Construction method of lung nodule benign and malignant differential diagnosis model based on single cell immunomapping

Abstract

The application provides a method for constructing a lung nodule benign and malignant differential diagnosis model based on single-cell immunomapping. The method uses peripheral blood samples to obtain PBMCs, and performs mass spectrometry flow analysis on the PBMCs to obtain a mass spectrometry flow analysis data set; a PARC clustering algorithm is used to divide cells into different phenotypes according to marker expression, and the expression proportion of each cell subgroup is used as a modeling feature to obtain a lung nodule benign and malignant differential diagnosis model, realizing the screening and early diagnosis of lung cancer. The technology has the characteristics of non-invasiveness, high sensitivity and high specificity, improves the diagnostic accuracy of lung cancer screening, and provides patients with earlier treatment opportunities and more suitable surgical methods.

Description

Methods for constructing a model for differential diagnosis of benign and malignant pulmonary nodules based on single-cell immunographics Technical Field

[0001] This invention belongs to the medical field, and more specifically relates to a method for establishing a model for differentiating between benign and malignant pulmonary nodules based on single-cell immunochromatography using mass cytometry. Background Technology

[0002] Lung cancer is one of the leading causes of cancer-related deaths worldwide. The vast majority of patients (48%) already have distant metastases at initial diagnosis, and the 5-year relative survival rate for these patients is only around 8%. In contrast, the 5-year survival rate for patients diagnosed with early-stage lung cancer can reach 62%, but the detection rate is only around 20%. For stage I cancer, the 5-year survival rate increases significantly, from 68% to 92%. Undoubtedly, increasing the detection rate of lung cancer at curable stages (stages 0, I, and II) is the most effective way to reduce lung cancer mortality. Improving the early diagnosis rate of lung cancer is crucial for reducing lung cancer mortality and improving prognosis.

[0003] However, due to a lack of clinical symptoms and sensitive technology, it is difficult to detect lung cancer in these early stages. Randomized controlled trials, including the US National Lung Screening Trial (NLST) and the Netherlands-Belgium Lung Screening Trial (NELSON), have shown that low-dose CT (LDCT) screening can significantly reduce lung cancer mortality. However, there are still uncertainties regarding the effectiveness and cost-effectiveness of LDCT in improving clinical efficacy, especially in the diagnosis of subsolid nodules, which is the most difficult and challenging. LDCT screening also suffers from a high rate of false positives: most nodules detected by LDCT in high-risk individuals are benign. A large-scale NLST study from the United States showed that although 24.2% of those who underwent LDCT were found to have lung nodules, a staggering 96.4% of positive nodules were diagnosed as benign (false positives) after follow-up. Other studies have shown that the proportion of benign lung nodules after surgical resection is as high as 20%, and after biopsy, it is 38%. Multiple studies have confirmed that the average nodule detection rate of LDCT screening is approximately 20%, while >90% of nodules are benign. An excessively high false-positive rate can lead to overdiagnosis, overtreatment, waste of medical resources, and increased anxiety among those being examined.

[0004] The Mayo Clinic's clinical lung cancer prediction model, developed in 1997 by the Mayo Clinic for patients with nodules ranging from 4 to 30 mm, was used to determine the nature of nodules. Other models, such as the Veterans Association (VA) model and the BROCK model, have been used to determine the nature of nodules. Their area under the curve (AUC) is 0.65-0.83, indicating low accuracy. Moreover, the Mayo Clinic's clinical lung cancer prediction model is based on Western patients and may not be applicable to Chinese patients, thus limiting its practical application.

[0005] Therefore, effectively differentiating and triaging pulmonary nodules, rapidly determining their benign or malignant nature, and removing malignant nodules as early as possible, while avoiding unnecessary overtreatment and reducing the proportion of benign nodules surgically removed, is crucial for the diagnosis and treatment of pulmonary nodules. There is a significant unmet clinical need for highly sensitive and specific methods to accurately identify malignant pulmonary nodules.

[0006] On the other hand, the World Health Organization (WHO) Classification of Lung Cancers (5th Edition, 2021) classifies atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS) as glandular precursor lesions, not within the scope of lung adenocarcinoma, and classifies minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IA) as two types of lung cancer with different degrees of invasion. The Lung Cancer Research Association / American Thoracic Society / European Respiratory Society Multidisciplinary Classification of Lung Adenocarcinoma indicates that MIA often does not spread to regional lymph nodes or metastasize, and its postoperative disease-free survival rate is almost 100%. Therefore, sublobar resection can be chosen for MIA without systematic lymph node dissection, while the surgical approach for IA patients needs to be determined based on clinical factors. Therefore, a method is needed to effectively differentiate between MIA and IA preoperatively to formulate surgical plans in advance.

[0007] The human immune system is closely related to the occurrence and development of tumors, and the tumor immune microenvironment (TME) is constantly changing during tumor development. Immune changes in tumors are not limited to the tumor itself but are often accompanied by systemic immune dysregulation. These findings highlight the complex interaction between tumors and the peripheral immune system. Studies show that lung tumors contain various types of infiltrating immune cells that play a crucial role in tumor development and progression. Macrophages and T cell populations have potential interactions within the tumor immune microenvironment, and lung tumors are also rich in other myeloid components, including neutrophils, non-classical monocytes, and intermediate monocytes. Furthermore, studies have shown that the presence of B cells is associated with protective immunity in lung cancer patients; other clinical studies have demonstrated that high-density tumor-infiltrating T cells are associated with increased median survival in cancer patients. Therefore, comprehensive and detailed monitoring of the human peripheral immune status may greatly aid in the differentiation between benign and malignant lung nodules.

[0008] In recent years, mass cytometry has combined traditional flow cytometry with mass spectrometry detection, using metal isotope tags instead of fluorescent tags and quantifying the tags using mass spectrometry. This allows for the simultaneous detection of over 40 target proteins at the single-cell level, with no interference between channels and no need for complex compensation calculations. This significantly enhances the ability to assess complex cellular systems and processes, making it a multi-parameter, high-throughput single-cell protein detection technology platform. By detecting multiple label combinations, CyTOF technology can distinguish various cell subpopulations, construct cellular atlases of healthy or diseased states, comprehensively analyze intracellular signal transduction networks, and provide high-dimensional analysis of the human body's basic immune status, obtaining comprehensive information on the composition, phenotype, and function of immune cells. Summary of the Invention

[0009] In view of this, the purpose of this invention is to provide a method for constructing a differential diagnostic model for benign and malignant pulmonary nodules based on single-cell immunoassay, specifically a method for establishing a differential diagnostic model for benign and malignant pulmonary nodules based on single-cell immunoassay using mass cytometry. Peripheral blood mononuclear cells (PBMCs) are obtained by processing peripheral blood samples using the Ficoll separation method (Ficoll density gradient centrifugation), and mass cytometry analysis is performed on the PBMCs to obtain a mass cytometry analysis dataset. The PARC clustering algorithm is used to classify cells into different phenotypes based on marker expression, and the expression ratio of each cell subgroup is used as a modeling feature to obtain a differential diagnostic model for benign and malignant pulmonary nodules.

[0010] To achieve the above objectives, the present invention adopts the following technical solution:

[0011] 1. Peripheral blood samples were processed using the Ficoll separation method to obtain PBMCs. The PBMCs were resuspended in 5 ml of pre-chilled flow cytometry-activated cell sorting (FACS) buffer (1×PBS + 0.5% BSA), then centrifuged at 400×g for 5 min at 4°C, the supernatant was discarded, and the cell pellet was resuspended in the buffer. PBMC cell counting and quality assessment were performed before CyTOF (Cystic Cytometry) analysis to ensure a count greater than 3×10⁻⁶. 6 The survival rate is greater than 85%.

[0012] 2. Forty metal-coupled antibodies were selected as markers for cell labeling. PBMCs were washed with PBS buffer, stained with 0.5 mM cisplatin, and Fc receptor binding was blocked for 30 min. Unbound antibodies were removed by centrifugation. PBMCs were then fixed in 200 µL of insertion solution overnight. Cells were washed and resuspended in distilled water, added to 20% EQ beads, and further analyzed by mass cytometry. The 40 metal-coupled antibody markers include: CD45, CD3, CD56, TCRγ / δ, CD196 (CCR6), CD14, IgD, CD123 (IL-3Rα), CD85j (ILT2), CD19, CD25 (IL-2Rα), CD274 (PD-L1), CD278 (ICOS), CD39, CD27, CD24, CD45RA, CD86, CD28, CD197 (CCR7), CD11c, CD33, CD152 (CTLA-4), CD161, CD185 (CXCR5), CD66b, CD183 (CXCR3), CD94, CD57, CD45RO, CD127 (IL-7Rα), CD279 (PD-1), CD38, and CD194. (CCR4), CD20, CD16, HLA-DR, CD4, CD8a, CD11b.

[0013] 3. The PARC clustering algorithm is used to divide cells into different phenotypes based on marker expression. The expression ratio of each cell subgroup is used as a modeling feature, and the random forest algorithm and 10-fold cross-validation are used to screen features.

[0014] 4. A model for differentiating between benign and malignant pulmonary nodules was obtained by modeling using the random forest method.

[0015] Optionally, step 3 also includes screening 34 immune cell subsets and markers as modeling features. The features of the 19-cell differential diagnostic model for benign and malignant pulmonary nodules include: CD33-CD14-CD3+CD4+CD28+, CD33-CD14-CD3+CD4+CD274+, CD33-CD14-CD3+CD4+CD197+CD45RA-, CD33-CD14-CD3+CD4+HLA_DR+CD38+, CD33-CD14-CD3+CD4+CXCR5-CD183-CCR6-, CD33-CD14-CD3+CD4+CD25+CD127-CD161-CD45RA+, CD 33-CD14-CD3+CD8+CD197+-CD45RA+, CD33-CD14-CD3-CD19+CD24+CD38+, CD33-CD14-CD3-CD20-CD38+CD27+, CD33-CD14-CD3-CD 56+CD16+CD94+, CD33-CD14-CD3-CD56+CD16+CD161+, CD3-CD19-CD56-CD14-CD123+CD11c+, CD33-CD14-CD3-CD56+CD16-, CD86, C D11c, CD183, CD94, CD4, CD11b; 15 features of the lung cancer invasion assessment model include: CD33-CD14-CD3+CD8+CD85j+, CD33-CD14-CD3+CD8+CD161-, CD33-CD14-CD3+CD4+, CD33-CD14-CD3+CD4+CD197-CD45RA+, CD33-CD14-CD3+CD4+HLA_DR+CD38+, CD33-CD14-CD3+CD4+HLA_DR+CD38-, CD33-C D14-CD3+CD8+, CD33-CD14-CD3+CXCR5+, CD33-CD14-CD3+CD8+CD197+CD45RA-, CD33-CD14-CD3-CD19+CD24+CD38+, CD33-CD14-C D3-CD56+CD16+, CD33-CD14-CD3-CD56+CD16+CD57+, CD33-CD14-CD3-CD56+CD16+HLA_DR+, CD3-CD19-CD56-CD14-HLA_DR-, CD56.

[0016] Optionally, step 3 also includes using training and validation sets, which involves dividing the samples into training and validation sets according to the order of their inclusion in the group.

[0017] Optionally, step 2 may also include a combination of 40 antibody markers.

[0018] Optionally, when selecting samples for enrollment in step 1, random enrollment is used, covering samples with different nodule sizes (e.g., ≤10mm, 11-20mm, 21-30mm, etc.), different types of nodules (e.g., solid nodules, partially solid nodules, pure ground-glass opacity nodules), and different degrees of adenocarcinoma invasion (e.g., atypical adenomatous hyperplasia AAH, carcinoma in situ AIS, minimally invasive adenocarcinoma MIA, invasive adenocarcinoma IA, etc.).

[0019] As can be seen from the above technical solution, this invention discloses a method for establishing a model for differentiating benign and malignant pulmonary nodules based on single-cell immunoassay. It demonstrates good detection efficacy in differentiating between lung cancer (pathologically confirmed CA) and non-cancerous samples (including imaging-confirmed Non-CA and pathologically confirmed Non-CA), with AUCs of 0.95 and 0.96 on the training and validation sets, respectively. This is superior to existing clinically used models: the Mayo model (AUCs of 0.75 and 0.70 on the training and validation sets, respectively), the Veterans Association (VA) model (AUCs of 0.73 and 0.65 on the training and validation sets, respectively), and the BROCK model (AUCs of 0.84 and 0.85 on the training and validation sets, respectively). Furthermore, it also performs exceptionally well in the most difficult-to-differentiate pathological non-cancerous and lung cancer groups, with AUCs of 0.92 and 0.90 on the training and validation sets, respectively, significantly superior to existing clinically used models: the Mayo model (AUCs of 0.69 and 0.61 on the training and validation sets, respectively). The (VA) model (AUCs of 0.68 and 0.61 for training and validation sets, respectively) and the BROCK model (AUCs of 0.72 and 0.65 for training and validation sets, respectively).

[0020] Meanwhile, the model scheme established in this invention can effectively distinguish between MIA and IA preoperatively, with AUCs of 0.97 and 0.93 on the training and validation sets, respectively. This invention's model improves the sensitivity and specificity of lung cancer screening, reduces the risk of missed and misdiagnosed cases, and can be used for auxiliary diagnosis and screening of lung cancer.

[0021] This invention provides a lung cancer screening technology based on cellular immunoprofiling analysis using mass cytometry. By detecting the expression profile of tumor-associated immune cells in the patient's peripheral blood, classifying peripheral blood sample data, and combining it with artificial intelligence algorithms to construct a learning model, the peripheral blood sample data is input into this model to obtain a risk score for lung cancer, thus achieving lung cancer screening and early diagnosis. This technology is non-invasive and features high sensitivity and specificity, enabling rapid and accurate detection of the expression profile of lung cancer-associated immune cells in peripheral blood, improving the diagnostic accuracy of lung cancer screening, and providing patients with earlier treatment opportunities and optimal treatment methods.

[0022] The advantages of this invention are: (1) it improves the sensitivity and specificity of lung cancer screening and reduces the risk of missed diagnosis and misdiagnosis; (2) it avoids invasive diagnostic procedures and reduces clinical risks; (3) it enables early diagnosis of lung cancer and provides patients with earlier treatment opportunities; (4) it further classifies the degree of lung cancer invasion and provides patients with more suitable surgical methods; (5) it adopts CyTOF technology, which has the characteristics of high throughput, high resolution and high sensitivity, and can quickly and accurately detect the expression profile of lung cancer-related immune cells; (6) it combines artificial intelligence algorithms to improve the accuracy and reliability of lung cancer screening. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0024] Figure 1 is a flowchart of the lung cancer screening based on CyTOF cell immune atlas according to the present invention.

[0025] Figure 2 is a box plot of risk scores for lung cancer and non-cancer samples in the training and validation sets of the lung cancer diagnostic model of this invention.

[0026] Figure 3 is the AUC diagram of the training set and validation set of the lung cancer diagnostic model of the present invention.

[0027] Figure 4 is a box plot of the risk score of the training and validation sets of the lung cancer diagnosis model of the present invention in the most difficult-to-distinguish pathological non-cancer group and lung cancer group.

[0028] Figure 5 shows the AUC plots of the training and validation sets of the lung cancer diagnostic model of this invention in the most difficult-to-distinguish pathological non-cancer group and lung cancer group.

[0029] Figure 6 is a box plot of risk score for lung cancer and non-cancer samples in the training and validation sets of the surgical method decision model of the present invention.

[0030] Figure 7 is the AUC diagram of the training set and validation set of the surgical method decision model of the present invention. Detailed Implementation

[0031] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] Example 1: A method for establishing a model for differentiating benign and malignant pulmonary nodules based on single-cell immunochromatography using mass cytometry.

[0033] The specific steps are as follows:

[0034] 1. Peripheral blood samples (5 ml / sample) were collected and transferred to the laboratory for further processing within 12 hours at room temperature or within 48 hours at 4°C. Subjects should meet the following requirements: over 18 years of age; a confirmed diagnosis (patients with planned surgical resection of pulmonary nodules confirmed by histopathology, or nodule with no change after 3 years of follow-up, or nodule diameter ≤4 mm); and signed informed consent. Exclusion criteria included: history of cancer-related treatment; acute infection phase; blood transfusion within the past 6 months; use of medications affecting peripheral blood components within the past 2 weeks; locally recurrent tumors; decompensated organ dysfunction; immunodeficiency syndrome; hematologic precancerous disorders; receiving immunosuppressive therapy; and coagulation disorders. A total of 1032 peripheral blood samples were collected in this project. As shown in Figure 1, the collected peripheral blood samples were processed as follows after being transferred to the laboratory.

[0035] 2. Sample pretreatment, including: Peripheral blood mononuclear cells (PBMCs) were isolated from the blood using Ficoll-Paque density gradient centrifugation. They were resuspended in 5 ml of pre-chilled FACS buffer (1×PBS + 0.5% BSA), then centrifuged at 400×g for 5 min at 4°C, the supernatant was discarded, and the cell pellet buffer was resuspended. PBMC cell counting and quality assessment were performed before CyTOF assay to ensure a count greater than 3×10⁻⁶. 6 The survival rate is greater than 85%.

[0036] 3. CyTOF staining and data analysis, including: selecting 40 metal-coupled antibodies as markers for cell labeling; washing PBMCs with PBS buffer, then staining with 0.5 mM cisplatin, blocking cell-antibody binding with Fc receptors for 30 min, and removing unbound antibodies by centrifugation. PBMCs were then fixed overnight in 200 µL of insertion solution. Cells were washed and resuspended in distilled water, added to 20% EQ beads, and further analyzed by flow cytometry. FCS files were normalized using bead normalization. Each sample data was debarcoded using a bi-state filtering scheme with a unique mass marker barcode. FlowJo software was used to exclude debris, dead cells, and double cells, leaving only live, single immune cells.

[0037] 4. Feature Selection: Samples were divided into training and validation sets according to their enrollment time. The training set included 178 lung cancer samples and 218 non-cancer control samples. First, we evaluated the negative and positive expression of markers on each cell in the training set. Then, based on the expression profiles of these markers, a random forest algorithm and 10-fold cross-validation were used to select characteristic cell subpopulations. Features with an importance level greater than 0.01 were recorded in each successful random forest model construction. If a feature occurred more than 350 times in 1000 cross-validations, it was counted. Finally, 19 characteristic cell subpopulations were selected for model construction.

[0038] 5. Model Building: Using 178 lung cancer samples and 218 non-cancer control samples from the training set, and employing the features selected using the above method, a lung cancer diagnostic model was established using the random forest method. The model calculates a risk score for each participant, which is the average probability of a sample being positive as determined by each decision tree in the random forest model, ranging from 0 to 1.

[0039] Example 2: Validation method for a model for differentiating benign and malignant pulmonary nodules based on single-cell immunochromatography using mass cytometry.

[0040] 1. Using the scheme provided in Example 1, CyTOF staining and data analysis were performed on 251 non-cancer samples and 283 lung cancer samples from the validation set that were not trained.

[0041] 2. New peripheral blood samples are input into a lung cancer diagnostic model constructed using 19 cell subpopulations to predict and evaluate the blood samples. Based on the prediction results of the lung cancer diagnostic model, it is determined whether the sample belongs to a lung cancer patient.

[0042] Example 3: Establishment and validation of a lung cancer invasion degree judgment model based on single-cell immunochromatography using mass cytometry.

[0043] 1. Using the scheme provided in Example 1, CyTOF staining and data analysis were performed on 113 lung nodule samples pathologically diagnosed as MIA and 105 lung nodule samples pathologically diagnosed as IA from the training set.

[0044] 2. Using the scheme provided in Example 1, a random forest algorithm and 10-fold cross-validation were employed to select characteristic cell subpopulations. A total of 15 cell subpopulations were selected as modeling features to construct a new model for determining the degree of infiltration of malignant pulmonary nodules.

[0045] 3. Using the scheme provided in Example 2, the model was validated using 111 lung nodule samples pathologically diagnosed as MIA and 106 lung nodule samples pathologically diagnosed as IA from the validation set.

[0046] Obviously, the above embodiments of the present invention are merely examples to illustrate the present invention more clearly, and are not intended to limit the implementation of the present invention. For those skilled in the art, other variations or modifications can be made based on the above description. It is impossible to exhaustively list all implementation methods here. Any obvious variations or modifications derived from the technical solutions of the present invention are still within the protection scope of the present invention.

[0047] As shown in Figures 2 and 3, the lung nodule differential diagnosis model disclosed in this invention has good detection efficiency in differentiating between lung cancer (pathologically confirmed CA) and non-cancer samples (including imaging-confirmed Non-CA and pathologically confirmed Non-CA). The AUC of the training set and validation set can reach 0.95 and 0.96, respectively, which is better than the existing clinically used models: Mayo model (AUC of 0.75 and 0.70, respectively), Veterans Association (VA) model (AUC of 0.73 and 0.65, respectively), and BROCK model (AUC of 0.84 and 0.85, respectively).

[0048] As shown in Figures 4 and 5, the lung nodule benign and malignant differential diagnosis model disclosed in this invention has excellent performance in the most difficult pathological non-cancer group and lung cancer group (AUC of 0.92 and 0.90 for training set and validation set, respectively), which is better than the existing clinical models: Mayo model, Veterans Association (VA) model and BROCK model.

[0049] Referring to Figures 6 and 7, the model scheme established in this paper can effectively distinguish between MIA and IA before surgery, with AUCs of 0.97 and 0.93 on the training and validation sets, respectively.

[0050] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. The steps disclosed in the embodiments are described simply because they correspond to the methods disclosed in the embodiments; relevant details can be found in the method section.

[0051] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for constructing a differential diagnostic model for benign and malignant pulmonary nodules based on single-cell immunoassay, characterized in that, Includes the following steps: Peripheral blood mononuclear cells were obtained by processing peripheral blood samples using the Ficoll separation method, and mass spectrometry flow cytometry analysis was performed on the peripheral blood mononuclear cells to obtain a mass spectrometry flow cytometry analysis dataset. The PARC clustering algorithm was used to classify cells into different phenotypes based on label expression, and the expression ratio of each cell subgroup was used as a modeling feature to obtain a differential diagnostic model for benign and malignant lung nodules. Specifically, this was achieved through the following steps: (1) Peripheral blood mononuclear cells were obtained by processing peripheral blood samples using the Ficoll separation method, and they were suspended in 5 ml of pre-cooled flow cytometry cell sorting buffer. Then, they were centrifuged at 400×g for 5 min at 4℃, the supernatant was discarded, and the cell precipitate buffer was resuspended. Before detection by CyTOF mass spectrometry flow cytometry, the cell count and quality assessment of peripheral blood mononuclear cells were performed to ensure that the count was greater than 3×10. 6 (1) The survival rate was greater than 85%; (2) 40 metal-coupled antibodies were selected as markers for cells; PBMCs were washed with PBS buffer, stained with 0.5 mM cisplatin, and their binding to the antibody was blocked by Fc receptor for 30 min. Unbound antibodies were removed by centrifugation, and the PBMCs were then fixed in 200 µL of insertion solution overnight. The cells were washed and resuspended in distilled water, and 20% cisplatin was added. In EQ magnetic beads, and further analyzed on mass spectrometry flow cytometry; (3) Using the PARC clustering algorithm, the cells were divided into different phenotypes according to the marker expression, and the expression ratio of each cell subgroup was used as the modeling feature. The random forest algorithm and 10-fold cross-validation were used to screen the features; the training set and validation set were used, and the samples were divided into training set and validation set according to the time order of enrollment; 34 immune cell subgroups and markers were screened as modeling features. The features of the lung nodule benign and malignant differential diagnosis model include: CD33-CD14-CD3+CD4+CD28+, CD33-CD14-CD3+CD4+CD274+, CD33-CD14-CD3+CD4+CD197+CD45RA-, CD33-CD14-CD3+CD4+HLA_DR+CD38+, CD33-CD14-CD3+CD4+CX CR5-CD183-CCR6-, CD33-CD14-CD3+CD4+CD25+CD127-CD161-CD45RA+, CD33-CD14-CD3+CD 8+CD197+-CD45RA+, CD33-CD14-CD3-CD19+CD24+CD38+, CD33-CD14-CD3-CD20-CD38+CD27+ , CD33-CD14-CD3-CD56+CD16+CD94+, CD33-CD14-CD3-CD56+CD16+CD161+, CD3-CD19-CD56 -CD14-CD123+CD11c+, CD33-CD14-CD3-CD56+CD16-, CD86, CD11c, CD183, CD94, CD4, CD11b;The 15 features used in the lung cancer invasion assessment model include: CD33-CD14-CD3+CD8+CD85j+, CD33-CD14-CD3+CD8+CD161-, CD33-CD14-CD3+CD4+, CD33-CD14-CD3+CD4+CD197-CD45RA+, CD33-CD14-CD3+CD4+HLA_DR+CD38+, CD33-CD14-CD3+CD4+HLA_DR+CD38-, CD33-CD14-CD3+CD8+, CD33-CD14-CD3+CXCR5+, C D33-CD14-CD3+CD8+CD197+CD45RA-, CD33-CD14-CD3-CD19+CD24+CD38+, CD33-CD14-CD3-CD56+CD16+, CD33-CD14-CD3-CD56+CD16+CD57+, CD33-CD14-CD3-CD56+CD16+HLA_DR+, CD3-CD19-CD56-CD14-HLA_DR-, CD56; (4) By modeling with random forest method, a differential diagnosis model for benign and malignant pulmonary nodules and a model for judging the degree of infiltration of malignant pulmonary nodules were obtained.

2. The construction method according to claim 1, characterized in that, Step (1) When selecting samples for enrollment, random enrollment is used to cover samples of different nodule sizes, different types of nodules, and different degrees of lung cancer infiltration.

3. The construction method according to claim 2, characterized in that, The different nodule sizes are ≤10mm, 11-20mm, and 21-30mm, and the different nodule types are solid nodules, partially solid nodules, and pure ground-glass opacity nodules. The samples with different degrees of lung cancer invasion are atypical adenomatous hyperplasia (AAH), carcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IA).

4. The construction method according to claim 1, characterized in that, The flow cytometry cell sorting buffer in step (1) is 1×PBS + 0.5%BSA.

5. The construction method according to claim 1, characterized in that, The 40 metal-coupled antibody markers mentioned in step (2) include: CD45, CD3, CD56, TCR γ / δ, CD196, CD14, IgD, CD123, CD85j, CD19, CD25, CD274, CD278, CD39, CD27, CD24, CD45RA, CD86, CD28, CD197, CD11c, CD33, CD152, CD161, CD185, CD66b, CD183, CD94, CD57, CD45RO, CD127, CD279 (PD-1), CD38, CD194, CD20, CD16, HLA-DR, CD4, CD8a, and CD11b.

6. The construction method according to claim 1, characterized in that, Step (2) uses a combination of 40 metal-coupled antibody markers.

Images