Urinary calculus examination image recognition and data visualization analysis and early warning reminding system

Abstract

The invention relates to the technical field of medical data processing, and particularly discloses a urinary calculus examination image recognition and data visualization analysis and early warning reminding system, which comprises an examination data analysis module, an early warning module, a data processing module and an early warning module, wherein the examination data analysis module is used for extracting calculus incidence related sequence data from user urinary calculus examination image and blood and urine report synchronous sequence data; position distribution, morphological characteristics and biochemical indexes are covered. The data visualization module is used for converting the data into a stone volume dynamic change simulation diagram, a biochemical index abnormal value association map and a stone position dynamic mapping diagram, so that a user can conveniently inquire. And the dynamic threshold reasoning module is used for carrying out space-time alignment and cross-local dimension anomaly fusion reasoning on the visualization result to obtain a user personalized multi-dimensional grading early warning threshold and a clinical decision simulation path. The early warning and report integration module determines a current early warning level according to the latest index and an early warning threshold value, and generates a comprehensive diagnosis and treatment report in combination with visual curve data and a decision path; patients and doctors can conveniently know illness states and formulate treatment schedules.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and particularly to a urinary stone examination image recognition, data visualization analysis and early warning reminder system. Background Art

[0002] In the field of medical health, urinary stone is a common urinary system disease, which seriously affects the quality of life of patients. Accurately diagnosing urinary stones and taking effective treatment measures in a timely manner are of crucial importance. Data such as urinary stone examination images (such as ultrasound, CT and other images) and blood and urine examination reports contain rich disease information, which plays a key role for doctors to judge the situation of stones and formulate treatment plans. Traditional diagnosis of urinary stones mainly relies on doctors' visual observation of examination images and manual analysis of examination report data. However, with the development of medical technology, the amount of data generated is becoming increasingly large and complex. Relying solely on manual analysis is not only inefficient, but also easily affected by factors such as doctors' subjective experience and fatigue, resulting in difficulties in ensuring the accuracy and consistency of diagnosis results. In recent years, with the continuous progress of artificial intelligence and data visualization technology, the application of these technologies to the diagnosis and analysis of urinary stones has become a research hotspot. Image recognition technology can quickly and accurately extract features and analyze urinary stone examination images, helping doctors to more clearly understand information such as the location and shape of stones; data visualization technology can present complex examination data in an intuitive and easy-to-understand graphical way, facilitating doctors and patients to understand; and the early warning reminder function based on data analysis can timely detect potential changes in the condition, providing strong support for clinical decision-making. By constructing a urinary stone examination image recognition, data visualization analysis and early warning reminder system, it is expected to achieve a comprehensive and in-depth analysis of urinary stone-related data, improve the diagnosis efficiency and accuracy, and provide more personalized and precise medical services for patients. This not only helps to improve the treatment effect of patients, but also promotes the development of the diagnosis technology of urinary system diseases towards intelligence and precision, with broad application prospects and important clinical significance.

[0003] There are many deficiencies in the existing technology for the diagnosis and analysis of urinary stones. First, it is difficult to effectively extract the key sequence data related to the onset of urinary stones in the synchronous sequence data of urinary stone examination images and blood and urine examination reports, and it is impossible to achieve a comprehensive analysis with time series alignment, resulting in an incomplete grasp of the characteristics of the onset of stones. Second, there is a lack of effective visualization means to convert complex sequence data related to the onset of stones into intuitive and easy-to-understand graphics, such as being unable to generate a simulation diagram of the dynamic change of stone volume, an association map of abnormal biochemical index values, and a dynamic mapping diagram of stone position, making it difficult for doctors and patients to clearly understand the changes in the condition. Furthermore, it is also impossible to perform in-depth multi-dimensional abnormal fusion reasoning on multi-dimensional visualization data, and it is impossible to obtain personalized multi-dimensional grading early warning thresholds and clinical decision-making simulation paths, resulting in inaccurate early warning and lack of targeted clinical guidance.

[0004] Therefore, the present invention proposes a urolithiasis examination image recognition, data visualization analysis and early warning reminder system. Summary of the Invention

[0005] The present invention provides a urolithiasis examination image recognition, data visualization analysis and early warning reminder system. The examination data analysis module accurately extracts relevant data such as the temporal alignment of the stone position distribution, morphology and pathogenic biochemical sequence indexes from the urolithiasis examination images and the synchronous sequence data of blood and urine examination reports, laying a comprehensive foundation for subsequent analysis. Then, the data visualization module converts it into a simulated graph of the dynamic change of the stone volume, an association map of abnormal biochemical index values, and a dynamic mapping map of the stone position, which are intuitive graphics for users to query the condition. Then, the dynamic threshold reasoning module performs spatio-temporal alignment and cross-local dimension abnormal fusion reasoning on these visualization results to obtain personalized multi-dimensional grading early warning thresholds and clinical decision simulation paths, considering individual differences to assist in precise treatment. Finally, the early warning and report integration module determines the current early warning level based on the latest indexes and early warning thresholds, and generates a comprehensive diagnosis and treatment report by combining the visualization curve data and clinical decision simulation paths generated based on the comprehensive examination visualization results, providing comprehensive condition information and treatment guidance for patients, and generally improving the scientificity and effectiveness of data processing, condition analysis and decision-making in the diagnosis and treatment process of urolithiasis, facilitating patients and doctors to understand the condition and formulate treatment plans.

[0006] The present invention provides a urolithiasis examination image recognition, data visualization analysis and early warning reminder system, including: An examination data analysis module, configured to extract the sequence data related to the onset of urolithiasis in the synchronous sequence data of the urolithiasis examination images of the user and the blood and urine examination reports, including the sequence feature of the position distribution of urolithiasis with temporal alignment, the sequence feature of morphology, and the biochemical sequence indexes related to the onset of urolithiasis; A data visualization module, configured to convert the sequence data related to the onset of urolithiasis into a simulated graph of the dynamic change of the stone volume, an association map of abnormal biochemical index values, and a dynamic mapping map of the stone position, as the comprehensive examination visualization result for the user to query; A dynamic threshold reasoning module, configured to perform spatio-temporal alignment and cross-local dimension abnormal fusion reasoning on the simulated graph of the dynamic change of the stone volume, the association map of abnormal biochemical index values, and the dynamic mapping map of the stone position, to obtain the personalized multi-dimensional grading early warning threshold and clinical decision simulation path of the user; An early warning and report integration module, configured to determine the current early warning level of the user based on the latest relevant indexes of the onset of urolithiasis of the user and the personalized multi-dimensional grading early warning threshold of the user, and generate a comprehensive diagnosis and treatment report of urolithiasis by combining the visualization curve data generated based on the comprehensive examination visualization result and the clinical decision simulation path.

[0007] Optionally, the examination data analysis module includes: An image recognition sub-module, which is used to extract the urinary calculus position data and morphological data of each urinary calculus examination image in the user's synchronous sequence data based on all the local urinary calculus images in each urinary calculus examination image of the user's synchronous sequence data; A data serialization sub-module, which is used to generate the position distribution sequence features and morphological sequence features of urinary calculi based on the urinary calculus position data and morphological data of all urinary calculus examination images in the user's synchronous sequence data; A report serialization analysis sub-module, which is used to generate the biochemical sequence indicators related to the occurrence of urinary calculi based on the biochemical indicators related to the occurrence of urinary calculi in all blood and urine examination reports in the user's synchronous sequence data; A timing alignment sub-module, which is used to perform timing alignment on the position distribution sequence features, morphological sequence features and biochemical sequence indicators related to the occurrence of urinary calculi of urinary calculi to obtain the sequence data related to the occurrence of urinary calculi.

[0008] Optionally, a data visualization module, including: A dynamic simulation sub-module of urinary calculi, which is used to generate a simulation diagram of the dynamic change of the calculus volume based on the morphological sequence features of the urinary calculi in the sequence data related to the occurrence of urinary calculi. At the same time, a dynamic mapping diagram of the calculus position is generated based on the position distribution sequence features of the urinary calculi in the sequence data related to the occurrence of urinary calculi; A first abnormal index extraction sub-module, which is used to extract the first abnormal biochemical index and the first sequential abnormal index from the position distribution sequence features and morphological sequence features of urinary calculi; A second abnormal index extraction sub-module, which is used to extract the second abnormal biochemical index and the second sequential abnormal index from the biochemical sequence indicators related to the occurrence of urinary calculi; An abnormal index mapping sub-module, which is used to generate an associated map of abnormal values of biochemical indicators based on the first abnormal biochemical index, the first sequential abnormal index, the second abnormal biochemical index and the second sequential abnormal index, as a comprehensive examination visualization result for the user to query.

[0009] Optionally, a dynamic threshold inference module, including: A cross-local dimension abnormal fusion inference sub-module, which is used to perform spatio-temporal alignment and cross-local dimension abnormal fusion inference on the simulation diagram of the dynamic change of the calculus volume, the associated map of abnormal values of biochemical indicators and the dynamic mapping diagram of the calculus position, to obtain multiple cross-local dimension abnormal fusion inference information and cross-local dimension abnormal fusion inference context of the patient; A dynamic threshold inference sub-module, which is used to determine the personalized multi-dimensional grading warning threshold and the clinical decision simulation path of the user based on the standard cross-local dimension abnormal fusion inference context and the multiple cross-local dimension abnormal fusion inference information and cross-local dimension abnormal fusion inference context of the patient.

[0010] Optionally, the cross-local dimension anomaly fusion inference sub-module includes: Anomaly data extraction unit, configured to extract the first urolithiasis diagnosis-related anomaly data from the simulated graph of the dynamic change of the stone volume, and at the same time, extract the second urolithiasis diagnosis-related anomaly data from the dynamic mapping graph of the stone position; Time span determination unit for determining a local division time span sequence based on the same anomaly value interval sequence in the first urolithiasis diagnosis-related anomaly data and the same anomaly value interval sequence in the second urolithiasis diagnosis-related anomaly data; Synchronous division unit, configured to synchronously divide the first urolithiasis diagnosis-related anomaly data, the second urolithiasis diagnosis-related anomaly data, and the biochemical index anomaly value association map based on the local division time span sequence to obtain multi-dimensional local anomaly data; Cross-dimension fusion inference unit, configured to perform cross-dimension fusion inference on the multi-dimensional local anomaly data to obtain multiple cross-local dimension anomaly fusion inference information and cross-local dimension anomaly fusion inference context of the patient.

[0011] Optionally, the time span determination unit includes: Cause correlation coefficient acquisition sub-unit, configured to acquire the urolithiasis cause correlation coefficient between each index data in the first urolithiasis diagnosis-related anomaly data and each index data in the second urolithiasis diagnosis-related anomaly data; Time span sequence generation unit, configured to determine the local division time span sequence based on the urolithiasis cause correlation coefficient between each index data in the first urolithiasis diagnosis-related anomaly data and each index data in the second urolithiasis diagnosis-related anomaly data, the same anomaly value interval sequence in the first urolithiasis diagnosis-related anomaly data, and the same anomaly value interval sequence in the second urolithiasis diagnosis-related anomaly data: ; In the formula, is the local division time span sequence, is the total number of all index data in the first urolithiasis diagnosis-related anomaly data, is the total number of all index data in the second urolithiasis diagnosis-related anomaly data, is the th index data in the first urolithiasis diagnosis-related anomaly data and the th index data in the second urolithiasis diagnosis-related anomaly data, is the average function, is the The first value in the sequence of the same type of outlier spacing for a certain type of indicator data, is the first value in the sequence of the same type of outlier spacing for a certain type of indicator data, for the first urolithiasis diagnosis-related abnormal data, is the second value in the sequence of the same type of outlier spacing for a certain type of indicator data, for the second urolithiasis diagnosis-related abnormal data, is the second value in the sequence of the same type of outlier spacing for a certain type of indicator data, for the first urolithiasis diagnosis-related abnormal data, is the th value in the sequence of the same type of outlier spacing for a certain type of indicator data, for the second urolithiasis diagnosis-related abnormal data, is the th value in the sequence of the same type of outlier spacing for a certain type of indicator data, and its value is equal to the minimum of the total number of values in the sequence of the same type of outlier spacing for a certain type of indicator data in the first urolithiasis diagnosis-related abnormal data and the total number of values in the sequence of the same type of outlier spacing for a certain type of indicator data in the second urolithiasis diagnosis-related abnormal data. the total number of values in the sequence of the same type of outlier spacing for a certain type of indicator data, the minimum of the total number of values in the sequence of the same type of outlier spacing for a certain type of indicator data in the second urolithiasis diagnosis-related abnormal data.

[0012] Optionally, the cross-dimensional fusion inference unit includes: a cause association rule acquisition subunit for acquiring all stone cause association rules; a compliance degree determination subunit for performing cross-dimensional combination on the multi-dimensional local abnormal data based on all stone cause association rules to obtain multiple cross-dimensional combined abnormal data, and determining the compliance degree of each cross-dimensional combined abnormal data with respect to the corresponding stone cause association rule; a fusion inference subunit for obtaining multiple cross-local dimension abnormal fusion inference information of the patient based on all stone cause association rules and all cross-dimensional combined abnormal data; an inference context generation subunit for generating a cross-local dimension abnormal fusion inference context based on all cross-dimensional combined abnormal data, the corresponding all stone cause association rules, and the corresponding compliance degrees, and combining the corresponding all cross-local dimension abnormal fusion inference information.

[0013] Optionally, the dynamic threshold inference sub-module includes: a macro context deviation analysis unit for determining the abnormal fusion inference macro deviation degree based on the standard cross-local dimension abnormal fusion inference context and the cross-local dimension abnormal fusion inference context; A grading early warning threshold determination unit, configured to determine a personalized multi-dimensional grading early warning threshold for the user based on all cross-local dimension abnormal fusion inference information and the macro deviation degree of abnormal fusion inference of the patient; A clinical decision-making path simulation unit, configured to determine a clinical decision-making simulation path for the user based on the cross-local dimension abnormal fusion inference context.

[0014] Optionally, the grading early warning threshold determination unit includes: A basic threshold determination subunit, configured to determine a multi-dimensional grading early warning basic threshold based on all cross-local dimension abnormal fusion inference information of the patient; A grading threshold determination subunit, configured to correct the multi-dimensional grading early warning basic threshold based on the macro deviation degree of abnormal fusion inference to obtain a personalized multi-dimensional grading early warning threshold for the user.

[0015] Optionally, the early warning and report integration module includes: An early warning level diagnosis sub-module, configured to determine the current early warning level of the user based on the latest relevant indicators of the user's urolithiasis onset and the personalized multi-dimensional grading early warning threshold of the user, and issue an early warning signal based on the current early warning level; An intervention recommendation generation sub-module, configured to determine the subsequent intervention priority recommendation for the user based on the clinical decision-making simulation path; A report integration sub-module, configured to generate a variety of visual curve data based on the comprehensive examination visualization results, and integrate the current early warning level of the user, the variety of visual curve data, and the subsequent intervention priority recommendation of the user to generate a comprehensive diagnosis and treatment report for urolithiasis.

[0016] The present invention has the following advantages over the prior art: The inspection data analysis module accurately extracts relevant data such as the time-sequentially aligned stone position distribution, morphology, and pathogenesis biochemical sequence indicators from the urolithiasis inspection images and the synchronous sequence data of blood and urine inspection reports, laying a comprehensive foundation for subsequent analysis; then the data visualization module converts it into a simulated graph of the dynamic change of stone volume, an association graph of abnormal biochemical index values, and a dynamic mapping graph of stone position, facilitating the user to query the condition with intuitive graphics; then the dynamic threshold inference module performs spatio-temporal alignment and cross-local dimension abnormal fusion inference on these visualization results to obtain a personalized multi-dimensional grading early warning threshold and a clinical decision-making simulation path, considering individual differences to assist in precise treatment; finally, the early warning and report integration module determines the current early warning level based on the latest indicators and the early warning threshold, and generates a comprehensive diagnosis and treatment report in combination with the visual curve data and the clinical decision-making simulation path, providing comprehensive condition information and treatment guidance for patients, and overall improving the scientificity and effectiveness of data processing, condition analysis, and decision-making in the urolithiasis diagnosis and treatment process, facilitating patients and doctors to understand the condition and formulate treatment plans.

[0017] Other features and advantages of the present invention will be set forth in the following description, and in part will be obvious from the description, or may be learned by practice of the present invention. The objectives and other advantages of the present invention may be realized and attained by the structure particularly pointed out in this application document.

[0018] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Description of the Drawings

[0019] The drawings are used to provide a further understanding of the present invention, and constitute a part of the description. They are used together with the embodiments of the present invention to explain the present invention, but do not constitute a limitation to the present invention. In the drawings: Figure 1 It is a schematic diagram of the architecture of the urinary calculus examination image recognition, data visualization analysis and early warning reminder system in the embodiment of the present invention; Figure 2 It is an example diagram of the cross-local dimension abnormal fusion inference context in the embodiment of the present invention. Detailed Embodiments

[0020] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0021] Referring to Figure 1 , the present invention provides a urinary calculus examination image recognition, data visualization analysis and early warning reminder system, including: An examination data analysis module, which is used to extract the sequence data related to the onset of calculus disease from the synchronous sequence data of the user's urinary calculus examination image and blood and urine examination reports, including the sequence features of the position distribution, morphological sequence features of the urinary calculus in time series alignment, and biochemical sequence indexes related to the onset of calculus disease; this module is responsible for extracting the sequence data closely related to the onset of calculus from the user's urinary calculus examination image and the synchronous sequence data of the corresponding blood and urine examination reports. For example, the urinary calculus examination images taken at different time points, as well as the blood and urine examination report data of the same period. By processing these data, the sequence features of the position distribution of the urinary calculus in time series alignment (such as the change of the calculus in different positions of the urinary system over time), morphological sequence features (such as the change of the size and shape of the calculus over time), and biochemical sequence indexes related to the onset of calculus disease (such as the fluctuation of the content of components related to calculus formation in blood or urine over time) are obtained, providing a comprehensive and orderly data basis for the in-depth analysis of each module of the subsequent system.

[0022] The data visualization module is used to convert the sequence data related to the occurrence of urinary stones into a simulation graph of the dynamic change of the stone volume, an association map of abnormal values of biochemical indicators, and a dynamic mapping graph of the stone position, which are used as the visualization results of the comprehensive examination for users to query; this module converts the sequence data related to the occurrence of urinary stones extracted by the examination data parsing module into intuitive and easy-to-understand graphs. According to the morphological sequence characteristics of urinary stones, a simulation graph of the dynamic change of the stone volume is generated, enabling users to clearly see the increase and decrease of the stone volume over time; based on the sequence characteristics of the position distribution, a dynamic mapping graph of the stone position is generated, intuitively showing the change of the stone position in the urinary system; at the same time, abnormal indicators are extracted from various sequence characteristics and indicators to generate an association map of abnormal values of biochemical indicators, revealing the relationship between the abnormalities of various biochemical indicators. These visualization results facilitate users to query at any time and quickly understand the trend of the disease.

[0023] The dynamic threshold inference module is used to perform spatio-temporal alignment and cross-local dimension abnormal fusion inference on the simulation graph of the dynamic change of the stone volume, the association map of abnormal values of biochemical indicators, and the dynamic mapping graph of the stone position, so as to obtain the user's personalized multi-dimensional grading warning threshold and the clinical decision simulation path; for the simulation graph of the dynamic change of the stone volume, the association map of abnormal values of biochemical indicators, and the dynamic mapping graph of the stone position generated by the data visualization module, this module performs spatio-temporal alignment and cross-local dimension abnormal fusion inference. For example, comprehensively consider the abnormal information shown in each graph at different time points and analyze the association between the abnormalities in different dimensions (such as position, morphology, biochemical indicators). Through this inference, a personalized multi-dimensional grading warning threshold for the user (such as the boundary value for dividing different risk levels according to the development of the stone) and a clinical decision simulation path (simulating the reasonable diagnosis and treatment steps for the user's condition) are obtained, providing an important reference for precision medicine.

[0024] The warning and report integration module is used to determine the user's current warning level based on the latest relevant indicators of the occurrence of the user's urinary stones and the user's personalized multi-dimensional grading warning threshold, and generate a comprehensive diagnosis and treatment report for urinary stones in combination with the visualization curve data and the clinical decision simulation path generated based on the visualization results of the comprehensive examination. This module compares the latest relevant indicators of the occurrence of the user's urinary stones with the personalized multi-dimensional grading warning threshold obtained by the dynamic threshold inference module to determine the current warning level, such as low risk, medium risk or high risk, etc. At the same time, in combination with the visualization curve data (such as the stone volume change curve, the biochemical indicator fluctuation curve, etc.) generated by the visualization results of the comprehensive examination, and the clinical decision simulation path, a comprehensive diagnosis and treatment report for urinary stones is generated. This report can help patients and doctors comprehensively understand the current situation and development trend of the disease, so as to formulate a scientific and reasonable treatment plan.

[0025] In an alternative embodiment, the examination data parsing module includes: The image recognition sub-module is used to extract the urolith position data and morphological data of each urolith examination image in the user's synchronous sequence data based on all the local urolith images in each urolith examination image. It works based on all the local urolith images in each urolith examination image in the user's synchronous sequence data. For example, in examination images such as ultrasound or CT, the local image area corresponding to each stone is identified. Then, the urolith position data (such as the specific coordinate position of the stone in the urinary system) and morphological data (such as the size, shape, contour and other characteristic data of the stone) are extracted from these local images. These data can describe in detail the spatial position and morphological characteristics of the urolith in each examination image, providing the original information for analyzing the changes of the stone at different times.

[0026] The data serialization sub-module is used to generate the position distribution sequence features and morphological sequence features of uroliths based on the urolith position data and morphological data of all urolith examination images in the user's synchronous sequence data. This module processes the urolith position data and morphological data of all urolith examination images extracted by the image recognition sub-module. Integrate the position data of the examination images at different time points to generate the position distribution sequence features of uroliths, reflecting the law of the position change of the stone over a period of time; similarly, organize the morphological data into morphological sequence features to reflect the evolution of the stone morphology over time. For example, through these sequence features, it can be seen whether the stone is gradually moving in a certain direction, or whether the morphology is gradually getting larger or smaller, etc., providing a basis for comprehensively understanding the development process of the stone.

[0027] The report serialization analysis sub-module is used to generate the biochemical sequence indicators related to urolithiasis based on the biochemical indicators related to urolithiasis in all blood and urine examination reports in the user's synchronous sequence data. This module focuses on the biochemical indicators related to urolithiasis in all blood and urine examination reports in the user's synchronous sequence data. Analyze and organize these indicators to generate the biochemical sequence indicators related to urolithiasis. For example, the content of components such as calcium, oxalic acid, and uric acid in the blood, and indicators such as the pH value and crystal components in the urine are processed to form sequences that change over time. These sequences can reflect the dynamic changes of the biochemical environment related to urolithiasis, helping to analyze the formation and development mechanism of uroliths from a biochemical perspective.

[0028] The time series alignment sub-module is used to perform time series alignment on the position distribution sequence features, morphological sequence features of urinary calculi, and biochemical sequence indicators related to the onset of calculi, so as to obtain sequence data related to the onset of calculi. Align the previously generated position distribution sequence features, morphological sequence features of urinary calculi, and biochemical sequence indicators related to the onset of calculi in chronological order. Since different types of data, although all reflecting information related to calculi, may have differences in acquisition time, through time series alignment, these data are made to match each other in the time dimension, thereby obtaining complete sequence data related to the onset of calculi. The integrated data in this way can more accurately reflect the temporal relationship between the changes in the position and morphology of calculi and the changes in biochemical indicators, providing an ordered and comprehensive data basis for subsequent comprehensive analysis and disease condition judgment.

[0029] In an alternative embodiment, the data visualization module includes: The dynamic simulation sub-module of urinary calculi is used to generate a simulation diagram of the dynamic change of the calculus volume based on the morphological sequence features of urinary calculi in the sequence data related to the onset of calculi. At the same time, it generates a dynamic mapping diagram of the calculus position based on the position distribution sequence features of urinary calculi in the sequence data related to the onset of calculi; this module uses the morphological sequence features of urinary calculi in the sequence data related to the onset of calculi to generate a simulation diagram of the dynamic change of the calculus volume. The morphological sequence features contain information such as the size and shape of the calculus changing over time. By analyzing and calculating this information, the change of the calculus volume at different time points is simulated in a graphical way, enabling users to intuitively see how the calculus volume increases or decreases. At the same time, a dynamic mapping diagram of the calculus position is generated based on the position distribution sequence features of urinary calculi. This feature records the change of the calculus position in the urinary system over time, and the movement trajectory of the calculus in the body can be clearly presented through the mapping diagram, helping users understand the dynamic changes in the calculus position. For example, if the morphological sequence features show that the major axis and minor axis of the calculus gradually increase over a period of time, the dynamic simulation sub-module can generate a corresponding simulation diagram of the gradually increasing calculus volume; if the position distribution sequence features indicate that the calculus moves from a certain part of the kidney to the ureter, the dynamic mapping diagram of the calculus position will intuitively show this movement process.

[0030] The first abnormal index extraction sub-module is used to extract the first abnormal biochemical index and the first sequential abnormal index from the location distribution sequence features and morphological sequence features of urinary calculi; this module focuses on mining abnormal information from the location distribution sequence features and morphological sequence features of urinary calculi. The first abnormal biochemical index refers to finding clues that may imply abnormal biochemical indicators from these sequences related to the physical characteristics of calculi. For example, if there is a sudden abnormal change in the calculus morphology, it may be related to changes in certain biochemical indicators, and the module will extract such potentially related biochemical indicators. The first sequential abnormal index is for the location distribution and morphological sequences themselves, to find abnormal sequence situations that do not conform to the normal change rules. For example, if the calculus location should move slowly but suddenly shows a large jump-like movement, this abnormal location sequence change will be extracted. These abnormal indicators provide key clues for further analyzing the occurrence of calculus disease.

[0031] The second abnormal index extraction sub-module is used to extract the second abnormal biochemical index and the second sequential abnormal index from the biochemical sequence indicators related to the occurrence of calculi; it mainly conducts the extraction work of abnormal indicators in the biochemical sequence indicators related to the occurrence of calculi. The second abnormal biochemical index refers to the index value that exceeds the normal range directly found from the biochemical sequence indicator data. For example, the content of a certain component closely related to calculus formation in the blood is too high or too low. The second sequential abnormal index focuses on the change rule of biochemical sequence indicators over time. If there is a situation that does not conform to the conventional change pattern, such as a certain indicator has been stable but suddenly shows continuous fluctuations, this abnormal sequence change will be extracted by this module, providing a basis for analyzing the change of the biochemical mechanism of calculus occurrence.

[0032] The abnormal index mapping sub-module is used to generate a mapping of abnormal values of biochemical indicators based on the first abnormal biochemical index, the first sequential abnormal index, the second abnormal biochemical index, and the second sequential abnormal index, as a comprehensive inspection visualization result for users to query. This module integrates the first abnormal biochemical index, the first sequential abnormal index, the second abnormal biochemical index, and the second sequential abnormal index obtained from the previous two abnormal index extraction sub-modules to generate a mapping of abnormal values of biochemical indicators. The mapping shows the mutual relationship between various abnormal indicators in an intuitive graphical way. For example, which abnormal calculus locations or morphologies are closely related to specific abnormal biochemical indicators, and the possible internal connections between different abnormal biochemical indicators. As a comprehensive inspection visualization result for users to query, doctors or patients can, by viewing this mapping, more comprehensively and deeply understand the relevance of various abnormal situations during the occurrence of calculus disease, providing strong support for accurately judging the condition and formulating treatment plans.

[0033] In an alternative embodiment, the dynamic threshold reasoning module includes: Cross - local - dimension abnormal fusion inference sub - module, which is used to perform spatio - temporal alignment and cross - local - dimension abnormal fusion inference on the simulated diagram of the dynamic change of stone volume, the associated atlas of abnormal biochemical index values, and the dynamic mapping diagram of stone position, so as to obtain multiple cross - local - dimension abnormal fusion inference information and cross - local - dimension abnormal fusion inference context of the patient (refer to Figure 2 ); This sub - module is responsible for processing three visualization results: the simulated diagram of the dynamic change of stone volume, the associated atlas of abnormal biochemical index values, and the dynamic mapping diagram of stone position. First, spatio - temporal alignment is carried out, which means matching data in different dimensions (volume, biochemical index, position) in terms of time and space concepts to ensure the consistency of analysis. For example, the change in stone volume at a certain moment is corresponded to the abnormality of biochemical index and the change in stone position at the same moment. Then, cross - local - dimension abnormal fusion inference is carried out, which comprehensively considers abnormal information from different local dimensions (volume, biochemistry, position within a short period of time) and explores the potential connections between them. For example, when the stone volume suddenly increases, combined with the changes in certain component indicators in the associated atlas of abnormal biochemical index values and the change in position in the dynamic mapping diagram of stone position, analyze the possible clinical significance represented by the simultaneous occurrence of these abnormalities. Through this reasoning method, multiple cross - local - dimension abnormal fusion inference information of the patient is obtained, and these information are the conclusions drawn from the comprehensive analysis of abnormalities in different dimensions. At the same time, a cross - local - dimension abnormal fusion inference context is generated, which is like a logical chain showing how various abnormalities are interrelated and interact with each other, providing a clear clue for subsequent in - depth analysis of the condition.

[0034] The dynamic threshold inference sub-module is used to determine the user's personalized multi-dimensional grading warning threshold and clinical decision simulation path based on the standard cross-local dimension anomaly fusion inference context, multiple cross-local dimension anomaly fusion inference information of the patient, and the cross-local dimension anomaly fusion inference context. This sub-module works based on the standard cross-local dimension anomaly fusion inference context, the patient's own cross-local dimension anomaly fusion inference information, and the context. The standard context is a general pattern established based on a large amount of clinical data or medical knowledge, representing the reasonable association and development path between different dimension anomalies under normal circumstances. By comparing the specific situation of the patient with it, the particularity of the patient's condition can be discovered. For example, if in the standard context, an increase in the stone volume is accompanied by specific biochemical index changes and position movement patterns, and the patient's situation is different, the unique features of the patient's condition can be analyzed. Through this comparative analysis, the user's personalized multi-dimensional grading warning threshold is determined. These thresholds are formulated according to the individual situation of the patient and are used to divide the severity of the condition or the risk level. For example, based on various abnormal conditions related to the stone, it is judged which risk level the patient is in, low, medium, or high. At the same time, based on the patient's cross-local dimension anomaly fusion inference context, the clinical decision simulation path is determined. This path simulates the reasonable treatment steps and decision-making sequence for the patient's condition, providing an important reference for doctors to formulate the actual treatment plan and helping doctors provide medical services to patients more accurately.

[0035] In an alternative embodiment, the cross-local dimension anomaly fusion inference sub-module includes: The abnormal data extraction unit is used to extract the first urolithiasis diagnosis-related abnormal data from the dynamic change simulation diagram of the stone volume, and at the same time, extract the second urolithiasis diagnosis-related abnormal data from the dynamic mapping diagram of the stone position; the main task of this unit is to extract the abnormal data related to urolithiasis diagnosis from the dynamic change simulation diagram of the stone volume and the dynamic mapping diagram of the stone position respectively. In the dynamic change simulation diagram of the stone volume, it may be noted that the stone volume suddenly increases or decreases rapidly. These abnormal change data are marked as the first urolithiasis diagnosis-related abnormal data. For example, under normal circumstances, the stone volume increases relatively slowly, but within a certain period of time, the growth rate significantly accelerates, and this abnormal growth data will be extracted. At the same time, in the dynamic mapping diagram of the stone position, if it is found that the stone has an abnormal movement trajectory, such as a stone that was originally stable in a certain area of the kidney suddenly moves rapidly to the ureter, this abnormal position change data is extracted as the second urolithiasis diagnosis-related abnormal data. These abnormal data are important bases for subsequent analysis of the condition change.

[0036] A time-span division determination unit is configured to determine a local time-span division sequence based on the same-type outlier interval sequences in the first urolithiasis diagnosis-related abnormal data and the same-type outlier interval sequences in the second urolithiasis diagnosis-related abnormal data. Here, the same-type outlier interval sequences, for example, in the first urolithiasis diagnosis-related abnormal data, there are multiple cases where the stone volume suddenly increases, and the time intervals between these increases constitute a kind of same-type outlier interval sequence; in the second urolithiasis diagnosis-related abnormal data, the time intervals between similar abnormal stone movement cases also form corresponding sequences. By analyzing these two groups of same-type outlier interval sequences, a local time-span division sequence is determined. This time-span sequence can reflect the distribution law of abnormal conditions in the time dimension and provide a time division basis for subsequent synchronous analysis of abnormal data in different dimensions. For example, if it is found that the sudden increase in stone volume occurs at regular intervals and there is a certain correlation with the time interval of abnormal stone movement, by calculating and analyzing these intervals, a suitable local time-span division can be obtained to better perform corresponding analysis of abnormal data in different dimensions in terms of time.

[0037] A synchronous division unit is configured to perform synchronous division on the first urolithiasis diagnosis-related abnormal data, the second urolithiasis diagnosis-related abnormal data, and the biochemical index outlier association graph based on the local time-span division sequence to obtain multi-dimensional local abnormal data. The purpose of this step is to make the abnormal data from different dimensions (stone volume, position, and biochemical index) consistent and comparable in time. Through synchronous division, the abnormal data in different dimensions are sorted according to the same time segments to obtain multi-dimensional local abnormal data. For example, taking the determined time-span as a standard, the time periods of abnormal increase in stone volume, the time periods of abnormal movement of stone position, and the time periods of abnormal changes in biochemical indexes are correspondingly divided, so that the relationships between abnormal conditions in different dimensions can be observed and analyzed on the same time scale, providing a more orderly data basis for subsequent cross-dimensional fusion reasoning.

[0038] The cross - dimensional fusion inference unit is used to perform cross - dimensional fusion inference on multi - dimensional local abnormal data to obtain multiple cross - local - dimension abnormal fusion inference information and cross - local - dimension abnormal fusion inference context of the patient. It comprehensively considers abnormal conditions in multiple dimensions such as stone volume, location, and biochemical indicators, and explores the deep - seated connections between them. Through this fusion inference, multiple cross - local - dimension abnormal fusion inference information of the patient is obtained. These information may reveal the internal relationship between abnormal changes in stone volume, specific location changes, and related biochemical indicator changes. For example, when the stone volume rapidly increases, its location moves to a specific area, and there are abnormal fluctuations in certain biochemical indicators. The possible causal relationship or mutual influence mechanism among these three constitutes a cross - local - dimension abnormal fusion inference information. At the same time, a cross - local - dimension abnormal fusion inference context is generated to show the mutual connection path between abnormal conditions in different dimensions in a logically clear way, helping doctors comprehensively understand the development and change mechanism of the disease and providing strong support for accurate diagnosis and treatment.

[0039] In an alternative embodiment, the time - span determination unit includes: The cause - and - effect correlation coefficient acquisition subunit is used to obtain the cause - and - effect correlation coefficients of urolithiasis between each index data in the first urolithiasis diagnosis - related abnormal data and each index data in the second urolithiasis diagnosis - related abnormal data; this subunit is responsible for finding the cause - and - effect correlation coefficients of urolithiasis between the index data in the first urolithiasis diagnosis - related abnormal data (from the dynamic change simulation diagram of stone volume) and the second urolithiasis diagnosis - related abnormal data (from the dynamic mapping diagram of stone location). This means it needs to analyze the abnormal index related to stone volume and the abnormal index related to stone location to see the degree of tightness of their association in the process of causing or developing urolithiasis. Suppose the index in the first urolithiasis diagnosis - related abnormal data is the stone volume growth rate, and the index in the second urolithiasis diagnosis - related abnormal data is the residence time of the stone in a specific area. The cause - and - effect correlation coefficient acquisition subunit will determine the degree of association between these two indexes in terms of urolithiasis cause through medical knowledge, past case data, or specific algorithms, and obtain a coefficient representing the degree of tightness of their association. Such analysis is carried out for each pair of index data to obtain the corresponding cause - and - effect correlation coefficients.

[0040] The time - span sequence generation unit is used to determine the local division time - span sequence based on the cause - and - effect correlation coefficients of urolithiasis between each index data in the first urolithiasis diagnosis - related abnormal data and each index data in the second urolithiasis diagnosis - related abnormal data, the same - kind abnormal value interval sequence in the first urolithiasis diagnosis - related abnormal data, and the same - kind abnormal value interval sequence in the second urolithiasis diagnosis - related abnormal data: ; where, For locally partitioning the time-span sequence, is the total number of all index data types in the first urolithiasis diagnosis-related abnormal data, is the total number of all index data types in the second urolithiasis diagnosis-related abnormal data, is the th index data type in the first urolithiasis diagnosis-related abnormal data and the th index data type in the second urolithiasis diagnosis-related abnormal data, and the urolithiasis causative correlation coefficient between them, is the mean function, is the 1st value in the same abnormal value interval sequence of the th index data type in the first urolithiasis diagnosis-related abnormal data (i.e., representing the time interval between the first abnormal value and the second abnormal value of the corresponding index value of the th index data type in the first urolithiasis diagnosis-related abnormal data), is the 1st value in the same abnormal value interval sequence of the th index data type in the second urolithiasis diagnosis-related abnormal data (i.e., representing the time interval between the first abnormal value and the second abnormal value of the corresponding index value of the th index data type in the second urolithiasis diagnosis-related abnormal data), is the 2nd value in the same abnormal value interval sequence of the th index data type in the first urolithiasis diagnosis-related abnormal data, is the 2nd value in the same abnormal value interval sequence of the th index data type in the second urolithiasis diagnosis-related abnormal data, is the th value in the same abnormal value interval sequence of the th index data type in the first urolithiasis diagnosis-related abnormal data, is the th value in the same abnormal value interval sequence of the th index data type in the second urolithiasis diagnosis-related abnormal data, and takes a value equal to the minimum of the total number of values in the same abnormal value interval sequence of the th index data type in the first urolithiasis diagnosis-related abnormal data and the total number of values in the same abnormal value interval sequence of the th index data type in the second urolithiasis diagnosis-related abnormal data.

[0041] This time-span sequence reflects the comprehensive correlation characteristics of different abnormal indicators over time, providing an important basis for time division in subsequent synchronous analysis of abnormal data in different dimensions. For example, if the abnormal situation of rapid growth of stone volume is closely related to the abnormal situation of sudden change in stone position in time (i.e., the causal correlation coefficient is large), then when determining the local division time-span sequence, these two groups of abnormal value interval sequences will be given higher weights, enabling the time-span to better reflect the time relationship between these two abnormalities.

[0042] In an alternative embodiment, the cross-dimensional fusion reasoning unit includes: A causal correlation rule acquisition subunit for obtaining all stone causal correlation rules; these rules are derived from medical research, clinical experience, and a large number of case analyses, describing the relationships between different factors and the formation of urinary stones. For example, there may be specific causal connections between abnormal changes in certain biochemical indicators and changes in the position and size of stones, and these connections constitute the stone causal correlation rules. These rules are the basis for subsequent analysis and provide a theoretical framework for understanding the patient's abnormal data.

[0043] An adherence degree determination subunit for performing cross-dimensional combination on multi-dimensional local abnormal data based on all stone causal correlation rules to obtain multiple cross-dimensional combined abnormal data, and determining the adherence degree of each cross-dimensional combined abnormal data to the corresponding stone causal correlation rule; Suppose the three abnormal data of sudden increase in stone volume, movement of the stone position to a specific area, and increase in a certain biochemical indicator come from different dimensions respectively. Combining them together forms a cross-dimensional combined abnormal data. Then, for each cross-dimensional combined abnormal data, according to the stone causal correlation rules, judge the degree of compliance of this combination with the rules, that is, determine its adherence degree to the corresponding stone causal correlation rule. This step helps to evaluate the rationality and possibility of each cross-dimensional combined abnormal data under the known medical knowledge system, providing a quantitative basis for subsequent fusion reasoning.

[0044] A fusion reasoning subunit for obtaining multiple cross-local dimension abnormal fusion reasoning information of the patient based on all stone causal correlation rules and all cross-dimensional combined abnormal data; this step comprehensively considers the adherence degree of each cross-dimensional combined abnormal data to the corresponding rule and the potential connections between different combinations. For example, if a cross-dimensional combined abnormal data has a high adherence degree to a certain stone causal correlation rule, it indicates that this abnormal combination has a high possibility of following this rule during the formation of stones. Through comprehensive analysis of all combinations and rules, multiple cross-local dimension abnormal fusion reasoning information of the patient is obtained. These information further reveal the internal connections between abnormal conditions in different dimensions and their impacts on the formation and development of urinary stones.

[0045] An inference context generation subunit, configured to generate a cross-local-dimension abnormal fusion inference context based on all cross-dimension combination abnormal data, all corresponding calculus formation causal association rules, and corresponding compliance degrees, and in combination with all corresponding cross-local-dimension abnormal fusion inference information. This context shows, in a visual or logical manner, how abnormal conditions in different dimensions are interrelated, and how they follow or deviate from known calculus formation causal association rules. It is like a detailed map, providing doctors and researchers with a clear idea to help them understand the complexity of the patient's condition, as well as the action paths of different abnormal conditions in the process of calculus formation, thus providing strong support for formulating more accurate diagnosis and treatment plans. For example, through the inference context, it can be intuitively seen how the abnormal increase in calculus volume interacts with specific biochemical index changes and calculus position movement, ultimately leading to the development of the calculus condition.

[0046] In an alternative embodiment, the dynamic threshold inference sub-module includes: A macro context deviation analysis unit, configured to determine the abnormal fusion inference macro deviation degree based on the standard cross-local-dimension abnormal fusion inference context and the cross-local-dimension abnormal fusion inference context; the core task of this unit is to evaluate the degree of difference between the patient's condition and the standard situation. It achieves this goal by comparing the standard cross-local-dimension abnormal fusion inference context with the patient's own cross-local-dimension abnormal fusion inference context. The standard cross-local-dimension abnormal fusion inference context is summarized based on a large number of normal or common cases, representing the association and development patterns of abnormal conditions in different dimensions under general cognition. The patient's cross-local-dimension abnormal fusion inference context is inferred based on the multi-dimensional abnormal information such as the specific calculus volume, position, and biochemical indexes of this patient. By carefully comparing these two contexts, finding the deviation between the patient's abnormal fusion inference pattern and the standard pattern, and then determining the abnormal fusion inference macro deviation degree. For example, if in the standard context, the increase in calculus volume is usually accompanied by specific position movement and biochemical index change order, and the patient's situation shows different development paths in some links, the macro context deviation analysis unit will quantify this difference and give a numerical value representing the degree of deviation. This deviation degree reflects the particularity of the patient's condition relative to the standard situation, providing an important reference for subsequent personalized warning threshold determination and clinical decision-making. The abnormal fusion inference macro deviation degree reflects the degree of deviation of the patient's condition from the standard situation.

[0047] The deviation degree between the standard cross-local-dimension abnormal fusion inference context and the patient's cross-local-dimension abnormal fusion inference context can be calculated through the following steps: Extract the key features in two contexts. These features may include the order, frequency, severity, etc. of abnormalities in dimensions such as stone volume, location, biochemical indicators, etc. For example, in the standard context, a specific biochemical indicator changes some time after the stone volume increases; while in the patient context, the time interval or the order of changes between the two may be different. Match the extracted features according to dimensions and chronological order for subsequent comparative analysis.

[0048] For the features after matching, calculate the quantitative differences in the abnormal conditions of each dimension. For example, for the stone volume dimension, calculate the difference in the volume growth rate between the standard context and the patient context; for the biochemical indicator dimension, calculate the difference in the degree to which the specific indicator value deviates from the standard range, etc.

[0049] Quantify the differences in the order and frequency of the appearance of abnormalities as well. For example, an abnormality appears once every 10 days in the standard context and once every 5 days in the patient context. Quantify this difference by calculating the frequency multiple, etc.

[0050] Assign weights to the feature differences in different dimensions, which are determined based on medical knowledge and clinical experience to determine the importance of each dimension to the impact of the disease condition. For example, changes in stone volume may have a greater impact on the disease condition and are assigned a higher weight; while changes in some minor biochemical indicators have a relatively lower weight.

[0051] Based on the quantitative values and weights of the feature differences in each dimension, calculate a comprehensive value through mathematical methods such as weighted summation. This value is the macro deviation degree of abnormal fusion reasoning, which reflects the overall deviation degree between the two contexts.

[0052] The grading warning threshold determination unit is used to determine the user's personalized multi-dimensional grading warning threshold based on all the cross-local dimension abnormal fusion reasoning information and the macro deviation degree of abnormal fusion reasoning of the patient; considering these two aspects of factors comprehensively, this unit will set a personalized multi-dimensional grading warning threshold for the patient. For example, if the cross-local dimension abnormal fusion reasoning information of the patient shows that various abnormalities related to stones are relatively serious, and the macro deviation degree of abnormal fusion reasoning indicates that the patient's condition deviates greatly from the standard situation, it may mean that the patient's condition is relatively special and serious. Then the grading warning threshold determination unit will set a relatively low warning threshold accordingly to more timely warn the patient's condition. These grading warning thresholds can more accurately divide the severity and risk level of the disease condition according to the actual situation of the patient individual, and provide more targeted warning prompts for the patient.

[0053] The clinical decision-making path simulation unit is used to determine the user's clinical decision simulation path based on the cross-local dimension anomaly fusion inference context. This unit determines the user's clinical decision simulation path based on the cross-local dimension anomaly fusion inference context. The cross-local dimension anomaly fusion inference context clearly shows the logical relationship and development path between different dimension anomalies in the patient's calculus condition, reflecting the internal mechanism of the condition. The clinical decision-making path simulation unit simulates the reasonable clinical decision steps and sequence for the patient's condition according to this context. For example, if the inference context shows that the increase in calculus volume is closely related to specific biochemical index anomalies, and this anomaly combination may lead to a higher risk of further calculus development, then the clinical decision-making path simulation unit may recommend intervening in the treatment of this biochemical index first, and then adjusting the subsequent treatment plan according to the change in calculus volume. This simulation path provides an important reference framework for doctors to make actual clinical treatment decisions, helping doctors formulate more scientific and personalized treatment plans according to the specific conditions of patients.

[0054] In an alternative embodiment, the grading warning threshold determination unit includes: The basic threshold determination subunit is used to determine the multi-dimensional grading warning basic threshold based on all the cross-local dimension anomaly fusion inference information of the patient; the cross-local dimension anomaly fusion inference information covers the comprehensive analysis results of the interrelationships of multiple dimension anomalies such as calculus volume, position, and biochemical indexes. Suppose this information indicates that the patient's calculus volume is growing rapidly, accompanied by movement at a specific position and significant changes in certain biochemical indexes. The basic threshold determination subunit will initially set a multi-dimensional grading warning basic threshold based on factors such as the severity, occurrence frequency, and mutual influence relationship of these anomalies. For example, if the calculus volume increases rapidly and the biochemical indexes fluctuate frequently, the basic threshold may be relatively low, meaning that a lower degree of anomaly change may trigger a higher-level warning, thereby reflecting a relatively serious condition of the disease. This basic threshold provides an initial framework for subsequent precise adjustment and is the initial warning limit based on the patient's own anomalies.

[0055] A grading threshold determination subunit is used to correct the multi-dimensional grading warning basic threshold based on the macro deviation degree of abnormal fusion reasoning, and obtain the user's personalized multi-dimensional grading warning threshold. This subunit corrects the multi-dimensional grading warning basic threshold based on the macro deviation degree of abnormal fusion reasoning, so as to obtain the user's personalized multi-dimensional grading warning threshold. The macro deviation degree of abnormal fusion reasoning reflects the deviation degree between the patient's abnormal disease fusion pattern and the standard pattern. If the macro deviation degree of abnormal fusion reasoning is large, it indicates that the patient's disease development pattern is significantly different from the common standard pattern. At this time, the grading threshold determination subunit will make corresponding adjustments to the basic threshold according to this large deviation. For example, the warning threshold may be further reduced to make the warning more sensitive, because the special disease development of the patient may require more timely attention and intervention. On the contrary, if the deviation degree is small, the basic threshold may be appropriately maintained to make the warning more in line with the normal situation. Through this deviation-based correction, the finally determined personalized multi-dimensional grading warning threshold can more accurately reflect the characteristics and risk degree of the patient's individual condition, and provide a more targeted warning standard for clinical practice.

[0056] In an alternative embodiment, the warning and reporting integration module includes: A warning level diagnosis sub-module is used to determine the user's current warning level based on the latest relevant indicators of the user's stone disease onset and the user's personalized multi-dimensional grading warning threshold, and issue a warning signal based on the current warning level; this sub-module compares the latest relevant indicators of the user's stone disease onset with the personalized multi-dimensional grading warning threshold obtained by the dynamic threshold reasoning module. The latest relevant indicators cover real-time data such as the location, size, and morphological changes of the stone, as well as biochemical indicators related to the stone disease onset in the blood and urine. By comparing these indicators with the corresponding warning thresholds, the warning level at which the user currently is located is judged. For example, if the volume of the user's stone has increased beyond the threshold of the corresponding level, and some key biochemical indicators are also in the abnormal range, it may be determined as a higher warning level. After determining the warning level, a corresponding warning signal is issued according to this level. The warning signal can be an intuitive visual prompt (such as a color mark in the electronic medical record system), a sound reminder (a mobile notification for medical staff), etc. The purpose is to timely inform the patient and medical staff of the severity of the current condition so that corresponding measures can be taken.

[0057] An intervention recommendation generation sub-module for determining the subsequent intervention priority recommendations for the user based on the clinical decision-making simulation path; the clinical decision-making simulation path is formulated according to the abnormal fusion inference context across local dimensions of the patient and includes a series of reasonable diagnosis and treatment steps for the patient's condition. The sub-module will evaluate the urgency and importance of each diagnosis and treatment step. For example, if the clinical decision-making simulation path shows that a stone is about to block the ureter, then the relevant interventions to take measures to relieve the blockage (such as surgery or medical lithotripsy) will be given a higher priority; while for some suggestions to improve living habits to prevent stone recurrence, the priority may be relatively low. In this way, a clear order of subsequent intervention guidance is provided for medical staff and patients.

[0058] A report integration sub-module for generating various visualization curve data based on the comprehensive examination visualization results and integrating the user's current warning level, various visualization curve data, and the user's subsequent intervention priority recommendations to generate a comprehensive diagnosis and treatment report for urinary stones. Based on the comprehensive examination visualization results provided by the data visualization module, such as the simulation diagram of the dynamic change of stone volume, the association map of abnormal biochemical index values, the dynamic mapping diagram of stone position, etc., various visualization curve data are generated. These curves can more intuitively display the changing trend of the condition over time, such as the growth curve of stone volume over time, the fluctuation curve of specific biochemical indicators, etc. The comprehensive diagnosis and treatment report provides comprehensive and detailed condition information for patients and medical staff, including both the severity and changing trend of the current condition, and targeted guidance suggestions for subsequent interventions, which helps to formulate a scientific and reasonable treatment plan.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A urinary calculus examination image recognition, data visualization analysis and early warning reminder system, characterized in that including: An inspection data parsing module, configured to extract stone disease-related sequence data from the synchronous sequence data of the user's urinary calculus inspection images and blood and urine inspection reports, including the position distribution sequence features, morphological sequence features of the urinary calculus, and biochemical sequence indicators related to the onset of the stone in a time series alignment; A data visualization module, configured to convert the stone disease-related sequence data into a simulated graph of the dynamic change of the stone volume, an association map of abnormal values of biochemical indicators, and a dynamic mapping map of the stone position, as the comprehensive inspection visualization result for the user to query; A dynamic threshold inference module, configured to perform spatio-temporal alignment and cross-local dimension abnormal fusion inference on the simulated graph of the dynamic change of the stone volume, the association map of abnormal values of biochemical indicators, and the dynamic mapping map of the stone position, to obtain the user's personalized multi-dimensional grading warning threshold and the clinical decision simulation path; A warning and report integration module, configured to determine the user's current warning level based on the latest relevant indicators of the onset of the stone of the user and the user's personalized multi-dimensional grading warning threshold, and generate a comprehensive diagnosis and treatment report for urinary calculus in combination with the visualization curve data and the clinical decision simulation path generated based on the comprehensive inspection visualization result.

2. The urinary calculus examination image recognition, data visualization analysis and early warning reminder system according to claim 1, wherein The inspection data parsing module includes: An image recognition sub-module, configured to extract the urinary calculus position data and morphological data of each urinary calculus inspection image in the user's synchronous sequence data based on all the local urinary calculus images in each urinary calculus inspection image of the user's synchronous sequence data; A data serialization sub-module, configured to generate the position distribution sequence features and morphological sequence features of the urinary calculus based on the urinary calculus position data and morphological data of all the urinary calculus inspection images in the user's synchronous sequence data; A report serialization analysis sub-module, configured to generate biochemical sequence indicators related to the onset of the stone based on the biochemical indicators related to the onset of the stone in all the blood and urine inspection reports in the user's synchronous sequence data; A time series alignment sub-module, configured to perform time series alignment on the position distribution sequence features, morphological sequence features, and biochemical sequence indicators related to the onset of the stone, to obtain the stone disease-related sequence data.

3. The urinary calculus examination image recognition, data visualization analysis and early warning reminder system according to claim 1, characterized in that The data visualization module includes: A urinary calculus dynamic simulation sub-module, configured to generate a simulated graph of the dynamic change of the stone volume based on the morphological sequence features of the urinary calculus in the stone disease-related sequence data, and at the same time, generate a dynamic mapping map of the stone position based on the position distribution sequence features of the urinary calculus in the stone disease-related sequence data; A first abnormal index extraction sub-module, configured to extract a first abnormal biochemical index and a first sequential abnormal index from the position distribution sequence features and morphological sequence features of the urinary calculus; A second abnormal index extraction sub-module, configured to extract a second abnormal biochemical index and a second sequential abnormal index from the biochemical sequence indicators related to the onset of the stone; An abnormal index mapping sub-module, configured to generate an association map of abnormal values of biochemical indicators based on the first abnormal biochemical index, the first sequential abnormal index, the second abnormal biochemical index, and the second sequential abnormal index, as the comprehensive inspection visualization result for the user to query.

4. The urinary calculus examination image recognition, data visualization analysis and early warning reminder system according to claim 1, characterized in that, The dynamic threshold inference module includes: The cross-local dimension abnormal fusion reasoning sub-module is used to perform spatio-temporal alignment and cross-local dimension abnormal fusion reasoning on the simulated diagram of the dynamic change of the stone volume, the associated map of abnormal biochemical index values, and the dynamic mapping diagram of the stone position, so as to obtain multiple cross-local dimension abnormal fusion reasoning information and cross-local dimension abnormal fusion reasoning context of the patient; The dynamic threshold reasoning sub-module is used to determine the personalized multi-dimensional grading warning threshold and the clinical decision simulation path of the user based on the standard cross-local dimension abnormal fusion reasoning context and the multiple cross-local dimension abnormal fusion reasoning information and cross-local dimension abnormal fusion reasoning context of the patient.

5. The urinary calculus examination image recognition, data visualization analysis and warning reminder system according to claim 4, characterized in that The cross-local dimension abnormal fusion reasoning sub-module includes: The abnormal data extraction unit is used to extract the first urolithiasis diagnosis-related abnormal data from the simulated diagram of the dynamic change of the stone volume, and at the same time, extract the second urolithiasis diagnosis-related abnormal data from the dynamic mapping diagram of the stone position; The time span division determination unit is used to determine the local division time span sequence based on the same abnormal value spacing sequence in the first urolithiasis diagnosis-related abnormal data and the same abnormal value spacing sequence in the second urolithiasis diagnosis-related abnormal data; The synchronous division unit is used to synchronously divide the first urolithiasis diagnosis-related abnormal data, the second urolithiasis diagnosis-related abnormal data, and the associated map of abnormal biochemical index values based on the local division time span sequence to obtain multi-dimensional local abnormal data; The cross-dimension fusion reasoning unit is used to perform cross-dimension fusion reasoning on the multi-dimensional local abnormal data to obtain multiple cross-local dimension abnormal fusion reasoning information and cross-local dimension abnormal fusion reasoning context of the patient.

6. The urinary calculus examination image recognition, data visualization analysis and early warning reminder system according to claim 5, characterized in that, The time span division determination unit includes: The cause correlation coefficient acquisition sub-unit is used to acquire the urolithiasis cause correlation coefficient between each index data in the first urolithiasis diagnosis-related abnormal data and each index data in the second urolithiasis diagnosis-related abnormal data; The time span sequence generation unit is used to determine the local division time span sequence based on the urolithiasis cause correlation coefficient between each index data in the first urolithiasis diagnosis-related abnormal data and each index data in the second urolithiasis diagnosis-related abnormal data, the same abnormal value spacing sequence in the first urolithiasis diagnosis-related abnormal data, and the same abnormal value spacing sequence in the second urolithiasis diagnosis-related abnormal data: ； Wherein, is the local partition time-span sequence, is the total number of all index data in the first urolithiasis diagnosis-related abnormal data, is the total number of all index data in the second urolithiasis diagnosis-related abnormal data, is the th index data in the first urolithiasis diagnosis-related abnormal data and the th index data in the second urolithiasis diagnosis-related abnormal data, and the urolithiasis cause correlation coefficient therebetween, is the averaging function, is the first value in the same-kind abnormal value interval sequence of the th index data in the first urolithiasis diagnosis-related abnormal data, is the first value in the same-kind abnormal value interval sequence of the th index data in the second urolithiasis diagnosis-related abnormal data, is the second value in the same-kind abnormal value interval sequence of the th index data in the first urolithiasis diagnosis-related abnormal data, is the second value in the same-kind abnormal value interval sequence of the th index data in the second urolithiasis diagnosis-related abnormal data, is the th value in the same-kind abnormal value interval sequence of the th index data in the first urolithiasis diagnosis-related abnormal data, is the th value in the same-kind abnormal value interval sequence of the th index data in the second urolithiasis diagnosis-related abnormal data, and takes a value equal to the minimum value between the total number of values in the same-kind abnormal value interval sequence of the th index data in the first urolithiasis diagnosis-related abnormal data and the total number of values in the same-kind abnormal value interval sequence of the th index data in the second urolithiasis diagnosis-related abnormal data.

7. The urinary calculus examination image recognition, data visualization analysis and early warning reminder system according to claim 5, characterized in that The cross-dimension fusion reasoning unit includes: The cause association rule acquisition sub-unit is used to acquire all the stone cause association rules; The compliance degree determination sub-unit is used to perform cross-dimension combination on the multi-dimensional local abnormal data based on all the stone cause association rules to obtain multiple cross-dimension combination abnormal data, and determine the compliance degree of each cross-dimension combination abnormal data with the corresponding stone cause association rule; The fusion reasoning sub-unit is used to obtain multiple cross-local dimension abnormal fusion reasoning information of the patient based on all the stone cause association rules and all the cross-dimension combination abnormal data; The inference context generation subunit is used to generate a cross-local dimension anomaly fusion inference context based on all cross-dimension combination anomaly data, all corresponding calculus formation association rules, the corresponding compliance levels, and in combination with all corresponding cross-local dimension anomaly fusion inference information.

8. The urinary calculus examination image recognition, data visualization analysis and early warning reminder system according to claim 4, characterized in that, The dynamic threshold inference sub-module includes: The macro context deviation analysis unit is used to determine the anomaly fusion inference macro deviation degree based on the standard cross-local dimension anomaly fusion inference context and the cross-local dimension anomaly fusion inference context; The hierarchical warning threshold determination unit is used to determine the user's personalized multi-dimensional hierarchical warning threshold based on all cross-local dimension anomaly fusion inference information of the patient and the anomaly fusion inference macro deviation degree; The clinical decision-making path simulation unit is used to determine the user's clinical decision simulation path based on the cross-local dimension anomaly fusion inference context.

9. The urinary calculus examination image recognition, data visualization analysis and early warning reminder system according to claim 8, characterized in that, The hierarchical warning threshold determination unit includes: The basic threshold determination subunit is used to determine the multi-dimensional hierarchical warning basic threshold based on all cross-local dimension anomaly fusion inference information of the patient; The hierarchical threshold determination subunit is used to correct the multi-dimensional hierarchical warning basic threshold based on the anomaly fusion inference macro deviation degree to obtain the user's personalized multi-dimensional hierarchical warning threshold.

10. The urinary calculus examination image recognition, data visualization analysis and early warning reminder system according to claim 1, characterized in that, The warning and report integration module includes: The warning level diagnosis sub-module is used to determine the user's current warning level based on the latest relevant indicators of the user's calculus onset and the user's personalized multi-dimensional hierarchical warning threshold, and issue a warning signal based on the current warning level; The intervention suggestion generation sub-module is used to determine the user's subsequent intervention priority suggestion based on the clinical decision simulation path; The report integration sub-module is used to generate various visualization curve data based on the comprehensive examination visualization results, and integrate the user's current warning level, various visualization curve data, and the user's subsequent intervention priority suggestion to generate a comprehensive diagnosis and treatment report for urinary calculi.

Images