A pathology critical value warning management system based on pathology knowledge graph

Abstract

The present invention discloses a pathology critical value warning management system based on a pathology knowledge graph, which relates to the field of medical health artificial intelligence technology. The system includes a pathology data acquisition module, a pathology feature extraction module, a pathology state matching module, a pathology state warning module, and a pathology state management module. After the pathology data is collected and preprocessed, the pathology feature extraction module constructs a knowledge graph and generates a composite feature vector. The pathology state matching module identifies acute pathological states and quantifies the degree of matching. The pathology state warning module combines the analysis results to construct a model to output pathology critical values. By integrating the pathology knowledge graph with artificial intelligence technology, the invention realizes intelligent warning and management of pathology critical values, improves the accuracy and efficiency of pathology analysis, provides clinicians with intuitive warning information and decision support, helps to timely discover and deal with acute pathological states, and improves the treatment effect of patients.

Description

Technical Field

[0001] The present invention relates to the field of medical health artificial intelligence technology, and in particular to a pathology critical value early warning management system based on a pathology knowledge graph. Background Art

[0002] Traditional pathology critical value early warning management refers to a set of early warning management mechanisms established by the pathology department during the pathology examination process for examination results that may indicate that a patient is in a life-threatening condition. In traditional management, once the pathology department discovers a critical value, it will immediately review and confirm the result to ensure the accuracy of the result. Subsequently, the critical value result will be quickly reported to the clinical department physician through the hospital information system or telephone. After receiving the report, the clinical department physician must promptly assess the patient's condition and take appropriate treatment measures. In addition, traditional pathology critical value early warning management also includes detailed recording, tracking and follow-up of critical value reports, as well as regular review and improvement of the critical value processing process to ensure patient safety and improve the quality of medical services.

[0003] In order to solve the problem that traditional pathology critical value warning management needs to be improved in dynamic pathology risk assessment and the application of fragmented clinical knowledge, the existing technology adopts manual review and simple information system transmission to handle it. After the pathologist finds the critical value, he confirms the result through manual review and then transmits the information to the clinical department through the hospital information system or telephone. However, this method may lead to untimely information transmission and incomplete application of clinical knowledge. Due to the fragmentation of clinical knowledge, doctors may need to spend extra time to find and integrate relevant knowledge after receiving critical value information, resulting in reduced decision-making efficiency. At the same time, the complexity of dynamic pathology risk assessment also makes manual processing prone to omissions, which in turn leads to delays in patient treatment and may even affect the patient's treatment effect and life safety. Therefore, a pathology critical value warning management system based on pathology knowledge graph is proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a pathology critical value warning management system based on a pathology knowledge graph to solve the problems raised in the above background technology.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is: a pathology critical value warning management system based on pathology knowledge graph, including a pathology data acquisition module, a pathology feature extraction module, a pathology state matching module, a pathology state warning module and a pathology state management module;

[0006] The pathology data acquisition module collects and pre-processes the patient's pathology data;

[0007] The pathological feature extraction module constructs a knowledge graph entity relationship table based on the preprocessed pathological data, extracts dynamic features and binds them to the knowledge graph to generate a composite feature vector;

[0008] The pathological state matching module is used to identify acute pathological states by combining composite feature vectors and quantify the degree of matching between pathological data and disease rules in the knowledge graph;

[0009] The pathological state warning module combines the analysis results of the pathological state matching module with the hierarchical attention mechanism to construct a pathological warning model and output a pathological critical value;

[0010] The pathological status management module combines the pathological critical value with the knowledge graph entity relationship table to perform graded warnings and construct a three-dimensional heat map.

[0011] A further improvement of the technical solution of the present invention is that the pathological state matching module includes a pathological identification unit, a pathological prediction unit and a pathological matching unit:

[0012] The pathology recognition unit is used to combine the composite feature vector and the generalized linear model architecture to construct a logistic regression recognition model to identify acute pathological conditions;

[0013] The pathology prediction unit is used to combine the dynamic characteristics of the pathology data, use the long short-term memory network model architecture, build a pathology prediction model, and output the predicted value of the pathology data;

[0014] The pathology matching unit is used to combine the collected pathology data with the graph neural network node propagation algorithm, construct a knowledge graph reasoning model, generate rule triggering strength, and quantify the degree of matching between the actual collected pathology data and the disease rules in the knowledge graph.

[0015] A further improvement of the technical solution of the present invention is that: in the pathology data acquisition module, the acquisition and preprocessing process of serum potassium ion concentration data and platelet count data includes:

[0016] An ion-selective electrode detection system is deployed in the pathology critical value early warning management system. The potassium ion concentration is calculated by measuring the potential change value. The ion-selective electrode detection system has a built-in potassium ion-specific electrode module, and the electrode surface is covered with a valinomycin selective sensitive membrane. The detection channel is connected to the sample delivery track. When the sample is injected into the detection chamber, a potential difference is generated inside and outside the electrode membrane. The potential change value is then measured to obtain the potassium ion concentration.

[0017] A dual-sheath flow optical counting system is deployed in the pathology critical value warning management system to count platelets by measuring forward scattered light intensity and side fluorescence intensity. The dual-sheath flow optical counting system integrates a 633nm semiconductor laser and a dual-angle scattered light detector, and the detection chamber is temperature-controlled at 37±0.5°C. The sample is then processed into single cells using sheath flow technology.

[0018] The acquired potassium ion concentration data and platelet data were preprocessed. For potassium ion concentration data preprocessing, when the potassium ion concentration fluctuation exceeded 0.3 mmol / L for three consecutive times, the automatic retest procedure was triggered, and the median of the potassium ion concentration of the three tests was taken as the calculation result. For platelet data preprocessing, when the platelet histogram showed a multi-peak distribution, the impedance method was automatically switched to review, and the cell volume was measured using the Coulter principle to eliminate the interference of small red blood cells. Particles with a volume of 2-20 femtoliters were counted and recorded as the effective platelet count.

[0019] A further improvement of the technical solution of the present invention is that: in the pathological feature extraction module, the process of extracting features from the pre-processed serum potassium ion concentration data and platelet count data includes:

[0020] Parse and extract the test item-critical threshold-associated pathological status triple from the patient's electronic medical record text, calculate the associated edge strength weight of the triple based on the evidence level of evidence-based medicine, store the triple as a graph database node, and use the average weight of the corresponding associated edge strength as the initial weight of the pathological status node in the knowledge graph. The graph database node attributes include test indicator parameters, pathological status code, and treatment timeliness requirements;

[0021] The serum potassium coefficient of variation was calculated by combining the pre-processed serum potassium concentration data with a 6-hour sliding window. When the serum potassium coefficient of variation exceeded 15%, the acute kidney injury node in the knowledge graph was automatically associated. The least squares method was used to fit the trend slope of the patient's platelet count within 12 hours. When the platelet trend slope was lower than -5×10 9 / L / h is bound to the disseminated intravascular coagulation node, where the coefficient of variation of serum potassium is the percentage of the standard deviation and mean of serum potassium concentration within the sliding window;

[0022] The deviation of serum potassium concentration and platelet count was calculated and combined with the weight of knowledge graph nodes to construct a weighted risk index. The critical threshold of serum potassium concentration was set to 3.2 mmol / L and the critical threshold of platelet count was set to [30, 50] × 10 9 / L, when the serum potassium concentration is lower than 3.2mmol / L and is associated with the heart failure node, a binary feature F1=1 is generated, and when the platelet count is between [30,50]×109 When the / L interval is associated with the postoperative bleeding node, the feature F2=1 is generated. The serum potassium variation coefficient, platelet trend slope, F1, F2 and weighted risk index are fused into a spatiotemporal feature vector, which is encapsulated with its timestamp and node code. The spatiotemporal feature vector is then transmitted to the pathological status matching module.

[0023] Among them, the serum potassium ion concentration deviation is the ratio of the difference between the current measured value of serum potassium ion concentration and the critical threshold of serum potassium ion concentration to the critical threshold of serum potassium ion concentration; the platelet count deviation is the ratio of the difference between the lower limit of the critical threshold of platelet count and the current measured value of platelet count to the lower limit of the critical threshold of platelet count; the weighted risk index is the cumulative sum of the product of the test indicator deviation and the associated edge strength weight of the pathological node in the corresponding knowledge graph.

[0024] A further improvement of the technical solution of the present invention is that: in the pathology recognition unit, a logistic regression recognition model is constructed, and the process of identifying acute pathological conditions includes:

[0025] The pathology recognition unit receives the spatiotemporal feature vector with the serum potassium coefficient of variation, platelet trend slope, F1, F2, and weighted risk index as input features, sets the initial value of the training weight coefficient of each input feature according to the knowledge graph node weight, performs weighted summation on the input feature and the training weight coefficient of each input feature to obtain a linear value, and constructs a logistic regression recognition model;

[0026] Based on the constructed logistic regression recognition model, the linear value is mapped to the probability of pathological state through the S-type function, and the pathological state threshold is set. When the pathological state probability exceeds the pathological state threshold, it is judged as an acute pathological state. When the pathological state probability is lower than the pathological state threshold, it is judged as a normal state.

[0027] The logarithmic loss function is used to calculate the difference between the predicted pathological state probability and the true label to obtain the loss value. The knowledge graph node weight is introduced as a regularization term. When F1=1, the learning rate of the heart failure-related weight coefficient is automatically increased to 1.5 times the basic value. If the platelet trend slope is lower than -5×10 for three consecutive hours, 9 / L / h, the trend slope weight is locked and no longer updated.

[0028] A further improvement of the technical solution of the present invention is that: in the pathology prediction unit, the process of constructing a pathology prediction model and outputting a predicted value of serum potassium ion concentration and a predicted value of platelet decrease rate includes:

[0029] The pathology prediction unit receives 6 consecutive hours of serum potassium concentration data and integrates it into a serum potassium concentration detection sequence, and receives 12 consecutive hours of platelet count data and integrates it into a platelet count detection sequence;

[0030] Based on the serum potassium concentration detection sequence and platelet count detection sequence, the difference between the serum potassium concentration in the current hour and the serum potassium concentration in the previous hour and the percentage of the serum potassium concentration in the previous hour were taken as the serum potassium concentration change rate, and the difference between the platelet count in the current hour and the platelet count in the previous hour and the percentage of the time interval were taken as the platelet decline rate;

[0031] Multiply the serum potassium concentration change rate with the acute kidney injury node weight in the knowledge graph to generate a weighted change feature. Combine the platelet decrease rate with the disseminated intravascular coagulation node weight to construct a risk-weighted rate.

[0032] The weighted change features and risk-weighted rate are input into the input layer of the long-short-term memory network architecture. The input gate in the long-short-term memory network architecture uses a Sigmoid function to linearly combine the weighted change features, risk-weighted rate, and the hidden state at the previous moment to generate a gating value between 0 and 1. The forget gate uses a Sigmoid function to determine the retention ratio of historical states and uses a hyperbolic tangent function to generate a new state recommended by the current input. The fully connected layer of the long-short-term memory network architecture multiplies the hidden state by the weight of the acute kidney injury node and the weight of the disseminated intravascular coagulation node, adds a bias term, and outputs the predicted values of serum potassium ion concentration and platelet decline rate.

[0033] Based on the collected serum potassium concentration data, platelet count data, predicted serum potassium concentration, predicted platelet decline rate, 6-hour serum potassium concentration sample size, and 12-hour platelet count sample size, the mean square error was used to calculate the prediction bias to obtain serum potassium loss, platelet loss, and total loss;

[0034] When the predicted serum potassium value exceeds the threshold interval of the associated disease in the knowledge graph, the cell state update amount in the pathology prediction model is adjusted; when the platelet prediction rate is lower than -5×10 9 When the number of beats is / L / h, the forget gate value in the pathology prediction model is locked to 1, and the historical state is maintained.

[0035] A further improvement of the technical solution of the present invention is that: in the pathology matching unit, the process of constructing a knowledge graph reasoning model and generating rule trigger strength includes:

[0036] The pathology matching unit receives the collected serum potassium concentration data and platelet count data, loads the graph database containing the test item nodes, pathology status nodes and associated edge strength weights, and simultaneously obtains the serum potassium predicted value and platelet decline rate predicted value output by the pathology prediction unit;

[0037] Based on the graph neural network node propagation algorithm, the initial states of serum potassium nodes and platelet nodes are initialized as the ratio of the corresponding measured value to the critical threshold. The state weight of the pathological node is the average weight of the associated edge strength. The state weight of each pathological node is calculated by aggregating neighborhood information, and the weighted attenuation mechanism is used to update the state weight of the pathological node in the knowledge graph. , the calculation process is as follows:

[0038] ;

[0039] in, is the state value of the pathological node at the previous moment, is the state value of the adjacent check node, is the strength weight of the associated edge, and the S-type function is used to compress the status of each pathological node to the interval [0,1] to construct a knowledge graph reasoning model;

[0040] Based on the serum potassium concentration and platelet count deviation, combined with the pathology node's associated edge strength weight and the real-time pathology node status weight, the weighted cumulative formula is used to calculate the cumulative sum of the serum potassium concentration deviation, platelet count deviation, the product of the corresponding associated edge strength weight and the associated pathology node's real-time status weight. The corresponding rule trigger strength is obtained to quantify the degree of match between the collected data and the knowledge graph rules.

[0041] Set the trigger intensity threshold of a single pathology node and the total trigger intensity threshold of multiple pathology nodes. When the trigger intensity of a single pathology node exceeds the single pathology node trigger intensity threshold, the corresponding handling rule is activated. When the total intensity of two or more pathology nodes exceeds the total trigger intensity threshold of multiple pathology nodes, it is set to the highest warning level. If the prediction error continues to exceed 15%, the weight of the associated edge is attenuated at a rate of 0.95, and a temporary rule edge with an initial weight of 0.5 is generated for abnormal data that is unrelated but has a deviation higher than 0.5.

[0042] A further improvement of the technical solution of the present invention is that: in the pathological state warning module, the process of constructing a pathological warning model and outputting a pathological critical value includes:

[0043] The pathological state warning module receives and uniformly quantifies the acute pathological state probability value, the serum potassium predicted value for the next two hours, the platelet decline rate predicted value, and the rule trigger strength vector. It expands the serum potassium predicted value and the platelet decline rate predicted value to generate a two-hour prediction sequence and performs six-hour sliding window mean smoothing on the rule trigger strength.

[0044] The weights of the logistic regression recognition model, pathology prediction model, and knowledge graph inference model are assigned through a trainable parameter matrix and a normalized exponential function. Based on the time series output of the pathology prediction model, the sigmoid function is used to calculate the prediction contribution weights of the current moment and the future moment, forming a two-layer attention allocation mechanism and constructing a pathology early warning model.

[0045] Perform spatial fusion calculation based on each model weight and predicted contribution weight to output pathological critical value , the calculation process is as follows:

[0046] ;

[0047] in, 、 and is the weight of the logistic regression recognition model, pathology prediction model and knowledge graph reasoning model, P is the pathological state probability output by the logistic regression recognition model, is the 6-hour sliding mean of the rule triggering intensity, and The weights assigned to the predicted values at different future time points output by the pathology prediction unit, and The predicted values of serum potassium concentration and platelet decrease rate in the next 1 hour and 2 hours;

[0048] The pathology criticality judgment threshold is adjusted according to the remaining proportion of each pathology treatment time window in the knowledge graph. When the pathology criticality value exceeds the pathology criticality judgment threshold, the warning level is determined in combination with the maximum node weight in the rule trigger intensity vector, and the standard treatment plan in the graph is associated to generate clinical decision recommendations.

[0049] A further improvement of the technical solution of the present invention is that: in the pathological state early warning module, the process of importing the latest output results of each model into the pathological early warning model and outputting the pathological critical value includes:

[0050] The latest acute pathological state probability values output by the logistic regression recognition model, pathology prediction model, and knowledge graph reasoning model, the serum potassium predicted value and platelet decrease rate predicted value for the next two hours, and the rule triggering intensity vector are imported into the pathology warning model to obtain the pathological critical value.

[0051] A further improvement of the technical solution of the present invention is that in the pathological status management module, the process of combining the pathological critical value with the knowledge graph entity relationship table to perform graded warning and construct a three-dimensional heat map includes:

[0052] Set upper and lower thresholds for associated disease nodes, and divide pathological critical values into special warning, level I warning, and level II warning;

[0053] If the pathological critical value exceeds 1.2 times the upper limit of the threshold of the associated disease node and two or more high-weight pathological nodes are activated at the same time, it is judged as a special-level warning. If the pathological critical value is within the threshold range of the associated disease node and a single high-weight node is triggered, it is judged as a level I warning. If the pathological critical value is close to the lower limit of the threshold of the associated disease node and the rule triggering intensity meets the standard, it is judged as a level II warning. The warning level is dynamically increased in combination with the remaining proportion of the treatment time window. When the remaining time is less than 30 minutes, the warning level is automatically upgraded, and the knowledge graph is linked to extract the standard treatment plan corresponding to the highest-weighted node;

[0054] The coordinate system of the three-dimensional heat map is defined as the horizontal 24-h time dimension axis, the vertical serum potassium and platelet dual-scale test index axis, and the vertical pathological status axis. The thermal value of each spatiotemporal point is calculated based on the rule trigger intensity and time attenuation factor, and the upper and lower thresholds of the spatiotemporal point thermal value are set. The red, orange, and yellow warning areas are mapped according to the threshold intervals of the spatiotemporal point thermal value. The continuous high-risk area implementation blocks are aggregated and displayed. When the spatiotemporal point thermal value suddenly increases by more than 2 times the historical average, a pulse flashing mark is added.

[0055] Due to the adoption of the above technical solution, the present invention has the following technical advancements compared to the prior art:

[0056] 1. The present invention provides a pathology critical value warning management system based on the pathology knowledge graph. Through the collaborative work of the pathology data acquisition module and the pathology feature extraction module, it can efficiently and accurately extract key features from massive pathology data, and bind them to the knowledge graph entity relationship table to generate a composite feature vector, which greatly improves the accuracy and efficiency of pathology data analysis and provides a solid foundation for subsequent pathology status matching and warning.

[0057] 2. The present invention provides a pathology critical value warning management system based on the pathology knowledge graph. The pathology state matching module can combine the composite feature vector to quickly identify the acute pathological state and quantify the matching degree between the pathology data and the disease rules in the knowledge graph. This function enables the system to timely detect the patient's pathology critical value and provide clinicians with timely and accurate warning information, which helps to shorten the diagnosis time and improve the treatment effect.

[0058] 3. The present invention provides a pathology critical value warning management system based on a pathology knowledge graph. The pathology status management module can combine the pathology critical value with the knowledge graph entity relationship table to perform graded warnings and construct a three-dimensional heat map. This function makes the warning information more intuitive and easy to understand, making it convenient for clinicians to quickly grasp the patient's condition and degree of criticality, thereby formulating a more reasonable and effective treatment plan. At the same time, the construction of the three-dimensional heat map also provides a powerful tool for the visualization and in-depth analysis of pathology data. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0060] Figure 1 A block diagram of the present invention. DETAILED DESCRIPTION

[0061] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0062] Examples, such as Figure 1 As shown, the present invention provides a pathology critical value warning management system based on pathology knowledge graph, including a pathology data acquisition module, a pathology feature extraction module, a pathology state matching module, a pathology state warning module and a pathology state management module;

[0063] The pathology data acquisition module collects and pre-processes the patient's pathology data, deploys an ion-selective electrode detection system in the pathology critical value early warning management system, and calculates the potassium ion concentration by measuring the potential change value. The ion-selective electrode detection system has a built-in potassium ion-specific electrode module, and the electrode surface is covered with a valinomycin selective sensitive membrane. The detection channel is connected to the sample delivery track, and the sample is injected into the detection chamber. A potential difference is generated inside and outside the electrode membrane, and then the potential change value is measured to obtain the potassium ion concentration. The dual-sheath flow optical counting system is deployed in the pathology critical value early warning management system to count platelets by measuring the forward scattered light intensity and the side fluorescence intensity. The dual-sheath flow optical counting system integrates a semi-circular microscope with a wavelength of 633nm. Conductor laser and dual-angle scattered light detector, and the detection chamber is temperature-controlled at 37±0.5℃. The sample is then processed into single cells using sheath flow technology, and the acquired potassium ion concentration data and platelet data are preprocessed. For the preprocessing of potassium ion concentration data, when the potassium ion concentration fluctuation exceeds 0.3mmol / L for three consecutive times, the automatic retest program is triggered, and the median of the potassium ion concentration of the three tests is taken as the calculation result. For the preprocessing of platelet data, when the platelet histogram shows a multi-peak distribution, the impedance method is automatically switched for review, and the cell volume is measured using the Coulter principle to exclude the interference of small red blood cells. The particles with a volume of 2-20 femtoliters are counted and recorded as the effective platelet count;

[0064] The pathological feature extraction module constructs a knowledge graph entity relationship table based on the preprocessed pathological data, extracts dynamic features and binds them to the knowledge graph to generate a composite feature vector. It parses and extracts the test item-critical threshold-associated pathological state triple from the patient's electronic medical record text, calculates the associated edge strength weight of the triple based on the evidence level of evidence-based medicine, stores the triple as a graph database node, and uses the average weight of the corresponding associated edge strength as the initial weight of the pathological state node in the knowledge graph. The graph database node attributes include test indicator parameters, pathological state coding, and treatment time requirements. The serum potassium variation coefficient is calculated by combining the preprocessed serum potassium ion concentration data and a 6-hour sliding window. When the serum potassium variation coefficient exceeds 15%, it is automatically associated with the acute kidney injury node in the knowledge graph. The least squares method is used to fit the patient's platelet trend slope within 12 hours. When the platelet trend slope is lower than -5×10 9 / L / h, the disseminated intravascular coagulation node is bound. The coefficient of variation of serum potassium is the percentage of the standard deviation and mean of serum potassium concentration within the sliding window. The deviation of serum potassium concentration and platelet count is calculated. The deviation of serum potassium concentration and platelet count is combined with the weight of the knowledge graph node to construct a weighted risk index. The critical threshold of serum potassium concentration is set to 3.2mmol / L, and the critical threshold of platelet count is set to [30,50]×10 9 / L, when the serum potassium concentration is lower than 3.2mmol / L and is associated with the heart failure node, a binary feature F1=1 is generated, and when the platelet count is between [30,50]×10 9 / L interval and associated with the postoperative bleeding node to generate feature F2=1, the serum potassium coefficient of variation, platelet trend slope, F1, F2 and weighted risk index are fused into a spatiotemporal feature vector, its timestamp and node code are encapsulated, and the spatiotemporal feature vector is transmitted to the pathological state matching module, where the serum potassium ion concentration deviation is the difference between the current serum potassium ion concentration measured value and the serum potassium ion concentration critical threshold and the ratio of the serum potassium ion concentration critical threshold, the platelet count deviation is the difference between the platelet count critical threshold and the current platelet count measured value and the ratio of the platelet count critical threshold lower limit, and the weighted risk index is the cumulative sum of the product of the test indicator deviation and the associated edge strength weight of the pathological node in the corresponding knowledge graph;

[0065] The pathological state matching module is used to identify acute pathological states by combining composite feature vectors and quantify the matching degree between pathological data and disease rules in the knowledge graph. The pathological state matching module includes a pathological recognition unit, a pathological prediction unit and a pathological matching unit. The pathological recognition unit is used to combine composite feature vectors and generalized linear model architecture to build a logistic regression recognition model to identify acute pathological states. The pathological recognition unit receives the spatiotemporal feature vector with serum potassium variation coefficient, platelet trend slope, F1, F2 and weighted risk index as input features, sets the initial value of the training weight coefficient of each input feature according to the knowledge graph node weight, and compares the input feature with the training weight coefficient of each input feature. Perform weighted summation to obtain the linear value, build a logistic regression recognition model, and based on the constructed logistic regression recognition model, map the linear value to the pathological state probability through the S-type function, set the pathological state threshold, and when the pathological state probability exceeds the pathological state threshold, it is judged as an acute pathological state. When the pathological state probability is lower than the pathological state threshold, it is judged as a normal state. Use the logarithmic loss function to calculate the difference between the predicted pathological state probability and the true label to obtain the loss value. The knowledge graph node weight is introduced as a regularization term. When F1=1, the learning rate of the heart failure-related weight coefficient is automatically increased to 1.5 times the basic value. If the platelet trend slope is lower than -5×10 for three consecutive hours, 9 / L / h, the locked trend slope weight is no longer updated. The pathology prediction unit is used to combine the dynamic characteristics of the pathology data, use the long short-term memory network model architecture, build a pathology prediction model, and output the predicted value of the pathology data. The pathology prediction unit receives 6 consecutive hours of serum potassium ion concentration data and integrates it into a serum potassium ion concentration detection sequence. It receives 12 consecutive hours of platelet count data and integrates it into a platelet count detection sequence. Based on the serum potassium ion concentration detection sequence and the platelet count detection sequence, the difference between the current hour serum potassium ion concentration and the previous hour serum potassium ion concentration and the percentage of the previous hour serum potassium ion concentration are used as the serum potassium ion concentration change rate. The difference between the current hour platelet count and the previous hour platelet count and the percentage of the time interval are used as the platelet decrease rate. The serum potassium ion concentration change rate is multiplied by the weight of the acute kidney injury node in the knowledge graph to generate a weighted change feature. The platelet decrease rate is combined with the weight of the disseminated intravascular coagulation node to construct a risk-weighted rate. The weighted change feature and the risk-weighted rate are input into the long short-term memory network architecture. The input layer of the long short-term memory network architecture uses the Sigmoid function to linearly combine the weighted change features, risk weighted rate, and hidden state of the previous moment to generate a gating value between 0 and 1. The forget gate uses the Sigmoid function to determine the retention ratio of the historical state and uses the hyperbolic tangent function to generate the new state recommended by the current input. The fully connected layer of the long short-term memory network architecture multiplies the hidden state with the acute kidney injury node weight and the disseminated intravascular coagulation node weight respectively, adds the bias term, and outputs the serum potassium concentration prediction value and the platelet decline rate prediction value. Based on the collected serum potassium concentration data, platelet count data, serum potassium concentration prediction value, platelet decline rate prediction value, 6 consecutive hours of serum potassium concentration sample volume, and 12 hours of platelet count sample volume, the mean square error is used to calculate the prediction deviation to obtain serum potassium loss, platelet loss, and total loss. When the serum potassium prediction value exceeds the threshold interval of the associated disease in the knowledge graph, the cell state update amount in the pathology prediction model is adjusted. When the platelet prediction rate is lower than -5×10 9 / L / h, the forget gate value in the pathology prediction model is locked to 1, and the historical state is maintained. The pathology matching unit is used to combine the collected pathology data with the graph neural network node propagation algorithm to construct a knowledge graph reasoning model, generate rule triggering strength, and quantify the degree of matching between the actual collected pathology data and the disease rules in the knowledge graph. The pathology matching unit receives the collected serum potassium ion concentration data and platelet count data, loads the graph database containing the test item nodes, pathology status nodes and associated edge strength weights, and synchronously obtains the serum potassium prediction value and platelet decline rate prediction value output by the pathology prediction unit. Based on the graph neural network node propagation algorithm, the initial states of the serum potassium node and the platelet node are initialized to the ratio of the corresponding measured value to the critical threshold, and the pathology node state weight is the average of the associated edge strength weights. The state weight of each pathology node is calculated by aggregating neighborhood information, and the weighted attenuation mechanism is used to update the state weight of the pathology node in the knowledge graph. , the calculation process is as follows:

[0066] ;

[0067] in, is the state value of the pathological node at the previous moment, is the state value of the adjacent check node, The knowledge graph reasoning model is constructed based on the association edge strength weight and the S-type function is used to compress the status of each pathology node to the interval [0,1]. Based on serum potassium concentration and platelet count deviation, combined with the association edge strength weight of the pathology node and the real-time pathology node status weight, a weighted accumulation formula is used to calculate the cumulative sum of the serum potassium concentration deviation and platelet count deviation multiplied by the corresponding association edge strength weight and the real-time status weight of the associated pathology node. The corresponding rule trigger strength is obtained to quantify the degree of match between the collected data and the knowledge graph rules. A single pathology node trigger strength threshold and a multi-pathology node total trigger strength threshold are set. When the trigger strength of a single pathology node exceeds the single pathology node trigger strength threshold, the corresponding treatment rule is activated. When the total strength of two or more pathology nodes exceeds the multi-pathology node total trigger strength threshold, the highest warning level is set. If the prediction error continues to exceed 15%, the association edge weight is attenuated by 0.95. Temporary rule edges with an initial weight of 0.5 are generated for unrelated abnormal data with a deviation higher than 0.5.

[0068] The pathological state warning module combines the analysis results of the pathological state matching module with the hierarchical attention mechanism to construct a pathological warning model and output the pathological critical value. The pathological state warning module receives and uniformly quantifies the acute pathological state probability value, the serum potassium predicted value for the next two hours, the platelet decrease rate predicted value, and the rule trigger strength vector, expands the serum potassium predicted value and the platelet decrease rate predicted value to generate a two-hour prediction sequence, and performs six-hour sliding window mean smoothing on the rule trigger strength. The weights of the logistic regression recognition model, the pathological prediction model and the knowledge graph inference model are allocated through the trainable parameter matrix and the normalized exponential function. For the time series output of the pathological prediction model, the S-type function is used to calculate the prediction contribution weights of the current moment and the future moment, forming a two-layer attention allocation mechanism, constructing the pathological warning model, and performing spatial fusion calculation based on the weights of each model and the prediction contribution weight to output the pathological critical value. , the calculation process is as follows:

[0069] ;

[0070] in, 、 and is the weight of the logistic regression recognition model, pathology prediction model and knowledge graph reasoning model, P is the pathological state probability output by the logistic regression recognition model, is the 6-hour sliding mean of the rule triggering intensity, and The weights assigned to the predicted values at different future time points output by the pathology prediction unit, and The predicted values of serum potassium concentration and platelet decline rate in the next 1 hour and 2 hours are used. The pathology criticality threshold is adjusted according to the remaining proportion of each pathology treatment time window in the knowledge graph. When the pathology criticality value exceeds the pathology criticality threshold, the warning level is determined in combination with the maximum node weight in the rule trigger strength vector, and the standard treatment plan in the graph is associated to generate clinical decision recommendations. The latest acute pathology state probability values output by the logistic regression recognition model, pathology prediction model, and knowledge graph reasoning model, the predicted serum potassium value and platelet decline rate value in the next two hours, and the rule trigger strength vector are imported into the pathology warning model to obtain the pathology criticality value.

[0071] The pathological status management module combines the pathological critical value with the knowledge graph entity relationship table to perform graded warnings, and constructs a three-dimensional heat map, sets the upper and lower limits of the associated disease node thresholds, and divides the pathological critical value into special warning, level I warning, and level II warning. If the pathological critical value exceeds 1.2 times the upper limit of the associated disease node threshold and activates two or more high-weight pathological nodes at the same time, it is determined to be a special warning. If the pathological critical value is in the threshold interval of the associated disease node and triggers a single high-weight node, it is determined to be a level I warning. If the pathological critical value is close to the lower limit of the associated disease node threshold and the rule triggering strength meets the standard, it is determined to be a level II warning. Combined with the treatment The remaining ratio of the time window dynamically increases the warning level. When the remaining time is less than 30 minutes, the warning level is automatically upgraded, and the knowledge graph is linked to extract the standard treatment plan corresponding to the highest weight node. The horizontal 24-hour time dimension axis, the vertical serum potassium and platelet dual-scale test index axis, and the vertical pathological state axis are defined to form the coordinate system of the three-dimensional heat map. The thermal value of each space-time point is calculated based on the rule trigger intensity and time attenuation factor, and the upper and lower limits of the space-time point thermal value threshold are set. The red, orange, and yellow warning areas are mapped according to the threshold range of the space-time point thermal value. The continuous high-risk area implementation blocks are displayed in an aggregated manner. When the space-time point thermal value suddenly increases by more than 2 times the historical average, a pulse flashing mark is added.

[0072] First, the pathology data collection module collects and preprocesses the patient's pathology data. Then, the pathology feature extraction module uses the preprocessed data to construct a knowledge graph entity relationship table, extracts dynamic features and binds them to the knowledge graph to generate a composite feature vector. Then, the pathology state matching module combines the composite feature vector to identify acute pathological states and quantify the degree of matching between pathology data and disease rules in the knowledge graph. Subsequently, the pathology state warning module combines the analysis results of the matching module with the hierarchical attention mechanism to construct a pathology warning model and output the pathology criticality value. Finally, the pathology state management module performs graded warnings based on the pathology criticality value and the knowledge graph entity relationship table, and constructs a three-dimensional heat map so that clinicians can intuitively and quickly understand the patient's condition and criticality.

[0073] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A pathology critical value early warning management system based on a pathology knowledge graph, characterized by: It includes pathological data acquisition module, pathological feature extraction module, pathological status matching module, pathological status early warning module and pathological status management module; The pathology data acquisition module collects and pre-processes the patient's pathology data; The pathological feature extraction module constructs a knowledge graph entity relationship table based on the preprocessed pathological data, extracts dynamic features and binds them to the knowledge graph to generate a composite feature vector; The pathological state matching module is used to identify acute pathological states by combining composite feature vectors and quantify the degree of matching between pathological data and disease rules in the knowledge graph; The pathological state warning module combines the analysis results of the pathological state matching module with the hierarchical attention mechanism to construct a pathological warning model and output a pathological critical value; The pathological status management module combines the pathological criticality value with the knowledge graph entity relationship table to perform graded warnings and construct a three-dimensional heat map; The pathological state matching module includes a pathological identification unit, a pathological prediction unit and a pathological matching unit: The pathology recognition unit is used to combine the composite feature vector and the generalized linear model architecture to construct a logistic regression recognition model to identify acute pathological conditions; The pathology prediction unit is used to combine the dynamic characteristics of the pathology data, use the long short-term memory network model architecture, build a pathology prediction model, and output the predicted value of the pathology data; The pathology matching unit is used to combine the collected pathology data with the graph neural network node propagation algorithm to build a knowledge graph inference model, generate rule triggering strength, and quantify the matching degree between the actual collected pathology data and the disease rules in the knowledge graph; In the pathology data acquisition module, the acquisition and preprocessing process of serum potassium ion concentration data and platelet count data includes: Deploy an ion-selective electrode detection system in the pathological critical value early warning management system to calculate the potassium ion concentration by measuring the potential change value; A dual-sheath flow optical counting system is deployed in the pathology critical value warning management system to count platelets by measuring forward scattered light intensity and side fluorescence intensity; The acquired potassium ion concentration data and platelet data were preprocessed. For potassium ion concentration data preprocessing, if the potassium ion concentration fluctuation exceeded 0.3 mmol / L for three consecutive times, an automatic retest procedure was triggered, and the median of the three potassium ion concentrations was taken as the calculation result. For platelet data preprocessing, if the platelet histogram showed a multimodal distribution, the impedance method was automatically switched to review, and the cell volume was measured using the Coulter principle to exclude interference from small red blood cells. Particles with a volume of 2-20 femtoliters were counted and recorded as the effective platelet count. In the pathological feature extraction module, the process of extracting features from the pre-processed serum potassium ion concentration data and platelet count data includes: Parse and extract the test item-critical threshold-associated pathological status triple from the patient's electronic medical record text, calculate the associated edge strength weight of the triple based on the evidence level of evidence-based medicine, store the triple as a graph database node, and use the average weight of the corresponding associated edge strength as the initial weight of the pathological status node in the knowledge graph. The graph database node attributes include test indicator parameters, pathological status code, and treatment timeliness requirements; The serum potassium coefficient of variation was calculated by combining the pre-processed serum potassium concentration data with a 6-hour sliding window. When the serum potassium coefficient of variation exceeded 15%, the acute kidney injury node in the knowledge graph was automatically associated. The least squares method was used to fit the trend slope of the patient's platelet count within 12 hours. When the platelet trend slope was lower than -5×10 9 / L / h is bound to the disseminated intravascular coagulation node, where the coefficient of variation of serum potassium is the percentage of the standard deviation and mean of serum potassium concentration within the sliding window; The deviation of serum potassium concentration and platelet count was calculated and combined with the weight of knowledge graph nodes to construct a weighted risk index. The critical threshold of serum potassium concentration was set to 3.2 mmol / L and the critical threshold of platelet count was set to [30, 50] × 10 9 / L, when the serum potassium concentration is lower than 3.2mmol / L and is associated with the heart failure node, a binary feature F1=1 is generated, and when the platelet count is between [30,50]×10 9 When the / L interval is associated with the postoperative bleeding node, the feature F2=1 is generated. The serum potassium variation coefficient, platelet trend slope, F1, F2 and weighted risk index are fused into a spatiotemporal feature vector, which is encapsulated with its timestamp and node code. The spatiotemporal feature vector is then transmitted to the pathological status matching module. Among them, the serum potassium ion concentration deviation is the ratio of the difference between the current measured value of serum potassium ion concentration and the critical threshold of serum potassium ion concentration to the critical threshold of serum potassium ion concentration; the platelet count deviation is the ratio of the difference between the lower limit of the critical threshold of platelet count and the current measured value of platelet count to the lower limit of the critical threshold of platelet count; the weighted risk index is the cumulative sum of the product of the test indicator deviation and the associated edge strength weight of the pathological node in the corresponding knowledge graph.

2. A pathology critical value early warning management system based on a pathology knowledge graph according to claim 1, characterized in that: In the pathology recognition unit, a logistic regression recognition model is constructed to identify acute pathological conditions, including: The pathology recognition unit receives the spatiotemporal feature vector with the serum potassium coefficient of variation, platelet trend slope, F1, F2, and weighted risk index as input features, sets the initial value of the training weight coefficient of each input feature according to the knowledge graph node weight, performs weighted summation on the input feature and the training weight coefficient of each input feature to obtain a linear value, and constructs a logistic regression recognition model; Based on the constructed logistic regression recognition model, the linear value is mapped to the probability of pathological state through the S-type function, and the pathological state threshold is set. When the pathological state probability exceeds the pathological state threshold, it is judged as an acute pathological state. When the pathological state probability is lower than the pathological state threshold, it is judged as a normal state. The logarithmic loss function is used to calculate the difference between the predicted pathological state probability and the true label to obtain the loss value. The knowledge graph node weight is introduced as a regularization term. When F1=1, the learning rate of the heart failure-related weight coefficient is automatically increased to 1.5 times the basic value. If the platelet trend slope is lower than -5×10 for three consecutive hours, 9 / L / h, the trend slope weight is locked and no longer updated.

3. A pathology critical value early warning management system based on a pathology knowledge graph according to claim 2, characterized in that: In the pathology prediction unit, the process of constructing a pathology prediction model and outputting a predicted value of serum potassium ion concentration and a predicted value of platelet decrease rate includes: The pathology prediction unit receives 6 consecutive hours of serum potassium concentration data and integrates it into a serum potassium concentration detection sequence, and receives 12 consecutive hours of platelet count data and integrates it into a platelet count detection sequence; Based on the serum potassium concentration detection sequence and platelet count detection sequence, the difference between the serum potassium concentration in the current hour and the serum potassium concentration in the previous hour and the percentage of the serum potassium concentration in the previous hour were taken as the serum potassium concentration change rate, and the difference between the platelet count in the current hour and the platelet count in the previous hour and the percentage of the time interval were taken as the platelet decline rate; Multiply the serum potassium concentration change rate with the acute kidney injury node weight in the knowledge graph to generate a weighted change feature. Combine the platelet decrease rate with the disseminated intravascular coagulation node weight to construct a risk-weighted rate. The weighted change characteristics and risk-weighted rate are input into the input layer of the long short-term memory network architecture to construct a pathology prediction model, which outputs the predicted values of serum potassium ion concentration and platelet decrease rate; Based on the collected serum potassium concentration data, platelet count data, predicted serum potassium concentration, predicted platelet decline rate, 6-hour serum potassium concentration sample size, and 12-hour platelet count sample size, the mean square error was used to calculate the prediction bias to obtain serum potassium loss, platelet loss, and total loss; When the predicted serum potassium value exceeds the threshold interval of the associated disease in the knowledge graph, the cell state update amount in the pathology prediction model is adjusted; when the platelet prediction rate is lower than -5×10 9 When the number of beats is / L / h, the forget gate value in the pathology prediction model is locked to 1, and the historical state is maintained.

4. A pathology critical value early warning management system based on a pathology knowledge graph according to claim 3, characterized in that: In the pathology matching unit, the process of constructing a knowledge graph reasoning model and generating rule trigger strength includes: The pathology matching unit receives the collected serum potassium concentration data and platelet count data, loads the graph database containing the test item nodes, pathology status nodes and associated edge strength weights, and simultaneously obtains the serum potassium predicted value and platelet decline rate predicted value output by the pathology prediction unit; Based on the graph neural network node propagation algorithm, the initial states of serum potassium nodes and platelet nodes are initialized as the ratio of the corresponding measured value to the critical threshold. The state weight of the pathological node is the average weight of the associated edge strength. The state weight of each pathological node is calculated by aggregating neighborhood information, and the weighted attenuation mechanism is used to update the state weight of the pathological node in the knowledge graph. , and use the S-type function to compress the status of each pathological node to the [0,1] interval to build a knowledge graph reasoning model; Based on the serum potassium concentration and platelet count deviation, combined with the pathology node's associated edge strength weight and the real-time pathology node status weight, the weighted cumulative formula is used to calculate the cumulative sum of the serum potassium concentration deviation, platelet count deviation, the product of the corresponding associated edge strength weight and the associated pathology node's real-time status weight. The corresponding rule trigger strength is obtained to quantify the degree of match between the collected data and the knowledge graph rules. Set the trigger intensity threshold of a single pathology node and the total trigger intensity threshold of multiple pathology nodes. When the trigger intensity of a single pathology node exceeds the single pathology node trigger intensity threshold, the corresponding handling rule is activated. When the total intensity of two or more pathology nodes exceeds the total trigger intensity threshold of multiple pathology nodes, it is set to the highest warning level. If the prediction error continues to exceed 15%, the weight of the associated edge is attenuated at a rate of 0.95, and a temporary rule edge with an initial weight of 0.5 is generated for abnormal data that is unrelated but has a deviation higher than 0.

5.

5. A pathology critical value early warning management system based on a pathology knowledge graph according to claim 4, characterized in that: In the pathological state warning module, the process of constructing a pathological warning model and outputting a pathological critical value includes: The pathological state warning module receives and uniformly quantifies the acute pathological state probability value, the serum potassium predicted value for the next two hours, the platelet decline rate predicted value, and the rule trigger strength vector. It expands the serum potassium predicted value and the platelet decline rate predicted value to generate a two-hour prediction sequence and performs six-hour sliding window mean smoothing on the rule trigger strength. The weights of the logistic regression recognition model, pathology prediction model, and knowledge graph inference model are assigned through a trainable parameter matrix and a normalized exponential function. Based on the time series output of the pathology prediction model, the sigmoid function is used to calculate the prediction contribution weights of the current moment and the future moment, forming a two-layer attention allocation mechanism and constructing a pathology early warning model. Perform spatial fusion calculation based on each model weight and predicted contribution weight to output pathological critical value , the pathology criticality judgment threshold is adjusted according to the remaining proportion of each pathology treatment time window in the knowledge graph. When the pathology criticality value exceeds the pathology criticality judgment threshold, the warning level is determined in combination with the maximum node weight in the rule trigger intensity vector, and the standard treatment plan in the graph is associated to generate clinical decision recommendations.

6. A pathology critical value early warning management system based on a pathology knowledge graph according to claim 5, characterized in that: In the pathological state early warning module, the process of importing the latest output results of each model into the pathological early warning model and outputting the pathological critical value includes: The latest acute pathological state probability values output by the logistic regression recognition model, pathology prediction model, and knowledge graph reasoning model, the serum potassium predicted value and platelet decrease rate predicted value for the next two hours, and the rule triggering intensity vector are imported into the pathology warning model to obtain the pathological critical value.

7. The pathology critical value early warning management system based on the pathology knowledge graph according to claim 6 is characterized by: In the pathological status management module, the process of combining the pathological critical value with the knowledge graph entity relationship table to perform graded warnings and construct a three-dimensional heat map includes: Set upper and lower thresholds for associated disease nodes, and divide pathological critical values into special warning, level I warning, and level II warning; If the pathological critical value exceeds 1.2 times the upper limit of the threshold of the associated disease node and two or more high-weight pathological nodes are activated at the same time, it is judged as a special-level warning. If the pathological critical value is within the threshold range of the associated disease node and a single high-weight node is triggered, it is judged as a level I warning. If the pathological critical value is close to the lower limit of the threshold of the associated disease node and the rule triggering intensity meets the standard, it is judged as a level II warning. The warning level is dynamically increased in combination with the remaining proportion of the treatment time window. When the remaining time is less than 30 minutes, the warning level is automatically upgraded, and the knowledge graph is linked to extract the standard treatment plan corresponding to the highest-weighted node; The coordinate system of the three-dimensional heat map is defined as the horizontal 24-h time dimension axis, the vertical serum potassium and platelet dual-scale test index axis, and the vertical pathological status axis. The thermal value of each spatiotemporal point is calculated based on the rule trigger intensity and time attenuation factor, and the upper and lower thresholds of the spatiotemporal point thermal value are set. The red, orange, and yellow warning areas are mapped according to the threshold intervals of the spatiotemporal point thermal value. The continuous high-risk area implementation blocks are aggregated and displayed. When the spatiotemporal point thermal value suddenly increases by more than 2 times the historical average, a pulse flashing mark is added.

Images