electroencephalogram (EEG) signals, intrathoracic pressure signals, and blood oxygenation signals. In step S13, the collected multimodal physiological data is input into the AI ​​analysis model to analyze the injury mechanism of the combined craniocerebral, thoracic and abdominal injuries, and a dynamic model is established based on the analysis results.

[0023] In one embodiment, existing small animal complex injury models have significant limitations in terms of preparation accuracy and system synergy, mainly in three aspects. First, in terms of impact parameter control, traditional models such as free-fall or explosive impact devices generally rely on mechanical open-loop control, which cannot achieve precise adjustment of impact direction and energy. Experiments have shown that an impact angle deviation of more than 2° can lead to differences in the degree of damage to multiple organs exceeding 30%, seriously affecting the consistency of experimental results. Taking the typical Harvard PAPM model as an example, its impact force error is as high as ±15%, resulting in poor repeatability of organ damage (coefficient of variation CV reaches 28%). Second, existing models generally lack the integrity of the organ synergistic conduction chain, often using a single site as the impact target (such as the CCI cranial model or the thoracoabdominal compression method), failing to construct a linkage pathway from skull-cerebrospinal fluid-spinal cord-diaphragm-thoracic cavity, making it difficult to simulate the cascade response of brain impact-induced autonomic nervous system disorder and subsequent changes in thoracic cavity pressure. Third, existing systems for animal anesthesia control are generally static and single-point settings, without constructing an anesthesia depth regulation mechanism based on EEG feedback, which leads to distortion of the physiological response of key organs (such as myocardium), and the inhibition rate can even exceed 40%.

[0024] At the mechanistic modeling level, existing predictive models are still mainly based on static geometric modeling and single-modal data-driven approaches, resulting in limited accuracy across scales and species. For example, typical finite element analysis (FEA) methods often use simplified geometries such as spheres or cylinders to represent complex brain tissue structures, making it difficult to capture axonal fractures induced by shear stress in high-gradient regions such as cerebral sulci and gyri, thus leading to errors exceeding 40% in predicting microscopic damage. Simultaneously, existing platforms do not temporally integrate impact mechanics parameters with biochemical responses (such as the expression of inflammatory factors IL-6 and TNF-α), resulting in a disruption of the causal chain of "mechanical impact-cytopathic effects-organ dysfunction." Furthermore, existing systems have not established parameter adaptation mechanisms for species extrapolation. Significant differences exist between mice and humans in key indicators such as cerebral blood flow regulation and physiological thresholds (e.g., the cerebral blood flow regulation threshold in mice is 22% higher than in humans). Without transfer calibration and dynamic calibration, the failure rate of clinical translation of models will increase dramatically, with over 80% of extrapolation experiments performing poorly in real-world human scenarios.

[0025] The main technical shortcomings of existing models can be summarized in four dimensions. First, the accuracy of impact parameter control is insufficient, stemming from the lack of closed-loop calibration capability in the drive system. Second, the ability to model organ collaboration is weak, due to the lack of conduction pathway structure. Third, the accuracy of AI damage identification is low, limited by the difficulty of traditional single-modality CNN models in identifying deep organ damage. Fourth, the accuracy of mechanism prediction is biased, rooted in the simplification of biomechanical modeling and the fragmentation of multi-omics information.

[0026] In current experimental animal model research, constructing a complex injury model that controllably simulates the combined craniocerebral, thoracic, and abdominal injury mechanism is of great significance for revealing the physiological processes of multi-organ interactions. By applying impact to the mouse skull, starting with the transmission of the impact along the organ-coordinated conduction chain, the path dependence and structural synergy of injury application were established. Traditional models often rely on a single impact method (such as pneumatic or free fall), resulting in a lack of controllability in the force transmission process. Deviations in the impact direction or angle can cause inconsistencies in the responses between organs, thus affecting experimental repeatability and the validity of mechanism deduction. By limiting the initial impact point to the skull and clarifying that the conduction chain sequentially includes cerebrospinal fluid, spinal cord, diaphragm, and thoracic cavity, this model was developed.

[0027] Furthermore, unlike the physical separation of "thoracic-abdomen / craniosynostosis" in the existing PAPM model from Harvard Medical School, this model simulates the complete process of actual external force transmission from the head to the chest and abdomen through a three-dimensional vector impact mechanism. For example, concussions often occur concurrently with sudden changes in intrathoracic pressure, and there is a chain reaction between the two in terms of time and response. By setting specific impact directions and structural constraints, this linkage is realistically reproduced within the model. For instance, when the impact is applied by the skull, the cerebrospinal fluid acts as a buffer to transmit pressure to the spinal cord, and then affects the thoracic cavity volume via the diaphragm. This pathway can trigger abnormalities in the autonomic nervous system regulation mechanism, thereby causing respiratory dysfunction.

[0028] During this structured shock experiment, multimodal physiological data were simultaneously acquired. These multimodal signals, including electroencephalogram (EEG) signals, intrathoracic pressure fluctuations, and blood oxygen concentration, are key indicators reflecting the interaction between the central nervous system, respiratory and circulatory systems, and oxygenation. In contrast, traditional physiological monitoring often employs single-channel recording methods (such as single-point pleural pressure monitoring), failing to reveal cross-organ dynamic correlations. By implanting a flexible sensor array in mice, data from different sites and physiological dimensions were simultaneously acquired. Using a millisecond-level timestamp protocol for cross-channel alignment, various time-series signals could be uniformly mapped onto a standardized response time axis. For example, in a specific shock experiment, the system accurately pinpointed the occurrence of high-frequency EEG oscillations 120 ms after the shock, the increase in intrathoracic pressure approximately 350 ms, and the lag in blood oxygen decrease to 600 ms, thereby establishing a three-stage physiological cascade of "nervous-respiratory-oxygenation."

[0029] Multimodal data is processed by artificial intelligence (AI) analysis models and transformed into causal outputs at the mechanism level. The introduction of AI analysis models overcomes the limitations of traditional biostatistical methods in handling multivariate, nonlinear, and temporally coupled problems. AI analysis models not only extract characteristic parameters from single-source signals such as EEG, pleural pressure, and blood oxygenation, but also fuse them into multidimensional interaction vectors between organs, thereby identifying potential pathways inducing changes in pleural pressure due to traumatic brain injury. For example, the model can learn a chain-like causal structure of "peak shear stress - release of inflammatory factors (such as IL-6) - autonomic instability - abnormal diaphragmatic reflex - changes in pleural pressure." This structure not only originates from data fitting but also integrates known physiological knowledge graphs, possessing high interpretability. Furthermore, through AI analysis models, quantifiable injury risk scores and organ function deterioration trend prediction curves can also be output as clinically translatable indicators.

[0030] The causal chain output generated by the AI ​​analysis model can be further transformed into a complete dynamic model. Unlike static damage assessment, the dynamic model focuses on the damage development process, the timing of inter-organ responses, and feedback loops. In practical applications, the model can predict whether a certain type of shear stress input will induce a surge in serum inflammatory factors after 6 hours, or lead to a decrease in pulmonary interstitial elasticity within 12 hours. Furthermore, this dynamic model provides a foundation for cross-species extrapolation and can be integrated into a human trauma database. Transfer learning can be used to refine the model parameters, improving its interpretability and reliability in clinical research.

[0031] This embodiment proposes a composite injury dynamic simulation system integrating structural control, data-driven approaches, and intelligent modeling. It mainly includes a high-precision, repeatable injury preparation module, a multimodal-driven mechanism prediction platform, and a cross-species adapted mechanism transfer framework. In model construction, a biomimetic multi-directional mechanical generator driven by electromagnetic-pneumatic composites is used to achieve directional impact on the mouse skull. This impact is controlled via a gyroscope feedback system with closed-loop angle control, achieving an accuracy of ±0.1°, effectively avoiding the organ damage variation (exceeding 30%) caused by impact deviations exceeding 2° in traditional free impact devices. To simulate multi-organ coupled injury pathways, an organ-coordinated conduction chain structure from skull to cerebrospinal fluid to spinal cord to diaphragm to thoracic cavity is designed. Referring to the thoracic-abdominal mixed respiratory mechanics mechanism, controllable reproduction of head-chest cascade injuries is achieved. Furthermore, integrating an EEG signal monitoring module into animal experiments allows for dynamic adjustment of anesthetic concentrations (such as isoflurane), forming a closed loop of anesthesia-physiological state coupling. This avoids interference from anesthetic inhibition on the physiological responses of key organs (such as the myocardium), thereby improving the stability and biological realism of the model output.

[0032] In terms of mechanism modeling, the platform utilizes a multimodal signal acquisition system (including EEG, intrathoracic pressure, and blood oxygenation) to achieve high-resolution tracking of the systemic physiological evolution following local injury and constructs a cross-scale biomechanical simulation engine. At the macroscopic level, this simulation system reconstructs complex structures such as brain sulci and alveoli based on μCT images, avoiding the simplification errors of organ geometry in traditional finite element models. At the microscopic level, it introduces molecular dynamics modeling techniques to simulate the axonal microtubule fracture process induced by impact stress. To establish a dynamic link between physical stress and biochemical reactions, the platform introduces a multi-omics coupling mechanism, mapping shock wave parameters to real-time acquired changes in inflammatory factor (such as IL-6) concentrations, forming a causal mathematical model of "mechanical stress - mitochondrial rupture - inflammatory factor storm - multiple organ failure," enhancing the predictive depth and biological explanatory power of the injury mechanism.

[0033] To address the issue of species physiological differences in clinical extrapolation from existing animal models, a cross-species mechanism transfer framework was designed. By importing human trauma databases (such as case data of traumatic brain injury combined with chest and abdominal injuries), the structural differences between mice and humans in key physiological parameters such as cerebral blood flow regulation threshold and thoracic elasticity were systematically compared and analyzed. Transfer learning algorithms were used to dynamically adjust mouse model parameters, effectively eliminating species-specific biases in response thresholds, inflammation rates, and organ compensatory capabilities, resulting in higher clinical translation reliability of the model's predictions. Experimental verification shows that this framework can reduce mechanism prediction errors from over 40% in traditional methods to less than 15%, demonstrating significant advantages in extrapolating animal experimental results to clinical mechanisms. In summary, this invention constructs a complete technical path of "controllable impact - organ response - AI mechanism modeling - clinical extrapolation," from mechanical structure control and signal linkage modeling to cross-species correction, overcoming key technical bottlenecks in accuracy, synergy, and conversion rate of existing models.

[0034] By integrating three major breakthroughs—multimodal technology, cross-organ synergistic mechanisms, and dynamic species adaptation—this invention achieves a significant leap forward in damage preparation accuracy, mechanism prediction depth, and clinical translation reliability. A horizontal comparison with existing technologies is shown in Table 1 below.

[0035] Table 1

[0036] To verify the feasibility and performance advantages of the AI-based mouse craniocerebral-thoracic-abdominal complex injury dynamic model preparation system proposed in this invention, this study conducted systematic animal experiments and model control tests. Fifty C57BL / 6 mice were used as experimental subjects. The experimental group used the electromagnetic-pneumatic composite impact system proposed in this invention to construct a complex injury model with a coordinated organ conduction chain of "skull → cerebrospinal fluid → spinal cord → diaphragm → thoracic cavity"; the control group used the Harvard PAPM model (pure mechanical impact). In the experimental group, a three-dimensional vector impact was applied, with the lateral impact angle to the cranium set at 30°±0.1° and the impact pressure in the thoracic and abdominal regions at 50 kPa. A multimodal sensor array was pre-implanted in each mouse to record real-time changes in brain parenchymal shear force, thoracic cavity pressure response, and synchronous physiological signal data. Quantitative analysis was performed using the evaluation method of a modified compression injury model. Specific data are shown in Table 2 below.

[0037] Table 2

[0038] To ensure the stable and reliable physiological state of experimental animals during injury application, an anesthesia-physiology coupling control module was integrated. This module dynamically adjusts the concentration of the inhaled anesthetic isoflurane based on changes in mouse electroencephalogram (EEG) signals, thereby maintaining a stable anesthesia level and minimizing interference with the myocardium and circulatory system. Experimental results showed that after adopting the anesthesia control strategy of this invention, the inhibition rate of myocardial contractility in mice significantly decreased from >40% commonly seen in traditional models to <8% (p<0.01), effectively eliminating the physiological response distortion caused by excessive or insufficient anesthesia, and ensuring the stability and reproducibility of the injury results.

[0039] Regarding the performance of the multimodal sensing array, the experiment employed a nanoprobe based on the principle of plasmon resonance to monitor changes in the elastic modulus of pulmonary interstitial tissue, achieving an accuracy of 0.1 kPa. This was combined with a micro-biochip to capture changes in the concentration of the inflammatory factor IL-6 in the blood, with a sampling frequency of 10 Hz. Experimental results showed that the system achieved an accuracy of 96.3% in identifying intracranial hemorrhage (hematoma), significantly outperforming the traditional MIT system's 65%. In identifying pulmonary contusions, the system could detect a minimum hemorrhage size of 0.2 mm, while the lower resolution limit of traditional MRI equipment under similar conditions was 2 mm, demonstrating the significant advantage of this system in the accuracy of deep injury identification.

[0040] In terms of artificial intelligence analysis, a dual-channel AI analysis model was constructed, simultaneously inputting mouse CT image data and structured medical text semantics (e.g., "axonal rupture → elevated IL-6"), fusing image features and physiological semantics. The CrossAttention mechanism was used to fuse multi-source features, outputting a composite injury score and damage level prediction results. Test results showed that the model achieved a deep injury grading accuracy of 92.7%, while the traditional CNN model without semantic information fusion only achieved 78.4%. Furthermore, the model successfully correlated the peak intracranial shear force (>15 kPa) with the upward trend of serum IL-6 concentration 6 hours later, with a correlation coefficient as high as r=0.91 (p<0.001), validating the ability to model the physiological causal chain of "local shear injury → systemic inflammatory response".

[0041] To address the issue of cross-species extrapolation, the system introduces a dynamic transfer learning mechanism to humanize the parameters of the mouse model. In the experiment, case data of "traumatic brain injury complicated by intraperitoneal hemorrhage" were retrieved from a human traffic accident database, and physiological response features were extracted for model calibration. Based on the differences between humans and mice in key parameters such as the cerebral blood flow regulation threshold (relatively higher in mice), the model automatically completes structural mapping and response adjustment. Taking the cerebral blood flow regulation threshold as an example, after the system down-adjusted relevant parameters in the mouse model by approximately 22%, key indicators such as the inflammatory response time window and changes in carboxyhemoglobin levels verified the feasibility and accuracy of cross-species mechanism transfer. Specific data are shown in Table 3 below.

[0042] Table 3

[0043] The technical solution in this embodiment realizes the organ-coordinated injury path from the skull to the thoracic cavity through a biomimetic three-dimensional impact mechanism, solving the problems of uncontrollable impact and fragmented organ response in existing complex injury models; it introduces a multimodal physiological sensor array and synchronous acquisition mechanism to improve the alignment accuracy of cross-organ data; and it integrates an AI analysis model to realize dynamic modeling of the causal chain between local injury and systemic physiological response, significantly enhancing the accuracy and interpretability of injury mechanism prediction and improving the extrapolation value of animal models in clinical mechanism research.

[0044] In one embodiment, such as Figure 2 As shown, step S11 includes the following steps S21-S22: In step S21, the electromagnetic coil is controlled to generate a pulsed magnetic field and simultaneously drive the pneumatic cavity to release compressed gas, generating a directional impact; In step S22, the output direction of the impact is adjusted in real time according to the gyroscope feedback signal so that the impact is transmitted along the organ-coordinated conduction chain.

[0045] In one embodiment, applying an impact to the mouse skull and transmitting the impact along the organ-coordinated conduction chain essentially embodies a multi-source mechanical excitation mechanism with directional control capabilities. Its core lies in achieving cascaded mechanical conduction from the skull down to multiple downstream organs through a structurally controllable energy input method, ensuring precise and consistent impact angles. By controlling an electromagnetic coil to excite a pulsed magnetic field and simultaneously driving a pneumatic cavity to release compressed gas, a composite mechanical impact source is constructed. This source utilizes electromagnetic drive for rapid response and initial directional positioning, combined with pneumatic release to enhance the impact amplitude and effective energy transmission range, thereby generating a directional shock wave with three-dimensional vector characteristics. Compared to traditional single-force-source mechanical impact methods, this design, through a dual-channel coordinated drive mechanism combining electromagnetic and pneumatic forces, significantly improves the flexibility and simulation accuracy of impact output, making it particularly suitable for simulating multi-directional, multi-organ-linked injury processes in complex injury scenarios such as explosions or collisions.

[0046] A closed-loop calibration mechanism that adjusts the impact output direction in real time based on gyroscope feedback signals solves the problems of poor experimental repeatability and large damage errors caused by unstable or uncontrollable impact direction in existing technologies. In actual operation, mice are small in size and have a delicate structure. Even a deviation of 1-2 degrees in the impact angle can cause the impact path to deviate from the originally set organ-coordinated conduction chain of "skull-cerebrospinal fluid-spinal cord-diaphragm-thoracic cavity", ultimately leading to significant differences in the type and severity of damage among different experimental individuals. Through the gyroscope feedback device, the angular deviation between the current driving device and the spatial posture of the mouse's head can be measured in real time before the impact is applied. The system then makes fine adjustments based on this to ensure that the impact is applied along the set conduction chain direction, effectively improving the consistency and reproducibility of model preparation.

[0047] For example, when constructing a model of brain injury linked to thoracic pressure changes, if the impact direction is slightly downward, it may inadvertently injure neck muscles, inducing non-targeted injury responses; if it is upward, the brain tissue will not receive sufficient force, failing to effectively trigger subsequent physiological causal chains (such as thoracic pressure abnormalities caused by autonomic nervous system abnormalities). This design, by introducing real-time gyroscope control, can precisely control the impact direction within ±0.1°, ensuring that the impact force is transmitted step-by-step from the skull along a predetermined organ-coordination pathway, accurately reproducing the cascade injury process of "brain-spinal cord-thoracic-abdomen". The controllability of the mechanical path not only improves the biological realism of the complex injury model but also provides a stable and consistent foundation for subsequent multimodal data acquisition, AI mechanism modeling, and physiological causal chain analysis.

[0048] In one embodiment, such as Figure 3 As shown, step S12 includes the following steps S31-S32: In step S31, the changes in intracranial pressure, fluctuations in pleural gas pressure, and blood oxygen concentration signals are acquired in real time through a flexible implantable sensor array. In step S32, the brain, chest, and blood data are processed across channels using a millisecond-level timestamp protocol to form multimodal physiological data with a unified time reference.

[0049] In one embodiment, for data acquisition in a mouse model of combined craniocerebral, thoracic, and abdominal injuries, multimodal physiological data acquisition integrating flexible implantable sensors and a high-precision time synchronization mechanism can ensure the temporal consistency of spatial multi-source signals and the high-precision reconstruction of physiological signals. By deploying a flexible implantable sensor array, signals of intracranial pressure, thoracic pressure, and blood oxygen concentration are collected separately, enabling structured, continuous, and real-time perception of the physiological responses of injured individuals across multiple systems in the "cranial-thoracic-blood" domain. Intracranial pressure reflects intracranial stress levels, thoracic gas pressure reflects changes in respiratory mechanics, and blood oxygen concentration directly reflects systemic oxygen supply imbalance. Compared to traditional independent channel recording methods, this sensor array layout improves the spatiotemporal coverage of signal sources, especially during the dynamic injury induction phase, enabling millisecond-level capture of subtle differences in the coordinated responses of various organs. Furthermore, by introducing a millisecond-level timestamp protocol, data streams across different sites and sensor channels are precisely aligned, constructing a multimodal data set under a unified time reference. For example, if the peak intracranial pressure occurs earlier than changes in intrathoracic pressure and a decrease in blood oxygenation, it may indicate that the damage chain originates in the central nervous system; conversely, if intrathoracic pressure fluctuations precede EEG abnormalities, it may point to a reverse impact mechanism. Traditional data acquisition systems often suffer from signal misalignment due to sampling clock drift or physical isolation of data channels, leading to incomplete or even misinterpreted causal chains in mechanism modeling. By using a millisecond-level unified time reference, comparable temporal logical relationships between various physiological signals are ensured, greatly improving the AI ​​analysis model's ability to discriminate complex physiological pathways. This approach not only achieves concurrent perception of multiple organs / indicators in data acquisition methods but also demonstrates high-precision, high-stability, and high-integration engineering design advantages in temporal processing strategies, providing a data foundation for subsequent AI-assisted modeling, physiological mechanism reconstruction, and cross-species migration applications.

[0050] In one embodiment, such as Figure 4 As shown, step S31 includes the following steps S41-S42: In step S41, a nanoprobe based on the principle of plasmon resonance is implanted in the mouse brain parenchyma to obtain intracranial pressure signals that reflect changes in local tissue elasticity. In step S42, a fiber optic sensor network is deployed in the chest and abdomen region to collect stress response and pleural gas pressure fluctuations in three-dimensional space.

[0051] In one embodiment, to address the issues of accuracy and spatial resolution in physiological signal acquisition during mouse complex injury modeling, a dual-region monitoring mechanism based on an implantable flexible sensor array is proposed, covering the brain parenchyma and thoracic and abdominal regions. By combining microscale resolution with three-dimensional stress detection, the quantitative accuracy and spatial resolution of the injury state are improved. Specifically, by implanting a nanoprobe based on the principle of plasmon resonance into the mouse brain parenchyma, changes in the elastic modulus of the microstructure of local brain tissue under impact can be monitored in real time. This is particularly sensitive in the early stages of nerve injury, reflecting early micro-injury states such as loose cell structure, fluid leakage, or axonal breakage. Due to its ultra-high sensitivity and tissue compatibility, the plasmon resonance nanoprobe can acquire high-precision dynamic curves of intracranial pressure under extremely low energy intervention, avoiding secondary damage or signal distortion caused by the mechanical rigidity of traditional sensors.

[0052] A fiber optic sensor network deployed in the chest and abdomen region is used to sense the three-dimensional stress field distribution and intrathoracic gas pressure fluctuations in real time. Fiber optic sensors possess high spatial resolution and electromagnetic interference resistance, making them suitable for deployment in physiological regions with intense dynamic strain. Especially when simulating impact-induced chest respiratory movement disturbances, lung tissue collapse, or increased abdominal pressure, the fiber optic network can accurately report physical characteristics such as stress concentration areas, fluctuation frequency, and amplitude changes. The collected data can form a spatially distributed vector field, which, combined with brain sensor data, enables cross-regional synchronous tracking from local neural stress to trunk stress response, thereby analyzing the spatial and temporal correlation characteristics of the damage force transmission path and organ response patterns. This fused sensor system solves problems such as blurred brain region signals, lost chest cavity data, and inability to link across regions in traditional models.

[0053] In one embodiment, such as Figure 5 As shown, step S13 includes the following steps S51-S53: In step S51, the temporal variation features of the electroencephalogram (EEG), intrathoracic pressure (IPP), and blood oxygenation signals are extracted; In step S52, a multidimensional feature vector representing the response relationship between organs is constructed based on the temporal change characteristics. In step S53, based on the multidimensional feature vector, a causal correlation output for predicting the evolution of damage mechanisms is generated through an AI analysis model.

[0054] In one embodiment, the key to AI-driven pathological mechanisms in mouse complex injury research lies in constructing inter-organ response relationship vectors based on the temporal characteristics of multimodal physiological data, and using this as a basis to reconstruct the causal relationship of the pathological process. By simultaneously acquiring EEG signals, intrathoracic pressure signals, and blood oxygenation signals, the trends of each physiological indicator over time after the onset of impact injury are obtained, thereby revealing the sequence and correlation strength of dynamic responses between organs. For example, if the EEG signal first shows a synchronous decrease, followed by an increase in the amplitude of intrathoracic pressure fluctuations, and then the blood oxygenation signal drops sharply, it can be inferred that brain dysfunction may be an upstream factor causing intrathoracic pressure regulation disorder and systemic hypoxia. A multidimensional feature vector representing the functional synergy between organs is also constructed. By performing operations such as differencing, frequency domain transformation, and trend fitting on the temporal data, synergistic parameters (such as time delay, response amplitude ratio, and phase synchronization coefficient) between the brain, thoracic, and blood systems are extracted, and these physiological covariates are combined into a vectorized structure and input into the AI ​​analysis model. This model can employ graph attention or Transformer structures from neural networks to highlight the relative weights and interaction patterns of each organ in the overall injury response chain. Taking the brain-thoracic cavity as an example, if multiple experiments show a stable delay relationship (e.g., 300 ms) between the peak shear stress and the increase in intrathoracic pressure, the model can adaptively strengthen the weights of this causal pathway and embed it into the overall mechanism map.

[0055] The AI ​​analysis model's final output not only predicts injury trends (such as future changes in a certain indicator value), but also generates cross-organ causal chains, expressed in the form of a path diagram. For example, the model can identify a chain reaction starting from "increased local shear stress in the brain," through "increased concentrations of inflammatory factors such as IL-6," "decreased HRV parameters in the autonomic nervous system," and finally "imbalance in intrathoracic pressure regulation," and express its dynamic evolution path using a graph structure. This transforms the traditional "injury-outcome" research paradigm of complex injuries into a "stress-response-intervention" mechanism reasoning framework, improving the interpretability and operability of injury prediction.

[0056] By combining the path diagrams output by the AI ​​analysis model with the physiological coupling equations between organs, a differential expression model with time / space as variables is formed. This theoretically describes how damage spreads from the nervous system to the respiratory system, and subsequently affects the circulatory system. For example, an equation for the release rate of inflammatory factors can be constructed based on the rate of change of brain shear stress, and then combined with a model of changes in pleural gas exchange parameters to achieve cascade simulation of the mechanism. This mathematical model not only facilitates simulation optimization under animal experimental conditions, but also allows for adjustment of the parameter structure in future cross-species migration, supporting extrapolation modeling of trauma mechanisms in other species.

[0057] In one embodiment, Figure 6 This is a block diagram illustrating an AI-based dynamic model preparation system for combined craniocerebral, thoracic, and abdominal injuries in mice, according to an exemplary embodiment. Figure 6 As shown, the AI-based mouse craniocerebral-thoracic-abdominal complex injury dynamic model preparation system includes an impact module 61, an acquisition module 62, and an analysis module 63.

[0058] The impact module 61 is used to apply an impact to the skull of a mouse, so that the impact is transmitted along the organ-coordinated conduction chain to induce a combined craniocerebral, thoracic and abdominal injury in the mouse. The organ-coordinated conduction chain is transmitted sequentially through the skull, cerebrospinal fluid, spinal cord and diaphragm to the thoracic cavity. The acquisition module 62 is used to simultaneously acquire multimodal physiological data during the application of impact, the multimodal physiological data including one or more of electroencephalogram signals, intrathoracic pressure signals and blood oxygenation signals; The analysis module 63 is used to input the collected multimodal physiological data into the AI ​​analysis model to analyze the injury mechanism of the combined craniocerebral, thoracic and abdominal injuries, and to establish a dynamic model based on the analysis results.

[0059] The impact module 61, the acquisition module 62, and the analysis module 63 included in the block diagram of the AI-based mouse craniocerebral-thoracic-abdominal complex injury dynamic model preparation system are controlled to execute the AI-based mouse craniocerebral-thoracic-abdominal complex injury dynamic model preparation method described in any of the above embodiments.

[0060] like Figure 7 As shown, the present invention provides an electronic device 700, which includes: a communication interface, a processor 701, and a memory 702; The memory 702 stores program instructions. When executed by the processor 701, which is connected to the memory 702 via the communication interface, the program instructions apply an impact to the mouse skull, causing the impact to be conducted along the organ-coordinated conduction chain to induce a combined craniocerebral, thoracic, and abdominal injury in the mouse. The organ-coordinated conduction chain is conducted sequentially through the skull, cerebrospinal fluid, spinal cord, and diaphragm to the thoracic cavity. During the application of the impact, multimodal physiological data are collected simultaneously. The multimodal physiological data includes one or more of the following: electroencephalogram (EEG) signals, thoracic pressure signals, and blood oxygenation signals. The collected multimodal physiological data are input into an AI analysis model to analyze the injury mechanism of the combined craniocerebral, thoracic, and abdominal injury, and a dynamic model is established based on the analysis results.

[0061] This invention provides a computer-readable storage medium storing computer program instructions. When executed by a processor, these instructions apply an impact to the skull of a mouse, causing the impact to be transmitted along an organ-coordinated conduction chain to induce a combined craniocerebral, thoracic, and abdominal injury in the mouse. The organ-coordinated conduction chain is transmitted sequentially through the skull, cerebrospinal fluid, spinal cord, and diaphragm to the thoracic cavity. During the application of the impact, multimodal physiological data are simultaneously collected, including one or more of electroencephalogram (EEG) signals, thoracic pressure signals, and blood oxygenation signals. The collected multimodal physiological data are input into an AI analysis model to analyze the injury mechanism of the combined craniocerebral, thoracic, and abdominal injury, and a dynamic model is established based on the analysis results.

[0062] 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 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 system of the present invention.

[0063] It should be understood that the various modules / units of the system 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.

[0064] 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.

[0065] 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.

[0066] 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 (GGPROM), 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.

[0067] 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.

[0068] 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 preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice based on AI, characterized in that, include: An impact was applied to the skull of a mouse, causing the impact to be transmitted along the organ-coordinated conduction chain to induce a combined craniocerebral, thoracic, and abdominal injury in the mouse. The organ-coordinated conduction chain was transmitted sequentially through the skull, cerebrospinal fluid, spinal cord, and diaphragm to the thoracic cavity. During the application of the impact, multimodal physiological data are collected simultaneously, including one or more of the following: electroencephalogram (EEG) signals, intrathoracic pressure signals, and blood oxygenation signals. The collected multimodal physiological data are input into an AI analysis model to analyze the injury mechanism of the combined craniocerebral, thoracic and abdominal injuries, and a dynamic model is established based on the analysis results.

2. The method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice based on AI as described in claim 1, characterized in that, The method of applying an impact to the mouse skull, causing the impact to be transmitted along the organ-coordinated conduction chain, includes: The electromagnetic coil is controlled to generate a pulsed magnetic field, which simultaneously drives the pneumatic cavity to release compressed gas, generating a directional impact. The output direction of the impact is adjusted in real time based on the feedback signal from the gyroscope, so that the impact is transmitted along the organ-coordinated conduction chain.

3. The method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice based on AI as described in claim 1, characterized in that, The simultaneous acquisition of multimodal physiological data includes one or more of the following: electroencephalogram (EEG) signals, intrathoracic pressure signals, and blood oxygenation signals: The system uses a flexible implantable sensor array to acquire real-time signals of intracranial pressure changes, pleural gas pressure fluctuations, and blood oxygen concentration. The brain, chest, and blood data are processed synchronously across channels using a millisecond-level timestamp protocol to form multimodal physiological data with a unified time reference.

4. The method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice based on AI as described in claim 3, characterized in that, The method of acquiring real-time changes in intracranial pressure and fluctuations in pleural gas pressure through a flexible implantable sensor array includes: Nanoprobes based on the principle of plasmon resonance were implanted in the brain parenchyma of mice to obtain intracranial pressure signals that reflect changes in local tissue elasticity. A fiber optic sensor network is deployed in the chest and abdomen region to collect stress response and pleural gas pressure fluctuations in three-dimensional space.

5. The method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice based on AI as described in claim 1, characterized in that, The step of inputting the collected multimodal physiological data into the AI ​​analysis model includes: Extract temporal variation features from electroencephalogram (EEG), intrathoracic pressure (IP), and blood oxygenation (BO) signals; Based on the temporal variation characteristics, a multidimensional feature vector representing the response relationship between organs is constructed; Based on the multidimensional feature vector, an AI analysis model generates causal correlation outputs for predicting the evolution of damage mechanisms.

6. The method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice based on AI as described in claim 1, characterized in that, Also includes: The causal correlation output includes a dynamic path diagram that starts from changes in local shear stress in the cranium and sequentially correlates the release of inflammatory factors, abnormal autonomic nerve function, and disordered regulation of intrathoracic pressure. This path is used to assist in establishing a mathematical model of the mechanism of cross-organ injury propagation.

7. A system for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice based on AI, characterized in that, include: An impact module is used to apply an impact to the skull of a mouse, so that the impact is transmitted along the organ-coordinated conduction chain to induce a combined craniocerebral, thoracic and abdominal injury in the mouse. The organ-coordinated conduction chain is transmitted sequentially through the skull, cerebrospinal fluid, spinal cord and diaphragm to the thoracic cavity. The acquisition module is used to simultaneously acquire multimodal physiological data during the application of impact, including one or more of electroencephalogram (EEG) signals, intrathoracic pressure signals, and blood oxygenation signals. The analysis module is used to input the collected multimodal physiological data into the AI ​​analysis model to analyze the injury mechanism of the combined craniocerebral, thoracic and abdominal injuries, and to establish a dynamic model based on the analysis results.

8. The AI-based dynamic model preparation system for combined craniocerebral, thoracic, and abdominal injuries in mice as described in claim 7, characterized in that: The impact module, the acquisition module, and the analysis module are controlled to execute the AI-based method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice, as described in any one of claims 1 to 6.

9. 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 connected to the memory via the communication interface, enable the electronic device to implement the AI-based dynamic model preparation method for combined craniocerebral, thoracic and abdominal injuries in mice as described in any one of claims 1 to 6.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that, When the program instructions are executed by the computer, the computer implements the AI-based method for preparing a dynamic model of combined craniocerebral, thoracic, and abdominal injuries in mice as described in any one of claims 1 to 6.

Images