Tumor marker combined detection method

Abstract

The invention relates to the field of tumor marker combination detection, and particularly discloses a tumor marker combination detection method which comprises the following steps: S1, tumor marker selection and preliminary evaluation: S11, candidate tumor marker selection: selecting a group of candidate tumor markers as evaluation objects according to tumor types, clinical requirements and research backgrounds; s12, data collection and preprocessing: collecting type information, clinical significance information, sensibility Seni and specificity Spei data of each candidate tumor marker, and data required for calculation of a detection value variation coefficient Timean; according to the method, through careful candidate tumor marker selection and preliminary evaluation and strict data collection and processing, a tumor marker subset with high complementarity can be screened out, so that the accuracy and reliability of detection are improved; and meanwhile, comprehensive evaluation is performed in combination with a machine learning prediction result and a fusion formula, so that the reliability of a detection result is further enhanced.

Description

Technical Field

[0001] The present invention belongs to the field of combined detection of tumor markers, and specifically relates to a method for combined detection of tumor markers. Background Art

[0002] Tumor marker detection refers to a method of quantitatively or qualitatively analyzing tumor markers in blood, urine, tissue, or other body fluids through specific detection techniques, thereby assisting in the diagnosis of cancer, evaluating the progression of the disease, and monitoring the treatment effect. These markers are usually proteins, carbohydrates, enzymes, or other chemical substances produced or released into body fluids by tumor cells.

[0003] In traditional techniques, the detection results of tumor markers are often analyzed separately, lacking a method for comprehensive evaluation. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a method for combined detection of tumor markers to solve the problem that in the prior art, the detection results of tumor markers are often analyzed separately and lack a method for comprehensive evaluation.

[0005] A method for combined detection of tumor markers includes the following steps:

[0006] S1. Selection and preliminary evaluation of tumor markers:

[0007] S11. Selection of candidate tumor markers: According to the tumor type, clinical needs, and research background, select a group of candidate tumor markers as the evaluation object;

[0008] S12. Data collection and preprocessing: Collect type information, clinical significance information, sensitivity Sen i and specificity Spe i data of each candidate tumor marker, as well as the data required for calculating the coefficient of variation T i mean of the detection value;

[0009] S13. Complementary evaluation: Apply the complementary evaluation formula to evaluate the complementarity of candidate tumor markers, obtain the complementary score C, and screen out a subset of tumor markers with strong complementarity;

[0010] S2. Sample selection and quality evaluation:

[0011] S21. Sample collection and preprocessing: According to the detection requirements, collect a certain number of samples and perform necessary preprocessing;

[0012] S22. Determination of sample quality evaluation indicators: Determine sample quality evaluation indicators, including sample purity, integrity, stability, and representativeness;

[0013] S23. Data collection and calculation: Collect the actual measured values, reference values, estimated maximum and minimum values of each evaluation index, as well as the stability evaluation index and its weight coefficient.

[0014] S24. Comprehensive quality evaluation: Apply the sample quality evaluation formula to comprehensively evaluate the sample quality, obtain the sample quality score Q, and screen out the samples with qualified quality.

[0015] Step S3. Tumor marker detection and result fusion:

[0016] S31. Tumor marker detection: Perform actual detection on the selected subset of tumor markers and collect the detection results.

[0017] S32. Data preprocessing: Calculate the mean μ i and standard deviation σ i of each tumor marker detection result, and apply machine learning algorithms for prediction to obtain the prediction result ML i ;

[0018] S33. Result fusion: Apply the tumor marker detection result fusion formula to fuse the tumor marker detection results to obtain the comprehensive evaluation result R.

[0019] S4. Result interpretation and application:

[0020] S41. Result interpretation: Based on the comprehensive evaluation result R, combined with clinical information and genetic background information, perform auxiliary diagnosis and prognosis evaluation on the tumor.

[0021] S42. Report generation: Generate a detailed test report, including test steps, results, interpretations, and suggestions.

[0022] S43. Suggestions for follow-up actions: Based on the test results, put forward suggestions for further examinations, treatments, and monitoring.

[0023] Preferably, in step S13, the complementary evaluation formula takes into account the type, clinical significance, sensitivity, and specificity of the tumor markers, as well as the variability and stability of the detection values.

[0024] Preferably, in step S13, the complementary evaluation formula is as follows:

[0025]

[0026] where C is the complementary score, n is the number of candidate tumor markers, T i type is the type score of the i-th tumor marker, is the clinical significance score of the i-th tumor marker, Sen i and Spei are the sensitivity and specificity of the i-th tumor marker, respectively, T i var and T i mean are the coefficient of variation and the average value of the measured values of the i-th tumor marker, respectively.

[0027] Preferably, in step S24, the sample quality assessment formula comprehensively considers multiple evaluation indicators, ensuring the reliability and representativeness of the sample.

[0028] Preferably, the sample quality assessment formula is as follows:

[0029]

[0030] where Q is the sample quality score, m is the number of sample quality evaluation indicators, V j is the actual measured value of the j-th evaluation indicator, is the reference value of the j-th evaluation indicator, and are the estimated maximum and minimum values of the j-th evaluation indicator, respectively, l is the number of sample stability evaluation indicators, P k is the value of the k-th stability indicator, is the estimated maximum value of the k-th stability indicator, γ k is the weight coefficient of the k-th stability indicator.

[0031] Preferably, in step S33, the result fusion formula combines the detection results of tumor markers and the machine learning prediction results, improving the accuracy and reliability of the detection.

[0032] Preferably, the tumor marker detection result fusion formula is as follows:

[0033]

[0034] where R is the comprehensive evaluation result, n′ is the number of actually detected tumor markers, w i is the weight of the i-th tumor marker, D i is the detection result of the i-th tumor marker, μ i and σ i are the mean and standard deviation of the detection results of the i-th tumor marker, respectively, ML i is the prediction result of the i-th tumor marker based on the machine learning algorithm.

[0035] Preferably, the result interpretation and application part combines clinical expertise and patient individual information, providing personalized diagnosis, prognosis assessment and follow-up action recommendations.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] Through careful selection and preliminary evaluation of candidate tumor markers, as well as strict data collection and processing, this method can screen out a subset of tumor markers with strong complementarity, thereby improving the accuracy and reliability of detection; at the same time, combining the machine learning prediction results and the fusion formula for comprehensive evaluation further enhances the reliability of the detection results;

[0038] By comprehensively evaluating the tumor marker detection results, clinical information, and genetic background information of patients, this method can provide personalized diagnosis, prognosis evaluation, and follow-up action suggestions for patients; this personalized medical service can better meet the needs of patients, improve the treatment effect and quality of life, and achieve more precise and effective medical treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic flow diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0041] As Figure 1 shown:

[0042] Embodiment 1: The present invention provides a method for detecting a combination of tumor markers, including the following steps:

[0043] S1. Selection and preliminary evaluation of tumor markers:

[0044] S11. Selection of candidate tumor markers: According to the tumor type, clinical needs, and research background, a group of candidate tumor markers are selected as the evaluation objects;

[0045] S12. Data collection and preprocessing: Collect the type information, clinical significance information, sensitivity Sen i and specificity Spe i data of each candidate tumor marker, as well as the data required for calculating the coefficient of variation T i mean of the detection value;

[0046] S13. Complementarity evaluation: Apply the complementarity evaluation formula to evaluate the complementarity of the candidate tumor markers, obtain the complementarity score C, and screen out a subset of tumor markers with strong complementarity;

[0047] S2. Sample Selection and Quality Assessment:

[0048] S21. Sample Collection and Pretreatment: Collect a certain number of samples according to the detection requirements and perform necessary pretreatment;

[0049] S22. Determination of Sample Quality Assessment Indicators: Determine the sample quality assessment indicators, including sample purity, integrity, stability, and representativeness;

[0050] S23. Data Collection and Calculation: Collect the actual measured values, reference values, estimated maximum and minimum values of each assessment indicator, as well as the stability assessment indicator and its weight coefficient;

[0051] S24. Comprehensive Quality Assessment: Apply the sample quality assessment formula to comprehensively evaluate the sample quality, obtain the sample quality score Q, and screen out the samples with qualified quality;

[0052] Step S3. Tumor Marker Detection and Result Fusion:

[0053] S31. Tumor Marker Detection: Perform actual detection on the selected subset of tumor markers and collect the detection results;

[0054] S32. Data Pretreatment: Calculate the mean μ i and standard deviation σ i of each tumor marker detection result, and apply machine learning algorithms for prediction to obtain the prediction result ML i ;

[0055] S33. Result Fusion: Apply the tumor marker detection result fusion formula to fuse the tumor marker detection results to obtain the comprehensive evaluation result R;

[0056] S4. Result Interpretation and Application:

[0057] S41. Result Interpretation: Based on the comprehensive evaluation result R, combined with clinical information and genetic background information, perform auxiliary diagnosis and prognosis assessment of the tumor;

[0058] S42. Report Generation: Generate a detailed detection report, including detection steps, results, interpretations, and suggestions;

[0059] S43. Suggestions for Follow-up Actions: Based on the detection results, put forward suggestions for further examinations, treatments, and monitoring.

[0060] As can be seen from the above, this method starts from the selection and preliminary evaluation of candidate tumor markers, and through data collection, preprocessing, and complementary evaluation, screens out a subset of tumor markers with strong complementarity; subsequently, sample selection and quality evaluation are carried out to ensure the purity, integrity, stability, and representativeness of the samples, so as to obtain high-quality test samples; in the tumor marker detection stage, the selected marker subset is actually detected, and combined with the machine learning prediction results, a fusion formula is applied to comprehensively evaluate the detection results; finally, according to the comprehensive evaluation results, combined with clinical information and genetic background information, auxiliary diagnosis and prognosis evaluation of tumors are carried out, and a detailed test report is generated, and suggestions for subsequent examinations, treatments, and monitoring are put forward. This method not only improves the accuracy and reliability of tumor detection, but also provides strong support for clinical decision-making, helping to achieve more personalized and precise medicine.

[0061] Example 2: This example is basically the same as the previous example, except that in step S13, the complementary evaluation formula takes into account the type, clinical significance, sensitivity, and specificity of the tumor markers, as well as the variability and stability of the test values.

[0062] Specifically, in step S13, the complementary evaluation formula is as follows:

[0063]

[0064] where C is the complementary score, n is the number of candidate tumor markers, T i type is the type score of the i-th tumor marker, is the clinical significance score of the i-th tumor marker, Sen i and Spe i are the sensitivity and specificity of the i-th tumor marker respectively, T i var and T i mean are the coefficient of variation and average value of the test value of the i-th tumor marker respectively;

[0065] The specific application process of the above formula is as follows:

[0066] First, clarify each parameter in the formula and collect the corresponding data. These parameters include:

[0067] C: The complementary score of the tumor marker combination, which is the target value to be calculated.

[0068] n: The number of candidate tumor markers, which depends on the types of markers actually selected.

[0069] T i type: The type score of the i-th tumor marker. It can be quantified according to the importance of the tumor type. For example, some tumor types have a higher degree of malignancy or are more difficult to treat, so the markers associated with them can obtain a higher type score.

[0070] The clinical significance score of the i-th tumor marker. It needs to be quantified according to the value of the marker in aspects such as diagnosis and prognosis. Markers that can provide more clinical information will obtain a higher clinical significance score.

[0071] Sen i and Spe i : They are the sensitivity and specificity of the i-th tumor marker respectively. Obtained through clinical trials or research, reflecting the accuracy and reliability of the marker in detecting tumors.

[0072] T i var and T i mean : They are the coefficient of variation and the mean of the detection values of the i-th tumor marker respectively. These values are used to evaluate the stability of the marker. The smaller the coefficient of variation and the larger the mean, usually indicating that the detection values of the marker are more stable.

[0073] II. Data Collection and Processing

[0074] After clarifying the formula parameters, collect the corresponding data. This involves consulting relevant literature, databases or conducting clinical trials. The collected data needs to be preprocessed to ensure its accuracy and consistency. For example, for sensitivity and specificity data, we need to ensure that it comes from reliable clinical trials or research; for type scores and clinical significance scores, we need to make reasonable quantification based on professional knowledge and clinical experience.

[0075] III. Formula Application and Calculation

[0076] After collecting sufficient data and preprocessing it, we can substitute this data into the formula for calculation. The specific steps are as follows:

[0077] For each candidate tumor marker i, calculate its type score, clinical significance score, sensitivity, specificity and stability indicators (coefficient of variation and mean).

[0078] Substitute these values into the corresponding positions in the formula.

[0079] According to the formula for calculation, obtain the complementary score C of the tumor marker combination.

[0080] IV. Result Interpretation and Application

[0081] After calculating the complementarity score C, it is interpreted and applied. Generally, the higher the score, the stronger the complementarity between the tumor marker combinations, that is, these markers can provide more comprehensive and accurate information in detecting tumors. Therefore, we can screen out the best marker combinations according to the score for subsequent diagnosis, prognosis evaluation, and treatment monitoring.

[0082] In addition, we can also combine the complementarity score with other clinical information for comprehensive analysis and judgment. For example, for certain patient groups with specific genetic backgrounds or clinical manifestations, we need to select marker combinations with higher complementarity scores for targeted detection and analysis.

[0083] Specifically, in step S24, the sample quality assessment formula comprehensively considers multiple evaluation indicators to ensure the reliability and representativeness of the sample.

[0084] Specifically, the sample quality assessment formula is as follows:

[0085]

[0086] Among them, Q is the sample quality score, m is the number of sample quality evaluation indicators, V j is the actual measured value of the jth evaluation indicator, is the reference value of the jth evaluation indicator, and are the estimated maximum and minimum values of the jth evaluation indicator respectively, l is the number of sample stability evaluation indicators, P k is the value of the kth stability indicator, is the estimated maximum value of the kth stability indicator, γ k is the weight coefficient of the kth stability indicator;

[0087] The specific application process of the above formula is as follows:

[0088] I. Formula Understanding and Parameter Setting

[0089] First, understand the structure of the formula and the meanings of each parameter. Q in the formula represents the sample quality score, which is an indicator comprehensively reflecting the sample quality. m and l represent the number of sample quality evaluation indicators and the number of sample stability evaluation indicators respectively. V j 、 and represent the actual measured value, reference value, estimated maximum value, and estimated minimum value of the jth evaluation indicator respectively. P k 、 and γ k represent the value, estimated maximum value, and weight coefficient of the kth stability indicator respectively.

[0090] When setting parameters, determine the evaluation indicators and stability indicators according to specific experimental or research requirements. For example, in biomedical research, common evaluation indicators include sample purity, integrity, stability, and representativeness, etc. The stability indicators include the impact of environmental factors such as temperature, humidity, and light on sample stability.

[0091] II. Data Collection and Preprocessing

[0092] After determining the evaluation indicators and stability indicators, collect the corresponding data. This involves using professional detection instruments or methods to conduct quantitative or qualitative analysis on the samples. The collected data needs to be preprocessed to ensure its accuracy and consistency. For example, for the actual measurement value V j , we need to ensure that it is obtained through a reliable method and has been properly calibrated and corrected. For the reference value V jref , we need to ensure that it is based on a large amount of experimental data or professional literature and has reliability and representativeness.

[0093] III. Formula Application and Calculation

[0094] After collecting sufficient data and preprocessing it, substitute this data into the formula for calculation. The specific steps are as follows:

[0095] For each evaluation indicator j, calculate the deviation between its actual measurement value V j and the reference value V jref , and perform weighted processing according to the square term in the formula.

[0096] Sum up the weighted deviations of all evaluation indicators and take the negative exponential function to obtain the partial score related to the sample quality.

[0097] For each stability indicator k, calculate the relative deviation between its value P k and the estimated maximum value P kmax , and perform weighted processing according to the product term in the formula.

[0098] Multiply the weighted relative deviations of all stability indicators to obtain the partial score related to the sample stability.

[0099] Multiply the partial scores related to the sample quality and stability to obtain the final sample quality score Q.

[0100] IV. Result Interpretation and Application

[0101] After calculating the sample quality score Q, interpret and apply it. A higher score means better sample quality and it is more suitable for subsequent experiments or research. Classify or categorize the samples according to the score to better manage and utilize these samples.

[0102] Specifically, in step S33, the result fusion formula combines the detection results of tumor markers and the machine learning prediction results, improving the accuracy and reliability of the detection.

[0103] As can be seen from the above, this method adopts a more refined complementary evaluation formula in step S13. This formula not only considers the type, clinical significance, sensitivity, and specificity of tumor markers, but also incorporates the variability and stability of the detection values, enabling a more accurate assessment of the complementarity of candidate tumor markers. In the sample quality assessment stage, Example 2 also adopts a sample quality assessment formula that comprehensively considers multiple evaluation indicators to ensure the reliability and representativeness of the samples. Finally, in step S33, the result fusion formula combines the actual detection results of tumor markers and the machine learning prediction results, further improving the accuracy and reliability of the detection; through these improvements, Example 2 provides more accurate and comprehensive support for clinical decision-making, contributing to the realization of more personalized and effective tumor diagnosis and treatment strategies.

[0104] Example 3: This example is basically the same as the previous example, except that the tumor marker detection result fusion formula is as follows:

[0105]

[0106] Where R is the comprehensive evaluation result, n′ is the number of actually detected tumor markers, w i is the weight of the i-th tumor marker, D i is the detection result of the i-th tumor marker, μ i and σ i are the mean and standard deviation of the detection results of the i-th tumor marker respectively, and ML i is the prediction result of the i-th tumor marker based on the machine learning algorithm;

[0107] The specific application process of the above formula is as follows:

[0108] I. Formula Preparation and Parameter Understanding

[0109] First, clarify each parameter in the formula and understand its meaning. These parameters include:

[0110] R: The comprehensive evaluation result, which is the target value to be calculated and reflects the fusion effect of the detection results of multiple tumor markers.

[0111] n′: The number of actually detected tumor markers, which depends on specific research or clinical needs.

[0112] w i$w_i$: The weight of the $i$-th tumor marker, which reflects the importance of this marker in the comprehensive evaluation. The determination of the weight is usually based on factors such as the sensitivity, specificity, and clinical significance of the marker.

[0113] D i $D_i$: The test result of the $i$-th tumor marker, which is the value obtained through experiments or clinical tests.

[0114] μ i and σ i $μ_i$ and $σ_i$: Respectively, the mean and standard deviation of the test results of the $i$-th tumor marker, which are used to describe the distribution characteristics of the test values of this marker. These values can be calculated from a large amount of experimental data or historical test records.

[0115] ML i $ML_i$: The prediction result of the $i$-th tumor marker based on machine learning algorithms. Machine learning algorithms can train models according to existing data and predict new test data, so as to provide more comprehensive information.

[0116] II. Data Collection and Processing

[0117] Before applying the formula, collect the corresponding data. This includes:

[0118] Tumor marker test results: Obtain the specific values of each tumor marker through experiments or clinical tests. These data should be accurate, reliable, and have been properly calibrated and corrected.

[0119] Mean and standard deviation: For each tumor marker, calculate the mean and standard deviation of its test results. These values can be obtained through statistical methods and are used to describe the distribution characteristics of the test values of the marker.

[0120] Machine learning prediction results: Use appropriate machine learning algorithms to predict tumor markers. This usually involves steps such as data preprocessing, feature selection, model training, and prediction. The prediction results should be combined with the actual test results to improve the accuracy of the comprehensive evaluation.

[0121] Weight determination: Determine the weight of each marker according to factors such as the sensitivity, specificity, and clinical significance of the marker. The determination of the weight should be based on reliable data and professional knowledge to ensure the fairness and accuracy of the comprehensive evaluation.

[0122] III. Formula Application and Calculation

[0123] After collecting sufficient data and performing preprocessing, substitute these data into the formula for calculation. The specific steps are as follows:

[0124] For each tumor marker $i$, calculate its test result $D_i$ i and the mean $μ_i$i The deviation between them is weighted according to the exponential function in the formula.

[0125] Sum the weighted deviations of all tumor markers and divide by the weighted sum of all markers (considering the weighted influence of the machine learning prediction result ML i to obtain the comprehensive evaluation result R.

[0126] IV. Result Interpretation and Application

[0127] After obtaining the comprehensive evaluation result R, it is interpreted and applied. The larger the value of R, the more consistent the detection results of multiple tumor markers are, and the higher the accuracy of the comprehensive evaluation. The tumor is assisted in diagnosis, prognosis evaluation or treatment monitoring according to the value of R. In addition, the value of R can be combined with other clinical information for comprehensive analysis and judgment to provide more personalized medical advice.

[0128] Specifically, the result interpretation and application part combines clinical professional knowledge and patient individual information to provide personalized diagnosis, prognosis evaluation and suggestions for follow-up actions.

[0129] As can be seen from the above, in the tumor marker combination detection method of this embodiment, the fusion formula of tumor marker detection results is optimized; the fusion formula not only considers the actual number of detected tumor markers, the weight of each marker and the detection results, but also introduces the machine learning prediction results, as well as the mean and standard deviation of the detection results of each marker, so as to more comprehensively reflect the status of tumor markers; in the specific application process, this formula can comprehensively consider multiple factors, improve the accuracy and reliability of detection; in addition, this embodiment has also been improved in the result interpretation and application part, combining clinical professional knowledge and patient individual information to provide personalized diagnosis, prognosis evaluation and suggestions for follow-up actions for patients; this personalized medical service can better meet the needs of patients and improve the treatment effect and quality of life.

[0130] The standard parts used in the present invention can all be purchased from the market. The special-shaped parts can be customized according to the description in the specification and the drawings. The specific connection methods of each part all adopt conventional means such as bolts, rivets, welding, etc. that are mature in the prior art. The machines, parts and equipment all adopt conventional models in the prior art. Coupled with the circuit connection adopting the conventional connection method in the prior art, it will not be elaborated here. The content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0131] In the description of the present invention, 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 quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0132] In the present invention, unless otherwise clearly defined and limited, the terms "mounted", "connected", "coupled", "fixed", etc. shall be construed in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0133] In the present invention, unless otherwise clearly defined and limited, the first feature being "on" or "under" the second feature may be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, the first feature being "above", "over" and "on top of" the second feature may be that the first feature is directly above or obliquely above the second feature, or merely indicates that the first feature has a higher horizontal height than the second feature. The first feature being "under", "beneath" and "underneath" the second feature may be that the first feature is directly below or obliquely below the second feature, or merely indicates that the first feature has a lower horizontal height than the second feature.

[0134] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0135] In the drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments are involved, and other structures can refer to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0136] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for combined detection of tumor markers, characterized in that: The following steps are involved: S1. Tumor marker selection and preliminary evaluation: S11. Selection of candidate tumor markers: Based on tumor type, clinical needs and research background, a group of candidate tumor markers are selected as evaluation objects; S12. Data collection and preprocessing: Collect the type information, clinical significance information, sensitivity information, and i and specific Spe i Data, and the coefficient of variation of the test value T i mean The data required for calculation; S13. Complementarity assessment: Use the complementarity assessment formula to assess the complementarity of candidate tumor markers, obtain a complementarity score C, and screen out a subset of tumor markers with strong complementarity; S2. Sample selection and quality assessment: S21. Sample collection and pretreatment: Collect a certain number of samples according to the testing requirements and perform necessary pretreatment; S22. Determination of sample quality assessment indicators: Determine sample quality assessment indicators, including sample purity, integrity, stability and representativeness; S23, data collection and calculation: collect the actual measured value, reference value, estimated maximum value and minimum value of each evaluation indicator, as well as the stability evaluation indicator and its weight coefficient; S24, comprehensive quality assessment: Apply the sample quality assessment formula to comprehensively assess the sample quality, obtain the sample quality score Q, and screen out samples with qualified quality; Step S3: Tumor marker detection and result fusion: S31. Tumor marker detection: actual detection of the selected tumor marker subsets and collection of test results; S32. Data preprocessing: Calculate the mean μ of each tumor marker test result i and standard deviation σ i , and apply machine learning algorithms to make predictions and get the prediction results ML i ; S33, result fusion: using the tumor marker test result fusion formula to fuse the tumor marker test results to obtain a comprehensive evaluation result R; S4. Interpretation and application of results: S41. Result interpretation: Based on the comprehensive evaluation result R, combined with clinical information and genetic background information, auxiliary diagnosis and prognosis evaluation of the tumor are performed; S42, Report Generation: Generate a detailed test report, including test steps, results, explanations and recommendations; S43. Follow-up action recommendations: Based on the test results, make further examination, treatment and monitoring recommendations.

2. A tumor marker combination detection method according to claim 1, characterized in that: In step S13, the complementarity evaluation formula takes into account the type, clinical significance, sensitivity and specificity of the tumor marker, as well as the variability and stability of the detection value.

3. A tumor marker combination detection method as claimed in claim 2, characterized in that: In step S13, the complementarity evaluation formula is as follows: Where C is the complementarity score, n is the number of candidate tumor markers, T i type is the type score of the ith tumor marker, is the clinical significance score of the ith tumor marker, Sen i and Spe i are the sensitivity and specificity of the ith tumor marker, T i var and T i mean are the coefficient of variation and mean value of the detection value of the ith tumor marker, respectively.

4. A tumor marker combination detection method as claimed in claim 3, characterized in that: In step S24, the sample quality evaluation formula comprehensively considers multiple evaluation indicators to ensure the reliability and representativeness of the sample.

5. A tumor marker combination detection method as claimed in claim 4, characterized in that: The sample quality evaluation formula is as follows: Among them, Q is the sample quality score, m is the number of sample quality evaluation indicators, V j is the actual measured value of the jth evaluation indicator, is the reference value of the jth evaluation indicator, and are the estimated maximum and minimum values ​​of the jth evaluation index, l is the number of sample stability evaluation indicators, P k is the value of the kth stability index, is the estimated maximum value of the kth stability index, γ k is the weight coefficient of the kth stability index.

6. A tumor marker combination detection method as claimed in claim 5, characterized in that: In step S33, the result fusion formula combines the detection results of tumor markers and the machine learning prediction results, thereby improving the accuracy and reliability of the detection.

7. A tumor marker combination detection method according to claim 6, characterized in that: The tumor marker detection result fusion formula is as follows: Among them, R is the comprehensive evaluation result, n′ is the number of tumor markers actually detected, and w i is the weight of the ith tumor marker, D i is the test result of the ith tumor marker, μ i and σ i are the mean and standard deviation of the i-th tumor marker test results, ML i is the prediction result of the i-th tumor marker based on the machine learning algorithm.

8. A tumor marker combination detection method as claimed in claim 1, characterized in that: In S4, the interpretation and application of results section combines clinical expertise and individual patient information to provide personalized diagnosis, prognosis assessment, and follow-up action recommendations.

Images