CN120600266B - A hemodialysis data processing method and system - Google Patents
A hemodialysis data processing method and systemInfo
- Publication number
- CN120600266B CN120600266B CN202511097406.0A CN202511097406A CN120600266B CN 120600266 B CN120600266 B CN 120600266B CN 202511097406 A CN202511097406 A CN 202511097406A CN 120600266 B CN120600266 B CN 120600266B
- Authority
- CN
- China
- Prior art keywords
- data
- patient
- physiological data
- instrument
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- External Artificial Organs (AREA)
Abstract
The invention discloses a data processing method and a system for hemodialysis, which relate to the technical field of hemodialysis and comprise the following steps of firstly, collecting instrument core parameters in real time through a sensor arranged in a dialysis instrument, collecting physiological data of a patient in real time through a circulating pipeline sensor arranged outside the patient, collecting environmental interference data in real time through a sensor arranged in a dialysis chamber, carrying out standardized processing, determining error sources according to an autocorrelation analysis result, a cross-correlation analysis result and a longitudinal trend analysis result, carrying out layering correction on the instrument core parameters, the physiological data of the patient and the environmental interference data, triggering a dialysis instrument self-checking program on internal errors, adopting adaptive filtering on external errors, establishing a patient error model on individual specific interference, outputting calibrated data, carrying out targeted processing on the errors, improving the accuracy of hemodialysis data processing, and being beneficial to improving the treatment effect of hemodialysis.
Description
Technical Field
The invention relates to the technical field of hemodialysis, in particular to a data processing method and system for hemodialysis.
Background
Hemodialysis is one of kidney replacement treatment modes of patients with acute and chronic renal failure, and is characterized in that in-vivo blood is drained to the outside of the body, and is subjected to substance exchange with electrolyte solution (dialysate) with similar concentration of an organism inside and outside the hollow fiber through a dialyzer consisting of innumerable hollow fibers, so that metabolic wastes in the body are removed, balance between electrolyte and acid and alkali is maintained, excessive moisture in the body is removed, and the whole process of back transfusion of the purified blood is called hemodialysis;
In the traditional hemodialysis data processing process, due to the fact that dialysis instruments are operated for a long time, hardware parts of the dialysis instruments often have faults, collected related instrument data are inaccurate, physiological characteristics of different patients are different, collected data are affected by environmental factors of a dialysis room, error sources are inconvenient to identify timely and accurately in the existing hemodialysis data processing process, due to the fact that effective error identification is lacking, all errors are often treated as the same type in the traditional method, targeted correction measures cannot be adopted according to different error sources, and when the situation of complex and changeable errors is faced, deviation of data processing results is easy to occur, and accurate assessment of dialysis sufficiency is affected.
Accordingly, the present invention provides a data processing method and system for hemodialysis to overcome and ameliorate the shortcomings of the prior art.
Disclosure of Invention
In order to solve the technical problems, the invention provides a data processing method and a system for hemodialysis, which are used for solving the corresponding technical problems in the background art.
In order to achieve the above purpose, the invention adopts the technical scheme that the data processing method for hemodialysis comprises the following steps:
Firstly, collecting instrument core parameters in real time through a sensor arranged in a dialysis instrument, collecting physiological data of a patient in real time through a circulating pipeline sensor arranged outside the patient, collecting environmental interference data in real time through a sensor arranged in a dialysis chamber, and performing standardized processing;
Acquiring acquisition frequency of instrument core parameters, acquisition frequency of patient physiological data and acquisition frequency of environmental interference data, performing cubic spline interpolation on low acquisition frequency parameters according to the highest acquisition frequency parameters serving as a reference time axis, generating virtual sampling values at the time points of the highest acquisition frequency parameters, and associating the virtual sampling values of the instrument core parameters, the virtual sampling values of the patient physiological data and the virtual sampling values of the environmental interference data at the same time point to form a time sequence matrix;
Defining an error type as an internal error caused by hardware faults of a dialysis instrument and an external error caused by environmental interference or individual differences of a patient, performing autocorrelation analysis on a virtual sampling value of a core parameter of the instrument based on a time sequence matrix, marking a high-frequency fault point in combination with a history maintenance record of the dialysis instrument, performing cross-correlation analysis on the virtual sampling value of environmental interference data and the virtual sampling value of physiological data of the patient, calculating an interference coupling coefficient, performing longitudinal trend analysis on data of the same patient for multiple treatments, identifying individual specific interference characteristics, and determining an error source according to an autocorrelation analysis result, a cross-correlation analysis result and a longitudinal trend analysis result;
and fourthly, carrying out layered correction on instrument core parameters, patient physiological data and environmental interference data based on error sources, triggering a dialysis instrument self-checking program on internal errors, adopting self-adaptive filtering on external errors, establishing a patient error model on individual specific interference, and outputting calibrated data.
Preferably, the instrument core parameters comprise blood pump rotation speed, transmembrane pressure and ultrafiltration rate, the patient physiological data comprise systolic pressure, venous pressure and activated clotting time, and the environment interference data comprise room temperature, power frequency noise intensity and illumination intensity.
Preferably, the specific process of marking the high-frequency fault point is as follows:
s101, acquiring acquisition frequency of instrument core parameters, acquisition frequency of patient physiological data and acquisition frequency of environmental interference data, taking a time axis corresponding to the highest acquisition frequency parameter as a reference time axis, wherein time points are sequentially as follows ;
The actual collection time point and the corresponding value of the low collection frequency parameter are taken as known data points, a cubic spline function is constructed between every two adjacent data points, and based on the constructed cubic spline function, the corresponding function value is calculated at each time point of the reference time axis, so that a virtual sampling value of the low collection frequency parameter on the reference time axis is obtained;
combining the virtual sampling value of the instrument core parameter, the virtual sampling value of the patient physiological data and the virtual sampling value of the environment interference data at the same time point to form a data row, and sequentially arranging the data rows corresponding to all the time points according to the time sequence of a reference time axis to form a time sequence matrix;
S102, calculating autocorrelation coefficients under different hysteresis orders k (k=0, 1,2,) according to the virtual sampling values of the instrument core parameters The calculation formula is as follows:
;
Wherein, the Representing a virtual sampling value of the instrument core parameter at an ith time point in the time sequence matrix;
Representing the average value of the virtual sampling values of the instrument core parameter at all time points;
respectively calculating autocorrelation coefficients of the blood pump rotating speed a, the transmembrane pressure b and the ultrafiltration rate c under different hysteresis orders to obtain a group of autocorrelation coefficient sequences respectively 、And;
S103, according to a preset autocorrelation coefficient thresholdFor each instrument core parameter, when the autocorrelation coefficients are the autocorrelation coefficient sequencesIs greater than the absolute value ofAt the time, the abnormal correlation exists between the value of the instrument core parameter and the value of the instrument core parameter at other time points under the hysteresis order k, and the corresponding hysteresis order k and the time point are recorded, wherein,Is the starting position of the point in time involved in the current calculation of the autocorrelation coefficients,Is relative to the starting time pointA time point after k time units;
Will exceed Is preliminarily marked as potential fault points to form a preliminary fault point set;
S104, acquiring a history maintenance record from a maintenance database of the dialysis instrument, and for the primary fault point setEach time point of (3)If inBefore and after the maintenance record related to the hardware fault of the dialysis instrument exists, the time point is thenFrom a set of preliminary fault pointsRemoving, screening to obtain a screened fault point set;
For the filtered fault point setEach time point of (3)Marking is performed in the time series matrix, and the time series matrix marked with the high-frequency fault points is output.
Preferably, the specific process of calculating the interference coupling coefficient is as follows:
S201, obtaining and combining virtual sampling values of environment interference data and virtual sampling values of patient physiological data at the same time point from a time sequence matrix, and respectively calculating cross-correlation coefficients of the virtual sampling values of the environment interference data and the virtual sampling values of the patient physiological data under different hysteresis orders m (m=0, 1, 2.) The calculation formula is as follows:
;
Wherein, the Representing a virtual sampling value of the environment interference data at a q-th time point in the time sequence matrix;
representing the average value of the virtual sampling values of the environmental interference data at all n time points;
Representing virtual sampling values of the physiological data of the patient at the (q+m) th time point in the time sequence matrix;
Representing virtual sample values of the patient physiological data at a q-th time point in the time series matrix;
representing an average of the virtual sample values of the patient physiological data at all n time points;
calculating the cross-correlation coefficients of the room temperature and the systolic pressure, the room temperature and the venous pressure, the room temperature and the activated coagulation time, the power frequency noise intensity and the systolic pressure, the power frequency noise intensity and the venous pressure, the power frequency noise intensity and the activated coagulation time, the illumination intensity and the systolic pressure, the illumination intensity and the venous pressure and the activated coagulation time under different hysteresis orders respectively to obtain a plurality of groups of cross-correlation coefficient sequences;
s202, according to a preset cross-correlation coefficient threshold value For each group of calculated cross-correlation coefficient sequences, finding out the value with the maximum absolute value of the cross-correlation coefficient and the corresponding hysteresis order, if the maximum absolute value exceeds the cross-correlation coefficient threshold valueIndicating that there is a high correlation between the ambient interference data and the patient physiological data, the maximum absolute value is taken as the interference coupling coefficient of the corresponding ambient interference data and the patient physiological data combination.
Preferably, the specific process of identifying individual specific interference features is as follows:
S301, obtaining virtual sampling values of core parameters of the same patient instrument at all time points, virtual sampling values of physiological data of the patient at all time points and virtual sampling values of environmental interference data at all time points through a time sequence matrix, and sorting data of each treatment into a matrix form according to the time sequence of the treatment, wherein each row represents one treatment, and each column corresponds to the values of the various data at different time points respectively;
S302, calculating the mean value of the physiological data of each patient aiming at the physiological data of each patient in each treatment of the patient The calculation formula is as follows:
;
wherein u is the virtual sampling point number of the physiological data of the patient in the treatment process;
is the p-th virtual sampling point value;
the contraction pressure, the venous pressure and the activated clotting time of each treatment of the patient are calculated respectively to obtain the average value of physiological data of each patient in each treatment;
s303, calculating the variance of the physiological data of each patient in each treatment The calculation formula is as follows:
;
The contraction pressure, the venous pressure and the activated clotting time of each treatment are respectively calculated to obtain the variance of physiological data of each patient in each treatment;
S304, comparing the mean value and the variance of different treatment times of the same patient, and if the mean value and the variance combination of the physiological data of the patient repeatedly appear in multiple treatments, primarily determining the combination as an individual specific interference characteristic;
The treatment times are taken as an abscissa, the mean value of physiological data of a patient is taken as an ordinate, a trend graph of the mean value changing along with the treatment times is drawn, the change trend of the mean value is observed, a linear regression method is used for fitting a change curve of the mean value along with the treatment times, a regression coefficient is calculated, and if the regression coefficient is not zero, the fact that the mean value has the linear change trend is indicated;
Taking the treatment times as an abscissa, taking the variance of the physiological data of the patient as an ordinate, drawing a trend graph of variance variation along with the treatment times, observing the variation trend of the variance, observing the periodical variation of the variance along with the increase of the treatment times by adopting a moving average method, and if the physiological data of the patient gradually rises along with the treatment times and the variance of the physiological data of the patient also shows the increasing trend, and the variation mode continuously exists in multiple treatments, further determining that the combination is an individual specific interference characteristic.
Preferably, the specific process of determining the error source is as follows:
S401, acquiring a high-frequency fault point of an autocorrelation analysis mark, combining a dialysis instrument historical maintenance record, and determining an internal error caused by hardware fault of the dialysis instrument if abnormal change exists in a core parameter of the instrument at a certain time point and the relevant maintenance record exists near the time point in the historical maintenance record;
S402, acquiring an interference coupling coefficient obtained through cross-correlation analysis and calculation, selecting a median as a preset standard threshold based on a distribution range of the interference coupling coefficient between the environmental interference data and the physiological data of the patient in a normal state, and determining an external error caused by the environmental interference if the interference coupling coefficient between the environmental interference data and the physiological data of the patient is greater than the preset standard threshold;
S403, acquiring individual specific interference characteristics identified by longitudinal trend analysis, and determining an external error caused by individual differences of patients if the instrument core parameters are not changed abnormally and no relevant maintenance record exists at the time point, and meanwhile, the interference coupling coefficient between the environmental interference data and the physiological data of the patients does not exceed a preset standard threshold value, and the individual specific interference characteristics exist in the physiological data of the patients.
Preferably, the specific process of outputting the calibrated data is as follows:
s501, triggering a dialysis instrument self-checking program when determining that the error source is an internal error caused by the hardware fault of the dialysis instrument, maintaining the hardware of the dialysis instrument and replacing a fault part, and processing environment interference data by adopting an adaptive filtering method when determining that the error source is an external error caused by the environment interference;
s502, when determining that the error source is an external error caused by individual difference of a patient, establishing a patient error model for individual specific interference by a regression analysis method by taking patient age, weight, environmental interference data and instrument core parameters as independent variables and patient physiological data as dependent variables, wherein the formula is as follows:
;
wherein Z is patient physiological data;
age of the patient;
Is the weight of the patient;
y is environmental interference data;
x is an instrument core parameter;
Are regression coefficients;
Is an error term;
Training and optimizing a patient error model through historical patient physiological data, historical environment interference data and historical instrument core parameters, and determining a regression coefficient value to obtain an updated patient error model;
s503, according to the processing results of different error types, correcting the instrument core parameters, the environmental interference data and the physiological data of the patient, recording the corrected data in a data record file, marking corresponding positions in a time sequence matrix, and outputting the corrected data according to a specified format.
A data processing system for hemodialysis comprises a data acquisition unit, a data processing unit, an error analysis unit and an error calibration unit;
The data acquisition unit is used for acquiring instrument core parameters in real time through a sensor arranged in the dialysis instrument, acquiring physiological data of a patient in real time through a circulating pipeline sensor arranged outside the patient, acquiring environmental interference data in real time through a sensor arranged in the dialysis chamber and carrying out standardized processing;
The data processing unit is used for acquiring the acquisition frequency of the instrument core parameters, the patient physiological data and the environment interference data, performing cubic spline interpolation on the low acquisition frequency parameters according to the highest acquisition frequency parameters serving as a reference time axis, generating virtual sampling values at the time points of the highest acquisition frequency parameters, and associating the virtual sampling values of the instrument core parameters, the virtual sampling values of the patient physiological data and the virtual sampling values of the environment interference data at the same time point to form a time sequence matrix;
The error analysis unit is used for defining the error type as an internal error caused by hardware faults of a dialysis instrument and an external error caused by environmental interference or individual difference of a patient, carrying out autocorrelation analysis on a virtual sampling value of a core parameter of the instrument based on a time sequence matrix, detecting periodic deviation, marking a high-frequency fault point in combination with a history maintenance record of the dialysis instrument, carrying out cross-correlation analysis on the virtual sampling value of environmental interference data and physiological data of the patient, calculating an interference coupling coefficient, carrying out longitudinal comparison on data of multiple treatments of the same patient, identifying individual specific interference, and determining an error source according to an autocorrelation analysis result, a cross-correlation analysis result and a longitudinal comparison result;
The error calibration unit is used for carrying out layered correction on instrument core parameters, patient physiological data and environment interference data based on error sources, triggering a dialysis instrument self-checking program on internal errors, adopting self-adaptive filtering on external errors, establishing a patient-specific error model on individual specific interference, and outputting calibrated data.
Compared with the prior art, the invention has the beneficial effects that: the method comprises the steps of acquiring instrument core parameters, patient physiological data and environmental interference data, acquiring acquisition frequencies of the instrument core parameters, the patient physiological data and the environmental interference data, performing tertiary spline interpolation on low acquisition frequency parameters according to the highest acquisition frequency parameters serving as a reference time axis, generating virtual sampling values at the highest acquisition frequency parameter time points, correlating the virtual sampling values of the instrument core parameters, the patient physiological data and the environmental interference data at the same time points to form a time sequence matrix, defining error types as internal errors caused by dialysis instrument hardware faults and external errors caused by environmental interference or patient individual differences, performing autocorrelation analysis on the virtual sampling values of the instrument core parameters, combining dialysis instrument history maintenance records, marking high-frequency fault points, performing cross-correlation analysis on the virtual sampling values of the environmental interference data and the virtual sampling values of the patient physiological data, calculating interference coupling coefficients, performing longitudinal trend analysis on data of the same patient multi-treatment, identifying individual specific interference characteristics, determining error sources according to the autocorrelation analysis results, the error sources, the dialysis instrument core parameters, the patient physiological data and the environmental interference data, and the external error caused by the individual difference, performing self-correlation analysis on the dialysis instrument, setting up an accurate correction on the hemodialysis instrument, and performing self-adaptive processing on the hemodialysis instrument, improving the blood error, correcting the blood error, and improving the blood-dialysis instrument accuracy, and the blood-dialysis data, and the self-correction model, and improving the accuracy, the safety of hemodialysis treatment is improved, and the risk of complications is reduced.
Drawings
FIG. 1 is a schematic diagram of the overall structure of a preferred embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiments of the invention:
Referring to fig. 1, a data processing method for hemodialysis includes the following steps:
Firstly, collecting instrument core parameters in real time through a sensor arranged in a dialysis instrument, collecting physiological data of a patient in real time through a circulating pipeline sensor arranged outside the patient, collecting environmental interference data in real time through a sensor arranged in a dialysis chamber, and performing standardized processing;
Acquiring acquisition frequency of instrument core parameters, acquisition frequency of patient physiological data and acquisition frequency of environmental interference data, performing cubic spline interpolation on low acquisition frequency parameters according to the highest acquisition frequency parameters serving as a reference time axis, generating virtual sampling values at the time points of the highest acquisition frequency parameters, and associating the virtual sampling values of the instrument core parameters, the virtual sampling values of the patient physiological data and the virtual sampling values of the environmental interference data at the same time point to form a time sequence matrix;
Defining an error type as an internal error caused by hardware faults of a dialysis instrument and an external error caused by environmental interference or individual differences of a patient, performing autocorrelation analysis on a virtual sampling value of a core parameter of the instrument based on a time sequence matrix, marking a high-frequency fault point in combination with a history maintenance record of the dialysis instrument, performing cross-correlation analysis on the virtual sampling value of environmental interference data and the virtual sampling value of physiological data of the patient, calculating an interference coupling coefficient, performing longitudinal trend analysis on data of the same patient for multiple treatments, identifying individual specific interference characteristics, and determining an error source according to an autocorrelation analysis result, a cross-correlation analysis result and a longitudinal trend analysis result;
and fourthly, carrying out layered correction on instrument core parameters, patient physiological data and environmental interference data based on error sources, triggering a dialysis instrument self-checking program on internal errors, adopting self-adaptive filtering on external errors, establishing a patient error model on individual specific interference, and outputting calibrated data.
The instrument core parameters comprise blood pump rotation speed, transmembrane pressure and ultrafiltration rate, the physiological data of patients comprise systolic pressure, venous pressure and activated clotting time, and the environmental interference data comprise room temperature, power frequency noise intensity and illumination intensity.
The specific process of marking the high-frequency fault point is as follows:
s101, acquiring acquisition frequency of instrument core parameters, acquisition frequency of patient physiological data and acquisition frequency of environmental interference data, taking a time axis corresponding to the highest acquisition frequency parameter as a reference time axis, wherein time points are sequentially as follows ;
The actual collection time point and the corresponding value of the low collection frequency parameter are taken as known data points, a cubic spline function is constructed between every two adjacent data points, and based on the constructed cubic spline function, the corresponding function value is calculated at each time point of the reference time axis, so that a virtual sampling value of the low collection frequency parameter on the reference time axis is obtained;
combining the virtual sampling value of the instrument core parameter, the virtual sampling value of the patient physiological data and the virtual sampling value of the environment interference data at the same time point to form a data row, and sequentially arranging the data rows corresponding to all the time points according to the time sequence of a reference time axis to form a time sequence matrix;
S102, calculating autocorrelation coefficients under different hysteresis orders k (k=0, 1,2,) according to the virtual sampling values of the instrument core parameters The calculation formula is as follows:
;
Wherein, the Representing a virtual sampling value of the instrument core parameter at an ith time point in the time sequence matrix;
Representing the average value of the virtual sampling values of the instrument core parameter at all time points;
respectively calculating autocorrelation coefficients of the blood pump rotating speed a, the transmembrane pressure b and the ultrafiltration rate c under different hysteresis orders to obtain a group of autocorrelation coefficient sequences respectively 、And;
S103, according to a preset autocorrelation coefficient thresholdFor each instrument core parameter, when the autocorrelation coefficients are the autocorrelation coefficient sequencesIs greater than the absolute value ofAt the time, the abnormal correlation exists between the value of the instrument core parameter and the value of the instrument core parameter at other time points under the hysteresis order k, and the corresponding hysteresis order k and the time point are recorded, wherein,Is the starting position of the point in time involved in the current calculation of the autocorrelation coefficients,Is relative to the starting time pointA time point after k time units;
Will exceed Is preliminarily marked as potential fault points to form a preliminary fault point set;
S104, acquiring a history maintenance record from a maintenance database of the dialysis instrument, and for the primary fault point setEach time point of (3)If inBefore and after the maintenance record related to the hardware fault of the dialysis instrument exists, the time point is thenFrom a set of preliminary fault pointsRemoving, screening to obtain a screened fault point set;
For the filtered fault point setEach time point of (3)Marking is performed in the time series matrix, and the time series matrix marked with the high-frequency fault points is output.
The specific process of calculating the interference coupling coefficient is as follows:
S201, obtaining and combining virtual sampling values of environment interference data and virtual sampling values of patient physiological data at the same time point from a time sequence matrix, and respectively calculating cross-correlation coefficients of the virtual sampling values of the environment interference data and the virtual sampling values of the patient physiological data under different hysteresis orders m (m=0, 1, 2.) The calculation formula is as follows:
;
Wherein, the Representing a virtual sampling value of the environment interference data at a q-th time point in the time sequence matrix;
representing the average value of the virtual sampling values of the environmental interference data at all n time points;
Representing virtual sampling values of the physiological data of the patient at the (q+m) th time point in the time sequence matrix;
Representing virtual sample values of the patient physiological data at a q-th time point in the time series matrix;
representing an average of the virtual sample values of the patient physiological data at all n time points;
calculating the cross-correlation coefficients of the room temperature and the systolic pressure, the room temperature and the venous pressure, the room temperature and the activated coagulation time, the power frequency noise intensity and the systolic pressure, the power frequency noise intensity and the venous pressure, the power frequency noise intensity and the activated coagulation time, the illumination intensity and the systolic pressure, the illumination intensity and the venous pressure and the activated coagulation time under different hysteresis orders respectively to obtain a plurality of groups of cross-correlation coefficient sequences;
s202, according to a preset cross-correlation coefficient threshold value For each group of calculated cross-correlation coefficient sequences, finding out the value with the maximum absolute value of the cross-correlation coefficient and the corresponding hysteresis order, if the maximum absolute value exceeds the cross-correlation coefficient threshold valueIndicating that there is a high correlation between the ambient interference data and the patient physiological data, the maximum absolute value is taken as the interference coupling coefficient of the corresponding ambient interference data and the patient physiological data combination.
The specific process of identifying individual specific interference features is as follows:
S301, obtaining virtual sampling values of core parameters of the same patient instrument at all time points, virtual sampling values of physiological data of the patient at all time points and virtual sampling values of environmental interference data at all time points through a time sequence matrix, and sorting data of each treatment into a matrix form according to the time sequence of the treatment, wherein each row represents one treatment, and each column corresponds to the values of the various data at different time points respectively;
S302, calculating the mean value of the physiological data of each patient aiming at the physiological data of each patient in each treatment of the patient The calculation formula is as follows:
;
wherein u is the virtual sampling point number of the physiological data of the patient in the treatment process;
is the p-th virtual sampling point value;
the contraction pressure, the venous pressure and the activated clotting time of each treatment of the patient are calculated respectively to obtain the average value of physiological data of each patient in each treatment;
s303, calculating the variance of the physiological data of each patient in each treatment The calculation formula is as follows:
;
The contraction pressure, the venous pressure and the activated clotting time of each treatment are respectively calculated to obtain the variance of physiological data of each patient in each treatment;
S304, comparing the mean value and the variance of different treatment times of the same patient, and if the mean value and the variance combination of the physiological data of the patient repeatedly appear in multiple treatments, primarily determining the combination as an individual specific interference characteristic;
The treatment times are taken as an abscissa, the mean value of physiological data of a patient is taken as an ordinate, a trend graph of the mean value changing along with the treatment times is drawn, the change trend of the mean value is observed, a linear regression method is used for fitting a change curve of the mean value along with the treatment times, a regression coefficient is calculated, and if the regression coefficient is not zero, the fact that the mean value has the linear change trend is indicated;
Taking the treatment times as an abscissa, taking the variance of the physiological data of the patient as an ordinate, drawing a trend graph of variance variation along with the treatment times, observing the variation trend of the variance, observing the periodical variation of the variance along with the increase of the treatment times by adopting a moving average method, and if the physiological data of the patient gradually rises along with the treatment times and the variance of the physiological data of the patient also shows the increasing trend, and the variation mode continuously exists in multiple treatments, further determining that the combination is an individual specific interference characteristic.
The specific process of determining the error source is as follows:
S401, acquiring a high-frequency fault point of an autocorrelation analysis mark, combining a dialysis instrument historical maintenance record, and determining an internal error caused by hardware fault of the dialysis instrument if abnormal change exists in a core parameter of the instrument at a certain time point and the relevant maintenance record exists near the time point in the historical maintenance record;
S402, acquiring an interference coupling coefficient obtained through cross-correlation analysis and calculation, selecting a median as a preset standard threshold based on a distribution range of the interference coupling coefficient between the environmental interference data and the physiological data of the patient in a normal state, and determining an external error caused by the environmental interference if the interference coupling coefficient between the environmental interference data and the physiological data of the patient is greater than the preset standard threshold;
S403, acquiring individual specific interference characteristics identified by longitudinal trend analysis, and determining an external error caused by individual differences of patients if the instrument core parameters are not changed abnormally and no relevant maintenance record exists at the time point, and meanwhile, the interference coupling coefficient between the environmental interference data and the physiological data of the patients does not exceed a preset standard threshold value, and the individual specific interference characteristics exist in the physiological data of the patients.
The specific process of outputting the calibrated data is as follows:
s501, triggering a dialysis instrument self-checking program when determining that the error source is an internal error caused by the hardware fault of the dialysis instrument, maintaining the hardware of the dialysis instrument and replacing a fault part, and processing environment interference data by adopting an adaptive filtering method when determining that the error source is an external error caused by the environment interference;
s502, when determining that the error source is an external error caused by individual difference of a patient, establishing a patient error model for individual specific interference by a regression analysis method by taking patient age, weight, environmental interference data and instrument core parameters as independent variables and patient physiological data as dependent variables, wherein the formula is as follows:
;
wherein Z is patient physiological data;
age of the patient;
Is the weight of the patient;
y is environmental interference data;
x is an instrument core parameter;
Are regression coefficients;
Is an error term;
Training and optimizing a patient error model through historical patient physiological data, historical environment interference data and historical instrument core parameters, and determining a regression coefficient value to obtain an updated patient error model;
s503, according to the processing results of different error types, correcting the instrument core parameters, the environmental interference data and the physiological data of the patient, recording the corrected data in a data record file, marking corresponding positions in a time sequence matrix, and outputting the corrected data according to a specified format.
A data processing system for hemodialysis comprises a data acquisition unit, a data processing unit, an error analysis unit and an error calibration unit;
The data acquisition unit is used for acquiring instrument core parameters in real time through a sensor arranged in the dialysis instrument, acquiring physiological data of a patient in real time through a circulating pipeline sensor arranged outside the patient, acquiring environmental interference data in real time through a sensor arranged in the dialysis chamber and performing standardized processing;
The data processing unit is used for acquiring the acquisition frequency of the instrument core parameters, the patient physiological data and the environment interference data, carrying out cubic spline interpolation on the low acquisition frequency parameters according to the highest acquisition frequency parameters serving as a reference time axis, generating virtual sampling values at the time points of the highest acquisition frequency parameters, and associating the virtual sampling values of the instrument core parameters, the virtual sampling values of the patient physiological data and the virtual sampling values of the environment interference data at the same time point to form a time sequence matrix;
The error analysis unit is used for defining the error type as an internal error caused by hardware faults of the dialysis instrument and an external error caused by environmental interference or individual difference of a patient, carrying out autocorrelation analysis on a virtual sampling value of a core parameter of the instrument based on a time sequence matrix, detecting periodic deviation, marking a high-frequency fault point in combination with a history maintenance record of the dialysis instrument, carrying out cross-correlation analysis on the virtual sampling value of environmental interference data and physiological data of the patient, calculating an interference coupling coefficient, carrying out longitudinal comparison on data of multiple treatments of the same patient, identifying individual specific interference, and determining an error source according to an autocorrelation analysis result, a cross-correlation analysis result and a longitudinal comparison result;
The error calibration unit is used for carrying out layering correction on instrument core parameters, patient physiological data and environment interference data based on error sources, triggering a dialysis instrument self-checking program on internal errors, adopting self-adaptive filtering on external errors, establishing a patient-specific error model on individual specific interference, and outputting calibrated data.
The method comprises the steps of acquiring instrument core parameters, patient physiological data and environmental interference data, acquiring acquisition frequencies of the instrument core parameters, the patient physiological data and the environmental interference data, performing tertiary spline interpolation on low acquisition frequency parameters according to the highest acquisition frequency parameters serving as a reference time axis, generating virtual sampling values at the highest acquisition frequency parameter time points, correlating the virtual sampling values of the instrument core parameters, the patient physiological data and the environmental interference data at the same time points to form a time sequence matrix, defining error types as internal errors caused by dialysis instrument hardware faults and external errors caused by environmental interference or patient individual differences, performing autocorrelation analysis on the virtual sampling values of the instrument core parameters, combining dialysis instrument history maintenance records, marking high-frequency fault points, performing cross-correlation analysis on the virtual sampling values of the environmental interference data and the virtual sampling values of the patient physiological data, calculating interference coupling coefficients, performing longitudinal trend analysis on data of the same patient multi-treatment, identifying individual specific interference characteristics, determining error sources according to the autocorrelation analysis results, the error sources, the dialysis instrument core parameters, the patient physiological data and the environmental interference data, and the external error caused by the individual difference, performing self-correlation analysis, triggering the hemodialysis instrument, improving the hemodialysis instrument self-adaptive treatment performance, improving the hemodialysis instrument self-adaptive performance, improving the hemodialysis instrument self-correction performance, and the hemodialysis instrument correction performance, and the blood-adaptive treatment model, improving the blood-quality, reducing the risk of complications.
The size of the interval and the threshold is set for the convenience of comparison, and the size of the threshold depends on the number of sample data and the number of cardinalities set for each group of sample data by a person skilled in the art, so long as the proportional relation between the parameter and the quantized value is not affected.
The formulas are all formulas with dimensions removed and numerical calculation, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by a person skilled in the art according to the actual situation;
In the two embodiments provided in the present application, it should be understood that the disclosed apparatus and system may be implemented in other manners, for example, the apparatus embodiments described above are merely illustrative, for example, the modules are divided into only one kind of logic function, and there may be other manners of dividing actually being implemented, for example, a plurality of modules or components may be combined or may be integrated into another system, or some features may be omitted or not implemented;
the foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511097406.0A CN120600266B (en) | 2025-08-06 | 2025-08-06 | A hemodialysis data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511097406.0A CN120600266B (en) | 2025-08-06 | 2025-08-06 | A hemodialysis data processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120600266A CN120600266A (en) | 2025-09-05 |
| CN120600266B true CN120600266B (en) | 2025-10-14 |
Family
ID=96891783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202511097406.0A Active CN120600266B (en) | 2025-08-06 | 2025-08-06 | A hemodialysis data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120600266B (en) |
Family Cites Families (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6788965B2 (en) * | 2001-08-03 | 2004-09-07 | Sensys Medical, Inc. | Intelligent system for detecting errors and determining failure modes in noninvasive measurement of blood and tissue analytes |
| US7050933B2 (en) * | 2001-08-24 | 2006-05-23 | Bio-Rad Laboratories, Inc. | Biometric quality control process |
| US8131463B2 (en) * | 2003-12-02 | 2012-03-06 | Gmv Aerospace And Defence, S.A. | GNSS navigation solution integrity in non-controlled environments |
| EP1729145B1 (en) * | 2005-06-02 | 2013-08-07 | GMV Aerospace and Defence S.A. | Method and system for providing GNSS navigation position solution with guaranteed integrity in non-controlled environments |
| CN103987337B (en) * | 2011-12-13 | 2017-05-17 | 皇家飞利浦有限公司 | Distorsion fingerprinting for EM tracking compensation, detection and error correction |
| US9076427B2 (en) * | 2012-05-10 | 2015-07-07 | Cirrus Logic, Inc. | Error-signal content controlled adaptation of secondary and leakage path models in noise-canceling personal audio devices |
| TWI717985B (en) * | 2020-01-30 | 2021-02-01 | 財團法人工業技術研究院 | Machine tool adjustment method and system thereof |
| CN114065114B (en) * | 2022-01-17 | 2022-04-15 | 武汉格蓝若智能技术有限公司 | A method and system for predicting measurement error of capacitive voltage transformer |
| WO2024141350A1 (en) * | 2022-12-26 | 2024-07-04 | Koninklijke Philips N.V. | Producing combined error values |
| CN117079794A (en) * | 2023-09-28 | 2023-11-17 | 淮安市第二人民医院 | Hemodialysis data information monitoring system based on Internet |
| CN117476175A (en) * | 2023-12-01 | 2024-01-30 | 华东医院 | Hemodialysis treatment system for nephrology department |
| CN118780642A (en) * | 2024-09-06 | 2024-10-15 | 国网山东省电力公司营销服务中心(计量中心) | A method and system for predicting power of photovoltaic power generation |
| CN118936542B (en) * | 2024-10-15 | 2025-03-04 | 临沂市计量检定所 | Meter metering detection calibration method and system |
| CN119004050B (en) * | 2024-10-24 | 2025-02-28 | 长春蓝天密封技术开发有限公司 | A metal gasket size measurement error analysis system and method |
| CN119574991A (en) * | 2024-11-15 | 2025-03-07 | 贵州兴黔信息科技有限公司 | A high-efficiency amplitude and phase test system for multi-channel passive antenna arrays |
| CN119276391B (en) * | 2024-12-09 | 2025-03-25 | 北京众谱达科技有限公司 | A method for error calibration of radio equipment under complex magnetic field interference |
| CN119394336B (en) * | 2025-01-03 | 2025-04-15 | 深圳市大晶光电科技有限公司 | A Gsensor automated testing method for IC environmental deviation |
| CN120085266A (en) * | 2025-03-04 | 2025-06-03 | 电子科技大学 | A RCS test calibration method under far-field conditions |
| CN120232464B (en) * | 2025-04-07 | 2025-11-21 | 江西天基电子科技有限公司 | A sensor error calibration method and system for a smartwatch |
| CN120351968A (en) * | 2025-04-07 | 2025-07-22 | 青岛智腾微电子有限公司 | Method and system for adjusting eccentric turntable in wide temperature range |
| CN120046084B (en) * | 2025-04-24 | 2025-08-22 | 深圳市川世达科技有限公司 | Intelligent calibration method and system for semiconductor testing equipment |
| CN120254739B (en) * | 2025-06-03 | 2025-08-19 | 广东米尔迪克智能机械实业有限公司 | High-frequency spark machine calibration method based on machining precision and stability control |
-
2025
- 2025-08-06 CN CN202511097406.0A patent/CN120600266B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN120600266A (en) | 2025-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2007344229B2 (en) | Follow-up of the vascular access of a dialyzed patient. | |
| CN116612891B (en) | Chronic patient data processing system | |
| US20220047789A1 (en) | Adequacy assessment method and system | |
| CN106999051A (en) | For detecting abnormal heart waveform and carrying out the devices, systems, and methods of physiological measure calculating | |
| EP3391255B1 (en) | System and method for detecting an operating state or a course of treatment during a blood treatment | |
| CN119074038B (en) | Cardiopulmonary sound data monitoring method and system based on big data | |
| CN116019429B (en) | Health monitoring method, device, equipment and storage medium based on physiological index | |
| CN119153070A (en) | Multi-parameter monitoring data analysis method | |
| CN118016305B (en) | Accurate diagnosis and treatment model construction method and system based on heart injury | |
| CN108877924A (en) | A kind of asthma method of determining probability and device | |
| CN120600266B (en) | A hemodialysis data processing method and system | |
| CN120072321B (en) | Intelligent nursing monitoring system and automatic analysis method for patient health data thereof | |
| CN118762851B (en) | An intelligent analysis method of medical records of pulmonary tuberculosis patients for early warning of hemoptysis | |
| CN118673389B (en) | Data collection system and data collection method of physical examination instrument | |
| CN119517374A (en) | Medical intelligent monitoring system and method based on smart bracelet | |
| CN117894461A (en) | Sleep quality assessment method, system, device, equipment and storage medium | |
| CN120570578B (en) | A method for real-time blood pressure monitoring in a blood sampling system | |
| CN120432077B (en) | Artificial intelligence-based venous catheter matching method and system | |
| CN120021984B (en) | Training methods, related equipment, and storage media for real-time blood glucose filtering models | |
| CN121122729A (en) | Health data modeling analysis method and system based on AI assistance | |
| CN118818067B (en) | Blood coagulation characteristic detection method and system based on household PT measurement | |
| CN118658644B (en) | Disease state change trend early warning system | |
| CN121237317A (en) | A method and system for analyzing the depth of anesthesia | |
| CN121191676A (en) | A multimodal physiological data monitoring system and method based on machine learning | |
| Serrano Alarcón et al. | Apnea-hypopnea index using deep learning models with whole and window-based time series |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |