Experimental animal postoperative urination state monitoring device and method

Abstract

The invention provides a device and method for monitoring the postoperative urination state of an experimental animal, and relates to the technical field of animal urination monitoring, and the device comprises a urination prediction module which is used for collecting diet characteristic information of the animal before an experiment, and carrying out the urination prediction; the urination volume acquisition module is used for monitoring urination after the experiment is finished; the deviation analysis module is used for obtaining a first postoperative dysuria probability according to the deviation between the predicted urination information and the total urination amount information; and the difficulty identification module is used for collecting animal activity images, carrying out urination difficulty identification, and calculating a postoperative urination difficulty probability as a postoperative urination state monitoring result in combination with the first postoperative urination difficulty probability. The technical problem that in the prior art, due to the fact that urination monitoring generally depends on a single data source, the accuracy of postoperative urination monitoring is low can be solved, and the accuracy of postoperative urination state monitoring of the experimental animal is improved by analyzing diet characteristic information and urination amount of the experimental animal and combining action analysis verification.

Description

Technical Field

[0001] The present application relates to the technical field of animal urination monitoring, and in particular to a device and method for monitoring the urination status of experimental animals after surgery. Background Art

[0002] With the deepening of biomedical research, laboratory animals play an increasingly important role in scientific experiments. Monitoring the postoperative status of laboratory animals, especially the monitoring of urination behavior, is of great significance for evaluating the effectiveness of surgery, detecting possible complications, and improving the welfare of laboratory animals. In the study of monitoring the postoperative status of laboratory animals, urination behavior is considered to be one of the important indicators for judging their postoperative recovery. Abnormal postoperative urination, such as difficulty urinating or insufficient urine output, may indicate that the animal has problems such as pain, impaired organ function, and may even reflect some underlying physiological or metabolic abnormalities. Many existing animal health monitoring systems rely mainly on a single data source to record urine volume and frequency by weighing or visual observation. However, single urine output data is easily affected by changes in the environment and diet. For example, urine evaporation may cause measurement errors, especially under experimental conditions with a long time span.

[0003] In summary, there are technical problems in the prior art that urination monitoring usually relies on a single data source and is easily affected by environmental factors, resulting in measurement errors, which further affects the accuracy of postoperative urination monitoring. Summary of the invention

[0004] The purpose of this application is to provide a device and method for monitoring the postoperative urination status of experimental animals, so as to solve the technical problem in the prior art that urination monitoring usually relies on a single data source and is easily affected by environmental factors, resulting in measurement errors, which further affects the accuracy of postoperative urination monitoring.

[0005] In view of the above problems, the present application provides a device and method for monitoring the postoperative urination status of experimental animals.

[0006] In a first aspect, the present application provides a device for monitoring the postoperative urination status of experimental animals, wherein the device comprises: a urination prediction module, the urination prediction module is used to collect dietary characteristic information of the experimental animals within a first preset time range before the experiment, perform urination prediction, and obtain predicted urination information; a urine volume acquisition module, the urine volume acquisition module is used to monitor the urination of the experimental animals within a second preset time range after the end of the experiment, and obtain total urine volume information, wherein the total urine volume information is obtained by evaporation compensation; a deviation analysis module, the deviation analysis module is used to classify and obtain a first postoperative urination difficulty probability according to the deviation between the predicted urination information and the total urine volume information; a difficulty recognition module, the difficulty recognition module is used to collect animal activity images of the experimental animals within the second preset time range, perform urination difficulty recognition, obtain a second postoperative urination difficulty probability, and calculate the postoperative urination difficulty probability in combination with the first postoperative urination difficulty probability as the postoperative urination status monitoring result of the experimental animals.

[0007] In a second aspect, the present application also provides a method for monitoring the postoperative urination status of experimental animals, wherein the method comprises: collecting dietary characteristic information of the experimental animals within a first preset time range before the experiment, performing urination prediction, and obtaining predicted urination information; within a second preset time range after the end of the experiment, performing urination monitoring on the experimental animals to obtain total urine volume information, wherein the total urine volume information is obtained by evaporation compensation; classifying and obtaining a first postoperative urination difficulty probability based on the deviation between the predicted urination information and the total urine volume information; collecting animal activity images of the experimental animals within the second preset time range, performing urination difficulty identification, and obtaining a second postoperative urination difficulty probability, and combining the first postoperative urination difficulty probability to calculate the postoperative urination difficulty probability as the postoperative urination status monitoring result of the experimental animals.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] Through the urination prediction module, the urination prediction module is used to collect the dietary characteristic information of the experimental animal within a first preset time range before the experiment, perform urination prediction, and obtain predicted urination information; the urine volume acquisition module, the urine volume acquisition module is used to monitor the urination of the experimental animal within a second preset time range after the end of the experiment, and obtain total urine volume information, wherein the total urine volume information is obtained by evaporation compensation; the deviation analysis module, the deviation analysis module is used to classify and obtain a first postoperative urination difficulty probability according to the deviation between the predicted urination information and the total urine volume information; the difficulty recognition module, the difficulty recognition module is used to collect the animal activity image of the experimental animal within the second preset time range, perform urination difficulty recognition, obtain a second postoperative urination difficulty probability, and combine the first postoperative urination difficulty probability to calculate the postoperative urination difficulty probability as the postoperative urination status monitoring result of the experimental animal. That is to say, the urination information is predicted by collecting the dietary characteristics of the animals before the experiment, and the urination of the animals is monitored after the experiment to calculate the total urine volume information; the predicted urination information and the total urine volume information are compared for deviation, and the first probability of postoperative urination difficulty is calculated; the activity images of the animals are collected, the behavioral characteristics of urination difficulty are identified, and the second probability of postoperative urination difficulty is calculated; the first probability of postoperative urination difficulty and the second probability of postoperative urination difficulty are combined to obtain the probability of postoperative urination difficulty, accurately evaluate the postoperative urination status of the experimental animals, improve the accuracy of postoperative urination difficulty monitoring of experimental animals, and reduce the risk of misjudgment.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 This is a schematic diagram of the structure of a device for monitoring the postoperative urination status of experimental animals in this application;

[0013] Figure 2 The present invention is a flowchart of a method for monitoring the postoperative urination status of experimental animals.

[0014] Explanation of reference numerals: urination prediction module 11 , urination volume acquisition module 12 , deviation analysis module 13 , difficulty identification module 14 . DETAILED DESCRIPTION

[0015] This application provides a device and method for monitoring the postoperative urination status of experimental animals, which solves the technical problem in the prior art that urination monitoring usually relies on a single data source and is easily affected by environmental factors, resulting in measurement errors, which further affects the accuracy of postoperative urination monitoring. The urination information is predicted by collecting the dietary characteristics of the animals before the experiment, and the urination of the animals is monitored after the experiment to calculate the total urination volume information; the predicted urination information and the total urination volume information are compared for deviation, and the first postoperative urination difficulty probability is calculated; the activity images of the animals are collected, the behavioral characteristics of urination difficulty are identified, and the second postoperative urination difficulty probability is calculated; the first postoperative urination difficulty probability and the second postoperative urination difficulty probability are combined to obtain the postoperative urination difficulty probability, accurately evaluate the postoperative urination status of the experimental animals, improve the accuracy of postoperative urination difficulty monitoring of experimental animals, and reduce the risk of misjudgment.

[0016] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0017] For example, please refer to the attached Figure 1 The present application provides a device for monitoring the postoperative urination status of an experimental animal, wherein the device is used to implement the steps of a method for monitoring the postoperative urination status of an experimental animal, and the device comprises:

[0018] The urination prediction module 11 is used to collect dietary characteristic information of the experimental animal within a first preset time range before the experiment, perform urination prediction, and obtain predicted urination information.

[0019] Specifically, through previous experiments or historical data, the diet and urination monitoring data of experimental animals are collected, including the animal's dietary characteristics and corresponding urination data, and the diet and urination are at the same time point. A series of sample diet feature information sets and sample urination information sets are extracted from them. Using the diet feature information set and urination information set in the sample data, training is performed through a machine learning algorithm (such as a linear regression model or a neural network model) to find the pattern between diet characteristics and urination volume. After the training is completed, the urination prediction path can predict the urination volume based on the input diet characteristics.

[0020] Before the experiment, the dietary characteristic information of the experimental animals within the first preset time range is collected, including the daily eating and drinking conditions of the experimental animals. The first preset time range is a fixed time period, which is a time window for collecting data set according to actual needs before the experimental animals are experimented, such as 12 hours, 24 hours, 48 ​​hours or longer. The collected dietary characteristic information of the experimental animals is input into the trained urination prediction path for urination prediction to obtain predicted urination information, including the expected number of urinations and urination volume of the experimental animals within the first preset time range before the experiment. By collecting the dietary characteristic information of the experimental animals before the experiment, performing urination prediction, and obtaining predicted urination information, the urination behavior of the experimental animals can be predicted in advance, while reducing unnecessary intervention.

[0021] The urine volume acquisition module 12 is used to monitor the urination of the experimental animal within a second preset time range after the end of the experiment to obtain total urine volume information, wherein the total urine volume information is obtained by evaporation compensation.

[0022] Specifically, within the second preset time range after the end of the experiment, the experimental animals are continuously monitored to collect relevant urination data, such as the number of urinations, time and urine volume, etc. The time of urination events, urine volume and other information are recorded in real time by a urine volume meter, a sensor installed at the bottom of the cage or other automated equipment. The second preset time range is similar to the first preset time range, and is a time window for collecting data set according to demand, which can be 1 hour, 5 hours, 24 hours after surgery, etc. During the experimental monitoring process, the urinated liquid is usually exposed to the air and may evaporate due to environmental factors (such as temperature and humidity). In order to compensate for the error caused by evaporation, the total urine volume needs to be corrected according to the evaporation ratio, and the compensated urine volume is obtained by dividing the measured discharge by 1-evaporation ratio. The evaporation ratio is different in different time periods, and the urine volume information needs to be compensated for evaporation according to the urination time. All urine volumes that have been compensated for evaporation are added together to obtain the total urine volume of the experimental animal within the time range. Through evaporation compensation, the influence of environmental factors (such as temperature and humidity) on urine volume measurement during the experiment is eliminated, ensuring that the final urine volume data is more accurate.

[0023] The deviation analysis module 13 is used to classify and obtain the first postoperative urinary difficulty probability according to the deviation between the predicted urination information and the total urination volume information.

[0024] Specifically, the deviation between the predicted urination information and the total urination volume information is calculated, and the urination volume deviation is obtained by calculating the difference between the predicted urination information and the total urination volume information, and calculating the ratio of the difference to the predicted urination information, thereby quantifying the difference between the predicted value and the actual value. The data of the urination volume deviation and the actual occurrence of postoperative dysuria of multiple samples are collected from historical experimental data to obtain a sample urination volume deviation set and a sample first postoperative dysuria probability set, and a dysuria classifier is trained. Each sample contains a urination volume deviation value and a corresponding probability of postoperative dysuria. By training these data, using machine learning algorithms such as decision trees, support vector machines (SVMs), or neural networks, the classifier will learn the relationship between the urination volume deviation and the probability of postoperative dysuria. For example, if the deviation is less than a certain threshold, it means that the probability of postoperative dysuria is low; if the deviation is large, the probability of postoperative dysuria is high. Once the classifier training is completed, the calculated urination volume deviation value is input into the classifier, the closest sample is indexed according to the urination volume deviation, and the corresponding dysuria probability, that is, the first postoperative dysuria probability, is output. By calculating the deviation between the predicted urination information and the actual urination volume, the prediction accuracy is quantified, and the deviation value is used as a key feature to input into the classifier, so as to more accurately predict the risk of postoperative dysuria. If an animal has a high probability of dysuria, measures can be taken in advance to avoid worsening of the condition and promote better postoperative recovery.

[0025] The difficulty identification module 14 is used to collect animal activity images of the experimental animal within the second preset time range, identify urination difficulties, obtain a second post-operative urination difficulty probability, and calculate the post-operative urination difficulty probability in combination with the first post-operative urination difficulty probability as the post-operative urination status monitoring result of the experimental animal.

[0026] Specifically, when an animal has difficulty urinating, a corresponding action performance will occur. The activity images of the experimental animals within the second preset time range, that is, the activity image sequence, are collected by video monitoring equipment or a camera, which reflects the behavioral characteristics of the animals during the postoperative recovery process, including whether they show urinary difficulties, such as frequent urination attempts, abnormal urination posture, etc. Similarly, based on the urination difficulties detection record data of the experimental animals, multiple sample activity image sequences, that is, different action performances, are obtained. At the same time, the probability of urinary difficulties in the experimental animals corresponding to different sample activity image sequences is collected to obtain a second postoperative urinary difficulties probability set, including the urinary difficulties corresponding to each activity image sequence. According to the sample activity image sequence set and the sample second postoperative urinary difficulties probability set, a convolutional neural network is used to train an activity urinary difficulties identifier. The collected activity image sequence is input into the activity urinary difficulties identifier to obtain the second postoperative urinary difficulties probability.

[0027] The urination time of the experimental animal during urination monitoring in the second preset time range is obtained, and the time weight is calculated according to the ratio of the urination time to the second preset time range. The image weight is obtained by using 1-time weight. The first probability of postoperative dysuria (probability based on urine volume deviation analysis) and the second probability of postoperative dysuria (probability based on active image recognition) are weighted and combined to calculate the final probability of postoperative dysuria. The time weight reflects the importance of urine volume data, and the image weight reflects the importance of behavioral images in prediction. The calculated probability of postoperative dysuria is used as the monitoring result of the animal's postoperative urination status, providing the experimenter with a clear value to determine whether further nursing measures or interventions are needed. By combining the analysis results of urine volume data and active image data, the actual dysuria situation of the experimental animal is fully reflected, which makes up for the lack of information that may be caused by a single data source. The weighted fusion of physical monitoring data (urine volume) and behavioral characteristic data (active images) can more accurately determine the probability of postoperative dysuria, thereby improving the reliability of prediction.

[0028] Furthermore, the urination prediction module 11 in the postoperative urination status monitoring device for experimental animals is also used for:

[0029] Collect dietary characteristic information of experimental animals within a first preset time range before the experiment; collect sample dietary characteristic information sets and sample urination information sets based on the dietary and urination monitoring data of the experimental animals; use the sample dietary characteristic information sets and sample urination information sets to train a urination prediction path; input the dietary characteristic information into the urination prediction path, and obtain predicted urination information through prediction output.

[0030] Specifically, the dietary characteristic information of the experimental animals is recorded within the first preset time range before the experiment. The first preset time range is a pre-set time period, which is a time window for collecting data set before the experimental animals are subjected to the experiment, such as 12 hours or 24 hours before the experiment. Dietary characteristic information refers to the diet-related data of the experimental animals before the experiment, including daily eating and drinking conditions, such as food intake, number of meals, water intake, food type, intake time, etc. For example, a food trough and a water bottle with a weight sensor are used to record the amount of food and the number of times the mice drink within 12 hours before the experiment, as well as the time point of each feeding and drinking.

[0031] According to the known diet and urination monitoring data of experimental animals, a certain number of sample data are selected to obtain a sample diet feature information set and a sample urination information set, which respectively record the diet characteristics of the experimental animals and the corresponding urination results. Through machine learning algorithms (such as linear regression models or neural network models), training is performed to find the law between diet characteristics and urine output. First, the sample diet feature information set and the sample urination information set are preprocessed, including data cleaning, standardization, feature extraction and other steps. According to the task requirements, select a suitable machine learning algorithm, such as linear regression, decision tree or neural network. In order to predict the urine output, a simple linear regression model can be used first to observe the linear relationship between diet characteristics and urine output. If the linear relationship is weak, a more complex model may be required, such as a random forest or a neural network.

[0032] The preprocessed sample dietary characteristics and urination information are used as input and output data sets, and a neural network is selected for model training. The number of nodes in the input layer is equal to the number of dietary characteristics, and the number of nodes in the input layer is determined according to the collected dietary characteristics. According to the complexity of the data, 1 to 3 hidden layers are selected, and each layer contains a number of neurons. The output layer contains a node for outputting the predicted urine output. The input layer receives the standardized dietary characteristic data, and passes the characteristic data to the output layer through layer-by-layer transmission to generate the predicted urine output. The neurons in each layer act through weights and biases, so that the neural network can combine different features and generate outputs. The mean square error (MSE) is used as the loss function to measure the difference between the predicted urine output and the actual urine output, and the loss function is obtained. Through the back-propagation algorithm, the partial derivative of the loss function with respect to each neuron parameter (weight and bias) is calculated to determine the change trend of the loss function, and the weight and bias are updated using an optimization algorithm (such as the Adam optimizer) so that the neural network can gradually reduce the prediction error. The neural network is trained through multiple rounds of iterations, and the model parameters are updated once on all training samples in each round of iteration.

[0033] The sample data set (test set) that did not participate in the training is input into the trained neural network model to evaluate the generalization ability of the model. The MSE or mean absolute error is calculated using the test set data to measure the prediction accuracy of the model. If the prediction error is large, the model is optimized by adjusting the neural network architecture (such as adding hidden layers, increasing the number of neurons), increasing the number of training times, adjusting the learning rate, etc., and finally the urination prediction path is obtained. The collected dietary characteristic data is input into the trained urination prediction path, and the model will output the predicted urination volume. Through the training sample data, a reliable mapping path between dietary characteristics and urination volume is established, so that the dietary conditions of experimental animals before the experiment can be used to accurately predict the postoperative urination volume and identify the risk of abnormal urination.

[0034] Furthermore, the urine volume acquisition module 12 in the postoperative urination status monitoring device for experimental animals is also used for:

[0035] Within a second preset time range after the end of the experiment, the experimental animal is monitored for urination to obtain urine volume information, and the urination time is collected; according to the urination time, the urine volume information is compensated for evaporation to obtain total urine volume information.

[0036] Specifically, within the second preset time range after the end of the experiment, a urination monitoring device is used to record the urine volume and urination time of the experimental animals. For example, the urine volume of each experimental animal can be automatically recorded by an electronic scale placed at the bottom of the cage. The weighing device can accurately detect the weight of each urination and synchronously record the time when each urination occurs. Anesthesia in surgical experiments may cause animals to have difficulty urinating. Urinating is monitored within the second preset time range after surgery, such as 1 hour. The final urine volume and the last urination time are obtained, such as a urine volume of 20 ml 45 minutes after surgery.

[0037] The urination volume is compensated for evaporation according to the urination time. Since urine evaporates within a certain period of time after discharge, the actual urination volume is less than the observed urination volume. Evaporation compensation refers to adjusting the urination volume information according to the urination time to compensate for some of the losses caused by urine evaporation. The urination time and the corresponding evaporation ratio in the historical test data are collected, and the evaporation ratio classifier is trained through a machine learning model (such as a decision tree, random forest or neural network). The urination time is input into the evaporation ratio classifier, and the corresponding evaporation ratio is mapped. According to the evaporation ratio, the urination volume information is compensated for evaporation to obtain the total urination volume information. If the monitoring time is short, evaporation compensation can be performed based on the final urination volume. If the monitoring time is long, the evaporation volume may vary due to temperature, humidity and urine exposure time. The urination volume needs to be classified according to the time period, and evaporation compensation is performed accordingly. The urination volume after evaporation compensation is summed up to obtain the total urination volume within the second preset time range. Through the evaporation compensation method, the total amount of urine excreted by experimental animals after the experiment can be estimated more accurately, reducing the error caused by evaporation, making the experimental data more real and reliable, improving the accuracy of urine output monitoring, avoiding underestimation due to evaporation, and helping to detect urination problems in a timely manner and intervene.

[0038] Furthermore, the urine volume acquisition module 12 in the postoperative urination status monitoring device for experimental animals is also used for:

[0039] According to the urination time, the evaporation ratio is mapped and obtained, wherein, according to the animal experiment urination monitoring data, a sample urination time set and a sample evaporation ratio set are collected, and an evaporation ratio classifier is constructed to perform mapping and classification; the evaporation ratio is used to perform evaporation compensation on the urine volume information to obtain the total urine volume information.

[0040] Specifically, since urine evaporates over time after discharge, it is necessary to calculate the evaporation ratio based on the urination time to more accurately estimate the actual amount of urine discharged. A large number of experimental animals' urination time and corresponding evaporation ratio data are collected from the existing animal experimental urination monitoring data as sample urination time sets and sample evaporation ratio sets, wherein the sample urination time set includes the urination data of the experimental animals at different time points, and the sample evaporation ratio set includes the evaporation ratio of urine at the corresponding time points. Use the collected sample urination time set and sample evaporation ratio set to train an evaporation ratio classifier, such as training through decision trees, support vector machines (SVM) and other algorithms. The input of the classifier is the urination time, and the output is the evaporation ratio. The decision tree maps the input data to the output category through a series of rules. It is a very intuitive model suitable for processing time-based data and mapping relationships. The support vector machine is used for classification tasks by finding a hyperplane in a high-dimensional space to maximize the boundaries between different categories. It is particularly suitable for the classification of high-dimensional data and is also quite effective in processing time data.

[0041] Data preprocessing is performed on the sample urination time set and the sample evaporation ratio set, including formatting, standardization or normalization, to ensure that the urination time and evaporation ratio are expressed in an appropriate format (such as numerical value or category). Key features are extracted from the urination time set, such as the length of time after urination, ambient temperature, humidity, etc. The key features of the urination time (as input features) and the corresponding evaporation ratio (as label data) are input into the decision tree model. During the training process, the decision tree finds the evaporation ratio corresponding to different urination time points by recursively splitting the feature space according to the different splitting nodes of the urination time. The goal of selecting the split point is to find the feature that can best distinguish different categories (i.e., different evaporation ratios) by splitting the feature space. The basis for selecting the split point is usually to measure the information contribution of a certain feature to the target variable (such as evaporation ratio). Commonly used standards include information gain and Gini index. Specifically, when starting to build a decision tree, the entropy or Gini index of the entire data set is calculated first. For each feature (urination time), try different split points. For each possible split point of each feature, calculate the entropy (or Gini index) of each subset after the split, and then calculate the information gain (or Gini gain) according to the formula. Select the feature and split point with the largest information gain or Gini gain as the current split point of the decision tree. Use cross-validation to avoid overfitting, that is, evaluate the performance of the model on unseen data by splitting the data set (for example, 80% training, 20% validation) and optimize the model parameters. After completing the training and validating the classifier, apply it to the actual urination monitoring data.

[0042] According to the urination time recorded each time, it is input into the evaporation ratio classifier and mapped to obtain the corresponding evaporation ratio. The evaporation ratio is used to compensate for the urine volume. Assuming that the urine volume 45 minutes after surgery is 20 ml, and the classifier determines that the evaporation ratio corresponding to the urination time point is 8%, the total urine volume information after compensation is 20 / (1-0.08)=21.74 ml. The evaporation ratio classifier is used to intelligently map and compensate for the evaporation ratios at different urination time points, significantly improving the accuracy of urine volume monitoring. The classifier is trained based on a large amount of sample data, and can accurately map the relationship between urination time and evaporation ratio, effectively reducing the error caused by urine evaporation, and making the experimental results closer to the actual urine volume.

[0043] Furthermore, the deviation analysis module 13 in the postoperative urination status monitoring device for experimental animals is also used for:

[0044] Calculate the difference between the predicted urination information and the total urination volume information, and calculate the ratio of the difference to the predicted urination information to obtain the urination volume deviation; collect a sample urination volume deviation set based on the urination difficulty detection record data of the experimental animals, and collect the probability of urination difficulty in animals under different sample urination volume deviations to obtain a sample first postoperative urination difficulty probability set; use the sample urination volume deviation set and the sample first postoperative urination difficulty probability set to construct a urination difficulty classifier; input the urination volume deviation into the urination difficulty classifier, obtain the first sample postoperative urination difficulty probability corresponding to the closest sample urination volume deviation, and obtain the first postoperative urination difficulty probability.

[0045] Specifically, the difference between the predicted urination information and the total urination volume information is calculated, and the ratio of this difference to the predicted urination information is calculated to obtain the urination volume deviation, which indicates the degree of deviation between the predicted urination volume and the actual urination volume. The urination difficulty detection record data refers to the observation of the urination of experimental animals in the postoperative stage to record whether they have urination difficulties. According to the urination difficulty detection record data of experimental animals, that is, the animals have abnormal delays, urination difficulties or pain during urination, and collect multiple sample urination volume deviations and corresponding postoperative urination difficulty record data. Postoperative urination difficulty refers to the urination function being affected due to physiological or drug effects after the animal undergoes surgery. The urination volume deviation set is the deviation value set of the predicted urination volume and the actual urination volume of experimental animals under different experimental conditions. The postoperative urination difficulty probability set is based on sample data, recording the probability of whether the animal has urination difficulties under different deviation values. Finally, the sample first postoperative urination difficulty probability set is obtained, including the probability of urination difficulties in animals under different urination volume deviations.

[0046] A dysuria classifier is constructed using the collected sample urine volume deviation set and the first postoperative dysuria probability set. The classifier learns the relationship between urine volume deviation and dysuria by analyzing these data, and predicts the probability of dysuria after surgery in animals given the urine volume deviation. Use supervised learning algorithms, such as decision trees, support vector machines (SVM), random forests, or neural networks. A model is established through a training data set, in which the input is the urine volume deviation and the output is the probability of dysuria. Taking the decision tree as an example, the urine volume deviation set is used as the input feature, the dysuria probability set is used as the target output, and the classifier is trained through the training set. In the decision tree model, each node represents a feature (i.e., urine volume deviation), and each branch represents a threshold judgment. During the training process, the decision tree selects the best features and split points, divides the data into different regions in turn, and finally outputs the probability of dysuria. For example, assume that the decision tree structure is as follows: if the urine volume deviation is ≤0.1, the predicted probability of dysuria is 50%; if the urine volume deviation is >0.1 and ≤0.2, the predicted probability of dysuria is 70%; if the urine volume deviation is >0.2, the predicted probability of dysuria is 80%.

[0047] The calculated urine volume deviation is input into the trained dysuria classifier, and the classifier will output the dysuria probability corresponding to the closest sample urine volume deviation. For example, if the urine volume deviation is 0.18, the classifier will determine that the urine volume deviation falls between 0.1 and 0.2, and therefore output a predicted dysuria probability of 70%. By establishing a dysuria classifier, it is possible to accurately predict whether an animal will have dysuria based on urine volume deviation, thereby improving the accuracy of monitoring the postoperative urination status of experimental animals and avoiding missing important dysuria symptoms.

[0048] Furthermore, the difficulty identification module 14 in the postoperative urination status monitoring device for experimental animals is also used for:

[0049] Collect animal activity images of the experimental animal within the second preset time range to obtain an activity image sequence; collect a set of sample activity image sequences based on the dysuria detection record data of the experimental animal, and collect the probability of dysuria in the experimental animal in different sample activity image sequences to obtain a sample second postoperative dysuria probability set; use a convolutional neural network to train an activity dysuria identifier with the sample activity image sequence set and the sample second postoperative dysuria probability set as supervised training data; input the activity image sequence into the activity dysuria identifier to identify and obtain the second postoperative dysuria probability.

[0050] Specifically, a camera or other image capture device is used to continuously capture active images of experimental animals within a second preset time range (i.e., the time range corresponding to postoperative urination monitoring) to monitor and analyze the behavior of experimental animals. An active image sequence refers to a series of images arranged in chronological order, which is used to record and analyze the activities of experimental animals. When an animal has difficulty urinating, corresponding movements will appear, such as frequent urination attempts, abnormal urination posture, etc. The urination difficulty detection record data refers to the observation of the urination of experimental animals in the postoperative stage to record whether they have difficulty urinating. According to the urination difficulty detection record data of the experimental animals, a relevant set of sample active image sequences is collected from the active image sequence, and the different active image sequences of the experimental animals will be marked according to the timestamp and associated with their corresponding urination difficulty detection records. Each sample image sequence corresponds to a record of urination difficulty, marked as urination difficulty or normal urination.

[0051] At the same time, the probability of urinary difficulties in experimental animals in different sample activity image sequences is recorded. Different action performances may have different probabilities for urinary difficulties. All activity image sequences of experimental animals and their corresponding urinary difficulties probabilities are summarized to form a second postoperative urinary difficulties probability set, which includes multiple urinary difficulties probabilities of animals in the postoperative recovery stage, and each probability corresponds to a specific set of activity image sequences. The sample activity image sequence set and the sample second postoperative urinary difficulties probability set are used as supervised training data to train the convolutional neural network model.

[0052] Convolutional neural networks are deep learning models that are particularly good at processing image data. They extract features from images through convolution operations and then gradually learn and recognize complex patterns in images through multi-layer networks. CNNs are usually composed of multiple convolutional layers, pooling layers, and fully connected layers. Convolutional neural networks automatically learn features in live images and understand which image features (such as animals standing, walking, urinating behavior, etc.) are associated with the occurrence of dysuria. During the training process, the network gradually reduces the error in predicting the probability of dysuria by adjusting its internal weights and parameters. The set of sample live image sequences is used as input, and the set of sample postoperative dysuria probabilities is used as output. The network is optimized through the back-propagation algorithm. The input sample live image sequence set first needs to be preprocessed, including standardization or normalization, image resizing, denoising, etc., to ensure that the quality of the input image is suitable for training. The convolution layer in CNN convolves the input sample live image sequence set to extract local features (such as edges, textures, etc.). The pooling layer is used to reduce the dimensionality of the data while maintaining the key features of the image. The features extracted by the convolutional layer and the pooling layer are passed to the fully connected layer for further processing, and finally the prediction result, that is, the probability of dysuria, is output. The error between the model prediction value and the true label is calculated (usually using the mean square error or cross entropy loss function), that is, the error between the predicted probability and the corresponding sample second postoperative dysuria probability is calculated, and the model weights are updated through optimization algorithms (such as Adam or SGD) to reduce the error. After training, CNN learns to identify which image features are closely related to the occurrence of dysuria.

[0053] Once the training is completed, the active dysuria identifier (i.e., the trained CNN model) can accept a new active image sequence as input, identify whether the animal has dysuria based on the features extracted from the image, and output the corresponding second postoperative dysuria probability. The collected active image sequence of the experimental animal within the second preset time range is input into the active dysuria identifier, and the model predicts the probability of dysuria in the animal based on the previously learned behavioral characteristics. For example, when the animal's active image sequence is input, the CNN model analyzes the behavioral pattern in the image, such as frequent attempts to urinate, long urination time, etc., and finally outputs a probability value of dysuria (e.g., 75%), indicating that the animal has a 75% chance of dysuria in the next period of time. By training the CNN model, the animal's active image sequence is automatically analyzed, and whether the animal has dysuria can be identified without manual intervention. Combining the active image sequence and the probability of dysuria, the model can deeply analyze the animal's behavioral characteristics and provide a more accurate prediction of dysuria. According to the behavioral patterns of different animals, it is predicted whether dysuria may occur after surgery, thereby providing each animal with personalized care and intervention plans, which helps to improve the postoperative recovery effect of experimental animals and reduce the incidence of complications.

[0054] Furthermore, the difficulty identification module 14 in the postoperative urination status monitoring device for experimental animals is also used for:

[0055] Obtain the urination time of the experimental animal during urination monitoring within the second preset time range; multiply the ratio of the urination time to the second preset time range by a preset time weight to obtain a time weight; use 1-the time weight to obtain an image weight; use the time weight and the image weight to perform a weighted calculation on the first probability of postoperative urination difficulty and the second probability of postoperative urination difficulty to obtain a postoperative urination difficulty probability.

[0056] Specifically, within the second preset time range, the urination behavior of the animal is monitored, and the start and end time of each urination is recorded. The urination time refers to the total length of time that the experimental animal urinates within the second preset time range. By monitoring the urination behavior of the experimental animal and recording the start and end time of urination, the urination time of the animal is calculated. The time weight is obtained by multiplying the ratio of the urination time to the second preset time range by the preset time weight. The preset time weight is a preset value, such as 0.6, which is used to adjust the importance of the urination time in the entire monitoring time period. The larger the ratio of the urination time to the second preset time range, the longer the urination time. The larger the time weight, the greater the impact of the stability and persistence of the urination behavior of the experimental animal in the postoperative recovery process on the probability of dysuria. The image weight is a weight adjusted in a complementary manner to the time weight, which is calculated based on the time weight and reflects the contribution of the animal activity image sequence to the prediction of the probability of dysuria. The image weight and the time weight should add up to 1.

[0057] According to the time weight and image weight, the first probability of postoperative dysuria (based on the deviation of urine volume) and the second probability of postoperative dysuria (based on the active image) are weighted and calculated to obtain the probability of postoperative dysuria. Postoperative dysuria probability = time weight × first probability of postoperative dysuria + image weight × second probability of postoperative dysuria. By adjusting the time weight and image weight, the model can flexibly respond to the urination behavior characteristics of different experimental animals. For some animals, the risk of dysuria may be more dependent on the behavioral characteristics in the active image, while for other animals, urination time may be more instructive. The dynamic adjustment of weights makes the model more adaptable and able to handle a wider range of animal behavior patterns. For example, assuming that the first probability of postoperative dysuria of animal A is 0.50, the second probability of postoperative dysuria is 0.65, the time weight is 0.4, and the image weight is 0.6, then the final probability of postoperative dysuria is 0.59. By calculating both time weights and image weights and combining two different probabilities of dysuria, the researchers were able to more comprehensively assess the risk of postoperative dysuria in experimental animals, taking into account both the duration of urination time and the visual evidence of urination behavior in the active image sequence, thereby improving the accuracy and comprehensiveness of the assessment.

[0058] In summary, the device for monitoring the postoperative urination status of experimental animals provided by the present application has the following technical effects:

[0059] Through the urination prediction module, the urination prediction module is used to collect the dietary characteristic information of the experimental animal within a first preset time range before the experiment, perform urination prediction, and obtain predicted urination information; the urine volume acquisition module, the urine volume acquisition module is used to monitor the urination of the experimental animal within a second preset time range after the end of the experiment, and obtain total urine volume information, wherein the total urine volume information is obtained by evaporation compensation; the deviation analysis module, the deviation analysis module is used to classify and obtain a first postoperative urination difficulty probability according to the deviation between the predicted urination information and the total urine volume information; the difficulty recognition module, the difficulty recognition module is used to collect the animal activity image of the experimental animal within the second preset time range, perform urination difficulty recognition, obtain a second postoperative urination difficulty probability, and combine the first postoperative urination difficulty probability to calculate the postoperative urination difficulty probability as the postoperative urination status monitoring result of the experimental animal. That is to say, the urination information is predicted by collecting the dietary characteristics of the animals before the experiment, and the urination of the animals is monitored after the experiment to calculate the total urine volume information; the predicted urination information and the total urine volume information are compared for deviation, and the first probability of postoperative urination difficulty is calculated; the activity images of the animals are collected, the behavioral characteristics of urination difficulty are identified, and the second probability of postoperative urination difficulty is calculated; the first probability of postoperative urination difficulty and the second probability of postoperative urination difficulty are combined to obtain the probability of postoperative urination difficulty, accurately evaluate the postoperative urination status of the experimental animals, improve the accuracy of postoperative urination difficulty monitoring of experimental animals, and reduce the risk of misjudgment.

[0060] Embodiment 2, based on the same inventive concept as the device for monitoring the postoperative urination status of experimental animals in the aforementioned embodiment 1, the present application also provides a method for monitoring the postoperative urination status of experimental animals, see the attached Figure 2 The method for monitoring the postoperative urination status of experimental animals comprises:

[0061] Collect dietary characteristic information of the experimental animals within a first preset time range before the experiment, perform urination prediction, and obtain predicted urination information; within a second preset time range after the end of the experiment, monitor the urination of the experimental animals to obtain total urine volume information, wherein the total urine volume information is obtained by evaporation compensation; classify and obtain a first post-operative dysuria probability based on the deviation between the predicted urination information and the total urine volume information; collect animal activity images of the experimental animals within the second preset time range, perform urination difficulty recognition, and obtain a second post-operative dysuria probability, and calculate and obtain the post-operative dysuria probability in combination with the first post-operative dysuria probability as the post-operative urination status monitoring result of the experimental animals.

[0062] Furthermore, the collecting of dietary characteristic information of the experimental animals within a first preset time range before the experiment to predict urination includes:

[0063] Collect dietary characteristic information of experimental animals within a first preset time range before the experiment; collect sample dietary characteristic information sets and sample urination information sets based on the dietary and urination monitoring data of the experimental animals; use the sample dietary characteristic information sets and sample urination information sets to train a urination prediction path; input the dietary characteristic information into the urination prediction path, and obtain predicted urination information through prediction output.

[0064] Furthermore, within a second preset time range after the end of the experiment, the experimental animal is monitored for urination to obtain total urine volume information, including:

[0065] Within a second preset time range after the end of the experiment, the experimental animal is monitored for urination to obtain urine volume information, and the urination time is collected; according to the urination time, the urine volume information is compensated for evaporation to obtain total urine volume information.

[0066] Further, performing evaporation compensation on the urine volume information according to the urination time includes:

[0067] According to the urination time, the evaporation ratio is mapped and obtained, wherein, according to the animal experiment urination monitoring data, a sample urination time set and a sample evaporation ratio set are collected, and an evaporation ratio classifier is constructed to perform mapping and classification; the evaporation ratio is used to perform evaporation compensation on the urine volume information to obtain the total urine volume information.

[0068] Further, the classifying and obtaining the probability of dysuria after the first surgery according to the deviation between the predicted urination information and the total urination volume information includes:

[0069] Calculate the difference between the predicted urination information and the total urination volume information, and calculate the ratio of the difference to the predicted urination information to obtain the urination volume deviation; collect a sample urination volume deviation set based on the urination difficulty detection record data of the experimental animals, and collect the probability of urination difficulty in animals under different sample urination volume deviations to obtain a sample first postoperative urination difficulty probability set; use the sample urination volume deviation set and the sample first postoperative urination difficulty probability set to construct a urination difficulty classifier; input the urination volume deviation into the urination difficulty classifier, obtain the first sample postoperative urination difficulty probability corresponding to the closest sample urination volume deviation, and obtain the first postoperative urination difficulty probability.

[0070] Furthermore, the collecting of the animal activity images of the experimental animal within the second preset time range, performing urination difficulty recognition, and obtaining the second postoperative urination difficulty probability includes:

[0071] Collect animal activity images of the experimental animal within the second preset time range to obtain an activity image sequence; collect a set of sample activity image sequences based on the dysuria detection record data of the experimental animal, and collect the probability of dysuria in the experimental animal in different sample activity image sequences to obtain a sample second postoperative dysuria probability set; use a convolutional neural network to train an activity dysuria identifier with the sample activity image sequence set and the sample second postoperative dysuria probability set as supervised training data; input the activity image sequence into the activity dysuria identifier to identify and obtain the second postoperative dysuria probability.

[0072] Further, the calculating the probability of postoperative dysuria in combination with the first probability of postoperative dysuria includes:

[0073] Obtain the urination time of the experimental animal during urination monitoring within the second preset time range; multiply the ratio of the urination time to the second preset time range by a preset time weight to obtain a time weight; use 1-the time weight to obtain an image weight; use the time weight and the image weight to perform a weighted calculation on the first probability of postoperative urination difficulty and the second probability of postoperative urination difficulty to obtain a postoperative urination difficulty probability.

[0074] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The device and specific examples of monitoring the postoperative urination status of experimental animals in the first embodiment are also applicable to the method of monitoring the postoperative urination status of experimental animals in the present embodiment. Through the above detailed description of the device for monitoring the postoperative urination status of experimental animals, those skilled in the art can clearly know the method of monitoring the postoperative urination status of experimental animals in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here. As for the method disclosed in the embodiment, since it corresponds to the device disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the device part.

[0075] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0076] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A device for monitoring the urination status of experimental animals after surgery, characterized in that: include: A urination prediction module, which is used to collect dietary characteristic information of the experimental animal within a first preset time range before the experiment, perform urination prediction, and obtain predicted urination information; A urine volume acquisition module, which is used to monitor the urination of the experimental animal within a second preset time range after the end of the experiment to obtain total urine volume information, wherein the total urine volume information is obtained by evaporation compensation; A deviation analysis module, the deviation analysis module is used to classify and obtain the probability of dysuria after the first operation according to the deviation between the predicted urination information and the total urination volume information; A difficulty identification module is used to collect animal activity images of the experimental animal within the second preset time range, identify urination difficulties, obtain a second post-operative urination difficulty probability, and calculate the post-operative urination difficulty probability in combination with the first post-operative urination difficulty probability as the post-operative urination status monitoring result of the experimental animal.

2. The postoperative urination status monitoring device for experimental animals according to claim 1, characterized in that: Collect the dietary characteristics of the experimental animals within the first preset time range before the experiment to predict urination, including: Collecting dietary characteristic information of the experimental animals within a first preset time range before the experiment; According to the experimental animals' diet and urination monitoring data, a sample diet characteristic information set and a sample urination information set are collected; Using the sample diet feature information set and the sample urination information set to train a urination prediction path; The dietary characteristic information is input into the urination prediction path, and the prediction output is used to obtain the predicted urination information.

3. The postoperative urination status monitoring device for experimental animals according to claim 1, characterized in that: Within a second preset time range after the end of the experiment, the experimental animal is monitored for urination to obtain total urine volume information, including: Within a second preset time range after the end of the experiment, monitoring the urination of the experimental animal to obtain urine volume information and collect urination time; According to the urination time, evaporation compensation is performed on the urine volume information to obtain total urine volume information.

4. The device for monitoring the postoperative urination status of experimental animals according to claim 3, characterized in that: According to the urination time, evaporation compensation is performed on the urine volume information, including: According to the urination time, the evaporation ratio is obtained by mapping, wherein a sample urination time set and a sample evaporation ratio set are collected according to the animal experiment urination monitoring data, and an evaporation ratio classifier is constructed to perform mapping classification; The evaporation ratio is used to perform evaporation compensation on the urine volume information to obtain total urine volume information.

5. The device for monitoring the postoperative urination status of experimental animals according to claim 3, characterized in that: According to the deviation between the predicted urination information and the total urination volume information, the probability of dysuria after the first operation is obtained by classification, including: Calculating a difference between the predicted urination information and the total urination volume information, and calculating a ratio of the difference to the predicted urination information to obtain a urination volume deviation; According to the urination difficulty detection record data of the experimental animals, the sample urine volume deviation set is collected, and the probability of urination difficulty in animals under different sample urine volume deviations is collected to obtain the sample first postoperative urination difficulty probability set; Using the sample urine volume deviation set and the sample first postoperative dysuria probability set, constructing a dysuria classifier; The urine volume deviation is input into the dysuria classifier, and the first sample postoperative dysuria probability corresponding to the closest sample urine volume deviation is obtained by index classification to obtain the first postoperative dysuria probability.

6. The device for monitoring the postoperative urination status of experimental animals according to claim 1, characterized in that: Collecting animal activity images of the experimental animal within the second preset time range, performing urination difficulty recognition, and obtaining a second postoperative urination difficulty probability, including: Collecting animal activity images of the experimental animal within the second preset time range to obtain an activity image sequence; According to the urination difficulty detection record data of the experimental animals, a set of sample activity image sequences is collected, and the probability of urination difficulty occurring in the experimental animals in different sample activity image sequences is collected to obtain a set of sample second postoperative urination difficulty probabilities; Using a convolutional neural network, the sample activity image sequence set and the sample second postoperative dysuria probability set are used as supervised training data to train an activity dysuria identifier; The active image sequence is input into the active urination difficulty identifier to identify and obtain the second postoperative urination difficulty probability.

7. The device for monitoring the postoperative urination status of experimental animals according to claim 1, characterized in that: Combining the first postoperative dysuria probability, calculating the postoperative dysuria probability includes: Obtaining the urination time of the experimental animal during urination monitoring within the second preset time range; According to the ratio of the urination time to the second preset time range, multiplying it by a preset time weight to obtain a time weight; Using 1-the time weight, obtain the image weight; The first probability of postoperative dysuria and the second probability of postoperative dysuria are weightedly calculated by using the time weight and the image weight to obtain the probability of postoperative dysuria.

8. A method for monitoring the postoperative urination status of experimental animals, characterized in that: The method for monitoring the postoperative urination status of an experimental animal is performed by a device for monitoring the postoperative urination status of an experimental animal according to any one of claims 1 to 7, and comprises: Collecting dietary characteristic information of the experimental animals within a first preset time range before the experiment, performing urination prediction, and obtaining predicted urination information; Within a second preset time range after the end of the experiment, monitoring the urination of the experimental animal to obtain total urine volume information, wherein the total urine volume information is obtained by evaporation compensation; According to the deviation between the predicted urination information and the total urination volume information, classify and obtain the probability of dysuria after the first operation; The animal activity images of the experimental animal within the second preset time range are collected to identify dysuria and obtain a second probability of dysuria after surgery. The second probability of dysuria after surgery is calculated and obtained in combination with the first probability of dysuria after surgery as the monitoring result of the postoperative urination status of the experimental animal.

Images