UVP-TOF-MS-based lung cancer screening model construction method
The lung cancer screening model constructed through UVP-TOF-MS technology solves the problems of high misdiagnosis rate and strong invasiveness of existing lung cancer screening methods, realizes accurate distinction between lung cancer patients, and provides a non-invasive and rapid Early screening method has clinical promotion potential.
Patent Information
- Application Number
- CN202411120870.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-15
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-08-15
AI Technical Summary
The existing lung cancer screening methods have problems such as high misdiagnosis rate, strong invasiveness, high cost and concealment of early diagnosis, resulting in most patients being diagnosed in the late stage, lacking convenient, accurate and non-invasive early screening methods.
Using the lung cancer screening model based on UVP-TOF-MS, an integrated learning model was constructed through full-spectrum analysis of exhaled air samples, a Bayesian optimization technique was used to adjust the model parameters, and combined with the logistic regression model, a comprehensive lung cancer screening was formed. Predictive model, assessing model performance through confusion matrix and ROC curves, identifying potential markers of exhaled lung cancer.
It has achieved an effective distinction between lung cancer patients and non-lung cancer patients, has high accuracy and sensitivity, and provides a non-invasive and rapid early screening method for lung cancer, with the potential to be extended to clinical practice.
Smart Images

Figure CN118983079A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of model construction for medicine, and specifically relates to a method for constructing a lung cancer screening model based on UVP-TOF-MS. Background Art
[0002] Lung cancer is a major social health problem, causing 16.8% of deaths worldwide. Data released by the World Health Organization (WHO) in 2022 showed that lung cancer (LC) was the most common cancer in men and the second most common cancer in women, and the mortality rate caused by lung cancer ranked first.
[0003] Lung cancer has a high mortality rate. In most countries, the five-year survival rate of lung cancer patients after diagnosis is only 10%-20%, and the five-year survival rate has not increased significantly in the past two decades. The main reason for the high mortality rate is that lung cancer is latent in the early stages and is often diagnosed in the late stages. The prognosis of lung cancer is closely related to its clinical stage, and early diagnosis can improve the patient's prognosis. Therefore, it is very important to choose an effective screening method or develop an appropriate screening plan.
[0004] At present, many methods have been used for lung cancer screening. Commonly used methods in clinical practice include chest X-ray scanning, chest CT, sputum culture testing, and puncture biopsy. At present, chest X-ray scanning is not recommended for the detection of lung cancer because it is difficult to show lesions in the lungs and cannot reduce mortality. According to the results of the National Lung Cancer Screening Trial in my country, the use of low-dose computed tomography (LDCT) to screen lung cancer is the most effective way to reduce lung cancer mortality. LDCT guided by the LungRADS algorithm of the American College of Radiology has been validated and performed well in the National Lung Cancer Screening Trial population in the United States. Data showed that the mortality rate of lung cancer was reduced by 20%. Therefore, LDCT can be used for lung cancer screening in high-risk populations. However, the false positive rate of LDCT is high, which may lead to more misdiagnosis and unnecessary examinations and treatments, and there is a risk of radiation exposure. Sputum cytology analysis is another lung cancer screening method, but this method usually requires multiple sampling, and has low accuracy and sensitivity, and cannot be used as an effective means for routine lung cancer screening. Lung tissue biopsy is the gold standard for cancer diagnosis. Lung tissue can be extracted through fiberoptic bronchoscopy or thoracentesis. However, this method is invasive, not suitable for multiple examinations, prone to complications and expensive. About 85% of patients are diagnosed at the late stage using the above traditional diagnostic methods. Therefore, a more convenient, accurate, cheap and fast method for early screening of lung cancer is urgently needed in clinical practice.
[0005] Biomarker detection is a new type of lung cancer screening method, including blood biomarkers liquid biopsy and volatile organic compounds (VOCs) detection in exhaled breath. VOCs are volatile organic compounds with a melting point below room temperature and a boiling point between 50-260°C. Most of the gas exhaled by the human body is VOCs. When pathological changes occur in the human body, the composition of VOCs may also change, and some of them are excreted from the lungs through the respiratory tract. The VOCs composition of each disease will change, so specific diseases can be screened out by detecting the VOCs composition. Some studies have also pointed out that VOCs can be used to diagnose lung cancer. Therefore, diagnostic technology based on VOCs analysis is considered to be a promising non-invasive early screening method for lung cancer. Compared with traditional detection technology, it has the advantages of rapidity, non-invasiveness, high sensitivity, and good repeatability. It is a hot topic in the early diagnosis of lung cancer in recent years. However, this technology lacks unified standards, so it has not yet been widely popularized in clinical practice.
[0006] Ultraviolet Photoionization-Mass spectrometry (UVP-MS) is an online mass spectrometry technology commonly used to detect volatile organic compounds in recent years. Ultraviolet Photoionization Time-of-flight Mass spectrometry (UVP-TOF-MS) is a relatively new detection technology with fast detection speed and high sensitivity. Compared with other mass spectrometry methods, it is less affected by sample humidity. UVP-TOF-MS can obtain analysis results immediately, skip laboratory testing, and greatly reduce waiting time. Therefore, the target can be monitored in real time through online analysis. Therefore, applying UVP-TOF-MS to patients' exhaled breath detection can theoretically become a potential lung cancer screening method. Summary of the invention
[0007] The present invention provides a method for constructing a lung cancer screening model based on UVP-TOF-MS. By constructing a corresponding lung cancer screening model, volatile organic compounds in exhaled gas are analyzed to find potential exhaled breath lung cancer markers.
[0008] The method for constructing a lung cancer screening model based on UVP-TOF-MS of the present invention is characterized by comprising the steps of:
[0009] A. Exhaled breath sample collection: Collect exhaled breath samples of lung cancer, normal exhaled breath samples and nodule exhaled breath samples that have been confirmed within a set time range, and define normal exhaled breath samples and nodule exhaled breath samples as non-cancer exhaled breath samples;
[0010] B. Analyze the full spectrum of each exhaled breath sample collected by UVP-TOF-MS equipment to obtain spectral data of each exhaled breath sample to form a spectral sample;
[0011] C. Data preprocessing: including data cleaning, missing value mean filling, outlier deletion, calibration of the spectrum sample data to the same level of distribution through calibration gas, environmental background subtraction and peak area calculation, dividing the spectrum sample into training set, validation set and test set, and selecting appropriate features; among them,
[0012] When the data of the spectrum sample is corrected by the calibration gas, it includes calculating the peak area of the mass-to-charge ratio of the calibration gas every day in the range of [77.7, 78.4], and setting the value of the mass-to-charge ratio intensity lower than 300 to 0; then calculating the area of the calibration gas of mass-to-charge ratio_78: setting a standard value, the quotient of the standard value divided by the area of the calibration gas of mass-to-charge ratio_78 every day as a coefficient value, and finally multiplying the area of each mass-to-charge ratio of each exhaled breath sample by the coefficient value of the corresponding time to obtain the area data of each mass-to-charge ratio after correction of each exhaled breath sample, selecting all features in the interval range of mass-to-charge ratio_15 to mass-to-charge ratio_249, and deleting features of mass-to-charge ratio_94 and the proportion of the value 0 being greater than 90%;
[0013] D. Model construction: construct an ensemble learning model, finely adjust the hyperparameters of the base classifier of the ensemble learning model through Bayesian optimization technology, and obtain the best model parameter combination; the base classifier of the ensemble learning model is sorted according to the information gain importance of each feature, and the top N most important features of information gain importance are selected to form a feature set of the ensemble learning model, where N is a preset natural number; the features in the feature set are applied to the logistic regression model, and the logistic regression model and the ensemble learning model together form a comprehensive lung cancer screening prediction model;
[0014] E. Model performance evaluation: The lung cancer screening prediction model is used to predict the test set through the confusion matrix, and the accuracy, sensitivity and specificity indicators of the lung cancer screening prediction model are calculated to quantify the predictive ability of the lung cancer screening prediction model; then the receiver operating characteristic (ROC) curve of the lung cancer screening prediction model is plotted, and the area under the curve (Area Under the Curve, AUC) is calculated to compare the diagnostic performance of the lung cancer screening prediction model under different parameters, and based on the analysis of the area under the curve, the lung cancer screening prediction model with the best performance is screened out.
[0015] The present invention is based on ultraviolet photoionization time-of-flight mass spectrometry (UVP-TOF-MS) to analyze volatile organic compounds (VOCs) in exhaled breath to screen for lung cancer. By collecting and analyzing the VOCs of subjects (including non-lung cancer patients and confirmed lung cancer patients) through UVP-TOF-MS, the data set is evaluated using methods such as confusion matrix and ROC curve, and the data are analyzed using an integrated learning model for several different groups of people such as non-lung cancer and lung cancer, normal people and lung cancer nodules and lung cancer, to find potential exhaled breath lung cancer markers.
[0016] Furthermore, in step B, the steps of performing full spectrum analysis on each exhaled breath sample collected by the UVP-TOF-MS device are as follows:
[0017] After the UVP-TOF-MS equipment is preheated and the state is stable, the collected exhaled breath samples are connected to the sampling pipeline one by one. In the full spectrum analysis of the exhaled breath samples, two spectral data points are collected for each exhaled breath sample, and the second spectral data of each exhaled breath sample is taken as the spectral sample of the exhaled breath sample.
[0018] Furthermore, in step C, the areas under the peak values of all qualitative VOCs in the spectrum sample are normalized to the interval (0, 1), and a data matrix is generated after data processing. The spectrum sample is divided into a training set, a validation set, and a test set according to a set ratio, and then the data is corrected.
[0019] Furthermore, when the data is corrected, the peak area and the standard gas area of the daily calibration gas data within the specified mass-to-charge ratio range are calculated, and then the area data of each mass-to-charge ratio after correction of each exhaled breath sample is obtained, and then all features within the set mass-to-charge ratio area range are selected.
[0020] The beneficial effects of the present invention include:
[0021] 1. Most of the different numbers of features selected by the model have significant differences and can be used as potential lung cancer markers, which has positive significance for lung cancer screening.
[0022] 2. It can well distinguish between lung cancer patients and non-lung cancer patients. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 The figure is a flow chart of the method for constructing a lung cancer screening model based on UVP-TOF-MS of the present invention.
[0024] Figure 2 This is a graph showing the contribution percentages of the top 30 features in Example 1.
[0025] Figure 3 a is the prediction graph of the confusion matrix for the validation set samples in Example 1.
[0026] Figure 3 b is the ROC curve diagram of the validation set samples in Example 1.
[0027] Figure 4 a is the prediction graph of the confusion matrix for the test set samples in Example 1.
[0028] Figure 4 b is the ROC curve diagram of the test set samples in Example 1.
[0029] Figure 5 These are the 28 characteristic graphs with significant differences in Example 1.
[0030] Figure 6 This is a graph showing the contribution percentages of the top 30 features in Example 2.
[0031] Figure 7 a is the prediction graph of the confusion matrix for the validation set samples in Example 2.
[0032] Figure 7 b is the ROC curve diagram of the validation set samples in Example 2.
[0033] Figure 8 a is the prediction graph of the confusion matrix for the test set samples in Example 2.
[0034] Figure 8 b is the ROC curve diagram of the test set samples in Example 2.
[0035] Fig. 9 These are the 22 characteristic graphs with significant differences in Example 2.
[0036] Fig.10 This is a graph showing the contribution percentages of the top 30 features in Example 3.
[0037] Fig.11 a is the prediction graph of the confusion matrix for the validation set samples in Example 3.
[0038] Fig.11 b is the ROC curve diagram of the validation set samples in Example 3.
[0039] Fig.12 a is the prediction graph of the confusion matrix for the test set samples in Example 3.
[0040] Fig.12 b is the ROC curve diagram of the test set samples in Example 3.
[0041] Fig.13 These are the 28 characteristic graphs with significant differences in Example 3. DETAILED DESCRIPTION
[0042] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.
[0043] like Figure 1 As shown, the method for constructing a lung cancer screening model based on UVP-TOF-MS of the present invention is characterized by comprising the steps of:
[0044] A. Exhaled breath sample collection: exhaled breath samples of lung cancer, normal exhaled breath samples and nodule exhaled breath samples confirmed within a set time range are collected, and normal exhaled breath samples and nodule exhaled breath samples are defined as non-cancer exhaled breath samples.
[0045] The exhaled breath samples in this embodiment were collected from patients who visited the West China Hospital of Sichuan University from October 2022 to April 2023 and whose chest CT showed space-occupying lesions in the lungs as research subjects, and healthy subjects were recruited as a control group.
[0046] Inclusion criteria: (1) Aged 18-70 years old, regardless of gender; (2) Complete clinical information, including hospitalization / outpatient number, age, gender, clinical diagnosis, etc.; (3) Meet one of the following conditions: a) Subjects suspected of lung cancer; b) Subjects with other benign respiratory diseases; c) Patients with other cancers, such as gastric cancer, esophageal cancer, and intestinal cancer; d) Healthy subjects without respiratory diseases and signs. Subjects who meet all of the above criteria can be included.
[0047] Exclusion criteria: (1) patients who have been diagnosed with lung cancer and received lung cancer treatment; (2) patients who ate after 22:00 the previous night; (3) patients with ventilation or gas exchange dysfunction; (4) patients with severe mental illness or cognitive impairment; (5) women who are pregnant or breastfeeding; (6) patients with a history of drug abuse or current drug abuse; (7) patients who are considered by the researchers to be unsuitable for participation in this study. Subjects who meet any of the above criteria will not be included.
[0048] This study has established the criteria and procedures for subject withdrawal to protect the rights and interests of the subjects. Subjects have the right to withdraw from the trial at any time without any reason. If the subject decides to withdraw from the trial, the researcher should try to find out the reason for the withdrawal and record this reason as the original text data. In order to protect the rights and interests of the subjects, ensure the quality of the trial, and avoid unnecessary economic losses, if the subject encounters the following situations, the researcher determines that the subject is unable to continue this clinical trial, and the researcher has the right to suspend his / her participation in the trial and require him / her to withdraw from the trial early: (1) The subject meets the exclusion criteria (new or previously undiscovered) and cannot continue to participate in the study; (2) The subject encounters other conditions that the researcher believes are unable to continue this clinical trial; (3) The subject is unwilling to continue to participate in this clinical trial for any reason.
[0049] In this example, a total of 4325 lung cancer samples and normal samples were collected from West China Hospital of Sichuan University, including 360 lung cancer (Lung cancer, referred to as LC) samples, 995 normal samples, and 2970 nodule samples. Normal samples and nodule samples were defined as non-lung cancer (Non-Lc) samples, totaling 3965 samples.
[0050] The clinical data of patients in this study were mainly collected from the HIS medical record system (Hospital Information System, HIS), and the clinical data of healthy physical examination populations were collected from the physical examination system. It mainly includes basic information of patients and examination results: gender, age, exposure history of risk factors such as smoking history, imaging examination, pathology report (histological classification, pathological stage), tumor location and size, laboratory examination (including: blood routine, biochemistry, tumor markers, etc.).
[0051] To ensure that the quality of exhaled breath collection meets the requirements, the exhaled breath is collected through an exhaled breath sample bag, and the following conditions must be met: 1) Exhaled breath is collected before surgery, chemotherapy, radiotherapy, etc.; 2) Fasting for more than 8 hours in the morning; 3) No smoking or drinking within 2 hours; 4) Use an offline sampling device to collect alveolar gas samples from subjects. Strict standard procedures for the collection of exhaled breath samples and detection and analysis of subjects have been formulated for the collection of exhaled breath samples, the collection of ambient air, and the transportation of exhaled breath sample bags to ensure the accuracy and scientificity of the test.
[0052] B. The UVP-TOF-MS device is used to analyze the full spectrum of each exhaled breath sample collected, and the spectrum data of each exhaled breath sample is obtained to form a spectrum sample:
[0053] After the exhaled breath sample collection bag containing the exhaled breath sample is sent to the laboratory according to standard procedures, the exhaled breath sample can be tested and analyzed. Mass spectrometry conditions and parameter settings of UVP-TOF-MS equipment: Equipment model: UVP-TOF-MSPLUS, injection tube and ion source temperature 70℃, ion source pressure 500 Pa, ion source current 1mA, integration time 50 s; Exhaled breath sample detection and analysis test process: (1) After the UVP-TOF-MS equipment is preheated and the state is stable, connect the exhaled breath sample sampling bag to the injection pipeline, open the bag valve, and start the full spectrum analysis of the exhaled breath sample. Each exhaled breath sample collects two spectral data points, and each exhaled breath sample takes the second spectral data as the result; (2) After the spectrum collection is completed, close the bag valve, open the nitrogen purge pipeline controlled by the mass flow controller (Mass Flow Controller, MFC), execute the pipeline cleaning process of the above two data points, and use clean high-purity nitrogen to discharge the gas residue in the pipeline; (3) After the pipeline cleaning process is completed, the above steps can be repeated to start the injection and analysis process of the next exhaled breath sample.
[0054] C. Data preprocessing: including data cleaning of the obtained spectrum samples, missing value mean filling processing, outlier deletion, calibration of the spectrum sample data to the same level distribution through calibration gas, environmental background subtraction and peak area calculation:
[0055] The peak areas (VOCs content) of all qualitative VOCs (volatile organic compounds) in the spectrum samples were normalized to the interval (0, 1). After data processing, a data matrix was generated. The spectrum samples were divided into training set, validation set and test set in a ratio of 3:1:1, and then the data was corrected.
[0056] When correcting the data, calculate the peak area and standard gas area of the M / Z (mass-to-charge ratio) of the daily calibration gas data in the range of [77.7, 78.4], set the M / Z value with an intensity value lower than 300 to 0, calculate the standard gas area of M / Z_78: take 3,000,000 as the standard value, and keep the quotient of the standard value divided by the area of the daily standard gas M / Z_78 as the coefficient value. Finally, multiply the area of each M / Z of each exhaled breath sample by the coefficient value of the corresponding time to obtain the area data of each M / Z after the exhaled breath sample is corrected. Select all features in the range of M / Z_15 to M / Z_249, and a total of 235 features are selected. Finally, delete the contaminated M / Z_94 in the exhaled breath sample bag itself and the features with a ratio of 0 greater than 90%.
[0057] D. Build the model: Build an integrated learning model, which can include a Random Forest (RF) model, a CatBoost model, or an XGBoost model. Accurate modeling is performed through training sets and validation sets to ensure the reliability and accuracy of the model. During the model training process, the base classifiers of the model are trained using the training set, and their performance is evaluated using the validation set. Then, Bayesian optimization techniques are applied to fine-tune the hyperparameters of these base classifiers (such as the learning rate and the maximum depth of the tree) to ensure that the best combination of model parameters is selected.
[0058] To further improve the performance and interpretability of the model, the information gain importance of each feature is scored based on the base classifier. By training the base classifier and collecting these scores, a feature importance curve is plotted, which arranges the features in descending order of their importance and shows their cumulative contribution. This curve is then analyzed to identify those features that have a decreasing effect on the performance of the model, which is usually reflected in a significant inflection point on the curve. Based on this inflection point, the top N most important features are selected to form the feature set of the model, where N is a preset natural number.
[0059] The features in the feature set are applied to a logistic regression model, which is a statistical learning method for solving classification problems. The training goal of the logistic regression model is to maximize the likelihood function, and optimization algorithms such as gradient descent are usually used to solve the parameters. Once the model training is completed, it can be used to classify new samples and output the corresponding category probabilities. The logistic regression model and the integrated learning model together form a comprehensive lung cancer screening prediction model. By analyzing the weights of the independent variables in the logistic regression model, key factors closely related to the occurrence of lung cancer can be identified. These factors and their weights will become the core indicators for predicting the risk of individual lung cancer, thereby being able to more accurately predict the possibility of lung cancer.
[0060] E. Model performance evaluation: Through the confusion matrix, the lung cancer screening prediction model is used to predict the test set, and the accuracy, sensitivity and specificity indicators of the lung cancer screening prediction model are calculated to quantify the predictive ability of the lung cancer screening prediction model; then the receiver operating characteristic (ROC) curve of the lung cancer screening prediction model is plotted, and the area under the curve (Area Under the Curve, AUC) is calculated to compare the diagnostic performance of the lung cancer screening prediction model under different parameters, and the best performing lung cancer screening prediction model is screened out based on the analysis of the area under the curve. The closer the AUC value is to 1, the higher the diagnostic accuracy of the model. Based on the analysis of the AUC value, the best performing diagnostic model can be screened out.
[0061] The confusion matrix, also known as the error matrix or likelihood matrix, is a standard format for expressing accuracy evaluation in the field of machine learning. The confusion matrix is a visualization tool, especially used in supervised learning. In structured accuracy evaluation, it is mainly used to compare classification results with actual measured values, and the accuracy of classification results can be displayed in a confusion matrix.
[0062] The confusion matrix means: each column of the confusion matrix represents the predicted category, and the total number of each column represents the number of data predicted to be in that category; each row represents the true category of the data, and the total number of data in each row represents the number of data instances in that category; the value in each column represents the number of true data predicted to be in that category. The structure of the confusion matrix is generally shown in Table 1.
[0063] Table 1:
[0064]
[0065] In Table 1, TP represents true positive, that is, the number of samples that are actually positive and correctly predicted as positive; FN represents false negative, that is, the number of samples that are actually positive but are mistakenly predicted as negative; FP represents false positive, that is, the number of samples that are actually negative but are mistakenly predicted as positive; TN represents true negative, that is, the number of samples that are actually negative and are correctly predicted as negative.
[0066] Sensitivity = true positive / (true positive + false negative) × 100% = TP / (TP+FN) × 100%;
[0067] Specificity = true negative / (false positive + true negative) × 100% = TN / (FP + TN) × 100%;
[0068] Correct rate = (true positive + true negative) / (true positive + false negative + false positive + true negative) × 100% = (TP+TN) / (TP+FP+FN+TN) × 100%.
[0069] Together, these metrics form an overall assessment of the performance of a classification model. Accuracy gives the overall proportion of the model’s predictions that are correct, while sensitivity and specificity measure the model’s ability to identify true positives and true negatives, respectively.
[0070] AUC (Area Under the Curve) is the area under the ROC (Receiver Operating Characteristic) curve, usually between 0.5 and 1. This metric is used to intuitively evaluate the performance of a classifier, where the closer the value is to 1, the better the classifier performance. AUC is an important performance evaluation metric because it provides a clearer comparison of classifier performance in the form of a single value than the ROC curve itself.
[0071] The calculation of AUC usually uses the trapezoidal rule, that is, calculating the total area under the ROC curve. The value of AUC is used to judge the quality of the classifier, and the specific explanation is as follows:
[0072] AUC = 1: It means that the classifier is perfect and is able to make perfect predictions by setting the threshold.
[0073] 0.5 < AUC < 1: Indicates that the classifier performs better than random guessing and has practical predictive value.
[0074] AUC = 0.5: This indicates that the classifier’s prediction performance is no different from random guessing, that is, it has no practical predictive value.
[0075] AUC < 0.5: This means that the classifier performs worse than random guessing, but could potentially perform better than random guessing if its predictions could be interpreted in reverse.
[0076] This approach makes AUC a concise and effective tool to measure and compare the performance of different classifiers when dealing with imbalanced datasets.
[0077] The present invention is based on ultraviolet photoionization time-of-flight mass spectrometry (UVP-TOF-MS) to analyze volatile organic compounds (VOCs) in exhaled breath to screen for lung cancer. By collecting and analyzing the VOCs of subjects (including non-lung cancer patients and confirmed lung cancer patients) through UVP-TOF-MS, the data set is evaluated using methods such as confusion matrix and ROC curve, and the data are analyzed using an integrated learning model for several different groups of people such as non-lung cancer and lung cancer, normal people and lung cancer nodules and lung cancer, to find potential exhaled breath lung cancer markers.
[0078] The present invention is further described below through multiple clinical data:
[0079] Embodiment 1:
[0080] The prediction model based on UVP-TOF-MS can effectively distinguish lung cancer patients from non-lung cancer patients (healthy people and nodule patients), as follows:
[0081] The collected lung cancer samples and non-lung cancer samples (a total of 877 cases) were divided into training set, validation set and test set according to 6:2:2: 526 samples in the training set; 176 samples in the validation set, including 90 lung cancer samples and 86 non-lung cancer samples; 175 samples in the test set, including 81 lung cancer samples and 94 non-lung cancer samples. The XGBoost (eXtreme Gradient Boosting) algorithm was used to establish a binary classification model.
[0082] The top 30 ranking results of the model's feature importance are as follows Figure 2 As shown in the Feature contribution percentage chart, Figure 2 It can be seen that feature M / Z_105_area has the highest contribution percentage to the model, feature M / Z_167_area has the second highest contribution to the model, feature M / Z_96_area has the third highest contribution to the model, and so on for other features. M / Z_92_area has the lowest contribution to the model.
[0083] The feature contribution percentage plot is a visualization method to show the impact of each feature in the model on the prediction results. Features are labeled M / Z plus a series of numbers. The importance of each feature is expressed as a percentage and is presented in the graph as a length. The longer the length of the bar, the greater the impact of the feature on the model's prediction results. The longest bar represents the most important feature, while the shortest represents the less influential feature.
[0084] Use the trained model to predict the validation set samples, and use the confusion matrix ( Figure 3 a) and ROC curve for evaluating diagnostic performance ( Figure 3 b) The prediction of the validation set samples is as follows Figure 3 a and Figure 3 As shown in b.
[0085] exist Figure 3 In a, 4 of the 90 lung cancer samples (True value vertical Lc) were predicted as non-lung cancer samples (Predicted value horizontal Non_lc), and 1 of the 86 non-lung cancer samples (True value vertical Non_lc) was predicted as a lung cancer sample (Predicted value horizontal Lc). The overall accuracy was 97.16%, the sensitivity was 95.56%, and the specificity was 98.84%; Figure 3 The ROC area AUC value in b is 0.9938, which is very close to 1, and the modeling effect is excellent.
[0086] Use the trained model to predict the test set samples to evaluate the model performance, and use the confusion matrix ( Figure 4 a) and ROC curve for evaluating diagnostic performance ( Figure 4 b) Prediction of test set samples, such as Figure 4 a and Figure 4 As shown in b.
[0087] exist Figure 4 In a, 1 of the 81 lung cancer samples (True value vertical Lc) was predicted as a non-lung cancer sample (Predicted value horizontal Non_lc), and 5 of the 94 non-lung cancer samples (True value vertical Non_lc) were predicted as lung cancer samples (Predicted value horizontal Lc). The overall accuracy was 96.57%, the sensitivity was 98.77%, and the specificity was 94.68%; Figure 4 The ROC area AUC value in b is 0.9971, which is very close to 1, and the modeling effect is excellent.
[0088] For non-lung cancer patients and cancer patients, the first 30 features of the XGBoost model were selected for non-parametric Mann-Whitney U test. There were 25 features with significant P values less than 0.05. These 25 features were used to draw box plots for non-lung cancer patients and lung cancer patients, and the P values of the non-parametric Mann-Whitney U test were displayed in the title of the figure, as shown in the figure below: Figure 5 shown.
[0089] Depend on Figure 5 It can be seen that the distribution of 25 specific mass-to-charge ratio (M / Z) features between the "non-lung cancer" (Nor_lc) and "lung cancer" (Lc) groups is different, and the P value of each feature indicates its statistical significance, which can well distinguish the two groups of people. Most features have a higher median in the lung cancer group, indicating that these features have a higher expression level in lung cancer, and the degree of dispersion of the features shows a certain difference between the two groups, especially in the lung cancer group. The more consistent expression may point to a specific biological process. For example, the features of M / Z_121_area and M / Z_135_area show obvious significant differences between non-lung cancer and lung cancer patients, which means that they may be closely related to the specific biological processes of lung cancer. In addition, the outliers of some features suggest the existence of possible subpopulations, which may play an important role in the future classification of lung cancer subtypes or personalized treatment.
[0090] Overall results: The accuracy of the training set was 100%, the accuracy of the validation set was 97.16%, and the accuracy of the test set was 96.57%; the prediction effects of the three data sets were very good, with accuracy rates greater than 95%, and the generalization ability of the prediction model was very good. It was proved that the prediction model based on UVP-TOF-MS can effectively distinguish lung cancer patients from non-lung cancer patients (healthy people and nodule patients).
[0091] Embodiment 2:
[0092] The prediction model based on UVP-TOF-MS can effectively distinguish lung cancer patients from healthy people, as follows:
[0093] The collected lung cancer samples and normal samples were divided into training set, validation set and test set according to 6:2:2: 525 samples in the training set; 176 samples in the validation set, including 78 lung cancer samples and 98 normal samples; 175 samples in the test set, including 91 lung cancer samples and 84 normal samples. The XGBoost algorithm was used to establish a binary classification model.
[0094] The top 30 ranking results of the model's feature importance are as follows Figure 6As shown in the Feature contribution percentage chart, feature M / Z_105_area has the highest contribution percentage to the model, feature M / Z_227_area has the second highest contribution percentage to the model, feature M / Z_240_area has the third highest contribution percentage to the model, and so on for other features.
[0095] Use the trained model to predict the validation set samples, and use the confusion matrix ( Figure 7 a) and ROC curve for evaluating diagnostic performance ( Figure 7 b) The prediction of the validation set samples is as follows Figure 7 a and Figure 7 As shown in b.
[0096] Depend on Figure 7 a It can be seen that 4 out of 78 lung cancer samples (Lc in the vertical direction of True value) in the validation set were predicted as normal samples (Normal in the horizontal direction of Predicted value), and 3 out of 98 normal samples (Normal in the vertical direction of True value) were predicted as lung cancer samples (Lc in the horizontal direction of Predicted value). The overall accuracy is 96.02%, the sensitivity is 94.87%, and the specificity is 96.94%. Figure 7 The area under the ROC curve in (b) is 0.9898, and the AUC is greater than 0.90, indicating that the classifier works very well.
[0097] Use the trained model to predict the test set samples to evaluate the model performance, and use the confusion matrix ( Figure 8 a) and ROC curve for evaluating diagnostic performance ( Figure 8 b) Prediction of test set samples, such as Figure 8 a and Figure 8 As shown in b.
[0098] Depend on Figure 8 a It can be seen that 4 of the 91 lung cancer samples (Lc in the vertical direction of True value) in the test set were predicted as normal samples (Normal in the horizontal direction of Predicted value), and 4 of the 84 normal samples (Normal in the vertical direction of True value) were predicted as lung cancer samples (Lc in the horizontal direction of Predicted value). The overall accuracy is 95.43%, the sensitivity is 95.60%, and the specificity is 95.24%. Figure 8The area under the ROC curve in (b) is 0.9958, and the AUC is greater than 0.90, indicating that the classifier works very well.
[0099] For normal people and cancer patients, the first 30 features of the XGBoost model were selected for non-parametric Mann-Whitney U test. There were 20 features with significant P values less than 0.05. These 20 features were plotted as box plots for normal people and lung cancer patients, and the P values of the non-parametric Mann-Whitney U test were displayed in the title of the figure, as shown in the figure below: Fig. 9 shown.
[0100] exist Fig. 9 Each box plot in the figure shows the distribution of a specific M / Z feature between normal people and lung cancer patients. Through the position of the median, we can observe that certain features are significantly increased or decreased in the lung cancer group, which may indicate that they play an important biological role in the development of lung cancer. The width of the interquartile range shows the dispersion of the data within each group. A narrower interquartile range indicates that the feature value is more concentrated in the group. The P value of each feature is also marked in the figure. A P value below 0.05 usually indicates that the difference is statistically significant, while a very low P value close to 0 more strongly indicates a significant difference between the two groups. For example, the features of M / Z 105_area and M / Z 167_area show extreme significant differences between normal people and lung cancer patients, which means that they may be closely related to biomarkers of lung cancer. In addition, the outliers on the box plot reflect specific individual differences, which may be related to the heterogeneity of the disease or different lung cancer subtypes. In summary, this set of box plots provides important information about the differences in the distribution of M / Z features between normal people and lung cancer patients, which is of great significance for understanding the molecular mechanisms of lung cancer, developing new diagnostic methods, and personalized treatment strategies. These features are expected to become key biomarkers in the diagnosis and treatment of lung cancer in the future.
[0101] Overall results: The accuracy of the training set was 100%, the accuracy of the validation set was 96.02%, and the accuracy of the test set was 95.43%; the prediction effects of the three data sets were very good, with accuracy rates greater than 95%, and the model generalization ability was very good. It was proved that the prediction model based on UVP-TOF-MS can effectively distinguish lung cancer patients from healthy people.
[0102] Embodiment 3:
[0103] The prediction model based on UVP-TOF-MS can effectively distinguish patients with lung cancer from patients with benign lung nodules as follows:
[0104] The collected lung cancer samples and nodule samples (a total of 876 cases) were divided into training set, validation set and test set according to 6:2:2: 525 samples in the training set; 176 samples in the validation set, including 78 lung cancer samples and 98 nodule samples; 175 samples in the test set, including 91 lung cancer samples and 84 nodule samples. The XGBoost algorithm was used to establish a binary classification model.
[0105] The top 30 ranking results of the model's feature importance are as follows Fig.10 As shown in the Feature contribution percentage chart, Fig.10 It can be seen that feature M / Z_105_area contributes the most to the model, feature M / Z_206_area contributes the second most, feature M / Z_179_area contributes the third most, and so on for other features. M / Z_118_area contributes the least to the model.
[0106] Use the trained model to predict the validation set samples, and use the confusion matrix ( Fig.11 a) and ROC curve for evaluating diagnostic performance ( Fig.11 b) The prediction of the validation set samples is as follows Fig.11 a and Fig.11 As shown in b.
[0107] Fig.11 In a, 3 out of 78 lung cancer samples (True value vertical Lc) were predicted as nodule samples (Predicted value horizontal Node), and 3 out of 98 nodule samples (True value vertical Node) were predicted as lung cancer samples (Predicted value horizontal Lc). The overall accuracy was 96.59%, the sensitivity was 96.15%, and the specificity was 96.94%; Fig.11 The AUC value of the ROC curve area in b is 0.9910, which is very close to 1, and the modeling effect is excellent.
[0108] Use the trained model to predict the test set samples, and use the confusion matrix ( Fig.12 a) and ROC curve for evaluating diagnostic performance ( Fig.12 b) The prediction of the test set samples is as follows Fig.12 a and Fig.12 As shown in b.
[0109] exist Fig.12In a, 2 of the 91 lung cancer samples (True value vertical Lc) were predicted as nodule samples (Predicted value horizontal Node), and 1 of the 84 nodule samples (True value vertical Node) was predicted as lung cancer sample (Predicted value horizontal Lc). The overall accuracy was 98.29%, the sensitivity was 97.80%, and the specificity was 98.81%. Fig.12 The AUC value of the ROC curve area in b is 0.9966, which is very close to 1, and the modeling effect is excellent.
[0110] The first 30 features of the XGBoost model were selected for nodule patients and cancer patients for non-parametric Mann-Whitney U test. The significant P value was less than 0.05. There were 26 features in total. The box plots of nodule patients and lung cancer patients were drawn for these 26 features, and the P value of the non-parametric Mann-Whitney U test was displayed in the title of the figure, as shown in the figure below: Fig.13 shown.
[0111] exist Fig.13 Each box plot presented in the figure reveals the distribution of a specific M / Z feature in nodule and lung cancer samples. The medians of these features are significantly different between the two types of samples, which may indicate that certain specific mass spectrometric features are closely related to the development of lung cancer. For example, the expression level of some features in the lung cancer group is significantly higher than that in the nodule group, which may reflect the expression pattern of lung cancer biomarkers. The presence of outliers indicates that there are individual differences in feature expression in both groups, which may be related to different disease subtypes or biological behaviors. Especially in lung cancer samples, higher or lower outliers may be related to disease heterogeneity or patient biomarker specificity. The P value of each feature is marked on the corresponding box plot in terms of statistical significance. Features with a P value lower than 0.05 indicate that the difference between nodule and lung cancer samples is statistically significant, which means that these features can be used to distinguish between two different biological states. In summary, the M / Z features shown in these box plots have important biological and clinical significance for distinguishing nodule and lung cancer samples. They may become valuable biomarkers for early diagnosis of lung cancer, monitoring disease progression, and guiding treatment decisions. Therefore, further study of these characteristics will help us better understand the molecular mechanisms of lung cancer and provide support for precision medicine for lung cancer.
[0112] Overall results: The accuracy of the training set was 100%, the accuracy of the validation set was 96.59%, and the accuracy of the test set was 98.29%; the prediction effects of the three data sets were all good, with the accuracy rates all greater than 90%, and the model generalization ability was good. It was proved that the prediction model based on UVP-TOF-MS can effectively distinguish lung cancer patients from nodule patients.
[0113] In the above embodiments, the obtained exhaled breath samples were divided into lung cancer samples, nodule samples and normal samples, and the VOCs in the exhaled breath samples were analyzed using UVP-TOF-MS. The model was built and evaluated using confusion matrix and ROC curve.
[0114] The evaluation results show that the lung cancer screening model of the present invention has excellent predictive ability in the three groups of non-lung cancer and lung cancer, normal people and lung cancer research, and nodules and lung cancer, and has the potential to be promoted to the clinic and used as an early screening method for lung cancer, and the characteristic results provide ideas for possible potential lung cancer biomarkers. The established lung cancer screening model provides a new path for the convenient, accurate, cheap and fast early screening method for lung cancer required in the clinic. At the same time, further research and improvement are needed in the optimization of the algorithm and the screening of characteristic markers in order to achieve better screening results.
[0115] The above embodiments only express the specific implementation methods of the present application, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the present application. For ordinary technicians in this field, several modifications and improvements made without departing from the concept of the present application all belong to the protection scope of the present application.
Claims
1. Construction method of lung cancer screening model based on UVP-TOF-MS, Its characteristics are: including the steps of: A. Exhaled breath sample collection: Collect exhaled breath samples of lung cancer, normal exhaled breath samples and nodule exhaled breath samples that have been confirmed within a set time range, and define normal exhaled breath samples and nodule exhaled breath samples as non-cancer exhaled breath samples; B. Analyze the full spectrum of each exhaled breath sample collected by UVP-TOF-MS equipment to obtain spectral data of each exhaled breath sample to form a spectral sample; C. Data preprocessing: including data cleaning, missing value mean filling, outlier deletion, calibration of the spectrum sample data to the same level of distribution through calibration gas, environmental background subtraction and peak area calculation, dividing the spectrum sample into training set, validation set and test set, and selecting appropriate features; among them, When the data of the spectrum sample is corrected by the calibration gas, it includes calculating the peak area of the mass-to-charge ratio of the calibration gas every day in the range of [77.7, 78.4], and setting the value of the mass-to-charge ratio intensity lower than 300 to 0; then calculating the area of the calibration gas of mass-to-charge ratio_78: setting a standard value, the quotient of the standard value divided by the area of the calibration gas of mass-to-charge ratio_78 every day as a coefficient value, and finally multiplying the area of each mass-to-charge ratio of each exhaled breath sample by the coefficient value of the corresponding time to obtain the area data of each mass-to-charge ratio after correction of each exhaled breath sample, selecting all features in the interval range of mass-to-charge ratio_15 to mass-to-charge ratio_249, and deleting features of mass-to-charge ratio_94 and the proportion of the value 0 being greater than 90%; D. Model construction: construct an ensemble learning model, finely adjust the hyperparameters of the base classifier of the ensemble learning model through Bayesian optimization technology, and obtain the best model parameter combination; the base classifier of the ensemble learning model is sorted according to the information gain importance of each feature, and the top N most important features of information gain importance are selected to form a feature set of the ensemble learning model, where N is a preset natural number; the features in the feature set are applied to the logistic regression model, and the logistic regression model and the ensemble learning model together form a comprehensive lung cancer screening prediction model; E. Model performance evaluation: The lung cancer screening prediction model is used to predict the test set through the confusion matrix, and the accuracy, sensitivity and specificity indicators of the lung cancer screening prediction model are calculated to quantify the predictive ability of the lung cancer screening prediction model; then the receiver operating characteristic curve of the lung cancer screening prediction model is plotted, and the area under the curve is calculated to compare the diagnostic performance of the lung cancer screening prediction model under different parameters. Based on the analysis of the area under the curve, the lung cancer screening prediction model with the best performance is screened out.
2. The method for constructing a lung cancer screening model based on UVP-TOF-MS according to claim 1, characterized in that: In step B, the steps of full spectrum analysis of each exhaled breath sample collected by UVP-TOF-MS equipment are as follows: After the UVP-TOF-MS equipment is preheated and the state is stable, the collected exhaled breath samples are connected to the sampling pipeline one by one. In the full spectrum analysis of the exhaled breath samples, two spectral data points are collected for each exhaled breath sample, and the second spectral data of each exhaled breath sample is taken as the spectral sample of the exhaled breath sample.
3. The method for constructing a lung cancer screening model based on UVP-TOF-MS according to claim 1, characterized in that: In step C, the area under the peak of all qualitative VOCs in the spectrum sample is normalized to the interval (0, 1), and a data matrix is generated after data processing. The spectrum sample is divided into a training set, a validation set, and a test set according to a set ratio, and then the data is corrected.
4. The method for constructing a lung cancer screening model based on UVP-TOF-MS as claimed in claim 3, characterized in that: When correcting the data, the peak area and standard gas area of the daily calibration gas data within the specified mass-to-charge ratio range are calculated, and then the area data of each mass-to-charge ratio after correction of each exhaled breath sample is obtained, and then all features within the set mass-to-charge ratio area range are selected.
Citation Information
Patent Citations
Method for early screening of lung cancer by using vacuum ultraviolet photoionization mass spectrometer
CN106137204A
High-sensitivity ultraviolet light ionization time-of-flight mass spectrometer and method for measuring ion time-of-flight
CN111613514A
Intelligent lung cancer detection method and system based on image and machine smell fusion
CN111833330A
Pulmonary tuberculosis risk assessment method and system based on exhaled gas mass spectrum detection
CN114324549A
Self-adaptive lung cancer screening method based on expiration measurement data element learning
CN117711633A
Cited By
Method for identifying ground glass pulmonary nodules
CN114692748A
A method for identifying ground-glass pulmonary nodules
CN114692748B
Emergency and critical patient early warning and screening system for detecting VOCs in exhaled air based on CI-TOFMS
CN119993495A
Early warning screening system for critical and severe patients based on detection of exhaled VOCs by CI-TOFMS
CN119993495B
