Correlation analysis method of leukemia stem cell transplantation prognosis influence factors

Abstract

The invention provides a correlation analysis method of leukemia stem cell transplantation prognosis influence factors. The correlation analysis method comprises the following steps: acquiring medical examination indexes of a leukemia stem cell transplantation patient; training an abnormal data identification model by using the medical examination indexes; performing data cleaning on the target medical examination index by using the abnormal data identification model to obtain a medical examination index after data cleaning; calculating the correlation between the medical examination index after each data is cleaned and the recovery index of the corresponding leukemia stem cell transplanted patient; and extracting the medical examination indexes of which the correlation is greater than a preset threshold value. By training the abnormal data recognition model, inaccurate medical examination indexes can be effectively eliminated or corrected, then correlation calculation of the medical examination indexes and patient healing indexes is completed, the remarkable influence of the medical examination indexes on patient prognosis can be deeply known, and data support is provided for formulating personalized treatment schemes.

Description

Technical Field

[0001] The present invention relates to the technical field of correlation analysis, and in particular to a method for correlation analysis of factors influencing the prognosis of leukemia stem cell transplantation. Background Art

[0002] Leukemia is a malignant tumor originating from the hematopoietic system, characterized by the proliferation of abnormal white blood cells, which suppresses normal blood cells. Stem cell transplantation (SCT) is an important treatment for certain types of leukemia, especially after patients have undergone regular chemotherapy and radiotherapy, as it can effectively restore the patient's hematopoietic function. However, the prognosis of stem cell transplantation is affected by many factors, including the patient's age, disease type, pre-transplant status, the degree of compatibility between the donor and recipient, the transplantation time window, and postoperative complications.

[0003] Currently, the prognostic evaluation of leukemia stem cell transplantation mainly relies on clinical experience and traditional statistical analysis methods, but these methods are relatively simple and limited, making it difficult to comprehensively evaluate and predict the comprehensive factors of patient prognosis. Summary of the Invention

[0004] To solve the above problems, the present invention aims to provide a method and system for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation.

[0005] A method for correlation analysis of factors influencing the prognosis of leukemia stem cell transplantation, comprising:

[0006] Step 1: Obtain medical examination indicators of leukemia stem cell transplant patients;

[0007] Step 2: using the medical test indicators to train an abnormal data recognition model;

[0008] Step 3: Use the abnormal data recognition model to clean the target medical test indicators to obtain the medical test indicators after data cleaning;

[0009] Step 4: Calculate the correlation between each medical examination index after data cleaning and the corresponding leukemia stem cell transplantation patient recovery index;

[0010] Step 5: Extract medical test indicators whose correlation is greater than a preset threshold.

[0011] Preferably, the step 2: using the medical test indicators to train an abnormal data recognition model includes:

[0012] Step 2.1: Encode the medical test indicators using UTF-8 to form encoded data;

[0013] Step 2.2: Extract the eigenvalues of the encoded data;

[0014] Step 2.3: Construct samples based on the eigenvalues of the encoded data;

[0015] Step 2.4: Input the sample into the neural network model for training to obtain an abnormal data recognition model;

[0016] Step 2.5: Use the abnormal data recognition model to clean the target medical test indicators to obtain the medical test indicators after data cleaning.

[0017] Preferably, the step 2.2: extracting the characteristic value of the encoded data includes:

[0018] Calculate the word frequency-inverse document frequency of the encoded data, and calculate the eigenvalue of the encoded data based on the word frequency-inverse document frequency. The calculation formula for the eigenvalue of the encoded data is:

[0019]

[0020] Among them, TF-IDF(i,j) represents the TF-IDF value of the i-th medical test indicator, TF represents the word frequency, IDF represents the inverse document frequency, LTFID(Fi,j) represents the characteristic value of the i-th medical test indicator, λ represents the adjustment parameter, and f i Indicates the position where the i-th medical test indicator first appears in the coded data, n j Indicates the total number of words in the encoded data.

[0021] Preferably, the step 2.3: constructing a sample based on the eigenvalues of the encoded data includes:

[0022] Step 2.3.1: Represent medical test indicators using word vectors;

[0023] Step 2.3.2: Construct a sample based on the word vector and the feature value of the encoded data; the sample construction formula is:

[0024]

[0025] in, Represents a sample, Represents word vectors.

[0026] Preferably, the step 4: calculating the correlation between each medical examination index after data cleaning and the corresponding leukemia stem cell transplantation patient recovery index includes:

[0027] Step 4.1: normalizing the medical examination indicators after data cleaning and the corresponding leukemia stem cell transplantation patient recovery indicators to obtain normalized medical examination indicators and recovery indicators;

[0028] Step 4.2: Construct a first matrix based on the normalized medical test indicators; wherein the first matrix is:

[0029]

[0030] Among them, A1(m) represents the mth value of the first normalized medical test index, A2(m) represents the mth value of the second normalized medical test index, and A n (m) represents the m values of the nth normalized medical test index;

[0031] Step 4.3: Use the normalized recovery index to construct the second matrix; the second matrix is:

[0032] D=[B1 B2…B N ]

[0033] Among them, B1 represents the recovery index of the first patient, B2 represents the recovery index of the second patient, and B N represents the recovery index of the nth patient;

[0034] Step 4.4: Calculate the correlation based on the extreme values in the first matrix and the second matrix.

[0035] Preferably, in step 4.1, the normalization process is:

[0036] Using the formula:

[0037]

[0038] The medical examination indicators after data cleaning and the corresponding leukemia stem cell transplantation patient recovery indicators were normalized to obtain normalized medical examination indicators and recovery indicators; where σ represents the standard deviation of the data set, μ represents the mean of the data set, X represents the original data set, and X′ represents the normalized data set.

[0039] Preferably, the step 4.4: calculating the correlation according to the extreme values in the first matrix and the second matrix includes:

[0040] Using the formula:

[0041]

[0042] Calculate the correlation between each medical examination index after data cleaning and the corresponding leukemia stem cell transplantation patient recovery index; Among them, B b A represents the recovery index of the bth patient, a(k) represents the kth value of the ath normalized medical examination index, ρ represents the adjustment coefficient, and γ represents the correlation between the ath normalized medical examination index and the corresponding leukemia stem cell transplantation patient recovery index.

[0043] The present invention also provides a correlation analysis system for factors affecting the prognosis of leukemia stem cell transplantation, comprising:

[0044] A data acquisition module is used to obtain medical examination indicators of leukemia stem cell transplant patients;

[0045] A training module, configured to train an abnormal data recognition model using the medical test indicators;

[0046] A data cleaning module is used to clean the target medical test indicators using an abnormal data recognition model to obtain the medical test indicators after data cleaning;

[0047] A correlation calculation module is used to calculate the correlation between each medical test index after data cleaning and the corresponding leukemia stem cell transplant patient recovery index;

[0048] The correlation screening module is used to extract medical test indicators whose correlation is greater than a preset threshold.

[0049] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps of the above-mentioned method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation.

[0050] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation are implemented.

[0051] The beneficial effect of the correlation analysis method and system for factors affecting the prognosis of leukemia stem cell transplantation provided by the present invention is that: compared with the existing technology, the present invention can effectively eliminate or correct inaccurate medical test indicators by training an abnormal data recognition model, and then complete the correlation calculation between medical test indicators and patient recovery indicators, which can deeply understand the significant impact of medical test indicators on patient prognosis and provide data support for formulating personalized treatment plans.

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 A flow chart of a method for correlation analysis of factors influencing the prognosis of leukemia stem cell transplantation provided by an embodiment of the present invention is shown;

[0055] Figure 2 A schematic diagram of a correlation analysis system for factors influencing the prognosis of leukemia stem cell transplantation provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0056] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0057] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0058] In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "connect," "fixed," etc. should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediary; or internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0059] See also Figure 1 , a correlation analysis method for factors affecting the prognosis of leukemia stem cell transplantation, comprising:

[0060] Step 1: Obtain medical examination indicators of leukemia stem cell transplant patients; medical examination indicators include blood routine and lymphocyte subsets.

[0061] Step 2: using the medical test indicators to train an abnormal data recognition model;

[0062] Furthermore, step 2 includes:

[0063] Step 2.1: Encode the medical test indicators using UTF-8 to form encoded data;

[0064] Step 2.2: Extract the eigenvalues of the encoded data;

[0065] In step 2.2, the word frequency-inverse document frequency of the encoded data is calculated, and the eigenvalue of the encoded data is calculated based on the word frequency-inverse document frequency. The calculation formula of the eigenvalue of the encoded data is:

[0066]

[0067] Among them, TF-IDF(i,j) represents the TF-IDF value of the i-th medical test indicator, TF represents the word frequency, IDF represents the inverse document frequency, LTFID(Fi,j) represents the characteristic value of the i-th medical test indicator, λ represents the adjustment parameter, and f i Indicates the position where the i-th medical test indicator first appears in the coded data, n j Indicates the total number of words in the encoded data.

[0068] Step 2.3: Construct samples based on the eigenvalues of the encoded data;

[0069] Furthermore, step 2.3 includes:

[0070] Step 2.3.1: Represent medical test indicators using word vectors;

[0071] Step 2.3.2: Construct a sample based on the word vector and the feature value of the encoded data; the sample construction formula is:

[0072]

[0073] in, Represents a sample, Represents word vectors.

[0074] Step 2.4: Input the sample into the neural network model for training to obtain an abnormal data recognition model;

[0075] Word vectors can capture the semantic relationship between words, while TF-IDF can highlight the weight of key indicators. By combining TF-IDF values with the semantic information of word vectors, the present invention can use neural network models to perform more complex feature learning, thereby improving training effects.

[0076] First, the sample is input into the convolutional layer for convolution and then substituted into the activation function. In the convolutional layer, the activation function maps the input signal to a new output space by performing a nonlinear transformation on the output of the neuron. This process introduces nonlinear characteristics, allowing the neural network to learn nonlinear relationships. The convolutional result is input into the pooling layer for downsampling. Finally, the pooled data is input into the fully connected layer, which outputs the classification result.

[0077] Step 2.5: Use the abnormal data recognition model to clean the target medical test indicators to obtain the medical test indicators after data cleaning.

[0078] Medical laboratory index data may have various problems, such as missing data, errors, outliers, etc. Cleaning data can help identify and correct these problems, improve data accuracy and consistency, and thus improve data quality.

[0079] Step 3: Use the abnormal data recognition model to clean the target medical test indicators to obtain the medical test indicators after data cleaning;

[0080] Step 4: Calculate the correlation between each medical examination index after data cleaning and the corresponding leukemia stem cell transplantation patient recovery index;

[0081] The recovery index can be determined by the patient's daily health status. At the same time, these health status indicators are weighted in combination with the opinions of medical experts to construct the recovery index for leukemia stem cell transplant patients.

[0082] Furthermore, step 4 includes:

[0083] Step 4.1: normalizing the medical examination indicators after data cleaning and the corresponding leukemia stem cell transplantation patient recovery indicators to obtain normalized medical examination indicators and recovery indicators;

[0084] In step 4.1, the normalization process is:

[0085] Using the formula:

[0086]

[0087] The medical examination indicators after data cleaning and the corresponding leukemia stem cell transplantation patient recovery indicators were normalized to obtain normalized medical examination indicators and recovery indicators; where σ represents the standard deviation of the data set, μ represents the mean of the data set, X represents the original data set, and X′ represents the normalized data set.

[0088] Step 4.2: Construct a first matrix based on the normalized medical test indicators; wherein the first matrix is:

[0089]

[0090] Among them, A1(m) represents the mth value of the first normalized medical test index, A2(m) represents the mth value of the second normalized medical test index, and A n (m) represents the m values of the nth normalized medical test index;

[0091] Step 4.3: Use the normalized recovery index to construct the second matrix; the second matrix is:

[0092] D=[B1 B2…B N ]

[0093] Among them, B1 represents the recovery index of the first patient, B2 represents the recovery index of the second patient, and B N represents the recovery index of the nth patient;

[0094] Step 4.4: Calculate the correlation based on the extreme values in the first matrix and the second matrix.

[0095] In step 4.4, the present invention may adopt the formula:

[0096]

[0097] Calculate the correlation between each medical examination index after data cleaning and the corresponding leukemia stem cell transplantation patient recovery index; Among them, B b A represents the recovery index of the bth patient, a (k) represents the kth value of the ath normalized medical examination index, ρ represents the adjustment coefficient, and γ represents the correlation between the ath normalized medical examination index and the corresponding leukemia stem cell transplantation patient recovery index.

[0098] Step 5: Extract medical test indicators whose correlation is greater than a preset threshold.

[0099] By training an abnormal data recognition model, the present invention can effectively eliminate or correct inaccurate medical test indicators, and then complete the correlation calculation between medical test indicators and patient recovery indicators. It can deeply understand the significant impact of medical test indicators on patient prognosis and provide data support for formulating personalized treatment plans.

[0100] See also Figure 2 The present invention also provides a correlation analysis system for factors affecting the prognosis of leukemia stem cell transplantation, comprising:

[0101] A data acquisition module is used to obtain medical examination indicators of leukemia stem cell transplant patients;

[0102] A training module, configured to train an abnormal data recognition model using the medical test indicators;

[0103] A data cleaning module is used to clean the target medical test indicators using an abnormal data recognition model to obtain the medical test indicators after data cleaning;

[0104] A correlation calculation module is used to calculate the correlation between each medical test index after data cleaning and the corresponding leukemia stem cell transplant patient recovery index;

[0105] The correlation screening module is used to extract medical test indicators whose correlation is greater than a preset threshold.

[0106] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus. The computer program, when executed by the processor, implements the steps of the above-mentioned method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation. Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation described in the above-mentioned technical solution, and are not further elaborated here.

[0107] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation are implemented. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as the beneficial effects of the method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation described in the above-mentioned technical solution, and will not be elaborated here.

[0108] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technical solution that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation, characterized in that: include: Step 1: Obtain medical examination indicators of leukemia stem cell transplant patients; Step 2: using the medical test indicators to train an abnormal data recognition model; Step 3: Use the abnormal data recognition model to clean the target medical test indicators to obtain the medical test indicators after data cleaning; Step 4: Calculate the correlation between each medical examination index after data cleaning and the corresponding leukemia stem cell transplantation patient recovery index; Step 5: Extract medical test indicators whose correlation is greater than a preset threshold.

2. The method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation according to claim 1, characterized in that: The step 2: using the medical test indicators to train an abnormal data recognition model includes: Step 2.1: Encode the medical test indicators using UTF-8 to form encoded data; Step 2.2: Extract the eigenvalues of the encoded data; Step 2.3: Construct samples based on the eigenvalues of the encoded data; Step 2.4: Input the sample into the neural network model for training to obtain an abnormal data recognition model; Step 2.5: Use the abnormal data recognition model to clean the target medical test indicators to obtain the medical test indicators after data cleaning.

3. The method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation according to claim 2, characterized in that: The step 2.2: extracting the characteristic value of the encoded data includes: Calculate the word frequency-inverse document frequency of the encoded data, and calculate the eigenvalue of the encoded data based on the word frequency-inverse document frequency. The calculation formula for the eigenvalue of the encoded data is: Among them, TF-IDF(i,j) represents the TF-IDF value of the i-th medical test indicator, TF represents the word frequency, IDF represents the inverse document frequency, LTFID(Fi,j) represents the characteristic value of the i-th medical test indicator, λ represents the adjustment parameter, and f i Indicates the position where the i-th medical test indicator first appears in the coded data, n j Represents the total number of words in the encoded data, and Z(i,j) represents the position parameter.

4. The method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation according to claim 3, characterized in that: The step 2.3: constructing a sample based on the eigenvalues of the encoded data, includes: Step 2.3.1: Represent medical test indicators using word vectors; Step 2.3.2: Construct a sample based on the word vector and the feature value of the encoded data; the sample construction formula is: in, Represents a sample, Represents word vectors.

5. The method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation according to claim 4, characterized in that: Step 4: Calculating the correlation between each medical test index after data cleaning and the corresponding leukemia stem cell transplant patient recovery index, including: Step 4.1: normalizing the medical examination indicators after data cleaning and the corresponding leukemia stem cell transplantation patient recovery indicators to obtain normalized medical examination indicators and recovery indicators; Step 4.2: Construct a first matrix based on the normalized medical test indicators; wherein the first matrix is: Among them, A1(m) represents the mth value of the first normalized medical test index, A2(m) represents the mth value of the second normalized medical test index, and A n (m) represents the m values of the nth normalized medical test index; Step 4.3: Use the normalized recovery index to construct the second matrix; the second matrix is: D=[B1 B2…B N ] Among them, B1 represents the recovery index of the first patient, B2 represents the recovery index of the second patient, and B N represents the recovery index of the nth patient; Step 4.4: Calculate the correlation based on the extreme values in the first matrix and the second matrix.

6. The method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation according to claim 5, characterized in that: In step 4.1, the normalization process is as follows: Using the formula: The medical examination indicators after data cleaning and the corresponding leukemia stem cell transplantation patient recovery indicators were normalized to obtain normalized medical examination indicators and recovery indicators; where σ represents the standard deviation of the data set, μ represents the mean of the data set, X represents the original data set, and X′ represents the normalized data set.

7. The method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation according to claim 6, characterized in that: The step 4.4: calculating the correlation based on the extreme values in the first matrix and the second matrix, includes: Using the formula: Calculate the correlation between each medical examination index after data cleaning and the corresponding leukemia stem cell transplantation patient recovery index; Among them, B b A represents the recovery index of the bth patient, a (k) represents the kth value of the ath normalized medical examination index, ρ represents the adjustment coefficient, and γ represents the correlation between the ath normalized medical examination index and the corresponding leukemia stem cell transplantation patient recovery index.

8. A correlation analysis system for factors affecting the prognosis of leukemia stem cell transplantation, characterized in that: include: A data acquisition module is used to obtain medical examination indicators of leukemia stem cell transplant patients; A training module, configured to train an abnormal data recognition model using the medical test indicators; A data cleaning module is used to clean the target medical test indicators using an abnormal data recognition model to obtain the medical test indicators after data cleaning; A correlation calculation module is used to calculate the correlation between each medical test index after data cleaning and the corresponding leukemia stem cell transplant patient recovery index; The correlation screening module is used to extract medical test indicators whose correlation is greater than a preset threshold.

9. An electronic device comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps of the method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for correlation analysis of factors affecting the prognosis of leukemia stem cell transplantation according to any one of claims 1 to 7 are implemented.

Images