CN108256460B - Method/system, computer storage medium and apparatus for early prognosis of potential patient - Google Patents
Method/system, computer storage medium and apparatus for early prognosis of potential patient Download PDFInfo
- Publication number
- CN108256460B CN108256460B CN201810026402.7A CN201810026402A CN108256460B CN 108256460 B CN108256460 B CN 108256460B CN 201810026402 A CN201810026402 A CN 201810026402A CN 108256460 B CN108256460 B CN 108256460B
- Authority
- CN
- China
- Prior art keywords
- data set
- coefficient
- multidimensional
- matrix
- intermediate variable
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Abstract
The invention provides an early diagnosis method/system, a computer readable storage medium and a device of a potential patient, wherein the early diagnosis method comprises the following steps: preprocessing the acquired physiological data set to form a preprocessed physiological data set; dividing the pre-processed physiological data set into a plurality of sub-data sets, and calculating a multidimensional kini coefficient on each sub-data set; and analyzing the potential patients according to the fluctuation characteristics of the calculated multidimensional kini coefficient. The method estimates the magnetocardiogram data difference between the myocardial ischemia patient and the normal person by calculating the Kerniy coefficient of the T wave band, realizes the early pre-diagnosis of the myocardial ischemia patient, reduces the influence of noise and interference on data analysis, improves the reliability of the result, and has strong universality.
Description
Technical Field
The invention belongs to the technical field of medical diagnosis, relates to a diagnosis method and a diagnosis system, and particularly relates to a method/system for early pre-diagnosis of a potential patient, a computer-readable storage medium and computer-readable storage equipment.
Background
The coefficient of kini measures the unevenness of data, and has wide application in the fields of sociology, finance, signal analysis and the like. When applied to magnetocardiogram data analysis, the kini coefficient values of the data depict an important feature of data sparsity, which has been rarely involved in previous studies.
The electrophysiological model of the heart shows that the sparsity of the magnetocardiogram data can reflect the onset of myocardial ischemia. When myocardial ischemia occurs, the local oxygen content of an ischemic part is reduced, so that the conduction of action potential in the region is delayed, additional abnormal current is generated on a normal heart micro-current distribution model, and the signal sparsity change is reflected on a magnetocardiogram signal, and the finding is also confirmed by analyzing magnetocardiogram data of nearly 200 clinical myocardial ischemia patients.
The classical single-dimension kini coefficient calculation method can only measure the nonuniformity of data in the aspect of single attribute, namely the sparsity of the magnetocardiogram data at a certain sampling point. The method is easily influenced by data background noise and measurement interference, and the obtained damping coefficient has large fluctuation and cannot truly reflect the data sparsity characteristic. An effective solution is to use a multidimensional kini coefficient method to calculate the kini values of a plurality of sampling points, smooth data and reduce the influence of noise.
In the past, methods for calculating multidimensional kini coefficients have been proposed, for example, a method for calculating the kini values of different dimensional attributes by using a single-dimensional kini coefficient method is used, and then an arithmetic mean of a plurality of kini values is obtained as a final result. The suitability of a multidimensional kini coefficient calculation method is measured, and the coefficient is required to have two characteristics: improving the correlation among different attributes of the data can improve the data unevenness; if the non-uniformity of one attribute of the data is lower than that of the other attribute, the former attribute is removed, so that the uniformity of the data as a whole can be improved. The classical multidimensional kini coefficient calculation method satisfies the second feature described above, but does not satisfy the first feature.
Therefore, how to provide an early pre-diagnosis method/system, a computer-readable storage medium and a device for a potential patient to solve the problem that the prior art cannot simultaneously satisfy two characteristics, so that the difference between the sparsity of the myocardial ischemia patient and the normal human magnetocardiogram data cannot be reflected, and the like, has become a technical problem to be solved in the field.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention aims to provide a method/system, a computer-readable storage medium and a device for early diagnosis of a potential patient, which are used to solve the problem that the prior art cannot simultaneously satisfy two characteristics, resulting in failure to reflect the sparsity difference between the myocardial ischemia patient and the normal human magnetocardiogram data.
To achieve the above and other related objects, one aspect of the present invention provides a method for early prognosis of a potential patient, comprising: preprocessing the acquired physiological data set to form a preprocessed physiological data set; dividing the pre-processed physiological data set into a plurality of sub-data sets, and calculating a multidimensional kini coefficient on each sub-data set; and analyzing the potential patients according to the fluctuation characteristics of the calculated multidimensional kini coefficient.
In an embodiment of the invention, the step of preprocessing the acquired physiological data set includes: filtering and denoising the acquired physiological data set; averaging the filtered and noise-reduced physiological data set; performing T-wave segmentation on the averaged physiological data set to form the preprocessed physiological data set; wherein the preprocessed physiological data set is a T-waveband magnetocardiogram data set.
In an embodiment of the present invention, the step of dividing the pre-processed physiological data set into a plurality of sub-data sets and calculating the multidimensional damping coefficient on each sub-data set includes: sequentially intercepting data from the T-band physiological data set, and dividing the data into a plurality of subdata sets; carrying out normalization processing on each subdata set to form a normalized matrix; multiplying the matrix and the transposed matrix to obtain a multiplied matrix; performing eigenvalue decomposition on the multiplication matrix to obtain an eigenvector corresponding to the maximum characteristic root; calculating a first intermediate variable for calculating the multidimensional kiney coefficient according to the normalized matrix and the eigenvector corresponding to the maximum characteristic root; rearranging each element in the first intermediate variable according to a descending order, and forming each element formed after the descending order into a second intermediate variable; and calculating the multidimensional kiney coefficient according to the first intermediate variable and the second intermediate variable.
In an embodiment of the present invention, the multidimensional damping coefficient is calculated according to a calculation formula of prestored multidimensional damping coefficients; the calculation formula of the pre-stored multidimensional kini coefficient is as follows:
wherein G represents a multidimensional Keyny coefficient, n is the number of rows of the matrix and is used for representing the number of magnetocardiogram channels, m is the number of columns of the matrix and is used for representing the number of sampling points of physiological data, ypIs a first intermediate variable, rpP is 1,2, …, n, p represents the second intermediate variable ypThe formed column vector y ═ y1,…,yn]The index of each scalar element.
In an embodiment of the invention, each element in the normalized matrix is equal to each element in each sub-data set divided by the mean of its corresponding row.
In an embodiment of the present invention, the step of sequentially intercepting the data from the T-band physiological data set and dividing the data into the plurality of sub-data sets includes using a sliding window with a preset kini coefficient dimension as a sampling interval, and sequentially intercepting the data from the T-band physiological data set and dividing the data into the plurality of sub-data sets.
In an embodiment of the present invention, the method for early pre-diagnosis of a potential patient further includes: and sliding the sliding window to the next sampling interval, and circularly executing each step of early diagnosis of the potential patient.
In another aspect, the present invention provides a system for early prognosis of a potential patient, comprising: the preprocessing module is used for preprocessing the acquired physiological data set to form a preprocessed physiological data set; the calculation module is used for dividing the preprocessed physiological data set into a plurality of sub data sets and calculating a multidimensional Keyny coefficient on each sub data set; and the analysis module is used for analyzing the potential patients according to the fluctuation characteristics of the calculated multidimensional kini coefficient.
Yet another aspect of the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for early prognosis of said potential patient.
A final aspect of the invention provides an apparatus comprising: a processor and a memory; the memory is configured to store a computer program and the processor is configured to execute the computer program stored by the memory to cause the apparatus to perform a method of early prognosis of the potential patient.
As described above, the method/system, computer-readable storage medium and apparatus for early pre-diagnosis of potential patients according to the present invention have the following advantages:
firstly, evaluating the magnetocardiogram data difference between a myocardial ischemia patient and a normal person by calculating the Kernig coefficient of a T wave band, and realizing early pre-diagnosis of the myocardial ischemia patient;
secondly, the influence of noise and interference on data analysis is reduced, and the reliability of results is improved.
Thirdly, besides the multichannel magnetocardiogram, the method can also be applied to the fields of electrocardiogram, electroencephalogram, magnetoencephalogram and the like, and has certain universality.
Drawings
FIG. 1A is a schematic flow chart illustrating an early pre-diagnosis method for a potential patient according to an embodiment of the present invention.
FIG. 1B is a schematic flow chart of S11 according to the present invention.
FIG. 1C is a schematic flow chart of S12 according to the present invention.
Fig. 2A shows a T-wave waveform and T-band kini coefficient plot for a normal human with dimension 3.
Fig. 2B shows a T-wave waveform and T-band kini coefficient plot for a myocardial ischemia patient with dimension 3.
Fig. 2C shows a graph of the T-wave waveform and the kini coefficient in different dimensions for myocardial ischemia patients with dimensions 1, 5, 20.
Fig. 3 is a schematic structural diagram of an early pre-diagnosis system for potential patients according to an embodiment of the present invention.
Description of the element reference numerals
3 early prognosis of potential patients
31 preprocessing module
32 calculation module
33 circulation module
34 analysis module
S11-S14
S111 to S113
S121 to S127
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
The invention provides a potential patient early pre-diagnosis method/system, a computer readable storage medium and equipment. The measurement indexes of the multidimensional kiney coefficient for normal T waves are as follows: in a T wave band, the distribution of the Gini coefficients is balanced, and no obvious fluctuation exists; the metrics for myocardial ischemia T-wave are: in the T wave band, particularly in the middle and the tail of the wave band, the distribution of the Keyney coefficient obviously fluctuates.
Example one
The present embodiments provide a method for early prognosis of a potential patient, comprising:
preprocessing the acquired physiological data set to form a preprocessed physiological data set;
dividing the pre-processed physiological data set into a plurality of sub-data sets, and calculating a multidimensional kini coefficient on each sub-data set;
and analyzing the potential patients according to the fluctuation characteristics of the calculated multidimensional kini coefficient.
The method for early pre-diagnosis of potential patients provided by the present embodiment will be described in detail with reference to the drawings. In practical applications, the physiological data set includes a magnetocardiogram data set, a centrogram data set, an electroencephalogram data set, a magnetoencephalogram data set, and the like. In this embodiment, the physiological data set is a magnetocardiogram data set. Referring to fig. 1A, a schematic flow chart of an early stage pre-diagnosis method for a potential patient is shown in an embodiment. As shown in fig. 1A, the early prognosis of the potential patient specifically includes the following steps:
s11, preprocessing the acquired magnetocardiogram data set to form a preprocessed magnetocardiogram data set.
Please refer to fig. 1B, which shows a schematic flow chart of S11. As shown in fig. 1B, the S11 specifically includes the following steps:
and S111, filtering and denoising the acquired magnetocardiogram data set. In this embodiment, the method is used to remove environmental noise and other interferences. The filtered and de-noised magnetocardiogram dataset is labeled as a QRS-T wave.
And S112, averaging the filtered and noise-reduced magnetocardiogram data sets, namely averaging QRS-T waves to obtain the averaged magnetocardiogram data sets.
S113, performing T-wave division on the averaged magnetocardiogram data set to form the preprocessed magnetocardiogram data set, wherein the preprocessed magnetocardiogram data set is a T-wave-band magnetocardiogram data set, and the T-wave-band magnetocardiogram data set is represented by F. The dimension of F is nxm, n is the channel number of the magnetocardiogram, m is the number of sampling points of magnetocardiogram data, and F is shown as the following formula:
s12, dividing the preprocessed magnetocardiogram dataset into a plurality of sub-datasets, and calculating multidimensional Keyny coefficients on each sub-dataset. In the present embodiment, the multidimensional yney coefficient is represented by G.
For example, the acquired magnetocardiogram data set takes 36-channel magnetocardiogram data as an example, the size F of the T-band magnetocardiogram data set is 36 × 174, and assuming that the dimension of the multiple-kini coefficient is 3, the kini coefficient is calculated every 3 sampling points. In the present embodiment, 174/3 ═ 58 kini coefficients can be obtained.
Please refer to fig. 1C, which shows a schematic flow chart of S12. As shown in fig. 1C, the S12 includes the following steps:
and S121, sequentially intercepting data of the T-waveband magnetocardiogram data set and dividing the data into a plurality of subdata sets. In this embodiment, data of a T-band magnetocardiogram data set is sequentially intercepted and divided into a plurality of sub-data sets by using a sliding window with a preset kini coefficient dimension as a sampling interval.
For example, with a window size of 3, data is sequentially cut from the beginning of F, and a sub data set F with a size of 36 × 3 is obtained by partitioning.
S122, carrying out normalization processing on each subdata set f to form a normalized matrix.
For example, the normalized matrix is denoted by a, which has dimensions of 36 × 3. Each element in the normalized matrix a is equal to the mean of each element in each sub-data set divided by its corresponding column. Wherein the normalized matrix a is represented as follows:
wherein the content of the first and second substances,
is the average of the 1 st to m columns of the matrix a.
S123, the matrix A and the transposed matrix ATMultiplying to obtain a multiplication matrix A.AT。
S124, multiplying the multiplication matrix A.ATAnd decomposing the characteristic value to obtain a characteristic vector x corresponding to the maximum characteristic root. Wherein the vector χ is normalized, i.e.
And S125, calculating a first intermediate variable for calculating the multidimensional kiney coefficient according to the normalized matrix and the feature vector corresponding to the maximum feature root. In this embodiment, the first intermediate variable is ypWhere p is 1,2, …, n, p represents a variable represented by the first intermediate variable ypThe formed column vector y ═ y1,…,yn]The index of each scalar element. . The first intermediate variable is shown as follows:
yp＝(A·χ)p,p＝1,2,…,n；
and S126, rearranging the elements in the first intermediate variable according to a descending order, and forming a second intermediate variable by the elements formed after the descending order. In this embodiment, the second intermediate variable is represented by rpAnd (p ═ 1,2, …, n).
And S127, calculating the multidimensional kiney coefficient according to the first intermediate variable and the second intermediate variable. In this embodiment, the multidimensional damping coefficient is calculated according to a calculation formula of prestored multidimensional damping coefficients; the calculation formula of the pre-stored multidimensional kini coefficient G is as follows:
wherein G represents the multidimensional kini coefficient, n is the number of rows of the matrix and is used for representing the number of magnetocardiogram channels, m is the number of columns of the matrix and is used for representing the number of sampling points of magnetocardiogram data, and ypIs a first intermediate variable, rpIs the second intermediate variable, p ═ 1,2, …, n.
And S13, sliding the sliding window to the next sampling interval, and circularly running S11-S12.
And S14, analyzing the potential patients according to the fluctuation characteristics of the calculated multidimensional kini coefficient. In the embodiment, T wave band of healthy people has balanced distribution of the kini coefficient and no obvious fluctuation; the metrics for myocardial ischemia T-wave are: in the T wave band, particularly in the middle and the tail of the wave band, the distribution of the Keyney coefficient obviously fluctuates. And if the distribution map of the Gini coefficient of the magnetocardiogram data of the person to be diagnosed fluctuates obviously, analyzing the person to be diagnosed as a potential patient with myocardial ischemia. And if the distribution map of the Gini coefficient of the magnetocardiogram data of the person to be diagnosed has no obvious fluctuation, analyzing the normal myocardium of the person to be diagnosed.
Referring to fig. 2A, 2B and 2C, the graphs of the T-wave waveform and the T-band kini coefficient of a normal person with dimension 3, the graphs of the T-wave waveform and the T-band kini coefficient of a myocardial ischemia patient with dimension 3, and the graphs of the T-wave waveform and the kini coefficient of different dimensions of myocardial ischemia patients with dimensions 1, 5 and 20 are shown, respectively. As shown in fig. 2C, curve a is a plot of the coefficient of kini with dimension equal to 1, curve B is a plot of the coefficient of kini with dimension equal to 5, and curve C is a plot of the coefficient of kini with dimension equal to 20.
The present embodiments also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, enables an early prognosis of the potential patient. Those of ordinary skill in the art will understand that: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The method for early pre-diagnosis of potential patients described in the embodiment has the following beneficial effects:
firstly, evaluating the magnetocardiogram data difference between a myocardial ischemia patient and a normal person by calculating the Kernig coefficient of a T wave band, and realizing early pre-diagnosis of the myocardial ischemia patient;
secondly, the influence of noise and interference on data analysis is reduced, and the reliability of results is improved.
Thirdly, besides the multichannel magnetocardiogram, the method can also be applied to the fields of electrocardiogram, electroencephalogram, magnetoencephalogram and the like, and has certain universality.
Example two
The present embodiments provide a system for early prognosis of a potential patient, comprising:
the preprocessing module is used for preprocessing the acquired physiological data set to form a preprocessed physiological data set;
the calculation module is used for dividing the preprocessed physiological data set into a plurality of sub data sets and calculating a multidimensional Keyny coefficient on each sub data set;
and the analysis module is used for analyzing the morbidity condition of myocardial ischemia according to the fluctuation characteristics of the calculated multidimensional kini coefficient.
The early pre-diagnosis of potential patients provided by the present embodiment will be described in detail below with reference to the drawings. It should be noted that the division of the modules of the above system is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the x module may be a processing element that is set up separately, or may be implemented by being integrated in a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and the function of the x module may be called and executed by a processing element of the apparatus. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, when one of the above modules is implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
In practical applications, the physiological data set includes a magnetocardiogram data set, a centrogram data set, an electroencephalogram data set, a magnetoencephalogram data set, and the like. In this embodiment, the physiological data set is a magnetocardiogram data set.
Referring to fig. 3, a schematic structural diagram of an embodiment of an early pre-diagnosis of a potential patient is shown. As shown in fig. 3, the early prognosis 3 of the potential patient includes: a preprocessing module 31, a calculation module 32, a circulation module 33 and an analysis module 34.
The preprocessing module 31 is configured to preprocess the acquired magnetocardiogram data set to form a preprocessed magnetocardiogram data set.
The preprocessing module 31 is specifically configured to perform filtering and denoising on the acquired magnetocardiogram data set; averaging the filtered and noise-reduced magnetocardiogram data sets; t-wave segmentation is performed on the averaged magnetocardiogram dataset to form the preprocessed magnetocardiogram dataset.
The calculating module 32 coupled to the preprocessing module 31 is configured to divide the preprocessed physiological data set into a plurality of sub-data sets, and calculate a multidimensional damping coefficient on each sub-data set.
Specifically, the calculation module 32 is configured to sequentially intercept data from the T-band magnetocardiogram data set with a sliding window with a preset kini coefficient dimension as a sampling interval, and divide the data into a plurality of sub-data sets; carrying out normalization processing on each subdata set to form a normalized matrix; multiplying the matrix and the transposed matrix to obtain a multiplied matrix; performing eigenvalue decomposition on the multiplication matrix to obtain an eigenvector corresponding to the maximum characteristic root; calculating a first intermediate variable for calculating the multidimensional kiney coefficient according to the normalized matrix and the eigenvector corresponding to the maximum characteristic root; rearranging each element in the first intermediate variable according to a descending order, and forming each element formed after the descending order into a second intermediate variable; and calculating the multidimensional kiney coefficient according to the first intermediate variable and the second intermediate variable.
A loop module 33 coupled to the calculation module 32 is configured to loop the preprocessing module 31 and the calculation module 32 by sliding the sliding window to the next sampling interval.
An analysis module 34 coupled to the calculation module 32 and the circulation module 33 is used for analyzing the potential patient according to the fluctuation characteristics of the calculated multidimensional kini coefficient. In the embodiment, T wave band of healthy people has balanced distribution of the kini coefficient and no obvious fluctuation; the metrics for myocardial ischemia T-wave are: in the T wave band, particularly in the middle and the tail of the wave band, the distribution of the Keyney coefficient obviously fluctuates. And if the distribution map of the Gini coefficient of the magnetocardiogram data of the person to be diagnosed fluctuates obviously, analyzing the person to be diagnosed as a potential patient with myocardial ischemia. And if the distribution map of the Gini coefficient of the magnetocardiogram data of the person to be diagnosed has no obvious fluctuation, analyzing the normal myocardium of the person to be diagnosed.
EXAMPLE III
The present embodiment provides an apparatus, comprising: a processor, a memory, a transceiver, a communication interface, and a system bus; the memory for storing the computer program and the communication interface for communicating with other devices, and the processor and the transceiver for executing the computer program enable the devices to perform the steps of the method for early pre-diagnosis of a potential patient as described in the first embodiment.
The above-mentioned system bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The communication interface is used for realizing communication between the database access device and other equipment (such as a client, a read-write library and a read-only library). The memory may include a Random Access Memory (RAM), and may further include a non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor may be a general-purpose processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the integrated circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components.
In summary, the method/system, computer-readable storage medium and apparatus for early pre-diagnosis of potential patients according to the present invention have the following advantages:
firstly, evaluating the magnetocardiogram data difference between a myocardial ischemia patient and a normal person by calculating the Kernig coefficient of a T wave band, and realizing early pre-diagnosis of the myocardial ischemia patient;
secondly, the influence of noise and interference on data analysis is reduced, and the reliability of results is improved.
Thirdly, besides the multichannel magnetocardiogram, the method can also be applied to the fields of electrocardiogram, electroencephalogram, magnetoencephalogram and the like, and has certain universality. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (9)
1. A method for early prognosis of a potential patient, comprising:
preprocessing the acquired physiological data set to form a preprocessed physiological data set; the preprocessed physiological data set is a T-waveband magnetocardiogram data set;
dividing the pre-processed physiological data set into a plurality of sub-data sets, and calculating a multidimensional kini coefficient on each sub-data set; the method comprises the following steps: sequentially intercepting data from the T-band physiological data set, and dividing the data into a plurality of subdata sets; carrying out normalization processing on each subdata set to form a normalized matrix; multiplying the matrix and the transposed matrix to obtain a multiplied matrix; performing eigenvalue decomposition on the multiplication matrix to obtain an eigenvector corresponding to the maximum characteristic root; calculating a first intermediate variable for calculating the multidimensional kiney coefficient according to the normalized matrix and the eigenvector corresponding to the maximum characteristic root; rearranging each element in the first intermediate variable according to a descending order, and forming each element formed after the descending order into a second intermediate variable; calculating a multidimensional kiney coefficient according to the first intermediate variable and the second intermediate variable; wherein the first intermediate variable is represented as yp＝(A·χ)p(ii) a p is 1,2, …, n, p stands for a first intermediate variable ypThe formed column vector y ═ y1,…,yn]An index for each scalar element; a represents a normalization matrix obtained after normalization processing is carried out on each subdata set; χ represents the multiplication matrix A.ATDecomposing the eigenvalue to obtain the eigenvector corresponding to the maximum characteristic root;
analyzing potential patients according to the fluctuation characteristics of the calculated multidimensional kini coefficient; if the distribution map of the Gini coefficient of the magnetocardiogram data of the person to be diagnosed fluctuates obviously, analyzing the person to be diagnosed as a potential patient with myocardial ischemia; and if the distribution map of the Gini coefficient of the magnetocardiogram data of the person to be diagnosed has no obvious fluctuation, analyzing the normal myocardium of the person to be diagnosed.
2. The method for early prognosis of potential patients as claimed in claim 1, wherein the step of pre-processing the acquired physiological data set comprises:
filtering and denoising the acquired physiological data set;
averaging the filtered and noise-reduced physiological data set;
t-wave segmentation is performed on the averaged physiological data set to form a pre-processed physiological data set.
3. The method of early pre-diagnosis of potential patients according to claim 1, wherein the multidimensional kini coefficients are calculated according to a calculation formula of pre-stored multidimensional kini coefficients; the calculation formula of the pre-stored multidimensional kini coefficient is as follows:
wherein G represents the multidimensional kini coefficient, n is the number of rows of the matrix and is used for representing the number of magnetocardiogram channels, ypIs a first intermediate variable, rpP is 1,2, …, n, p represents the second intermediate variable ypThe formed column vector y ═ y1,…,yn]The index of each scalar element.
4. The method of claim 1, wherein each element in the normalized matrix is equal to the mean of each element in each subset divided by its corresponding column.
5. The method of claim 1, wherein the step of sequentially truncating the T-band physiological data set into a plurality of sub-data sets comprises sequentially truncating the T-band physiological data set into a plurality of sub-data sets by using a sliding window with a predetermined Keyny coefficient dimension as a sampling interval.
6. The method for early prognosis of potential patients as claimed in claim 5, wherein the method for early prognosis of potential patients further comprises: and sliding the sliding window to the next sampling interval, and circularly executing each step of the early pre-diagnosis method.
7. An early pre-diagnosis system for a potential patient, comprising:
the preprocessing module is used for preprocessing the acquired physiological data set to form a preprocessed physiological data set; the preprocessed physiological data set is a T-waveband magnetocardiogram data set;
the calculation module is used for dividing the preprocessed physiological data set into a plurality of sub data sets and calculating a multidimensional Keyny coefficient on each sub data set; the computing module sequentially intercepts data from the T-waveband physiological data set and divides the data into a plurality of subdata sets; carrying out normalization processing on each subdata set to form a normalized matrix; multiplying the matrix and the transposed matrix to obtain a multiplied matrix; performing eigenvalue decomposition on the multiplication matrix to obtain an eigenvector corresponding to the maximum characteristic root; calculating a first intermediate variable for calculating the multidimensional kiney coefficient according to the normalized matrix and the eigenvector corresponding to the maximum characteristic root; rearranging each element in the first intermediate variable according to a descending order, and forming each element formed after the descending order into a second intermediate variable; calculating a multidimensional kiney coefficient according to the first intermediate variable and the second intermediate variable; wherein the first intermediate variable is represented as yp＝(A·χ)p(ii) a p is 1,2, …, n, p stands for a first intermediate variable ypThe formed column vector y ═ y1,…,yn]An index for each scalar element; a represents a normalization matrix obtained after normalization processing is carried out on each subdata set; χ represents the multiplication matrix A.ATDecomposing the eigenvalue to obtain the eigenvector corresponding to the maximum characteristic root;
the analysis module is used for analyzing potential patients according to the fluctuation characteristics of the calculated multidimensional kini coefficient; if the distribution map of the Gini coefficient of the magnetocardiogram data of the person to be diagnosed fluctuates obviously, analyzing the person to be diagnosed as a potential patient with myocardial ischemia; and if the distribution map of the Gini coefficient of the magnetocardiogram data of the person to be diagnosed has no obvious fluctuation, analyzing the normal myocardium of the person to be diagnosed.
8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method for early prognosis of a potential patient according to any one of claims 1 to 6.
9. An apparatus, comprising: a processor and a memory;
the memory is for storing a computer program, and the processor is for executing the computer program stored by the memory to cause the apparatus to perform a method of early prognosis of a potential patient according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810026402.7A CN108256460B (en) | 2018-01-11 | 2018-01-11 | Method/system, computer storage medium and apparatus for early prognosis of potential patient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810026402.7A CN108256460B (en) | 2018-01-11 | 2018-01-11 | Method/system, computer storage medium and apparatus for early prognosis of potential patient |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108256460A CN108256460A (en) | 2018-07-06 |
| CN108256460B true CN108256460B (en) | 2022-01-18 |
Family
ID=62726093
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810026402.7A Active CN108256460B (en) | 2018-01-11 | 2018-01-11 | Method/system, computer storage medium and apparatus for early prognosis of potential patient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108256460B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107468243A (en) * | 2017-09-01 | 2017-12-15 | 北京大智商医疗器械有限公司 | A kind of method and device for assessing stupor degree |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013012739A1 (en) * | 2011-07-16 | 2013-01-24 | Simon Adam J | Systems and methods for the physiological assessment of brian health and the remote quality control of eeg systems |
-
2018
- 2018-01-11 CN CN201810026402.7A patent/CN108256460B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107468243A (en) * | 2017-09-01 | 2017-12-15 | 北京大智商医疗器械有限公司 | A kind of method and device for assessing stupor degree |
Non-Patent Citations (1)
| Title |
|---|
| EEG data classification using wavelet features selected by Wilcoxon statistics;Thanh Nguyen等;《Neural Computing and Applications》;20141224;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108256460A (en) | 2018-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Han et al. | Deep residual learning for compressed sensing CT reconstruction via persistent homology analysis | |
| Xiao et al. | Fast covariance estimation for high-dimensional functional data | |
| Zhang et al. | Tensor envelope partial least-squares regression | |
| Don et al. | Accuracy and speed in computing the Chebyshev collocation derivative | |
| Albasri et al. | EEG electrode selection for person identification thru a genetic-algorithm method | |
| Lee | On generalized multivariate decision tree by using GEE | |
| Tabelow et al. | Statistical parametric maps for functional MRI experiments in R: The package fmri | |
| Bonettini et al. | Scaling techniques for gradient projection-type methods in astronomical image deblurring | |
| Madsen et al. | Quantifying functional connectivity in multi‐subject fMRI data using component models | |
| Wang et al. | Sparse sufficient dimension reduction using optimal scoring | |
| Jia et al. | Preconditioning to comply with the irrepresentable condition | |
| Bachmayr et al. | Multilevel representations of isotropic Gaussian random fields on the sphere | |
| CN108256460B (en) | Method/system, computer storage medium and apparatus for early prognosis of potential patient | |
| Li et al. | svt: Singular value thresholding in MATLAB | |
| CN111753921A (en) | Hyperspectral image clustering method, device, equipment and storage medium | |
| WO2021114306A1 (en) | High-precision pet reconstruction method and apparatus based on gpu acceleration | |
| Berthelot et al. | Alternative ways to compare the detrended fluctuation analysis and its variants. Application to visual tunneling detection | |
| Silva et al. | Cuda-based parallelization of power iteration clustering for large datasets | |
| CN107895387B (en) | MRI image reconstruction method and device | |
| Estatico et al. | Shift-invariant approximations of structured shift-variant blurring matrices | |
| Lake | Nonparametric entropy estimation using kernel densities | |
| Riaz et al. | Stepwise covariance-free common principal components (CF-CPC) with an application to neuroscience | |
| Maadooliat et al. | Nonparametric collective spectral density estimation with an application to clustering the brain signals | |
| Hazelton et al. | Semiparametric density deconvolution | |
| Hong et al. | Source density‐driven independent component analysis approach for fMRI data |
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 |