Perioperative period data calculation method, terminal equipment and computer readable storage medium

Abstract

The invention is suitable for the technical field of data processing, and provides a perioperative period data calculation method, terminal equipment and a computer readable storage medium, and the method comprises the steps: obtaining time sequence data of a first mode in an operation process of a target disease, and obtaining first time sequence data; extracting a first time sequence feature of the first time sequence data; predicting a second time sequence feature of second time sequence data according to the first time sequence feature; wherein the second time sequence data is time sequence data of a second mode in the operation process of the target disease. In the embodiment of the invention, the time sequence characteristic of the time sequence data of another mode is predicted through the time sequence characteristic of the time sequence data of one mode, so that the time sequence data of different modes are finely aligned at the characteristic level, the association of the data of different modes at the characteristic level is considered, and the accuracy and robustness of data completion are effectively improved.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to a perioperative data calculation method, a terminal device, and a computer-readable storage medium. Background Art

[0002] With the continuous advancement of medical technology and the growing clinical needs, multimodal medical models play an important role in medical research and clinical practice. Multimodal medical models have the potential to process complex data and provide accurate diagnosis and treatment plans. They can integrate a variety of medical data, including imaging, genes, electronic medical records, etc., to provide strong support for disease diagnosis, risk prediction and personalized treatment.

[0003] Due to technical limitations, disease progression, and other reasons, some modal data may not be available or have high heterogeneity, which affects the accuracy and reliability of subsequent processing such as disease diagnosis and risk prediction. Therefore, how to optimize the use of missing data sets without sacrificing the performance of multimodal medical models has become an important direction of current research. Summary of the invention

[0004] The embodiments of the present application provide a perioperative data calculation method, a terminal device, and a computer-readable storage medium, which can improve the accuracy and robustness of data completion.

[0005] In a first aspect, an embodiment of the present application provides a perioperative data calculation method, comprising: Acquire time series data of a first modality during a surgical procedure for a target disease to obtain first time series data; Extracting a first time series feature of the first time series data; Predicting a second time series feature of second time series data based on the first time series feature; wherein the second time series data is time series data of a second modality during surgery for the target disease.

[0006] In an embodiment of the present application, the time series features of time series data of one modality are used to predict the time series features of time series data of another modality, so that the time series data of different modalities are finely aligned at the feature level, and the correlation between the data of different modalities at the feature level is taken into account, which effectively improves the accuracy and robustness of data completion.

[0007] In a possible implementation manner of the first aspect, predicting a second time series feature of second time series data according to the first time series feature includes: Performing time series analysis according to the first time series feature to generate a third time series feature; wherein the time series analysis is used to obtain the overall trend and change law of the input data; Performing frequency domain analysis according to the first time series feature to generate a fourth time series feature; wherein the frequency domain analysis is used to obtain frequency domain features of input data and transform the obtained frequency domain features into the time domain; The second timing characteristic is obtained according to the third timing characteristic and the fourth timing characteristic.

[0008] In the above method, polynomial regression is used to model the inherent overall trend and change law of the time series feature sequence, providing macro guidance for subsequent processing. Frequency domain analysis enables the model to have a deeper understanding of the semantic meaning of the time series, thereby generating more accurate and detailed time series features. The combination of the results of time series analysis and frequency domain analysis helps to accurately mine time series features.

[0009] In a possible implementation manner of the first aspect, the method further includes: Acquire first sample data and second sample data during a surgical procedure for the target disease; wherein the first sample data is time series data of the first modality, and the second sample data is time series data of the second modality; Performing fusion processing on the first sample data and the second sample data to obtain fused time series data; A first model is trained according to the fused time series data to obtain the trained first model; wherein the trained first model is used to extract the first time series features of the first time series data.

[0010] In the above training method, by fusing time series data of different modalities, the trained model can learn the intrinsic correlation between time series data of different modalities, which helps to improve the accuracy of the model.

[0011] In a possible implementation manner of the first aspect, the method further includes: Acquire third sample data and fourth sample data during the surgical procedure of the target disease; wherein the third sample data is the time series data of the first modality, and the fourth sample data is the time series data of the second modality; A second model is trained according to the third sample data and the fourth sample data to obtain the trained second model; wherein the trained second model is used to predict the second time series feature of the second time series data according to the first time series feature.

[0012] In a possible implementation manner of the first aspect, the training a second model according to the third sample data and the fourth sample data to obtain the trained second model includes: Performing multi-dimensional feature extraction on the third sample data and the fourth sample data in the frequency domain to obtain multi-dimensional frequency domain features; Completing the third sample data and the fourth sample data according to the multi-dimensional frequency domain features to obtain the third sample data and the fourth sample data after preliminary completion; The second model is trained according to the third sample data and the fourth sample data after preliminary completion to obtain the trained second model.

[0013] In the above method, the multi-dimensional frequency domain features enrich the data representation capability and are conducive to providing multi-dimensional and multi-level feature information; preliminary completion is performed based on the multi-dimensional frequency domain features to make the sample data more complete and accurate, thereby providing reliable data support for subsequent model training.

[0014] In a possible implementation manner of the first aspect, the step of training the second model includes: Inputting the third sample data into the trained first model to obtain actual time series features of the third sample data; Inputting the actual time series characteristics of the third sample data into the second model to obtain the predicted time series characteristics of the fourth sample data; Inputting the fourth sample data into the trained first model to obtain actual time series features of the fourth sample data; Calculate the model loss value according to the actual time series characteristics of the third sample data, the actual time series characteristics of the fourth sample data, and the predicted time series characteristics; If the model loss value is less than a preset value, determining the current second model as the trained second model; If the model loss value is greater than a preset value, the model parameters of the second model are adjusted according to the model loss value to obtain the adjusted second model, and the adjusted second model is continued to be trained until the trained second model is obtained.

[0015] In a possible implementation manner of the first aspect, calculating the model loss value according to the actual time series feature of the third sample data, the actual time series feature of the fourth sample data, and the predicted time series feature includes: Obtaining a predicted probability of occurrence of the target disease according to the predicted time series characteristics of the fourth sample data; Calculate a first loss value according to the predicted occurrence probability and the actual occurrence probability corresponding to the fourth sample data; Calculate a second loss value according to the actual time series characteristics and the predicted time series characteristics of the fourth sample data; Predicting the predicted time series characteristics of the third sample data according to the actual time series characteristics of the fourth sample data; Calculate a third loss value according to the actual time series characteristics and the predicted time series characteristics of the third sample data; The model loss value is calculated according to the first loss value, the second loss value and the third loss value.

[0016] In the calculation method of the above model loss value, the first loss value is an important indicator to measure the difference between the predicted probability of occurrence of the target disease and the actual probability of occurrence, which forms an indirect constraint on the model and is conducive to improving the accuracy of data reconstruction; the second loss value can improve the accuracy of the model in reconstructing the timing characteristics during the forward propagation process to retain the integrity of the original information; the third loss value further constrains and optimizes the model during the backward reconstruction process, improving the stability and consistency of the model in the reverse process; the three loss values ​​are organically combined to form the cornerstone of the model optimization process, which can constrain the model from multiple aspects, thereby helping to improve the accuracy of data completion.

[0017] In a possible implementation manner of the first aspect, predicting the predicted time series feature of the third sample data according to the actual time series feature of the fourth sample data includes: Inputting the actual time series features of the fourth sample data into the third model, and outputting the predicted time series features of the third sample data; Among them, the third model includes multiple cascaded residual blocks, each of the residual blocks includes a dimensionality reduction network layer and a dimensionality increase network layer, and the output end of the dimensionality reduction network layer is respectively connected to the input end of the dimensionality increase network layer in the same residual block and the output end of the dimensionality reduction network layer in the next residual block.

[0018] Through the third model mentioned above, the intermediate features of each residual block are fused with the intermediate features of the next residual block through jump connections. Through the encoding and decoding process of layer-by-layer refinement and adaptive fusion, higher-level and abstract features in the input mining data are input. Through this third model, not only the model's ability to understand complex time series data is deepened, but also the accuracy and interpretability of data completion are significantly improved. In addition, through the reverse constraint model of the third module, it is beneficial to improve the consistency and integrity of data during the data completion process.

[0019] In a second aspect, an embodiment of the present application provides a perioperative data calculation device, comprising: An acquisition unit, used to acquire time series data of a first modality during a surgery for a target disease, to obtain first time series data; A first model, used to extract a first time series feature of the first time series data; The second model is used to predict the second time series characteristics of the second time series data according to the first time series characteristics; wherein the second time series data is the time series data of the second modality during the surgery of the target disease.

[0020] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the perioperative data calculation method as described in any one of the first aspects above.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the perioperative data calculation method as described in any one of the above-mentioned first aspects is implemented.

[0022] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes the perioperative data calculation method described in any one of the first aspects above.

[0023] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0025] Figure 1 is a flowchart of a perioperative data calculation method provided in an embodiment of the present application; Figure 2 is a schematic diagram of a second model provided in an embodiment of the present application; Figure 3 is a schematic diagram of a perioperative data calculation model provided in an embodiment of the present application; Figure 4 is a schematic diagram of a training framework provided in an embodiment of the present application; Figure 5 is a schematic diagram of a third model provided in an embodiment of the present application; Figure 6 is a structural block diagram of a perioperative data calculation device provided in an embodiment of the present application; Figure 7 It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0027] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0028] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0029] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0030] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0031] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways.

[0032] With the continuous advancement of medical technology and the growing clinical needs, multimodal medical models play an important role in medical research and clinical practice. Multimodal medical models have the potential to process complex data and provide accurate diagnosis and treatment plans. They can integrate a variety of medical data, including imaging, genes, electronic medical records, etc., to provide strong support for disease diagnosis, risk prediction and personalized treatment.

[0033] Due to technical limitations, disease progression, and other reasons, some modal data may not be available or have high heterogeneity, which affects the accuracy and reliability of subsequent processing such as disease diagnosis and risk prediction. Therefore, how to optimize the use of missing data sets without sacrificing the performance of multimodal medical models has become an important direction of current research.

[0034] Based on this, an embodiment of the present application provides a perioperative data calculation method. In the embodiment of the present application, the time series features of time series data of one modality are used to predict the time series features of time series data of another modality, so that the time series data of different modalities are finely aligned at the feature level, and the correlation of different modal data at the feature level is considered, which effectively improves the accuracy and robustness of data completion.

[0035] See also Figure 1 , is a flowchart of a perioperative data calculation method provided in an embodiment of the present application. As an example but not a limitation, the method may include the following steps: S101, acquiring time series data of a first modality during a surgery for a target disease to obtain first time series data.

[0036] In the embodiments of the present application, time series data refers to data arranged in chronological order. Time series data may be medical data such as images, genes, and electronic medical records involved in the surgical process of the target disease. Among them, the medical indicators represented by time series data of different modalities are different. For example, when the target disease is cardiovascular disease, the time series data of the first modality may be heart rate data, and the time series data of the second modality may be mean arterial pressure data.

[0037] It is understandable that in the embodiments of the present application, the time series characteristics of time series data of one modality are used to predict the time series characteristics of time series data of another modality. For example, the time series characteristics of heart rate data in cardiovascular disease surgery can be used to predict the time series characteristics of mean arterial pressure data in cardiovascular disease surgery.

[0038] S102: Extract a first time series feature of the first time series data.

[0039] Optionally, the first time series data may be input into a trained first model to output first time series features of the first time series data.

[0040] In the above method, since the first model is pre-trained, using the first model to extract time series features can not only improve the feature extraction accuracy but also improve the feature extraction efficiency.

[0041] In one implementation, the pre-training process of the first model may include the following steps: Acquire first sample data and second sample data during a surgical procedure for a target disease; wherein the first sample data is time series data of a first modality, and the second sample data is time series data of a second modality; fuse the first sample data and the second sample data to obtain fused time series data; train a first model based on the fused time series data to obtain a trained first model.

[0042] Optionally, the time series data of different modalities can be standardized before the fusion process. For example, the first sample data and the second sample data are respectively subjected to normal distribution standardization. Normal distribution standardization, also known as Z-score standardization or dedimensionalization, is a commonly used data preprocessing method. Its main purpose is to convert the original data into a distribution form with a mean of 0 and a standard deviation of 1, so that data of different dimensions or magnitudes can be compared and further analyzed. The formula for normal distribution standardization is: ; in, is the original data, is the mean of the original data, is the standard deviation of the original data. ‌Indicates the average level or central tendency of the data. ‌Standard deviation ‌Indicates the degree of dispersion of data distribution, that is, the average distance between data points and the mean.

[0043] Through standardization, a new data set can be obtained, in which each data point represents the degree of deviation of the original data point relative to the mean, and the unit is standard deviation. In this way, no matter what the dimension or magnitude of the original data is, the standardized data can be compared and analyzed on the same scale.

[0044] Optionally, the semantic-aware focused attention mechanism (CAFA) can be used for fusion processing. The specific process includes the following: Will The data is evenly divided into M data groups, and the time domain attention calculation is performed on the data group as a unit, so as to globally interact and model the time series data during cardiovascular surgery; through the formula Capturing the long-term dependencies in each data group can better understand the dynamic changes of time series data and provide more accurate and comprehensive information for subsequent modal coding and feature extraction; Perform multi-dimensional QKV decomposition on the information output by LSTM, and use the formula The QKV vector is converted into a context-aware hidden representation (or feature representation) that can preserve the semantic information of the input sequence; then the formula Concatenate the calculated hidden representations into feature vectors (i.e. fuse time series data).

[0045] Among them, the splie() function is used to split the input data into multiple data groups. LSTM() is a function of the Long Short-Term Memory network, which effectively controls the flow and retention of information in the sequence by introducing memory units and a series of gating mechanisms (such as input gates, forget gates, and output gates), so that dependencies can be captured in long time series. The softmax() function is used to convert a real-valued vector into a probability distribution function. The concat() function is used to connect multiple sequences.

[0046] Exemplarily, during the pre-training process of the first model, the fused time series data is input into the first model, and the predicted time series features are output; the cross entropy loss between the predicted time series features and the true time series features is calculated to obtain the loss value of the first model; if the loss value of the first model is less than a preset value, the current first model is recorded as the trained first model; if the loss value of the first model is greater than or equal to the preset value, the model parameters of the first model are adjusted according to the loss value of the first model, and the adjusted first model is continued to be trained until the trained first model is obtained.

[0047] S103: predict a second time series feature of second time series data according to the first time series feature.

[0048] The second time series data is the time series data of the second modality during the surgery for the target disease.

[0049] In one implementation, S103 may include: Performing time series analysis according to the first time series feature to generate a third time series feature; wherein the time series analysis is used to obtain the overall trend and change law of the input data; Performing frequency domain analysis according to the first time series feature to generate a fourth time series feature; wherein the frequency domain analysis is used to obtain the frequency domain features of the input data and transform the obtained frequency domain features into the time domain; The second timing characteristic is obtained according to the third timing characteristic and the fourth timing characteristic.

[0050] Optionally, you can use the formula Perform timing analysis. represents the input data of the tth time step of the i-th decoder, Dis the total number of decoders. is a polynomial space matrix. It is the third timing feature.

[0051] In this method, polynomial regression is used to model the inherent overall trend and change law of the time series feature sequence, providing macro-guidance for subsequent processing.

[0052] Optionally, frequency domain analysis can be performed using the following formula:

[0053] Among them, FFT() is Fourier transform, which is used to convert time domain data into frequency domain data. argTopK means taking K data with larger values ​​in the sequence. IFFT() is inverse Fourier transform, which is used to convert frequency domain data into time domain data.

[0054] The above method is equivalent to converting the time series data to the frequency domain, obtaining the part with larger spectrum amplitude from the frequency domain data, and converting it back to the time domain. This enables the model to understand the semantic meaning of the time series more deeply, thereby generating more accurate and detailed time series features.

[0055] Optionally, the method for obtaining the second timing feature according to the third timing feature and the fourth timing feature may be: performing timing feature diffusion processing on the first timing feature to obtain the timing diffusion feature; performing timing analysis on the timing diffusion feature to obtain the third timing feature; performing frequency domain analysis on the timing diffusion feature to obtain the fourth timing feature; and weighting the timing diffusion feature, the third timing feature and the fourth timing feature to obtain the second timing feature.

[0056] Among them, the time series feature diffusion processing can use the encoder in the transformer model.

[0057] Optionally, multiple decoders may be provided, each of which performs the above-mentioned timing analysis and frequency domain analysis to obtain the second timing characteristics output by each decoder; then the second timing characteristics output by each of the multiple decoders are averaged to output the final second timing characteristics.

[0058] In one implementation, S103 may be implemented by a second model. Specifically, the first time series feature is input into a trained second model, and a second time series feature of predicted second time series data is output.

[0059] For example, see Figure 2 , is a schematic diagram of the second model provided in the embodiment of the present application. As an example and not a limitation, Figure 2As shown, the second model may include D decoders, each decoder including a time series feature diffusion module, a global perception module and a multi-frequency aggregation module. Among them, the feature diffusion module is used to perform time series feature diffusion processing on the input data. The global perception module is used to perform time series analysis on the input data. The multi-frequency aggregation module is used to perform frequency domain analysis on the input data.

[0060] The second model mentioned above is a generative model based on diffusion structure, which can achieve high-quality reconstruction from the time series features of one modality to the time series features of another modality, effectively improving the accuracy of data completion.

[0061] For example, see Figure 3 , is a schematic diagram of a perioperative data calculation model provided in an embodiment of the present application. As an example and not a limitation, Figure 3 As shown, the perioperative data calculation model may include a trained first model and a trained second model. The above S101-S102 can be implemented by the perioperative data calculation model, specifically: the first time series data is input into the perioperative data calculation model, the trained first model extracts the first time series feature of the first time series data, and the first time series feature is input into the second model; the trained second model predicts the second time series feature of the second time series data according to the first time series feature, that is, the perioperative data calculation model outputs the second time series feature.

[0062] In an embodiment of the present application, the time series features of time series data of one modality are used to predict the time series features of time series data of another modality, so that the time series data of different modalities are finely aligned at the feature level, and the correlation between the data of different modalities at the feature level is taken into account, which effectively improves the accuracy and robustness of data completion.

[0063] It should be noted that the first model in the perioperative data calculation model can be pre-trained separately. The perioperative data calculation model is constructed using the pre-trained first model and the untrained second model, and then the perioperative data calculation model is trained, that is, the second model in the perioperative data calculation model is trained to obtain the trained perioperative data calculation model. In practical applications, data completion is achieved through the trained perioperative data calculation model.

[0064] The following describes the training method for the perioperative data calculation model.

[0065] S201, obtaining third sample data and fourth sample data during a surgery for the target disease.

[0066] The third sample data is the time series data of the first modality, and the fourth sample data is the time series data of the second modality.

[0067] S202: Train a second model according to the third sample data and the fourth sample data to obtain the trained second model.

[0068] In the embodiment of the present application, a training framework is built to train the perioperative data calculation model.

[0069] See also Figure 4 , is a schematic diagram of a training framework provided in an embodiment of the present application. As an example and not a limitation, Figure 4 As shown, the training framework may include a first model, a second model, a third model and a prediction module.

[0070] based on Figure 4 In the training framework shown, the training process in S202 may include: The third sample data x a Input the first trained model to obtain the actual time series features of the third sample data h ; The actual time series characteristics of the third sample data h Input the second model to get the fourth sample data x b Prediction time series characteristics h’ ; The fourth sample data x b Input the trained first model to obtain the actual time series features of the fourth sample data h’’ ; According to the actual timing characteristics of the third sample data h , the actual time series characteristics of the fourth sample data h’ and predicting time series features h’’ Calculate the model loss value; If the model loss value is less than the preset value, the current second model is determined as the trained second model; If the model loss value is greater than the preset value, the model parameters of the second model are adjusted according to the model loss value to obtain the adjusted second model, and the adjusted second model is continued to be trained until the trained second model is obtained.

[0071] In one embodiment, the calculation method of the model loss value may include: According to the predicted time series characteristics of the fourth sample data h’ Get the predicted probability of occurrence of the target disease s’ ; According to the predicted probability s’ The actual probability of occurrence corresponding to the fourth sample data s Calculate the first loss value L cls ; According to the actual timing characteristics of the fourth sample data h’’ and predicting time series features h’ Calculate the second loss value L f ; According to the actual timing characteristics of the fourth sample data h’’ Predict the time series characteristics of the third sample data h’’’ ; According to the actual timing characteristics of the third sample data h and predicting time series features h’’’ Calculate the third loss value L b ; According to the first loss value L cls , the second loss value L f and the third loss value L b Calculate the model loss value.

[0072] based on Figure 4 In one implementation, the training framework shown in FIG. 1 can be used to predict the time series features of the fourth sample data. h’ Input prediction module, output predicted probability of occurrence of target disease s’ The actual occurrence probability corresponding to the fourth sample data s It can be manually labeled or the probability of occurrence can be obtained based on expert prior knowledge.

[0073] It should be noted that the prediction module can be pre-trained. Optionally, the output of the prediction module can be a probability value between 0 and 1, indicating the probability of occurrence of the target disease after surgery. Calculate the first loss value L cls It can be used to calculate the probability of occurrence of a prediction s’ and the actual probability of occurrence s The difference between them can be calculated by cross entropy loss or binary cross entropy loss.

[0074] Optionally, the first loss value can be L cls , the second loss value L f and the third loss value L b The weighted model loss value is obtained.

[0075] It can be understood that the first loss value can characterize the accuracy of the occurrence probability prediction based on the predicted time series characteristics of the fourth sample data, the second loss value can characterize the degree of difference between the actual time series characteristics and the predicted time series characteristics of the fourth sample data, and the third loss value can characterize the degree of difference between the actual time series characteristics and the predicted time series characteristics of the third sample data.

[0076] In the calculation method of the above model loss value, the first loss value is an important indicator to measure the difference between the predicted probability of occurrence of the target disease and the actual probability of occurrence, which forms an indirect constraint on the model and is conducive to improving the accuracy of data reconstruction; the second loss value can improve the accuracy of the model in reconstructing the timing characteristics during the forward propagation process to retain the integrity of the original information; the third loss value further constrains and optimizes the model during the backward reconstruction process, improving the stability and consistency of the model in the reverse process; the three loss values ​​are organically combined to form the cornerstone of the model optimization process, which can constrain the model from multiple aspects, thereby helping to improve the accuracy of data completion.

[0077] based on Figure 4 The training framework shown in FIG. 1 may, in one implementation, convert the actual time series features of the fourth sample data into h’’ Input the third model and output the predicted time series characteristics of the third sample data h’’’。

[0078] Optionally, the third model may include multiple cascaded residual blocks, each of which includes a dimensionality reduction network layer and a dimensionality increase network layer, and the output end of the dimensionality reduction network layer is respectively connected to the input end of the dimensionality increase network layer in the same residual block and the output end of the dimensionality reduction network layer in the next residual block.

[0079] For example, see Figure 5 , is a schematic diagram of the third model provided in the embodiment of the present application. As an example and not a limitation, Figure 5 As shown, the third model includes 3 residual blocks.

[0080] The output of the dimension reduction network layer in the first residual block is connected to the input of the dimension increase network layer in the first residual block, and is connected to the output of the dimension reduction network layer in the second residual block. The output of the dimension reduction network layer in the second residual block is connected to the input of the dimension increase network layer in the second residual block, and is connected to the output of the dimension reduction network layer in the third residual block.

[0081] The input data of the first residual block and the output data of the dimension-increasing network layer in the first residual block are weighted to generate the output data of the first residual block, and serve as the input data of the second residual block. The input data of the second residual block and the output data of the dimension-increasing network layer in the second residual block are weighted to generate the output data of the second residual block, and serve as the input data of the third residual block. The input data of the third residual block and the output data of the dimension-increasing network layer in the third residual block are weighted to generate the output data of the third residual block, and serve as the output data of the third model.

[0082] It should be noted that Figure 5 Only the case of three residual blocks is shown. In practical applications, more or fewer residual blocks can be cascaded. In the embodiment of the present application, the number of residual blocks included in the third model is not specifically limited.

[0083] Through the third model mentioned above, the intermediate features of each residual block are fused with the intermediate features of the next residual block through jump connections. Through the encoding and decoding process of layer-by-layer refinement and adaptive fusion, higher-level and abstract features in the input mining data are input. Through this third model, not only the model's ability to understand complex time series data is deepened, but also the accuracy and interpretability of data completion are significantly improved. In addition, through the reverse constraint model of the third module, it is beneficial to improve the consistency and integrity of data during the data completion process.

[0084] In one embodiment, before training the second model, the sample data may be preliminarily completed, including: Performing multi-dimensional feature extraction on the third sample data and the fourth sample data in the frequency domain to obtain multi-dimensional frequency domain features; Completing the third sample data and the fourth sample data according to the multi-dimensional frequency domain features to obtain the third sample data and the fourth sample data after preliminary completion; The second model is trained according to the preliminarily completed third sample data and the fourth sample data to obtain a trained second model.

[0085] In one implementation, the initial completion process can be implemented by the following formula:

[0086]

[0087]

[0088]

[0089] Among them, MSVD() is used to perform dimensionality mapping. split() is used to split the input data into multiple groups of data. FFT() is used to perform Fourier transform on the input data to convert the input data into frequency domain data. It is a multilayer perceptron (MLP) in the frequency domain. IFFT() is used to perform inverse Fourier transform on the input data to convert the input data into time domain data. concat() is used to merge multiple sets of data into one-dimensional data.

[0090] Optionally, after concat, the missing parts of the sample data obtained from the one-dimensional data are completed to the corresponding positions of the sample data according to the corresponding relationship of the sampling time, so as to achieve preliminary completion of the sample data. In the above preliminary completion process, the multi-dimensional frequency domain features are split into multiple groups of data, enriching the data representation capability; then, the multi-layer perceptron is used to extract features from the multiple groups of data, which is conducive to providing multi-dimensional and multi-level feature information; through the above preliminary completion process, the sample data can be effectively preliminarily completed, making the sample data more complete and accurate, thereby providing reliable data support for subsequent model training.

[0091] In one implementation, the above-mentioned MSVD() dimensionality-up mapping process can be implemented by the following formula: ; Among them, x n is the data of the nth sampling point in the sample data. Shuffle() is used to rearrange the elements in the array in random order. m is the rearranged data. SVD() is used to perform singular value decomposition on the input data. m is the data after SVD decomposition. n The data after dimension increase.

[0092] The above-mentioned dimensionality-increasing mapping process is helpful to dig out the internal correlation of the data, greatly enriches the data representation capability, and provides a reliable data basis for subsequent data completion.

[0093] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0094] Corresponding to the perioperative data calculation method described in the above embodiment, Figure 6 This is a structural block diagram of the perioperative data calculation device provided in an embodiment of the present application. For the sake of convenience of explanation, only the parts related to the embodiment of the present application are shown.

[0095] Reference Figure 6 , the device 6 comprises: The acquisition unit 61 is used to acquire time series data of a first modality during a surgery for a target disease to obtain first time series data.

[0096] The first model 62 is used to extract the first time series features of the first time series data.

[0097] The second model 63 is used to predict the second time series characteristics of the second time series data according to the first time series characteristics; wherein the second time series data is the time series data of the second modality during the surgery of the target disease.

[0098] Optionally, the second model 63 is also used for: Performing time series analysis according to the first time series feature to generate a third time series feature; wherein the time series analysis is used to obtain the overall trend and change law of the input data; Performing frequency domain analysis according to the first time series feature to generate a fourth time series feature; wherein the frequency domain analysis is used to obtain frequency domain features of input data and transform the obtained frequency domain features into the time domain; The second timing characteristic is obtained according to the third timing characteristic and the fourth timing characteristic.

[0099] Optionally, the device 6 further includes a training unit 64, configured to: Acquire first sample data and second sample data during a surgical procedure for the target disease; wherein the first sample data is time series data of the first modality, and the second sample data is time series data of the second modality; Performing fusion processing on the first sample data and the second sample data to obtain fused time series data; A first model is trained according to the fused time series data to obtain the trained first model; wherein the trained first model is used to extract the first time series features of the first time series data.

[0100] Optionally, the training unit 64 is further configured to: Acquire third sample data and fourth sample data during the surgical procedure of the target disease; wherein the third sample data is the time series data of the first modality, and the fourth sample data is the time series data of the second modality; A second model is trained according to the third sample data and the fourth sample data to obtain the trained second model; wherein the trained second model is used to predict the second time series feature of the second time series data according to the first time series feature.

[0101] Optionally, the training unit 64 is further configured to: Performing multi-dimensional feature extraction on the third sample data and the fourth sample data in the frequency domain to obtain multi-dimensional frequency domain features; Completing the third sample data and the fourth sample data according to the multi-dimensional frequency domain features to obtain the third sample data and the fourth sample data after preliminary completion; The second model is trained according to the third sample data and the fourth sample data after preliminary completion to obtain the trained second model.

[0102] Optionally, the training unit 64 is further configured to: Inputting the third sample data into the trained first model to obtain actual time series features of the third sample data; Inputting the actual time series characteristics of the third sample data into the second model to obtain the predicted time series characteristics of the fourth sample data; Inputting the fourth sample data into the trained first model to obtain actual time series features of the fourth sample data; Calculate the model loss value according to the actual time series characteristics of the third sample data, the actual time series characteristics of the fourth sample data, and the predicted time series characteristics; If the model loss value is less than a preset value, determining the current second model as the trained second model; If the model loss value is greater than a preset value, the model parameters of the second model are adjusted according to the model loss value to obtain the adjusted second model, and the adjusted second model is continued to be trained until the trained second model is obtained.

[0103] Optionally, the training unit 64 is further configured to: Obtaining a predicted probability of occurrence of the target disease according to the predicted time series characteristics of the fourth sample data; Calculate a first loss value according to the predicted occurrence probability and the actual occurrence probability corresponding to the fourth sample data; Calculate a second loss value according to the actual time series characteristics and the predicted time series characteristics of the fourth sample data; Predicting the predicted time series characteristics of the third sample data according to the actual time series characteristics of the fourth sample data; Calculate a third loss value according to the actual time series characteristics and the predicted time series characteristics of the third sample data; The model loss value is calculated according to the first loss value, the second loss value and the third loss value.

[0104] Optionally, the training unit 64 is further configured to: Inputting the actual time series features of the fourth sample data into the third model, and outputting the predicted time series features of the third sample data; Among them, the third model includes multiple cascaded residual blocks, each of the residual blocks includes a dimensionality reduction network layer and a dimensionality increase network layer, and the output end of the dimensionality reduction network layer is respectively connected to the input end of the dimensionality increase network layer in the same residual block and the output end of the dimensionality reduction network layer in the next residual block.

[0105] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0106] in addition, Figure 6 The perioperative data calculation device shown may be a software unit, a hardware unit, or a combination of software and hardware units built into an existing terminal device, or may be integrated into the terminal device as an independent accessory, or may exist as an independent terminal device.

[0107] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0108] Figure 7 Schematic diagram of the structure of the terminal device provided in the embodiment of the present application. Figure 7 As shown, the terminal device 7 of this embodiment includes: at least one processor 70 ( Figure 7 Only one is shown in the figure) a processor, a memory 71, and a computer program 72 stored in the memory 71 and executable on the at least one processor 70, wherein the processor 70 implements the steps in any of the above-mentioned embodiments of the perioperative data calculation method when executing the computer program 72.

[0109] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 7It is only an example of the terminal device 7 and does not constitute a limitation on the terminal device 7. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0110] The processor 70 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0111] In some embodiments, the memory 71 may be an internal storage unit of the terminal device 7, such as a hard disk or memory of the terminal device 7. In other embodiments, the memory 71 may also be an external storage device of the terminal device 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 7. Further, the memory 71 may also include both an internal storage unit and an external storage device of the terminal device 7. The memory 71 is used to store an operating system, an application program, a boot loader, data, and other programs, such as the program code of the computer program. The memory 71 may also be used to temporarily store data that has been output or is to be output.

[0112] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0113] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0114] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0115] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0116] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0117] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A perioperative data calculation method, characterized in that: include: Acquire time series data of a first modality during a surgical procedure for a target disease to obtain first time series data; Extracting a first time series feature of the first time series data; Predicting a second time series feature of second time series data based on the first time series feature; wherein the second time series data is time series data of a second modality during surgery for the target disease.

2. The perioperative data calculation method according to claim 1, characterized in that: The predicting a second time series feature of second time series data according to the first time series feature includes: Performing time series analysis according to the first time series feature to generate a third time series feature; wherein the time series analysis is used to obtain the overall trend and change law of the input data; Performing frequency domain analysis according to the first time series feature to generate a fourth time series feature; wherein the frequency domain analysis is used to obtain frequency domain features of input data and transform the obtained frequency domain features into the time domain; The second timing characteristic is obtained according to the third timing characteristic and the fourth timing characteristic.

3. The perioperative data calculation method according to claim 1, characterized in that: The method further comprises: Acquire first sample data and second sample data during a surgical procedure for the target disease; wherein the first sample data is time series data of the first modality, and the second sample data is time series data of the second modality; Performing fusion processing on the first sample data and the second sample data to obtain fused time series data; A first model is trained according to the fused time series data to obtain the trained first model; wherein the trained first model is used to extract the first time series features of the first time series data.

4. The perioperative data calculation method according to claim 3, characterized in that: The method further comprises: Acquire third sample data and fourth sample data during the surgical procedure of the target disease; wherein the third sample data is the time series data of the first modality, and the fourth sample data is the time series data of the second modality; A second model is trained according to the third sample data and the fourth sample data to obtain the trained second model; wherein the trained second model is used to predict the second time series feature of the second time series data according to the first time series feature.

5. The perioperative data calculation method according to claim 4, characterized in that: The step of training the second model according to the third sample data and the fourth sample data to obtain the trained second model includes: Performing multi-dimensional feature extraction on the third sample data and the fourth sample data in the frequency domain to obtain multi-dimensional frequency domain features; Completing the third sample data and the fourth sample data according to the multi-dimensional frequency domain features to obtain the third sample data and the fourth sample data after preliminary completion; The second model is trained according to the third sample data and the fourth sample data after preliminary completion to obtain the trained second model.

6. The perioperative data calculation method according to claim 4 or 5, characterized in that: The step of training the second model comprises: Inputting the third sample data into the trained first model to obtain actual time series features of the third sample data; Inputting the actual time series characteristics of the third sample data into the second model to obtain the predicted time series characteristics of the fourth sample data; Inputting the fourth sample data into the trained first model to obtain actual time series features of the fourth sample data; Calculate the model loss value according to the actual time series characteristics of the third sample data, the actual time series characteristics of the fourth sample data, and the predicted time series characteristics; If the model loss value is less than a preset value, determining the current second model as the trained second model; If the model loss value is greater than a preset value, the model parameters of the second model are adjusted according to the model loss value to obtain the adjusted second model, and the adjusted second model is continued to be trained until the trained second model is obtained.

7. The perioperative data calculation method according to claim 6, characterized in that: The calculating the model loss value according to the actual time series feature of the third sample data, the actual time series feature of the fourth sample data and the predicted time series feature includes: Obtaining a predicted probability of occurrence of the target disease according to the predicted time series characteristics of the fourth sample data; Calculate a first loss value according to the predicted occurrence probability and the actual occurrence probability corresponding to the fourth sample data; Calculate a second loss value according to the actual time series characteristics and the predicted time series characteristics of the fourth sample data; Predicting the predicted time series characteristics of the third sample data according to the actual time series characteristics of the fourth sample data; Calculate a third loss value according to the actual time series characteristics and the predicted time series characteristics of the third sample data; The model loss value is calculated according to the first loss value, the second loss value and the third loss value.

8. The perioperative data calculation method according to claim 7, characterized in that: The predicting the predicted time series feature of the third sample data according to the actual time series feature of the fourth sample data includes: Inputting the actual time series features of the fourth sample data into the third model, and outputting the predicted time series features of the third sample data; Among them, the third model includes multiple cascaded residual blocks, each of the residual blocks includes a dimensionality reduction network layer and a dimensionality increase network layer, and the output end of the dimensionality reduction network layer is respectively connected to the input end of the dimensionality increase network layer in the same residual block and the output end of the dimensionality reduction network layer in the next residual block.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images