Full-automatic pain sense measuring system based on artificial intelligence integrated vital sign monitoring

Abstract

The invention belongs to the technical field of neurobiology and pain mechanism research, and discloses a full-automatic pain sense measuring system based on artificial intelligence integrated vital sign monitoring, which is integrated with multi-mode biological signal acquisition equipment, can synchronously record pain sense behaviors and physiological data (such as heart rate, respiratory rate, body temperature, excretion and the like) of experimental animals, and can be used for measuring the pain sense of the experimental animals. And the acquired data is analyzed and processed in real time by using an artificial intelligence algorithm to generate quantitative pain assessment indexes. Compared with a traditional pain assessment method depending on subjective observation, the system has the advantages that the efficiency and accuracy of data acquisition and analysis are remarkably improved, the human deviation can be reduced, and the assessment error rate is reduced to 5% or below. The method is particularly suitable for research of complex pain models and high-throughput drug screening, the preclinical research and development period can be remarkably shortened by 20%-30%, and the research and development cost is reduced. The invention has obvious market demand and economic benefit, and provides important technical support for the field of pain research.

Description

Technical Field

[0001] The present invention belongs to the technical field of neurobiology and pain mechanism research, and in particular relates to a fully automatic pain measurement system based on artificial intelligence integrated vital sign monitoring. Background Art

[0002] Since their development, thermal radiation and mechanical analgesia have been important tools for assessing pain responses, but the limitations of traditional manual measurement methods and existing analgesia instruments restrict the precision, repeatability and accuracy of the experiment. First, the traditional method requires the experimenter to manually manipulate the thermal radiation light source or von Frey filament to stimulate the test animal. Whether and how the animal responds mainly depends on the subjective judgment of the experimenter, resulting in unsatisfactory objectivity of the results. Secondly, although the existing automated analgesia instruments have solved the problem of stability in applying stimulation, they can only record the paw withdrawal threshold and paw withdrawal latency, and fail to integrate key pain-related physiological indicators such as heart rate, respiratory rate, body temperature, etc. The lack of these experimental data often limits the comprehensive judgment and analysis of pain responses by researchers.

[0003] 1. Limitations of traditional pain measurement

[0004] Traditional pain measurement relies on the experimenter to manually apply thermal radiation or von Frey stimulation and determine the pain threshold based on the animal's behavioral response (such as raising or retracting the paw) observed with the naked eye. This manual operation has several obvious limitations:

[0005] Strong subjectivity: It is often difficult for experimenters to completely control the intensity, angle, position and other factors when applying stimulation. Differences in experimenters' experience and techniques may lead to large fluctuations in results. This subjectivity makes the repeatability of experimental results poor, especially when comparing between multiple experimenters, it is difficult to obtain consistent results.

[0006] Long time consumption: Traditional thermal radiation pain measurement requires that animals be acclimated to the test environment in advance. In order to eliminate the subjective errors caused by the above-mentioned human operation, each animal needs to repeat the test at least 3-5 times, with an interval of 5-10 minutes each time. It takes 30-60 minutes for a mouse to complete a thermal radiation pain measurement experiment; the von Frey pain measurement experiment requires the gradual replacement of nylon filaments of different specifications (20 types) to apply pressures of different intensities, and a certain time interval is required between each mechanical stimulation, which not only increases the complexity of the experiment, but also significantly prolongs the experimental time. Each experiment requires multiple steps and a large number of repeated operations, which limits the efficiency of the experiment and the feasibility of large-scale application.

[0007] Single detection index: Traditional methods rely only on simple behavioral responses (such as the number and duration of paw retraction) to determine the pain threshold, and fail to capture other indicators of the animal during the pain process, such as the trajectory of paw retraction or leg lifting, leg lifting speed, autonomous movement of other parts of the body, and autonomic nervous function responses other than the trunk. It is known that when animals perceive pain, there are obvious changes in autonomic nervous function, such as increased heart rate, rapid breathing, increased excretion (urination, defecation), pupil dilation, increased glucocorticoid levels, and a series of other changes. Therefore, a single behavioral indicator cannot provide a complete assessment of pain behavior, which will inevitably affect the integrity and objectivity of the research results.

[0008] 2. Disadvantages of existing automated pain meters

[0009] In order to solve the problems of traditional pain measurement, an automated pain meter was developed, which uses a force sensor to automatically increase the intensity of mechanical stimulation linearly with a specified slope within a specified range, and automatically records the animal's paw retraction reaction-related parameters (paw retraction time and threshold). Although electronic equipment has improved the accuracy of measurement and has made significant progress over traditional manual methods, such as achieving stimulation stability and reducing human intervention through mechanization, there are still several significant limitations, especially in terms of automation level, vital sign detection function, and accuracy of judgment criteria:

[0010] Insufficient automation: Existing automated pain measuring instruments mainly record specific behavioral indicators (such as paw retraction time or paw retraction threshold), but have limited support for the overall automation of the experimental process. For example, experimenters still need to manually adjust stimulation parameters, position test animals, and observe the experimental environment. In addition, existing equipment usually lacks a full-process automation system and cannot independently complete closed-loop operations from experimental design, data collection to data analysis. This not only increases the operational burden of experimenters, but also easily leads to data deviations due to human intervention.

[0011] Lack of vital sign monitoring: Current pain measuring instruments mainly focus on behavioral indicators, such as paw withdrawal threshold and paw withdrawal time, but pain, as a complex physiological and psychological experience, is not only manifested as behavioral responses, but is also accompanied by obvious changes in autonomic nervous function. For example, pain can cause increased heart rate, rapid breathing, temperature fluctuations, urination and defecation. However, existing pain measuring instruments fail to integrate these vital sign information and cannot provide a comprehensive pain assessment. Especially for the study of chronic pain or complex pain mechanisms, this limitation of a single data source significantly affects the scientific nature and clinical significance of the experiment.

[0012] The judgment criteria are not precise enough: Current automated analgesics mainly rely on the quantification of a single behavioral response as the basis for pain assessment, such as whether the paw retraction time exceeds a fixed threshold. However, animals' responses to pain are often diverse and complex, including the synergy of behavioral changes and autonomic nervous activity. Relying solely on behavioral data may miss important pain-related information, especially under low-intensity stimulation or chronic pain conditions. In addition, existing instruments have difficulty capturing subtle behavioral changes (such as limb movement trajectories, reaction speed) and the dynamic process of physiological responses, resulting in low accuracy of the judgment criteria, which is difficult to meet the needs of refined research.

[0013] 3. The need for a fully automated, vital signs integrated von Frey system

[0014] In order to overcome the limitations of existing pain meters, it is of great significance and urgent need to develop a new type of pain meter that is highly automated, integrates multimodal data collection functions, and combines artificial intelligence-assisted analysis. Specific needs include:

[0015] High degree of automation: The new pain meter should achieve high degree of automation of the entire experimental process, from experimental setup, animal positioning, stimulation application to data collection and analysis, all of which can be completed autonomously through the system. This can not only reduce human intervention and operating errors, but also greatly improve experimental efficiency, especially in studies that require large sample sizes or long-term continuous testing. In addition, automated instruments should have the ability to dynamically adjust experimental parameters, such as adjusting the intensity and duration of stimulation according to the real-time response of the animal, so as to achieve personalized and sensitive pain assessment.

[0016] Multimodal data integration: The new pain meter needs to be able to simultaneously collect and integrate the animal's behavioral response and vital signs data. In addition to the traditional paw retraction threshold and paw retraction time, it should also include key autonomic nervous function indicators such as heart rate, respiratory rate, body temperature, urination, and defecation. This integration of multimodal data can not only more comprehensively reflect the overall physiological and behavioral characteristics of animals in pain, but also reveal the dynamic process and mechanism of pain response. In addition, the addition of a high-resolution video recording system can capture subtle changes in animal behavior, such as limb movement trajectory, reaction speed, movement coordination, etc., to provide support for multi-dimensional pain assessment.

[0017] Artificial intelligence-assisted analysis: The new pain meter combines artificial intelligence (AI) technology for automatic processing and advanced analysis of multimodal data. For example, AI models can extract features from behavioral videos and physiological data through machine learning algorithms to identify complex patterns related to pain. In addition, AI can also be used to establish a pain grading system based on multimodal data, providing more accurate pain assessment results than a single indicator. Through real-time analysis and feedback, the system can automatically judge the reliability of experimental data, indicate potential problems and optimize experimental design. This intelligent function will significantly enhance the depth and breadth of pain research and save researchers a lot of time and energy.

[0018] 4. Technical advantages and innovation of the new system

[0019] Precise control and automation: The new system uses precision sensors and automation devices to achieve high-precision control of various pain stimulation methods such as thermal radiation and mechanical stimulation. Parameters such as stimulation intensity, duration, and frequency can be preset before the experiment, or dynamically adjusted through real-time feedback to ensure high consistency of experimental conditions and reduce errors caused by human operation. The system can monitor the behavior and physiological reactions of animals in real time during the experiment without the intervention of experimenters, greatly improving experimental efficiency and data collection integrity.

[0020] The system integrates full-process automation functions from stimulation application to data processing, including automatic animal positioning, stimulation application, data acquisition and analysis, and generation of standardized experimental reports. This integrated design significantly reduces operation time, improves experimental repeatability and the feasibility of large-scale experiments.

[0021] Multi-dimensional pain response assessment: The system combines traditional behavioral indicators such as paw retraction time and paw retraction threshold with vital signs data such as heart rate, respiratory rate, body temperature, urination and defecation frequency to build a multimodal pain assessment system. This integrated assessment method can more comprehensively reflect the complex response of animals to painful stimuli and provide researchers with comprehensive data support. High-definition cameras and motion capture systems can record subtle features of animal behavior, such as limb movement trajectory, leg lifting speed, movement frequency and coordination. Combined with deep learning models, these data can be used to identify subtle pain-related behavioral patterns, thereby achieving more sensitive pain assessment. In addition, changes in autonomic nervous function of animals under painful conditions (such as increased heart rate and rapid breathing) are often highly biologically relevant. The new system uses these autonomic nervous signals as an important data source, combined with behavioral responses, to improve the detection accuracy and judgment ability of pain responses.

[0022] Artificial intelligence algorithm-assisted analysis: (1) Multimodal data processing and feature extraction: The system uses machine learning and deep learning algorithms to efficiently process and extract features from the collected multimodal data (behavior, vital signs, imaging data, etc.). Through data fusion technology, the system can explore the correlation between various indicators and provide a more accurate and scientific pain response assessment; (2) Adaptive analysis model: Based on the dynamic changes of experimental data, the artificial intelligence model can achieve adaptive learning, thereby continuously optimizing the pain assessment criteria. For example, the system can automatically adjust the analysis algorithm according to different experimental animal species, pain model types or stimulation methods to adapt to diverse research needs; (3) Prediction and grading function: AI-assisted analysis can not only determine pain responses in real time, but also predict the trend of experimental results based on historical data, such as the development process of chronic pain or the potential effect of drug intervention. At the same time, the system can establish a grading model based on multimodal data, quantify the degree of pain into different levels, and provide a refined reference for experimental and clinical research.

[0023] 5. Data support and theoretical basis

[0024] Behavioral responses (such as paw withdrawal threshold and leg lifting time) are the core of traditional pain measurement, but modern research has shown that relying solely on behavioral indicators cannot fully reflect the complexity of pain. Pain is a multidimensional perceptual phenomenon involving the synergy of behavioral responses, changes in the autonomic nervous system, and central nervous system activity. Therefore, vital sign data (such as heart rate, respiratory rate, and body temperature) as important physiological manifestations of pain have become an important direction to supplement traditional methods. For example, Smith et al. found that changes in heart rate are closely related to the intensity of pain stimulation, especially in acute pain models. Studies have shown that the heart rate of animals increased significantly after pain stimulation, and the change in heart rate was positively correlated with the intensity of pain response. Hurtig et al.'s research also showed that experimental animals showed significant heart rate acceleration and rapid breathing under mechanical pain stimulation, and these physiological reactions combined with simple paw withdrawal behavior can better distinguish behavioral responses caused by pain from other factors. In addition, respiratory acceleration and irregular changes caused by pain stimulation have also been confirmed. For example, Johnson et al. found that acute thermal radiation stimulation caused a significant increase in the respiratory rate of mice, and the respiratory irregularity index could accurately distinguish between pain and non-pain states, with a sensitivity of more than 80%. A study conducted by Williams et al. based on a chronic pain rat model found that integrating behavioral data and vital signs (such as heart rate variability and body temperature) can significantly improve the accuracy of pain assessment (R 2 From 0.65 to 0.85), and revealed more neural system mechanisms.

[0025] In recent years, artificial intelligence technology has developed rapidly in pain research, providing powerful tool support for the integrated analysis of multimodal data. The behavioral video analysis algorithm based on convolutional neural network (CNN) by Zhao et al. can accurately extract small behavioral changes from animal videos, such as gait deviation and limb movement amplitude, and the accuracy of identifying pain behavior exceeds 90%. In a study conducted by Green et al. combining vital signs and behavioral data, machine learning models (such as random forests) can effectively predict the degree of pain, and the model accuracy reaches 87%. In addition, deep learning algorithms based on multimodal data (such as multimodal Transformer) have been successfully applied to feature extraction of pain reactions and can predict different types of pain reactions. Wang et al.'s research shows that this method improves the accuracy of single-mode analysis by 25%-30%. In summary of the above research, the new fully automatic integrated vital sign detection pain measurement system involved in the present invention will have a potential impact in the field of pain research with its significant technical advantages of precise control, multi-dimensional data integration and AI-assisted analysis. This system not only overcomes the limitations of traditional and existing automated analgesics, but also provides strong tool support for scientists to explore pain mechanisms and develop personalized pain treatment plans.

[0026] Through the above analysis, the problems and defects of the prior art are as follows:

[0027] (1) Insufficient automation level: Existing automated pain measurement instruments mainly record specific behavioral indicators (such as paw withdrawal time or paw withdrawal threshold), but have limited support for the overall automation of the experimental process.

[0028] (2) Lack of vital sign monitoring: Current pain measurement instruments mainly focus on behavioral indicators, such as paw withdrawal threshold and paw withdrawal time. However, pain, as a complex physiological and psychological experience, is not only manifested as behavioral responses, but is also accompanied by obvious changes in autonomic nervous function.

[0029] (3) The judgment criteria are not precise enough: Current automated analgesics mainly rely on the quantification of a single behavioral response as the basis for pain assessment, such as whether the paw withdrawal time exceeds a certain fixed threshold. Summary of the invention

[0030] In view of the problems existing in the prior art, the present invention provides a fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring.

[0031] The present invention is implemented as follows: a fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring comprises:

[0032] All-in-one experimental box, wireless infrared body temperature detector, wireless millimeter-wave radar detector, infrared high-speed camera, three-degree-of-freedom robotic arm driven by electric servo motor, stimulator with integrated thermal radiation and high-precision pressure sensor, recording, calculation and analysis platform with integrated vital signs monitoring, pain monitoring and mouse movement posture analysis.

[0033] A metal grid plate is arranged inside the integrated experimental box to separate the integrated experimental box into two layers, the upper layer is a light-transmitting transparent experimental box, which is used to place experimental animals and is equipped with a wireless infrared body temperature detector, a wireless millimeter-wave radar detector, and an infrared high-speed camera; the lower layer is an opaque dark box, which is equipped with a three-degree-of-freedom robotic arm driven by an electric servo motor; a stimulator with thermal radiation and high-precision pressure sensors is integrated on the three-degree-of-freedom robotic arm.

[0034] Furthermore, a wireless infrared body temperature detector can realize non-invasive monitoring of the body temperature of mice in a freely moving state.

[0035] Furthermore, the wireless millimeter wave radar detector can non-invasively monitor the heart rate and respiratory movement of mice in a freely moving state;

[0036] The infrared high-speed camera has a resolution of 1920x1080 pixels and a frame rate of 120fps. It is used to monitor the movement posture of experimental animals in all directions and record the characteristic behaviors of pain perception of mice, such as leg retraction or leg lifting, paw licking or scratching, and other behaviors such as autonomous movements of the head, trunk and tail.

[0037] The three-degree-of-freedom robotic arm driven by an electric servo motor is driven by an electric servo motor to achieve movement in three directions of XYZ for thermal radiation and von Frey mechanical stimulation to move to different plantar positions of the animal.

[0038] Furthermore, the motion ranges of the three-degree-of-freedom robotic arm driven by the electric servo motor in the X, Y, and Z directions are: 0-50.0 cm in the X direction, 0-50.0 cm in the Y direction, and 0-20.0 cm in the Z direction.

[0039] Furthermore, the high-precision pressure sensor adjusts the maximum force, linear rate of change of force, magnitude of initial force, and duration of initial force of von Frey mechanical stimulation for mechanical stimulation of the plantar surface of the animal.

[0040] Furthermore, the infrared camera on the lower layer has a resolution of 640x480 pixels and a frame rate of 30fps, which is used to accurately locate the heat source on the soles of the experimental animals; the data obtained by the camera is analyzed by the animal posture analysis computing platform and then fed back to control the operation of the robotic arm.

[0041] Another object of the present invention is to provide a fully automatic pain measurement method based on artificial intelligence integrated vital signs monitoring, comprising:

[0042] Step 1: Prepare the experimental environment;

[0043] Place the experimental animals on the upper layer of the integrated experimental box and ensure that the wireless infrared body temperature detector, wireless millimeter wave radar detector and infrared high-speed camera are in working condition;

[0044] Step 2: Vital signs monitoring;

[0045] Use wireless infrared temperature detectors to monitor the body temperature of experimental animals in a free-moving state; use wireless millimeter-wave radar detectors to monitor heart rate and respiratory movement;

[0046] Step 3: Behavioral feature capture;

[0047] The movement posture of experimental animals is captured in real time by infrared high-speed cameras, including pain-related behaviors such as leg retraction, leg lifting, and paw licking;

[0048] Step 4: application of pain stimulus;

[0049] Control the three-degree-of-freedom robotic arm driven by an electric servo motor to precisely position the stimulator integrating thermal radiation or von Frey mechanical stimulation to the sole of the experimental animal; adjust the stimulation intensity, change rate and duration through a high-precision pressure sensor;

[0050] Step 5: Data processing and analysis;

[0051] Use the animal posture analysis computing platform to perform machine learning analysis on the data captured by high-speed cameras and infrared cameras, establish a quantitative pain index model, and evaluate the pain response of animals;

[0052] Step 6: Data storage and visualization;

[0053] All data collected during the experiment, including pressure sensor data, vital signs monitoring data, and machine learning analysis results, are stored in real time in a central database and presented through a visual interface.

[0054] Another object of the present invention is to provide a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the fully automatic pain measurement method based on artificial intelligence integrated vital signs monitoring.

[0055] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to perform the steps of the fully automatic pain measurement method based on artificial intelligence integrated vital signs monitoring.

[0056] Another object of the present invention is to provide an information data processing terminal, which is used to implement the fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring.

[0057] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0058] First, the present invention relates to a multimodal pain assessment system and its application method, and discloses a fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring, aiming to provide an efficient and objective assessment tool for scientific research, preclinical drug testing and other fields. The system integrates multimodal biological signal acquisition equipment, which can synchronously record the pain behavior and physiological data (such as heart rate, respiratory rate, body temperature, excretion, etc.) of experimental animals, and uses artificial intelligence algorithms to analyze and process the collected data in real time to generate quantitative pain assessment indicators. Compared with the traditional pain assessment method that relies on subjective observation, the system significantly improves the efficiency and accuracy of data collection and analysis, can reduce human bias, and reduce the assessment error rate to less than 5%. The present invention is particularly suitable for the research of complex pain models and high-throughput drug screening, which can significantly shorten the preclinical research and development cycle (shorten the time by 20%-30%) and reduce the research and development cost (reduce the cost by 15%-20%). The system has broad application prospects in scientific research and new drug development of pharmaceutical companies. Through multi-dimensional and automated evaluation schemes, it can help pain mechanism research and pain drug development, and solve the problems of inefficiency and subjectivity in the current research and development process. The present invention has significant market demand and economic benefits, and provides important technical support for the field of pain research.

[0059] The present invention relates to an automated pain measurement system based on artificial intelligence integrated vital signs monitoring, which aims to overcome the limitations of traditional and existing automated pain meters, and achieves comprehensive, accurate, and automated measurement of animal pain responses by integrating a fully automatic program-controlled stimulation device, a multimodal vital signs sensor, and an artificial intelligence algorithm. The present invention can not only accurately control the intensity and time of stimulation, but also synchronously collect multimodal data in real time, including the animal's behavioral responses, vital signs (such as heart rate, respiratory rate, body temperature), and autonomic nervous activity. By fusing multimodal data, the system can provide a more objective and comprehensive pain assessment, providing an efficient and reliable experimental tool for neuroscience, pharmacology, and pain research.

[0060] The fully automatic program-controlled stimulation device is equipped with a programmable three-degree-of-freedom robotic arm that carries thermal radiation and electronic von Frey. It is driven by an electric servo motor and can move in three directions, XYZ, and apply precise and highly repeatable stimulation, including thermal radiation, mechanical force, and electrical stimulation. The stimulation device is controlled by a microprocessor and can accurately adjust the stimulation intensity, application location, and duration. The thermal radiation stimulation intensity range is 1-50mW / cm 2 , resolution 0.1mW / cm 2 ; The electromechanical stimulation force range (vonFrey filament) is 0.1-50g, the accuracy is 0.01g, and the stimulation time control accuracy is 0.1 second. The 3D adjustable mechanical arm can accurately locate the stimulation site with a positioning accuracy of ±0.1mm. Through program settings, automatic switching of multiple types of stimulation can be achieved, which is suitable for different experimental needs. Built-in high-precision optical and mechanical sensors can record stimulation feedback to ensure the consistency and stability of experimental conditions.

[0061] The multimodal vital signs sensor uses a camera and millimeter-wave radar to achieve contactless and comprehensive monitoring of the animal's vital signs. The camera monitors the animal's millisecond-level body movements. The millimeter-wave radar monitors the animal's respiratory rate and heart rate. The respiratory rate measurement range is 50-300 times / minute, the error is ±2 times / minute, and the average detection error of the breathing interval is 1.5 seconds; the heart rate measurement range is 150-900bpm, the error is ±2bpm, and the average detection error of the heart rate is 4bpm. The body temperature is obtained through infrared thermal imaging and skin temperature sensors, with a body temperature resolution of ±0.1℃. Based on high-definition cameras and acceleration sensors, the movement trajectory, speed, claw lifting angle and other dynamic behavior parameters can also be recorded. The movement behavior resolution is ±0.1mm / s and the camera frame rate is 120fps.

[0062] Multimodal sensors will enable real-time synchronous acquisition of multiple biological signals and support long-term monitoring. The multi-sensor integrated module is connected to the main control unit via Bluetooth or Wi-Fi to simplify experimental operations. In addition, motion artifacts are automatically removed to ensure data accuracy. The fusion data of multimodal sensors can provide a more comprehensive and accurate data source for the determination of pain stimulation.

[0063] 1. High degree of automation: The integrated design realizes full process automation of stimulation application, data acquisition and analysis, significantly improving experimental efficiency and accuracy.

[0064] 2. Multi-dimensional pain response assessment: For the first time, behavioral responses and vital signs data are fully integrated to provide a comprehensive pain assessment from the surface to the system level.

[0065] 3. Intelligent data analysis: Use artificial intelligence to achieve data mining and automated analysis, accurately evaluate pain mechanisms and support personalized experimental design.

[0066] 4. Potential applications and impacts: (1) Scientific research: enhance the depth and breadth of research on pain mechanisms; (2) Drug development: support high-throughput screening and optimize the development process of pain treatment drugs; (3) Clinical transformation: provide precise model tools for research on neurological diseases, chronic pain, and drug dependence.

[0067] The expected income and commercial value of the technical solution of the present invention after transformation are as follows: Expected income: RMB 1 million to 5 million. Automatic animal pain meter products are produced and sold to domestic universities and research institutes.

[0068] The technical solution of the present invention fills the technical gap in the industry at home and abroad: the technical solution proposes an animal pain measurement solution with high automation, objective and accurate pain behavior measurement and low cost. It realizes the joint analysis of multimodal data such as animal heart rate, respiratory rate, body temperature, body movement, paw retraction time and paw retraction threshold.

[0069] Application prospects

[0070] 1. Contributions in the field of scientific research

[0071] (1) Improve the efficiency of basic research: The system realizes automatic and continuous monitoring of animal pain responses by introducing advanced multimodal biological signal acquisition and analysis technology. Traditional pain research relies on manual recording of animal behavior by experimenters, which usually consumes a lot of manpower and time. In contrast, the system can obtain rich pain response data in a shorter time by analyzing biological signals and behavioral data in real time, providing researchers with efficient tools and shortening the experimental cycle.

[0072] (2) Enhance the objectivity and accuracy of research data: Traditional pain scoring methods (such as the visual analogue scale) rely on subjective observation and are often biased by the experience and emotions of the assessor. According to existing data statistics, the error rate of traditional methods can be as high as 20%-30%. This system automatically generates quantitative indicators through precise signal analysis algorithms to ensure the scientificity and consistency of research results, filling the gap in the objectivity of traditional methods.

[0073] (3) Promote the development of new pain models: Complex pain states (such as neuropathic pain) require more sophisticated experimental model support. This system can evaluate the quality of model construction through multi-dimensional indicators (neural activity, behavioral frequency, biomarkers, etc.), provide comprehensive data support for the development and verification of new pain models, and improve the conversion efficiency of basic research results.

[0074] 2. Contribution to preclinical drug testing

[0075] (1) Solve the problems of inefficiency and subjectivity of traditional evaluation: Existing preclinical pain drug evaluation usually relies on a single behavioral indicator, with slow data collection and a single dimension. For example, the classic "hot plate test" and "mechanical stimulation test" methods can usually only test the short-term reactions of animals in a specific environment. This system continuously collects biological signal data (such as heart rate, respiration, body temperature, excretion, etc.) and behavioral data to achieve all-weather multi-dimensional monitoring, which improves experimental efficiency by 30%-50% compared to traditional methods. In addition, human factors in the existing evaluation process have a great impact on the data, especially in the identification of complex behavioral patterns, where there are subjective biases. This system uses AI algorithms to automatically analyze multimodal data, reduce evaluation errors, and reduce subjective bias to less than 5%, greatly improving the reliability of the results.

[0076] (2) Accelerate drug development and screening: According to statistics, the average drug development cycle is 10-15 years, of which the preclinical stage takes 3-6 years. Through high-throughput automated analysis, this system can screen out potential candidate drugs in a short period of time and reduce the risk of ineffective compounds entering the next stage. It is estimated that the system has the potential to shorten the preclinical testing time by 20%-30% and reduce R&D costs by 15%-20%.

[0077] (3) Support personalized drug development: The mechanism of action of pain medications is complex and diverse due to individual differences, and traditional methods are difficult to accurately capture the effects of different drugs in specific patient groups. This system can deeply analyze the target specificity and mechanism of action of drugs by integrating multimodal data, providing a strong scientific basis for the development of personalized pain treatment drugs.

[0078] (4) Comprehensiveness and high-throughput analysis: This system can integrate multimodal data acquisition functions (behavioral, neural, immune, and metabolic signals), thereby covering multi-dimensional drug efficacy evaluation at one time.

[0079] (5) Reduce development risks: Use precise analytical methods to help screen highly effective compounds, prevent undesirable candidates from entering the clinical trial stage, and significantly reduce the probability of clinical failure.

[0080] 3. Market demand and economic benefit analysis

[0081] (1) Market demand forecast: The pain medication market is an important part of the global drug market. According to EvaluatePharma, the global pain medication market size was approximately US$75 billion in 2022 and is expected to reach US$100 billion in 2030. As a core tool for improving R&D efficiency, this system will have important value in this fast-growing market.

[0082] (2) Economic Benefit Forecast

[0083] Direct benefits: The system can be sold as scientific research equipment to research institutions and pharmaceutical companies, and the price of a single set of equipment is expected to be around US$100,000. Based on the potential customer base of 2,000 related institutions around the world, the initial market penetration rate is 5%-10%, and the annual revenue can reach US$50 million to US$100 million.

[0084] Indirect benefits: By helping pharmaceutical companies shorten their R&D cycles and reduce failure rates, this system can save a single company $10 million to $50 million in R&D costs each year, which will improve the economic benefits of the entire industry in the long run.

[0085] 4. Commercialization potential

[0086] (1) Technological leadership: There is currently no efficient pain assessment system on the market that integrates multimodal analysis technology. This system has a clear competitive advantage in the industry due to its uniqueness.

[0087] (2) Diversified application prospects: In addition to pain research, the system can also be applied to multiple fields such as neuroscience, behavior, and toxicology, further expanding the market size.

[0088] (3) Sustainability: The system has the potential for upgrading. Through continuous optimization of the cloud computing platform and AI algorithms, it can provide users with long-term data analysis services, further enhance customer stickiness and bring in sustainable revenue.

[0089] In short, this system provides important technical support for scientific research and the pharmaceutical industry through efficient and objective evaluation methods. Its unique value in shortening the R&D cycle, reducing the failure rate and promoting innovation makes it have significant market competitiveness and commercialization potential. In the future, this system will not only innovate the pain measurement experimental paradigm and improve scientific research efficiency, but also promote drug development in the field of pain treatment.

[0090] Second, as auxiliary evidence of the inventiveness of the claims of the present invention, it is also reflected in the following important aspects:

[0091] (1) The expected benefits and commercial value of the technical solution of the present invention after transformation are:

[0092] Direct benefits: The fully automatic pain meter of the present invention is sold to domestic universities and research institutes, and can also be sold as scientific research equipment to global research institutions and pharmaceutical companies. The price of a single set of equipment is expected to be around US$100,000. Based on the potential customer base of 1,000 related institutions worldwide, the initial market penetration rate is 5%-10%, and the annual income can reach US$50 million to US$100 million. In the domestic market, with the continuous increase in scientific research investment and the emphasis on pain research, the demand for the pain meter will gradually increase, and the expected income can reach RMB 1 million to 5 million.

[0093] Indirect benefits: From an industry perspective, the pain medication market is huge and growing. The global pain medication market size is about $75 billion in 2022 and is expected to reach $100 billion in 2030. This system can help pharmaceutical companies shorten the R&D cycle (by 20%-30%) and reduce the failure rate, saving a single company $10 million to $50 million in R&D costs each year. In the long run, it will significantly improve the economic benefits of the entire industry, promote the development of the pain medication market, and bring huge commercial value.

[0094] (2) The technical solution of the present invention fills the technical gap in the industry at home and abroad:

[0095] At present, in the field of pain measurement technology at home and abroad, traditional methods and existing instruments have many limitations. Traditional pain measurement methods rely on manual operation and subjective judgment, and have problems such as strong subjectivity, high time consumption, and single detection indicators; although existing automated pain meters have made progress, they are still insufficient in terms of automation level, vital sign monitoring function, and accuracy of judgment criteria.

[0096] The present invention proposes an animal pain measurement scheme with a high degree of automation, objective and accurate measurement of pain behavior and low cost. For the first time, the joint analysis of multimodal data such as the animal's heart rate, respiratory rate, body temperature, body movement, paw retraction time and paw retraction threshold is realized. The integrated multimodal biosignal acquisition equipment synchronously records the pain behavior and physiological data of experimental animals, and uses artificial intelligence algorithms to perform real-time analysis and processing on the collected data to generate quantitative pain assessment indicators. This system, which combines a fully automatic program-controlled stimulation device, a multimodal vital sign sensor and an artificial intelligence algorithm, is the first of its kind in the industry and fills a gap in related technologies.

[0097] (3) Whether the technical solution of the present invention solves the technical problems that people have been eager to solve but have not been able to solve successfully:

[0098] Researchers have always hoped to achieve efficient, objective and comprehensive pain measurement in the field of pain research to promote the study of pain mechanisms and the development of pain treatment drugs, but they always face many challenges:

[0099] The subjectivity and inefficiency of traditional pain measurement methods: Traditional manual measurement methods rely on the experimenter to manually manipulate stimuli and subjectively judge the animal's response. The results are not objective and repeatable, and the experiment time is long and the efficiency is low, making it difficult to meet the needs of large-scale experiments.

[0100] Functional limitations of existing automated pain meters: Although existing automated pain meters have solved some stability problems, their automation level is insufficient and they lack a full-process automated system. They lack vital signs monitoring and cannot provide a comprehensive pain assessment. The judgment criteria are not precise enough to meet the needs of refined research.

[0101] The present invention uses a highly automated design to achieve autonomous completion of the entire experimental process from setup to analysis, reducing human intervention and errors; integrates multimodal data acquisition functions, fully integrates behavioral responses and vital sign data, and provides a full range of pain assessment; uses artificial intelligence algorithms for intelligent data analysis, accurately assesses pain mechanisms and supports personalized experimental design. It effectively solves these technical problems that have long plagued this field and provides a powerful tool for pain research and drug development.

[0102] (4) Whether the technical solution of the present invention overcomes technical prejudice:

[0103] In the field of pain measurement, there has long been a technical bias that pain measurement mainly relies on behavioral indicators (such as paw withdrawal threshold and paw withdrawal time), focusing only on the obvious behavioral responses of animals to assess the degree of pain. This bias has led researchers to ignore other important indicators such as changes in autonomic nervous function that accompany pain as a complex physiological and psychological experience.

[0104] Most existing pain measurement technologies are designed and optimized around behavioral indicators, but the integration and utilization of vital signs data are insufficient. The present invention overcomes this technical bias and emphasizes that pain is a multidimensional perceptual phenomenon involving the synergy of behavioral responses, changes in the autonomic nervous system, and central nervous system activities. By combining vital signs data such as heart rate, respiratory rate, and body temperature with traditional behavioral indicators, a multimodal pain assessment system is constructed to more comprehensively reflect the complex responses of animals to painful stimuli. At the same time, artificial intelligence technology is used to process and analyze multimodal data, explore the correlation between various indicators, and achieve more accurate pain assessment, breaking through the constraints of traditional technical biases and bringing new ideas and methods to pain measurement technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0105] Figure 1 It is a structural block diagram of a fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring provided by an embodiment of the present invention.

[0106] Figure 2 This is a flow chart of a fully automatic pain measurement method based on artificial intelligence integrated vital signs monitoring provided by an embodiment of the present invention.

[0107] Figure 1 In: 1. Integrated experimental box; 2. Hard opaque partition; 3. Metal grid plate; 4. Wireless infrared body temperature detector; 5. Wireless millimeter wave radar detector; 6. Infrared high-speed camera; 7. Three-degree-of-freedom robotic arm driven by electric servo motor; 8. Stimulator integrating thermal radiation and high-precision pressure sensors; 9. Recording, calculation and analysis platform integrating vital signs monitoring, pain monitoring and mouse movement posture analysis. DETAILED DESCRIPTION

[0108] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0109] like Figure 1 As shown, an embodiment of the present invention provides a fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring, comprising:

[0110] All-in-one experimental box 1, wireless infrared body temperature detector 4, wireless millimeter wave radar detector 5, infrared high-speed camera 6, three-degree-of-freedom robotic arm driven by electric servo motor 7, stimulator integrating thermal radiation and high-precision pressure sensor 8, recording, calculation and analysis platform integrating vital sign monitoring, pain monitoring and mouse movement posture analysis 9.

[0111] A metal grid plate is arranged inside the integrated experimental box to separate the integrated experimental box into two layers, the upper layer is a light-transmitting transparent experimental box, which is separated by a hard opaque partition 2, used to place experimental animals and is equipped with a wireless infrared body temperature detector 4, a wireless millimeter-wave radar detector 5, and an infrared high-speed camera 6; the lower layer is an opaque dark box, which is equipped with a three-degree-of-freedom robotic arm 7 driven by an electric servo motor; a stimulator 8 with a thermal radiation and high-precision pressure sensor is integrated on the three-degree-of-freedom robotic arm.

[0112] The wireless infrared body temperature detector provided in the embodiment of the present invention can realize non-invasive monitoring of the body temperature of mice in a freely moving state.

[0113] The wireless millimeter wave radar detector provided by the embodiment of the present invention realizes non-invasive monitoring of the heart rate and respiratory movement of mice in a freely moving state;

[0114] The infrared high-speed camera has a resolution of 1920x1080 pixels and a frame rate of 120fps. It is used to monitor the movement posture of experimental animals in all directions and record the characteristic behaviors of pain perception of mice, such as leg retraction or leg lifting, paw licking or scratching, and other behaviors such as autonomous movements of the head, trunk and tail.

[0115] The three-degree-of-freedom robotic arm driven by an electric servo motor is driven by an electric servo motor to achieve movement in three directions of XYZ for thermal radiation and von Frey mechanical stimulation to move to different plantar positions of the animal.

[0116] The motion ranges of the three-degree-of-freedom mechanical arm driven by the electric servo motor provided in the embodiment of the present invention in the X, Y, and Z directions are: 0-50.0 cm in the X direction, 0-50.0 cm in the Y direction, and 0-20.0 cm in the Z direction.

[0117] The high-precision pressure sensor provided by the embodiment of the present invention adjusts the maximum force, linear change rate of force, initial force, and duration of initial force of von Frey mechanical stimulation for mechanical stimulation of the plantar of an animal.

[0118] The infrared camera of the lower layer provided in the embodiment of the present invention has a resolution of 640x480 pixels and a frame rate of 30fps, which is used to accurately locate the heat source on the sole of the foot of the experimental animal; the data obtained by the camera is analyzed by the animal posture analysis computing platform and then fed back to control the operation of the robotic arm.

[0119] like Figure 2 As shown, an embodiment of the present invention provides a fully automatic pain measurement method based on artificial intelligence integrated vital signs monitoring, including:

[0120] S101: Experimental environment preparation;

[0121] Place the experimental animals on the upper layer of the integrated experimental box and ensure that the wireless infrared body temperature detector, wireless millimeter wave radar detector and infrared high-speed camera are in working condition;

[0122] S102: Vital signs monitoring;

[0123] Use wireless infrared temperature detectors to monitor the body temperature of experimental animals in a free-moving state; use wireless millimeter-wave radar detectors to monitor heart rate and respiratory movement;

[0124] S103: Behavioral feature capture;

[0125] The movement posture of experimental animals is captured in real time by infrared high-speed cameras, including pain-related behaviors such as leg retraction, leg lifting, and paw licking;

[0126] S104: pain stimulus application;

[0127] Control the three-degree-of-freedom robotic arm driven by an electric servo motor to precisely position the stimulator integrating thermal radiation or von Frey mechanical stimulation to the sole of the experimental animal; adjust the stimulation intensity, change rate and duration through a high-precision pressure sensor;

[0128] S105: Data processing and analysis;

[0129] Use the animal posture analysis computing platform to perform machine learning analysis on the data captured by high-speed cameras and infrared cameras, establish a quantitative pain index model, and evaluate the pain response of animals;

[0130] S106: Data storage and visualization;

[0131] All data collected during the experiment, including pressure sensor data, vital signs monitoring data, and machine learning analysis results, are stored in real time in a central database and presented through a visual interface.

[0132] A computer device is provided in an embodiment of the present invention, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the fully automatic pain measurement method based on artificial intelligence integrated vital signs monitoring.

[0133] A computer-readable storage medium provided by an embodiment of the present invention stores a computer program. When the computer program is executed by a processor, the processor executes the steps of the fully automatic pain measurement method based on artificial intelligence integrated vital signs monitoring.

[0134] An embodiment of the present invention provides an information data processing terminal, which is used to implement the fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring.

[0135] The present invention is specifically implemented:

[0136] 1. Fully automatic program-controlled stimulation device

[0137] 1.1 Design structure

[0138] Stimulation module: A multifunctional integrated device is used, including a thermal radiation source (infrared lamp or laser), a mechanical stimulation module (electrically controlled von Frey device) and an electrical stimulation module. All modules are connected through a microcontroller unit (MCU), which can realize automatic switching of different stimulation types.

[0139] Positioning module: The three-axis robotic arm is equipped with a high-precision servo motor to achieve precise control of the stimulation position with an error of less than 0.1mm.

[0140] Control unit: Embedded software is used to preset and adjust stimulation parameters in real time, including stimulation intensity, duration, interval time and application position.

[0141] 1.2 Experimental operation process

[0142] Preset parameters: The experimenter inputs stimulation parameters through the system interface, such as thermal radiation intensity (10mW / cm 2 ), von Frey filament strength (0.1 g).

[0143] Animal positioning: The experimental animals are placed on a dedicated transparent platform. An infrared thermal imaging camera is installed at the bottom of the platform, and the top robotic arm automatically positions itself to the target area (such as the hind paw).

[0144] Stimulation application: The system applies stimulation in sequence according to the preset program. After the stimulation is completed, the system automatically records the response behavior, such as the claw retraction action or the claw lifting angle.

[0145] Parameter adjustment: Optimize experimental settings by automatically adjusting stimulation intensity and duration based on animal responses through a real-time feedback mechanism.

[0146] 1.3 Data Collection and Storage

[0147] Data such as the time and intensity of each stimulation and the animal's initial response delay are recorded in real time and stored in a database for subsequent analysis.

[0148] 2. Multimodal vital signs sensor

[0149] 2.1 Sensor module design

[0150] Heart rate and breathing monitoring: Uses millimeter wave radar technology to record heart rate and breathing rate.

[0151] Body temperature monitoring: Use high-precision infrared thermal imaging sensors to collect animal surface temperature distribution.

[0152] Movement behavior monitoring: A high-speed camera combined with an acceleration sensor records the animal's movement trajectory, leg-raising height, and leg-raising speed.

[0153] 2.2 Experimental operation process

[0154] Sensor installation: Place the animal in the device. Set the detection frequency of the millimeter-wave radar according to the physiological characteristics of different animals. Start the millimeter-wave radar to measure the basic vital signs of the animal, establish a baseline of vital signs, and obtain the heart rate, respiratory rate, etc. of the animal in a resting state.

[0155] Synchronous acquisition: While the stimulus is being applied, the sensor synchronously collects vital signs and motion behavior data, with a sampling frequency of up to 1000Hz.

[0156] Real-time display and recording: The system interface displays the collected multi-modal data in real time, including heart rate curve, respiratory waveform, body temperature heat map and behavior trajectory.

[0157] 2.3 Data storage and calibration

[0158] The data is stored on the local hard disk and uploaded to the cloud storage regularly to support cross-experiment comparison.

[0159] Regularly calibrate the sensor using a standard calibration tool (such as a standard heart rate simulator) to ensure data accuracy.

[0160] 3. Artificial intelligence algorithm assisted analysis

[0161] 3.1 Algorithm model design

[0162] Behavior recognition model: Use convolutional neural network (CNN) to analyze experimental videos and extract behavioral features such as paw retraction and leg lifting.

[0163] Multimodal data fusion model: Based on the Transformer architecture, vital signs and behavioral response data are integrated into a unified feature vector for assessing pain intensity.

[0164] Classification and prediction model: Random forest (RF) or support vector machine (SVM) is used to classify the pain degree under different stimulation conditions and output quantitative results.

[0165] 3.2 Experimental operation process

[0166] Data preprocessing: Standardize the original multimodal data and filter out artifacts and noise signals.

[0167] Feature extraction: The system automatically extracts behavioral features (such as the speed and angle of the paw lifting) and physiological features (such as the amplitude of heart rate changes and breathing rate changes).

[0168] Model training and validation: Input experimental data to train the AI ​​model, and use labeled data sets for cross-validation to evaluate model performance.

[0169] Real-time analysis and report generation: While the experiment is ongoing, the system runs the model in real time and provides a pain assessment report, including pain scores, trends in vital signs, etc.

[0170] 3.3 Model performance indicators

[0171] Behavior recognition accuracy: >95%.

[0172] Multimodal data fusion analysis time: <100ms / data packet.

[0173] Pain intensity classification accuracy: increased to 85%-90%.

[0174] 4. System comprehensive experimental operation

[0175] Animal adaptation: Place the experimental animals on the platform and allow them to adapt to the environment for 15-30 minutes to ensure that their physiological state is stable.

[0176] Stimulation and data acquisition: The system is programmed to gradually apply thermal, mechanical or electrical stimulation of varying intensities.

[0177] Multimodal sensors synchronously collect vital signs and behavioral data, ensuring that all data are accurately time-stamped.

[0178] Data analysis: After the experiment, the system automatically runs the AI ​​algorithm to conduct a comprehensive analysis of the collected data and generate a pain assessment report.

[0179] Result output and archiving: The experimental results are presented in the form of charts and archived in the experimental database. Experimenters can access and share data through the cloud.

[0180] The AI-based multimodal data fusion analysis module includes: (1) Deep learning algorithm: Use convolutional neural network (CNN) and recurrent neural network (RNN) to extract features from behavioral videos and identify pain-related movement patterns. (2) Machine learning classifier: Use models such as support vector machine (SVM) and random forest (RF) to grade pain severity based on vital signs and behavioral data. (3) Multimodal data fusion model: Based on the Transformer architecture, behavioral data and physiological signals are integrated to identify complex pain phenotypes. Performance indicators include: behavioral recognition accuracy > 95%; multimodal data fusion accuracy increased to 85%-90%; real-time analysis delay < 100ms; and sensitivity of pain severity grading increased by 25%. Through data modeling and prediction, automatic analysis and visualization of experimental data are achieved to reduce subjective errors of experimenters. Automatically generate reports to provide personalized pain assessment and experimental optimization suggestions. At the same time, it also supports model updates and iterations, and is compatible with multiple types of animal models and experimental conditions.

[0181] This system coordinates and controls multiple stimulation modules (such as thermal radiation source, electrically controlled von Frey device, and electrical stimulation module) through an embedded microcontroller unit (MCU). The experimenter presets the stimulation parameters, such as the intensity of thermal radiation or the strength of mechanical stimulation. The system uses a three-axis robotic arm to accurately locate the target area of ​​the experimental animal (such as the hind paw) and automatically applies stimulation. During the process, the stimulation parameters can be adjusted in real time according to the animal's response to optimize the experimental settings and ensure the accuracy of the stimulation. The relevant data of each stimulation (such as time, intensity, and response delay) will be collected and stored in real time.

[0182] The system is equipped with millimeter-wave radar, high-precision infrared thermal imaging sensor and high-definition camera, which are used to monitor the heart rate, respiratory rate, body surface temperature and movement behavior of animals respectively. During the experiment, stimulation is applied simultaneously with vital signs monitoring, and the sensor records multimodal data at a high sampling frequency of 1000Hz. The collected data includes heart rate curve, respiratory waveform, heat map and behavior trajectory, which are displayed in real time on the system interface and stored synchronously in the local database to ensure data integrity and traceability.

[0183] The system records all experimental data, including stimulation type, parameter settings, and physiological and behavioral responses of animals. Data is stored on the local hard drive and uploaded to the cloud storage regularly for cross-experiment comparison and long-term tracking. Sensors are regularly calibrated to ensure data accuracy and consistency. Through efficient data management processes, experimenters can quickly obtain key indicators and generate reports.

[0184] The system has built-in deep learning algorithms (such as convolutional neural networks (CNNs) and machine learning models (such as random forest SVMs) to analyze multimodal data. CNN extracts features from behavioral videos to identify pain-related movements such as paw retraction and leg lifting; the vital sign data is integrated by a multimodal fusion model to generate a unified feature vector for grading the degree of pain. During the analysis process, the model runs in real time to identify pain phenotypes and generate analysis reports, including pain scores and vital sign trends.

[0185] The system automates the entire process from animal adaptation to the environment, stimulation application to data collection and analysis. Through the real-time feedback mechanism, the stimulation parameters can be automatically adjusted according to the dynamic response of the animal, thereby optimizing the experimental conditions. The synchronous collection and analysis of multimodal data ensures high accuracy and consistency of the experimental results, reducing the subjective errors of the experimenters.

[0186] After the experiment, the system runs the AI ​​algorithm to conduct a comprehensive analysis of the data and generate a report containing pain scores, behavioral and physiological trend graphs. The report is automatically archived and can be accessed or shared through the cloud. At the same time, the system supports the update and iteration of the algorithm model to ensure that it is suitable for multiple types of experimental conditions and animal models. Through the automated and intelligent data processing process, the experimental efficiency and data reliability are significantly improved.

[0187] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. It can be understood by a person of ordinary skill in the art that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0188] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. A fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring, characterized in that: The fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring includes: All-in-one experimental box, wireless infrared body temperature detector, wireless millimeter-wave radar detector, infrared high-speed camera, three-degree-of-freedom robotic arm driven by electric servo motor, stimulator with integrated thermal radiation and high-precision pressure sensor, recording, calculation and analysis platform with integrated vital signs monitoring, pain monitoring and mouse movement posture analysis. A metal grid plate is arranged inside the integrated experimental box to separate the integrated experimental box into two layers, the upper layer is a light-transmitting transparent experimental box, which is used to place experimental animals and is equipped with a wireless infrared body temperature detector, a wireless millimeter-wave radar detector, and an infrared high-speed camera; the lower layer is an opaque dark box, which is equipped with a three-degree-of-freedom robotic arm driven by an electric servo motor; a stimulator with thermal radiation and high-precision pressure sensors is integrated on the three-degree-of-freedom robotic arm.

2. The fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring as claimed in claim 1, characterized in that: Wireless infrared body temperature detector, to achieve non-invasive monitoring of the body temperature of mice in free movement.

3. The fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring as claimed in claim 1, characterized in that: Wireless millimeter-wave radar detectors can non-invasively monitor the heart rate and respiratory movements of mice in free-moving conditions; The infrared high-speed camera has a resolution of 1920x1080 pixels and a frame rate of 120fps. It is used to monitor the movement posture of experimental animals in all directions and record the characteristic behaviors of pain perception of mice, such as leg retraction or leg lifting, paw licking or scratching, and other behaviors such as autonomous movements of the head, trunk and tail. The three-degree-of-freedom robotic arm driven by an electric servo motor is driven by an electric servo motor to achieve movement in three directions of XYZ for thermal radiation and von Frey mechanical stimulation so as to move to different plantar positions of the animal.

4. The fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring as claimed in claim 1, characterized in that: The motion ranges of the three-degree-of-freedom robotic arm driven by the electric servo motor in the X, Y, and Z directions are: 0-50.0 cm in the X direction, 0-50.0 cm in the Y direction, and 0-20.0 cm in the Z direction.

5. The fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring as claimed in claim 1, characterized in that: The high-precision pressure sensor adjusts the maximum force, linear rate of change of force, initial force, and duration of initial force of von Frey mechanical stimulation for the plantar mechanical stimulation of the animal.

6. The fully automatic pain measurement system based on artificial intelligence integrated vital signs monitoring as claimed in claim 1, characterized in that: The infrared camera on the lower layer has a resolution of 640x480 pixels and a frame rate of 30fps, which is used to accurately locate the heat source on the soles of the experimental animals. The data obtained by the camera is analyzed by the animal posture analysis computing platform and then fed back to control the operation of the robotic arm.

7. A fully automatic pain measurement method based on artificial intelligence integrated vital signs monitoring implementing the system as claimed in any one of claims 1 to 6, characterized in that: include: Step 1: Prepare the experimental environment; Place the experimental animals on the upper layer of the integrated experimental box and ensure that the wireless infrared body temperature detector, wireless millimeter wave radar detector and infrared high-speed camera are in working condition; Step 2: Vital signs monitoring; Use wireless infrared temperature detectors to monitor the body temperature of experimental animals in a free-moving state; use wireless millimeter-wave radar detectors to monitor heart rate and respiratory movement; Step 3: Behavioral feature capture; The movement posture of experimental animals is captured in real time by infrared high-speed cameras, including pain-related behaviors such as leg retraction, leg lifting, and paw licking; Step 4: Pain stimulus application; Control the three-degree-of-freedom robotic arm driven by an electric servo motor to precisely position the stimulator integrating thermal radiation, cold radiation or von Frey mechanical stimulation to the sole of the experimental animal; adjust the stimulation intensity, change rate and duration through a high-precision pressure sensor; Step 5: Data processing and analysis; Use the animal posture analysis computing platform to perform machine learning analysis on the data captured by high-speed cameras and infrared cameras, establish a quantitative pain index model, and evaluate the pain response of animals; Step 6: Data storage and visualization; All data collected during the experiment, including pressure sensor data, vital signs monitoring data, and machine learning analysis results, are stored in real time in a central database and presented through a visual interface.

Images