Kidney aging clock evaluation method based on kidney pathology and artificial intelligence

Abstract

The invention belongs to the technical field of kidney aging assessment, and particularly relates to a kidney aging clock assessment method based on kidney pathology and artificial intelligence. According to the kidney aging evaluation method, the kidney aging degree can be evaluated more accurately by analyzing the pathological characteristics related to kidney aging and calculating the correlation weight, the aging clock score is generated, the kidney aging process is quantified, and the kidney aging evaluation accuracy is improved by monitoring the aging clock score of the kidney in real time and optimizing the evaluation period length according to the allowable deviation score. The kidney senescence state can be found in time, in the normal senescence state, the evaluation period can be adjusted in time, the kidney senescence evaluation efficiency can be improved, in the abnormal senescence state, a corresponding response mechanism can be triggered, it is ensured that measures can be taken rapidly in the abnormal senescence state, and the kidney senescence evaluation efficiency is improved. Therefore, corresponding data support can be provided for clinical diagnosis and treatment.

Description

Technical Field

[0001] The present invention belongs to the technical field of kidney aging assessment, and specifically relates to a kidney aging clock assessment method based on kidney pathology and artificial intelligence. Background Art

[0002] Computer models that measure biological age and aging rate are called aging clocks. Renal aging is a gradual process of degenerative changes in tissue structure and physiological function, characterized by decreased glomerular filtration rate, weakened tubular function, decreased number of nephrons, reduced microcirculation, decreased immune function, and weakened antioxidant capacity. The measurement of the renal aging clock is of great significance for understanding changes in individual renal function and health status, and is useful for early detection of chronic kidney disease, formulation of personalized treatment plans, assessment of renal health risks, timely formulation of preventive measures, monitoring of treatment effects, and research on the mechanism of renal aging. In general, measuring the renal aging clock helps to have a more comprehensive understanding of renal health and function, thereby better preventing, diagnosing and treating kidney-related diseases.

[0003] In the existing technology, there are some kidney aging assessment methods based on biomarkers and clinical data, but these methods often have problems such as insufficient accuracy and complex operation. In addition, due to individual differences and the complexity of kidney function, it is difficult to accurately reflect the actual situation of kidney aging, resulting in the inability to timely detect and intervene in kidney disease. Based on this, this program proposes a kidney aging clock assessment method based on kidney pathology and artificial intelligence to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a renal aging clock assessment method based on renal pathology and artificial intelligence, which can monitor the degree of renal aging in real time and optimize the length of the assessment cycle, thereby improving the accuracy and timeliness of renal aging assessment.

[0005] The technical solution adopted by the present invention is as follows: The renal aging clock assessment method based on renal pathology and artificial intelligence includes: Preprocessing the acquired pathological characteristic information, and classifying the preprocessed pathological characteristic information to obtain multiple pathological special subsets; Extracting features from the pathological feature information in each of the pathological special subsets to obtain pathological features related to kidney aging; Performing correlation analysis on the pathological features and the kidney aging clock to obtain the correlation weight between each pathological feature and the kidney aging clock; According to the correlation weights of each of the pathological characteristics, the degree of kidney aging is evaluated and analyzed, and multiple aging clock scores are generated simultaneously; Identifying the renal aging state according to the aging clock score, wherein the renal aging state includes a normal aging state and an abnormal aging state; In the normal aging state, the aging clock score of the kidney continues to be monitored, and the allowable deviation score is synchronously output, and then the cycle length of the periodic assessment of the degree of kidney aging is optimized according to the allowable deviation score; In the abnormal aging state, the alarm mechanism is immediately triggered and an alarm signal is sent out synchronously.

[0006] In a preferred embodiment, the step of preprocessing the acquired pathological characteristic information and classifying the preprocessed pathological characteristic information to obtain a plurality of pathological special subsets includes: Acquiring the pathological characteristic information, wherein the pathological characteristic information includes kidney tissue slice images, biochemical index data, and gene expression data; Preprocessing the pathological characteristic information, wherein the preprocessing includes image denoising, data normalization, and missing value processing; The preprocessed pathological feature information is classified according to the corresponding pathological specialties to form multiple pathological specialty subsets.

[0007] In a preferred embodiment, the step of extracting the pathological characteristic information in each of the pathological special subsets to obtain the pathological characteristics associated with kidney aging includes: Obtaining pathological feature information in each of the pathological specialty subsets; To obtain baseline characteristics associated with kidney aging; The baseline feature is feature matched with the pathological feature information in the pathological special subset, and feature information related to kidney aging is extracted from the pathological special subset and recorded as a pathological feature.

[0008] In a preferred embodiment, the step of performing correlation analysis on the pathological features and the kidney aging clock to obtain the correlation weight between each pathological feature and the kidney aging clock includes: Obtaining all the pathological features and the continuous time periods in which each of the pathological features undergoes unique changes, and recording them as association analysis time periods, wherein each of the pathological features corresponds to a number of association analysis time periods; Marking the pathological features that have uniquely changed in each of the association analysis periods as variable features, and marking the pathological features that have not changed as quantitative features; Obtaining the difference in kidney aging between the start node and the end node of the association analysis period, and recording it as an association condition parameter; A weight allocation function is obtained, and the association condition parameter is input into the weight allocation function, and an output result of the weight allocation function is recorded as an association weight.

[0009] In a preferred embodiment, the step of evaluating and analyzing the degree of kidney aging based on the associated weights of each of the pathological features and synchronously generating multiple aging clock scores includes: Obtaining the associated weight of each of the pathological features and the historical change amount of each of the pathological features; Taking an average of the historical changes of each of the pathological characteristics to obtain an average change parameter; An evaluation function is obtained, and the association weight and the average change parameter of the pathological feature are input into the evaluation function, and the output result of the evaluation function is recorded as an aging clock score.

[0010] In a preferred embodiment, the step of identifying the kidney aging state based on the aging clock score comprises: Acquire an aging clock score of the kidney and a state evaluation threshold corresponding to the aging clock score; comparing the state evaluation threshold with the aging clock score; When the aging clock score is greater than the state evaluation threshold, it indicates that the kidney aging is abnormal, and the kidney aging state is recorded as an abnormal aging state; When the aging clock score is less than or equal to the state evaluation threshold, it indicates that kidney aging is normal, and the kidney aging state is recorded as a normal aging state.

[0011] In a preferred embodiment, the step of optimizing the cycle length of the periodic assessment of the degree of renal aging according to the allowable deviation score comprises: Taking the current node as the reference point, reverse offset processing is performed, and the monitoring period is constructed based on the reference point and the offset point after reverse offset; Setting a plurality of evaluation nodes within the monitoring period, and outputting the allowable deviation score under each of the evaluation nodes in real time; Obtaining a first condition function, inputting the allowable deviation score into the first condition function, and calibrating an output result of the first condition function as an optimization condition parameter; The allowable duration of normal kidney aging is calculated based on the optimized condition parameters, and the period length of the periodic assessment of the degree of kidney aging is determined based on the allowable duration.

[0012] In a preferred embodiment, the steps of calculating the allowable duration of normal kidney aging according to the optimized condition parameters, and determining the cycle length of the periodic assessment of the degree of kidney aging according to the allowable duration, include: Obtaining the optimization condition parameters according to a preset allowable deviation threshold; Obtaining a second condition function, and inputting the optimization condition parameter and the allowable deviation threshold into the second condition function, and marking the output result of the second condition function as the allowable duration; Obtaining a standard duration, and comparing the standard duration with an allowable duration; When the allowable duration is less than or equal to the standard duration, the reference point is offset according to the allowable duration to obtain the allowable duration period, and then the end node of the allowable duration period is reversely offset to obtain the risk node, and the time length between the risk node and the reference point is recorded as the period length of the periodic assessment of the degree of renal aging; When the allowable duration is greater than the standard duration, the standard duration is directly recorded as the cycle length for the periodic assessment of the degree of kidney aging.

[0013] The present invention also provides a kidney aging clock evaluation system based on kidney pathology and artificial intelligence, using the above-mentioned kidney aging clock evaluation method based on kidney pathology and artificial intelligence, including: An information classification module, wherein the information classification module is used to preprocess the acquired pathological characteristic information and classify the preprocessed pathological characteristic information to obtain a plurality of pathological special subsets; A feature extraction module, the feature extraction module is used to extract the pathological feature information in each of the pathological special subsets to obtain pathological features related to kidney aging; An association analysis module, wherein the association analysis module is used to perform association analysis on the pathological features and the kidney aging clock to obtain an association weight between each pathological feature and the kidney aging clock; An aging assessment module, which is used to assess and analyze the degree of kidney aging based on the associated weights of each of the pathological characteristics, and to synchronously generate multiple aging clock scores; A state recording module, the state recording module is used to identify the kidney aging state according to the aging clock score, wherein the kidney aging state includes a normal aging state and an abnormal aging state; A first response module, the first response module is used to continue to monitor the aging clock score of the kidney in the normal aging state, and synchronously output the allowable deviation score, and then optimize the cycle length of the periodic evaluation of the degree of kidney aging according to the allowable deviation score; The second response module is used to immediately trigger an alarm mechanism and synchronously send out an alarm signal in the abnormal aging state.

[0014] And, an electronic device, the electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned renal aging clock assessment method based on renal pathology and artificial intelligence.

[0015] The technical effects achieved by the present invention are: The present invention can more accurately evaluate the degree of kidney aging and generate an aging clock score by analyzing the pathological characteristics related to kidney aging and calculating the associated weights, thereby quantifying the progress of kidney aging. By real-time monitoring of the kidney aging clock score and optimizing the evaluation cycle length according to the allowable deviation score, the present invention can timely detect the kidney aging state, and in the normal aging state, can timely adjust the evaluation cycle to improve the evaluation efficiency of kidney aging. In the abnormal aging state, it can trigger the corresponding response mechanism to ensure that measures can be taken quickly in the abnormal aging state, thereby providing corresponding data support for clinical diagnosis and treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic flow chart of the method of the present invention; Figure 2 It is a schematic diagram of the system module of the present invention; Figure 3 It is a structural diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0020] See also Figure 1 As shown, the present invention provides a method for evaluating the renal aging clock based on renal pathology and artificial intelligence, comprising: S1, preprocessing the acquired pathological characteristic information, and classifying the preprocessed pathological characteristic information to obtain multiple pathological special subsets; S2, extracting the pathological characteristic information in each pathological special subset to obtain the pathological characteristics related to kidney aging; S3, performing correlation analysis between pathological features and the renal aging clock, and obtaining correlation weights between each pathological feature and the renal aging clock; S4. Evaluate and analyze the degree of kidney aging based on the correlation weights of various pathological features, and simultaneously generate multiple aging clock scores; S5. identifying the renal aging state according to the aging clock score, wherein the renal aging state includes a normal aging state and an abnormal aging state; S6. Under normal aging conditions, continue to monitor the aging clock score of the kidney and synchronously output the allowable deviation score, and then optimize the cycle length of the periodic assessment of the degree of kidney aging according to the allowable deviation score; S7. Under abnormal aging conditions, the alarm mechanism is immediately triggered and an alarm signal is sent out simultaneously.

[0021] As described in the above steps S1-S7, kidney aging is a gradual process of degenerative changes in tissue structure and physiological function, and is closely related to a variety of pathological factors. Accurate assessment of the degree of kidney aging can provide strong support for clinical diagnosis and treatment. In this embodiment, the collected kidney pathology feature information is first preprocessed to ensure the quality and availability of the kidney pathology feature information. The preprocessing steps include data cleaning, standardization and normalization to eliminate noise and inconsistency. After the preprocessing is completed, the kidney pathology feature information will be classified and processed to form multiple pathology feature subsets with specific themes. Then, the feature information in each pathology special subset is extracted accordingly to identify the pathology features closely related to the kidney aging process, and then the pathology features are compared with the kidney aging clock. Association analysis calculates the association weights between each pathological feature and the kidney aging clock to reflect the importance of different pathological features in the kidney aging process. Based on the association weights of the pathological features, the degree of kidney aging is comprehensively evaluated and analyzed to obtain the kidney aging clock score, which can quantitatively reflect the kidney aging state. There are two types of kidney aging states: normal aging state and abnormal aging state. In the normal aging state, the kidney aging clock score will continue to be monitored, and the allowable deviation score will be output synchronously. According to the allowable deviation score, the cycle length of the periodic evaluation of the degree of kidney aging can be optimized to achieve more efficient monitoring. In the abnormal aging state, the alarm mechanism will be triggered immediately and an alarm signal will be issued synchronously, which can promptly remind medical personnel to take appropriate intervention measures to prevent further deterioration of kidney function.

[0022] In a preferred embodiment, the steps of preprocessing the acquired pathological characteristic information and classifying the preprocessed pathological characteristic information to obtain a plurality of pathological special subsets include: S101, obtaining pathological characteristic information, where the pathological characteristic information includes kidney tissue slice images, biochemical index data, and gene expression data; S102, preprocessing the pathological characteristic information, the preprocessing including image denoising, data normalization and missing value processing; S103, classifying the preprocessed pathological feature information according to corresponding pathological specialties to form a plurality of pathological specialty subsets.

[0023] As described in the above steps S101-S103, in the process of processing pathological characteristic information, the acquired data first needs to be preprocessed accordingly to ensure the quality and availability of the data, including detailed analysis and processing of various types of pathological characteristic information so that subsequent classification processing can proceed smoothly. Specifically, the process of acquiring pathological characteristic information involves a variety of different types of data, such as kidney tissue section images, biochemical indicator data, and gene expression data, etc. Each of these data has different characteristics and formats, so they need to be processed separately. During preprocessing, for image data, denoising processing is required to remove noise and interference in the image to ensure the quality and clarity of the image. Secondly, for numerical data, such as biochemical indicator data and gene expression data, data normalization processing is required. , scale the data to a uniform range to facilitate subsequent analysis and comparison. In addition, for missing values ​​in the data, appropriate processing is required, such as filling or processing these missing values ​​through interpolation, deletion or estimation, so as to ensure the integrity and accuracy of the data. After the pathological characteristic information is preprocessed, it is necessary to classify the preprocessed pathological characteristic information according to the corresponding pathological specialties. The purpose is to classify different types of pathological characteristic information into different categories to form multiple pathological specialty subsets. Each subset contains characteristic information related to a specific pathological specialty, such as a specific type of kidney disease, a specific category of biochemical indicators, or a specific functional area of ​​gene expression, such as glomerular lesion subsets, tubulointerstitial lesion subsets, vascular lesion subsets, etc., so as to better serve pathological diagnosis and research.

[0024] In a preferred embodiment, the step of extracting the pathological characteristic information in each pathological special subset to obtain the pathological characteristics related to kidney aging includes: S201, obtaining pathological characteristic information in each pathological special subset; S202, obtaining baseline characteristics associated with kidney aging; S203, feature matching is performed between the baseline feature and the pathological feature information in the pathological special subset, feature information related to kidney aging is extracted from the pathological special subset, and recorded as the pathological feature.

[0025] As described in the above steps S201-S203, in order to conduct in-depth research on the pathological features related to kidney aging, it is necessary to perform corresponding feature extraction on the pathological feature information in each pathological special subset. First, the pathological feature information in each pathological special subset needs to be obtained. Secondly, the baseline features related to kidney aging need to be obtained. The baseline features are standard indicators used for comparison and reference, that is, the standards for measuring and evaluating the correlation between pathological features and kidney aging. Finally, the baseline features are feature matched with the pathological feature information in the pathological special subset. In this way, the feature information related to kidney aging can be extracted from the pathological special subset. At the same time, these feature information will be recorded as pathological features to provide corresponding pre-data support for subsequent analysis.

[0026] In a preferred embodiment, the step of performing correlation analysis on the pathological features and the kidney aging clock to obtain the correlation weight between each pathological feature and the kidney aging clock includes: S301, obtaining all pathological features and continuous time periods in which each pathological feature undergoes unique changes, and recording them as association analysis time periods, wherein each pathological feature corresponds to a number of association analysis time periods; S302, marking the pathological features that have uniquely changed in each association analysis period as variable features, and marking the pathological features that have not changed as quantitative features; S303, obtaining the difference in kidney aging between the start node and the end node of the association analysis period, and recording it as an association condition parameter; S304: Obtain a weight distribution function, input the associated condition parameter into the weight distribution function, and record the output result of the weight distribution function as the associated weight.

[0027] As described in the above steps S301-S304, when determining the association weight between each pathological feature and the kidney aging clock, it is first necessary to collect relevant pathological features. In order to determine the impact of each pathological feature on kidney aging, after the pathological feature collection is completed, the continuous time period in which each pathological feature undergoes a unique change will be synchronously located. This embodiment calibrates it as an association analysis period, that is, within the association analysis period, only one pathological feature changes, and the other pathological features do not change. For the only pathological feature that has changed, it will be calibrated as a variable feature, and correspondingly, the remaining pathological features that have not changed will be calibrated as quantitative features. In this way, each pathological feature can be calibrated one by one, and then the difference in kidney aging at the start node and the end node of each association analysis period needs to be obtained. The difference in kidney aging reflects the degree of kidney aging affected by the variable feature during the association analysis period. At the same time, the difference in kidney aging will be recorded as an association condition parameter, and finally a weight allocation function is introduced to allocate weights to the association condition parameters under each pathological feature, wherein the expression of the weight allocation function is: , where represents the association weight, The association condition parameter, n, represents the number of pathological features. By inputting the association condition parameter into the weight distribution function, the association weight between each pathological feature and the kidney aging clock can be calculated, providing corresponding data support for the subsequent evaluation of the kidney aging status.

[0028] In a preferred embodiment, the steps of evaluating and analyzing the degree of kidney aging based on the associated weights of various pathological features and synchronously generating multiple aging clock scores include: S401, obtaining the association weight of each pathological feature and the historical change amount of each pathological feature; S402, taking an average value of the historical changes of each pathological feature to obtain an average change parameter; S403: Obtain an evaluation function, input the association weight and average change parameter of the pathological feature into the evaluation function, and record the output result of the evaluation function as an aging clock score.

[0029] As described in the above steps S401-S403, after the correlation weights of various pathological features are output, it is first necessary to obtain the correlation weights of various pathological features. The correlation weights reflect the importance of different pathological features in the process of kidney aging. At the same time, it is also necessary to collect the historical changes of various pathological features and calculate the average value of the historical changes of various pathological features to obtain the average change parameter, so as to understand the average change of the pathological features in the historical time period. Then, an evaluation function is introduced, and the correlation weights of the pathological features and the average change parameters are combined and calculated according to the evaluation function, so as to preliminarily determine the kidney aging clock score, wherein the expression of the evaluation function is: , where represents the aging clock score, m represents the number of pathological features, The average change parameters of each pathological feature are represented. Based on the above formula, the aging clock score for evaluating the degree of kidney aging can be output.

[0030] In a preferred embodiment, the step of identifying the kidney aging state according to the aging clock score comprises: S501, obtaining a kidney aging clock score and a state evaluation threshold corresponding to the aging clock score; S502, comparing the state evaluation threshold with the aging clock score; When the aging clock score is greater than the status evaluation threshold, it indicates abnormal kidney aging, and the kidney aging status is recorded as abnormal aging status; When the aging clock score is less than or equal to the status evaluation threshold, it indicates that kidney aging is normal, and the kidney aging status is recorded as normal aging status.

[0031] As described in the above steps S501-S502, after the aging clock score is output, it will be used as a basis to identify the kidney aging state. First, the aging clock score and the state evaluation threshold corresponding to the aging clock score are obtained. The state evaluation threshold is determined based on a large amount of historical data and is used to distinguish the normal range and abnormal range of kidney aging. Then, the obtained state evaluation threshold is compared with the aging clock score accordingly. If the aging clock score is greater than the state evaluation threshold, it indicates that the degree of kidney aging exceeds the normal range and there is an abnormality. In this case, the kidney aging state is recorded as an abnormal aging state. On the contrary, if the aging clock score is less than or equal to the state evaluation threshold, it indicates that the degree of kidney aging is within the normal range. At this time, the kidney aging state is recorded as a normal aging state.

[0032] In a preferred embodiment, the step of optimizing the cycle length of the periodic assessment of the degree of renal aging according to the allowable deviation score comprises: S601, taking the current node as the reference point, performing reverse offset processing, and constructing a monitoring period based on the reference point and the offset point after reverse offset; S602, setting multiple evaluation nodes within the monitoring period, and outputting the allowable deviation score under each evaluation node in real time; S603, obtaining a first condition function, inputting the allowable deviation score into the first condition function, and calibrating the output result of the first condition function as an optimization condition parameter; S604. Calculate the allowable duration of normal kidney aging based on the optimized condition parameters, and determine the period length of periodic assessment of kidney aging degree based on the allowable duration.

[0033] As described in the above steps S601-S604, when the kidney is in a normal aging state, the current time node is first used as the reference point, and then reverse offset processing is performed to construct a monitoring period. Multiple evaluation nodes are set within the monitoring period, and the allowable deviation score under each evaluation node is synchronously output, wherein the allowable deviation score = aging clock score - state evaluation threshold, and then the first conditional function is introduced, and the expression of the first conditional function is: , where Q represents the optimization condition parameter, T represents the length of the monitoring period, and n represents the number of evaluation nodes. It represents the allowable deviation score. By inputting the allowable deviation score into the first conditional function, the optimization condition parameters can be calculated. Then, the allowable duration of normal kidney aging will be calculated based on the optimization condition parameters. After the allowable duration is output, it will be used as a basis to further determine the cycle length of the periodic assessment of the degree of kidney aging, so as to monitor the health of the kidneys.

[0034] In a preferred embodiment, the steps of calculating the allowable duration of normal kidney aging based on the optimized condition parameters, and determining the cycle length of the periodic assessment of the degree of kidney aging based on the allowable duration, include: Step 1, obtain the optimization condition parameters according to the preset allowable deviation threshold; Step 2, obtaining a second conditional function, and inputting the optimization condition parameter and the allowable deviation threshold into the second conditional function, and marking the output result of the second conditional function as the allowable duration; Step 3, obtain the standard duration, and compare the standard duration with the allowable duration; When the allowable duration is less than or equal to the standard duration, the reference point is offset according to the allowable duration to obtain the allowable duration period, and then the end node of the allowable duration period is reversely offset to obtain the risk node, and the time length between the risk node and the reference point is recorded as the period length of the periodic assessment of the degree of renal aging; When the allowed duration is greater than the standard duration, the standard duration is directly recorded as the cycle length for periodic assessment of kidney aging.

[0035] As described in the above steps Step 1 to Step 3, after the optimization condition parameters are output, the optimization condition parameters and the allowable deviation threshold are input into a preset second condition function, wherein the expression of the second condition function is: , t represents the allowed duration, Indicates the allowable deviation threshold, It represents the allowable deviation score at the current node. Through the calculation of the second conditional function, a result calibrated as the allowable duration can be output. The allowable duration will reflect the maximum length of time that the kidney is in the normal aging process. Then the preset standard duration is introduced. The standard duration is a reference value based on medical research and clinical experience. Then the standard duration is compared with the allowable duration. When the allowable duration is less than or equal to the standard duration, it indicates that the degree of kidney aging is gradually becoming abnormal. At this time, it is necessary to offset the reference point (current node) according to the allowable duration, so as to obtain the allowable duration period, and then reversely offset the end node of the allowable duration period, so as to obtain the risk node, and record the time length between the risk node and the reference point as the cycle length of the periodic assessment of the degree of kidney aging. However, if the calculated allowable duration is greater than the standard duration, the standard duration will be directly recorded as the cycle length of the periodic assessment of the degree of kidney aging, so as to ensure that the assessment cycle will not be too long, so that problems that may arise in the process of kidney aging can be discovered and dealt with in a timely manner.

[0036] See also Figure 2 , a renal aging clock assessment system based on renal pathology and artificial intelligence, using the above-mentioned renal aging clock assessment method based on renal pathology and artificial intelligence, including: An information classification module is used to pre-process the acquired pathological characteristic information and classify the pre-processed pathological characteristic information to obtain multiple pathological special subsets; A feature extraction module is used to extract the pathological feature information in each pathological special subset to obtain the pathological features related to kidney aging; The association analysis module is used to perform association analysis between the pathological features and the kidney aging clock to obtain the association weight between each pathological feature and the kidney aging clock; Aging assessment module: The aging assessment module is used to evaluate and analyze the degree of kidney aging based on the associated weights of various pathological characteristics, and simultaneously generate multiple aging clock scores; A state recording module, the state recording module is used to identify the kidney aging state according to the aging clock score, wherein the kidney aging state includes a normal aging state and an abnormal aging state; A first response module, which is used to continue monitoring the kidney's aging clock score under normal aging conditions, and synchronously output the allowable deviation score, and then optimize the cycle length of the periodic assessment of the kidney's aging degree according to the allowable deviation score; The second response module is used to immediately trigger the alarm mechanism and simultaneously send out an alarm signal in an abnormal aging state.

[0037] As mentioned above, the system includes an information classification module, a feature extraction module, an association analysis module, an aging assessment module, a state recording module, a first response module and a second response module. The information classification module performs preliminary preprocessing on the feature information obtained from the kidney pathology sample. After the preprocessing is completed, the information classification module will perform detailed classification processing on the preprocessed pathological feature information, thereby obtaining a plurality of pathological special subsets with different pathological features. The feature extraction module is responsible for extracting features from the pathological feature information in each pathological special subset, so as to identify pathological features related to the kidney aging process. The association analysis module performs corresponding association analysis on the relationship between the pathological features and the kidney aging clock. Through the association analysis, the association weights between each pathological feature and the kidney aging clock can be calculated, thereby revealing the importance of different pathological features in the kidney aging process. The aging assessment module is based on the association of each pathological feature. Weight, comprehensively evaluate and analyze the degree of kidney aging. The system can generate multiple scores related to the degree of kidney aging, namely aging clock scores. The state recording module identifies the aging state of the kidney based on the aging clock score. The system divides the aging state of the kidney into two categories: normal aging state and abnormal aging state, for the convenience of subsequent monitoring and management. The first response module works when the kidney is in a normal aging state. It will continuously monitor the aging clock score of the kidney and output an allowable deviation range based on the score result. In this way, the first response module can optimize the cycle length of the periodic assessment of the degree of kidney aging, thereby improving the efficiency and accuracy of the assessment. The second response module is activated when the kidney is in an abnormal aging state. Once an abnormal aging state is detected, the second response module will immediately trigger the alarm mechanism and simultaneously send out an alarm signal so that relevant personnel can quickly take corresponding intervention measures to ensure kidney health.

[0038] See also Figure 3 , an electronic device, the electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; Among them, the memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the above-mentioned renal aging clock assessment method based on renal pathology and artificial intelligence.

[0039] The processors of the above electronic devices can be of various types, such as a central processing unit (CPU), a graphics processing unit (GPU) or an application-specific integrated circuit (ASIC). These processors can efficiently perform complex computing tasks, and the memory can include a random access memory (RAM), a read-only memory (ROM), a solid-state drive (SSD) or other types of storage devices, and also include input and output devices and an arithmetic unit. The input and output devices include a keyboard, a mouse, a touch screen, a display, etc., which are used to interact with the user, and the arithmetic unit is responsible for performing various mathematical and logical operations.

[0040] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0041] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.

Claims

1. A renal aging clock assessment method based on renal pathology and artificial intelligence, characterized by: include: Preprocessing the acquired pathological characteristic information, and classifying the preprocessed pathological characteristic information to obtain multiple pathological special subsets; Extracting features from the pathological feature information in each of the pathological special subsets to obtain pathological features related to kidney aging; Performing correlation analysis on the pathological features and the kidney aging clock to obtain the correlation weight between each pathological feature and the kidney aging clock; According to the correlation weights of each of the pathological characteristics, the degree of kidney aging is evaluated and analyzed, and multiple aging clock scores are generated simultaneously; Identifying the renal aging state according to the aging clock score, wherein the renal aging state includes a normal aging state and an abnormal aging state; In the normal aging state, the aging clock score of the kidney continues to be monitored, and the allowable deviation score is synchronously output, and then the cycle length of the periodic assessment of the degree of kidney aging is optimized according to the allowable deviation score; In the abnormal aging state, the alarm mechanism is immediately triggered and an alarm signal is sent out synchronously.

2. The method for evaluating the renal aging clock based on renal pathology and artificial intelligence according to claim 1, characterized in that: The step of preprocessing the acquired pathological characteristic information and classifying the preprocessed pathological characteristic information to obtain a plurality of pathological special subsets includes: Acquiring the pathological characteristic information, wherein the pathological characteristic information includes kidney tissue slice images, biochemical index data, and gene expression data; Preprocessing the pathological characteristic information, wherein the preprocessing includes image denoising, data normalization, and missing value processing; The preprocessed pathological feature information is classified according to the corresponding pathological specialties to form multiple pathological specialty subsets.

3. The method for evaluating the renal aging clock based on renal pathology and artificial intelligence according to claim 1, characterized in that: The step of extracting the pathological characteristic information in each of the pathological special subsets to obtain the pathological characteristics related to kidney aging includes: Obtaining pathological feature information in each of the pathological specialty subsets; To obtain baseline characteristics associated with kidney aging; The baseline feature is feature matched with the pathological feature information in the pathological special subset, and feature information related to kidney aging is extracted from the pathological special subset and recorded as a pathological feature.

4. The method for evaluating the renal aging clock based on renal pathology and artificial intelligence according to claim 1, characterized in that: The step of performing correlation analysis on the pathological features and the kidney aging clock to obtain the correlation weight between each pathological feature and the kidney aging clock includes: Obtaining all the pathological features and the continuous time periods in which each of the pathological features undergoes unique changes, and recording them as association analysis time periods, wherein each of the pathological features corresponds to a number of association analysis time periods; Marking the pathological features that have uniquely changed in each of the association analysis periods as variable features, and marking the pathological features that have not changed as quantitative features; Obtaining the difference in kidney aging between the start node and the end node of the association analysis period, and recording it as an association condition parameter; A weight allocation function is obtained, and the association condition parameter is input into the weight allocation function, and an output result of the weight allocation function is recorded as an association weight.

5. The method for evaluating the renal aging clock based on renal pathology and artificial intelligence according to claim 1, characterized in that: The step of evaluating and analyzing the degree of kidney aging based on the associated weights of each of the pathological characteristics and synchronously generating multiple aging clock scores includes: Obtaining the associated weight of each of the pathological features and the historical change amount of each of the pathological features; Taking an average of the historical changes of each of the pathological characteristics to obtain an average change parameter; An evaluation function is obtained, and the association weight and the average change parameter of the pathological feature are input into the evaluation function, and the output result of the evaluation function is recorded as an aging clock score.

6. The method for evaluating the renal aging clock based on renal pathology and artificial intelligence according to claim 1, characterized in that: The step of identifying the kidney aging state according to the aging clock score comprises: Acquire an aging clock score of the kidney and a state evaluation threshold corresponding to the aging clock score; comparing the state evaluation threshold with the aging clock score; When the aging clock score is greater than the state evaluation threshold, it indicates that the kidney aging is abnormal, and the kidney aging state is recorded as an abnormal aging state; When the aging clock score is less than or equal to the state evaluation threshold, it indicates that kidney aging is normal, and the kidney aging state is recorded as a normal aging state.

7. The method for evaluating the renal aging clock based on renal pathology and artificial intelligence according to claim 1, characterized in that: The step of optimizing the cycle length of the periodic assessment of the degree of kidney aging according to the allowable deviation score comprises: Taking the current node as the reference point, reverse offset processing is performed, and the monitoring period is constructed based on the reference point and the offset point after reverse offset; Setting a plurality of evaluation nodes within the monitoring period, and outputting the allowable deviation score under each of the evaluation nodes in real time; Obtaining a first condition function, inputting the allowable deviation score into the first condition function, and calibrating an output result of the first condition function as an optimization condition parameter; The allowable duration of normal kidney aging is calculated based on the optimized condition parameters, and the period length of the periodic assessment of the degree of kidney aging is determined based on the allowable duration.

8. The method for evaluating the renal aging clock based on renal pathology and artificial intelligence according to claim 7, characterized in that: The steps of calculating the allowable duration of normal kidney aging according to the optimized condition parameters, and determining the cycle length of the periodic assessment of the degree of kidney aging according to the allowable duration, include: Obtaining the optimization condition parameters according to a preset allowable deviation threshold; Obtaining a second condition function, and inputting the optimization condition parameter and the allowable deviation threshold into the second condition function, and marking the output result of the second condition function as the allowable duration; Obtaining a standard duration, and comparing the standard duration with an allowable duration; When the allowable duration is less than or equal to the standard duration, the reference point is offset according to the allowable duration to obtain the allowable duration period, and then the end node of the allowable duration period is reversely offset to obtain the risk node, and the time length between the risk node and the reference point is recorded as the period length of the periodic assessment of the degree of renal aging; When the allowable duration is greater than the standard duration, the standard duration is directly recorded as the cycle length for the periodic assessment of the degree of kidney aging.

9. A renal aging clock assessment system based on renal pathology and artificial intelligence, characterized by: The method for evaluating the renal aging clock based on renal pathology and artificial intelligence according to any one of claims 1 to 8 comprises: An information classification module, wherein the information classification module is used to preprocess the acquired pathological characteristic information and classify the preprocessed pathological characteristic information to obtain a plurality of pathological special subsets; A feature extraction module, the feature extraction module is used to extract the pathological feature information in each of the pathological special subsets to obtain pathological features related to kidney aging; An association analysis module, wherein the association analysis module is used to perform association analysis on the pathological features and the kidney aging clock to obtain an association weight between each pathological feature and the kidney aging clock; An aging assessment module, which is used to assess and analyze the degree of kidney aging based on the associated weights of each of the pathological characteristics, and to synchronously generate multiple aging clock scores; A state recording module, the state recording module is used to identify the kidney aging state according to the aging clock score, wherein the kidney aging state includes a normal aging state and an abnormal aging state; A first response module, the first response module is used to continue to monitor the aging clock score of the kidney in the normal aging state, and synchronously output the allowable deviation score, and then optimize the cycle length of the periodic evaluation of the degree of kidney aging according to the allowable deviation score; The second response module is used to immediately trigger an alarm mechanism and synchronously send out an alarm signal in the abnormal aging state.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the renal aging clock assessment method based on renal pathology and artificial intelligence as described in any one of claims 1 to 8.

Images