Rehabilitation nursing intelligent monitoring method and system based on image acquisition

Abstract

The invention discloses a rehabilitation nursing intelligent monitoring method and system based on image acquisition, and belongs to the technical field of rehabilitation nursing intelligent monitoring, and the method comprises the steps: collecting limb image data of a patient and a synchronous pain response value to generate a monitoring model; processing the current image data based on a monitoring model to evaluate and output a pain risk value; analyzing the fluctuation trend of a pain response curve formed based on the pain risk value to generate and output a nursing scheme; collecting subsequent image data in the process of executing the nursing scheme, monitoring a limb recovery state and outputting recovery feedback information to adjust the nursing scheme; according to the method, continuous assessment of pain risks is achieved by establishing quantitative association of visual features and pain responses, the nursing scheme is generated based on dynamic fluctuation trend analysis, a closed-loop management process is formed by recovering feedback information, and the efficiency and safety of rehabilitation nursing are improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of intelligent monitoring of rehabilitation nursing, and particularly relates to an intelligent monitoring method and system for rehabilitation nursing based on image acquisition. BACKGROUND

[0002] With the continuous rise of population aging and the incidence of chronic diseases, the demand for professional rehabilitation nursing services is increasing. The traditional rehabilitation nursing mode highly depends on the on-site observation and manual assessment of medical staff. This mode not only has high labor intensity and low efficiency, but also is easily affected by subjective factors, and is difficult to realize standardization and scaling. Therefore, it is very important to introduce intelligent and automatic monitoring technology to objectively and real-time monitor and evaluate the rehabilitation process of patients.

[0003] The traditional scheme relies on physiological electrical signals such as electroencephalogram or electromyogram to judge the pain response or muscle activation state of patients. However, the expression of pain perception and physiological electrical signals has strong individual difference, and different patients have completely different responses to the same stimulus, which makes it difficult to make reliable cross-individual comparison and evaluation. In addition, physiological electrical signals mainly reflect the electrical activity of neuromuscular, and cannot directly capture the kinematic information which is crucial in rehabilitation training, such as joint activity angle, smoothness of motion trajectory and existence of compensatory action, etc. The lack of information dimension makes the system not comprehensive enough in evaluating the overall situation of the recovery of patients' limb function, which is not conducive to the design of nursing scheme.

[0004] Therefore, there is an urgent need for a new rehabilitation nursing monitoring method and system in the industry. SUMMARY

[0005] The purpose of the present application is to provide an intelligent monitoring method for rehabilitation nursing based on image acquisition, which can accurately and carefully evaluate the pain and recovery of the patient's limbs, and also can feedback the corresponding nursing scheme according to the evaluation results.

[0006] To achieve the above-mentioned purpose of the application, the technical solution adopted by the present application is as follows: an intelligent monitoring method for rehabilitation nursing based on image acquisition, comprising the following steps: When monitoring the rehabilitation nursing of patients, the current image data of the patients is collected in real time, and the pain risk value representing the current state is evaluated and output based on the pre-generated monitoring model; Based on the plurality of pain risk values recorded within a preset time period, the fluctuation trend of the pain response curve is analyzed; According to the fluctuation trend, a nursing scheme is generated and output; And, in the process of executing the nursing scheme, the recovery state of the limbs is monitored in response to the subsequent image data collected, and recovery feedback information for adjusting the nursing scheme is output.

[0007] Preferably, the step of pre-generating the monitoring model comprises: collecting image data of a patient's limb and determining a pain response value synchronized with the image data collection time of the patient's limb; extracting a first to-be-measured parameter and a first to-be-measured feature based on the image data of the patient's limb and the pain response value, respectively; and pairing the first to-be-measured parameter with the first to-be-measured feature to form a training data pair, so as to generate the monitoring model by using a plurality of sets of the training data pair.

[0008] Preferably, the step of extracting the first to-be-measured parameter comprises: identifying a key region of the patient's limb in the image data of the patient's limb, and extracting the first to-be-measured parameter based on the key region.

[0009] Preferably, the step of evaluating and outputting the pain risk value representing the current state comprises: inputting a second to-be-measured parameter extracted based on the current image data into the monitoring model, determining and outputting the pain risk value by calculating a similarity value between the second to-be-measured parameter and the first to-be-measured parameter contained in the monitoring model.

[0010] Preferably, the step of determining and outputting the pain risk value comprises: comparing the similarity value with a preset decision threshold value; and when the similarity value is greater than or equal to the decision threshold value, calculating a treatment period based on the similarity value, and determining a decision risk value as the pain risk value according to the treatment period.

[0011] Preferably, the step of analyzing the fluctuation trend forming the pain response curve comprises: calculating a fluctuation amplitude and a fluctuation frequency based on the pain response curve; and when the fluctuation amplitude and the fluctuation frequency respectively satisfy the conditions of preset amplitude threshold value and frequency threshold value, determining the fluctuation trend as a high fluctuation stage, so as to generate the care plan based on the high fluctuation stage.

[0012] Preferably, the step of monitoring the limb recovery state comprises: extracting a third to-be-measured parameter based on the subsequent image data; and judging the limb recovery state by calculating an average similarity value between the third to-be-measured parameter and the first to-be-measured parameter contained in the monitoring model to generate the recovery feedback information.

[0013] Preferably, the step of adjusting the care plan comprises: in response to the recovery feedback information, when the recovery feedback information represents a non-recovery normal state, calculating an average pain risk value; and, when the average pain risk value is higher than a preset risk threshold, outputting an inhibition nursing scheme as the adjusted nursing scheme; or, when the average pain risk value is lower than or equal to the risk threshold, outputting a maintenance nursing scheme as the adjusted nursing scheme.

[0014] The application also provides a rehabilitation nursing intelligent monitoring system based on image acquisition, comprising: an image data acquisition module, configured to acquire current image data representing a patient state and subsequent image data in a nursing scheme execution process; a pain risk assessment module, configured in response to the current image data acquired by the image data acquisition module, for evaluating and outputting a pain risk value based on a preset monitoring model, and analyzing a plurality of the pain risk values generated within a preset time period to determine a fluctuation trend of a pain response curve; a nursing scheme generation module, configured in response to the fluctuation trend determined by the pain risk assessment module, for generating and outputting a nursing scheme; and, a recovery state monitoring module, configured in response to the subsequent image data acquired by the image data acquisition module, for monitoring a limb recovery state and outputting recovery feedback information for adjusting the nursing scheme by the nursing scheme generation module.

[0015] Illustratively, the nursing scheme generation module is further configured to output an inhibition nursing scheme as the nursing scheme when the recovery feedback information represents a non-recovery normal state and the average pain risk value calculated based thereon is higher than a preset risk threshold. Advantages

[0016] 1) The application acquires patient limb image data, determines a pain response value synchronized with the acquisition time, and then extracts a first to-be-measured parameter and a first to-be-measured feature to generate a monitoring model. In the monitoring stage, the model can output a quantitative pain risk value by comparing a second to-be-measured parameter with the first to-be-measured parameter contained in the model based on newly acquired current image data, thereby establishing a direct quantitative correlation between objective limb visual representation and subjective pain perception, realizing objective evaluation of patient pain risk, and improving the reliability of monitoring.

[0017] 2) The present application records multiple pain risk values within a preset time period to form a pain response curve, and analyzes the fluctuation trend of the curve. By calculating the fluctuation amplitude and frequency and comparing them with the corresponding threshold, the high fluctuation stage or low fluctuation stage can be identified to represent different recovery states. Therefore, the present application can grasp the rehabilitation process of the patient from the macro perspective of the fluctuation trend, so that the generated nursing plan is more targeted and predictable, and active intervention can be made according to the dynamic evolution of the patient's state.

[0018] 3) After the execution of the nursing plan, the present application collects subsequent image data to evaluate the limb recovery state and outputs recovery feedback information, which will be directly used to guide the selection of subsequent nursing plans. For example, according to the limb recovery state and the calculated average pain risk value, adaptive adjustment is made between the suppression nursing plan and the maintenance nursing plan, realizing dynamic optimization and intelligent decision-making of rehabilitation nursing, and ensuring that the nursing measures can continuously adapt to the actual recovery situation of the patient. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 is a method flowchart of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application will be further described in detail below with specific examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the protection scope of the present application.

[0021] Example 1 Please refer to Figure 1 The present embodiment provides a rehabilitation nursing intelligent monitoring method based on image acquisition, which objectively evaluates the pain risk value and limb recovery state of the patient during the rehabilitation process through a non-contact method, and generates an adaptive nursing plan accordingly. The specific process includes the following steps: Step S100: When monitoring the rehabilitation nursing of the patient, the pain risk value representing the current state is evaluated and outputted in response to the real-time acquisition of the current image data of the patient and based on the pre-generated monitoring model; Step S200: Based on the multiple pain risk values recorded within a preset time period, the fluctuation trend of the pain response curve is analyzed; Step S300: According to the fluctuation trend, a nursing plan is generated and outputted; Step S400: During the execution of the nursing plan, the limb recovery state is monitored in response to the acquisition of subsequent image data, and recovery feedback information for adjusting the nursing plan is outputted.

[0022] Specifically, a monitoring model is established that can associate the first parameter to be measured with the first feature to be measured, and image data of the patient's limbs undergoing rehabilitation training are continuously collected through image acquisition equipment, such as a high-definition camera. The model records single-frame or continuous multi-frame visual information of the morphology, position and dynamic changes of the patient's limbs during the rehabilitation training. At the same time, the patient's pain response is synchronously recorded through wearable devices or the guidance of medical staff, thereby determining the pain response value synchronized with the acquisition time of the patient's limb image data, so as to quantitatively represent the patient's subjective perception or physiological reaction of the pain level.

[0023] The monitoring model is a computational model used to map limb status parameters extracted from image data into quantified pain risk values. Its specific formula is as follows: Where, Represents the pain risk value, which is the final output of the model, representing the quantitative assessment result of the possibility of pain occurring under the current limb state; represents the current limb state vector (i.e., the first parameter to be measured or the second parameter to be measured in this article), which means the feature vector that is collected and extracted in real time and describes the current comprehensive state of the patient's limbs; Represents the training sample vector, which means the first a sample of a limb state parameter vector, i.e. a specific first parameter to be measured; Represents a kernel function, which means a function used to calculate the similarity between two input vectors in a high-dimensional feature space, such as a Gaussian kernel function ; Represents the Lagrange multiplier, which means the weight coefficient learned by the model through training data, which is used to determine the contribution of each training sample to the final prediction result; Represents the bias term, which means the bias parameter of the model, used to adjust the decision boundary; It represents the number of support vectors, which means the number of training samples that play a decisive role in the location of the decision boundary after model training.

[0024] Furthermore, in order for the monitoring model to accurately learn the relationship between pain and limb performance, it is necessary to extract a first parameter to be measured and a first feature to be measured from the raw data. The first parameter to be measured is a quantitative value that can comprehensively reflect the dynamic and static characteristics of the limb, extracted and calculated from the collected training image data during the model training phase. The first feature to be measured is generated based on the pain response value and is a target label or feature vector that can be learned by the monitoring model.

[0025] On the one hand, based on the collected image data of the patient's limb, the first parameter to be measured is extracted. Preferably, it is necessary to identify the key areas of the patient's limb in the image data of the patient's limb, such as the joint center or muscle contour, which are important for evaluating the recovery status. The identification process may specifically include: in a preset scanning area, for example, according to the limb position pre-defined by the ergonomic model, the starting point in the area, such as the geometric center of the area, is set as the initial key point; based on the initial key point, and using the prior knowledge of the limb bone structure, a preset positional relationship is extracted to describe the geometric constraints of the relative direction and distance ratio between different key areas, such as the relative direction and distance ratio between the knee joint and the ankle joint; based on the positional relationship, a series of possible joint positions are inferred from the initial key point to form multiple candidate areas, which are multiple image sub-areas that may contain real key areas; through image feature matching or morphological analysis, the area with the highest confidence is screened out from the multiple candidate areas as the final key area, and a key area list is formed.

[0026] After identifying the key areas, the inter-frame difference method or optical flow method is used to analyze the patient's limb image data to determine the limb tremor amplitude in the key areas. This involuntary tremor is an important objective indicator of the pain stress response. The limb tremor amplitude can be a quantitative indicator representing the involuntary small vibrations of the limb calculated by analyzing the position changes of the key areas between consecutive image frames; combined with the limb tremor amplitude, other key parameters such as joint movement angle and movement speed are extracted; the key parameters are weighted and fused using a preset formula to obtain a calculated value that can comprehensively reflect the limb state, and this calculated value is used as the first parameter to be measured. The purpose of this preset formula is to normalize parameters of different physical units and dimensions and give higher weights to parameters that better reflect the pain state, so as to generate a single calculated value that can comprehensively reflect the limb state.

[0027] On the other hand, based on the pain response value fed back by the patient, the first feature to be measured is extracted, which may specifically include: accurately recording the starting point of the pain reported by the patient through interactive equipment or manual inquiry, and calculating the pain starting time and the pain recovery period from the peak to the baseline based on the timestamp of the pain starting point. The length of the pain recovery period reflects the regulatory ability of the patient's nervous system; based on the calculated pain starting time and pain recovery period, the pain response value is comprehensively determined, for example, it is quantified into a numerical value within a specific range; based on the pain response value, the first feature to be measured is generated for model learning, which can be the numerical value itself or an encoded vector.

[0028] The first to-be-measured parameters extracted above are time-stamped aligned and paired with the first to-be-measured features to form training data pairs, which are data pairs composed of a first to-be-measured parameter and a first to-be-measured feature time-aligned therewith, and used as basic units for training the monitoring model. By collecting multiple sets of training data pairs at different rehabilitation stages, a monitoring model capable of predicting a pain risk value according to the first to-be-measured parameters is trained and generated by using a machine learning algorithm, such as a support vector machine, a neural network, or a gradient boosting tree.

[0029] Further, in the rehabilitation care process, a real-time monitoring mode is entered, current image data of the patient is collected, and second to-be-measured parameters are extracted based on the current image data. The second to-be-measured parameters are quantitative values reflecting the current state of the limb extracted from the current image data in the real-time monitoring stage by using the same method as that for extracting the first to-be-measured parameters.

[0030] Further, the second to-be-measured parameters are input into the monitoring model, which outputs a pain risk value by comparing the input second to-be-measured parameters with the first to-be-measured parameters contained in the monitoring model in terms of similarity in a high-dimensional space. Specifically, it can include: calculating a similarity value between the second to-be-measured parameters and the first to-be-measured parameters contained in the monitoring model, such as by calculating the Euclidean distance or the cosine similarity; comparing the similarity value with a preset decision threshold, which is set to ensure the reliability of the prediction, and if the similarity value is less than the decision threshold, it means that the current state of the limb has a lower correlation with all known pain states, and a preset default risk value is output as the pain risk value at this time, which usually represents a low-risk or unknown-risk pain risk value; if the similarity value is greater than or equal to the decision threshold, a treatment period is calculated based on the similarity value, which can be used to guide the duration of subsequent treatment or rehabilitation actions, and a decision risk value is determined and output as the pain risk value according to the treatment period.

[0031] In order to macroscopically grasp the pain change rule of the patient, multiple pain risk values generated in a preset time period are continuously recorded and connected in chronological order to form a pain response curve for visually displaying the pain risk change trend.

[0032] Further, the fluctuation trend of the pain response curve is analyzed, and a nursing scheme is output based on the analysis result. The fluctuation trend analysis can analyze the change mode of the pain response curve in a specific time period, mainly focusing on the degree and speed of change. Specifically, the fluctuation amplitude and fluctuation frequency of the pain response curve in a preset time period are calculated based on the pain response curve by a signal processing algorithm. The fluctuation amplitude reflects the change amplitude of the pain degree, and the fluctuation frequency reflects the rate of pain change. The calculated fluctuation amplitude is compared with a preset amplitude threshold, and the fluctuation frequency is compared with a preset frequency threshold. When the fluctuation amplitude meets the amplitude threshold condition and the fluctuation frequency meets the frequency threshold condition, the current fluctuation trend is determined as a high fluctuation stage, which usually means that the patient is in an unstable pain period. In other cases, the fluctuation trend is determined as a low fluctuation stage, which indicates that the pain state is relatively stable. The step of outputting the nursing scheme is based on the judgment of the high fluctuation stage or the low fluctuation stage, so as to realize the dynamic adjustment of the nursing strategy.

[0033] In the process of executing the nursing scheme output by the system, in order to form a closed-loop feedback system, it is necessary to continuously track the nursing effect, and it is necessary to continue to collect subsequent image data, and based on these subsequent image data, the third to-be-measured parameter is extracted by the same method as the above steps. The third to-be-measured parameter is a quantitative value extracted from the subsequent image data by the same method as the first to-be-measured parameter in the effect evaluation stage after the execution of the nursing scheme.

[0034] In order to judge the limb recovery state, the average similarity value between the third to-be-measured parameter and the first to-be-measured parameter contained in the monitoring model is calculated. The average similarity value can macroscopically reflect the overall matching degree of the current limb state and all known states in the model. According to the average similarity value, the limb recovery state is judged, and recovery feedback information is output, which is information representing whether the limb is currently in a normal recovery state or an abnormal recovery state. For example, the average similarity value can be compared with a preset reference threshold. If the average similarity value is higher than the reference threshold, the recovery feedback information represents a normal recovery state. If the average similarity value is lower than or equal to the reference threshold, the recovery feedback information represents an abnormal recovery state. It should be noted that the average similarity value is an average value obtained by calculating the similarity between the third to-be-measured parameter and all first to-be-measured parameters contained in the monitoring model, which is used to macroscopically evaluate the overall matching degree of the current limb state and all states learned by the model.

[0035] In response to the recovery feedback information, decision-making and plan optimization are executed. If the recovery feedback information indicates that the normal state has not been restored, the average pain risk value during the monitoring period will be calculated. If the recovery feedback information indicates that the normal state has been restored, the current care plan will continue to be executed and the subsequent average pain risk value will be recorded. The average pain risk is the value obtained by averaging multiple pain risk values ​​output by the system, which is used to reflect the overall pain risk level during the period; the calculated or recorded average pain risk value is compared with the preset risk threshold, which is the upper limit of acceptable pain in the rehabilitation plan. If the average pain risk value is higher than the risk threshold, it indicates that the current care plan may be too radical, and the suppression care plan will be output as the care plan, for example, it is recommended to reduce the training intensity. If the average pain risk value is lower than or equal to the risk threshold, it indicates that the current plan is safe and effective, and the maintenance care plan will be output as the care plan.

[0036] This embodiment can evaluate the patient's pain risk value and limb recovery status, generate a nursing plan based on the feedback of the evaluation results, and form a closed-loop management process in actual application. At the same time, by performing interventional feedback and multiple data calibrations, the execution quality and safety of rehabilitation care are effectively improved.

[0037] Example 2 This embodiment provides an intelligent rehabilitation nursing monitoring system based on image acquisition. This system is used to implement the above-mentioned intelligent rehabilitation nursing monitoring method based on image acquisition. It can objectively assess the pain risk value through real-time analysis of the patient's image data, and automatically generate and adjust the nursing plan based on the fluctuation trend of the pain response curve, thereby realizing an intelligent closed-loop management process for the rehabilitation process. The system can be divided into the following collaborative modules: The image data acquisition module is used to perform the image data acquisition task. At the beginning of monitoring, it is responsible for real-time acquisition of current image data representing the patient's status. For example, it can capture static or dynamic images of specific limbs or faces of patients during rehabilitation activities. During the implementation of the nursing plan, subsequent image data is continuously collected for subsequent recovery status monitoring. The image data can be a two-dimensional color image or a three-dimensional image data containing depth information.

[0038] The pain risk assessment module is responsible for converting raw image data into quantitative pain risk values ​​and analyzing their dynamic changes. Its specific workflow is as follows: Receive current image data provided by the image data acquisition module, and extract second parameters to be measured from the image data, for example, visual indicators related to pain including patient's facial micro-expressions, limb muscle tension, and joint movement angle identified by computer vision algorithms.

[0039] The extracted second to-be-measured parameter is input into a pre-generated monitoring model, which internally stores a large amount of reference data, i.e. the mapping relationship between the first to-be-measured parameter (derived from a large number of patient limb image data) and the first to-be-measured feature (derived from the pain response value collected synchronously with the image) established in the model training stage. The monitoring module evaluates the degree of association between the current state and the historical pain state by calculating the similarity value between the input second to-be-measured parameter and the first to-be-measured parameter stored in the model.

[0040] In order to improve the accuracy of the evaluation, the calculated similarity value is compared with a preset decision threshold. When the similarity value is greater than or equal to the decision threshold, it indicates that the current state is highly similar to a certain known pain state. A treatment period is further calculated based on the similarity value, and a decision risk value is determined according to the treatment period, which is finally output as a pain risk value representing the current state.

[0041] In a preset time period, a plurality of output pain risk values are recorded continuously, and a pain response curve is drawn based on these data points. By analyzing the curve, the fluctuation amplitude and frequency are calculated. When the calculated fluctuation amplitude and frequency meet the preset amplitude threshold and frequency threshold conditions, for example, the fluctuation is intense and frequent, the current fluctuation trend is determined as a high fluctuation stage, and the judgment result is transmitted to the nursing scheme generation module.

[0042] The nursing scheme generation module is responsible for generating and adjusting the nursing scheme according to the analysis results, and its functions include: Initial scheme generation, in response to the fluctuation trend determined by the pain risk assessment module, specifically when the "high fluctuation stage" signal is received, a targeted nursing scheme is generated and output according to the preset nursing knowledge base or rule engine, for example, the scheme may suggest suspending or reducing the intensity of the current rehabilitation activity, reminding the nursing staff to intervene manually or suggesting to take specific relaxation measures.

[0043] Dynamic adjustment of the scheme, during the execution of the nursing scheme, recovery feedback information is received from the recovery state monitoring module. When the recovery feedback information indicates that the patient's limb is not in a normal state, the average pain risk value is calculated based on a series of recent pain risk values. The average pain risk value is compared with a preset risk threshold. If the average pain risk value is higher than the risk threshold, it indicates that the current nursing scheme is ineffective or the patient's pain is aggravated, and an adjusted inhibition nursing scheme is output, for example, to further reduce the activity intensity or stop the activity completely. Otherwise, if the average pain risk value is lower than or equal to the risk threshold, it indicates that the current scheme is controllable, and a maintenance nursing scheme is output, i.e. the current scheme is continued to be executed and monitored.

[0044] The recovery state monitoring module is responsible for continuously tracking and evaluating the limb recovery state of the patient during the execution of the nursing plan, and its workflow is as follows: The subsequent image data collected by the image data acquisition module during the execution of the nursing plan is received, and based on these subsequent image data, the module extracts a third to-be-measured parameter, which is consistent with the second to-be-measured parameter in type and dimension.

[0045] By calculating the average similarity value between the third to-be-measured parameter and the first to-be-measured parameter contained in the monitoring model, the overall closeness of the current limb state to the various reference states recorded in the model is quantitatively evaluated, and this average similarity value can comprehensively reflect whether the limb is tending towards a normal pain-free state or still exhibiting pain-related visual features.

[0046] Based on the calculated average similarity value, the current limb recovery state is determined, and corresponding recovery feedback information (e.g., recovery to normal state or not) is generated and sent to the nursing plan generation module as a basis for adjusting the nursing plan.

[0047] In addition, in order for the above-mentioned system to operate effectively, the monitoring model needs to be generated in advance, and this generation process is usually completed offline before the system is deployed, specifically including: collecting a large amount of patient limb image data, and at the same time of collecting each frame of image data, a pain response value is synchronously obtained and recorded through a standard pain assessment scale (such as NRS digital scoring method) or a physiological sensor; identifying key areas (such as joints, around the wound) in the collected patient limb image data, and extracting the first to-be-measured parameter based on these key areas, and extracting the first to-be-measured feature based on the corresponding pain response value; pairing the first to-be-measured parameter with the first to-be-measured feature to form a training data pair, using multiple sets of such training data pairs, training through a machine learning algorithm (such as support vector machine, neural network), and finally generating a monitoring model that can accurately reflect the relationship between image parameters and pain degree.

[0048] Through the cooperative work of the above-mentioned image data acquisition module, pain risk assessment module, nursing plan generation module and recovery state monitoring module, the pain risk value of the patient can be objectively and continuously monitored, avoiding the delay and deviation of subjective reports, and the nursing plan can be intelligently generated and adjusted according to the fluctuation trend of the pain response curve, thereby improving the scientificity and individualization level of rehabilitation nursing, and being applicable to postoperative rehabilitation, chronic pain management and nursing scenes for patients with limited communication ability.

[0049] The above only is the preferred embodiment of the present application, and is not used to limit the present application, for the person skilled in the art, the present application can have various changes and changes, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application, should be included in the protection scope of the present application.

Claims

1. A rehabilitation nursing intelligent monitoring method based on image acquisition, characterized in that: The following steps are involved: When monitoring rehabilitation care for a patient, the system responds to the patient's current image data collected in real time and, based on a pre-generated monitoring model, evaluates and outputs a pain risk value representing the current state; analyzing a fluctuation trend of a pain response curve based on a plurality of pain risk values ​​recorded within a preset time period; Generate and output a nursing plan based on the fluctuation trend; Furthermore, during the execution of the nursing plan, the recovery state of the limb is monitored in response to the subsequent image data collected, and recovery feedback information for adjusting the nursing plan is output.

2. The method for intelligent monitoring of rehabilitation nursing based on image acquisition according to claim 1, characterized in that: The steps of pre-generating the monitoring model include: Collecting image data of a patient's limb and determining a pain response value synchronized with a time at which the image data of the patient's limb is collected; extracting a first parameter to be measured and a first feature to be measured based on the patient's limb image data and the pain response value respectively; Furthermore, the first parameter to be measured is paired with the first feature to be measured to form a training data pair, so as to generate the monitoring model using a plurality of sets of the training data pairs.

3. The method for intelligent monitoring of rehabilitation nursing based on image acquisition according to claim 2, characterized in that: The step of extracting the first parameter to be measured includes: A key area of ​​the patient's limb is identified in the patient's limb image data, and the first parameter to be measured is extracted based on the key area.

4. The method for intelligent monitoring of rehabilitation nursing based on image acquisition according to claim 2, characterized in that: The step of evaluating and outputting a pain risk value representing the current state includes: A second parameter to be measured extracted based on the current image data is input into the monitoring model, and the pain risk value is determined and output by calculating a similarity value between the second parameter to be measured and the first parameter to be measured included in the monitoring model.

5. The method for intelligent monitoring of rehabilitation nursing based on image acquisition according to claim 4, characterized in that: The step of determining and outputting the pain risk value includes: Comparing the similarity value with a preset determination threshold; Furthermore, when the similarity value is greater than or equal to the determination threshold, a treatment period is calculated based on the similarity value, and a determination risk value is determined according to the treatment period as the pain risk value.

6. The method for intelligent monitoring of rehabilitation nursing based on image acquisition according to claim 1, characterized in that: The step of analyzing the fluctuation trend of the pain response curve includes: calculating the fluctuation amplitude and the fluctuation frequency based on the pain response curve; Furthermore, when the fluctuation amplitude and the fluctuation frequency respectively meet the conditions of the preset amplitude threshold and frequency threshold, the fluctuation trend is determined to be a high fluctuation stage, so as to generate the nursing plan based on the high fluctuation stage.

7. The method for intelligent monitoring of rehabilitation nursing based on image acquisition according to claim 2, characterized in that: The step of monitoring the limb recovery status comprises: extracting a third parameter to be measured based on the subsequent image data; Furthermore, the recovery state of the limb is determined by calculating an average similarity value between the third parameter to be measured and the first parameter to be measured included in the monitoring model to generate the recovery feedback information.

8. The method for intelligent monitoring of rehabilitation nursing based on image acquisition according to claim 1, characterized in that: The step of adjusting the nursing regimen includes: In response to the recovery feedback information, when the recovery feedback information indicates that the patient has not returned to a normal state, calculating an average pain risk value; and, when the average pain risk value is higher than a preset risk threshold, outputting the suppressed nursing plan as the adjusted nursing plan; Alternatively, when the average pain risk value is lower than or equal to the risk threshold, the maintenance care plan is output as the adjusted care plan.

9. An intelligent monitoring system for rehabilitation nursing based on image acquisition, characterized in that: include: An image data acquisition module, used to acquire current image data representing the patient's condition and subsequent image data during the execution of the nursing plan; a pain risk assessment module, configured in response to the current image data acquired by the image data acquisition module, for assessing and outputting a pain risk value based on a preset monitoring model, and analyzing a plurality of pain risk values ​​generated within a preset time period to determine a fluctuation trend of a pain response curve; a nursing plan generating module, configured in response to the fluctuation trend determined by the pain risk assessment module, for generating and outputting a nursing plan; And, a recovery status monitoring module is configured in response to the subsequent image data collected by the image data collection module, for monitoring the limb recovery status and outputting recovery feedback information for the care plan generation module to adjust the care plan.

10. The intelligent monitoring system for rehabilitation nursing based on image acquisition according to claim 9, characterized in that: The nursing plan generating module is further configured to output a suppressed nursing plan as the nursing plan when the recovery feedback information indicates that the normal state has not been restored and the average pain risk value calculated based on the recovery feedback information is higher than a preset risk threshold.

Images