CN118969248B - Obstructive renal fibrosis progress quantitative evaluation system based on data analysis - Google Patents

Abstract

The invention relates to the technical field of data processing, in particular to an obstructive renal fibrosis progress quantitative evaluation system based on data analysis, which comprises a data acquisition module, a data processing module, an obstructive renal fibrosis analysis module and a control module, wherein the data acquisition module is used for acquiring obstructive renal fibrosis characteristic data, the data processing module is used for preprocessing the obstructive renal fibrosis characteristic data to output standard obstructive renal fibrosis data, the obstructive renal fibrosis analysis module is used for determining an obstructive renal fibrosis evaluation value according to the standard obstructive renal fibrosis data, and the control module is used for adjusting the number of directions of data polling or combining the variance of response delay and the linear fitting degree of the error amount of the evaluation model to judge the accuracy of data acquisition when the stability of response delay judgment evaluation according to the variance of the obstructive renal fibrosis evaluation model is not in accordance with requirements.

Description

A quantitative assessment system for the progression of obstructive renal fibrosis based on data analysis

Technical Field

The present invention relates to the technical field of data processing, and in particular to a quantitative evaluation system for the progression of obstructive renal fibrosis based on data analysis.

Background Art

Obstructive renal fibrosis is a common urinary system disease, and its progression may cause serious damage to kidney function. Traditional methods for evaluating obstructive renal fibrosis often rely on the doctor's subjective judgment and limited detection indicators, such as the degree of renal pelvic separation in ultrasound examination and the thickness of renal parenchyma in CT examination. These methods have certain limitations in accuracy and comprehensiveness. With the continuous development of medical technology, various advanced detection equipment and technologies have been applied, generating a large amount of data related to obstructive renal fibrosis, including imaging data, biochemical index data, and patient clinical symptoms and signs data. However, these data are usually scattered and isolated, making them difficult to be effectively integrated and analyzed. The main purpose of this study is to evaluate the degree and progression of obstructive renal fibrosis through urine obstructive renal fibrosis marker data and hydronephrosis imaging data, so as to complete the evaluation of obstructive renal fibrosis more accurately, comprehensively and individually.

Chinese Patent Publication No.: CN113069146A discloses a method for evaluating unilateral hydronephrosis in children. Two-dimensional ultrasound is used to measure and calculate the volume of both kidneys of the child in detail. According to K=VL/VR, the K value is calculated. By comparing the calculated K value with the K value threshold obtained in previous studies, the patient's condition changes can be intuitively reflected. Our previous work shows that this indicator can not only be used for the evaluation of the recovery of hydronephrosis after UPJO surgery and the effect of surgery, but can also be used for the preoperative prognosis judgment of congenital hydronephrosis, providing clinicians with an evaluation of the condition changes. It can be seen that the method for evaluating unilateral hydronephrosis in children has the problem of insufficient evaluation stability.

Summary of the invention

To this end, the present invention provides a quantitative assessment system for obstructive renal fibrosis progression based on data analysis, so as to overcome the problem of insufficient quality stability of obstructive renal fibrosis progression assessment in the prior art.

To achieve the above objectives, the present invention provides a quantitative assessment system for the progression of obstructive renal fibrosis based on data analysis, comprising:

A data acquisition module is used to collect characteristic data of obstructive renal fibrosis, wherein the characteristic data of obstructive renal fibrosis include urine obstructive renal fibrosis marker data and hydronephrosis imaging data;

A data processing module connected to the data acquisition module, used for preprocessing the obstructive renal fibrosis characteristic data to output standard obstructive renal fibrosis data, including a comparison and correction unit used for performing comparative analysis on the obstructive renal fibrosis characteristic data to output corrected obstructive renal fibrosis characteristic data;

an obstructive renal fibrosis analysis module, connected to the data processing module, for determining an obstructive renal fibrosis evaluation value according to the standard obstructive renal fibrosis data, comprising a mapping establishment unit for generating a plurality of mappings by training the standard obstructive renal fibrosis data and a model generation unit connected to the mapping establishment unit for generating an obstructive renal fibrosis evaluation model according to the plurality of mappings;

A control module, which is respectively connected to the data acquisition module, the data processing module and the obstructive renal fibrosis analysis module, and is used to adjust the number of data polling directions when the stability of the evaluation determined by the variance of the response delay of the obstructive renal fibrosis evaluation model does not meet the requirements, or to judge the accuracy of data acquisition by combining the variance of the response delay and the linear fit between the abnormal amount of the acquired data and the model error amount, and to determine the number of organ interaction parameter mapping groups to be adjusted according to the accuracy determination result or to adjust the number of comparison types according to the average difference amount of the acquired data.

Furthermore, the obstructive renal fibrosis analysis module also includes a model updating unit connected to the model generating unit for updating the obstructive renal fibrosis model.

Furthermore, the control module is connected to the obstructive renal fibrosis analysis module and the data acquisition module, respectively, to obtain the response delay of the obstructive renal fibrosis assessment model after inputting several batches of data to calculate the variance of the response delay, and when the variance of the response delay is greater than a preset first variance, it is determined that the stability of the assessment does not meet the requirements, and when the variance of the response delay is greater than a preset second variance, the number of directions of the data polling is increased.

Further, the increased number of directions of the data polling is determined by a difference between the variance of the response delay and the preset second variance.

Furthermore, the control module is connected to the data acquisition module and the obstructive renal fibrosis analysis module respectively, and is also used to preliminarily determine that the accuracy of data acquisition does not meet the requirements when the variance of the response delay is greater than or equal to the preset first variance and less than or equal to the preset second variance, collect obstructive renal fibrosis characteristic data, and calculate the error amount of the evaluation model according to the evaluation model, thereby calculating the linear fit between the abnormal data amount of data acquisition and the error amount of the evaluation model, wherein,

If the linear fit between the amount of abnormal data collected and the error amount of the evaluation model is greater than a preset second fit, the control module determines for the second time that the accuracy of the data collection does not meet the requirements, and increases the number of mappings between non-renal organ operating parameters and obstructive renal fibrosis characteristic data.

Furthermore, the increase in the number of organ interaction parameter mapping groups is determined by the difference between the linear fit between the amount of abnormal data collected by the data and the error amount of the evaluation model and a preset second fit.

Furthermore, the control module is connected to the data acquisition module and the obstructive renal fibrosis analysis module respectively, and is also used to collect obstructive renal fibrosis characteristic data to calculate the average value of the difference amount of the collected data, and when the average value of the difference amount of the collected data is greater than the average value of the preset first data difference amount, it is determined that the evaluated data acquisition accuracy does not meet the requirements, and when the average value of the difference amount of the collected data is greater than the average value of the preset second data difference amount, the number of comparison types of the obstructive renal fibrosis characteristic data is increased.

Furthermore, the increase range of the number of the comparison types of the collected data is determined by an average value of the data collection difference amount and an average value of a preset second data difference amount.

Furthermore, the linear fit between the amount of abnormal data collected and the amount of error of the evaluation model is the average value of the sum of the straight-line distances between a number of coordinate points in the coordinate system and a straight-line image of a linear regression function in the coordinate system generated by linear regression calculation using the horizontal coordinate characterization parameters and the vertical coordinate characterization parameters;

The coordinate system uses the amount of abnormal data collected from the characteristic data of obstructive renal fibrosis as the horizontal coordinate and the amount of difference in the evaluation model as the vertical coordinate.

Furthermore, the average value of the difference in collected data is the ratio of the sum of the differences between several batches of collected data and standard collected data to the number of batches, wherein the data amount of each batch of collected data is the same.

Compared with the prior art, the beneficial effect of the present invention lies in that, by setting a data acquisition module, a data processing module, an obstructive renal fibrosis analysis module and a control module, the present invention evaluates the degree of obstructive renal fibrosis through the obstructive renal fibrosis evaluation model generated by the model generation unit in the obstructive renal fibrosis analysis module, thereby improving the accuracy of the evaluation; by adjusting the number of data polling directions, the influence of insufficient evaluation stability caused by the large amount of data required for the model to be used when updating and generating is reduced, which may cause the overall system to run stuck when running at the same time; by adjusting the number of mappings of non-renal organ operating parameters and obstructive renal fibrosis characteristic data according to the linear fit between the amount of abnormal data collected and the error amount of the evaluation model, the degree of interference caused by non-renal organs on changes in ureter data or fibrosis data is reduced; by adjusting the number of comparison types according to the average value of the difference amount of collected data, the influence of reduced data collection accuracy caused by signal interference of external equipment on the data collection equipment is reduced, thereby achieving improved stability in the evaluation of the progression of obstructive renal fibrosis.

Furthermore, the present invention sets an obstructive renal fibrosis model update unit to update the obstructive renal fibrosis model when an error occurs in the evaluation of the obstructive renal fibrosis evaluation model, thereby overcoming the problem of unstable operation of the obstructive renal fibrosis model, enabling model training to be realized, and improving the accuracy of the obstructive renal fibrosis analysis system.

Furthermore, the present invention, by setting a control module and a data acquisition module, performs polling after the characteristic data of obstructive renal fibrosis is collected, thereby overcoming the problem of response delay caused by too much data accumulation in the obstructive renal fibrosis evaluation system during the data collection process, and improves the efficiency of system operation by increasing the number of directions of the data polling.

Furthermore, the present invention calculates the variance of the response delay and the linear fit between the amount of abnormal data collected and the error amount of the evaluation model by setting up a control module and an obstructive renal fibrosis analysis module, thereby overcoming the problem of being unable to control the floating trend of the response delay data and the amount of abnormal data collected and the error amount of the evaluation model, and enhancing the accuracy of the data in the system.

Furthermore, the present invention sets a data processing module to pre-process the collected data, converts the obstructive renal fibrosis characteristic data into standard obstructive renal fibrosis characteristic data, and compares and analyzes the obstructive renal fibrosis characteristic data, thereby overcoming the problem of messy collection of obstructive renal fibrosis characteristic data and improving the efficiency of the obstructive renal fibrosis analysis system.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is an overall structural block diagram of a system for quantitatively evaluating the progression of obstructive renal fibrosis based on data analysis according to an embodiment of the present invention;

2 is a structural block diagram of an obstructive renal fibrosis analysis module of a quantitative assessment system for obstructive renal fibrosis progression based on data analysis according to an embodiment of the present invention;

3 is a block diagram of the connection structure of the obstructive renal fibrosis analysis module and the control module of the obstructive renal fibrosis progression quantitative assessment system based on data analysis according to an embodiment of the present invention;

FIG4 is a structural block diagram of a data processing module of a quantitative assessment system for the progression of obstructive renal fibrosis based on data analysis according to an embodiment of the present invention.

DETAILED DESCRIPTION

In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

It will be understood by those skilled in the art that, unless otherwise stated, the singular forms "a", "an" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in this specification refers to the presence of features, integers, steps, operations, elements/components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements/components. It should be understood that when we refer to a module as being "connected" or "coupled" to another module, it may be directly connected or coupled to the other module, or there may be an intermediate unit. In addition, "connected" or "coupled" used herein may include wireless connection or wireless coupling.

Please refer to FIG. 1, FIG. 2, FIG. 3 and FIG. 4, which are respectively an overall structural block diagram of a quantitative assessment system for obstructive renal fibrosis progression based on data analysis, a structural block diagram of an obstructive renal fibrosis analysis module, a connection structural block diagram of the obstructive renal fibrosis analysis module and a control module, and a structural block diagram of a data processing module. The quantitative assessment system for obstructive renal fibrosis progression based on data analysis of the present invention comprises:

A data acquisition module is used to collect characteristic data of obstructive renal fibrosis, wherein the characteristic data of obstructive renal fibrosis include urine obstructive renal fibrosis marker data and hydronephrosis imaging data;

A data processing module, connected to the data acquisition module, for preprocessing the obstructive renal fibrosis characteristic data to output standard obstructive renal fibrosis data, including a comparison and correction unit for performing comparative analysis on the obstructive renal fibrosis characteristic data to output corrected obstructive renal fibrosis characteristic data and a preprocessing unit for preprocessing data transmitted by the data acquisition module;

an obstructive renal fibrosis analysis module, connected to the data processing module, for determining an obstructive renal fibrosis evaluation value according to the standard obstructive renal fibrosis data, comprising a mapping establishment unit for generating a plurality of mappings by training the standard obstructive renal fibrosis data and a model generation unit connected to the mapping establishment unit for generating an obstructive renal fibrosis evaluation model according to the plurality of mappings;

A control module, which is respectively connected to the data acquisition module, the data processing module and the obstructive renal fibrosis analysis module, and is used to adjust the number of data polling directions when the stability of the evaluation determined by the variance of the response delay of the obstructive renal fibrosis evaluation model does not meet the requirements, or to determine the accuracy of data acquisition by combining the variance of the response delay and the linear fit between the abnormal amount of the acquired data and the model error amount, and to determine the number of organ interaction parameter mapping groups to be adjusted according to the accuracy determination result or to adjust the number of comparison types according to the average difference amount of the acquired data.

Specifically, the standard obstructive renal fibrosis data is the normal value range of various obstructive renal fibrosis characteristic data, such as the standard value range of renal parenchyma thickness is [1.5cm, 2.5cm]. The modified obstructive renal fibrosis characteristic data refers to the data retained after comparing and screening the characteristic data collected by the data acquisition module with the standard obstructive renal fibrosis data.

Specifically, the specific process of correcting the characteristic data of obstructive renal fibrosis is the process of removing abnormal data.

Specifically, the obstructive renal fibrosis analysis module determines the obstructive renal fibrosis evaluation value based on the standard obstructive renal fibrosis data. When the urine obstructive renal fibrosis marker data is the content of fibronectin in serum, and the hydronephrosis imaging data is the thickness of the renal parenchyma, the obstructive renal fibrosis evaluation value is: fibronectin content weight coefficient × fibronectin content + renal parenchyma thickness weight coefficient × renal parenchyma thickness, the sum of the fibronectin content weight coefficient and the renal parenchyma thickness weight coefficient is equal to 1, wherein the preferred embodiment of the fibronectin content weight coefficient is 0.4, and the preferred embodiment of the renal parenchyma thickness weight coefficient is 0.6.

Optionally, the preset standard obstructive renal fibrosis evaluation value may range from [72.9, 113.5], the preset standard fibronectin content may range from [180 mg/L, 280 mg/L], and the preset standard renal parenchyma thickness may range from [1.5 cm, 2.5 cm];

In implementation, for example, if the patient's fibronectin content is 200 mg/L and the thickness of the renal parenchyma is 2 cm, then the obstructive renal fibrosis evaluation value is 200×0.4+2×0.6=81.2, and it is determined that the patient's obstructive renal fibrosis evaluation value is within the range of the standard obstructive renal fibrosis evaluation value;

For another example, if the patient's fibronectin content is 300 mg/L and the thickness of the renal parenchyma is 2 cm, then the obstructive renal fibrosis assessment value is 300×0.4+2×0.6=121.2, which means that the patient's obstructive renal fibrosis assessment value is not within the range of the standard obstructive renal fibrosis assessment value.

In implementation, the present invention sets a data acquisition module, a data processing module, an obstructive renal fibrosis analysis module and a control module, and uses the obstructive renal fibrosis evaluation model generated by the model generation unit in the obstructive renal fibrosis analysis module to evaluate the degree of obstructive renal fibrosis, thereby improving the accuracy of the evaluation. By adjusting the number of data polling directions, the influence of insufficient evaluation stability caused by the large amount of data required for the model to be updated and generated running at the same time, which may cause the overall system to run stuck, is reduced. By adjusting the number of mappings of non-renal organ operating parameters and obstructive renal fibrosis characteristic data according to the linear fit between the amount of abnormal data collected and the error amount of the evaluation model, the degree of interference caused by non-renal organs on changes in ureter data or fibrosis data is reduced. By adjusting the number of comparison types according to the average value of the difference in the collected data, the influence of the reduction in data collection accuracy due to signal interference of external equipment on the data collection equipment is reduced, thereby achieving an improvement in the stability of obstructive renal fibrosis progression evaluation.

Specifically, the obstructive renal fibrosis analysis module further includes a model updating unit connected to the model generating unit for updating the obstructive renal fibrosis model.

Specifically, the updating process of the obstructive renal fibrosis evaluation model is as follows: if an error occurs in the evaluation of the obstructive renal fibrosis evaluation model, the input data of the obstructive renal fibrosis model is locked according to the error, and the input data is marked, and the marked input data is put into the training set for training to update the obstructive renal fibrosis model.

Specifically, the control module is connected to the obstructive renal fibrosis analysis module and the data acquisition module, respectively, to obtain the response delay of the obstructive renal fibrosis assessment model after inputting several batches of data to calculate the variance of the response delay, and when the variance of the response delay is greater than a preset first variance, it is determined that the stability of the assessment does not meet the requirements, and when the variance of the response delay is greater than a preset second variance, the number of directions of the data polling is increased;

Specifically, the variance of the response delay means the variance of the response delay duration generated by the obstructive renal fibrosis assessment model after inputting several times the same amount of obstructive renal fibrosis characteristic data. The calculation method of the variance of the response delay is a conventional technical means well known to those skilled in the art, and therefore the calculation process of the variance of the response delay will not be repeated here.

Specifically, the response delay time is the difference between the time taken by the obstructive renal fibrosis assessment model from inputting the same amount of obstructive renal fibrosis characteristic data several times to the obstructive renal fibrosis assessment model processing the above data and outputting the obstructive renal fibrosis evaluation value and the standard time.

Specifically, the standard time is related to the amount of data input into the obstructive renal fibrosis assessment model at a single time. Generally speaking, those skilled in the art will understand that the more data the obstructive renal fibrosis assessment model inputs at a single time, the more data the obstructive renal fibrosis assessment model needs to process. Therefore, in a general sense, the time required for the obstructive renal fibrosis assessment model to output the obstructive renal fibrosis evaluation value is longer.

In implementation, the characteristic data of obstructive renal fibrosis include the content of fibronectin in serum, the thickness of renal parenchyma, the width of renal pelvic separation, the content of monocyte chemoattractant protein-1 in urine, and the content of ADAMTS18 in urine; the direction of data polling can start from the content of fibronectin, and then the thickness of renal parenchyma, the width of renal pelvic separation, the content of monocyte chemoattractant protein-1 in urine, and end with the content of ADAMTS18 in urine; the direction of data polling can also start from the content of ADAMTS18 in urine, and then The content of monocyte chemoattractant protein-1 in urine, the width of renal pelvic separation, the thickness of renal parenchyma, and end with the content of fibronectin in serum; the characteristic data of obstructive renal fibrosis can also be polled starting from the content of fibronectin in serum and the content of ADAMTS18 in urine, respectively. The order of polling in one direction is the content of fibronectin in serum and the thickness of renal parenchyma, and the order of polling in the other direction is the content of ADAMTS18 in urine and the content of monocyte chemoattractant protein-1 in urine, and end with the width of renal pelvic separation.

Specifically, the ADAMTS18 is a disintegrin-like metalloproteinase 18 containing a type I platelet-binding protein motif.

Specifically, the increased number of directions of the data polling is determined by the difference between the variance of the response delay and the preset second variance.

Optionally, the preset value range of the first variance may be [1.5s, 2s], and the preset value range of the second variance may be [2s, 3s].

Preferably, the preferred embodiment of the preset first variance is 1.5 s, and the preferred embodiment of the preset second variance is 2.5 s.

In implementation, when the variance of the response delay exceeds the preset second variance by 4s, the number of data polling directions is increased to 3 times the current number of data polling directions; when the variance of the response delay exceeds the preset second variance by more than 0.5s, the number of data polling directions is increased by 1. For example, in one possible embodiment, when the variance of the response delay is 3.5s, the number of original data polling directions is 1, and the number of data polling directions becomes: 1+[(3.5-2.5)/0.5]×1=3, i.e., when the variance of the response delay is 3.5s, the number of data polling directions becomes 3.

For another example, in a possible embodiment, when the variance of the response delay is 6.5s, the number of directions of the original data polling is 1, and the number of directions of the data polling becomes: 1+[(6.5-2.5)/4]×3=4, that is, when the variance of the response delay is 6.5s, the number of directions of the data polling becomes 4.

Specifically, the control module is connected to the data acquisition module and the obstructive renal fibrosis analysis module respectively, and is also used to preliminarily determine that the accuracy of data acquisition does not meet the requirements when the variance of the response delay is greater than or equal to the preset first variance and less than or equal to the preset second variance, collect obstructive renal fibrosis characteristic data, and calculate the error amount of the evaluation model according to the evaluation model, thereby calculating the linear fit between the abnormal data amount of data acquisition and the error amount of the evaluation model, wherein,

If the linear fit between the amount of abnormal data collected and the error amount of the evaluation model is greater than a preset second fit, the control module determines for the second time that the accuracy of the data collection does not meet the requirements, and increases the number of mappings between non-renal organ operating parameters and obstructive renal fibrosis characteristic data.

Optionally, the preset value range of the second fitness degree may be [1, 2].

Preferably, the second degree of fit is preset to be 1.5.

In implementation, each time the linear fit exceeds the value of the preset second fit by more than 0.5, the number of mappings of non-renal organ operating parameters and obstructive renal fibrosis characteristic data increases by 1. For example, in one possible embodiment, when the linear fit is 3, the number of original mappings of non-renal organ operating parameters and obstructive renal fibrosis characteristic data is 1, and the number of mappings of non-renal organ operating parameters and obstructive renal fibrosis characteristic data becomes: 1+[(3-1.5)/0.5]×1=4, that is, when the linear fit is 3, the number of original mappings of non-renal organ operating parameters and obstructive renal fibrosis characteristic data becomes 4.

For another example, when the linear fit is 2.5, the number of mappings between the original non-renal organ operating parameters and the characteristic data of obstructive renal fibrosis is 1, and the number of mappings between the non-renal organ operating parameters and the characteristic data of obstructive renal fibrosis becomes: 1+[(2.5-2)/0.5]×1=2, that is, when the linear fit is 2.5, the number of mappings between the original non-renal organ operating parameters and the characteristic data of obstructive renal fibrosis becomes 2.

Specifically, the number of organ interaction parameter mapping groups is the number of one-to-one correspondences between the data in the two sets of non-renal organ operation parameters and obstructive renal fibrosis characteristic data;

Specifically, when obstruction causes a stress response in the body, the blood pressure value in the non-renal organ operation parameters and the aspartate aminotransferase content in the liver in the obstructive renal fibrosis characteristic data form a set of mappings. When other characteristic data remain unchanged, the blood pressure value is directly proportional to the aspartate aminotransferase content, and the blood pressure value increases with the increase of aspartate aminotransferase content.

Specifically, the increase in the number of organ interaction parameter mapping groups is determined by the difference between the linear fit between the amount of abnormal data collected and the error amount of the evaluation model and a preset second fit.

Specifically, the control module is connected to the data acquisition module and the obstructive renal fibrosis analysis module, respectively, and is also used to collect obstructive renal fibrosis characteristic data to calculate the average value of the difference amount of the collected data, and when the average value of the difference amount of the collected data is greater than the average value of the preset first data difference amount, it is determined that the evaluated data acquisition accuracy does not meet the requirements, and when the average value of the difference amount of the collected data is greater than the average value of the preset second data difference amount, the number of comparison types of the obstructive renal fibrosis characteristic data is increased.

Specifically, the comparison types of obstructive renal fibrosis characteristic data include comparison with the obstructive renal fibrosis characteristic data of the previous month and the month before that whose collection time points are consistent with the obstructive renal fibrosis characteristic data, and comparison with the obstructive renal fibrosis characteristic data of the previous collection cycle whose air temperature is the same as that of the collection environment of the current obstructive renal fibrosis characteristic data.

Optionally, taking fibronectin content data as an example, the preset value range of the average value of the first data difference amount may be [1 mg/L, 1.5 mg/L], and the preset value range of the second data difference amount may be [2 mg/L, 3 mg/L];

Preferably, the preferred embodiment of the average value of the average value of the preset first data difference amount is 1.5 mg/L, and the preferred embodiment of the average value of the preset second data difference amount is 2.5 mg/L;

In one or more embodiments, every time the average value of the difference amounts of the plurality of collected data exceeds the average value of the preset second data difference amount by 3 mg/L, the comparison types of the collected data are increased by 3;

For example, the average value of the difference amounts of several collected data is 5.5 mg/L, and the number of the current collected data comparison types is 5, then the number of collected data comparison types increases to: 3+[(5.5-2.5)/3]×3=6.

Specifically, the increase range of the number of the collected data comparison types is determined by the average value of the data collection difference amount and the average value of the preset second data difference amount.

Specifically, the linear fit between the amount of abnormal data collected by the obstructive renal fibrosis characteristic data and the amount of error of the evaluation model is the average value of the sum of the straight-line distances between a number of coordinate points in the coordinate system and a straight-line image of a linear regression function generated by linear regression calculation using the horizontal coordinate characterization parameters and the vertical coordinate characterization parameters in the coordinate system;

The coordinate system uses the amount of abnormal data collected from the characteristic data of obstructive renal fibrosis as the horizontal coordinate and the amount of difference in the evaluation model as the vertical coordinate.

Optionally, the preset standard linear fit is [0.9, 1.1];

Preferably, the preferred embodiment of the preset standard linear fit degree is 1;

In an embodiment, if the amount of abnormal data collected (x) and the amount of error of the evaluation model (y) have n points in the coordinate system, a linear regression function can be obtained:

y＝a+bx+c;

a is the intercept, b is the slope, and c is the error term;

In the coordinate system, there is a point P(x,y). The steps to determine the fitting line Ax+By+C=0 by the linear regression function are: the intercept a represents the value of y when x=0, and the slope b represents the average change in y for every unit increase in x.

In the coordinate system, the distance d from point P(x,y) to the line Ax+By+C=0 is calculated as:

Then the linear fit S of the abnormal data volume of the obstructive renal fibrosis characteristic data collection and the error volume of the evaluation model is:

Wherein, S is the linear fit between the amount of abnormal data collected from the characteristic data of obstructive renal fibrosis and the error amount of the evaluation model, _dn is the straight-line distance between the nth coordinate point and the straight line Ax+By+C=0, n is the number of coordinate points, and n is a natural number greater than or equal to 1.

Specifically, the average value of the difference in collected data is the ratio of the sum of the difference in collected data for several times to the total number of collection times.

So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims (10)

1. A quantitative evaluation system for progression of obstructive renal fibrosis based on data analysis, comprising:

the data acquisition module is used for acquiring obstructive renal fibrosis characteristic data, wherein the obstructive renal fibrosis characteristic data comprises urine obstructive renal fibrosis marker data and hydronephrosis imaging data;

The data processing module is connected with the data acquisition module and used for preprocessing the obstructive renal fibrosis characteristic data to output standard obstructive renal fibrosis data, and comprises a contrast correction unit used for carrying out contrast analysis on the obstructive renal fibrosis characteristic data to output corrected obstructive renal fibrosis characteristic data;

An obstructive renal fibrosis analysis module connected to the data processing module for determining an obstructive renal fibrosis evaluation value from the standard obstructive renal fibrosis data, comprising a map building unit for generating a number of maps by training the standard obstructive renal fibrosis data and a model generating unit connected to the map building unit for generating an obstructive renal fibrosis evaluation model from the number of maps;

The control module is respectively connected with the data acquisition module, the data processing module and the obstructive renal fibrosis analysis module and is used for adjusting the number of data polling directions when the stability evaluated according to the variance judgment of the response delay of the obstructive renal fibrosis evaluation model is not satisfactory, or combining the variance of the response delay and the linear fitting degree of the abnormal quantity of the acquired data and the error quantity of the model to judge the accuracy of data acquisition, and determining the number of the organ interaction parameter mapping groups to be adjusted or adjusting the number of comparison types according to the average difference quantity of the acquired data according to the judgment result of the accuracy.

2. The quantitative evaluation system for the progression of obstructive renal fibrosis based on data analysis of claim 1 wherein the obstructive renal fibrosis analysis module further comprises a model update unit connected to the model generation unit for updating the obstructive renal fibrosis model.

3. The quantitative evaluation system of the progression of the obstructive renal fibrosis based on data analysis of claim 2 wherein the control module is connected to the obstructive renal fibrosis analysis module and the data acquisition module, respectively, for obtaining a response delay of the obstructive renal fibrosis evaluation model after inputting a number of batches of data to calculate a variance of the response delay, determining that the stability of the evaluation is unsatisfactory when the variance of the response delay is greater than a preset first variance, and increasing the number of directions of the data polls when the variance of the response delay is greater than a preset second variance.

4. The quantitative assessment system of obstructive renal fibrosis progression based on data analysis of claim 3 wherein the number of directions of the data polls after augmentation is determined by the difference of the variance of the response delay and the preset second variance.

5. The quantitative evaluation system for the progression of obstructive renal fibrosis based on data analysis of claim 4, wherein the control module is further coupled to the data acquisition module and the obstructive renal fibrosis analysis module, respectively, and is further configured to initially determine that the accuracy of the data acquisition is unsatisfactory when the variance of the response delay is greater than or equal to a preset first variance and less than or equal to the preset second variance, acquire obstructive renal fibrosis characteristic data, and calculate an error amount of the evaluation model based on the evaluation model, thereby calculating a linear fitness of the abnormal data amount of the data acquisition to the error amount of the evaluation model, wherein,

If the linear fitting degree of the abnormal data quantity of the data acquisition and the error quantity of the evaluation model is larger than the preset second fitting degree, the control module secondarily judges that the accuracy of the data acquisition is not in accordance with the requirement, and the number of the mappings of the non-renal organ operation parameters and the obstructive renal fibrosis characteristic data is increased.

6. The quantitative assessment system of obstructive renal fibrosis progression based on data analysis of claim 5 wherein the magnitude of the increase in the number of mappings of non-renal organ operational parameters to obstructive renal fibrosis characterization data is determined by a difference in a linear fitness of an abnormal data volume of the data acquisition to an error volume of an assessment model to a preset second fitness.

7. The quantitative evaluation system for the progression of obstructive renal fibrosis based on data analysis of claim 6 wherein the control module is further coupled to the data acquisition module and the obstructive renal fibrosis analysis module, respectively, to acquire obstructive renal fibrosis characteristic data to calculate an average of the differential amounts of the acquired data, to determine that the evaluated data acquisition accuracy is unsatisfactory when the average of the differential amounts of the acquired data is greater than an average of a preset first differential amount of data, and to increase the number of comparison types of the obstructive renal fibrosis characteristic data when the average of the differential amounts of the acquired data is greater than an average of a preset second differential amount of data.

8. The quantitative assessment system of obstructive renal fibrosis progression based on data analysis of claim 7 wherein the magnitude of the increase in the number of acquired data contrast types is determined by an average of the data acquisition differences and an average of a preset second data difference.

9. The quantitative evaluation system for the progression of obstructive renal fibrosis based on data analysis of claim 8, wherein the linear fitness of the amount of abnormal data acquired by the data and the amount of error of the evaluation model is an average of a sum of linear distances of a number of coordinate points in a coordinate system and a linear regression function generated by linear regression calculation with an abscissa characterizing parameter and an ordinate characterizing parameter in the coordinate system;

The coordinate system takes abnormal data quantity acquired by the characteristic data of the obstructive renal fibrosis as an abscissa and takes the difference quantity of the evaluation model as an ordinate.

10. The quantitative assessment system for the progression of obstructive renal fibrosis based on data analysis of claim 9 wherein the average of the differences in the acquired data is the ratio of the sum of the differences in the number of batches of acquired data to the standard acquired data to the number of batches, wherein the data amount of the acquired data for each of the batches is the same.