A lung cancer detection method and system using high-throughput sequencing technology

Abstract

The present invention provides a lung cancer detection method and system using high-throughput sequencing technology, which belongs to the field of bioinformatics technology, and specifically includes: determining the false detection data of lung cancer markers in the detection depth corresponding to high-throughput sequencing and the PCR amplification process based on the analysis results of the detection data, and combining the distribution data of lung cancer markers and other types of lung cancer markers in different patients to perform the credibility coefficient of lung cancer markers and determine the credible markers, determine the similarity between the distribution data of the credible markers of the patient and the markers of different historically diagnosed patients, and combine the credibility coefficients of different credible markers to perform the distribution similarity coefficient between the patient and different historically diagnosed patients and determine the reference diagnosed patients, and output the patient's lung cancer detection results based on the distribution data of misdiagnosed patients among the reference diagnosed patients within different similarity coefficient intervals, thereby improving the accuracy of the diagnosis results.

Description

Technical Field

[0001] The present invention belongs to the field of bioinformatics, and in particular relates to a lung cancer detection method and system using high-throughput sequencing technology. Background Art

[0002] In order to detect and process lung cancer, the invention patent application CN202311543059.0 "Knowledge Graph Carcinogenicity Representation Prediction Method for Multi-Type Mutations in Lung Cancer Genome" uses data comparison and correction results of whole genome high-throughput sequencing results, transforms abnormal data and constructs a preliminary knowledge graph, incorporates additional information and improves the knowledge graph, but there are the following technical problems:

[0003] In the process of lung cancer detection using high-throughput sequencing technology, existing technical solutions often perform lung cancer detection based on the identification results of tumor markers or marker combinations in genetic test results. However, in addition to the influence of the patient's own genetic mutation, the genetic test results are also related to PCR amplification, detection depth, etc. Therefore, if the influence of other factors is ignored, the accuracy of the lung cancer test results cannot be guaranteed.

[0004] In response to the above technical problems, the present invention provides a method and system for lung cancer detection using high-throughput sequencing technology. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, a method for detecting lung cancer using high-throughput sequencing technology is provided.

[0007] A method for detecting lung cancer using high-throughput sequencing technology, specifically comprising:

[0008] S1 uses high-throughput sequencing technology to determine the sequencing results of the patient's lung cancer markers, and if it is determined that the sequencing results of the patient are abnormal based on the distribution data of the patient's lung cancer markers and the diagnostic matching data of different types of lung cancer markers, proceed to the next step;

[0009] S2, based on the analysis results of the detection data, determining the false detection data of the lung cancer marker in the detection depth corresponding to the high-throughput sequencing and the PCR amplification process, and combining the distribution data of the lung cancer marker and other types of lung cancer markers in different patients to determine the credibility coefficient of the lung cancer marker and the credibility marker;

[0010] S3: determining the similarity between the distribution data of the patient's credible markers and markers of different historically diagnosed patients, and determining the distribution similarity coefficients of the patient and different historically diagnosed patients and reference diagnosed patients in combination with the credibility coefficients of different credible markers;

[0011] S4 outputs the detection result of the lung cancer of the patient based on the distribution data of misdiagnosed patients among the reference diagnosed patients in different similarity coefficient intervals.

[0012] The beneficial effects of the present invention are:

[0013] Based on the distribution data of the patient's lung cancer markers and the diagnostic matching data of different types of lung cancer markers, it is determined whether the patient's sequencing results are abnormal, thereby achieving an accurate assessment of whether the patient's sequencing results are abnormal from the perspective of the distribution quantity of lung cancer markers and the accuracy of different lung cancer markers in lung cancer diagnosis, achieving differentiated analysis and processing of sequencing results of different patients, and also improving the accuracy of the patient's lung cancer detection analysis results.

[0014] Based on the distribution data of misdiagnosed patients among reference diagnosed patients within different similarity coefficient intervals, the patient's lung cancer test results are output, fully considering the distribution of misdiagnosed patients among different reference diagnosed patients, while also achieving comprehensive consideration of the similarity coefficients of different reference diagnosed patients, and achieving accurate assessment of the misdiagnosis rate of the patient's lung cancer test results, avoiding the technical problem of inaccurate lung cancer diagnosis results caused by single consideration of sequencing data.

[0015] A further technical solution is that the distribution data of the patient's lung cancer marker is determined according to the distribution position of the gene fragment corresponding to the patient's lung cancer marker.

[0016] A further technical solution is that the diagnosis matching data of the lung cancer marker is determined according to the distribution data of misdiagnosed patients among the historically diagnosed patients corresponding to the lung cancer marker.

[0017] A further technical solution is to determine whether the sequencing result of the patient is abnormal, specifically including:

[0018] Based on the distribution data of the lung cancer markers of the patient, determining the lung cancer markers of the patient and using them as patient matching markers;

[0019] Determine the distribution data of misdiagnosed patients among historically diagnosed patients corresponding to the different patient matching markers according to the diagnostic matching data of different patient matching markers, and determine the diagnostic matching coefficients of the different patient matching markers through the distribution data of the misdiagnosed patients;

[0020] The diagnostic matching markers of the patient are determined by the diagnostic matching coefficients of different patient matching markers, and the number of diagnostic matching markers is used to determine whether the sequencing result of the patient is abnormal.

[0021] A further technical solution is that the diagnosis matching coefficient is determined according to the distribution ratio of misdiagnosed patients.

[0022] A further technical solution is that the patient's diagnostic matching marker is a patient matching marker having a diagnostic matching coefficient greater than a preset matching coefficient.

[0023] A further technical solution is to output the detection result of the patient's lung cancer, specifically including:

[0024] Determine the distribution ratio of misdiagnosed patients in different similarity coefficient intervals based on the distribution data of misdiagnosed patients among reference diagnosed patients in different similarity coefficient intervals;

[0025] Determine the corresponding preset correction factor based on the number of reference diagnosed patients in different similarity coefficient intervals, and determine the weight coefficient of different similarity coefficient intervals by multiplying the preset weight coefficient corresponding to different similarity coefficient intervals by the preset correction factor;

[0026] The misdiagnosis rate of lung cancer diagnosis of the patient is determined according to the weight coefficients of different similarity coefficient intervals and the distribution ratio of misdiagnosed patients, and the lung cancer diagnosis misdiagnosis rate is used to output the detection result of the patient's lung cancer.

[0027] A further technical solution is to use the misdiagnosis rate of lung cancer diagnosis to output the detection result of the patient's lung cancer, which specifically includes:

[0028] When the misdiagnosis rate of lung cancer diagnosis is less than a preset misdiagnosis rate, determining that the lung cancer detection result of the patient is the presence of lung cancer;

[0029] When the misdiagnosis rate of lung cancer diagnosis is not less than a preset misdiagnosis rate, it is determined that the detection result of the patient's lung cancer is that lung cancer is not present.

[0030] In a second aspect, the present invention provides a computer system, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, the above-mentioned lung cancer detection method using high-throughput sequencing technology is executed.

[0031] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0032] 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

[0033] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0034] Figure 1 A flow chart of a method for detecting lung cancer using high-throughput sequencing technology.

[0035] Figure 2 is a flow chart of a method for determining that a patient's sequencing result has an abnormality.

[0036] Figure 3 It is a flow chart of the method for determining the reliability coefficient of lung cancer markers.

[0037] Figure 4 is a flow chart with reference to a method of diagnosing a patient's condition.

[0038] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0040] In addition to being affected by the patient's own gene mutations, the results of genetic testing are also related to PCR amplification, detection depth, etc. Therefore, it is necessary to comprehensively consider the influence of multiple factors to determine the results of lung cancer testing.

[0041] The patient's lung cancer markers are used as patient matching markers. The diagnostic matching coefficients of different patient matching markers are determined according to the proportion of misdiagnosed patients in historically diagnosed patients corresponding to different patient matching markers. When the sum of the diagnostic matching coefficients of different patient matching markers is less than 0.7, it is determined that the patient's sequencing results are abnormal.

[0042] The false detection ratio corresponding to the lung cancer marker is determined based on the detection depth corresponding to the high-throughput sequencing and the false detection data of the lung cancer marker in the PCR amplification process. The credibility coefficient of the lung cancer marker is determined using the false detection ratio. When the false detection ratio is 0.1, the credibility coefficient of the lung cancer marker is determined to be 0.9, and the lung cancer marker with a credibility coefficient greater than 0.95 is used as a credible marker.

[0043] The credibility coefficients of similar lung cancer markers were normalized and summed to determine the distribution similarity coefficient between the patient and patients with different historical diagnoses. The historically diagnosed patients with a distribution similarity coefficient greater than 0.7 were used as reference diagnosis patients.

[0044] The misdiagnosis rate of lung cancer diagnosis is determined by using the proportion of misdiagnoses in reference diagnosis patients. When the misdiagnosis rate of lung cancer diagnosis is less than the preset misdiagnosis rate, the lung cancer detection result of the patient is determined to be the presence of lung cancer. When the misdiagnosis rate of lung cancer diagnosis is not less than the preset misdiagnosis rate, the lung cancer detection result of the patient is determined to be the absence of lung cancer.

[0045] Embodiment 1 To solve the above problem, according to one aspect of the present invention, Figure 1 As shown, a method for detecting lung cancer using high-throughput sequencing technology is provided, which specifically includes:

[0046] S1 uses high-throughput sequencing technology to determine the sequencing results of the patient's lung cancer markers, and if it is determined that the sequencing results of the patient are abnormal based on the distribution data of the patient's lung cancer markers and the diagnostic matching data of different types of lung cancer markers, proceed to the next step;

[0047] S2, based on the analysis results of the detection data, determining the false detection data of the lung cancer marker in the detection depth corresponding to the high-throughput sequencing and the PCR amplification process, and combining the distribution data of the lung cancer marker and other types of lung cancer markers in different patients to determine the credibility coefficient of the lung cancer marker and the credibility marker;

[0048] S3: determining the similarity between the distribution data of the patient's credible markers and markers of different historically diagnosed patients, and determining the distribution similarity coefficients of the patient and different historically diagnosed patients and reference diagnosed patients in combination with the credibility coefficients of different credible markers;

[0049] S4 outputs the detection result of the lung cancer of the patient based on the distribution data of misdiagnosed patients among the reference diagnosed patients in different similarity coefficient intervals.

[0050] Furthermore, the distribution data of the patient's lung cancer marker is determined according to the distribution position of the gene fragment corresponding to the patient's lung cancer marker.

[0051] It should be noted that the diagnosis matching data of the lung cancer marker is determined based on the distribution data of misdiagnosed patients among the historically diagnosed patients corresponding to the lung cancer marker.

[0052] It is understandable that if Figure 2 As shown, it is determined that the sequencing results of the patient are abnormal, specifically including:

[0053] Based on the distribution data of the lung cancer markers of the patient, determining the lung cancer markers of the patient and using them as patient matching markers;

[0054] Determine the distribution data of misdiagnosed patients among historically diagnosed patients corresponding to the different patient matching markers according to the diagnostic matching data of different patient matching markers, and determine the diagnostic matching coefficients of the different patient matching markers through the distribution data of the misdiagnosed patients;

[0055] The diagnostic matching markers of the patient are determined by the diagnostic matching coefficients of different patient matching markers, and the number of diagnostic matching markers is used to determine whether the sequencing result of the patient is abnormal.

[0056] Specifically, the diagnosis matching coefficient is determined according to the distribution ratio of misdiagnosed patients.

[0057] It should be noted that the patient's diagnostic matching marker is a patient matching marker whose diagnostic matching coefficient is greater than a preset matching coefficient.

[0058] It is understandable that when the number of diagnostic matching markers is greater than the preset number of markers, it is determined that the sequencing result of the patient is abnormal.

[0059] Further, when there is no abnormality in the sequencing result of the patient, the detection result of the lung cancer of the patient is determined to be the absence of lung cancer.

[0060] It should also be noted that the determination of abnormalities in the sequencing results of the patient specifically includes:

[0061] Based on the distribution data of the lung cancer markers of the patient, determining the lung cancer markers of the patient and using them as patient matching markers;

[0062] Determine, according to the diagnosis matching data of different patient matching markers, the distribution data of misdiagnosed patients among the historically diagnosed patients corresponding to the different patient matching markers, and determine the diagnosis matching marker in the patient matching marker by the number of misdiagnosed patients;

[0063] The number of diagnostic matching markers is used to determine whether the sequencing results of the patient are abnormal.

[0064] Specifically, determining that the sequencing result of the patient is abnormal includes:

[0065] S11: determining the lung cancer marker of the patient based on the distribution data of the lung cancer marker of the patient, and using the marker as a patient matching marker;

[0066] S12 determines distribution data of misdiagnosed patients among historically diagnosed patients corresponding to different patient matching markers according to the diagnosis matching data of different patient matching markers, and determines the diagnosis matching coefficients of different patient matching markers through the distribution data of misdiagnosed patients;

[0067] S13 determines the comprehensive matching coefficient of the patient through the diagnostic matching coefficients of different patient matching markers, and uses the comprehensive matching coefficient to determine whether the sequencing result of the patient is abnormal.

[0068] Optionally, before entering step S12, it is also necessary to determine whether the number of the patient's matching markers is greater than the preset number of matching markers. When the number of the patient's matching markers is greater than the preset number of matching markers, it is determined that there is an abnormality in the sequencing result of the patient. When the number of the patient's matching markers is not greater than the preset number of matching markers, proceed to step S12.

[0069] Optionally, the above step S12 includes steps S121-S124, specifically:

[0070] S121 determines the distribution data of misdiagnosed patients among historically diagnosed patients corresponding to different patient matching markers according to the diagnostic matching data of different patient matching markers. When there are patient matching markers whose distribution number of misdiagnosed patients accounts for less than a preset number, the process proceeds to step S122. When there are no patient matching markers whose distribution number of misdiagnosed patients accounts for less than a preset number, it is determined that there is no abnormality in the sequencing result of the patient.

[0071] S122: Patient matching markers whose distribution number of misdiagnosed patients accounts for less than the preset number are used as screening markers. When the number of historically diagnosed patients corresponding to the screening markers is greater than the preset number of patients, it is determined that the sequencing result of the patient is abnormal. When the number of historically diagnosed patients corresponding to the screening markers is not greater than the preset number of patients, the process proceeds to step S123.

[0072] S123 determines the data reliable markers in the screening markers according to the number of historically diagnosed patients corresponding to the screening markers. When the number of the data reliable markers meets the requirement, it is determined that the sequencing result of the patient is abnormal. When the number of the data reliable markers does not meet the requirement, the process proceeds to step S124.

[0073] S124 determines the diagnostic matching coefficients of different patient matching markers through the distribution data of misdiagnosed patients, and proceeds to step S13.

[0074] Optionally, the above step S13 includes steps S131-S134, specifically:

[0075] S131: When the diagnostic matching coefficients of different patient matching markers are all less than the preset matching coefficient threshold, the process proceeds to step S132; when there is a patient matching marker whose diagnostic matching coefficient is not less than the preset matching coefficient threshold, the process proceeds to step S133;

[0076] S132: when the number of the patient's markers is less than the preset marker number threshold, it is determined that there is no abnormality in the sequencing result of the patient; when the number of the patient's markers is not less than the preset marker number threshold, the process proceeds to step S134;

[0077] S133: taking the patient matching markers whose diagnostic matching coefficient is not less than the preset matching coefficient threshold as matching markers; when the number of the matching markers is greater than the preset matching marker number threshold, it is determined that the sequencing result of the patient is abnormal; when the number of the matching markers is not greater than the preset matching marker number threshold, proceeding to step S134;

[0078] S134 determines the comprehensive matching coefficient of the patient through the diagnostic matching coefficients of different patient matching markers, and uses the comprehensive matching coefficient to determine whether the sequencing result of the patient is abnormal.

[0079] Furthermore, the misdetection data of the lung cancer marker includes the number of patients misdetected with the lung cancer marker and the percentage of the number of patients misdetected.

[0080] Specifically, Figure 3 As shown, the method for determining the credibility coefficient of the lung cancer marker is:

[0081] Determining the false detection ratio corresponding to the lung cancer marker based on the detection depth corresponding to the high-throughput sequencing and the false detection data of the lung cancer marker during the PCR amplification process;

[0082] According to the distribution data of the lung cancer marker and other types of lung cancer markers in different patients, determine the patient in which the lung cancer marker and other types of lung cancer markers are simultaneously present, and use the patient as a matching patient, and determine the matching marker among the other types of lung cancer markers according to the proportion of the number of matching patients;

[0083] The credibility coefficient of the lung cancer marker is determined based on the proportion of the matching marker in the lung cancer marker of the patient and the false detection ratio.

[0084] Furthermore, the matching marker is a standard substance of other types of lung cancer whose number of matching patients accounts for a greater proportion than a preset number.

[0085] It should also be noted that the credibility coefficient of the lung cancer marker is determined according to the product of the proportion of the number of the matching marker in the lung cancer marker of the patient and the false positive rate.

[0086] It is understandable that the credibility coefficient of the lung cancer marker ranges from 0 to 1, wherein when the credibility coefficient of the lung cancer marker is greater than a preset credibility coefficient, the lung cancer marker is determined to be a credible marker.

[0087] In another embodiment, the method for determining the credibility coefficient of the lung cancer marker is:

[0088] Determine the number of accurately diagnosed patients corresponding to the lung cancer marker based on the detection depth corresponding to the high-throughput sequencing and the false detection data of the lung cancer marker during the PCR amplification process;

[0089] According to the distribution data of the lung cancer marker and other types of lung cancer markers in different patients, determine the patient in which the lung cancer marker and other types of lung cancer markers are simultaneously present, and use the patient as a matching patient, and determine the matching marker among the other types of lung cancer markers according to the proportion of the number of matching patients;

[0090] The credibility coefficient of the lung cancer marker is determined based on the number of accurately diagnosed patients corresponding to the lung cancer marker and the number of matching markers.

[0091] Further, the credibility coefficient of the lung cancer marker is determined based on the product of a preset credibility coefficient corresponding to the number of accurately diagnosed patients corresponding to the lung cancer marker and a preset credibility coefficient corresponding to the number of matching markers.

[0092] In one embodiment, the method for determining the credibility coefficient of the lung cancer marker is:

[0093] S21, determining the false detection ratio corresponding to the lung cancer marker based on the detection depth corresponding to the high-throughput sequencing and the false detection data of the lung cancer marker during the PCR amplification process, and determining the diagnostic matching coefficient of the lung cancer marker based on the number of falsely detected patients;

[0094] S22: determining, based on the distribution data of the lung cancer marker and other types of lung cancer markers in different patients, a patient in which the lung cancer marker and other types of lung cancer markers are simultaneously present, and taking the patient as a matching patient; determining matching markers among the other types of lung cancer markers according to the number ratio of matching patients; and determining a marker matching coefficient of the lung cancer marker based on the number of matching markers, the number of matching patients of different matching markers, and the number ratio;

[0095] S23 determines the credibility coefficient of the lung cancer marker based on the marker matching coefficient and the diagnosis matching coefficient of the matching marker.

[0096] Optionally, the above step S21 includes steps S211-S213, which are specifically:

[0097] S211 determines the number of misdetected patients corresponding to the lung cancer marker based on the detection depth corresponding to the high-throughput sequencing and the misdetected data of the lung cancer marker in the PCR amplification process; when the number of misdetected patients is greater than the preset number of patients, it is determined that the lung cancer marker is not a credible marker; when the number of misdetected patients is not greater than the preset number of patients and is within the preset number interval, the process proceeds to step S212; when it is not within the preset number interval, the process proceeds to step S213;

[0098] S212 determines the false positive rate corresponding to the lung cancer marker. When the false positive rate does not meet the requirement, it is determined that the lung cancer marker is not a reliable marker. When the false positive rate meets the requirement, the process proceeds to step S213.

[0099] S213 determines the diagnostic matching coefficient of the lung cancer marker based on the false detection ratio and the number of falsely detected patients corresponding to the lung cancer marker. When the diagnostic matching coefficient of the lung cancer marker is less than a preset matching coefficient threshold, it is determined that the lung cancer marker is not a credible marker. When the diagnostic matching coefficient of the lung cancer marker is not less than the preset matching coefficient threshold, the process proceeds to step S22.

[0100] Optionally, the above step S22 includes steps S221-S223, specifically:

[0101] S221: according to the distribution data of the lung cancer marker and other types of lung cancer markers in different patients, determine the patient in which the lung cancer marker and other types of lung cancer markers are simultaneously present, and use the patient as a matching patient; when there is no other type of lung cancer marker whose number of matching patients accounts for a greater proportion than a preset number of matching patients, determine that the lung cancer marker is not a credible marker; when there is another type of lung cancer marker whose number of matching patients accounts for a greater proportion than a preset number of matching patients, proceed to step S222;

[0102] S222: determining matching markers among the other types of lung cancer markers according to the proportion of the number of matching patients; when the number of matching markers is greater than a preset matching marker number threshold, proceeding to step S224; when the number of matching markers is not greater than the preset matching marker number threshold, proceeding to step S223;

[0103] S223 determines the basic matching coefficients of different matching markers according to the number of matching patients of different matching markers and the proportion of the number. When there is no matching marker with a basic matching coefficient within the preset matching coefficient interval, it is determined that the lung cancer marker is not a credible marker. When there is a matching marker with a basic matching coefficient within the preset matching coefficient interval, the process proceeds to step S224.

[0104] S224 determines the marker matching coefficient of the lung cancer marker based on the number of matching markers, the number of matching patients of different matching markers, and the proportion of the number. When the marker matching coefficient is less than a preset coefficient threshold, it is determined that the lung cancer marker is not a credible marker. When the marker matching coefficient is not less than the preset coefficient threshold, the process proceeds to step S23.

[0105] Specifically, Figure 4 As shown, the method for determining the reference diagnosis patient is:

[0106] Based on the similarity between the distribution data of the patient's credible markers and the markers of the historically diagnosed patients, determining the matching data of the patient's credible markers and using them as similar markers;

[0107] The distribution similarity coefficient between the patient and the historically diagnosed patient is determined according to the number of similar markers and the credibility coefficients of different similar markers, and the distribution similarity coefficient is used to determine whether the historically diagnosed patient is a reference diagnosed patient.

[0108] Furthermore, the distribution similarity coefficient between the patient and the historically diagnosed patient is determined based on the weighted sum of the credibility coefficients of different similar markers.

[0109] It should also be noted that when the distribution similarity coefficient of the historically diagnosed patient is greater than a preset similarity coefficient threshold, the historically diagnosed patient is determined to be a reference diagnosed patient.

[0110] Optionally, the method for determining the reference diagnosis patient is:

[0111] When it is determined that there is no matching credible marker between the patient and the historically diagnosed patient based on the similarity of the distribution data of the credible marker of the patient and the marker of the historically diagnosed patient:

[0112] It is determined that the historically diagnosed patient does not belong to the reference diagnosed patient;

[0113] When it is determined that the patient has a matching credible marker with the historically diagnosed patient:

[0114] The matched credible markers are regarded as similar markers. When the number of similar markers is less than the preset similar marker number threshold:

[0115] Obtaining credibility coefficients of different similar markers, and when an average value of the credibility coefficients of different similar markers is less than a preset credibility coefficient threshold, determining that the historically diagnosed patient does not belong to the reference diagnosed patient;

[0116] When the average value of the credibility coefficients of different similar markers is not less than the preset credibility coefficient threshold:

[0117] When the credibility coefficients of the similar markers are determined to be within a preset credibility coefficient interval using the credibility coefficients of different similar markers: it is determined that the historically diagnosed patient does not belong to the reference diagnosed patient;

[0118] When there are similar markers that are not within the preset confidence coefficient interval or the number of similar markers is not less than the preset similar marker number threshold:

[0119] The distribution similarity coefficient between the patient and the historically diagnosed patient is determined according to the number of similar markers and the credibility coefficients of different similar markers, and the distribution similarity coefficient is used to determine whether the historically diagnosed patient is a reference diagnosed patient.

[0120] Specifically, outputting the detection result of the patient's lung cancer includes:

[0121] Determine the distribution ratio of misdiagnosed patients in different similarity coefficient intervals based on the distribution data of misdiagnosed patients among reference diagnosed patients in different similarity coefficient intervals;

[0122] Determine the corresponding preset correction factor based on the number of reference diagnosed patients in different similarity coefficient intervals, and determine the weight coefficient of different similarity coefficient intervals by multiplying the preset weight coefficient corresponding to different similarity coefficient intervals by the preset correction factor;

[0123] The misdiagnosis rate of lung cancer diagnosis of the patient is determined according to the weight coefficients of different similarity coefficient intervals and the distribution ratio of misdiagnosed patients, and the lung cancer diagnosis misdiagnosis rate is used to output the detection result of the patient's lung cancer.

[0124] A further technical solution is to use the misdiagnosis rate of lung cancer diagnosis to output the detection result of the patient's lung cancer, which specifically includes:

[0125] When the misdiagnosis rate of lung cancer diagnosis is less than a preset misdiagnosis rate, determining that the lung cancer detection result of the patient is the presence of lung cancer;

[0126] When the misdiagnosis rate of lung cancer diagnosis is not less than a preset misdiagnosis rate, it is determined that the detection result of the patient's lung cancer is that lung cancer is not present.

[0127] Embodiment 2 In the second aspect, as Figure 5 As shown, the present invention provides a computer system, comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, the above-mentioned lung cancer detection method using high-throughput sequencing technology is executed.

[0128] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0129] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0130] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A method for detecting lung cancer using high-throughput sequencing technology, characterized in that: Specifically include: Determining the sequencing results of the patient's lung cancer markers using high-throughput sequencing technology, and if it is determined that the sequencing results of the patient are abnormal based on the distribution data of the patient's lung cancer markers and the diagnostic matching data of different types of lung cancer markers, proceeding to the next step; Determine the false detection data of the lung cancer marker in the detection depth corresponding to the high-throughput sequencing and the PCR amplification process based on the analysis results of the detection data, and determine the credibility coefficient and credible marker of the lung cancer marker using the false detection data of the lung cancer marker and the distribution data of the lung cancer marker and other types of lung cancer markers in different patients; Determine the similarity of the distribution data of the patient's credible markers and markers of different historically diagnosed patients, and determine the distribution similarity coefficients of the patient and different historically diagnosed patients and reference diagnosed patients in combination with the credibility coefficients of different credible markers; Outputting the detection result of lung cancer of the patient based on the distribution data of misdiagnosed patients among the reference diagnosed patients in different similarity coefficient intervals; The diagnosis matching data of the lung cancer marker is determined according to the distribution data of misdiagnosed patients among the historically diagnosed patients corresponding to the lung cancer marker; The method for determining the credibility coefficient of the lung cancer marker is: Determining the false detection ratio corresponding to the lung cancer marker based on the detection depth corresponding to the high-throughput sequencing and the false detection data of the lung cancer marker during the PCR amplification process; According to the distribution data of the lung cancer marker and other types of lung cancer markers in different patients, determine the patient in which the lung cancer marker and other types of lung cancer markers are simultaneously present, and use the patient as a matching patient, and determine the matching marker among the other types of lung cancer markers according to the proportion of the number of matching patients; The credibility coefficient of the lung cancer marker is determined based on the proportion of the matching marker in the lung cancer marker of the patient and the false detection ratio.

2. The method for detecting lung cancer using high-throughput sequencing technology according to claim 1, wherein: The distribution data of the patient's lung cancer marker is determined according to the distribution position of the gene fragment corresponding to the patient's lung cancer marker.

3. The method for detecting lung cancer using high-throughput sequencing technology according to claim 1, wherein: Determining that the sequencing results of the patient are abnormal, specifically including: Based on the distribution data of the lung cancer markers of the patient, determining the lung cancer markers of the patient and using them as patient matching markers; Determine the distribution data of misdiagnosed patients among historically diagnosed patients corresponding to the different patient matching markers according to the diagnostic matching data of different patient matching markers, and determine the diagnostic matching coefficients of the different patient matching markers through the distribution data of the misdiagnosed patients; The diagnostic matching markers of the patient are determined by the diagnostic matching coefficients of different patient matching markers, and the number of diagnostic matching markers is used to determine whether the sequencing result of the patient is abnormal.

4. The method for detecting lung cancer using high-throughput sequencing technology according to claim 3, characterized in that: The diagnosis matching coefficient is determined according to the distribution ratio of misdiagnosed patients.

5. The method for detecting lung cancer using high-throughput sequencing technology according to claim 1, wherein: The patient's diagnostic matching marker is a patient matching marker whose diagnostic matching coefficient is greater than a preset matching coefficient.

6. The method for detecting lung cancer using high-throughput sequencing technology according to claim 1, wherein: The method for determining the reference diagnosis patient is: Based on the similarity between the distribution data of the patient's credible markers and the markers of the historically diagnosed patients, determining the matching data of the patient's credible markers and using them as similar markers; The distribution similarity coefficient between the patient and the historically diagnosed patient is determined according to the number of similar markers and the credibility coefficients of different similar markers, and the distribution similarity coefficient is used to determine whether the historically diagnosed patient is a reference diagnosed patient.

7. The method for detecting lung cancer using high-throughput sequencing technology according to claim 6, characterized in that: The distribution similarity coefficient between the patient and the historically diagnosed patient is determined based on the weighted sum of the credibility coefficients of different similar markers.

8. The method for detecting lung cancer using high-throughput sequencing technology according to claim 6, wherein: When the distribution similarity coefficient of the historically diagnosed patient is greater than a preset similarity coefficient threshold, the historically diagnosed patient is determined to be a reference diagnosed patient.

9. A computer system comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, a lung cancer detection method using high-throughput sequencing technology as described in any one of claims 1-8 is executed.

Images