Movatterモバイル変換


[0]ホーム

URL:


CN120600266A - Hemodialysis data processing method and system - Google Patents

Hemodialysis data processing method and system

Info

Publication number
CN120600266A
CN120600266ACN202511097406.0ACN202511097406ACN120600266ACN 120600266 ACN120600266 ACN 120600266ACN 202511097406 ACN202511097406 ACN 202511097406ACN 120600266 ACN120600266 ACN 120600266A
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.)
Granted
Application number
CN202511097406.0A
Other languages
Chinese (zh)
Other versions
CN120600266B (en
Inventor
李思思
吕红红
张苗苗
王欢
张姣姣
刘微娜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Air Force Medical University
Original Assignee
Air Force Medical University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Air Force Medical UniversityfiledCriticalAir Force Medical University
Priority to CN202511097406.0ApriorityCriticalpatent/CN120600266B/en
Priority claimed from CN202511097406.0Aexternal-prioritypatent/CN120600266B/en
Publication of CN120600266ApublicationCriticalpatent/CN120600266A/en
Application grantedgrantedCritical
Publication of CN120600266BpublicationCriticalpatent/CN120600266B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Landscapes

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

Hemodialysis data processing method and system
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 parametersThe calculation formula is as follows:
;
Wherein, theRepresenting 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 respectivelyAnd;
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 exceedIs 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, theRepresenting 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 valueFor 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 patientThe 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 treatmentThe 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 parametersThe calculation formula is as follows:
;
Wherein, theRepresenting 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 respectivelyAnd;
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 exceedIs 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, theRepresenting 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 valueFor 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 patientThe 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 treatmentThe 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 (8)

Translated fromChinese
1.一种血液透析的数据处理方法,其特征在于,包括以下步骤:1. A method for processing hemodialysis data, comprising the following steps:步骤一、通过设置在透析仪器内部的传感器实时采集仪器核心参数,通过设置在患者体外的循环管路传感器实时采集患者生理数据,通过设置在透析室室内的传感器实时采集环境干扰数据并进行标准化处理;Step 1: The core parameters of the dialysis instrument are collected in real time by sensors installed inside the dialysis instrument, the patient's physiological data are collected in real time by sensors installed in the circulation pipeline outside the patient's body, and the environmental interference data are collected in real time by sensors installed in the dialysis room and standardized;步骤二、获取仪器核心参数的采集频率、患者生理数据的采集频率以及环境干扰数据的采集频率,并根据最高采集频率参数为基准时间轴,对低采集频率参数进行三次样条插值,在最高采集频率参数时间点上生成虚拟采样值,将同一时间点的仪器核心参数的虚拟采样值、患者生理数据的虚拟采样值以及环境干扰数据的虚拟采样值进行关联,形成时间序列矩阵;Step 2: Obtain the acquisition frequency of the instrument core parameters, the acquisition frequency of the patient physiological data, and the acquisition frequency of the environmental interference data, and perform cubic spline interpolation on the low acquisition frequency parameters based on the highest acquisition frequency parameter as the reference time axis, generate virtual sampling values at the time point of the highest acquisition frequency parameter, and associate 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 series matrix;步骤三、将误差类型定义为由透析仪器硬件故障引起的内部误差以及由环境干扰或患者个体差异引起的外部误差,基于时间序列矩阵,对仪器核心参数的虚拟采样值进行自相关分析,结合透析仪器历史维护记录,标记高频故障点,对环境干扰数据的虚拟采样值与患者生理数据的虚拟采样值进行互相关分析,计算干扰耦合系数,对同一患者多次治疗的数据进行纵向趋势分析,识别个体特异性干扰特征,根据自相关分析结果、互相关分析结果以及纵向趋势分析结果确定误差来源;Step 3: Define the error types as internal errors caused by dialysis instrument hardware failures and external errors caused by environmental interference or individual patient differences. Based on the time series matrix, perform autocorrelation analysis on the virtual sampling values of the instrument's core parameters. Combined with the historical maintenance records of the dialysis instrument, mark high-frequency fault points. Perform cross-correlation analysis on the virtual sampling values of the environmental interference data and the virtual sampling values of the patient's physiological data, calculate the interference coupling coefficient, perform longitudinal trend analysis on the data of multiple treatments for the same patient, identify individual-specific interference characteristics, and determine the error source based on the results of the autocorrelation analysis, cross-correlation analysis, and longitudinal trend analysis.步骤四、基于误差来源,对仪器核心参数、患者生理数据以及环境干扰数据进行分层修正,对内部误差触发透析仪器自检程序,对外部误差采用自适应滤波,对个体特异性干扰建立患者误差模型,并输出校准后数据。Step 4: Based on the source of error, perform hierarchical corrections on the instrument core parameters, patient physiological data, and environmental interference data. Trigger the dialysis instrument self-test program for internal errors, use adaptive filtering for external errors, establish a patient error model for individual-specific interference, and output the calibrated data.2.根据权利要求1所述的一种血液透析的数据处理方法,其特征在于,所述仪器核心参数包括血泵转速、跨膜压以及超滤率,所述患者生理数据包括收缩压、静脉压以及活化凝血时间,所述环境干扰数据包括室温、工频噪声强度以及光照强度。2. A hemodialysis data processing method according to claim 1, characterized in that the instrument core parameters include blood pump speed, transmembrane pressure and ultrafiltration rate, the patient physiological data include systolic blood pressure, venous pressure and activated clotting time, and the environmental interference data includes room temperature, power frequency noise intensity and light intensity.3.根据权利要求2所述的一种血液透析的数据处理方法,其特征在于,标记高频故障点的具体过程如下:3. The hemodialysis data processing method according to claim 2, wherein the specific process of marking high-frequency fault points is as follows:S101、获取仪器核心参数的采集频率、患者生理数据的采集频率以及环境干扰数据的采集频率,将最高采集频率参数对应的时间轴作为基准时间轴,时间点依次为S101, obtain the acquisition frequency of the instrument core parameters, the acquisition frequency of the patient's physiological data, and the acquisition frequency of the environmental interference data, and use the time axis corresponding to the highest acquisition frequency parameter as the reference time axis. The time points are ;以低采集频率参数的实际采集时间点和对应数值作为已知数据点,在每两个相邻数据点之间构建一个三次样条函数,并基于构建好的三次样条函数,在基准时间轴的各个时间点上计算对应的函数值,得到低采集频率参数在基准时间轴上的虚拟采样值;The actual acquisition time points and corresponding values of the low acquisition frequency parameters are used as known data points, and a cubic spline function is constructed between every two adjacent data points. Based on the constructed cubic spline function, the corresponding function values are calculated at each time point on the reference time axis to obtain the virtual sampling values of the low acquisition frequency parameters on the reference time axis.将同一时间点的仪器核心参数的虚拟采样值、患者生理数据的虚拟采样值以及环境干扰数据的虚拟采样值组合形成数据行,按照基准时间轴的时间顺序,将所有时间点对应的数据行依次排列,以形成时间序列矩阵;The virtual sampling values of the instrument core parameters, the virtual sampling values of the patient's physiological data, and the virtual sampling values of the environmental interference data at the same time point are combined to form a data row. The data rows corresponding to all time points are arranged in sequence according to the time sequence of the reference time axis to form a time series matrix.S102、根据仪器核心参数的虚拟采样值,计算在不同滞后阶数k(k=0,1,2,…)下的自相关系数,其计算公式为:S102. Calculate the autocorrelation coefficients at different lag orders k (k = 0, 1, 2, ...) based on the virtual sampling values of the instrument core parameters. , and its calculation formula is: ;其中,表示仪器核心参数在时间序列矩阵中第i个时间点的虚拟采样值;in, Represents the virtual sampling value of the instrument core parameter at the i-th time point in the time series matrix;表示该仪器核心参数在所有时间点虚拟采样值的平均值; It represents the average value of the virtual sampling values of the instrument core parameters at all time points;分别计算血泵转速a、跨膜压b以及超滤率c在不同滞后阶数下的自相关系数,得到各自的一组自相关系数序列以及Calculate the autocorrelation coefficients of blood pump speed a, transmembrane pressure b and ultrafiltration rate c at different lag orders respectively, and obtain a set of autocorrelation coefficient sequences for each as well as ;S103、根据预设的自相关系数阈值,对于每个仪器核心参数的自相关系数序列,当自相关系数的绝对值超过时,说明在该滞后阶数k下,仪器核心参数的取值与自身在其他时间点的取值存在异常相关性,记录对应的滞后阶数k和时间点,其中,是当前计算自相关系数所涉及的时间点起始位置,是相对于起始时间点滞后k个时间单位后的时间点;S103, according to the preset autocorrelation coefficient threshold , for each instrument core parameter autocorrelation coefficient sequence, when the autocorrelation coefficient The absolute value exceeds When the lag order k is reached, it indicates that the value of the instrument core parameter is abnormally correlated with its own value at other time points. Record the corresponding lag order k and time point. ,in, is the starting position of the time point involved in the current calculation of the autocorrelation coefficient, Relative to the starting time point The time point after the lag of k time units;将超过的时间点初步标记为潜在的故障点,形成初步故障点集合will exceed The time points are initially marked as potential failure points to form a preliminary failure point set ;S104、从透析仪器的维护数据库中获取历史维护记录,对于初步故障点集合中的每一个时间点,若在前后存在与透析仪器硬件故障相关的维护记录,则将该时间点从初步故障点集合中移除,经过筛选后,得到筛选后的故障点集合S104, obtain historical maintenance records from the maintenance database of the dialysis instrument, and Every time point in , if in If there is a maintenance record related to the dialysis instrument hardware failure before and after, then the time point From the initial fault point collection Remove, and after screening, get the filtered fault point set ;对于筛选后的故障点集合中的每一个时间点,在时间序列矩阵中进行标记,并将标记了高频故障点的时间序列矩阵输出。For the filtered fault point set Every time point in , mark them in the time series matrix, and output the time series matrix with marked high-frequency fault points.4.根据权利要求3所述的一种血液透析的数据处理方法,其特征在于,计算干扰耦合系数的具体过程如下:4. The hemodialysis data processing method according to claim 3, wherein the specific process of calculating the interference coupling coefficient is as follows:S201、自时间序列矩阵中,获取相同时间点的环境干扰数据的虚拟采样值与患者生理数据的虚拟采样值并组合,对于环境干扰数据的虚拟采样值与患者生理数据的虚拟采样值的组合,分别计算其在不同滞后阶数m(m=0,1,2,…)下的互相关系数,其计算公式为:S201. Obtain virtual sampling values of environmental interference data and virtual sampling values of patient physiological data at the same time point from the time series matrix and combine them. For each combination of virtual sampling values of environmental interference data and virtual sampling values of patient physiological data, calculate their cross-correlation coefficients at different lag orders m (m=0, 1, 2, ...). , and its calculation formula is: ;其中,表示环境干扰数据在时间序列矩阵中第q个时间点的虚拟采样值;in, Represents the virtual sampling value of the environmental interference data at the qth time point in the time series matrix;表示该环境干扰数据在所有n个时间点虚拟采样值的平均值; Represents the average value of the virtual sampling values of the environmental interference data at all n time points;表示患者生理数据在时间序列矩阵中第q+m个时间点的虚拟采样值; Represents the virtual sampling value of the patient's physiological data at the q+mth time point in the time series matrix;表示患者生理数据在时间序列矩阵中第q个时间点的虚拟采样值; Represents the virtual sampling value of the patient's physiological data at the qth time point in the time series matrix;表示该患者生理数据在所有n个时间点虚拟采样值的平均值; Represents the average value of the virtual sampling values of the patient's physiological data at all n time points;分别计算室温与收缩压、室温与静脉压、室温与活化凝血时间、工频噪声强度与收缩压、工频噪声强度与静脉压、工频噪声强度与活化凝血时间、光照强度与收缩压、光照强度与静脉压、光照强度与活化凝血时间在不同滞后阶数下的互相关系数,得到多组互相关系数序列;The cross-correlation coefficients between room temperature and systolic blood pressure, room temperature and venous pressure, room temperature and activated clotting time, power frequency noise intensity and systolic blood pressure, power frequency noise intensity and venous pressure, power frequency noise intensity and activated clotting time, light intensity and systolic blood pressure, light intensity and venous pressure, and light intensity and activated clotting time at different lag orders were calculated respectively, and multiple sets of cross-correlation coefficient sequences were obtained;S202、根据预设的互相关系数阈值,对于每组计算得到的互相关系数序列,找出互相关系数绝对值最大的值及其对应的滞后阶数,若该最大绝对值超过互相关系数阈值,说明该环境干扰数据与患者生理数据之间存在高相关性,则将该最大绝对值作为对应环境干扰数据与患者生理数据组合的干扰耦合系数。S202: According to the preset mutual correlation coefficient threshold For each set of calculated cross-correlation coefficient sequences, find the value with the largest absolute value of the cross-correlation coefficient and its corresponding lag order. If the maximum absolute value exceeds the cross-correlation coefficient threshold , indicating that there is a high correlation between the environmental interference data and the patient's physiological data, the maximum absolute value is used as the interference coupling coefficient of the combination of the corresponding environmental interference data and the patient's physiological data.5.根据权利要求4所述的一种血液透析的数据处理方法,其特征在于,识别个体特异性干扰特征的具体过程如下:5. The hemodialysis data processing method according to claim 4, wherein the specific process of identifying individual-specific interference features is as follows:S301、通过时间序列矩阵获取同一患者仪器核心参数于各时间点的虚拟采样值、患者生理数据于各时间点的虚拟采样值以及环境干扰数据于各时间点的虚拟采样值,并按照治疗的时间顺序,将每次治疗的数据整理为矩阵形式,每一行代表一次治疗,各列分别对应上述各类数据在不同时间点的取值;S301. Obtain virtual sampling values of instrument core parameters, patient physiological data, and environmental interference data at each time point for the same patient through a time series matrix, and organize the data of each treatment into a matrix format according to the chronological order of the treatments, with each row representing one treatment and each column corresponding to the values of the aforementioned data at different time points.S302、针对患者每次治疗中的各项患者生理数据,计算患者生理数据的均值,其计算公式为:S302: Calculate the mean of each patient's physiological data for each treatment. , and its calculation formula is: ;其中,u是该次治疗过程中患者生理数据的虚拟采样点数;Where u is the number of virtual sampling points of the patient's physiological data during the treatment process;是第p个虚拟采样点值; is the value of the pth virtual sampling point;分别对患者每次治疗的收缩压、静脉压以及活化凝血时间进行上述计算,得到每次治疗中各项患者生理数据的均值;The above calculations were performed on the patient's systolic blood pressure, venous pressure, and activated clotting time for each treatment, and the mean values of the patient's physiological data for each treatment were obtained;S303、针对每次治疗中的各项患者生理数据,计算患者生理数据的方差,其计算公式为:S303: Calculate the variance of each patient's physiological data for each treatment. , and its calculation formula is: ;分别对每次治疗的收缩压、静脉压以及活化凝血时间进行上述计算,得到每次治疗中各项患者生理数据的方差;The above calculations were performed for the systolic blood pressure, venous pressure, and activated clotting time for each treatment, and the variance of each patient's physiological data in each treatment was obtained;S304、对同一患者不同治疗次数之间的均值和方差进行对比,若患者生理数据的均值和方差组合在多次治疗中反复出现,则初步确定该组合为个体特异性干扰特征;S304. Compare the means and variances of the same patient's physiological data between different treatment times. If a combination of the means and variances of the patient's physiological data appears repeatedly in multiple treatments, preliminarily determine that the combination is an individual-specific interference feature.以治疗次数为横坐标,患者生理数据均值为纵坐标,绘制均值随治疗次数变化的趋势图,观察均值的变化趋势,使用线性回归法拟合均值随治疗次数的变化曲线,计算回归系数,若回归系数不为零,则说明均值存在线性变化趋势;With the number of treatments as the horizontal axis and the mean of the patient's physiological data as the vertical axis, a trend graph of the mean changing with the number of treatments was drawn to observe the changing trend of the mean. The linear regression method was used to fit the curve of the mean changing with the number of treatments and the regression coefficient was calculated. If the regression coefficient was not zero, it indicated that the mean had a linear changing trend.以治疗次数为横坐标,患者生理数据方差为纵坐标,绘制方差随治疗次数变化的趋势图,观察方差的变化趋势,采用移动平均法观察方差随治疗次数的增加而呈现的周期性变化,若患者生理数据随治疗次数逐渐升高,同时其方差也呈现增大的趋势,且这种变化模式在多次治疗中持续存在,则进一步确定该组合为个体特异性干扰特征。With the number of treatments as the horizontal axis and the variance of the patient's physiological data as the vertical axis, a trend graph of the variance changing with the number of treatments was drawn to observe the changing trend of the variance. The moving average method was used to observe the cyclical changes in the variance with the increase in the number of treatments. If the patient's physiological data gradually increased with the number of treatments and its variance also showed an increasing trend, and this change pattern persisted in multiple treatments, then the combination was further determined to be an individual-specific interference feature.6.根据权利要求5所述的一种血液透析的数据处理方法,其特征在于,确定误差来源的具体过程如下:6. The hemodialysis data processing method according to claim 5, wherein the specific process of determining the error source is as follows:S401、获取自相关分析标记的高频故障点,结合透析仪器历史维护记录,若某时间点仪器核心参数存在异常变化,并在历史维护记录中此时间点附近有过相关的维护记录,则确定为由透析仪器硬件故障引起的内部误差;S401. Obtain high-frequency fault points marked by autocorrelation analysis and combine them with the historical maintenance records of the dialysis instrument. If there is an abnormal change in the instrument core parameters at a certain time point, and there is a related maintenance record near this time point in the historical maintenance records, it is determined that the error is caused by an internal dialysis instrument hardware failure.S402、获取互相关分析计算得到的干扰耦合系数,并基于常态下环境干扰数据与患者生理数据之间干扰耦合系数的分布范围,选取中位数作为预设标准阈值,若环境干扰数据与患者生理数据之间的干扰藕合系数大于预设标准阈值,则确定为由环境干扰引起的外部误差;S402. Obtaining the interference coupling coefficient calculated by cross-correlation analysis, and selecting the median as a preset standard threshold based on the distribution range of the interference coupling coefficient between the environmental interference data and the patient's physiological data under normal conditions. If the interference coupling coefficient between the environmental interference data and the patient's physiological data is greater than the preset standard threshold, it is determined to be an external error caused by environmental interference;S403、获取纵向趋势分析识别的个体特异性干扰特征,若仪器核心参数未出现异常变化且在该时间点无相关的维护记录,同时环境干扰数据与患者生理数据之间的干扰耦合系数也并未超过预设标准阈值,而患者生理数据存在个体特异性干扰特征,则确定为由患者个体差异引起的外部误差。S403. Obtain individual-specific interference characteristics identified by longitudinal trend analysis. If there are no abnormal changes in the instrument core parameters and there are no relevant maintenance records at that time point, and the interference coupling coefficient between the environmental interference data and the patient's physiological data does not exceed the preset standard threshold, and the patient's physiological data has individual-specific interference characteristics, then it is determined to be an external error caused by individual differences among patients.7.根据权利要求6所述的一种血液透析的数据处理方法,其特征在于,输出校准后数据的具体过程如下:7. The hemodialysis data processing method according to claim 6, wherein the specific process of outputting the calibrated data is as follows:S501、当确定误差来源为由透析仪器硬件故障引起的内部误差时,触发透析仪器自检程序,对透析仪器硬件进行维修和更换故障部件,当确定误差来源为由环境干扰引起的外部误差时,采用自适应滤波方法对环境干扰数据进行处理;S501. When it is determined that the error source is an internal error caused by a dialysis instrument hardware failure, the dialysis instrument self-test program is triggered to repair the dialysis instrument hardware and replace the faulty parts. When it is determined that the error source is an external error caused by environmental interference, the environmental interference data is processed using an adaptive filtering method.S502、当确定误差来源为由患者个体差异引起的外部误差时,以患者年龄、体重、环境干扰数据以及仪器核心参数为自变量,以患者生理数据为因变量,通过回归分析法对个体特异性干扰建立患者误差模型,其公式为:S502. When the error source is determined to be external error caused by individual patient differences, a patient error model is established for individual-specific interference using the patient's age, weight, environmental interference data, and instrument core parameters as independent variables and the patient's physiological data as dependent variables through regression analysis. The formula is: ;其中,Z为患者生理数据;Where Z is the patient's physiological data;为患者年龄; is the patient's age;为患者体重; is the patient's weight;Y为环境干扰数据;Y is the environmental interference data;X为仪器核心参数;X is the instrument core parameter;均为回归系数; All are regression coefficients;为误差项; is the error term;通过历史患者生理数据、历史环境干扰数据以及历史仪器核心参数,对患者误差模型进行训练和优化,确定回归系数的值,得到更新后的患者误差模型;The patient error model is trained and optimized through historical patient physiological data, historical environmental interference data, and historical instrument core parameters, and the value of the regression coefficient is determined to obtain an updated patient error model;S503、根据不同误差类型的处理结果,对仪器核心参数、环境干扰数据以及患者生理数据进行修正,并将修正后的数据记录在数据记录文件中,同时在时间序列矩阵中对应位置进行标记,并将校准后的数据按照规定格式输出。S503. According to the processing results of different error types, the instrument core parameters, environmental interference data and patient physiological data are corrected, and the corrected data are recorded in the data recording file. At the same time, the corresponding positions in the time series matrix are marked, and the calibrated data are output in the specified format.8.一种血液透析的数据处理系统,其特征在于,包括数据获取单元、数据处理单元、误差分析单元以及误差校准单元;8. A hemodialysis data processing system, comprising a data acquisition unit, a data processing unit, an error analysis unit, and an error calibration unit;所述数据获取单元用于通过设置在透析仪器内部的传感器实时采集仪器核心参数,通过设置在患者体外的循环管路传感器实时采集患者生理数据,通过设置在透析室室内的传感器实时采集环境干扰数据并进行标准化处理;The data acquisition unit is used to collect the core parameters of the dialysis instrument in real time through sensors installed inside the dialysis instrument, collect the patient's physiological data in real time through sensors installed in the circulation pipeline outside the patient's body, and collect environmental interference data in real time through sensors installed in the dialysis room and perform standardized processing;所述数据处理单元用于获取仪器核心参数、患者生理数据以及环境干扰数据的采集频率,并根据最高采集频率参数为基准时间轴,对低采集频率参数进行三次样条插值,在最高采集频率参数时间点上生成虚拟采样值,将同一时间点的仪器核心参数的虚拟采样值、患者生理数据的虚拟采样值以及环境干扰数据的虚拟采样值进行关联,形成时间序列矩阵;The data processing unit is used to obtain the acquisition frequency of the instrument core parameters, the patient physiological data, and the environmental interference data, and perform cubic spline interpolation on the low acquisition frequency parameters based on the highest acquisition frequency parameter as the reference time axis, generate virtual sampling values at the time point of the highest acquisition frequency parameter, and associate 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 series matrix;所述误差分析单元用于将误差类型定义为由透析仪器硬件故障引起的内部误差以及由环境干扰或患者个体差异引起的外部误差,基于时间序列矩阵,对仪器核心参数的虚拟采样值进行自相关分析,检测周期性偏差,结合透析仪器历史维护记录,标记高频故障点,对环境干扰数据的虚拟采样值与患者生理数据进行互相关分析,计算干扰耦合系数,对同一患者多次治疗的数据进行纵向对比,识别个体特异性干扰,根据自相关分析结果、互相关分析结果以及纵向对比结果确定误差来源;The error analysis unit is used to define the error type as internal error caused by dialysis instrument hardware failure and external error caused by environmental interference or individual patient differences. Based on the time series matrix, autocorrelation analysis is performed on the virtual sampling values of the instrument core parameters to detect periodic deviations. In combination with the historical maintenance records of the dialysis instrument, high-frequency fault points are marked. Cross-correlation analysis is performed on the virtual sampling values of the environmental interference data and the patient's physiological data to calculate the interference coupling coefficient. The data of multiple treatments for the same patient are longitudinally compared to identify individual-specific interference. The error source is determined based on the results of the autocorrelation analysis, cross-correlation analysis, and longitudinal comparison.所述误差校准单元用于基于误差来源,对仪器核心参数、患者生理数据以及环境干扰数据进行分层修正,对内部误差触发透析仪器自检程序,对外部误差采用自适应滤波,对个体特异性干扰建立患者专属误差模型,并输出校准后数据。The error calibration unit is used to perform hierarchical corrections on instrument core parameters, patient physiological data, and environmental interference data based on the source of the error, trigger the dialysis instrument self-test program for internal errors, use adaptive filtering for external errors, establish a patient-specific error model for individual-specific interference, and output calibrated data.
CN202511097406.0A2025-08-06 A hemodialysis data processing method and systemActiveCN120600266B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202511097406.0ACN120600266B (en)2025-08-06 A hemodialysis data processing method and system

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202511097406.0ACN120600266B (en)2025-08-06 A hemodialysis data processing method and system

Publications (2)

Publication NumberPublication Date
CN120600266Atrue CN120600266A (en)2025-09-05
CN120600266B CN120600266B (en)2025-10-14

Family

ID=

Citations (23)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20030060692A1 (en)*2001-08-032003-03-27Timothy L. RuchtiIntelligent system for detecting errors and determining failure modes in noninvasive measurement of blood and tissue analytes
EP1428021A1 (en)*2001-08-242004-06-16Bio-Rad Laboratories, Inc.Biometric quality control process
EP1729145A1 (en)*2005-06-022006-12-06Gmv, S.A.Method and system for providing GNSS navigation position solution with guaranteed integrity in non-controlled environments
US20100033370A1 (en)*2003-12-022010-02-11Gmv Aerospace And Defence, S.A.Gnss navigation solution integrity in non-controlled environments
CN103987337A (en)*2011-12-132014-08-13皇家飞利浦有限公司Distorsion fingerprinting for EM tracking compensation, detection and error correction
CN104303228A (en)*2012-05-102015-01-21美国思睿逻辑有限公司Error-signal content controlled adaptation of secondary and leakage path models in noise-canceling personal audio devices
US20210237218A1 (en)*2020-01-302021-08-05Industrial Technology Research InstituteMachine tool adjustment method and system thereof
CN114065114A (en)*2022-01-172022-02-18武汉格蓝若智能技术有限公司Method and system for predicting metering error of capacitive voltage transformer
CN117079794A (en)*2023-09-282023-11-17淮安市第二人民医院Hemodialysis data information monitoring system based on Internet
CN117476175A (en)*2023-12-012024-01-30华东医院Hemodialysis treatment system for nephrology department
WO2024141350A1 (en)*2022-12-262024-07-04Koninklijke Philips N.V.Producing combined error values
CN118780642A (en)*2024-09-062024-10-15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
CN118936542A (en)*2024-10-152024-11-12临沂市计量检定所 A method and system for instrument measurement detection and calibration
CN119004050A (en)*2024-10-242024-11-22长春蓝天密封技术开发有限公司System and method for analyzing dimension measurement errors of metal gasket
CN119276391A (en)*2024-12-092025-01-07北京众谱达科技有限公司 A method for error calibration of radio equipment under complex magnetic field interference
CN119394336A (en)*2025-01-032025-02-07深圳市大晶光电科技有限公司 A Gsensor automated testing method for IC environmental deviation
CN119574991A (en)*2024-11-152025-03-07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
CN120046084A (en)*2025-04-242025-05-27深圳市川世达科技有限公司 Intelligent calibration method and system for semiconductor testing equipment
CN120085266A (en)*2025-03-042025-06-03电子科技大学 A RCS test calibration method under far-field conditions
CN120232464A (en)*2025-04-072025-07-01江西天基电子科技有限公司 A sensor error calibration method and system for smart watch
CN120254739A (en)*2025-06-032025-07-04广东米尔迪克智能机械实业有限公司 A high frequency spark machine calibration method based on machining accuracy and stability control
CN120314529A (en)*2025-05-192025-07-15陕西麟云超算科技有限公司 A system and method for error correction of marine environment observation data
CN120351968A (en)*2025-04-072025-07-22青岛智腾微电子有限公司Method and system for adjusting eccentric turntable in wide temperature range

Patent Citations (23)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20030060692A1 (en)*2001-08-032003-03-27Timothy L. RuchtiIntelligent system for detecting errors and determining failure modes in noninvasive measurement of blood and tissue analytes
EP1428021A1 (en)*2001-08-242004-06-16Bio-Rad Laboratories, Inc.Biometric quality control process
US20100033370A1 (en)*2003-12-022010-02-11Gmv Aerospace And Defence, S.A.Gnss navigation solution integrity in non-controlled environments
EP1729145A1 (en)*2005-06-022006-12-06Gmv, S.A.Method and system for providing GNSS navigation position solution with guaranteed integrity in non-controlled environments
CN103987337A (en)*2011-12-132014-08-13皇家飞利浦有限公司Distorsion fingerprinting for EM tracking compensation, detection and error correction
CN104303228A (en)*2012-05-102015-01-21美国思睿逻辑有限公司Error-signal content controlled adaptation of secondary and leakage path models in noise-canceling personal audio devices
US20210237218A1 (en)*2020-01-302021-08-05Industrial Technology Research InstituteMachine tool adjustment method and system thereof
CN114065114A (en)*2022-01-172022-02-18武汉格蓝若智能技术有限公司Method and system for predicting metering error of capacitive voltage transformer
WO2024141350A1 (en)*2022-12-262024-07-04Koninklijke Philips N.V.Producing combined error values
CN117079794A (en)*2023-09-282023-11-17淮安市第二人民医院Hemodialysis data information monitoring system based on Internet
CN117476175A (en)*2023-12-012024-01-30华东医院Hemodialysis treatment system for nephrology department
CN118780642A (en)*2024-09-062024-10-15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
CN118936542A (en)*2024-10-152024-11-12临沂市计量检定所 A method and system for instrument measurement detection and calibration
CN119004050A (en)*2024-10-242024-11-22长春蓝天密封技术开发有限公司System and method for analyzing dimension measurement errors of metal gasket
CN119574991A (en)*2024-11-152025-03-07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
CN119276391A (en)*2024-12-092025-01-07北京众谱达科技有限公司 A method for error calibration of radio equipment under complex magnetic field interference
CN119394336A (en)*2025-01-032025-02-07深圳市大晶光电科技有限公司 A Gsensor automated testing method for IC environmental deviation
CN120085266A (en)*2025-03-042025-06-03电子科技大学 A RCS test calibration method under far-field conditions
CN120232464A (en)*2025-04-072025-07-01江西天基电子科技有限公司 A sensor error calibration method and system for smart watch
CN120351968A (en)*2025-04-072025-07-22青岛智腾微电子有限公司Method and system for adjusting eccentric turntable in wide temperature range
CN120046084A (en)*2025-04-242025-05-27深圳市川世达科技有限公司 Intelligent calibration method and system for semiconductor testing equipment
CN120314529A (en)*2025-05-192025-07-15陕西麟云超算科技有限公司 A system and method for error correction of marine environment observation data
CN120254739A (en)*2025-06-032025-07-04广东米尔迪克智能机械实业有限公司 A high frequency spark machine calibration method based on machining accuracy and stability control

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
AMATOBI, DA 等: "Improved quantitative microbial risk assessment (QMRA) for drinking water sources in developing countries", 《APPLIED WATER SCIENCE》, vol. 12, no. 03, 31 March 2022 (2022-03-31)*
张莹 等: "呼吸机计量校准中的误差分析与质量控制策略", 《中国品牌与防伪》, no. 01, 15 January 2025 (2025-01-15), pages 110 - 111*
徐姣: "基于时间序列的高精度外测数据预处理方法研究", 《中国优秀硕士学位论文全文数据库(电子期刊) 工程科技II辑》, no. 10, 15 October 2024 (2024-10-15)*
朱松岩: "甲醛时空变化分析预测与反演以及掩星探测切高校正算法研究", 《中国优秀硕士学位论文全文数据库(电子期刊) 工程科技I辑》, no. 04, 15 April 2019 (2019-04-15)*

Similar Documents

PublicationPublication DateTitle
AU2007344229B2 (en)Follow-up of the vascular access of a dialyzed patient.
US20220047789A1 (en)Adequacy assessment method and system
CN116612891B (en)Chronic patient data processing system
CN112675393A (en)Ventilator removing management system and method
EP3391255B1 (en)System and method for detecting an operating state or a course of treatment during a blood treatment
CN117153336B (en)Hemodialysis monitoring system and method based on hemodialysis machine
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
CN108877924A (en)A kind of asthma method of determining probability and device
CN120072321A (en)Intelligent nursing monitoring system and automatic analysis method for patient health data thereof
CN118512677A (en) A monitoring and evaluation system for hemodialysis access function
CN120600266B (en) A hemodialysis data processing method and system
CN116077021A (en)Sleep brain electricity, snore detection and analysis device
CN120600266A (en)Hemodialysis data processing method and system
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
CN118747325A (en) A method for evaluating the quality of electrocardiogram lead data
CN120570578A (en)Blood pressure real-time monitoring method of blood sampling system
CN120432077B (en) Artificial intelligence-based venous catheter matching method and system
CN118658644B (en)Disease state change trend early warning system
CN118818067B (en)Blood coagulation characteristic detection method and system based on household PT measurement
CN117894461A (en)Sleep quality assessment method, system, device, equipment and storage medium
CN120021984A (en) Training method of real-time blood glucose filtering model and related equipment and storage medium
Serrano Alarcón et al.Apnea-hypopnea index using deep learning models with whole and window-based time series

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp