Intelligent processing method and system for urinary surgery diagnosis and treatment data

Abstract

The invention discloses an intelligent processing method and system for urinary surgery diagnosis and treatment data, and relates to the technical field of medical data. In the data feature extraction process, the method not only covers urinary flow dynamic features such as the average fluid resistance coefficient FRavg and the pressure and flow velocity dynamic integral DPI, but also covers urinary flow dynamic features such as the average fluid resistance coefficient FRavg and the pressure and flow velocity dynamic integral DPI; and the urine conductivity change rate delta UEC, the urine suspended particle volume ratio change rate delta VSP and the functional index urination efficiency Neff of the abnormal characteristic of the urine are comprehensively extracted and analyzed. By further calculating the bladder emptying function index BEI and the urine fluid resistance index FRE, detailed evaluation of the bladder function and the urinary tract patency is achieved. On the basis of the comprehensive diagnosis score Pf1, the system can accurately identify first-level or second-level evacuation abnormity through hierarchical contrastive analysis, and triggers deep analysis when necessary, thereby providing a more comprehensive diagnosis basis for complex cases such as early bladder dysfunction or urinary tract obstruction.

Description

Technical Field

[0001] The present invention relates to the field of medical data technology, and in particular to an intelligent processing method and system for urology diagnosis and treatment data. Background Art

[0002] Urology is an important branch of medical science, covering the diagnosis and treatment of urinary system diseases, including the treatment of kidney, ureter, bladder, urethra and male reproductive organs and other related diseases. In the sub-field of urology, urodynamic analysis is a core technical means, which is mainly used to evaluate the functional status of the bladder and urinary tract. By measuring multiple parameters such as urine flow rate, bladder pressure, urine composition, etc., urodynamic analysis can provide detailed data support for bladder emptying function and urinary tract patency. These analytical data play a vital role in the diagnosis, efficacy evaluation and treatment plan design of urinary system diseases.

[0003] Although urodynamic analysis is widely used in urology at present, existing methods have some significant limitations. On the one hand, the methods of collecting diagnostic data are diverse and discrete. The multidimensional data collected by sensors, such as urine flow rate, bladder pressure, etc., have poor consistency in time series and are easily affected by equipment parameters and individual differences of patients, resulting in insufficient accuracy and reliability of the data. On the other hand, the existing analysis methods have limited processing capabilities for multidimensional data. Most diagnoses rely on a single indicator, such as maximum flow rate or residual urine volume, and fail to comprehensively consider the complex effects of dynamic changes, such as fluid resistance and bladder recovery rate. This single analysis method may lead to deviations in diagnostic results, especially in early abnormal or complex cases. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method and system for intelligently processing urology diagnosis and treatment data, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented by the following technical scheme: comprising the following steps:

[0006] S1. Use urology diagnosis and treatment equipment and sensors to monitor urology diagnosis and treatment patients in real time, collect urology diagnosis and treatment data of urology diagnosis and treatment patients in real time, build a central processing system, and set a standard interface to transmit the urology diagnosis and treatment data to the central processing system;

[0007] S2. Receive urology diagnosis and treatment data in real time in the central processing system, pre-process the urology diagnosis and treatment data to obtain a standardized data set, and at the same time build a time series database and store the standardized data set in the time series database;

[0008] S3, extracting the standardized data set, performing urodynamic feature extraction, urine abnormality feature extraction and functional index feature extraction, and then integrating the feature vectors obtained by the feature extraction to obtain a urology diagnosis and treatment feature set;

[0009] S4, constructing a urinary diagnosis and treatment algorithm model, extracting the urinary diagnosis and treatment feature set and inputting it into the urinary diagnosis and treatment algorithm model, respectively outputting the bladder emptying function index BEI and the urine fluid resistance index FRE, and then comprehensively calculating the bladder emptying function index BEI and the urine fluid resistance index FRE to obtain a comprehensive diagnostic score Pf1;

[0010] Based on the output result of the comprehensive diagnostic score Pf1, a preliminary comparative evaluation is performed to analyze the patient's urinary function status. If the preliminary comparative evaluation shows secondary emptying abnormality, a deep analysis is performed;

[0011] S5. The in-depth analysis outputs the bladder recovery rate index BRI by calculation, and outputs the comprehensive dynamic risk score Pf2 based on the bladder recovery rate index BRI. A secondary comparative evaluation is performed based on the output result of the comprehensive dynamic risk score Pf2, and a diagnosis and treatment recommendation is output based on the secondary comparative evaluation result.

[0012] Preferably, said S1 includes S11 and S12;

[0013] S11. Use urology diagnosis and treatment equipment and sensors to monitor urology diagnosis and treatment patients in real time, and set the sampling rate of the urology diagnosis and treatment equipment and sensors to 5 minutes / time, so as to collect urology diagnosis and treatment data of urology diagnosis and treatment patients in real time;

[0014] The urological diagnosis and treatment equipment and sensors include a flow meter, a conductivity sensor, an optical particle size analyzer, a fluid resistance sensor, a time stamp sensor, and a portable bladder scanner;

[0015] The urology diagnosis and treatment data include urine flow rate UFR, urine conductivity UEC, urine suspended particle volume ratio VSP, fluid resistance coefficient FR, urine outflow time UOT and residual urine ratio RUR;

[0016] S12. Build a central processing system and set up a standard communication interface USB to connect the OCR image scanning device to the central processing system by wire, and transmit the collected urology diagnosis and treatment data to the central processing system.

[0017] Preferably, S2 includes S21 and S22;

[0018] S21, receiving urology diagnosis and treatment data in real time in a central processing system, and preprocessing the urology diagnosis and treatment data, wherein the preprocessing includes time standardization processing, outlier detection and repair, and normalization processing to obtain a standardized data set;

[0019] The standardized data set includes urine flow rate UFR(t) at time t, urine conductivity UEC(t) at time t, urine suspended particle volume ratio VSP(t) at time t, fluid resistance coefficient FR(t) at time t, urine outflow time UOT(t) and residual urine ratio RUR(t) at time t

[0020] The time standardization process uses linear interpolation to perform time standardization on the data when the examination time series of different patient cases are inconsistent;

[0021] The outlier detection and repair is performed by detecting outliers in the urology diagnosis and treatment data based on the Mahalanobis distance and repairing them using the Bessel interpolation method;

[0022] The normalization and standardization process uses the Z-Score standardization method to eliminate the influence of different dimensions of the urology diagnosis and treatment data;

[0023] S22. Construct a time series database in the central processing system and set a transmission port. Write the standardized data set into the time series database through the transmission port and sort and store it according to the inspection time series.

[0024] Preferably, said S3 includes S31, S32 and S33;

[0025] S31, extracting the urine flow rate UFR(t) at time t and the fluid resistance coefficient FR(t) at time t in the real-time standardized data set from the time series database through the transmission port, extracting urodynamic characteristics, and obtaining the average fluid resistance coefficient FRavg and the pressure flow rate dynamic integral DPI;

[0026] The average fluid resistance coefficient FRavg and the pressure flow rate dynamic integral DPI are calculated and output by the following algorithm formula;

[0027]

[0028] Where T represents the total sampling time, αt 2 represents the nonlinear correction term of time, β represents the sensitivity coefficient of bladder pressure to urine flow rate, and dt represents the time calculus variable.

[0029] Preferably, S32, extracting the urine conductivity UEC(t) at time t and the urine suspended particle volume ratio VSP(t) at time t in the real-time standardized data set in the time series database through the transmission port, extracting abnormal urine characteristics, and obtaining the change rate △UEC of urine conductivity and the change rate △VSP of urine suspended particle volume ratio;

[0030] The change rate of urine conductivity △UEC and the change rate of urine suspended particle volume ratio △VSP are calculated and outputted by the following algorithm formula;

[0031]

[0032] In the formula, UEC i (t) represents the urine conductivity at time t collected for the i-th time, represents the mean value of urine conductivity, γ represents the weight coefficient of the extreme value product part, max(UEC) represents the upper limit of urine conductivity, min(UEC) represents the lower limit of urine conductivity, and n represents the total number of sampling times;

[0033] VSPend represents the volume ratio of urine suspended particles at the end of urination, VSPstart represents the volume ratio of urine suspended particles at the start of urination, δ represents the weight coefficient of the square term of particle concentration, and Td represents the total duration of urination;

[0034] S33, extracting the urine flow rate UFR(t) and urine outflow time UOT at time t in the real-time standardized data set from the time series database through the transmission port, extracting functional indicator features, and obtaining the urination efficiency Neff;

[0035] The urination efficiency Neff is calculated and outputted by the following algorithm formula;

[0036]

[0037] In the formula, ZPN represents the total urine output, and ε represents the weight coefficient for compensating the influence of low flow rate;

[0038] The obtained average fluid resistance coefficient FRavg, pressure flow rate dynamic integral DPI, urine conductivity change rate △UEC, urine suspended particle volume ratio change rate △VSP and urination efficiency Neff are then integrated to obtain the urinary diagnosis and treatment feature set.

[0039] Preferably, S4 includes S41, S42 and S43;

[0040] S41, by constructing a urinary diagnosis and treatment algorithm model, extracting a urinary diagnosis and treatment feature set, and inputting it into the urinary diagnosis and treatment algorithm model, respectively calculating and outputting a bladder emptying function index BEI and a urine fluid resistance index FRE, respectively analyzing the bladder emptying function and urinary tract patency;

[0041] The bladder emptying function index BEI and urine fluid resistance index FRE are calculated and outputted by the following algorithm formula;

[0042]

[0043]

[0044] Wherein, e represents an exponential function, k represents the adjustment coefficient of the negative impact of residual urine ratio on bladder emptying, λ represents the importance weight coefficient of the fluid resistance peak, and max(FR(t)) represents the peak value of the fluid resistance coefficient FR(t) at time t.

[0045] Preferably, S42, based on the obtained bladder emptying function index BEI and urine fluid resistance index FRE, combined with the pressure flow rate dynamic integral DPI and the change rate of urine conductivity △UEC, a comprehensive diagnostic score Pf1 is comprehensively calculated and output to comprehensively analyze the diagnosis of the patient's urinary diagnosis and treatment data;

[0046] The comprehensive diagnostic score Pf1 is calculated and output by the following algorithm formula;

[0047]

[0048] In the formula, ln represents the logarithmic function, ln(1+DPI) represents the logarithmic correction of the dynamic integral of pressure and flow rate, Represents the combined penalty term of volatility and resistance;

[0049] S43, based on the output result of the comprehensive diagnostic score Pf1, a preliminary comparative evaluation is performed to analyze the bladder function in the diagnosis and treatment data of urinary patients, and a grade classification is performed based on the evaluation results. The specific evaluation contents are as follows;

[0050] When the comprehensive diagnostic score Pf1>120, it means that the emptying function is normal and the urinary tract is unobstructed, and no intervention is required at this time;

[0051] When 60≤comprehensive diagnostic score Pf1≤120, a first-level abnormal emptying prompt is generated, and continuous observation is required;

[0052] When the comprehensive diagnostic score Pf1 is less than 60, a secondary emptying abnormality prompt is generated, and in-depth analysis is performed at this time;

[0053] Among them, the first-level emptying abnormality is less than the second-level emptying abnormality.

[0054] Preferably, the S5 includes S51, S52 and S53;

[0055] S51. When the secondary emptying abnormality is found in the preliminary comparison and evaluation, a deep analysis is performed. The deep analysis is performed by using an intra-bladder pressure sensor to detect the initial bladder pressure P0, calculate and output the bladder pressure dynamic change index BP(t) at time t, and then combine the pressure flow rate dynamic integral DPI, the fluid resistance coefficient FR(t) at time t, and the urination efficiency Neff based on the bladder pressure dynamic change index BP(t) at time t to perform a comprehensive calculation and output the bladder recovery rate index BRI;

[0056] The bladder recovery rate index BRI is calculated and output by the following algorithm formula;

[0057]

[0058] Wherein, O represents the bladder recovery rate constant, ρ represents the amplitude, wt represents the frequency, cos represents the cosine function, ζ represents the sensitivity coefficient for adjusting the bladder recovery rate, and e -Ot represents the exponential decay term;

[0059] Among them, (P0·e -Ot +ρ·cos(wt)) represents the bladder pressure dynamic change index BP(t) at time t.

[0060] Preferably, S52, based on the bladder recovery rate index BRI combined with the comprehensive diagnostic score Pf1, calculate and output the comprehensive dynamic risk score Pf2, and conduct in-depth analysis of bladder emptying function, urinary tract resistance and dynamic characteristics;

[0061] The comprehensive dynamic risk score Pf2 is calculated and output by the following algorithm formula;

[0062]

[0063] Where, θ represents the adjustment coefficient of the average fluid resistance coefficient FRavg;

[0064] S53, based on the output result of the comprehensive dynamic risk score Pf2, a secondary comparative evaluation is performed, and a diagnostic suggestion is generated based on the secondary comparative evaluation result. The specific evaluation contents are as follows;

[0065] When the comprehensive dynamic risk score Pf2>140, it means that the bladder and urinary tract function is normal, and no adjustment is needed at this time;

[0066] When 80≤comprehensive diagnostic score Pf2≤140, it indicates primary abnormality of bladder and urinary tract function, and the first diagnostic suggestion is generated, prompting drug and behavioral intervention;

[0067] When the comprehensive dynamic risk score Pf2 is less than 80, it indicates secondary abnormalities in bladder and urinary tract function. At this time, a second diagnosis recommendation is generated, prompting imaging tests and surgical evaluation.

[0068] Among them, level one abnormality is less than level two abnormality.

[0069] An intelligent processing system for urology diagnosis and treatment data, including a diagnosis and treatment data acquisition module, a diagnosis and treatment processing module, a feature extraction module, a data analysis and diagnosis module, and a depth analysis and optimization evaluation module;

[0070] The diagnosis and treatment data acquisition module uses urology diagnosis and treatment equipment and sensors to monitor urology diagnosis and treatment patients in real time, collects urology diagnosis and treatment data of urology diagnosis and treatment patients in real time, builds a central processing system, and sets a standard interface to transmit the urology diagnosis and treatment data to the central processing system;

[0071] The diagnosis and treatment processing module receives the urology diagnosis and treatment data in real time in the central processing system, pre-processes the urology diagnosis and treatment data to obtain a standardized data set, and at the same time builds a time series database and stores the standardized data set in the time series database;

[0072] The feature extraction module extracts the standardized data set to extract urodynamic features, urine abnormality features and functional index features, and then integrates the feature vectors obtained by the feature extraction to obtain a urology diagnosis and treatment feature set;

[0073] The data analysis and diagnosis module constructs a urinary diagnosis and treatment algorithm model, extracts a urinary diagnosis and treatment feature set and inputs it into the urinary diagnosis and treatment algorithm model, outputs the bladder emptying function index BEI and the urine fluid resistance index FRE respectively, and then comprehensively calculates the bladder emptying function index BEI and the urine fluid resistance index FRE to obtain a comprehensive diagnostic score Pf1;

[0074] Based on the output result of the comprehensive diagnostic score Pf1, a preliminary comparative evaluation is performed to analyze the patient's urinary function status. If the preliminary comparative evaluation shows secondary emptying abnormality, a deep analysis is performed;

[0075] The deep analysis and optimization evaluation module calculates and outputs the bladder recovery rate index BRI through the deep analysis, and calculates and outputs the comprehensive dynamic risk score Pf2 based on the bladder recovery rate index BRI, performs a secondary comparative evaluation based on the output result of the comprehensive dynamic risk score Pf2, and outputs diagnosis and treatment recommendations based on the secondary comparative evaluation results.

[0076] The present invention provides a method and system for intelligent processing of urology diagnosis and treatment data. It has the following beneficial effects:

[0077] (1) This method uses urology diagnosis and treatment equipment and sensors to collect urology diagnosis and treatment data in real time. At the same time, the data sampling rate can reach once every 5 minutes, ensuring high-frequency and comprehensive data coverage. Combined with the central processing system, the collected data is time-standardized, outliers are repaired and normalized, which solves problems such as individual differences among patients, equipment interference, and inconsistent data time series. In addition, through the construction of a time series database, efficient storage and management of data is achieved. This high-precision data collection and processing method significantly improves the accuracy and consistency of diagnostic data, provides a reliable data basis for subsequent feature extraction and evaluation, and reduces the time and cost required for manual data collation and calculation.

[0078] (2) In the process of data feature extraction, this method not only covers urodynamic characteristics such as the average fluid resistance coefficient FRavg and the pressure-flow dynamic integral DPI, but also comprehensively extracts and analyzes the abnormal urine characteristics of urine conductivity change rate ΔUEC and urine suspended particle volume ratio change rate ΔVSP and the functional indicator urination efficiency Neff. By constructing a urological diagnosis and treatment algorithm model, the method further calculates the bladder emptying function index BEI and the urine fluid resistance index FRE, achieving a detailed evaluation of bladder function and urinary tract patency. Based on the comprehensive diagnostic score Pf1, the system can accurately identify primary or secondary emptying abnormalities through hierarchical comparative analysis, and trigger in-depth analysis when necessary. This multi-dimensional dynamic characteristic evaluation method avoids the limitations of traditional single indicator analysis and provides a more comprehensive diagnostic basis for complex diseases such as early bladder dysfunction or urinary tract obstruction.

[0079] (3) This method further calculates the bladder recovery rate index BRI and the comprehensive dynamic risk score Pf2 through a deep analysis module to provide a more in-depth risk assessment for patients with secondary abnormal emptying. For patients with a comprehensive dynamic risk score Pf2>140, the system determines that the bladder and urinary tract function is normal and no adjustment is required; for patients with a comprehensive dynamic risk score Pf2≤80≤14, a first-level abnormality is indicated and medication or behavioral intervention is recommended; and for patients with a comprehensive dynamic risk score Pf2<80, the system generates a second-level abnormality alarm and recommends imaging examinations such as cystoscopy or CT or necessary surgical treatments such as urinary tract unblocking surgery. This intelligent hierarchical assessment and personalized diagnostic recommendations not only reduce overtreatment and waste of resources, but also effectively reduce the risk of misdiagnosis, provide patients with a more optimized treatment path, and improve the efficiency of diagnosis and treatment and the quality of prognosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 A schematic diagram of the steps of an intelligent processing method for urology diagnosis and treatment data of the present invention;

[0081] Figure 2 The figure is a flow chart of an intelligent processing system for urology diagnosis and treatment data according to the present invention. DETAILED DESCRIPTION

[0082] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0083] Example 1

[0084] See also Figure 1 The present invention provides an intelligent processing method for urology diagnosis and treatment data. To achieve the above purpose, the present invention is implemented through the following technical scheme: comprising the following steps:

[0085] S1. Use urology diagnosis and treatment equipment and sensors to monitor urology diagnosis and treatment patients in real time, collect urology diagnosis and treatment data of urology diagnosis and treatment patients in real time, build a central processing system, and set up a standard interface to transmit the urology diagnosis and treatment data to the central processing system;

[0086] S2. Receive urology diagnosis and treatment data in real time in the central processing system, pre-process the urology diagnosis and treatment data to obtain a standardized data set, and at the same time build a time series database and store the standardized data set in the time series database;

[0087] S3, extracting standardized data sets, extracting urodynamic features, urine abnormality features and functional index features, and then integrating the feature vectors obtained by feature extraction to obtain a urology diagnosis and treatment feature set;

[0088] S4, constructing a urinary diagnosis and treatment algorithm model, extracting the urinary diagnosis and treatment feature set and inputting it into the urinary diagnosis and treatment algorithm model, respectively outputting the bladder emptying function index BEI and the urine fluid resistance index FRE, and then comprehensively calculating the bladder emptying function index BEI and the urine fluid resistance index FRE to obtain a comprehensive diagnostic score Pf1;

[0089] Based on the output results of the comprehensive diagnostic score Pf1, a preliminary comparative evaluation is performed to analyze the patient's urinary function status. If the preliminary comparative evaluation shows secondary emptying abnormalities, a deep analysis is performed;

[0090] S5. In-depth analysis is performed by calculating and outputting the bladder recovery rate index BRI, and based on the bladder recovery rate index BRI, calculating and outputting the comprehensive dynamic risk score Pf2, and based on the output result of the comprehensive dynamic risk score Pf2, a secondary comparative evaluation is performed, and diagnosis and treatment recommendations are output based on the secondary comparative evaluation result.

[0091] In this embodiment, the method constructs a complete system from data collection to intelligent diagnosis and treatment suggestion output through five interlocking steps, realizing the efficiency and precision of the diagnosis and treatment process. First, by using flow meters, conductivity sensors, optical particle size analyzers, pressure sensors and other equipment, urology diagnosis and treatment data is collected in real time, and the data is transmitted and centrally managed in real time through the central processing system, overcoming the problems of discrete data collection and time series asynchrony in traditional methods. Secondly, the central processing system performs time standardization, outlier repair and normalization on the data to generate a high-quality standardized data set, and efficiently stores and manages the data through a time series database, providing a structured and reliable data foundation for subsequent analysis. In the feature extraction stage, the method integrates and forms a urology diagnosis and treatment feature set by deeply analyzing the urodynamic characteristics, abnormal urine characteristics and functional indicators, which significantly enhances the comprehensiveness of the evaluation of bladder emptying function and urinary tract patency. The diagnosis and treatment algorithm model constructed based on the feature set further calculates the bladder emptying function index BEI and the urine fluid resistance index FRE, and generates a comprehensive diagnostic score Pf1, which realizes the quantitative evaluation of the patient's urinary function status and the preliminary identification of primary abnormalities. When the system detects secondary emptying abnormalities, the deep analysis module calculates the bladder recovery rate index BRI and generates a comprehensive dynamic risk score Pf2, providing accurate stratified diagnosis and personalized treatment recommendations for complex cases through secondary evaluation. Compared with traditional urology diagnosis and treatment methods, this method solves the problems of data consistency and single analysis dimension through real-time data collection and intelligent processing; by establishing a dynamic scoring and risk assessment mechanism, it makes up for the lack of early identification and risk stratification of complex cases.

[0092] Example 2

[0093] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: S1 includes S11 and S12;

[0094] S11. Use urology diagnosis and treatment equipment and sensors to monitor urology diagnosis and treatment patients in real time, and set the sampling rate of the urology diagnosis and treatment equipment and sensors to 5 minutes / time, so as to collect urology diagnosis and treatment data of urology diagnosis and treatment patients in real time;

[0095] Urological diagnostic equipment and sensors include flow meters, conductivity sensors, optical particle size analyzers, fluid resistance sensors, time-stamp sensors, and portable bladder scanners;

[0096] Urology diagnosis and treatment data include urine flow rate UFR, urine conductivity UEC, urine suspended particle volume ratio VSP, fluid resistance coefficient FR, urine outflow time UOT and residual urine ratio RUR;

[0097] Urine flow rate UFR and urine conductivity UEC are collected and acquired in real time through a flow meter and conductivity sensor installed in the urine outflow channel;

[0098] The urine suspended particle volume ratio (VSP) uses an optical particle size analyzer combined with an image processing algorithm to quantify the particles in the urine sample, indicating whether there are stones, bacteria or abnormal sediments in the urine;

[0099] The fluid resistance coefficient FR is measured in real time by embedding a pressure sensor in the urinary tract to measure the pressure changes when the fluid passes through;

[0100] The urine outflow time UOT starts the timer when the urine starts to flow through the time mark sensor. When the flow returns to zero, the timer is stopped and the urine outflow time UOT value is output;

[0101] The residual urine ratio (RUR) is obtained by measuring the volume of urine remaining in the bladder using ultrasound equipment immediately after urination and comparing it with the total urine output;

[0102] S12. Build a central processing system and set up a standard communication interface USB to connect the OCR image scanning device to the central processing system by wire, and transmit the collected urology diagnosis and treatment data to the central processing system.

[0103] In this embodiment, the method realizes the real-time collection and transmission of urology diagnosis and treatment data through the efficient collaboration of urology diagnosis and treatment equipment and sensors in the intelligent processing method of urology diagnosis and treatment data, providing a solid foundation for subsequent diagnosis and treatment. In S11, devices such as flowmeter, conductivity sensor, optical particle size analyzer, pressure sensor, time stamp sensor and portable bladder scanner collect data in real time at a sampling frequency of 5 minutes / time, solving the problem of data dispersion and discontinuity in traditional collection methods. Combining the image processing algorithm of the optical particle size analyzer with the data acquisition of the ultrasonic device, the method significantly improves the accuracy and consistency of diagnosis and treatment data. The data transmission path is further optimized through the construction of the central processing system and the setting of the standard communication interface, and the collected multi-dimensional diagnosis and treatment data is centrally managed, providing an efficient and unified platform for subsequent processing and analysis. This method has not only made significant breakthroughs in real-time and data accuracy, but also overcomes the limitations of the single data dimension of traditional equipment through multi-sensor collaboration, and expands the breadth and depth of diagnosis and treatment data. In addition, the introduction of the central processing system and the application of the USB standard interface simplify the data transmission process, eliminate cross-device compatibility issues, and improve the stability and scalability of the system.

[0104] Example 3

[0105] This embodiment is explained in Example 2. Please refer to Figure 1 , specifically: S2 includes S21 and S22;

[0106] S21. Receive urology diagnosis and treatment data in real time in the central processing system, and preprocess the urology diagnosis and treatment data, wherein the preprocessing includes time standardization, outlier detection and repair, and normalization, to obtain a standardized data set;

[0107] The standardized data set includes urine flow rate UFR(t) at time t, urine conductivity UEC(t) at time t, urine suspended particle volume ratio VSP(t) at time t, fluid resistance coefficient FR(t) at time t, urine outflow time UOT(t) and residual urine ratio RUR(t) at time t

[0108] Time standardization processing uses linear interpolation to time standardize the data when the examination time series of different patient cases are inconsistent;

[0109] Outlier detection and repair: Outliers in urology diagnosis and treatment data are detected based on Mahalanobis distance and repaired using Bessel interpolation;

[0110] Normalization and standardization processing uses Z-Score standardization method to eliminate the influence of different dimensions of urology diagnosis and treatment data;

[0111] S22. Build a time series database in the central processing system and set a transmission port. Write the standardized data set into the time series database through the transmission port and sort and store it according to the inspection time series.

[0112] In this embodiment, the method greatly improves the data quality and management efficiency by comprehensively preprocessing and constructing a time series database for the diagnosis and treatment data received in real time. The central processing system generates a high-quality standardized data set through time standardization, outlier detection and repair, and normalization and standardization. The inconsistent examination time series of different patients are unified by linear interpolation, the Mahalanobis distance method is used to identify data anomalies and combined with the Bessel interpolation method to repair, ensuring the integrity and accuracy of the data; at the same time, the Z-Score standardization method is used to eliminate dimensional differences and improve the reliability of data analysis. The central processing system constructs a time series database, efficiently writes the standardized data set through the transmission port, and stores it in order according to the inspection time series, laying a solid foundation for subsequent data extraction and analysis. This method significantly optimizes the data preprocessing process and solves the problem of analysis deviation caused by inconsistent time series, outlier interference and inconsistent dimensions in previous diagnosis and treatment data. At the same time, the time series database is constructed in real time by the central processing system, the data management mode is improved, the efficient storage and sequential retrieval of data are realized, and the limitations of discrete and difficult to track data in traditional methods are overcome.

[0113] Example 4

[0114] This embodiment is explained in Example 3, please refer to Figure 1 , specifically: S3 includes S31, S32 and S33;

[0115] S31, extracting the urine flow rate UFR(t) at time t and the fluid resistance coefficient FR(t) at time t in the real-time standardized data set from the time series database through the transmission port, extracting urodynamic characteristics, and obtaining the average fluid resistance coefficient FRavg and the pressure flow rate dynamic integral DPI;

[0116] The average fluid resistance coefficient FRavg and the pressure flow rate dynamic integral DPI are calculated and output by the following algorithm formula;

[0117]

[0118] Where T represents the total sampling time, αt 2 It represents the nonlinear correction term of time, describing the gradual change of fluid resistance with the extension of urination time, reflecting the possible resistance peak and increasing trend. β represents the sensitivity coefficient of bladder pressure to urine flow rate, which is used to reflect the sensitivity of bladder pressure to urine flow rate and adjust the coupling relationship between bladder power and flow rate. dt represents the time calculus variable.

[0119] The average fluid resistance coefficient FRavg is used to reflect the change in resistance encountered by urine when it flows through the urinary tract and to evaluate the patency of the urinary tract;

[0120] The dynamic pressure-flow integral (DPI) is used to assess the bladder's ability to respond to changes in flow rate and whether there are abnormal characteristics in urine flow rate.

[0121] S32, extracting the urine conductivity UEC(t) at time t and the urine suspended particle volume ratio VSP(t) at time t in the real-time standardized data set in the time series database through the transmission port, extracting abnormal urine characteristics, and obtaining the change rate △UEC of the urine conductivity and the change rate △VSP of the urine suspended particle volume ratio;

[0122] The change rate of urine conductivity △UEC and the change rate of urine suspended particle volume ratio △VSP are calculated and output by the following algorithm formula;

[0123]

[0124] In the formula, UEC i (t) represents the urine conductivity at time t collected for the i-th time, represents the mean value of urine conductivity, γ represents the weight coefficient of the extreme value product part, which is used to control the contribution of the maximum value and the minimum value product to the total fluctuation complexity, max(UEC) represents the upper limit of urine conductivity, min(UEC) represents the lower limit of urine conductivity, and n represents the total number of sampling times;

[0125] VSPend represents the volume ratio of urine suspended particles at the end of urination, VSPstart represents the volume ratio of urine suspended particles at the start of urination, δ represents the weight coefficient of the square term of particle concentration, and Td represents the total duration of urination;

[0126] The rate of change of urine conductivity △UEC is used to reflect the dynamic changes of ion concentration in urine and help identify metabolic disorders or urinary tract infections;

[0127] The change rate of the volume ratio of urine suspended particles, △VSP, is used to reflect the dynamic distribution of suspended particles such as cells, crystals or bacteria in urine, helping to identify stones, infections or sediment-related diseases;

[0128] S33, extracting the urine flow rate UFR(t) and urine outflow time UOT at time t in the real-time standardized data set from the time series database through the transmission port, extracting functional indicator features, and obtaining the urination efficiency Neff;

[0129] The urination efficiency Neff is calculated and output by the following algorithm formula;

[0130]

[0131] In the formula, ZPN represents the total urine output, and ε represents the weight coefficient for compensating the influence of low flow rate;

[0132] The obtained average fluid resistance coefficient FRavg, pressure flow rate dynamic integral DPI, urine conductivity change rate △UEC, urine suspended particle volume ratio change rate △VSP and urination efficiency Neff are then integrated to obtain the urinary diagnosis and treatment feature set.

[0133] In this embodiment, the method comprehensively constructs a urinary diagnosis and treatment feature set by extracting urodynamic features, abnormal urine features and functional index features, and realizes a multi-dimensional evaluation of bladder function and urinary tract status. The urine flow rate UFR(t) and fluid resistance coefficient FR(t) in the time series database are used to calculate the average fluid resistance coefficient FRavg and the pressure flow rate dynamic integral DPI, which effectively reflects the resistance change when urine flows through the urinary tract and the bladder's ability to respond to flow rate changes, and provides a dynamic evaluation of urinary tract patency and bladder dynamics. Based on urine conductivity UEC(t) and urine suspended particle volume ratio VSP(t), the urine conductivity change rate ΔUEC and the urine suspended particle volume ratio change rate ΔVSP are calculated respectively to evaluate the dynamic change characteristics of ion concentration and particles in urine, and help identify metabolic disorders, infections, stones and other diseases. The urination efficiency Neff is calculated by urine flow rate UFR(t) and urine outflow time UOT, and the bladder emptying capacity is accurately quantified. This method can not only capture dynamic characteristics such as time-related flow rate and resistance changes and abnormal characteristics such as urine composition fluctuations, but also realize a multi-level comprehensive evaluation of bladder emptying function and urinary tract patency. At the same time, based on real-time standardized data sets and efficient algorithms, it solves the problems of insufficient dynamic feature analysis and incomplete data dimensions in traditional technologies, and provides a more detailed and accurate basis for diagnosis.

[0134] Example 5

[0135] This embodiment is explained in Example 4. Please refer to Figure 1 , specifically: S4 includes S41, S42 and S43;

[0136] S41, by constructing a urinary diagnosis and treatment algorithm model, extracting a urinary diagnosis and treatment feature set, and inputting it into the urinary diagnosis and treatment algorithm model, respectively calculating and outputting a bladder emptying function index BEI and a urine fluid resistance index FRE, respectively analyzing the bladder emptying function and urinary tract patency;

[0137] The bladder emptying function index BEI and urine fluid resistance index FRE are calculated and output by the following algorithm formula;

[0138]

[0139] Wherein, e represents an exponential function, k represents the adjustment coefficient of the negative impact of residual urine ratio on bladder emptying, λ represents the importance weight coefficient of the fluid resistance peak, and max(FR(t)) represents the peak value of the fluid resistance coefficient FR(t) at time t.

[0140] S42, based on the obtained bladder emptying function index BEI and urine fluid resistance index FRE, combined with the pressure flow rate dynamic integral DPI and the change rate of urine conductivity △UEC, a comprehensive diagnostic score Pf1 is comprehensively calculated and output to comprehensively analyze the diagnosis of the patient's urinary diagnosis and treatment data;

[0141] The comprehensive diagnostic score Pf1 is calculated and output by the following algorithm formula;

[0142]

[0143] In the formula, ln represents the logarithmic function, ln(1+DPI) represents the logarithmic correction of the dynamic integral of pressure and flow rate, and the logarithmic transformation is used to smooth the numerical distribution of the dynamic integral to avoid excessive influence of large values ​​on the total score. It represents the comprehensive penalty term of fluctuation and resistance. The square root of the sum of squares is taken to couple the comprehensive effects of conductivity fluctuation and fluid resistance on bladder function.

[0144] S43. Based on the output result of the comprehensive diagnostic score Pf1, a preliminary comparative evaluation is performed to analyze the bladder function in the diagnosis and treatment data of urinary patients, and a grade classification is performed based on the evaluation results. The specific evaluation contents are as follows;

[0145] When the comprehensive diagnostic score Pf1>120, it means that the emptying function is normal and the urinary tract is unobstructed, and no intervention is required at this time;

[0146] When 60≤comprehensive diagnostic score Pf1≤120, a first-level abnormal emptying prompt is generated, and continuous observation is required;

[0147] When the comprehensive diagnostic score Pf1 is less than 60, a secondary emptying abnormality prompt is generated, and in-depth analysis is performed at this time;

[0148] Among them, the first-level emptying abnormality is less than the second-level emptying abnormality.

[0149] In this embodiment, the method realizes a comprehensive and quantitative evaluation of bladder function and urinary tract patency by constructing a diagnosis and treatment algorithm model and calculating multidimensional diagnostic indicators. The urinary diagnosis and treatment feature set is then used to input the algorithm model, and the bladder emptying function index BEI and the urine fluid resistance index FRE are output respectively to evaluate the bladder emptying capacity and urinary tract patency respectively. Among them, the bladder emptying function index BEI corrects the adverse effect of the residual urine ratio on bladder emptying through an exponential function, and FRE refines the analysis of the dynamic characteristics of urinary tract resistance by introducing the weight of the fluid resistance peak. At the same time, by comprehensively analyzing the bladder emptying function index BEI, the urine fluid resistance index FRE, the pressure flow dynamic integral DPI and the urine conductivity change rate ΔUEC, the comprehensive diagnostic score Pf1 is calculated, and the bladder function and urinary tract patency are integrated into a global quantitative indicator, which effectively avoids the limitations of single parameter evaluation. According to the scoring results of the comprehensive diagnostic score Pf1, the patient's status is divided into normal, primary emptying abnormality and secondary emptying abnormality, and targeted intervention suggestions or triggering in-depth analysis are provided. This method quantifies multidimensional features into global scores by constructing a urology diagnosis and treatment algorithm model, significantly improving the accuracy and comprehensiveness of diagnosis. Through multi-index fusion evaluation, it can not only capture the dynamic changes of bladder function and urinary tract resistance, but also effectively overcome the problem of insufficient identification of complex cases in traditional technologies. In particular, through the hierarchical evaluation of the comprehensive diagnostic score Pf1, it can achieve early identification of mild abnormalities and accurate classification of severe abnormalities, providing a scientific basis for personalized intervention and further in-depth analysis.

[0150] Example 6

[0151] This embodiment is explained in Example 5. Please refer to Figure 1 , specifically: S5 includes S51, S52 and S53;

[0152] S51. When the secondary emptying abnormality is found in the preliminary comparison and evaluation, a deep analysis is performed. The deep analysis uses the intra-bladder pressure sensor to detect the initial bladder pressure P0, calculates and outputs the bladder pressure dynamic change index BP(t) at time t, and then combines the pressure flow rate dynamic integral DPI, the fluid resistance coefficient FR(t) at time t, and the urination efficiency Neff based on the bladder pressure dynamic change index BP(t) at time t to perform a comprehensive calculation and output the bladder recovery rate index BRI;

[0153] The bladder recovery rate index (BRI) is calculated and output by the following algorithm formula:

[0154]

[0155] Where O represents the bladder recovery rate constant, ρ represents the amplitude, which represents the intensity of pressure fluctuation during bladder recovery, wt represents the frequency, which reflects the periodic characteristics of bladder muscle activity, cos represents the cosine function, ζ represents the sensitivity coefficient for adjusting the bladder recovery rate, and e -Ot represents the exponential decay term, describing how quickly the bladder pressure returns to normal levels;

[0156] Among them, (P0·e -Ot +ρ·cos(wt)) represents the bladder pressure dynamic change index BP(t) at time t.

[0157] S52, based on the bladder recovery rate index BRI combined with the comprehensive diagnostic score Pf1, calculate and output the comprehensive dynamic risk score Pf2, and conduct in-depth analysis of bladder emptying function, urinary tract resistance and dynamic characteristics;

[0158] The comprehensive dynamic risk score Pf2 is calculated and output by the following algorithm formula;

[0159]

[0160] Where, θ represents the adjustment coefficient of the average fluid resistance coefficient FRavg;

[0161] S53. Based on the output result of the comprehensive dynamic risk score Pf2, a secondary comparative evaluation is performed, and a diagnostic suggestion is generated based on the secondary comparative evaluation result. The specific evaluation contents are as follows;

[0162] When the comprehensive dynamic risk score Pf2>140, it means that the bladder and urinary tract function is normal, and no adjustment is needed at this time;

[0163] When the comprehensive diagnostic score Pf2 is 80≤≤140, it indicates that the bladder and urinary tract function is abnormal at the first level, indicating that the bladder recovery is slow or the urinary tract resistance is slightly high, and there may be slight functional disorders. At this time, the first diagnostic suggestion is generated, prompting drug and behavioral intervention;

[0164] When the comprehensive dynamic risk score Pf2 is less than 80, it indicates secondary abnormalities in bladder and urinary tract function, indicating a significant decrease in bladder recovery ability or abnormally high urinary tract resistance. At this time, a second diagnosis recommendation is generated, prompting imaging tests and surgical evaluations, such as cystoscopy, CT, and urinary tract unblocking surgery.

[0165] Among them, level one abnormality is less than level two abnormality.

[0166] In this embodiment, the method further evaluates patients with secondary emptying abnormalities through a deep analysis module, and realizes the generation of accurate diagnosis and personalized treatment recommendations. The initial bladder pressure P0 is detected in real time using an intra-bladder pressure sensor, and the bladder recovery rate index BRI is calculated by combining the bladder pressure dynamic change index BP(t), the pressure flow rate dynamic integral DPI, the fluid resistance coefficient FR(t) at time t, and the urination efficiency Neff to comprehensively evaluate the pressure recovery ability and dynamic characteristics of the bladder. The bladder recovery rate index BRI is then combined with the comprehensive diagnostic score Pf1 to further calculate the comprehensive dynamic risk score Pf2 to achieve a deep analysis of bladder emptying function, urinary tract resistance and dynamic characteristics. According to the scoring results of the comprehensive dynamic risk score Pf2, the patient's status is divided into normal function, primary abnormality, and secondary abnormality, and targeted diagnostic recommendations are generated, including personalized treatment plans such as drug or behavioral intervention and imaging examination or surgical evaluation. This step significantly improves the diagnostic accuracy and risk stratification capabilities of complex cases by introducing the bladder recovery rate index BRI and the comprehensive dynamic risk score Pf2. Traditional methods usually rely on static or single indicators for diagnosis, which cannot fully capture the changes in bladder pressure recovery and urinary tract dynamic characteristics. This method can more accurately identify bladder dysfunction and subtle changes in urinary tract resistance through multi-dimensional parameter fusion analysis and dynamic scoring models, especially for early and complex cases. In addition, the hierarchical diagnostic logic further optimizes the diagnosis and treatment process, provides targeted interventions for patients with different conditions, reduces the incidence of misdiagnosis and missed diagnosis, and improves the utilization efficiency of medical resources.

[0167] Example 7

[0168] See also Figure 1 and Figure 2 , an intelligent processing system for urology diagnosis and treatment data, including a diagnosis and treatment data acquisition module, a diagnosis and treatment processing module, a feature extraction module, a data analysis and diagnosis module, and a depth analysis and optimization evaluation module;

[0169] The diagnosis and treatment data acquisition module uses urology diagnosis and treatment equipment and sensors to monitor urology diagnosis and treatment patients in real time, collects urology diagnosis and treatment data of urology diagnosis and treatment patients in real time, builds a central processing system, and sets up a standard interface to transmit urology diagnosis and treatment data to the central processing system;

[0170] The diagnosis and treatment processing module receives the urology diagnosis and treatment data in real time in the central processing system, pre-processes the urology diagnosis and treatment data to obtain a standardized data set, and at the same time builds a time series database and stores the standardized data set in the time series database;

[0171] The feature extraction module extracts standardized data sets to extract urodynamic features, urine abnormality features, and functional index features, and then integrates the feature vectors obtained by feature extraction to obtain a urology diagnosis and treatment feature set;

[0172] The data analysis and diagnosis module constructs a urinary diagnosis and treatment algorithm model, extracts the urinary diagnosis and treatment feature set and inputs it into the urinary diagnosis and treatment algorithm model, outputs the bladder emptying function index BEI and the urine fluid resistance index FRE respectively, and then comprehensively calculates the bladder emptying function index BEI and the urine fluid resistance index FRE to obtain the comprehensive diagnostic score Pf1;

[0173] Based on the output results of the comprehensive diagnostic score Pf1, a preliminary comparative evaluation is performed to analyze the patient's urinary function status. If the preliminary comparative evaluation shows secondary emptying abnormalities, a deep analysis is performed;

[0174] The deep analysis and optimization evaluation module calculates and outputs the bladder recovery rate index BRI through deep analysis, and calculates and outputs the comprehensive dynamic risk score Pf2 based on the bladder recovery rate index BRI. Based on the output results of the comprehensive dynamic risk score Pf2, a secondary comparative evaluation is performed, and diagnosis and treatment recommendations are output based on the secondary comparative evaluation results.

[0175] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. An intelligent processing method for urology diagnosis and treatment data, characterized by: The following steps are involved: S1. Use urology diagnosis and treatment equipment and sensors to monitor urology diagnosis and treatment patients in real time, collect urology diagnosis and treatment data of urology diagnosis and treatment patients in real time, build a central processing system, and set a standard interface to transmit the urology diagnosis and treatment data to the central processing system; S2. Receive urology diagnosis and treatment data in real time in the central processing system, pre-process the urology diagnosis and treatment data to obtain a standardized data set, and at the same time build a time series database and store the standardized data set in the time series database; S3, extracting the standardized data set, performing urodynamic feature extraction, urine abnormality feature extraction and functional index feature extraction, and then integrating the feature vectors obtained by the feature extraction to obtain a urology diagnosis and treatment feature set; S4, constructing a urinary diagnosis and treatment algorithm model, extracting a urinary diagnosis and treatment feature set and inputting it into the urinary diagnosis and treatment algorithm model, respectively outputting the bladder emptying function index BEI and the urine fluid resistance index FRE, and then comprehensively calculating the bladder emptying function index BEI and the urine fluid resistance index FRE to obtain a comprehensive diagnostic score Pf1, and based on the output result of the comprehensive diagnostic score Pf1, performing a preliminary comparative evaluation and analysis of the patient's urinary function status, and performing a deep analysis if the preliminary comparative evaluation shows secondary emptying abnormality; S5. The in-depth analysis outputs the bladder recovery rate index BRI by calculation, and outputs the comprehensive dynamic risk score Pf2 based on the bladder recovery rate index BRI. A secondary comparative evaluation is performed based on the output result of the comprehensive dynamic risk score Pf2, and a diagnosis and treatment recommendation is output based on the secondary comparative evaluation result.

2. The intelligent processing method for urology diagnosis and treatment data according to claim 1, characterized in that: Said S1 includes S11 and S12; S11. Use urology diagnosis and treatment equipment and sensors to monitor urology diagnosis and treatment patients in real time, and set the sampling rate of the urology diagnosis and treatment equipment and sensors to 5 minutes / time, so as to collect urology diagnosis and treatment data of urology diagnosis and treatment patients in real time; The urological diagnosis and treatment equipment and sensors include a flow meter, a conductivity sensor, an optical particle size analyzer, a fluid resistance sensor, a time stamp sensor, and a portable bladder scanner; The urology diagnosis and treatment data include urine flow rate UFR, urine conductivity UEC, urine suspended particle volume ratio VSP, fluid resistance coefficient FR, urine outflow time UOT and residual urine ratio RUR; S12. Build a central processing system and set up a standard communication interface USB to connect the OCR image scanning device to the central processing system by wire, and transmit the collected urology diagnosis and treatment data to the central processing system.

3. The intelligent processing method for urology diagnosis and treatment data according to claim 2 is characterized by: The S2 includes S21 and S22; S21, receiving urology diagnosis and treatment data in real time in a central processing system, and preprocessing the urology diagnosis and treatment data, wherein the preprocessing includes time standardization processing, outlier detection and repair, and normalization processing to obtain a standardized data set; The standardized data set includes urine flow rate UFR(t) at time t, urine conductivity UEC(t) at time t, urine suspended particle volume ratio VSP(t) at time t, fluid resistance coefficient FR(t) at time t, urine outflow time UOT(t) and residual urine ratio RUR(t) at time t The time standardization process uses linear interpolation to perform time standardization on the data when the examination time series of different patient cases are inconsistent; The outlier detection and repair is performed by detecting outliers in the urology diagnosis and treatment data based on the Mahalanobis distance and repairing them using the Bessel interpolation method; The normalization and standardization process uses the Z-Score standardization method to eliminate the influence of different dimensions of the urology diagnosis and treatment data; S22. Construct a time series database in the central processing system and set a transmission port. Write the standardized data set into the time series database through the transmission port and sort and store it according to the inspection time series.

4. The intelligent processing method for urology diagnosis and treatment data according to claim 3 is characterized by: The S3 includes S31, S32 and S33; S31, extracting the urine flow rate UFR(t) at time t and the fluid resistance coefficient FR(t) at time t in the real-time standardized data set from the time series database through the transmission port, extracting urodynamic characteristics, and obtaining the average fluid resistance coefficient FRavg and the pressure flow rate dynamic integral DPI; The average fluid resistance coefficient FRavg and the pressure flow rate dynamic integral DPI are calculated and output by the following algorithm formula; Where T represents the total sampling time, αt 2 represents the nonlinear correction term of time, β represents the sensitivity coefficient of bladder pressure to urine flow rate, and dt represents the time calculus variable.

5. The intelligent processing method for urology diagnosis and treatment data according to claim 4 is characterized by: S32, extracting the urine conductivity UEC(t) at time t and the urine suspended particle volume ratio VSP(t) at time t in the real-time standardized data set in the time series database through the transmission port, extracting abnormal urine characteristics, and obtaining the change rate △UEC of the urine conductivity and the change rate △VSP of the urine suspended particle volume ratio; The change rate of urine conductivity △UEC and the change rate of urine suspended particle volume ratio △VSP are calculated and outputted by the following algorithm formula; In the formula, UEC i (t) represents the urine conductivity at time t collected for the i-th time, represents the mean value of urine conductivity, γ represents the weight coefficient of the extreme value product part, max(UEC) represents the upper limit of urine conductivity, min(UEC) represents the lower limit of urine conductivity, and n represents the total number of sampling times; VSPend represents the volume ratio of urine suspended particles at the end of urination, VSPstart represents the volume ratio of urine suspended particles at the start of urination, δ represents the weight coefficient of the square term of particle concentration, and Td represents the total duration of urination; S33, extracting the urine flow rate UFR(t) and urine outflow time UOT at time t in the real-time standardized data set from the time series database through the transmission port, extracting functional indicator features, and obtaining the urination efficiency Neff; The urination efficiency Neff is calculated and outputted by the following algorithm formula; In the formula, ZPN represents the total urine output, and ε represents the weight coefficient for compensating the influence of low flow rate; The obtained average fluid resistance coefficient FRavg, pressure flow rate dynamic integral DPI, urine conductivity change rate △UEC, urine suspended particle volume ratio change rate △VSP and urination efficiency Neff are then integrated to obtain the urinary diagnosis and treatment feature set.

6. The intelligent processing method for urology diagnosis and treatment data according to claim 5, characterized in that: The S4 includes S41, S42 and S43; S41, by constructing a urinary diagnosis and treatment algorithm model, extracting a urinary diagnosis and treatment feature set, and inputting it into the urinary diagnosis and treatment algorithm model, respectively calculating and outputting a bladder emptying function index BEI and a urine fluid resistance index FRE, respectively analyzing the bladder emptying function and urinary tract patency; The bladder emptying function index BEI and urine fluid resistance index FRE are calculated and outputted by the following algorithm formula; Wherein, e represents an exponential function, k represents the adjustment coefficient of the negative impact of residual urine ratio on bladder emptying, λ represents the importance weight coefficient of the fluid resistance peak, and max(FR(t)) represents the peak value of the fluid resistance coefficient FR(t) at time t.

7. The intelligent processing method for urology diagnosis and treatment data according to claim 6, characterized in that: S42, based on the obtained bladder emptying function index BEI and urine fluid resistance index FRE, combined with the pressure flow rate dynamic integral DPI and the change rate of urine conductivity △UEC, a comprehensive diagnostic score Pf1 is comprehensively calculated and output to comprehensively analyze the diagnosis of the patient's urinary diagnosis and treatment data; The comprehensive diagnostic score Pf1 is calculated and output by the following algorithm formula; In the formula, ln represents the logarithmic function, ln(1+DPI) represents the logarithmic correction of the dynamic integral of pressure and flow rate, Represents the combined penalty term of volatility and resistance; S43, based on the output result of the comprehensive diagnostic score Pf1, a preliminary comparative evaluation is performed to analyze the bladder function in the diagnosis and treatment data of urinary patients, and a grade classification is performed based on the evaluation results. The specific evaluation contents are as follows; When the comprehensive diagnostic score Pf1>120, it means that the emptying function is normal and the urinary tract is unobstructed, and no intervention is required at this time; When 60≤comprehensive diagnostic score Pf1≤120, a first-level abnormal emptying prompt is generated, and continuous observation is required; When the comprehensive diagnostic score Pf1 is less than 60, a secondary emptying abnormality prompt is generated, and in-depth analysis is performed at this time; Among them, the first-level emptying abnormality is less than the second-level emptying abnormality.

8. The intelligent processing method for urology diagnosis and treatment data according to claim 7, characterized in that: The S5 includes S51, S52 and S53; S51. When the secondary emptying abnormality is found in the preliminary comparison and evaluation, a deep analysis is performed. The deep analysis is performed by using an intra-bladder pressure sensor to detect the initial bladder pressure P0, calculate and output the bladder pressure dynamic change index BP(t) at time t, and then combine the pressure flow rate dynamic integral DPI, the fluid resistance coefficient FR(t) at time t, and the urination efficiency Neff based on the bladder pressure dynamic change index BP(t) at time t to perform a comprehensive calculation and output the bladder recovery rate index BRI; The bladder recovery rate index BRI is calculated and output by the following algorithm formula; Wherein, O represents the bladder recovery rate constant, ρ represents the amplitude, wt represents the frequency, cos represents the cosine function, ζ represents the sensitivity coefficient for adjusting the bladder recovery rate, and e -Ot represents the exponential decay term; Among them, (P0·e -Ot +ρ·cos(wt)) represents the bladder pressure dynamic change index BP(t) at time t.

9. The intelligent processing method for urology diagnosis and treatment data according to claim 8, characterized in that: S52, based on the bladder recovery rate index BRI combined with the comprehensive diagnostic score Pf1, calculate and output the comprehensive dynamic risk score Pf2, and conduct in-depth analysis of bladder emptying function, urinary tract resistance and dynamic characteristics; The comprehensive dynamic risk score Pf2 is calculated and output by the following algorithm formula; Where, θ represents the adjustment coefficient of the average fluid resistance coefficient FRavg; S53, based on the output result of the comprehensive dynamic risk score Pf2, a secondary comparative evaluation is performed, and a diagnostic suggestion is generated based on the secondary comparative evaluation result. The specific evaluation contents are as follows; When the comprehensive dynamic risk score Pf2>140, it means that the bladder and urinary tract function is normal, and no adjustment is needed at this time; When 80≤comprehensive diagnostic score Pf2≤140, it indicates primary abnormality of bladder and urinary tract function, and the first diagnostic suggestion is generated, prompting drug and behavioral intervention; When the comprehensive dynamic risk score Pf2 is less than 80, it indicates secondary abnormalities in bladder and urinary tract function. At this time, a second diagnosis recommendation is generated, prompting imaging tests and surgical evaluation. Among them, level one abnormality is less than level two abnormality.

10. An intelligent processing system for urology diagnosis and treatment data, applied to an intelligent processing method for urology diagnosis and treatment data according to any one of claims 1 to 9, characterized in that: It includes diagnosis and treatment data acquisition module, diagnosis and treatment processing module, feature extraction module, data analysis and diagnosis module and in-depth analysis and optimization evaluation module; The diagnosis and treatment data acquisition module uses urology diagnosis and treatment equipment and sensors to monitor urology diagnosis and treatment patients in real time, collects urology diagnosis and treatment data of urology diagnosis and treatment patients in real time, builds a central processing system, and sets a standard interface to transmit the urology diagnosis and treatment data to the central processing system; The diagnosis and treatment processing module receives the urology diagnosis and treatment data in real time in the central processing system, pre-processes the urology diagnosis and treatment data to obtain a standardized data set, and at the same time builds a time series database and stores the standardized data set in the time series database; The feature extraction module extracts the standardized data set to extract urodynamic features, urine abnormality features and functional index features, and then integrates the feature vectors obtained by the feature extraction to obtain a urology diagnosis and treatment feature set; The data analysis and diagnosis module constructs a urinary diagnosis and treatment algorithm model, extracts a urinary diagnosis and treatment feature set and inputs it into the urinary diagnosis and treatment algorithm model, outputs the bladder emptying function index BEI and the urine fluid resistance index FRE respectively, and then comprehensively calculates the bladder emptying function index BEI and the urine fluid resistance index FRE to obtain a comprehensive diagnostic score Pf1; Based on the output result of the comprehensive diagnostic score Pf1, a preliminary comparative evaluation is performed to analyze the patient's urinary function status. If the preliminary comparative evaluation shows secondary emptying abnormality, a deep analysis is performed; The deep analysis and optimization evaluation module calculates and outputs the bladder recovery rate index BRI through the deep analysis, and calculates and outputs the comprehensive dynamic risk score Pf2 based on the bladder recovery rate index BRI, performs a secondary comparative evaluation based on the output result of the comprehensive dynamic risk score Pf2, and outputs diagnosis and treatment recommendations based on the secondary comparative evaluation results.

Images