CN113823409B - Method and system for evaluating risk of hypotension event in dialysis - Google Patents
Method and system for evaluating risk of hypotension event in dialysis Download PDFInfo
- Publication number
- CN113823409B CN113823409B CN202111112325.5A CN202111112325A CN113823409B CN 113823409 B CN113823409 B CN 113823409B CN 202111112325 A CN202111112325 A CN 202111112325A CN 113823409 B CN113823409 B CN 113823409B
- Authority
- CN
- China
- Prior art keywords
- rbv
- threshold
- data
- risk
- rate
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 208000001953 Hypotension Diseases 0.000 title claims abstract description 32
- 238000000502 dialysis Methods 0.000 title claims abstract description 31
- 230000036543 hypotension Effects 0.000 title claims abstract description 18
- 238000001914 filtration Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 41
- 238000011156 evaluation Methods 0.000 claims description 22
- 230000007423 decrease Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 14
- 208000021822 hypotensive Diseases 0.000 claims description 14
- 230000001077 hypotensive effect Effects 0.000 claims description 14
- 238000011157 data evaluation Methods 0.000 claims description 13
- 230000007704 transition Effects 0.000 claims description 13
- 238000005094 computer simulation Methods 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 4
- 239000008280 blood Substances 0.000 description 5
- 210000004369 blood Anatomy 0.000 description 5
- 238000012502 risk assessment Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 238000000108 ultra-filtration Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 230000000004 hemodynamic effect Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000006641 stabilisation Effects 0.000 description 2
- 238000011105 stabilization Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000010420 art technique Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 208000020832 chronic kidney disease Diseases 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/021—Measuring pressure in heart or blood vessels
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/026—Measuring blood flow
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pathology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Physiology (AREA)
- Cardiology (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Epidemiology (AREA)
- Computing Systems (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Hematology (AREA)
- Vascular Medicine (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- External Artificial Organs (AREA)
Abstract
The invention discloses a method and a system for evaluating risk of hypotension events in dialysis. The first derivative curve of the ideal RBV curve is determined. RBV data in the dialysis process are collected at predetermined intervals, each collected data is filtered by a Kalman filter, the falling rate of the RBV data is calculated, and the falling rate is filtered by the Kalman filter. And calculating a safety line and a forbidden line at the current moment through the first derivative curve, and determining a risk coefficient according to the comparison of the descending rate and the sizes of the safety line and the forbidden line. The method can filter interference in the acquired RBV data, and improve the accuracy of evaluating the risk of the hypotension event in the dialysis process of the patient by using the RBV. Meanwhile, the dynamic threshold value is used for calculating the risk of the hypotension event, so that the method can be better suitable for the tolerance change of patients in different time periods to the unbalance degree. The filtering algorithm is simple, the processing speed is high, and the real-time processing of RBV data can be realized.
Description
Technical Field
The invention relates to the technical field of medical management, in particular to a method and a system for evaluating the risk of hypotension events in dialysis.
Background
Hypotension in dialysis is the most common complication in dialysis treatment of chronic kidney disease patients, and one of the main reasons for this is that imbalance between ultrafiltration rate in dialysis and refill rate in the patient's body results in rapid decrease of blood volume in the core area of the patient's body, exceeding the patient's tolerance. By analyzing the Relative Blood Volume (RBV) changes of a patient during treatment, an imbalance condition in the patient can be inferred, thereby assessing the risk of the patient developing a hypotensive event. The risk value can be applied to biofeedback closed-loop control in the dialysis process, and can intervene in the unbalance condition of the patient in advance, so that the probability of hypotension of the patient is reduced. In particular, it is often determined whether a patient's hypotension event or the degree of risk of occurrence of the producer is determined by whether the absolute value, amount of change, rate of change (first derivative), second derivative of the RBV exceeds one or more thresholds.
CN110151153a discloses a prior art solution that determines whether a hypotensive event is occurring in a patient by acquiring patient RBV data every 5 minutes, thresholding the second derivative of RBV, SDRBV, and optionally combining blood pressure data. In addition, another fuzzy logic technique is employed in this document, which uses at least two fuzzy modules to receive hemodynamic parameters (e.g., relative blood volume and blood pressure), and by weighting the outputs of each fuzzy module, ultimately outputs at least one variable for evaluating the patient's risk of developing a hypotensive event.
CN104346521a discloses another prior art technique employing an apparatus and method for predicting hemodynamic parameters of a patient under treatment after learning individual dialysis parameters of the patient using a learning algorithm or neural network.
The prior art has the following defects:
noise from the RBV can greatly interfere with the derivative change of the RBV, thereby reducing the accuracy of the determination of hypotensive events.
2. Tolerance changes in the degree of imbalance in the patient during treatment are not considered.
3. Non-real time, optimal intervention opportunities may be missed.
4. The judgment result is a logic value, which is unfavorable for the follow-up accurate feedback control.
Disclosure of Invention
The invention aims at: aiming at all or part of the problems, an assessment method for risk of hypotension event in dialysis and an assessment system for risk of hypotension event in dialysis are provided, so that accuracy of assessing risk of hypotension event in dialysis of patients by using RBV is improved.
The technical scheme adopted by the invention is as follows:
a method of assessing risk of a hypotensive event in dialysis, comprising:
RBV data in the dialysis process are collected at preset interval time, and the following flow is executed for each collected RBV data:
filtering the RBV data using a pre-constructed Kalman filter; calculating a rate of decrease of the observed RBV data, filtering the calculated rate of decrease using the Kalman filter;
and evaluating the filtered drop rate based on an evaluation threshold set for the current moment.
Further, the evaluation threshold set for the current time includes a first threshold and a second threshold higher than the first threshold.
Further, the step of evaluating the filtered drop rate based on an evaluation threshold set for the current time is to calculate a risk coefficient of the filtered drop rate based on the first threshold and the second threshold.
Further, the evaluating the filtered drop rate based on an evaluation threshold set for the current time includes:
and when the filtered dropping rate is between the first threshold and the second threshold, evaluating the filtered dropping rate by adopting a linear interpolation method or a monotonically increasing curve.
Further, the first threshold is a value of a first derivative of a set ideal RBV curve at a current moment, the second threshold is N times of the first threshold, and N is a constant larger than 1.
Further, the value FDRBV of the first derivative of the ideal RBV curve at the ith moment i Is calculated by (a) a calculation methodThe method comprises the following steps:
FDRBV i =n×EDRBV×a i ,
wherein DRBV is the expected RBV drop, T is the total treatment time, n is the amplification factor, and a is the attenuation parameter.
Further, the system state prediction equation of the kalman filter is:
the update equation is:
wherein X is k X is the system state at the current moment k-1 Z is the system state at the last moment k For the system state observed at the current moment, A is a state transition matrix, H is an observation matrix, Q, R respectively represents a system prediction model and a noise covariance matrix of a sensor, and P k Is X k Covariance matrix, P k-1 Is X k-1 Is the covariance matrix of (1), I is the identity matrix, K k The Kalman gain matrix is an intermediate calculation, with ". Times. -indicated as estimated and". Times. -indicated as predicted.
Further, the method for calculating the state transition matrix a includes:
constructing a calculation model of RBV at t moment;
discretizing the computational model;
calculating the change rate of RBV;
and representing the system state by using a discretized calculation model and the change rate, and analogizing with a standard representation mode of the system state to obtain a state transition matrix.
Further, the method for calculating the observation matrix H includes:
calculating the observed rate of decline of the RBV data;
and using a discretized calculation model and the descent rate to represent the observed system state, and analogy with an observed system state standard representation mode to obtain an observation matrix.
The invention provides an evaluation system for risk of hypotension events in dialysis, which comprises a data acquisition part, a data evaluation part and a data output part, wherein the data evaluation part is pre-constructed with a Kalman filter and is provided with evaluation thresholds corresponding to all moments;
the data acquisition part acquires RBV data in the dialysis process according to the configured acquisition period;
the data evaluation unit filters the RBV data using the kalman filter, calculates a rate of decrease of the observed RBV data, and filters the calculated rate of decrease using the kalman filter; based on an evaluation threshold at the current moment, evaluating the filtered drop rate;
the data output unit outputs the evaluation result of the data evaluation unit.
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
1. according to the invention, the relative blood volume data is preprocessed by Kalman filtering, and the influence of interference signals is filtered by using a simple algorithm, so that the actual relative blood volume change condition of a patient is better reflected, and the accuracy of evaluating the risk of hypotension events in the dialysis process of the patient by using RBV is improved. And because the Kalman filtering algorithm is simple, the processing speed is high, the real-time processing of RBV data can be realized, and the response time of correction measures is reduced.
2. According to the invention, the dynamic threshold value is used for calculating the risk of the hypotension event, so that the method can be better suitable for the tolerance change of patients in different time periods to the unbalance degree.
3. The final evaluation result of the method and the system is the normalized risk coefficient obtained by evaluating the descent rate, and the risk level judgment is finer, so that the subsequent feedback control or the parameter determination of the correction measure is convenient.
Drawings
The invention will now be described by way of example and with reference to the accompanying drawings in which:
FIG. 1 is a flow chart of one embodiment of the evaluation method of the present invention.
Detailed Description
All of the features disclosed in this specification, or all of the steps in a method or process disclosed, may be combined in any combination, except for mutually exclusive features and/or steps.
Any feature disclosed in this specification (including any accompanying claims, abstract) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. That is, each feature is one example only of a generic series of equivalent or similar features, unless expressly stated otherwise.
Example 1
As shown in fig. 1, the method for assessing the risk of a hypotensive event in dialysis includes the following steps:
first step, determining a First Derivative (FDRBV) curve of an ideal RBV curve for a dialysis procedure
First, the expected RBV Decrease (DRBV) for this treatment is determined, as well as the total treatment duration T, which is set to 24% by default, is 4 hours. Of course, both data may be determined based on patient reality. The average decrease rate of RBV (EDRBV) throughout the treatment is:
take 5 times of EDRBV as initial FDRBV, the FDRBV at the ith moment in treatment is expressed as FDRBV i FDRBV i Calculation using the following formula:
FDRBV i =5×EDRBV×0.985 i
second step, establishing Kalman filter equation and determining filtering parameters
The kalman filter is an algorithm for optimally estimating the state of a system by inputting and outputting observation data of the system, and the observation data comprises the influence of noise and interference in the system, so that the optimal estimation can be also regarded as a filtering process. The kalman filter (hereinafter filter) works according to two equations: a system state transition equation and a system observation equation.
By X k Representing the state of the system at the current time, the state transition equation of the system can be expressed as:
X k =AX k-1 +Bu k +ω k
wherein A is a state transition matrix; x is X k-1 Representing the system state at the last moment; b is a control matrix; u (u) k Representing a control vector; omega k ~N(0,Q k ) Representing the process excitation noise, the mean value is 0, and the variance is Q k Is a gaussian white noise of (c).
At the same time in Z k Representing the system state at the current time observed using the measurement system, which can be expressed as:
Z k =HX k +ν k
wherein H is called an observation matrix; v k ~N(0,R k ) Represents observation noise, the mean value is 0, and the variance is R k Is a gaussian white noise of (c).
The RBV of the patient during dialysis treatment was constantly changing (decreasing) due to ultrafiltration, noted RBV, and the rate of decrease noted m. Rbv at time t can be expressed as:
rbv t =rbv t-Δt +m t-Δt ×Δt
wherein Δt represents the change time period, rbv t-Δt Rbv, m representing the time t- Δt t-Δt Indicating the rate of change of t- Δt.
The above formula rbv discretization is expressed as:
rbv k =rbv k-1 +m k-1
from analysis of the rbv data collected, the rate of descent m was continuously reduced during treatment without unexpected intervention (patient stabilization treatment), with the empirical formula:
m k =a×m k-1
the predictive equation of the system can be generalized as:
unified representation of system states as X k The method comprises the following steps:
then there are:
namely:
B0
the value of a is 0.985 in this embodiment, and the FDRBV is calculated in the first step i Parameters in the formula.
For rbv in the treatment directly observed, it was noted rbv'. The rate of decrease m 'of rbv' is defined as:
where C is a constant, linerFit (C) represents the slope of the most recent C rbv' data by linear fitting. The value of C determines the estimation of the short-term or long-term change of rbv ', and in this embodiment, if the short-term change needs to be estimated, the value of C takes a smaller value, and specifically depends on the acquisition period of rbv' data, where the period is 1min, and C takes 5.
The observed system state is uniformly denoted as Z k :
Since the observed parameters rbv ', m' are the same amount as the system states rbv, m, no conversion is required, Z k And can be expressed as:
namely:
the following 5 formulas are needed for filtering:
system state prediction equation:
where "]" is an estimated value, and "-" is a predicted value (the same applies below).
Updating the equation:
wherein P is k Is X k Covariance matrix, P k-1 Is X k-1 Q, R represent the system prediction model and the noise covariance matrix of the sensor, respectively, which need to be determined according to the actual situation, K k The Kalman gain matrix is the intermediate calculated quantity, and I is the identity matrix. In this embodiment, the preferred values are:
third, RBV data is collected and filtered
RBV data is collected at predetermined time intervals (e.g., every minute).
Taking the collected RBV data as a first input of a filter; and obtaining a slope (linearFit (C)) according to the correlation algorithm in the second step, filtering the RBV data and the slope thereof as a second input of the filter, removing noise, and outputting the filtered RBV and slope. Of course, only the slope may be filtered.
Fourth, generating hypotension risk assessment coefficient
According to the method in the first step, FDRBV of the current moment is calculated i It is used as a safety line for RBV slope and is amplified to a certain extent (e.g. n X FDRBV i N is a positive integer greater than 1) as a prohibition line of the RBV slope. And performing risk assessment on the collected RBV data based on the set safety line and the set forbidden line. Specifically, risk assessment is performed according to the magnitude relation between the slope of the filtered RVB and the safety line and the forbidden line.
1. If the slope of the filtered RVB exceeds n FDRBV i It is considered that there is a high probability that a hypotensive event has occurred (or will occur), the risk factor of which is noted as 1.
2. If the slope of the filtered RBV is less than the FDRBV i Then the risk of a hypotensive event is considered to be absent, with a risk factor of 0.
3. If the slope of the filtered RBV is at FDRBV i With n x FDRBV i And calculating the risk coefficient by adopting a linear interpolation method or other monotonically increasing curves.
And fifthly, judging whether the treatment process is finished, if so, finishing the evaluation, otherwise, jumping to the third step, and continuing to evaluate RBV data acquired next time.
Example two
The embodiment discloses an evaluation system for risk of hypotension events in dialysis, which comprises a data acquisition part, a data evaluation part and a data output part. The data evaluation unit is pre-configured with a Kalman filter, and sets an evaluation threshold corresponding to each time.
The evaluation threshold is set based on the first derivative curve (FDRBV) of the ideal RBV curve. First, the expected RBV Decrease (DRBV) for this treatment is determined, as well as the total treatment duration T, which is set to 24% by default, is 4 hours. Of course, both data may be determined based on patient reality. The average decrease rate of RBV (EDRBV) throughout the treatment is:
taking n times of EDRBV as initial FDRBV, the FDRBV at the ith moment in treatment is expressed as FDRBV i FDRBV i Calculation using the following formula:
FDRBV i =n×EDRBV×a i ;
wherein n is the magnification, a is the attenuation parameter, and a <1; in this example n is 5 and a is 0.985.
The evaluation threshold includes a safety line and a prohibition line, and is used for FDRBV at the current moment i As a safety line for the slope of RBV and to amplify it to a certain extent (e.g. NxFDRBV i N is a constant greater than 1) as a forbidden line for the RBV slope.
The pre-constructed kalman filter is specifically as follows:
the kalman filter (hereinafter filter) works according to two equations: a system state transition equation and a system observation equation.
By X k Representing the state of the system, the state transition equation of the system can be expressed as:
X k =AX k-1 +Bu k +ω k
wherein A is a state transition matrix; x is X k-1 Representing the system state at the last moment; b is a control matrix; u (u) k Representing a control vector; omega k ~N(0,Q k ) Representing the process excitation noise, the mean value is 0, and the variance is Q k Is a gaussian white noise of (c).
At the same time in Z k Representing the current state of the system observed using the measurement system, which can be expressed as:
Z k =HX k +ν k
wherein H is called an observation matrix; v k ~N(0,R k ) Represents observation noise, the mean value is 0, and the variance is R k Is a gaussian white noise of (c).
The RBV of the patient during dialysis treatment was constantly changing (decreasing) due to ultrafiltration, noted RBV, and the rate of decrease noted m. Rbv at time t can be expressed as:
rbv t =rbv t-Δt +m t-Δt ×Δt
wherein Δt represents the change time period, rbv t-Δt Rbv, m representing the time t- Δt t-Δt Indicating the rate of change of t- Δt.
The above formula rbv discretization is expressed as:
rbv k =rbv k-1 +m k-1
from analysis of the rbv data collected, the rate of descent m was continuously reduced during treatment without unexpected intervention (patient stabilization treatment), with the empirical formula:
m k =a×m k-1
the predictive equation of the system can be generalized as:
unified representation of system states as X k The method comprises the following steps:
then there are:
namely:
B0
the value of a is 0.985 in the scheme, and the FDRBV is calculated in the first step i Parameters in the formula.
For rbv in the treatment directly observed, it was noted rbv'. The rate of decrease m 'of rbv' is defined as:
where C is a constant, linerFit (C) represents the slope of the most recent C rbv' data by linear fitting. The value of C determines the estimation of the short-term or long-term change of rbv ', and in this embodiment, if the short-term change needs to be estimated, the value of C takes a smaller value, and specifically depends on the acquisition period of rbv' data, where the period is 1min, and C takes 5.
The observed system state is uniformly denoted as Z k :
Since the observed parameters rbv ', m' are the same amount as the system states rbv, m, no conversion is required, Z k And can be expressed as:
namely:
the following 5 formulas are needed for filtering:
system state prediction equation:
wherein, the "≡" is an estimated value (hereinafter); with "-means that the predicted value (the same applies below).
Updating the equation:
wherein Q, R represents the system prediction model and the noise covariance matrix of the sensor, and K is determined according to the actual situation k Is Kalman gain matrixIs the intermediate calculation amount, I is the identity matrix. In this embodiment, the preferred values are:
the data acquisition part acquires RBV data at preset time intervals (such as every minute), and the RBV data acquired each time is transmitted to the data evaluation part.
The data evaluation unit uses the received RBV data as a first input of the filter; and obtaining a slope (linearFit (C)) according to the correlation algorithm in the second step, filtering the RBV data and the slope thereof as a second input of the filter, removing noise, and outputting the filtered RBV and slope. Of course, only the slope may be filtered.
For the filtered slope, performing risk assessment according to the magnitude relation between the slope and the safety line and the forbidden line:
1. if the slope of the filtered RVB exceeds n FDRBV i It is considered that there is a high probability that a hypotensive event has occurred (or will occur), the risk factor of which is noted as 1.
2. If the slope of the filtered RBV is less than the FDRBV i Then the risk of a hypotensive event is considered to be absent, with a risk factor of 0.
3. If the slope of the filtered RBV is at FDRBV i With n x FDRBV i And calculating the risk coefficient by adopting a linear interpolation method or other monotonically increasing curves.
The data output part is connected with the data evaluation part and outputs the evaluation result (namely risk coefficient) of the RBV data acquired by the data acquisition part each time. The data output by the data output part can be used as a parameter of feedback control or correction measures.
The invention is not limited to the specific embodiments described above. The invention extends to any novel one, or any novel combination, of the features disclosed in this specification, as well as to any novel one, or any novel combination, of the steps of the method or process disclosed.
Claims (5)
1. A method of assessing risk of a hypotensive event in dialysis, comprising:
RBV data in the dialysis process are collected at preset interval time, and the following flow is executed for each collected RBV data:
filtering the RBV data using a pre-constructed Kalman filter; calculating a rate of decrease of the observed RBV data, filtering the calculated rate of decrease using the Kalman filter; the system state prediction equation of the Kalman filter is as follows:
the update equation is:
wherein X is k X is the system state at the current moment k-1 Z is the system state at the last moment k For the system state observed at the current moment, A is a state transition matrix, H is an observation matrix, Q, R respectively represents a system prediction model and a noise covariance matrix of a sensor, and P k Is X k Covariance matrix, P k-1 Is X k-1 Is the covariance matrix of (1), I is the identity matrix, K k The Kalman gain matrix is an intermediate calculation quantity, and is represented by "<" > as an estimated value and by "-" as a predicted value;
based on an evaluation threshold set for the current moment, evaluating the filtered drop rate; the evaluation threshold set at the current moment comprises a first threshold and a second threshold higher than the first threshold, wherein the first threshold is a value of a first derivative of a set ideal RBV curve at the current moment, the second threshold is N times of the first threshold, and N is a constant larger than 1;
if the filtered drop rate exceeds the second threshold, the risk factor is recorded as 1;
if the filtered drop rate is less than the first threshold, the risk factor is recorded as 0;
if the filtered drop rate is between the first threshold and the second threshold, calculating a risk coefficient by adopting a linear interpolation method or a monotonically increasing curve.
2. The method for assessing the risk of a hypotensive event in dialysis according to claim 1, wherein the value FDRBV of the first derivative FDRBV of the ideal RBV curve at the i-th moment i The calculation method of (1) is as follows:
FDRBV i =n×EDRBV×a i ,
where n is the magnification, DRBV is the expected decrease in RBV, T is the total time of treatment, and a is the decay parameter.
3. The method for assessing the risk of a hypotensive event in dialysis according to claim 1, wherein the method for calculating the state transition matrix a comprises:
constructing a calculation model of RBV at t moment;
discretizing the computational model;
calculating the change rate of RBV;
and representing the system state by using a discretized calculation model and the change rate, and obtaining a state transition matrix by classifying the system state standard representation mode.
4. A method for assessing the risk of a hypotensive event in dialysis according to claim 3, wherein the method for calculating the observation matrix H comprises:
calculating the observed rate of decline of the RBV data;
and using a discretized calculation model and the descent rate to represent the observed system state, and analogy with an observed system state standard representation mode to obtain an observation matrix.
5. The system for evaluating the risk of the hypotension event in dialysis is characterized by comprising a data acquisition part, a data evaluation part and a data output part, wherein the data evaluation part is pre-constructed with a Kalman filter and is provided with evaluation thresholds corresponding to all moments;
the data acquisition part acquires RBV data in the dialysis process according to the configured acquisition period;
the data evaluation unit filters the RBV data using the kalman filter, calculates a rate of decrease of the observed RBV data, and filters the calculated rate of decrease using the kalman filter; based on an evaluation threshold at the current moment, evaluating the filtered drop rate; the system state prediction equation of the Kalman filter is as follows:
the update equation is:
wherein X is k X is the system state at the current moment k-1 Z is the system state at the last moment k For the system state observed at the current moment, A is a state transition matrix, H is an observation matrix, Q, R respectively represents a system prediction model and a noise covariance matrix of a sensor, and P k Is X k Covariance matrix, P k-1 Is X k-1 Is the covariance matrix of (1), I is the identity matrix, K k The Kalman gain matrix is an intermediate calculation quantity, and the "≡" is an estimateA value, with "representing a predicted value;
the evaluation threshold set at the current moment comprises a first threshold and a second threshold higher than the first threshold, wherein the first threshold is a value of a first derivative of a set ideal RBV curve at the current moment, the second threshold is N times of the first threshold, and N is a constant larger than 1;
if the filtered drop rate exceeds the second threshold, the risk factor is recorded as 1;
if the filtered drop rate is less than the first threshold, the risk factor is recorded as 0;
if the filtered drop rate is between the first threshold and the second threshold, calculating a risk coefficient by adopting a linear interpolation method or a monotonically increasing curve;
the data output unit outputs the evaluation result of the data evaluation unit.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111112325.5A CN113823409B (en) | 2021-09-23 | 2021-09-23 | Method and system for evaluating risk of hypotension event in dialysis |
PCT/CN2022/099129 WO2023045425A1 (en) | 2021-09-23 | 2022-06-16 | Method and system for evaluating risk of intradialytic hypotension event |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111112325.5A CN113823409B (en) | 2021-09-23 | 2021-09-23 | Method and system for evaluating risk of hypotension event in dialysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113823409A CN113823409A (en) | 2021-12-21 |
CN113823409B true CN113823409B (en) | 2023-12-29 |
Family
ID=78921048
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111112325.5A Active CN113823409B (en) | 2021-09-23 | 2021-09-23 | Method and system for evaluating risk of hypotension event in dialysis |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113823409B (en) |
WO (1) | WO2023045425A1 (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113823409B (en) * | 2021-09-23 | 2023-12-29 | 重庆山外山血液净化技术股份有限公司 | Method and system for evaluating risk of hypotension event in dialysis |
CN117009831B (en) * | 2023-10-07 | 2023-12-08 | 山东世纪阳光科技有限公司 | Fine chemical accident risk prediction assessment method |
CN117798744B (en) * | 2024-02-29 | 2024-05-10 | 茌平县汇通机械制造有限公司 | Method for monitoring running state of numerical control machine tool |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109195508A (en) * | 2016-07-22 | 2019-01-11 | 爱德华兹生命科学公司 | The derived prediction to the following low blood pressure of mean arterial pressure (MAP) |
CN109195507A (en) * | 2016-07-08 | 2019-01-11 | 爱德华兹生命科学公司 | Low blood pressure analyzes the prediction weighting of parameter |
CN110648755A (en) * | 2019-09-10 | 2020-01-03 | 云南博亚医院有限公司 | Hemodialysis quality evaluation and management system |
CN111939353A (en) * | 2019-05-14 | 2020-11-17 | 吴元昊 | Construction method of prediction model of hypotensive event in hemodialysis |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9002440B2 (en) * | 2010-07-08 | 2015-04-07 | Intelomed, Inc. | System and method for characterizing circulatory blood flow |
CN104703534B (en) * | 2012-08-28 | 2017-11-03 | 弗雷泽纽斯医疗保健控股有限公司 | The method that the instruction of ill event in dialysis is detected by measuring relative blood volume, blood pressure and heart rate |
DE102013101989A1 (en) * | 2013-02-28 | 2014-09-18 | B. Braun Avitum Ag | Fuzzy logic |
EP3542707A1 (en) * | 2018-03-20 | 2019-09-25 | Gambro Lundia AB | Sensor and apparatus for determining at least one parameter of blood circulating in an extracorporeal blood circuit |
CN108986419B (en) * | 2018-10-17 | 2021-02-26 | 暨南大学 | Data alarming method for hemodialysis |
CN113823409B (en) * | 2021-09-23 | 2023-12-29 | 重庆山外山血液净化技术股份有限公司 | Method and system for evaluating risk of hypotension event in dialysis |
-
2021
- 2021-09-23 CN CN202111112325.5A patent/CN113823409B/en active Active
-
2022
- 2022-06-16 WO PCT/CN2022/099129 patent/WO2023045425A1/en unknown
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109195507A (en) * | 2016-07-08 | 2019-01-11 | 爱德华兹生命科学公司 | Low blood pressure analyzes the prediction weighting of parameter |
CN109195508A (en) * | 2016-07-22 | 2019-01-11 | 爱德华兹生命科学公司 | The derived prediction to the following low blood pressure of mean arterial pressure (MAP) |
CN111939353A (en) * | 2019-05-14 | 2020-11-17 | 吴元昊 | Construction method of prediction model of hypotensive event in hemodialysis |
CN110648755A (en) * | 2019-09-10 | 2020-01-03 | 云南博亚医院有限公司 | Hemodialysis quality evaluation and management system |
Also Published As
Publication number | Publication date |
---|---|
WO2023045425A1 (en) | 2023-03-30 |
CN113823409A (en) | 2021-12-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113823409B (en) | Method and system for evaluating risk of hypotension event in dialysis | |
JP4748854B2 (en) | Method and medium for determining whether a sensor is connected to a blood perfused tissue sample | |
US10342910B2 (en) | Device and method for predicting intradialytic parameters | |
CN107809948B (en) | Method and device for determining the course of a blood pressure | |
RU2681362C2 (en) | Method and apparatus for estimating fall risk of user | |
JP3923035B2 (en) | Biological condition analysis apparatus and biological condition analysis method | |
Fetanat et al. | A physiological control system for an implantable heart pump that accommodates for interpatient and intrapatient variations | |
AU2011213041B2 (en) | System and method for diagnosing sleep apnea based on results of multiple approaches to sleep apnea identification | |
KR20150113700A (en) | System and method for diagnosis | |
US11059349B2 (en) | Enhanced climate control | |
JP2004089267A (en) | Sleeping depth estimation device and bedding equipped with the same | |
EP3656304A1 (en) | A method and a system for determining the maximum heart rate of a user of in a freely performed physical exercise | |
CN108961447B (en) | Method for judging whether seat is occupied or not, seat system and attendance checking method | |
CN111317458A (en) | Blood pressure detection system based on deep learning | |
CN116204805B (en) | Micro-pressure oxygen cabin and data management system | |
CA3139034A1 (en) | System and method for filtering time-varying data for physiological signal prediction | |
CN113782214B (en) | Health management method and system with health data analysis function | |
US20220265217A1 (en) | Drowsiness estimation information correction device, drowsiness estimation device, drowsiness estimation information correction method, drowsiness estimation method, and recording medium | |
CN107785080A (en) | Health index appraisal procedure and system based on bioelectrical impedance analysis device | |
CN108828170B (en) | Mariculture dissolved oxygen concentration acquisition device and method with multi-protocol output | |
KR100901433B1 (en) | A measuring method of a skin emanation | |
CN102665554B (en) | Apparatus for registration of transitions between psychophysiological states of individual and method for performing the same | |
JPH05200005A (en) | Electric hemadynamometer | |
CN115721275B (en) | Pulse wave data acquisition and blood pressure measurement method, device, equipment and medium | |
US20230206691A1 (en) | Emotion determination device and emotion determination method |
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 |