Pleural effusion auxiliary diagnosis method based on biomarker

Abstract

The invention relates to the technical field of pleural effusion diagnosis, and discloses a pleural effusion auxiliary diagnosis method based on a biomarker. Screening a biomarker for auxiliary diagnosis of pleural effusion; respectively carrying out data processing on the biomarkers to obtain standardized data of each biomarker; calculating the weight of each biomarker in the disease to which the pleural effusion belongs according to the standardized data of each biomarker; inputting the standardized data of each biomarker and the weight of each biomarker in the disease to which the pleural effusion belongs into a trained pleural effusion auxiliary diagnosis model, and determining the disease to which the pleural effusion belongs; the number of hidden layers in the pleural effusion auxiliary diagnosis model is changed along with the variety and number of biomarkers input into the pleural effusion auxiliary diagnosis model. The pleural effusion can be quickly and accurately diagnosed, and the diagnosis reliability is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pleural effusion diagnosis, and in particular to a biomarker-based auxiliary diagnosis method for pleural effusion. Background Art

[0002] Pleural effusion is an abnormal collection of fluid within the pleural area, indicating an imbalance in the balance between the production and removal of exudate. Excessive pleural effusion is a symptom of the underlying disease, not a condition. Cardiac, respiratory, and systemic diseases have all been associated with pleural effusion. Therefore, in addition to a pulmonologist, a patient with a pericardial effusion may also see a rheumatologist, oncologist, thoracic surgeon, and hematologist. For optimal treatment, the cause of the pleural effusion must be identified.

[0003] Due to the complexity and diversity of pleural effusion, a single biomarker is often difficult to fully and accurately reflect its cause. Etiology diagnosis is usually performed based on biomarkers of clinical characteristics, morphology, and cell biological characteristics of pleural effusion. These biomarkers can be derived from the pleural effusion itself, such as proteins, enzymes, cytokines, tumor markers, etc., or they can be indicators that indirectly reflect the status of pleural effusion by testing samples such as patient blood and urine.

[0004] As the function of the neural network model improves, it can be used to diagnose pleural effusion. However, due to the large number of biomarkers required for diagnosing pleural effusion, the following problems exist when using the neural network model to diagnose and predict pleural effusion: 1. When a large number of biomarkers are used as inputs to the neural network model, it puts a lot of pressure on the accuracy of the model's feature learning, reducing the prediction accuracy; 2. Using a neural network model with a fixed number of layers for different types and numbers of biomarkers wastes model computing power and reduces prediction efficiency.

[0005] Therefore, there is an urgent need for a biomarker-based auxiliary diagnosis method for pleural effusion that can accurately diagnose pleural effusion and improve the reliability of diagnostic results and predictive efficiency. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a biomarker-based auxiliary diagnosis method for pleural effusion, comprising the following steps: S1: Screening of biomarkers for auxiliary diagnosis of pleural effusion; S2: performing data processing on the biomarkers respectively to obtain standardized data of each biomarker; S3: Calculate the weight of each biomarker in the disease to which pleural effusion belongs based on the standardized data of each biomarker; S4: inputting the standardized data of each biomarker and the weight of each biomarker in the disease to which the pleural effusion belongs into the trained pleural effusion auxiliary diagnosis model to determine the disease to which the pleural effusion belongs; The number of hidden layers in the pleural effusion auxiliary diagnosis model is determined by the following formula: h = ka × log (1 + b × n); Wherein, h represents the number of hidden layers in the pleural effusion auxiliary diagnosis model; n represents the number of types of biomarkers, k is the first constant, a is the second constant, and b is the third constant.

[0007] As an implementation method of the present application, the pleural effusion auxiliary diagnosis model is a convolutional neural network, including feature encoding, feature enhancement and feature decoding; Among them, the attention module is used for feature enhancement, and the calculation formula of the attention module is: ; ; in, represents the element multiplier, F represents the input feature map, (F) and (A C ) are channel attention module and spatial attention module respectively, The attention map generated for the channel attention module, Attention maps generated for the spatial attention module; In addition, the residual is used to jump the link of the feature, specifically: The residual block is formed by the filter; Use the filter to connect with the residual, and then multiply it with the previous layer feature corresponding to the residual to obtain the deep layer feature corresponding to the residual; The semantic category corresponding to the deep feature is determined by multiplying the deep feature and a preset convolution kernel.

[0008] As an implementation method of the present application, the calculation process of the channel attention module is: ; in, represents the sigmoid activation function, MLP represents the dimensionality reduction operation of the multilayer perceptron; max-pool represents the maximum pooling operation, and avg-pool represents the average pooling operation.

[0009] As an implementation method of the present application, the calculation process of the spatial attention module is: ; in Represents a convolution operation.

[0010] As an implementation method of the present application, the biomarkers include: adenosine deaminase, lactate dehydrogenase, total protein, glucose, carcinoembryonic antigen, cytokeratin 19 fragment, body mass index, neuron-specific enolase, white blood cell count, monocyte count, multinuclear cell count, mesothelial cell count, specific gravity, pH value, color, gender, age, smoking status, body temperature, pulse rate, respiratory rate, blood pressure, and medical history.

[0011] As an implementation method of the present application, in S2, data processing is performed on the biomarkers respectively to obtain standardized data of each biomarker: If the biomarker value is a positive indicator, then ; If the biomarker value If is a negative indicator, ; in, is the normalized data of biomarkers, max{ } represents the maximum value of the jth biomarker, min{ } represents the minimum value of the jth biomarker.

[0012] As an implementation method of the present application, the weight of each biomarker in the disease to which pleural effusion belongs is calculated in S3 according to the standardized data of each biomarker, including the following steps: S31: Calculate the information entropy of each biomarker using the entropy weight method according to the standardized data of each biomarker, and the calculation formula is: ; Where n is the number of biomarker types, E j is the information entropy of the jth biomarker; S32: According to the information entropy of each biomarker, the weight of each biomarker in diagnosing the disease to which pleural effusion belongs is calculated using the following formula: , and the sum of the weights of each biomarker in the same pleural effusion disease is 1; Among them, W j is the weight of the jth biomarker in diagnosing the disease to which pleural effusion belongs.

[0013] As an implementation method of the present application, the number of hidden layers of the pleural effusion auxiliary diagnosis model is 30.

[0014] As an implementation method of the present application, when training the pleural effusion auxiliary diagnosis model, 80% of the sample data are randomly selected as a training set, and the remaining sample data are used as a test set.

[0015] As an implementation method of the present application, the diseases to which the pleural effusion belongs determined by the pleural effusion auxiliary diagnosis model are: malignant tumor combined with pleural effusion, parapulmonary effusion and congestive heart failure.

[0016] The embodiments of the present invention have the following technical effects: 1. In this application, pleural effusion is diagnosed based on biomarkers using a pleural effusion auxiliary diagnosis model. The selected pleural effusion auxiliary diagnosis model is a convolutional neural network, including feature encoding, feature enhancement and feature decoding; wherein, the attention module is used during feature enhancement to focus the training of the pleural effusion auxiliary diagnosis model on key areas and improve the accuracy of the model; and residuals are used for feature jump links to improve the compatibility of feature learning, enhance the accuracy of the pleural effusion auxiliary diagnosis model, and further improve the sensitivity and specificity of pleural effusion auxiliary diagnosis.

[0017] 2. In combination with the number of types of biomarkers, the number of hidden layers in the pleural effusion auxiliary diagnosis model is determined, so that the number of hidden layers changes with the number of types of biomarkers input into the pleural effusion auxiliary diagnosis model, thereby avoiding the waste of computing power and low prediction efficiency caused by using a network model with a fixed number of hidden layers for biomarkers of different types and numbers.

[0018] 3. In this application, the weights of each biomarker obtained by the entropy weight method in diagnosing the disease to which pleural effusion belongs are input into the trained pleural effusion auxiliary diagnosis model together with the standardized data of each biomarker to determine the disease to which pleural effusion belongs. Taking into account the possibility that different types of pleural effusion diseases may have different performances on the same biomarker, the reliability of the pleural effusion auxiliary diagnosis model is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 is a flow chart of a biomarker-based auxiliary diagnosis method for pleural effusion provided in an embodiment of the present invention; Figure 2It is a structural schematic diagram of a pleural effusion auxiliary diagnosis model provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0022] The detection of biomarkers in pleural effusion can be used for clinical auxiliary diagnosis of related diseases. How to screen pleural effusion biomarkers with high specificity and sensitivity and improve the diagnostic efficiency of concurrent pleural effusion-related diseases has always been a hot topic and difficulty in research in this field. This application adopts a deep learning method to introduce artificial intelligence analysis into the clinical examination of pleural effusion diseases, aiming to study the biological characteristics of pleural effusion from a multidimensional perspective, select auxiliary clinical diagnostic indicators, and evaluate the clinical value of the screened biomarkers in auxiliary clinical diagnosis.

[0023] Specifically, the present invention provides a biomarker-based auxiliary diagnosis method for pleural effusion, such as Figure 1 As shown, the method comprises the following steps: S1: Screening of biomarkers for auxiliary diagnosis of pleural effusion; Clinically, there are many biomarkers used to diagnose diseases such as pleural effusion. ROC curve analysis can be used to sort the biomarkers according to the AUC values, and the biomarkers with large AUC values ​​can be selected to accurately identify biomarkers sensitive to pleural effusion, avoiding errors caused by manual screening and reliance on clinical experience.

[0024] As an implementation method of the present application, the biomarkers include: adenosine deaminase, lactate dehydrogenase, total protein, glucose, carcinoembryonic antigen, cytokeratin 19 fragment, body mass index, neuron-specific enolase, white blood cell count, monocyte count, multinuclear cell count, mesothelial cell count, specific gravity, pH value, color, gender, age, smoking status, body temperature, pulse rate, respiratory rate, blood pressure, and medical history.

[0025] The inventor collected 286 patients with pleural effusion diseases in the Second Hospital of Tianjin Medical University from January 2021 to January 2023. According to the treatment characteristics and clinical diagnosis and treatment guidelines of combined pleural effusion, the diseases combined with pleural effusion were selected as follows: malignant tumor combined with pleural effusion (MPE) (189 cases); parapulmonary effusion (PPE) (52 cases) and congestive heart failure (CHF) and other three groups (45 cases). For the included research subjects, the patient's medical history, symptoms and signs, electrocardiogram (ECG), chest ultrasound and chest X-ray imaging examination were collected; laboratory tests were performed at the same time: the number of white blood cells (WBC) and red blood cells (RBB) in the blood; the density (RBB) and the number of red blood cells (RBB) of pleural effusion. (ECG), chest ultrasound and chest X-ray imaging examinations; laboratory tests are also performed: the number of white blood cells (WBC) and red blood cells (RBC) in the blood; the density of pleural effusion; the electrochemiluminescence method is used to measure the levels of four biomarkers such as ADA, TP, Glu and LDH; the immunochemiluminescence method is used to measure the levels of three tumor markers such as CEA, CYRFA21-1 and NSE.

[0026] According to the diagnosis and treatment guidelines for malignant tumor combined pleural effusion, parapulmonary effusion disease and congestive heart failure disease, the general clinical data of the subjects were collected, including body temperature, pulse rate, respiratory rate and systolic blood pressure. The results showed that there was no statistically significant difference in these indicators among the three groups (p>0.05).

[0027] The 23 biomarkers in the blood and pleural effusion of the above-mentioned research subjects were analyzed. The results showed that the differences in TP, ADA, CEA, CYFRA211, NSE, and MNC% among the three groups of pleural effusion diseases were statistically significant (P<0.05), while the three physical characteristics of pleural effusion, such as color, transparency, and specific gravity, and the other six biomarkers (including WBC, PNC%, MTC%, pH level, GLU, and LDH) were not statistically significant (p>0.05). Furthermore, the ROC curve was used to analyze the clinical value of the above three types of diseases. The results showed that the AUC values ​​of each indicator were: CEA (0.778), CYFRA21-1 (0.768), TP (0.737), NSE (0.718), SG (0.694), WBC (0.666), MTC% (0.614), ADA (0.566), pH (0.469), MNC% (0.487), GLU (0.543), PNC% (0.455), and MTC% (0.443). The pleural effusion of the congestive heart failure group was further analyzed. The AUC values ​​of the ROC curve analysis were as follows: pH (0.768), ADA (0.702), TP (0.772), LDH (0.693), CEA (0.784), CYRFA21-1 (0.731), NSE (0.765), WBC (0.645), MNC % (0.701), PNC % (0.564), and MTC % (0.664). The Shapiro-Wilk normality test was used to test the normality of the variables. The median and interquartile range were used to represent the distribution of biomarkers in pleural effusion. For categorical variables, chi-square test and Fisher exact test were used for intergroup comparison; for continuous variables, nonparametric Kruskal-Wallis test (because the variables were not normally distributed) was used for intergroup comparison. If the Kruskal-Wallis test result was significant, post hoc analysis was performed using the Dunn test. To determine the clinical utility of the biomarker in the study group and to assess the performance of the biomarker in distinguishing pleural effusions, the marker values ​​were reviewed by receiver operating characteristic (ROC) analysis. P < 0.05 indicated statistical significance. The ROC plot summarizes the performance of the curve classifier at all possible thresholds and is a commonly used graph. When the threshold for assigning observations to a particular class is changed, the sensitivity value is plotted against the false-positive rate or certainty1 value or true-positive rate.

[0028] S2: performing data processing on the biomarkers respectively to obtain standardized data of each biomarker; Since each indicator has different measurement units and different value ranges, the data must be standardized. Therefore, the following method will be used to standardize the data. Through this operation, all data will be in the range of [0, 1], specifically: If the biomarker value is a positive indicator, then ; If the biomarker value If is a negative indicator, ; in, is the normalized data of biomarkers, max{ } represents the maximum value of the jth biomarker, min{ } represents the minimum value of the jth biomarker.

[0029] By processing the values ​​of the biomarkers separately, the standardized data of each biomarker is obtained, thereby avoiding the problem of data inconsistency caused by different measurement units and different value ranges for each biomarker, facilitating subsequent calculations and improving computing power.

[0030] S3: Calculate the weight of each biomarker in the disease to which pleural effusion belongs based on the standardized data of each biomarker; Information entropy is an important aspect in determining the weight of evaluating biomarkers; a high information entropy indicates that the biomarker's comprehensive score contains a lot of information, so the weight is high. Entropy can be used to calculate the degree of disorder and its application in information systems.

[0031] As an implementation method of the present application, the weight of each biomarker in the disease to which pleural effusion belongs is calculated in S3 according to the standardized data of each biomarker, including the following steps: S31: Calculate the information entropy of each biomarker using the entropy weight method according to the standardized data of each biomarker, and the calculation formula is: ; Where n is the number of biomarker types, E j is the information entropy of the jth biomarker; S32: According to the information entropy of each biomarker, the weight of each biomarker in diagnosing the disease to which pleural effusion belongs is calculated using the following formula: , and the sum of the weights of each biomarker in the same pleural effusion disease is 1; Among them, W jis the weight of the jth biomarker in diagnosing the disease to which pleural effusion belongs.

[0032] A high information entropy value indicates that the data contains a large number of valuable features, so a higher weight should be given to the model.

[0033] Different types of pleural effusions may manifest differently on the same biomarker, so different biomarkers play different roles in diagnosing diseases to which pleural effusions belong. In this application, the weights of each biomarker in diagnosing diseases to which pleural effusions belong obtained by the entropy weight method are input into a trained pleural effusion auxiliary diagnosis model together with the standardized data of each biomarker to determine the disease to which the pleural effusions belong; this makes the output results of the pleural effusion auxiliary diagnosis model more accurate.

[0034] S4: inputting the standardized data of each biomarker and the weight of each biomarker in the disease to which the pleural effusion belongs into the trained pleural effusion auxiliary diagnosis model to determine the disease to which the pleural effusion belongs; The number of hidden layers in the pleural effusion auxiliary diagnosis model is determined by the following formula: h=ka×log(1+b×n); Wherein, h represents the number of hidden layers in the pleural effusion auxiliary diagnosis model; n represents the number of biomarkers; k is the first constant, which represents the maximum number of hidden layers in the absence of biomarkers; a is the second constant, which represents the maximum reduction in the number of hidden layers; b is the third constant, which represents the maximum reduction in the number of hidden layers.

[0035] The trend of the above formula, that is, the more types of biomarkers there are, the fewer the number of hidden layers in the auxiliary diagnosis model for pleural effusion, and the fewer the number of biomarkers there are, the more the number of hidden layers in the auxiliary diagnosis model for pleural effusion. In combination with the number of types of biomarkers, the number of hidden layers in the auxiliary diagnosis model for pleural effusion is determined, so that the number of hidden layers varies with the number of types of biomarkers input into the auxiliary diagnosis model for pleural effusion, avoiding the problem of waste of computing power and low prediction efficiency caused by using a network model with a fixed number of hidden layers for different numbers of biomarkers.

[0036] This study constructed an auxiliary diagnosis model for pleural effusion and analyzed the auxiliary detection value of the above-mentioned pleural effusion biomarkers from multiple dimensions. According to the characteristics of excessive pleural effusion, the clinical characteristics of patients with pleural effusion, biochemical biomarkers, tumor markers, and different types of cells in pleural effusion, an auxiliary diagnosis model for pleural effusion was designed, involving 30 hidden layers. The clinical applicability of multidimensional analysis of clinical detection markers was achieved. This study helps to improve the diagnostic efficiency of complex pleural effusion-related diseases and has potential for clinical application.

[0037] As an implementation method of the present application, the pleural effusion auxiliary diagnosis model is a convolutional neural network, including feature encoding, feature enhancement and feature decoding; The pleural effusion auxiliary diagnosis model consists of an input layer, a hidden layer, and an output layer. The input layer consists of the standardized data of 23 biomarkers and the weights of each biomarker in the disease to which pleural effusion belongs. The standardized data of each biomarker and its weight in the disease to which pleural effusion belongs are as follows: Figure 2 x1, x2, …, x23. The input data is converted to output data by applying information weights to the input data, adding biases and passing them to the activation functions of each layer. All biomarkers are converted into mathematical information and fed into the algorithm. The algorithm parameters (biases and weights) are adjusted mathematically to reduce the error between the actual results and the output values. After the training is completed, the deep learning algorithm is complete and is evaluated on the test data. Each convolutional layer consists of many units, each of which performs a convolution transformation on the previous layer by convolution multiplication with the filter. The neural network transforms the input information by convolution with the filter and returns a new signal as output. This signal reduces the features that the filter does not care about and only retains the main features. Through convolution, the key features are extracted and transmitted to the convolutional layer. Each analysis and training layer outputs a relevant biomarker, and finally summarizes the calculation results of important biomarkers in the auxiliary diagnosis of pleural effusion diseases.

[0038] Figure 2 Schematic diagram of the structure of the auxiliary diagnosis model for pleural effusion provided by an embodiment of the present invention. The auxiliary diagnosis model for pleural effusion is a convolutional neural network, and the hidden layer of the auxiliary diagnosis model for pleural effusion implements feature encoding, feature enhancement and feature decoding, automatically extracts features of pleural effusion biomarkers, and performs end-to-end training.

[0039] When encoding features, the encoder has four layers, each layer repeats two 3x3 convolution operations; each convolution is followed by a data normalization layer and an activation function (ReLU). Due to the large amount of data, the network performance is unstable. Finally, downsampling is performed through a 2×2 maximum pooling layer with a stride of 2 to double the number of feature channels.

[0040] After encoding the feature data, the underlying feature dataset is obtained, and an attention module (CBAM) is introduced between the two-step convolution operations, as shown in Figure 2 As shown in the attention module.

[0041] Among them, the attention module is used for feature enhancement, and the calculation formula of the attention module is: ; ; in, represents the element multiplier, F represents the input feature map, (F) and (A C ) are channel attention module and spatial attention module respectively, The attention map generated for the channel attention module, Attention maps generated for the spatial attention module; The channel attention module collects feature map information through average pooling and maximum pooling operations at the same time, and then performs feature dimension reduction through a multi-layer perceptron (MLP). Finally, the two features are added together, the weight coefficient is obtained through the Sigmoid activation function, and multiplied with the input feature map to obtain the scaled new feature. The calculation process of the channel attention module is: ; in, represents the sigmoid activation function, MLP represents the dimensionality reduction operation of the multilayer perceptron; max-pool represents the maximum pooling operation, and avg-pool represents the average pooling operation.

[0042] The spatial attention module first performs maximum pooling and average pooling operations along the channel axis and merges the results. Then, a convolution layer with a convolution size of 7×7 and a Sigmoid activation function is used to perform spatial attention mapping on the concatenated feature map. The calculation process of the spatial attention module is: ; in Represents a convolution operation. For example, a convolution operation with a convolution size of 7×7 may be selected. Each layer of the feature decoding part includes an upsampled feature map, followed by a 2×2 convolutional layer to halve the number of feature channels. The jump link in U-Net connects the features of the encoder and decoder. The features of the encoder are data calculated in the early layers of the network and belong to shallow features, while the features of the decoder are calculated in the deep layers of the network. The resulting data must go through multiple layers of calculation before it can be summarized as deep features. In this way, there is a semantic gap in the features merged at both ends of the jump link. Therefore, incompatible feature sets interfere with the fusion process. This part introduces Res path, which uses residuals to replace ordinary jump links. Specifically: The residual block is formed by the filter; Use the filter to connect with the residual, and then multiply it with the previous layer feature corresponding to the residual to obtain the deep layer feature corresponding to the residual; The semantic category corresponding to the deep feature is determined by multiplying the deep feature and a preset convolution kernel.

[0043] Exemplarily, each residual block consists of a 3×3 filter and a 1×1 filter. The filter is used in the convolution layer, the filter is connected to the residual, and then element-by-element multiplication is performed for fusion. 4, 3, 2, and 1 residual blocks are used on the four residual paths from the shallow layer to the deep layer, respectively. This allows the deep network to not only supplement the spatial information lost in the pooling operation, but also to maximize the fusion of these feature information. The last layer uses a 1×1 convolution to map the feature vector of each component to the corresponding semantic category.

[0044] Based on biomarkers, pleural effusion is diagnosed using a pleural effusion auxiliary diagnosis model. The selected pleural effusion auxiliary diagnosis model is a convolutional neural network, including feature encoding, feature enhancement, and feature decoding. Among them, the attention module is used during feature enhancement to focus the training of the pleural effusion auxiliary diagnosis model on key areas and improve the accuracy of the model. In addition, residuals are used for feature jump links to improve the compatibility of feature learning, enhance the accuracy of the pleural effusion auxiliary diagnosis model, and further improve the sensitivity and specificity of pleural effusion auxiliary diagnosis. As an implementation method of the present application, when training the pleural effusion auxiliary diagnosis model, 80% of the sample data are randomly selected as a training set, and the remaining sample data are used as a test set.

[0045] When training the pleural effusion auxiliary diagnosis model, the algorithm is used to optimize the cross entropy loss function and iterate. The loss is monitored on the test set to reduce overfitting of the deep model. The model with the highest accuracy is stored and used to generate classification performance on the test set. The designed algorithm randomly selects 80% of the data as a training set and the remaining 20% ​​as a test set to avoid excessive dependence of the network model on the biomarker type and improve the robustness of the model. The embodiments of the present application are implemented under the PyTorch framework and performed on a computer equipped with an Intel Core i9-7900X processor and a TITANV GPU. The operating system is Ubuntu 18.04.4 LTS.

[0046] When the pleural effusion auxiliary diagnosis model trained by this method is used for auxiliary diagnosis of male effusion, the accuracy rate can reach 78%.

[0047] As an implementation method of the present application, the diseases to which pleural effusion belongs determined by the pleural effusion auxiliary diagnosis model are: malignant tumor combined with pleural effusion, parapulmonary effusion and congestive heart failure. Figure 2 As shown in y1, y2 and y3, these are also the most important diseases of pleural effusion at present.

[0048] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0049] It should also be noted that the orientations or positional relationships indicated by the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A biomarker-based auxiliary diagnosis method for pleural effusion, characterized in that: The steps include: S1: Screening of biomarkers for auxiliary diagnosis of pleural effusion; S2: performing data processing on the biomarkers respectively to obtain standardized data of each biomarker; S3: Calculate the weight of each biomarker in the disease to which pleural effusion belongs based on the standardized data of each biomarker; S4: inputting the standardized data of each biomarker and the weight of each biomarker in the disease to which the pleural effusion belongs into the trained pleural effusion auxiliary diagnosis model to determine the disease to which the pleural effusion belongs; The number of hidden layers in the pleural effusion auxiliary diagnosis model is determined by the following formula: h = ka × log (1 + b × n); Wherein, h represents the number of hidden layers in the pleural effusion auxiliary diagnosis model; n represents the number of types of biomarkers, k is the first constant, a is the second constant, and b is the third constant.

2. A biomarker-based pleural effusion auxiliary diagnosis method according to claim 1, characterized in that: The pleural effusion auxiliary diagnosis model is a convolutional neural network. Including feature encoding, feature enhancement and feature decoding; Among them, the attention module is used for feature enhancement, and the calculation formula of the attention module is: ； ； in, represents the element multiplier, F represents the input feature map, (F) and (A C ) are channel attention module and spatial attention module respectively, The attention map generated for the channel attention module, Attention maps generated for the spatial attention module; In addition, the residual is used to jump the link of the feature, specifically: The residual block is formed by the filter; Use the filter to connect with the residual, and then multiply it with the previous layer feature corresponding to the residual to obtain the deep layer feature corresponding to the residual; The semantic category corresponding to the deep feature is determined by multiplying the deep feature and a preset convolution kernel.

3. A biomarker-based auxiliary diagnosis method for pleural effusion according to claim 2, characterized in that: The calculation process of the channel attention module is: ； in, represents the sigmoid activation function, MLP represents the dimensionality reduction operation of the multilayer perceptron; max-pool represents the maximum pooling operation, and avg-pool represents the average pooling operation.

4. A biomarker-based pleural effusion auxiliary diagnosis method according to claim 3, characterized in that: The calculation process of the spatial attention module is: ； in Represents a convolution operation.

5. The biomarker-based auxiliary diagnosis method for pleural effusion according to claim 1, characterized in that: The biomarkers include: adenosine deaminase, lactate dehydrogenase, total protein, glucose, carcinoembryonic antigen, cytokeratin 19 fragment, body mass index, neuron-specific enolase, white blood cell count, monocyte count, multinuclear cell count, mesothelial cell count, specific gravity, pH value, color, sex, age, smoking status, body temperature, pulse rate, respiratory rate, blood pressure, and medical history.

6. The biomarker-based auxiliary diagnosis method for pleural effusion according to claim 1, characterized in that: In S2, data processing is performed on the biomarkers respectively to obtain standardized data of each biomarker: If the biomarker value is a positive indicator, then ； If the biomarker value If is a negative indicator, ； in, is the normalized data of biomarkers, max{ } represents the maximum value of the jth biomarker, min{ } represents the minimum value of the jth biomarker.

7. A biomarker-based auxiliary diagnosis method for pleural effusion according to claim 6, characterized in that: In S3, according to the standardized data of each biomarker, the weight of each biomarker in the disease to which pleural effusion belongs is calculated, comprising the following steps: S31: Calculate the information entropy of each biomarker using the entropy weight method according to the standardized data of each biomarker, and the calculation formula is: ； Where n is the number of biomarker types, E j is the information entropy of the jth biomarker; S32: According to the information entropy of each biomarker, the weight of each biomarker in diagnosing the disease to which pleural effusion belongs is calculated using the following formula: , and the sum of the weights of each biomarker in the same pleural effusion disease is 1; Among them, W j is the weight of the jth biomarker in diagnosing the disease to which pleural effusion belongs.

8. The biomarker-based auxiliary diagnosis method for pleural effusion according to claim 1, characterized in that: The number of hidden layers of the pleural effusion auxiliary diagnosis model is 30.

9. The biomarker-based auxiliary diagnosis method for pleural effusion according to claim 1, characterized in that: When training the pleural effusion auxiliary diagnosis model, 80% of the sample data are randomly selected as the training set, and the remaining sample data are used as the test set.

10. The biomarker-based auxiliary diagnosis method for pleural effusion according to claim 1, characterized in that: The diseases to which pleural effusion belongs determined by the pleural effusion auxiliary diagnosis model are: malignant tumor combined with pleural effusion, parapulmonary effusion and congestive heart failure.

Images