A pain assessment device, method and apparatus
Patent Information
- Application Number
- CN202610307635.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-13
- Publication Date
- 2026-07-21
Smart Images
Figure CN122423804A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of medical electronic equipment and quantitative sensory assessment technology, specifically, it relates to a pain assessment device, method and apparatus. Background Technology
[0002] Pain, as the fifth vital sign, requires objective and accurate assessment, which is fundamental to clinical diagnosis, drug trials, and rehabilitation follow-up. However, current mainstream pain assessment methods still heavily rely on patient self-assessment tools such as the Visual Analogue Scale (VAS), Numerical Rating Scale (NRS), and McGill Pain Questionnaire (MPQ). While these scales are simple and easy to use, the results are highly susceptible to influences such as education level, emotional state, language ability, and momentary attention. The coefficient of variation for retests conducted at different times or by different assessors often exceeds 30%, failing to meet the reproducibility requirements of pain research and precision medicine. Meanwhile, commercially available electronic stimulation pain devices only provide electrical stimulation thresholds, and their stimulation patterns differ significantly from the most common clinical "mechanical tenderness" and "dull pressure pain," exhibiting problems such as limited stimulation dimensions and low ecological validity. While functional magnetic resonance imaging (fMRI) and laser evoked potentials (LAPs) can directly record central pain pathway activity, they face bottlenecks such as high equipment prices, complex operation, and the need for professional technicians, hindering their widespread use in outpatient and emergency departments, community hospitals, and home settings. Therefore, there is an urgent clinical need for a new pain assessment tool that combines subjective quantification, multimodal stimulation, low cost, and bedside availability to overcome the "technological gap" between traditional subjective scales and high-end neuroimaging. Summary of the Invention
[0003] This application provides a pain assessment device, method, and apparatus to at least address the problems of existing pain assessment methods relying on patient subjective descriptions leading to poor repeatability, electrical stimulation instruments having a single stimulation dimension that does not match daily pain scenarios, and neuroelectrophysiological devices being expensive, complex to operate, and unsuitable for rapid bedside or community screening.
[0004] According to a first aspect of this application, a pain assessment device is provided, comprising: a mechanical pressure output module, a pressure sensing module, a subject response input module, a processing module, and a result output module; The mechanical pressure output module is used to apply mechanical pressure to the test site; the pressure sensing module is rigidly coupled to the mechanical pressure output module and is used to generate pressure-time correspondence signals as pressure changes over time in real time. Subjects reported that the input module was electrically connected to the pressure sensing module to generate event markers at the moment pain was generated and / or at the moment when the pain became intolerable. The processing module is connected to the pressure sensing module and the subject response input module. It is used to receive pressure-time corresponding signals and event markers, and extract the pain threshold pressure value and tolerance threshold pressure value from the pressure-time corresponding signals according to the event markers. Then, it calls the pre-stored continuous function model for converting pressure values into pain scores to convert the pain threshold pressure value and tolerance threshold pressure value into a quantitative pain score. The continuous function model is a polynomial function obtained by least squares fitting based on population samples. The output module is connected to the processing module via a signal and is used to present or export quantitative pain scores.
[0005] In one embodiment, the mechanical pressure output module includes: an electrically controlled linear actuator for outputting a controllable linear displacement after receiving a drive signal from the processing module; a pressure head rigidly connected to the output end of the electrically controlled linear actuator and converting the linear displacement into mechanical pressure on the test part; and a displacement / force feedback sensor for providing real-time feedback of the pressure head's displacement or actual pressure value to the processing module to form a closed-loop control.
[0006] In one embodiment, the subject response input module specifically includes: a trigger for generating a level change when pressed; and a signal interface for signal connection with the processing module to form an event marker.
[0007] In one embodiment, the pain assessment device further includes: a display screen, a power button, a zeroing button, a unit switching button, an event sound configuration button, a power supply, and a USB interface.
[0008] According to a second aspect of this application, a pain assessment method is also provided, using the pain assessment device described above, comprising: Mechanical pressure was applied to the test site and the pressure-time correspondence signal was recorded as the pressure changed over time. Receive event markers issued by subjects when they experience pain and / or when the pain becomes intolerable; Based on the event markers, extract the corresponding pain threshold pressure value and tolerance threshold pressure value from the pressure-time correspondence signal; The pain threshold pressure value and the tolerance threshold pressure value are substituted into a pre-established continuous function model for converting the pressure value into a pain score to obtain a quantitative pain score. The continuous function model is a polynomial function obtained by fitting a population sample using the least squares method.
[0009] In one embodiment, mechanical pressure is applied via a force gauge, and the pressure load resolution is ≤0.01 N.
[0010] In one embodiment, the event marker is triggered by a test subject via a reaction button connected via USB and sent to the evaluation terminal in real time as a digital signal.
[0011] In one embodiment, the continuous function model is a mathematical model established by using the least squares method to fit polynomial curves to the stress data and pain rating data of the population sample. The fitted polynomial is used to infer the stress threshold corresponding to three points of pain, five points of pain, or seven points of pain.
[0012] In one embodiment, the pain assessment method further includes comparing a quantitative pain score with age, gender, and / or test site stratified reference values in a built-in normal reference value library to determine whether the subject's pain perception is within the normal range.
[0013] In one embodiment, the pain assessment method further includes: displaying the pain threshold pressure value, tolerance threshold pressure value, and quantitative pain score in real time on the assessment software interface, and automatically generating a graphic report, the report content including a pressure-time curve, threshold line, and a comparison chart with the normal reference range.
[0014] According to a third aspect of this application, a pain assessment device is also provided, comprising: The pressurization unit is used to apply mechanical pressure to the test site and record the pressure-time correspondence signal as the pressure changes over time. An event tagging unit is used to receive event tags emitted by the subject when they experience pain and / or when the pain becomes intolerable; The pressure value extraction unit is used to extract the corresponding pain threshold pressure value and tolerance threshold pressure value from the pressure-time correspondence signal based on the event marker. The pain scoring unit is used to substitute the pain threshold pressure value and the tolerance threshold pressure value into a pre-established continuous function model for converting the pressure value into a pain score, so as to obtain a quantitative pain score. The continuous function model is a polynomial function obtained by fitting a population sample using the least squares method.
[0015] In one embodiment, mechanical pressure is applied via a force gauge, and the pressure load resolution is ≤0.01 N.
[0016] In one embodiment, the event marker is triggered by a test subject via a reaction button connected via USB and sent to the evaluation terminal in real time as a digital signal.
[0017] In one embodiment, the continuous function model is a mathematical model established by using the least squares method to fit polynomial curves to the stress data and pain rating data of the population sample. The fitted polynomial is used to infer the stress threshold corresponding to three points of pain, five points of pain, or seven points of pain.
[0018] In one embodiment, the pain assessment method further includes comparing a quantitative pain score with age, gender, and / or test site stratified reference values in a built-in normal reference value library to determine whether the subject's pain perception is within the normal range.
[0019] In one embodiment, the pain assessment method further includes: displaying the pain threshold pressure value, tolerance threshold pressure value, and quantitative pain score in real time on the assessment software interface, and automatically generating a graphic report, the report content including a pressure-time curve, threshold line, and a comparison chart with the normal reference range.
[0020] This application uses a 0.01 N-level mechanical pressure probe to collect pressure pain signals in real time, and marks the instantaneous pressure value with the subject's button press event. Then, it substitutes the pressure into the population fitting curve to directly convert the pressure into a pain score, realizing the objectivity and quantification of pain assessment and completing it in three minutes. It gets rid of the subjective bias of traditional questionnaires and the cost threshold of high-end electrophysiological equipment. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 This application provides a specific implementation method for an intelligent pain assessment device.
[0023] Figure 2 A flowchart of a pain assessment method provided in this application.
[0024] Figure 3 This is a specific implementation of an electronic device in the embodiments of this application.
[0025] Figure 4 This is a schematic diagram of the adapter in an embodiment of this application.
[0026] Figure 5 This is a schematic diagram of the test subject's reaction component in an embodiment of this application. Detailed Implementation
[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0028] Pain, as the fifth vital sign, requires objective and accurate assessment, which is fundamental to clinical diagnosis, drug trials, and rehabilitation follow-up. However, current mainstream pain assessment methods still heavily rely on patient self-assessment tools such as the Visual Analogue Scale (VAS), Numerical Rating Scale (NRS), and McGill Pain Questionnaire (MPQ). While these scales are simple and easy to use, the results are highly susceptible to influences such as education level, emotional state, language ability, and momentary attention. The coefficient of variation for retests conducted at different times or by different assessors often exceeds 30%, failing to meet the reproducibility requirements of pain research and precision medicine. Meanwhile, commercially available electronic stimulation pain devices only provide electrical stimulation thresholds, and their stimulation patterns differ significantly from the most common clinical "mechanical tenderness" and "dull pressure pain," exhibiting problems such as limited stimulation dimensions and low ecological validity. While functional magnetic resonance imaging (fMRI) and laser evoked potentials (LAPs) can directly record central pain pathway activity, they face bottlenecks such as high equipment prices, complex operation, and the need for professional technicians, hindering their widespread use in outpatient and emergency departments, community hospitals, and home settings. Therefore, there is an urgent clinical need for a new pain assessment tool that combines subjective quantification, multimodal stimulation, low cost, and bedside availability to overcome the "technological gap" between traditional subjective scales and high-end neuroimaging.
[0029] To address the aforementioned issues, this application provides a pain assessment device, comprising: a mechanical pressure output module, a pressure sensing module, a subject response input module, a processing module, and a result output module; The mechanical pressure output module is used to apply mechanical pressure to the test site; the pressure sensing module is rigidly coupled to the mechanical pressure output module and is used to generate pressure-time correspondence signals as pressure changes over time in real time. Subjects reported that the input module was electrically connected to the pressure sensing module to generate event markers at the moment pain was generated and / or at the moment when the pain became intolerable. The processing module is connected to the pressure sensing module and the subject response input module. It is used to receive pressure-time corresponding signals and event markers, and extract the pain threshold pressure value and tolerance threshold pressure value from the pressure-time corresponding signals according to the event markers. Then, it calls the pre-stored continuous function model for converting pressure values into pain scores to convert the pain threshold pressure value and tolerance threshold pressure value into a quantitative pain score. The continuous function model is a polynomial function obtained by least squares fitting based on population samples. The output module is connected to the processing module via a signal and is used to present or export quantitative pain scores.
[0030] In one embodiment, the mechanical pressure output module includes: an electrically controlled linear actuator for outputting a controllable linear displacement after receiving a drive signal from the processing module; a pressure head rigidly connected to the output end of the electrically controlled linear actuator and converting the linear displacement into mechanical pressure on the test part; and a displacement / force feedback sensor for providing real-time feedback of the pressure head's displacement or actual pressure value to the processing module to form a closed-loop control.
[0031] In one embodiment, the subject response input module specifically includes: a trigger for generating a level change when pressed; and a signal interface for signal connection with the processing module to form an event marker.
[0032] In one embodiment, the pain assessment device further includes: a display screen, a power button, a zeroing button, a unit switching button, an event sound configuration button, a power supply, and a USB interface.
[0033] The displacement / force feedback sensor sends the actual mechanical force applied by the pressure head back to the processing module in real time, forming a closed loop of "drive → monitoring → correction". This closed loop ensures that the pressure rate remains constant within a certain range, avoiding overshoot caused by hand tremors or motor creep, and ensuring that the coefficient of variation of the pain threshold in three repeated tests by the same subject is less than a certain value, meeting the repeatability requirements of the international guidelines for quantitative sensory testing.
[0034] The trigger uses a mechanical micro switch and a debounce circuit, which reduces the delay from level change to the interrupt pin of the processing module. Combined with a high-frequency sampling frequency, the "subjective pain moment" can be locked within the shortest possible time window, which reduces the pressure error and ensures that the accuracy of the pain threshold pressure value is on par with the device resolution.
[0035] like Figure 1 The image shows a specific implementation of an intelligent pain assessment device. Based on international standards for quantitative sensory measurement, a prototype of an intelligent pain / sensory assessment system was developed. It objectively detects the function of pain conduction pathways, quantitatively measures pain (tenderness) thresholds and tolerance, and links to a computer program to present and record objective and accurate pain assessment results in real time.
[0036] The main parts include: (1) Pain (tenderness) force meter: ① Pressure detection component: quantitatively measures pressure perception threshold, pain perception threshold (the instant when pressure is converted into pain) and pain tolerance threshold (the instant when pain becomes unbearable); load resolution can reach 0.01 Newtons (N).
[0037] ② LCD screen: Displays real-time pressure changes and allows for the use of various dosage units. It also displays the battery level.
[0038] ③ Power button / Power button ④ Zero button: When the user presses the zero button, the current test data is cleared and the current pressure value is set as the new reference pressure.
[0039] ⑤ Unit switch key: Newton / kilogram / pound ⑥ Event Sound Configuration Key: This key allows you to configure sound effects for various events. ⑦ Power supply: Rechargeable battery.
[0040] ⑧ USB interface: Used to connect to a computer with the testing software installed.
[0041] (2) Supporting evaluation software functions: ① Built-in normal reference value library, which can be customized and added by users. ② Comparison function for different test sites (including left-right comparison, front-back comparison, etc.) ③ Automatic statistical analysis of multiple test results ④ Automatically generates graphic reports, with customizable report templates. ⑤ Data transfer function: All data can be exported to Excel spreadsheets for easy statistical analysis. ⑥ Real-time synchronization of force count and test duration ①In another specific embodiment, the device may also include additional accessories: a pressure probe calibration kit: weights that can be used to verify the calibration of the pressure gauge. ② Adapter, such as Figure 4 As shown, one end is connected to a pressure gauge and the other end is connected to a computer. ③ Test subject response components, such as Figure 5 As shown, one end is a USB cable that connects to the test computer, and the other end is a reaction button used to record the reaction of the test subject.
[0042] ④ Force gauge battery charger According to a second aspect of this application, a pain assessment method is also provided, using the pain assessment device described above, such as... Figure 2 As shown, it includes: S201: Apply mechanical pressure to the test site and record the pressure-time correspondence signal as the pressure changes over time; S202: Receive event markers issued by the subject when they experience pain and / or when the pain becomes intolerable; S203: Extract the corresponding pain threshold pressure value and tolerance threshold pressure value from the pressure-time correspondence signal based on the event marker; S204: Substitute the pain threshold pressure value and the tolerance threshold pressure value into a pre-established continuous function model for converting the pressure value into a pain score to obtain a quantitative pain score. The continuous function model is a polynomial function obtained by fitting a population sample using the least squares method.
[0043] This process transforms "subjective pain language" into "objective pressure readings": closed-loop pressurization ensures a constant rate, event marking is synchronized with 1 kHz sampling, and the threshold pressure error is ≤0.01 N; the continuous function model outputs a pain score of 0-10 points at once, avoiding interval jumps caused by segmented scales, and the CV of clinical retesting is <5%, meeting the requirements.
[0044] In one embodiment, mechanical pressure is applied via a force gauge, and the pressure load resolution is ≤0.01 N.
[0045] In one embodiment, the event marker is triggered by a test subject via a reaction button connected via USB and sent to the evaluation terminal in real time as a digital signal.
[0046] In one embodiment, the continuous function model is a mathematical model established by using the least squares method to fit polynomial curves to the stress data and pain rating data of the population sample. The fitted polynomial is used to infer the stress threshold corresponding to three points of pain, five points of pain, or seven points of pain.
[0047] In one specific embodiment, the processing module further includes a multimodal data acquisition module, a dynamic pain response modeling module, a cognitive-physiological coupling analysis module, an uncertainty perception threshold detection module, a context-adaptive evaluation module, and a result output module; The multimodal data acquisition module is used to simultaneously acquire mechanical pressure signals, heart rate variability signals, skin conductance signals, and facial expression video streams; The dynamic pain response modeling module is used to construct a three-dimensional dynamic trajectory model of the pain response. The model uses pressure P and time t as input variables and pain intensity S as output variable, and uses a time-series differential equation to describe the dynamic evolution of pain perception. dS / dt = α(P - P_0) * f(t) + β(dP / dt) - γS + ε(t) Where P_0 is the individual baseline pressure threshold, f(t) is the time modulation function, α, β, γ are individualized parameters, and ε(t) is the random perturbation term; The cognitive-physiological coupling analysis module is used to construct a bidirectional coupling network between the cognitive factor vector C and the physiological response vector Ph, and to calculate the dynamic coupling strength matrix M, where the element M_{ij} represents the time-varying coupling strength between the i-th cognitive factor and the j-th physiological response. The uncertainty perception threshold detection module is used to calculate the posterior probability distribution P(θ|D) of the pain threshold based on the Bayesian inference framework, and output the probabilistic threshold estimation result and its confidence interval. The context-adaptive evaluation module is used to dynamically adjust model parameters based on contextual information such as subject demographics, testing environment, and circadian rhythm, through a meta-learning algorithm to achieve cross-scenario adaptive evaluation. The results output module is used to output quantitative pain scores, pain sensitivity profiles, and confidence levels.
[0048] In one specific embodiment, the dynamic pain response modeling module includes: an individual baseline learning submodule: based on the subject's historical test data, using Gaussian process regression to learn the distribution of the individual baseline stress threshold P_0; P_0 ~ GP(μ_0(P), k(P,P')) Where μ_0 is the mean function and k is the kernel function; Time modulation function submodule: The time modulation function f(t) adopts a piecewise exponential decay form: f(t) = { 1, t ≤ T_onset { exp(-λ(t-T_onset)), t>T_onset Where T_onset is the moment when pain occurs, and λ is the attenuation coefficient, reflecting the pain adaptation effect; The deep neural network prediction submodule uses a long short-term memory network (LSTM) to learn the nonlinear dynamic features of the pain response. The network input is the pressure sequence {P(t-τ),...,P(t)} and the pressure change rate sequence {dP(t-τ) / dt,...,dP(t) / dt}, and the output is the predicted pain intensity sequence {S(t+1),...,S(t+Δt)}.
[0049] In one specific embodiment, the cognitive-physiological coupling analysis module includes: a cognitive factor extraction submodule: extracting a cognitive factor vector C=[C_1,C_2,...,C_m] through questionnaire scales and voice emotion analysis, including pain catastrophizing index, anxiety level, attention focus, and expected anxiety level; Physiological response extraction submodule: Extracts physiological response vector Ph=[Ph_1,Ph_2,...,Ph_n] from multimodal signals, including heart rate variability LF / HF ratio, skin conductance response amplitude, and facial electromyographic activity intensity; Dynamically Coupled Network Modeling Submodule: Constructing a time-varying coupling model between cognition and physiology. dPh(t) / dt = A*Ph(t) + B*C(t) + D*(C(t) Ph(t)) + ξ(t) Where A is the physiological self-coupling matrix, B is the cognitive driving matrix, and D is the cross-coupling tensor. This represents the outer product operation, where ξ(t) is the noise term; Coupling strength calculation submodule: Calculates the time-varying coupling strength matrix M(t), where the element M_{ij}(t) represents the influence strength of the i-th cognitive factor on the j-th physiological response at time t.
[0050] In one specific embodiment, the uncertainty perception threshold detection module includes: Prior distribution setting submodule: Sets the prior distribution of the pain threshold θ to a truncated normal distribution: θ ~ TN(μ_prior, σ_prior^2, [θ_min, θ_max]) Where μ_prior and σ_prior^2 are set based on population statistics, and [θ_min, θ_max] is the physically feasible interval; Likelihood function construction submodule: Constructing the likelihood function based on multimodal observation data D: P(D|θ) = ∏ P(D_i|θ)^{w_i} Where D_i represents the observation data of the i-th mode, and w_i represents the reliability weight of that mode; Posterior inference submodule: Calculates the posterior distribution using variational inference or Markov chain Monte Carlo methods. P(θ|D) ∝ P(D|θ) * P(θ) Probabilistic output submodule: Outputs the probability distribution characteristics of the threshold, including the posterior mean, median, confidence interval, and probability density function.
[0051] In one specific embodiment, the context-adaptive evaluation module includes: Context feature extraction submodule: Extracts context feature vector X_ctx=[age, gender, BMI, test time, ambient temperature, ambient noise, test site]; The meta-learning parameter tuning submodule employs the Model Independent Meta-Learning (MAML) algorithm to learn a set of initial model parameters θ_meta, enabling rapid adaptation to new contexts with only a small number of gradient updates. θ' = θ_meta - α* L(θ_meta; X_ctx, y) Where α is the task learning rate and L is the task loss function; Domain Adaptation Submodule: Employs an adversarial domain adaptation method, learning context-independent shared feature representations through a gradient reversal layer, and jointly optimizing the domain classifier loss and task loss. L_total = L_task + λ*(-L_domain) Where λ is the domain adaptation weight coefficient.
[0052] In one specific embodiment, the multimodal data acquisition module further includes: The timing alignment submodule uses the Dynamic Time Warping (DTW) algorithm to align signals of different modes. The alignment cost function takes into account both the peak value of the pressure signal and the delay in the physiological response. Feature-level fusion submodule: After extracting time-frequency domain features for each modality, feature fusion based on an attention mechanism is employed. F_fused = Σ w_i * F_i Where F_i is the feature vector of the i-th modality, and w_i is the attention weight, which is dynamically calculated through a learnable attention network; Decision-level fusion submodule: After each modality independently outputs pain score predictions, a weighted voting fusion method is used. S_final = Σ v_i * S_i / Σ v_i Where v_i is the confidence weight of the i-th mode, which is positively correlated with the historical prediction accuracy of that mode.
[0053] In one embodiment, the pain assessment method further includes comparing a quantitative pain score with age, gender, and / or test site stratified reference values in a built-in normal reference value library to determine whether the subject's pain perception is within the normal range.
[0054] In one embodiment, the pain assessment method further includes: displaying the pain threshold pressure value, tolerance threshold pressure value, and quantitative pain score in real time on the assessment software interface, and automatically generating a graphic report, the report content including a pressure-time curve, threshold line, and a comparison chart with the normal reference range.
[0055] In one specific embodiment, the pain assessment method and device include: 1. Pain (tenderness) force gauge module 1.1 Pressure Detection Component Pain threshold calculation: The pain threshold is calculated using the following algorithm by measuring pressure data.
[0056] Pain threshold = baseline pressure + k × pressure change Here, k is an adjustment parameter, the reference pressure is the initially measured pressure, and the pressure change is the pressure change that triggers pain.
[0057] Tolerance threshold calculation: The tolerance threshold can be calculated by the changes in data during continuous pressure application.
[0058] Tolerance threshold = reference pressure + k × pressure change Similar to pain threshold calculation, but different adjustment parameters may be used.
[0059] 2. Supporting evaluation software functional modules 2.1 Normal Reference Value Library Algorithm: Utilize statistical methods based on extensive clinical trials or laboratory data, such as mean and standard deviation, to create a database of normal reference values. The following formula can be used:
[0060] Where Xi is each value in the sample, and n is the number of samples.
[0061] 2.2 Test Site Comparison Function Algorithm: To compare data from different test sites, a percentage difference formula can be used: Percentage difference = | (value A) Value B) / Value A | × 100% Or the difference value formula: Difference value = numerical value A Numerical value B 2.3 Statistical Analysis Functions Algorithm: Use descriptive statistical methods, such as calculating the mean, median, and standard deviation.
[0062] Inferential statistical methods, such as t-tests and analysis of variance, can be used to test whether there are significant differences between two or more groups of data.
[0063] 2.4 Report Generation Function Algorithm: Utilizing a template engine or text processing algorithm, the collected data is populated into the report template. Variable substitution can be used: reporttext = reporttemplate.replace(variable, actual data) 2.5 Data transmission function Algorithm: Export the collected data to an Excel spreadsheet. This can be done using Excel format libraries or APIs. For example, using the pandas library in Python: import pandas as pd df = pd.DataFrame(data) df.to_excel('output.xlsx', index=False) 2.6 Real-time synchronization function WebSocket Connection Establishment: A bidirectional WebSocket connection is established between the evaluation software and the force gauge. WebSocket is a protocol for full-duplex communication over a single TCP connection, providing persistent connections and enabling real-time data transmission.
[0064] Real-time data transmission: When the force gauge acquires new data, it instantly sends the data to the evaluation software via a WebSocket connection. This can include pressure values, test duration, and other relevant information. WebSocket allows for real-time data exchange between the two parties, avoiding frequent connection and disconnection operations.
[0065] Event Triggering Mechanism: When a specific event occurs on the force gauge, such as the start or end of a test, or the reaching of a specific threshold, an event notification is sent to the evaluation software via WebSocket. The evaluation software can then trigger corresponding actions based on these events, such as updating the interface, logging, or triggering other operations.
[0066] Based on Python and Flask-SocketIO: # Evaluate software code from flask import Flask, render_template from flask_socketio import SocketIO app = Flask(__name__) socketio = SocketIO(app) @socketio.on('connect') def handle_connect(): print('WebSocket Connected') @socketio.on('real-time-data') def handle_real_time_data(data): print('Received Real-Time Data:', data) # Processing real-time data, updating the interface, and other operations. if __name__ == '__main__': socketio.run(app) # Force gauge terminal code import socketio sio = socketio.Client() @sio.event def connect(): print('Connected to WebSocket') def send_real_time_data(data): sio.emit('real-time-data', data) if __name__ == '__main__': sio.connect('http: / / localhost:5000') # Evaluate the WebSocket address of the software # The force gauge collects data and calls send_real_time_data to send real-time data. 3. Intelligent pain stimulation module 1. Measurement of pain threshold and maximum tolerance 1.1 Pressure Data Acquisition Module 1 measures the pain threshold and maximum tolerance of the subjects to obtain corresponding stress data.
[0067] 1.2 Data Processing The collected pressure data is preprocessed, including outlier removal and smoothing, to ensure the accuracy and reliability of the data.
[0068] 2. Polynomial Curve Fitting Module 2.1 Polynomial Fitting A mathematical model between stress data and pain levels was established by using the least squares method to fit polynomial curves.
[0069]
[0070] 2.2 Least Squares Method The goal of the least squares method is to minimize the sum of squared residuals to ensure that the fitted values are optimally related to the actual pain levels.
[0071]
[0072] 3. Threshold Inference Module By fitting the obtained polynomial curve, a threshold is set so that when the pressure data p exceeds the threshold, it can be inferred that the patient will feel three points of pain, five points of pain, or seven points of pain.
[0073]
[0074] This application uses a 0.01 N-level mechanical pressure probe to collect pressure pain signals in real time, and marks the instantaneous pressure value with the subject's button press event. Then, it substitutes the pressure into the population fitting curve to directly convert the pressure into a pain score, realizing the objectivity and quantification of pain assessment and completing it in three minutes. It gets rid of the subjective bias of traditional questionnaires and the cost threshold of high-end electrophysiological equipment.
[0075] In one specific embodiment of this application, the pain assessment method further includes the following steps: S1: Simultaneously acquire mechanical pressure signals, heart rate variability signals, skin conductance signals, and facial expression video streams of the subjects; S2: Construct a dynamic pain response trajectory model, using the time-series differential equation dS / dt = α(P-P_0)*f(t) + β(dP / dt) - γS + ε(t) to describe the dynamic evolution of pain perception, and combine it with a deep neural network to predict individualized pain response trajectories; S3: Construct a bidirectional coupling network between cognitive factors and physiological responses, calculate the time-varying coupling strength matrix, and quantify the influence of psychological factors on physiological responses; S4: Calculate the posterior probability distribution of pain threshold based on the Bayesian inference framework, and output the probabilistic threshold estimate and its confidence interval; S5: Dynamically adjust model parameters based on contextual information such as subject demographics, testing environment, and circadian rhythms using meta-learning algorithms; S6: Integrates multimodal assessment results to output quantitative pain scores, pain sensitivity profiles, and assessment confidence levels.
[0076] The dynamic pain response trajectory modeling described in step S2 also includes: Gaussian process regression was used to learn the distribution of the individual baseline stress threshold P_0; A piecewise exponential decay function is used as the time modulation function f(t) to reflect the pain adaptation effect; We use a Long Short-Term Memory (LSTM) network to learn the nonlinear temporal characteristics of pain response and predict future changes in pain intensity.
[0077] The cognitive-physiological coupling analysis described in step S3 also includes: Cognitive factors such as pain catastrophizing index, anxiety level, and attention focus were extracted through questionnaires and voice emotion analysis. Physiological responses such as heart rate variability (LF / HF ratio), skin conductance amplitude, and facial electromyographic activity intensity were extracted from multimodal signals. Construct a time-varying coupling model that includes self-coupling, cognitive-driven, and cross-coupling terms.
[0078] The uncertainty perception threshold detection in step S4 further includes: Define a truncated normal prior distribution for pain threshold; A weighted likelihood function is constructed based on multimodal observation data; The posterior probability distribution is calculated using variational inference or the MCMC method. Output probabilistic threshold estimation results, including posterior mean, confidence interval, and probability density function.
[0079] To make the technical solution of this application clearer, a detailed description is provided below with reference to specific embodiments.
[0080] Example 1: Dynamic Pain Response Trajectory Modeling Suppose a subject is undergoing a pain threshold test, with a pressure application rate of 0.5 N / s and a test duration of 30 seconds. The system is modeled according to the following steps: Step 1: Based on the subject's three historical test data, the distribution of the individual baseline P_0 is learned through Gaussian process regression, resulting in P_0 ~ N(2.8, 0.3^2). Step 2: The pressure signal P(t) is acquired in real time, and the pressure change rate dP / dt = 0.5 N / s is calculated. Step 3: When P(t) exceeds the 95% confidence upper limit of P_0 (approximately 3.4N), the analgesic response period is determined, and T_onset = t is set. Step 4: Individual parameters are fitted based on historical data: α = 0.85, β = 0.32, γ = 0.15, λ = 0.08. Step 5: The differential equation is solved to predict the pain response trajectory S(t). Step 6: An LSTM network predicts the pain intensity change over the next 500ms based on the recent 50ms pressure sequence.
[0081] Example 2: Cognitive-Physiological Coupling Analysis Assume a subject's cognitive factor assessment results are: Pain Catastrophizing Index = 28 (moderate to high level), State Anxiety = 45 (moderate level). Physiological responses collected during the test are: HRV LF / HF = 2.8 (high sympathetic activity), SCR amplitude = 0.8 μS (moderate response).
[0082] The system calculated the cognitive-physiological coupling strength: M_{catastrophizing,HRV} = 0.42 (the strength of the effect of pain catastrophizing on heart rate variability) M_{anxiety,SCR} = 0.38 (the strength of the effect of anxiety on skin conductance response) The coupling analysis results indicate that the subject's pain perception is significantly affected by psychological factors, and the assessment results need to be corrected for cognitive factors.
[0083] Example 3: Probabilistic Threshold Output The system infers the probability distribution of the pain threshold output based on Bayesian inference: - Posterior mean: E[θ|D] = 3.52 N - Posterior standard deviation: SD[θ|D] = 0.28 N - 95% confidence interval: [2.98, 4.06] N - Peak probability density: P(θ=3.5|D) = 1.42 Compared to the single numerical output of traditional methods (such as "pain threshold = 3.5N"), the probabilistic output provides richer information: the subject's pain threshold has a 95% probability of falling within the range of 2.98-4.06N, with an assessment uncertainty of ±0.28N.
[0084] Based on the same inventive concept, this application also provides a pain assessment device that can be used to implement the methods described in the above embodiments, as described in the following embodiments. Since the principle by which this pain assessment device solves the problem is similar to that of the pain assessment method, the implementation of the pain assessment device can refer to the implementation of the pain assessment method, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0085] According to a third aspect of this application, a pain assessment device is also provided, comprising: The pressurization unit is used to apply mechanical pressure to the test site and record the pressure-time correspondence signal as the pressure changes over time. An event tagging unit is used to receive event tags emitted by the subject when they experience pain and / or when the pain becomes intolerable; The pressure value extraction unit is used to extract the corresponding pain threshold pressure value and tolerance threshold pressure value from the pressure-time correspondence signal based on the event marker. The pain scoring unit is used to substitute the pain threshold pressure value and the tolerance threshold pressure value into a pre-established continuous function model for converting the pressure value into a pain score, so as to obtain a quantitative pain score. The continuous function model is a polynomial function obtained by fitting a population sample using the least squares method.
[0086] In one embodiment, mechanical pressure is applied via a force gauge, and the pressure load resolution is ≤0.01 N.
[0087] In one embodiment, the event marker is triggered by a test subject via a reaction button connected via USB and sent to the evaluation terminal in real time as a digital signal.
[0088] In one embodiment, the continuous function model is a mathematical model established by using the least squares method to fit polynomial curves to the stress data and pain rating data of the population sample. The fitted polynomial is used to infer the stress threshold corresponding to three points of pain, five points of pain, or seven points of pain.
[0089] In one embodiment, the pain assessment method further includes comparing a quantitative pain score with age, gender, and / or test site stratified reference values in a built-in normal reference value library to determine whether the subject's pain perception is within the normal range.
[0090] In one embodiment, the pain assessment method further includes: displaying the pain threshold pressure value, tolerance threshold pressure value, and quantitative pain score in real time on the assessment software interface, and automatically generating a graphic report, the report content including a pressure-time curve, threshold line, and a comparison chart with the normal reference range.
[0091] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0092] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0093] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0095] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.
[0096] This application also provides a specific implementation of an electronic device capable of implementing all the steps in the methods described above. See [link to implementation details]. Figure 3 The electronic device specifically includes the following: Figure 3 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of this application. The electronic device includes: a processor 901, a memory 902, and a bus 903.
[0097] The processor 901 and the memory 902 communicate with each other via the bus 903.
[0098] The processor 901 is used to call the computer program in the memory 902. When the processor executes the computer program, it implements all the steps in the method in the above embodiments. For example, when the processor executes the computer program, it implements the following steps: S201: Apply mechanical pressure to the test site and record the pressure-time correspondence signal as the pressure changes over time; S202: Receive event markers issued by the subject when they experience pain and / or when the pain becomes intolerable; S203: Extract the corresponding pain threshold pressure value and tolerance threshold pressure value from the pressure-time correspondence signal based on the event marker; S204: Substitute the pain threshold pressure value and the tolerance threshold pressure value into a pre-established continuous function model for converting the pressure value into a pain score to obtain a quantitative pain score. The continuous function model is a polynomial function obtained by fitting a population sample using the least squares method.
[0099] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the methods in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the methods in the above embodiments. For example, when the processor executes the computer program, it implements the following steps: S201: Apply mechanical pressure to the test site and record the pressure-time correspondence signal as the pressure changes over time; S202: Receive event markers issued by the subject when they experience pain and / or when the pain becomes intolerable; S203: Extract the corresponding pain threshold pressure value and tolerance threshold pressure value from the pressure-time correspondence signal based on the event marker; S204: Substitute the pain threshold pressure value and the tolerance threshold pressure value into a pre-established continuous function model for converting the pressure value into a pain score to obtain a quantitative pain score. The continuous function model is a polynomial function obtained by fitting a population sample using the least squares method.
[0100] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, for hardware + program embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. Although the embodiments in this specification provide the method operation steps as shown in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive means. The order of steps listed in the embodiments is merely one possible execution order among many steps and does not represent the only execution order. In actual device or terminal product execution, the methods can be executed in the order shown in the embodiments or drawings or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, product, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in the process, method, product, or apparatus that includes said elements is not excluded. For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of this specification, the functions of each module can be implemented in one or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms. This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions, which are executable by the processor of the computer or other programmable data processing device, produce instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0101] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The various embodiments in this specification are described in a progressive manner, and similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the description of the method embodiments. In the description of this specification, the reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., means that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the embodiments of this specification.
[0102] In this specification, the illustrative expressions of the terms used do not necessarily refer to the same embodiments or examples. Furthermore, those skilled in the art can combine and integrate different embodiments or examples described in this specification, as well as features of different embodiments or examples, without contradiction. The above descriptions are merely embodiments of this specification and are not intended to limit the embodiments of this specification. Various modifications and variations can be made to the embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of this specification should be included within the scope of the claims of the embodiments of this specification.
Claims
1. A pain assessment device, characterized in that, include: The system includes a mechanical pressure output module, a pressure sensing module, a subject response input module, a processing module, and a result output module, with a pain assessment model integrated in the processing module. The mechanical pressure output module is used to apply mechanical pressure to the test site; the pressure sensing module is rigidly coupled to the mechanical pressure output module and is used to generate a pressure-time correspondence signal that changes pressure over time in real time. The subject response input module is electrically connected to the pressure sensing module and is used to generate an event marker at the moment of pain and / or the moment when the pain becomes intolerable. The processing module is signal-connected to the pressure sensing module and the subject response input module. It is used to receive the pressure-time correspondence signal and the event marker, and extract the pain threshold pressure value and tolerance threshold pressure value from the pressure-time correspondence signal according to the event marker. Then, it calls a pre-stored continuous function model for converting pressure values into pain scores to convert the pain threshold pressure value and tolerance threshold pressure value into a quantitative pain score. The continuous function model is a polynomial function obtained by least squares fitting based on population samples. The result output module is signal-connected to the processing module and is used to present or export the quantitative pain score. The pain assessment model includes: a multimodal data acquisition module, a dynamic pain response modeling module, a cognitive-physiological coupling analysis module, an uncertainty perception threshold detection module, a context-adaptive assessment module, and a result output module; The multimodal data acquisition module is used to simultaneously acquire mechanical pressure signals, heart rate variability signals, skin conductance signals, and facial expression video streams; The dynamic pain response modeling module is used to construct a three-dimensional dynamic trajectory model of the pain response. The model uses pressure P and time t as input variables and pain intensity S as output variable, and uses a time-series differential equation to describe the dynamic evolution of pain perception. dS / dt = α(P - P_0) * f(t) + β(dP / dt) - γS + ε(t) Where P_0 is the individual baseline pressure threshold, f(t) is the time modulation function, α, β, γ are individualized parameters, and ε(t) is the random perturbation term; The cognitive-physiological coupling analysis module is used to construct a bidirectional coupling network between the cognitive factor vector C and the physiological response vector Ph, and to calculate the dynamic coupling strength matrix M, where the element M_{ij} represents the time-varying coupling strength between the i-th cognitive factor and the j-th physiological response. The uncertainty perception threshold detection module is used to calculate the posterior probability distribution P(θ|D) of the pain threshold based on the Bayesian inference framework, and output the probabilistic threshold estimation result and its confidence interval. The context-adaptive evaluation module is used to dynamically adjust model parameters based on contextual information such as subject demographics, testing environment, and circadian rhythm, through a meta-learning algorithm to achieve cross-scenario adaptive evaluation. The results output module is used to output quantitative pain scores, pain sensitivity profiles, and confidence levels.
2. The pain assessment device according to claim 1, characterized in that, The mechanical pressure output module includes: an electrically controlled linear actuator for outputting a controllable linear displacement after receiving a drive signal from the processing module; a pressure head rigidly connected to the output end of the electrically controlled linear actuator and converting the linear displacement into mechanical pressure on the test part; and a displacement / force feedback sensor for providing real-time feedback of the pressure head's displacement or actual pressure value to the processing module to form a closed-loop control.
3. The pain assessment device according to claim 1, characterized in that, The subject response input module specifically includes: a trigger for generating a level change when pressed; and a signal interface for signal connection with the processing module to form the event marker.
4. The pain assessment device according to claim 1, characterized in that, Also includes: Display screen, power button, reset button, unit switch button, event sound configuration button, power supply and USB port.
5. A pain assessment method, using the pain assessment device as described in claims 1-3, characterized in that, include: Mechanical pressure was applied to the test site and the pressure-time correspondence signal was recorded as the pressure changed over time. Receive event markers issued by subjects when they experience pain and / or when the pain becomes intolerable; Based on the event markers, extract the corresponding pain threshold pressure value and tolerance threshold pressure value from the pressure-time correspondence signal; The pain threshold pressure value and the tolerance threshold pressure value are substituted into a pre-established continuous function model for converting the pressure value into a pain score to obtain a quantitative pain score. The continuous function model is a polynomial function obtained by fitting a population sample using the least squares method. The process of applying mechanical pressure to the test site and recording the pressure-time correspondence signal as the pressure changes over time includes: S1: Simultaneously acquire mechanical pressure signals, heart rate variability signals, skin conductance signals, and facial expression video streams of the subjects; S2: Construct a dynamic pain response trajectory model, using the time-series differential equation dS / dt = α(P-P_0)*f(t) + β(dP / dt) - γS + ε(t) to describe the dynamic evolution of pain perception, and combine it with a deep neural network to predict individualized pain response trajectories; S3: Construct a bidirectional coupling network between cognitive factors and physiological responses, and calculate the time-varying coupling strength matrix; S4: Calculate the posterior probability distribution of pain threshold based on the Bayesian inference framework, and output the probabilistic threshold estimate and its confidence interval; S5: Based on the subject's contextual information, the model parameters are dynamically adjusted using a meta-learning algorithm. The contextual information includes the testing environment and circadian rhythm. S6: Integrates multimodal assessment results to output quantitative pain scores, pain sensitivity profiles, and assessment confidence levels.
6. The pain assessment method according to claim 5, characterized in that, The mechanical pressure is applied by a force gauge, and the pressure load resolution is ≤0.01 N.
7. The pain assessment method according to claim 5, characterized in that, The event marker is triggered by the test subject via a reaction button connected via USB and sent to the evaluation terminal in real time as a digital signal.
8. The pain assessment method according to claim 5, characterized in that, The continuous function model is a mathematical model established by fitting a polynomial curve to the population sample pressure data and pain rating data using the least squares method. The fitted polynomial is used to infer the pressure threshold corresponding to three points of pain, five points of pain, or seven points of pain.
9. The pain assessment method according to claim 5, characterized in that, Also includes: The quantitative pain score is compared with age, gender, and / or test site stratified reference values in a built-in normal reference value library to determine whether the subject's pain perception is within the normal range.
10. The pain assessment method according to claim 5, characterized in that, Also includes: The pain threshold pressure value, tolerance threshold pressure value, and quantitative pain score are displayed synchronously in real time on the assessment software interface, and a graphic report is automatically generated. The report includes a pressure-time curve, threshold line, and a comparison chart with the normal reference range.
11. A pain assessment device, characterized in that, include: The pressurization unit is used to apply mechanical pressure to the test site and record the pressure-time correspondence signal as the pressure changes over time. An event tagging unit is used to receive event tags emitted by the subject when they experience pain and / or when the pain becomes intolerable; The pressure value extraction unit is used to extract the corresponding pain threshold pressure value and tolerance threshold pressure value from the pressure-time correspondence signal based on the event marker. The pain scoring unit is used to substitute the pain threshold pressure value and the tolerance threshold pressure value into a pre-established continuous function model for converting the pressure value into a pain score to obtain a quantitative pain score. The continuous function model is a polynomial function obtained by fitting a population sample using the least squares method.
12. The pain assessment device according to claim 11, characterized in that, The mechanical pressure is applied by a force gauge, and the pressure load resolution is ≤0.01 N.
13. The pain assessment device according to claim 11, characterized in that, The event marker is triggered by the test subject via a reaction button connected via USB and sent to the evaluation terminal in real time as a digital signal.
14. The pain assessment device according to claim 11, characterized in that, The continuous function model is a mathematical model established by fitting a polynomial curve to the population sample pressure data and pain rating data using the least squares method. The fitted polynomial is used to infer the pressure threshold corresponding to three points of pain, five points of pain, or seven points of pain.
15. The pain assessment device according to claim 11, characterized in that, Also includes: The quantitative pain score is compared with age, gender, and / or test site stratified reference values in a built-in normal reference value library to determine whether the subject's pain perception is within the normal range.
16. The pain assessment device according to claim 11, characterized in that, Also includes: The pain threshold pressure value, tolerance threshold pressure value, and quantitative pain score are displayed synchronously in real time on the assessment software interface, and a graphic report is automatically generated. The report includes a pressure-time curve, threshold line, and a comparison chart with the normal reference range.
17. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the pain assessment method according to any one of claims 5 to 10.
18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the pain assessment method of any one of claims 5 to 10.