A system for managing and evaluating clinical rehabilitation data for a patient with rhabdomyolysis

Abstract

The application provides a clinical rehabilitation data management and evaluation system for rhabdomyolysis patients, and relates to a medical information management system.The system comprises an index acquisition module, a rate detection module, a curvature analysis module, a node identification module and a trend construction module.In the application, the rate difference sequence of creatine kinase and myoglobin and the curvature sequence of urine sodium and blood creatinine are combined to break through the limitations of traditional single-parameter static analysis, realize dynamic capture of multi-index collaborative trend, construct a joint evolution label system by combining the consistency discrimination of creatine kinase and blood potassium concentration change direction, accurately locate the multi-system interaction risk nodes, and statistically distribute the direction consistency proportion of myoglobin and blood creatinine in the correlation period, so as to convert the discrete parameter correlation into a dynamic visual model.The method solves the problems of data dispersion misjudgment and collaborative evolution mode fragmentation in the traditional technology, and provides a multi-dimensional dynamic evaluation framework for the rhabdomyolysis rehabilitation process in clinical practice.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical information management system, and particularly relates to a clinical rehabilitation data management and evaluation system for rhabdomyolysis patients. BACKGROUND

[0002] The technical field of medical information management system includes systematic collection, structured management and analysis processing of a large amount of heterogeneous data generated in the clinical medical process. The core goal of this technical field is to improve the efficiency of clinical decision-making, optimize resource allocation and realize the intelligentization of disease management, covering multiple key links such as patient medical record filing, health index dynamic monitoring, disease development process tracking and individualized treatment path management. The medical information management system integrates clinical information resources such as electronic health records, physiological parameter monitoring data and test results, establishes a cross-department and cross-process data linkage mechanism, thereby realizing fine data support and information coordination for the whole process of patient treatment, and ensuring efficient operation of each link of clinical work under a unified data platform.

[0003] Among them, the clinical rehabilitation data management and evaluation system for rhabdomyolysis patients refers to the key physiological data and disease change information involved in the clinical treatment and rehabilitation process of rhabdomyolysis patients. The system periodically collects and archives data such as patient muscle enzyme level changes, urine volume records and kidney function test values, and continuously tracks and dynamically classifies each parameter based on the set index classification standard, and compares the time series data and trend pre-evaluation based on the disease evolution timeline. The system generally uses means such as multi-cycle data point extraction, physiological index correlation mapping and data standardization comparison to assist in realizing fine-grained identification of patient status and clinical information evaluation, and providing data support for treatment plan development.

[0004] The prior art still has structural defects in the multi-dimensional parameter collaborative analysis and dynamic trend identification of the data management of patients with rhabdomyolysis. The traditional method relies on periodic collection and independent parameter archiving, which breaks the time correlation of key indicators such as creatine kinase and myoglobin, and cannot reflect the interaction mechanism of different biochemical indicators in the rehabilitation process. The existing system limits the monitoring of rate changes to static comparison within a single time window, failing to build a continuous analysis framework for adjacent rate differences, resulting in the identification of abnormal fluctuation points lagging behind the actual disease evolution. In the trend analysis dimension, the existing technology uses a single parameter linear regression model, lacks curvature feature extraction of indicators such as urine sodium concentration and blood creatinine, and cannot capture the collaborative time nodes of trend mutations of multiple parameters. In addition, the existing method does not establish a consistency verification mechanism across indicators, making it difficult to identify joint risk evolution patterns of creatine kinase and blood potassium concentration, resulting in fragmented data for clinical decision-making. In terms of data presentation, the existing system uses discrete report forms to display test results, and fails to convert the correlation of multiple parameter trends into a time-continuous visual map, restricting the clinical applicability of dynamic rehabilitation evaluation. These defects make the traditional technology unable to meet the complex monitoring needs of the interaction of multiple systems in the rehabilitation process of rhabdomyolysis. SUMMARY

[0005] The purpose of the present application is to solve the problems existing in the prior art and to provide a rhabdomyolysis patient clinical rehabilitation data management evaluation system.

[0006] In order to achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0007] A rhabdomyolysis patient clinical rehabilitation data management evaluation system comprises:

[0008] An index collection module acquires creatine kinase values, myoglobin values, urine sodium concentrations, blood creatinine levels, lactate dehydrogenase values and blood potassium concentrations of rhabdomyolysis patients at time nodes during the rehabilitation period, and generates a patient continuous index distribution table by structurally organizing the data according to time sequence;

[0009] A rate detection module extracts the time change rate of creatine kinase values and myoglobin values based on the patient continuous index distribution table, establishes a difference sequence between adjacent rates, judges abnormal points of rate variation amplitude, and generates a rehabilitation period rate abnormal record set;

[0010] A curvature analysis module extracts the time trend changes of urine sodium concentration, lactate dehydrogenase value and blood creatinine level based on the rehabilitation period rate abnormal record set and the patient continuous index distribution table, constructs a curvature sequence for continuous data, identifies trend mutation time points, and generates a curvature linkage inflection point set;

[0011] The node identification module locates the intersection time node according to the curvature linkage inflection point set and the rehabilitation period rate anomaly record set, calls the node creatine kinase value and blood potassium concentration, judges the consistency of the change direction, establishes a joint trend label combined with the index change direction, and generates a risk joint evolution node label set.

[0012] Optionally, the patient continuous index distribution table includes creatine kinase value, myoglobin value, urine sodium concentration, blood creatinine level, lactate dehydrogenase value, and blood potassium concentration, the rehabilitation period rate anomaly record set includes creatine kinase rate difference sequence, myoglobin rate difference sequence, and variable amplitude abnormal point, the curvature linkage inflection point set includes urine sodium concentration curvature sequence, lactate dehydrogenase curvature sequence, and blood creatinine curvature sequence, and the risk joint evolution node label set includes joint time node, index change direction consistency judgment result, and joint trend label.

[0013] Optionally, the index collection module includes:

[0014] The data acquisition submodule acquires creatine kinase value, myoglobin value, urine sodium concentration, blood creatinine level, lactate dehydrogenase value, and blood potassium concentration of a rhabdomyolysis patient at a time node in a rehabilitation period, collects data according to patient number, records the indexes in the corresponding time points according to time, and generates six index time sequence data;

[0015] The time arrangement submodule extracts the time node of each patient according to the six index time sequence data, calls the index value corresponding to the time point, arranges the data in time sequence, calculates the interval value between adjacent times, establishes a sequentially arranged data set, and generates a continuous time sequence structure value;

[0016] The index distribution submodule summarizes the six index values of the time node according to the continuous time sequence structure value, forms an index arrangement table based on time advancement, calculates the value change in the time period, establishes the distribution relationship of the index with time, and generates a patient continuous index distribution table.

[0017] Optionally, the specific calculation formula of arranging the data in time sequence is:

[0018]

[0019] wherein, Δt i represents the weighted time interval between the i th time point and the i+1 th time point, T i represents the time value of the i th time node, T i+1 represents the time value of the i+1 th time node, V ij represents the original value of the i th time node under the j th index, T ja weighted coefficient corresponding to the jth index (note that T j Unlike T i , which represents a time value), m represents the total number of indexes, j is the index of the index from 1 to m, and i is the index of the current time point.

[0020] Optionally, the rate detection module comprises:

[0021] The rate extraction submodule obtains the creatine kinase value and the myoglobin value in the patient continuous index distribution table based on the patient continuous index distribution table, locates the continuous records of the indexes in time sequence, constructs a rate sequence in combination with the numerical relationship of adjacent time points, and generates a set of time-varying rate values;

[0022] The difference construction submodule extracts the numerical change of adjacent rates based on the order relationship between the rate values in the set of time-varying rate values, arranges and constructs a difference sequence in time sequence, and obtains a rate change difference sequence;

[0023] The abnormality identification submodule calls the change information in the rate change difference sequence, identifies an abnormal amplitude according to a rate variation amplitude threshold, marks the corresponding time node and records, and establishes a rehabilitation period rate abnormality record set.

[0024] Optionally, the specific calculation formula for identifying the abnormal amplitude according to the rate variation amplitude threshold is:

[0025]

[0026] where ΔR i represents the rate variation intensity index of the ith moment in the rehabilitation period, r i,j represents the actual observation value of the rate of the jth call item at the ith moment in the rehabilitation period, represents the arithmetic mean of the rate observation values of all call items at the ith moment in the rehabilitation period, σ i,j represents the standard deviation calculated from the difference between the rate observation value of the jth call item at the ith moment in the rehabilitation period and the corresponding , w i,j represents the rate reliability weight factor of the jth call item at the ith moment in the rehabilitation period, n represents the total number of call items participating in the calculation in the rehabilitation period, and ∈ represents a very small positive constant number set to avoid division by zero error.

[0027] Optionally, the curvature analysis module comprises:

[0028] The trend extraction submodule obtains the rehabilitation period rate abnormality record set and the patient continuous index distribution table, extracts the time series of urine sodium concentration, lactate dehydrogenase value and blood creatinine level, constructs a trend sequence of the indexes in time sequence, and generates an index time trend sequence value;

[0029] The curvature calculation submodule calls the index data of adjacent time nodes based on the index time trend sequence value, analyzes the change pattern in the time period, sequentially constructs the curvature sequence corresponding to the index, and generates an index curvature change trend value;

[0030] The inflection point identification submodule judges the change direction of adjacent nodes according to the index curvature change trend value, identifies the curvature mutation position, screens the co-occurrence nodes of the three indexes, and obtains a curvature linkage inflection point set.

[0031] Optionally, the node identification module comprises:

[0032] The inflection point extraction submodule obtains the time sequence corresponding to the two sets based on the curvature linkage inflection point set and the rehabilitation period rate anomaly record set, judges whether the data of the two sets at the same time stamp exist, generates an intersection time node set by matching the time stamp intersection set between the two sets, and generates an intersection time node set.

[0033] The parameter linkage determination submodule calls the creatine kinase value and the blood potassium concentration value corresponding to the time points in the intersection time node set, judges whether the change direction of the creatine kinase value and the change direction of the blood potassium concentration are the same, screens the time nodes with consistent change directions by the direction consistency judgment operation, and generates a parameter consistency node sequence.

[0034] The risk label generation submodule establishes a joint trend direction label according to the change direction of the creatine kinase value and the change direction of the blood potassium concentration corresponding to each time node in the parameter consistency node sequence, generates a risk joint evolution node label set by pairing the trend label with the time node set.

[0035] Optionally, the system further comprises:

[0036] The trend construction module calls the risk joint evolution node label set, extracts the myoglobin value and the blood creatinine level in the associated time period, counts the proportion of indexes with consistent change directions, annotates the trend range, and generates a rehabilitation stage fluctuation trend channel map.

[0037] The rehabilitation stage fluctuation trend channel map comprises the consistent index proportion in the associated time period and the trend range annotation.

[0038] Optionally, the trend construction module comprises:

[0039] The data extraction submodule obtains the time range annotated in the risk joint evolution node label set, collects the myoglobin value and the blood creatinine level in the corresponding time period, aligns the time granularity, calculates the total number of samples and the values of the two types of indexes at the corresponding time points, and generates a myoglobin and blood creatinine alignment index set.

[0040] The index comparison submodule extracts index values at continuous time points based on the myoglobin and blood creatinine alignment index set, judges whether the change directions of the two indexes are consistent, calculates the proportion of time periods with consistent directions, and generates an index change consistency rate;

[0041] The trend generation submodule labels time periods in the direction consistent interval according to the index change consistency rate, extracts the maximum and minimum values of myoglobin and blood creatinine to construct upper and lower boundaries, connects the boundary nodes to construct a channel map, and obtains a rehabilitation stage fluctuation trend channel map.

[0042] Compared with the prior art, the advantages and positive effects of the present application are:

[0043] In the present application, by combining the rate difference sequence of creatine kinase and myoglobin with the curvature sequence of urine sodium and blood creatinine, the traditional single-parameter static analysis limitation is broken through, dynamic capture of multi-index collaborative trend is realized, combined with the consistency discrimination of creatine kinase and blood potassium concentration change direction, a joint evolution label system is constructed, multi-system interaction risk nodes are accurately located, the direction consistency proportion distribution of myoglobin and blood creatinine in the associated period is counted, and the discrete parameter association is converted into a dynamic visualization model. This method solves the problems of data discrete misjudgment and collaborative evolution mode fragmentation in traditional technology, and provides a multi-dimensional dynamic evaluation framework for the rehabilitation process of rhabdomyolysis in clinic. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 The system flowchart of the present application is shown in the figure;

[0045] Figure 2 The system block diagram of the present application is shown in the figure. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical scheme and advantages of the present application clearer, further detailed description will be made below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application, and are not used to limit the present application.

[0047] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and therefore cannot be understood as indicating or implying that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise specifically limited.

[0048] Please refer toFigure 1 The embodiment of the present application provides a kind of clinical rehabilitation data management evaluation system of Rhabdomyolysis patient, comprising:

[0049] Index acquisition module obtains the creatine kinase value, myoglobin value, urine sodium concentration, blood creatinine level, lactate dehydrogenase value and blood potassium concentration of Rhabdomyolysis patient in rehabilitation cycle time node, and data is structured and arranged according to time sequence, and generates patient continuous index distribution table;

[0050] Rate detection module is based on patient continuous index distribution table, extracts the time variation rate of creatine kinase value and myoglobin value, establishes difference sequence between adjacent rates, judges the amplitude anomaly point of rate variation, and generates rehabilitation cycle rate anomaly record set;

[0051] Curvature analysis module is based on rehabilitation cycle rate anomaly record set and patient continuous index distribution table, extracts the time trend change of urine sodium concentration, lactate dehydrogenase value and blood creatinine level, constructs curvature sequence for continuous data, identifies trend mutation time point, and generates curvature linkage inflection point set;

[0052] Node identification module positions the intersection time node of curvature linkage inflection point set and rehabilitation cycle rate anomaly record set according to curvature linkage inflection point set and rehabilitation cycle rate anomaly record set, calls creatine kinase value and blood potassium concentration of node, judges change direction consistency, and then establishes joint trend label in combination with the change direction of index, and generates risk joint evolution node label set;

[0053] Trend construction module calls risk joint evolution node label set, extracts myoglobin value and blood creatinine level in associated time period, and the proportion of index with consistent change direction is counted, and the trend range is annotated, and rehabilitation stage fluctuation trend channel map is generated.

[0054] Patient continuous index distribution table includes creatine kinase value, myoglobin value, urine sodium concentration, blood creatinine level, lactate dehydrogenase value, blood potassium concentration, rehabilitation cycle rate anomaly record set includes creatine kinase rate difference sequence, myoglobin rate difference sequence, variation amplitude anomaly point, curvature linkage inflection point set includes urine sodium concentration curvature sequence, lactate dehydrogenase curvature sequence, blood creatinine curvature sequence, trend mutation time point, risk joint evolution node label set includes joint time node, index change direction consistency judgment result, joint trend label, and rehabilitation stage fluctuation trend channel map includes consistent index proportion in associated time period, trend range annotation.

[0055] Index acquisition module includes:

[0056] The data acquisition submodule obtains creatine kinase values, myoglobin values, urine sodium concentrations, blood creatinine levels, lactate dehydrogenase values and blood potassium concentrations at time nodes in the rehabilitation period of a patient with rhabdomyolysis, collects data according to patient numbers, records the indicators into corresponding time points according to time records, and generates six indicators time series data;

[0057] The data acquisition submodule screens patient groups diagnosed with rhabdomyolysis by interfacing with a medical information system, traverses all test records of the patient during the rehabilitation period with the patient number as the primary key, extracts six indicator values such as creatine kinase according to the execution time of the medical order, for example, patient number P001 records creatine kinase values of 5200 U / L, 3800 U / L, 2800 U / L and 1800 U / L at 1st, 3rd, 5th and 7th day of treatment respectively, and myoglobin values are 850 ng / mL, 620 ng / mL, 450 ng / mL and 300 ng / mL respectively, if the data at a certain time node is missing, the mean value is filled based on the detection results of the adjacent time points, for example, the myoglobin value of patient P002 at 3rd day is missing, the intermediate value of 750 ng / mL is taken as the completion value between the value of 1st day 900 ng / mL and the value of 5th day 600 ng / mL, finally the indicator values at different time nodes are integrated into a structured table file according to the patient number, the table fields include patient number, time node and detection value of six indicators, and stored as a data collection arranged in ascending order of time.

[0058] The time arrangement submodule extracts the time nodes of each patient according to the six indicators time series data, calls the indicator values corresponding to the time points, arranges the data in time sequence, calculates the interval value between adjacent times, establishes a sequentially arranged data collection, and generates a continuous time sequence structure value;

[0059] The specific calculation formula for arranging data in time sequence is:

[0060]

[0061] Where, Δt i represents the weighted time interval between the i-th time point and the i+1-th time point, T i represents the time value of the i-th time node, T i+1 represents the time value of the i+1-th time node, V ij represents the original value of the i-th time node under the j-th indicator, T j represents the weighted coefficient corresponding to the j-th indicator (note that T j is different from T i , which does not represent the time value), m represents the total number of indicators, j is the indicator index from 1 to m, and i is the index of the current time point;

[0062] Formula details and formula calculation derivation process:

[0063] Parameter Description and Acquisition Method:

[0064] T i Acquired through system logs or sensor records.

[0065] T i+1 Acquired through system logs or sensor records.

[0066] V i,j For example, milliseconds, times, etc., collected through real-time monitoring systems.

[0067] T j Set based on the importance or influence of the indicator, usually determined through expert evaluation or historical data analysis.

[0068] m represents the number of indicators involved in the calculation.

[0069] Specific value setting and basis:

[0070] Set time node T i = 120 minutes, T i+1 = 150 minutes, indicating an interval of 30 minutes between two time points.

[0071] Number of indicators m = 3, indicating that three indicators are involved in the calculation.

[0072] Indicator original value:

[0073] V i,1 = 100 (unit: milliseconds), acquired through system response time monitoring.

[0074] V i,2 = 200 (unit: times), acquired through request frequency statistics.

[0075] V i,3 = 300 (unit: milliseconds), acquired through processing time monitoring.

[0076] Weighting coefficient:

[0077] T1 = 1.0, indicating that this indicator is the baseline indicator.

[0078] T2 = 1.5, indicating that the importance of this indicator is 1.5 times that of the baseline indicator.

[0079] T3 = 2.0, indicating that the importance of this indicator is 2 times that of the baseline indicator.

[0080] Formula calculation process:

[0081] Calculate the sum of time values:

[0082] T i+1 + Ti = 150 + 120 = 270;

[0083] Calculate the numerator part:

[0084]

[0085] Calculate the denominator part:

[0086]

[0087] Calculate the final result:

[0088]

[0089] Result interpretation:

[0090] This result shows that, between the current time node i and the next time node i+1, considering the original values of each indicator and their weighting coefficients, the weighted time interval value calculated is approximately 0.27. This value is used to establish a sequentially arranged data set, generating a continuous time series structure value.

[0091] The indicator distribution submodule, based on the continuous time series structure value, aggregates the six indicator values of the time node, forms an indicator ranking table based on time advancement, calculates the value changes within the time period, establishes the distribution relationship of indicators with time, and generates a continuous indicator distribution table for the patient;

[0092] The indicator distribution submodule expands the six indicators of patient P001 into a longitudinal numerical sequence according to the time node, marks the detection values at each time point and the change amplitude between adjacent time points, for example, the creatine kinase value decreases from 5200 U / L to 3800 U / L, with a change amplitude of 26.9% decrease, and sets the judgment rule, if the creatine kinase single decrease amplitude exceeds 30% or the myoglobin value continuously exceeds 500 ng / mL, the early warning mark is triggered, for the blood potassium concentration, set the normal reference range as 3.5 to 5.0 millimoles per liter, below 3.5 is marked as low potassium event, above 5.0 is marked as high potassium event, for example, the blood potassium value of patient P006 on the 3rd day is 5.2 millimoles per liter, which is classified as high potassium and records the abnormal identification, finally forms a detailed distribution table containing time node, original value, change amplitude and early warning identification, stored in matrix form and associated to patient number.

[0093] The rate detection module includes:

[0094] The rate extraction submodule, based on the continuous indicator distribution table of the patient, obtains the creatine kinase value and myoglobin value in the continuous indicator distribution table of the patient, locates the continuous records of the indicators in time sequence, constructs the rate sequence combining the numerical relationship of adjacent time points, and generates a set of time change rate values;

[0095] The rate extraction submodule extracts creatine kinase and myoglobin index values from a distribution data table containing continuous health indicators, which includes patient number, detection time, index type, and specific value fields. All records are arranged in chronological order, and then the same type of indicators are paired according to consecutive time points. For example, if a patient receives creatine kinase detection on March 1, March 2, and March 3, with detection values of 140, 160, and 180, respectively, the first group is formed by pairing March 1 and March 2, and the second group is formed by pairing March 2 and March 3. The change rate between the two time points is calculated for each group, and then combined with the interval length between the two time points to obtain the change rate in that time period. For example, if detection is performed once a day, the first group change rate is 20 units per day, and the second group change rate is also 20 units per day. The above operation is performed gradually in all continuous detection time periods to form an ordered rate sequence. Myoglobin also needs to be processed in the same way. To ensure the accuracy of the calculation, detection interval abnormalities or data missing situations should be excluded. For example, if there is a continuous detection interval of more than three days or detection data is abnormally deviated, data cleaning or interpolation means should be used to process it before performing rate calculation. Finally, two indicators each form a complete change rate set, which is recorded in chronological order to form a rate data set that can be used for subsequent analysis.

[0096] The difference construction submodule extracts the numerical change between adjacent rates based on the order relationship between the rate values in the time change rate value set, arranges the difference values in chronological order to construct a difference value sequence, and obtains a rate change difference value sequence.

[0097] After obtaining the rate value set, the difference construction submodule starts to extract the numerical change between any two adjacent rates to construct a difference set. In this process, the rate sequence is compared one by one in chronological order, and the difference between each two adjacent rates is calculated. For example, if the first rate is 20 and the second rate is 25, the difference is 5. This operation continues between the second and third rates, and so on. It needs to be particularly noted whether the time interval is equal during the construction process. If the detection time interval between two rates is different, a standardization method should be used to adjust it to ensure that the difference has reference value. For example, an intermediate rate point is inserted in the larger interval through linear interpolation to keep the front and back intervals consistent, and then the difference extraction operation is performed. Each difference is sorted in chronological order to form a difference sequence, and the starting rate and ending rate values corresponding to each difference are recorded to ensure that the original detection change path can be traced back in the subsequent module. This sequence can be used to identify abnormal change trends or rhythm mutations after it is generated.

[0098] The abnormality recognition submodule calls the change information in the rate change difference value sequence, identifies abnormal amplitudes according to the rate variation amplitude threshold, marks the corresponding time nodes and records them, and establishes a rehabilitation period rate abnormality record set.

[0099] The specific calculation formula of identifying abnormal amplitude according to the rate change amplitude threshold is:

[0100]

[0101] Wherein, ΔR i represents the rate change intensity index of the i th moment of the rehabilitation period, r i,j represents the actual observation value of the rate of the i th calling item at the i th moment in the rehabilitation period, represents the arithmetic mean of the rate observation value of all calling items at the i th moment in the rehabilitation period, σ i,j represents the standard deviation calculated by the difference between the rate observation value of the i th calling item at the i th moment in the rehabilitation period and the corresponding , w i,j represents the rate reliability weight factor of the i th calling item at the i th moment in the rehabilitation period, n represents the total number of calling items participating in the calculation in the rehabilitation period, and ∈ represents a very small positive constant number set to avoid division by zero error;

[0102] Formula details and formula calculation derivation process:

[0103] At the i th moment of the rehabilitation period, the calling rate data of n = 3 sub-modules are collected, which are respectively: r i,1 = 120 times / min, r i,2 = 100 times / min, r i,3 = 80 times / min.

[0104] Calculate the average rate

[0105]

[0106] Calculate the standard deviation σ i,j of each sub-module, which is calculated by using Welford iterative method. The collected rate data are: 110, 120, 130.

[0107] First step: M1 = 110, S1 = 0;

[0108] Second step:

[0109] Third step:

[0110] The standard deviation is:

[0111] Similarly, it is calculated that:

[0112] σ i,2 = 8, σi,3 = 5.

[0113] The confidence weighting factor w is set i,j according to the stability and historical performance indicators of the sub-module. According to the WRR weight setting method in the QoS configuration, the weight value ranges from 1 to 10, and the higher the weight, the higher the priority. Set:

[0114] w i,1 = 1.0, w i,2 = 0.8, w i,3 = 0.6.

[0115] Set ∈ = 0.01 to prevent the denominator from being zero.

[0116] Substitute the above values into the formula to calculate ΔR i :

[0117]

[0118] The results show that the rate variation intensity index of the i-th moment of the rehabilitation period is 0.229, indicating that the sub-module call rate has a certain degree of fluctuation. This index can be used to identify abnormal amplitudes, mark the corresponding time nodes and record them, and establish a rehabilitation period rate anomaly record set.

[0119] The curvature analysis module includes:

[0120] The trend extraction submodule obtains the rehabilitation period rate anomaly record set and the patient continuous index distribution table, extracts the time series of urine sodium concentration, lactate dehydrogenase value and blood creatinine level, constructs the trend sequence of the index in time order, and generates the index time trend sequence value;

[0121] The trend extraction submodule is used to extract rate abnormal data records and patient continuous detection indicators from the rehabilitation period. First, the rehabilitation database is used to obtain the patient population whose rehabilitation rate deviates from the statistical mean in all rehabilitation records. The deviation standard can be set as a range greater than or less than two standard deviations of the average value of the population. For example, if the overall average gait recovery rate is 0.6 levels per week, and a case only improves 0.3 levels in two weeks, it is judged as an abnormal record. Then, the continuous measurement data of urine sodium concentration, lactate dehydrogenase value and serum creatinine level are obtained from the electronic medical record or laboratory information system of such cases, and are sorted according to the time node to construct a time series. On this basis, the sliding window method is used to smooth each indicator value to improve the stability of the data sequence. For example, the values of the last five detection time points are assigned different weights, with the weight of the recent time value being larger and the weight of the remote time point being smaller. Finally, the trend value of the node is obtained by weighting, and the trend expression of the indicator at the current time node is generated. For example, the continuous five-day urine sodium measurement values of a patient are 120, 130, 145, 155 and 160 units. After applying the weighted average method, the trend value of the fifth day is about 147 units. In this way, all time nodes are processed in turn to form the trend sequence of each of the three indicators and obtain complete time trend information.

[0122] The curvature calculation submodule calls the indicator data of adjacent time nodes based on the indicator time trend sequence value, analyzes the change pattern in the time period, and sequentially constructs the curvature sequence corresponding to the indicator to generate the indicator curvature change trend value.

[0123] The curvature calculation submodule selects the trend values of adjacent time nodes based on the trend sequence, performs difference operation, analyzes the numerical change pattern of the indicator in the continuous time period, and estimates the change curvature degree of the current node through comprehensive comparison of the direction and amplitude of the front and back difference values to form a curvature value sequence. For example, if the urine sodium trend values of the last three days first increase and then decrease, it indicates that the change direction of the current node reverses, and the ratio of the two change amplitudes needs to be evaluated. For example, from 140 to 150 and then to 135 units, it can be considered that the curvature of the node is obvious. The method is used to process all time nodes of urine sodium, lactate dehydrogenase and serum creatinine to generate a set of curvature change trend data of each indicator.

[0124] The inflection point recognition submodule judges the change direction of adjacent nodes according to the indicator curvature change trend value, identifies the curvature mutation position, selects the co-occurring nodes of the three indicators, and obtains a set of curvature linkage inflection points.

[0125] The inflection point identification submodule, on the basis of the curvature trend sequence, judges the curvature change direction of adjacent time nodes in turn. If there is a mutation from negative to positive or from positive to negative, and the variation amplitude exceeds the set limit, for example, the threshold is set to 10 units, if the curvatures before and after a node are -15 and 12 respectively, the node can be marked as a mutation point. The mutation points of the three indicators are summarized one by one, and the positions where the three indicators all have curvature mutations at the same time point are further screened out and marked as co-occurring nodes. These nodes are collected into a curvature linkage inflection point set, representing the time positions where the three indicators have abnormal changes in curvature.

[0126] The node identification module comprises:

[0127] The inflection point extraction submodule, based on the curvature linkage inflection point set and the rehabilitation cycle rate anomaly record set, acquires the time sequences corresponding to the two sets, judges whether the data of the two sets at the same time stamp exist, generates an intersection time node set by matching the time stamp intersection between the two sets, and outputs the intersection time node set.

[0128] The inflection point extraction submodule, based on the curvature linkage inflection point set and the rehabilitation cycle rate anomaly record set, first selects a frequency of one sample per second for the time series data collected by the electromyographic signal, continuously extracts signal points to analyze their change trend, applies the difference method to estimate the change rate by taking the values before and after each point, calculates the local curvature degree of the signal according to the difference between the positions before and after the point, sets a judgment threshold such as 0.08, extracts the points with obvious change characteristics in the time series as the curvature inflection point set, extracts the step speed data from the wearable device, calculates the speed mean value and fluctuation range by setting three consecutive time windows, and classifies the larger speed change amplitude into the rate anomaly record set. The fluctuation size is evaluated by standardization processing to judge whether the step speed at a certain time has abnormal characteristics. After obtaining the time point sets corresponding to the two sets respectively, it is judged by traversal whether there is a coincident time point. All time points appearing in both sets are extracted to form a new intersection time point set, which is used for further calculation by the subsequent module.

[0129] The parameter linkage determination submodule calls the creatine kinase value and the blood potassium concentration value corresponding to the time points in the intersection time node set, judges whether the change direction of the creatine kinase value and the change direction of the blood potassium concentration are the same, selects the time nodes with consistent change directions through the direction consistency judgment operation, and generates a parameter consistency node sequence.

[0130] The parameter linkage determination sub-module calls the creatine kinase value and the blood potassium concentration value corresponding to the time points in the intersection time point set, extracts the corresponding creatine kinase measurement result and blood potassium detection result in each intersection time point, respectively compares the data value size of each time point and the previous time point, judges whether the value is rising, falling or remaining unchanged by comparing the increasing and decreasing change direction of the current value and the previous value, for example, the creatine kinase value of a certain time point rises from 180 to 220, and the corresponding change direction is rising, while the blood potassium value at the same time rises from 4.3 to 4.7, which is also determined to be rising, the time points with consistent change direction of the two parameters are included in the consistency node sequence, if the change direction is inconsistent, the time point is excluded, and through repeated comparison and screening, the time node set meeting the conditions is obtained.

[0131] The risk label generation sub-module establishes a joint trend direction label according to the creatine kinase value change direction and the blood potassium concentration change direction corresponding to each time node in the parameter consistency node sequence, generates a risk joint evolution node label set through pairing of the trend label and the time node set.

[0132] The risk label generation sub-module respectively combines the change trends of the two parameters at the time according to the creatine kinase value change direction and the blood potassium concentration change direction corresponding to each time node in the parameter consistency node sequence, establishes a unified trend description label, for example, when both parameters show an upward trend, the label is “++”, if both show a downward trend, the label is “--”, and if one shows an upward trend and the other shows a downward trend, the label is “+-”, each trend label is paired with the corresponding time point to form a risk joint evolution label set, which represents the change pairing of the two indicators at each time node and can be used for further trend modeling or early warning classification.

[0133] The trend construction module comprises:

[0134] The data extraction sub-module obtains the time range labeled in the risk joint evolution node label set, collects the myoglobin value and the blood creatinine level in the corresponding time period, aligns the time granularity, removes the missing samples, calculates the total number of samples and the values of the two indicators at the corresponding time points, and generates a myoglobin and blood creatinine aligned indicator set.

[0135] The data extraction submodule needs to read the time range information labeled by the risk joint evolution node label set, which is usually derived from pathological state evolution data or medical model identification results. The label set records the health risk state of each patient in a specific time period, and the time field is usually represented in the form of "start time" and "end time". First, the time field is uniformly formatted to ensure no errors in subsequent time series integration. When collecting myoglobin and blood creatinine indicator values within the time period, the laboratory examination records that meet the time range are extracted by interfacing with the experimental data platform, including the corresponding examination time and original values of the two indicators for each record. Further, the time series indicator pairs are arranged according to the patient dimension. In the data alignment stage, a unified reference time axis is established with minute or hour granularity, and the original data is mapped to this axis. A time window range is set for each time point to match the actual detection time, to fill in missing or uniform intervals. For example, if the granularity is set to every hour, the closest detection value is collected based on the whole hour benchmark to complete data filling or interpolation. After that, only records with both indicator values at the same time point are retained as valid samples for subsequent analysis. In the process of removing data missing samples, a threshold can be set to determine whether the number of valid records of each patient within a certain time period meets the specified standard. For example, if the effective time point accounts for more than 80% of the theoretical time points, samples that do not meet the condition are removed. Then, the total number of remaining samples is counted, and the two indicator values are arranged at the unified time points. The output is in the form of a dictionary or table, with each time point corresponding to a set of myoglobin and blood creatinine values. For example, from 08:00 on April 1, 2025 to 08:00 on April 2, 2025, a total of 24 hours, after removing missing data, there are 20 hours of complete data, which constitute the aligned indicator set. For example, at the 09:00 time point on April 1, 2025, the myoglobin value is 87.1 and the blood creatinine value is 135.6.

[0136] The index comparison submodule extracts the indicator values at consecutive time points based on the myoglobin and blood creatinine aligned indicator set, judges whether the change directions of the two indicators are consistent, calculates the proportion of time periods with consistent directions, and generates the index change consistency rate.

[0137] The index comparison submodule establishes a change analysis section with each two consecutive time points as a group after obtaining the alignment index set, for example, 08:00 and 09:00 form a section, extracts the change trend of two indexes in each section, and performs difference comparison on the index values of the previous time point and the next time point, for example, the myoglobin is 85.6 at 08:00 and 87.1 at 09:00, which is considered to be rising, and the blood creatinine rises from 134.2 to 135.6 in the same time period, and it is judged that the change directions of the two are the same, the number of sections with the same direction in all time periods is counted, and then the ratio is calculated with the total number of sections, to obtain the proportion of the same direction, for example, 23 consecutive time sections are generated, among which 18 sections have the same change direction of the two indexes, so the consistency rate is 18 divided by 23 and multiplied by a percentage, that is, about 78.26%, which is used as the final index change consistency rate for subsequent trend channel atlas construction.

[0138] The trend generation submodule marks the time sections in the direction consistent interval according to the index change consistency rate, extracts the maximum and minimum values of myoglobin and blood creatinine to construct the upper and lower boundaries, connects the boundary nodes to construct the channel atlas, and obtains the fluctuation trend channel atlas of the rehabilitation stage;

[0139] The trend generation submodule obtains the index change consistency rate, selects time sections with a higher direction consistency rate, and marks all consecutive consistent time sections, extracts all values of myoglobin and blood creatinine in each time section, calculates the maximum and minimum values in the section, and uses them as the upper and lower boundaries of the index fluctuation in the section. In the atlas construction stage, the minimum value points in each time section form a lower boundary curve, and the maximum value points form an upper boundary curve. Through a visualization tool, a closed area structure is drawn to form a trend channel atlas. For example, between 10:00 and 14:00 on April 1, 2025, the minimum value of myoglobin in the interval is 88, and the maximum value is 110. The minimum value of blood creatinine in the same time is 137, and the maximum value is 151. When drawing, time is taken as the horizontal axis, and index values are taken as the vertical axis. In each time section, upper and lower boundary curves are drawn and the intermediate area is filled to form a complete fluctuation trend graph of the rehabilitation stage.

[0140] The above is only a preferred embodiment of the present application, and does not limit the present application in other forms. Any skilled person in the art can modify or change the above disclosed technical content to equivalent embodiments applied to other fields, but any simple modification, equivalent change and modification made according to the technical essence of the present application to the above embodiments still belongs to the protection scope of the technical solution of the present application.

Claims

1. A clinical rehabilitation data management and evaluation system for patients with rhabdomyolysis, characterized in that: The system includes: The indicator acquisition module obtains creatine kinase, myoglobin, urinary sodium concentration, serum creatinine, lactate dehydrogenase and serum potassium concentration at time points during the recovery period of patients with rhabdomyolysis. The data is then organized according to time order to generate a continuous indicator distribution table for patients. The rate detection module extracts the time change rate of creatine kinase and myoglobin values ​​based on the patient's continuous index distribution table, establishes a difference sequence between adjacent rates, identifies abnormal points in rate change amplitude, and generates a set of abnormal rate records for the rehabilitation cycle. The rate detection module includes: The rate extraction submodule, based on the patient continuous index distribution table, obtains the creatine kinase value and myoglobin value in the patient continuous index distribution table, locates the continuous records of the index in chronological order, constructs the rate sequence by combining the numerical relationship of adjacent time points, and generates a set of time change rate values. The difference construction submodule extracts the numerical changes of adjacent rates based on the sequential relationship between rate values ​​in the time change rate value set, arranges them in time order to construct a difference sequence, and obtains the rate change difference sequence. The anomaly identification submodule calls the change information in the rate change difference sequence, identifies the abnormal amplitude based on the rate change amplitude threshold, marks the corresponding time node and records it, and establishes a recovery cycle rate anomaly record set. The specific calculation formula for identifying abnormal amplitudes based on the threshold of rate change amplitude is as follows: Where, ΔR i r represents the rate of change intensity at time i of the rehabilitation cycle. i,j This represents the actual observed rate of the j-th call item at time i during the recovery cycle. σ represents the arithmetic mean of the rate observations of all calls at time i in the recovery cycle. i,j This represents the rate observation value of the j-th call item at time i in the rehabilitation cycle and its corresponding value. The standard deviation calculated from the difference, w i,j The rate reliability weight factor represents the j-th call item at time i in the recovery cycle, n represents the total number of call items involved in the calculation in the recovery cycle, and ∈ represents a minimal positive real constant set to avoid division by zero error; The curvature analysis module, based on the abnormal record set of the rehabilitation cycle rate and the patient's continuous index distribution table, extracts the time trend changes of urinary sodium concentration, lactate dehydrogenase value and serum creatinine level, constructs a curvature sequence for continuous data, identifies time points of trend change, and generates a set of curvature linkage inflection points. The node identification module locates the intersection time node of the curvature linkage inflection point set and the rehabilitation cycle rate abnormal record set, calls the node creatine kinase value and blood potassium concentration, and judges the consistency of the change direction of creatine kinase value and blood potassium concentration. It establishes a joint trend label based on the change direction of the indicators and generates a risk joint evolution node label set.

2. The clinical rehabilitation data management and evaluation system for patients with rhabdomyolysis according to claim 1, characterized in that: The patient continuous indicator distribution table includes creatine kinase value, myoglobin value, urinary sodium concentration, serum creatinine level, lactate dehydrogenase value, and serum potassium concentration. The abnormal recovery cycle rate record set includes creatine kinase rate difference sequence, myoglobin rate difference sequence, and abnormal fluctuation points. The curvature linkage inflection point set includes urinary sodium concentration curvature sequence, lactate dehydrogenase curvature sequence, serum creatinine curvature sequence, and trend change time points. The risk joint evolution node label set includes joint time nodes, consistency judgment results of indicator change direction, and joint trend labels.

3. The clinical rehabilitation data management and evaluation system for patients with rhabdomyolysis according to claim 1, characterized in that: The indicator acquisition module includes: The data acquisition submodule acquires creatine kinase, myoglobin, urinary sodium concentration, serum creatinine, lactate dehydrogenase and serum potassium concentration at time points during the recovery period of patients with rhabdomyolysis. The data is collected by patient number and the indicators are assigned to the corresponding time points according to the time record to generate time series data of six indicators. The time processing submodule extracts the time nodes of each patient based on the time series data of the six indicators, calls the corresponding indicator values ​​of the time points, arranges the data in chronological order, calculates the interval values ​​between adjacent times, establishes a sequentially arranged data set, and generates continuous time series structure values. The indicator distribution submodule, based on the continuous time series structure values, summarizes the values ​​of six indicators at time nodes, forms an indicator arrangement table based on time progression, calculates the changes in values ​​within a time period, establishes the distribution relationship of indicators over time, and generates a continuous indicator distribution table for patients.

4. The clinical rehabilitation data management and evaluation system for patients with rhabdomyolysis according to claim 3, characterized in that: The specific calculation formula for arranging the data in chronological order is as follows: Where Δti represents the weighted time interval between the i-th time point and the (i+1)-th time point, T i T represents the time value at the i-th time point. i+1 V represents the time value at the (i+1)th time node. i ,j represents the original value of the j-th indicator at the i-th time point, T j The value represents the weighting coefficient corresponding to the j-th indicator, m represents the total number of indicators, j is the index of the indicator from 1 to m, and i is the index of the current time point.

5. The clinical rehabilitation data management and evaluation system for patients with rhabdomyolysis according to claim 1, characterized in that: The curvature analysis module includes: The trend extraction submodule acquires the abnormal record set of the rehabilitation cycle rate and the patient's continuous index distribution table, extracts the time series of urinary sodium concentration, lactate dehydrogenase value and serum creatinine level, constructs the trend sequence of the index in time order, and generates the index time trend sequence value. The curvature calculation submodule, based on the time trend sequence value of the indicator, calls the indicator data of adjacent time nodes, analyzes the change pattern within the time period, constructs the curvature sequence corresponding to the indicator in sequence, and generates the indicator curvature change trend value. The inflection point identification submodule determines the direction of change of adjacent nodes based on the curvature change trend value of the indicators, identifies the location of curvature abrupt change, filters the co-occurrence nodes of the three indicators, and obtains a set of curvature linkage inflection points.

6. The clinical rehabilitation data management and evaluation system for patients with rhabdomyolysis according to claim 5, characterized in that: The node identification module includes: The inflection point extraction submodule obtains the time series corresponding to the two sets based on the curvature linkage inflection point set and the rehabilitation cycle rate abnormal record set, determines whether the data of the two sets exist at the same timestamp, and generates the intersection time node set by matching the timestamp intersection between the sets. The parameter linkage judgment submodule calls the creatine kinase value and blood potassium concentration value corresponding to the time points of the intersection time node set, judges whether the change direction of creatine kinase value and the change direction of blood potassium concentration are the same, and filters the time nodes with the same change direction through the direction consistency judgment operation to generate a parameter consistency node sequence. The risk label generation submodule establishes a joint trend direction label based on the direction of change of creatine kinase value and the direction of change of blood potassium concentration corresponding to each time node in the parameter consistency node sequence. By pairing the trend label with the time node set, a risk joint evolution node label set is generated.

7. The clinical rehabilitation data management and evaluation system for patients with rhabdomyolysis according to claim 1, characterized in that: The system also includes: The trend construction module calls the risk co-evolution node label set, extracts myoglobin values ​​and serum creatinine levels within the associated time period, calculates the proportion of indicators with consistent change directions, marks the corresponding trend range, and generates a fluctuation trend channel map of the rehabilitation stage. The fluctuation trend channel map of the rehabilitation stage includes the proportion of consistent indicators and the labeling of trend range within the associated time period.

8. The clinical rehabilitation data management and evaluation system for patients with rhabdomyolysis according to claim 7, characterized in that: The trend construction module includes: The data extraction submodule obtains the time range of the risk co-evolution node labels, collects the myoglobin value and serum creatinine level within the corresponding time period, aligns the time granularity, calculates the total number of samples and the two types of indicator values ​​at the corresponding time points, and generates a set of aligned indicators for myoglobin and serum creatinine. The indicator comparison submodule, based on the set of aligned indicators of myoglobin and serum creatinine, extracts indicator values ​​at continuous time points, determines whether the change directions of the two indicators are consistent, and calculates the proportion of time periods in which the myoglobin value and serum creatinine level are consistent, generating the indicator change consistency rate. The trend generation submodule marks the time period within the consistent direction interval based on the consistency rate of the indicator changes, extracts the maximum and minimum values ​​of myoglobin and serum creatinine to construct upper and lower boundaries, connects the boundary nodes to construct a channel map, and obtains the channel map of the fluctuation trend in the rehabilitation stage.

Images