Lung cancer screening model construction device, lung cancer screening device, equipment and medium

Abstract

The present application relates to a device for constructing a lung cancer screening model, a lung cancer screening device, equipment and a medium. The device for constructing a lung cancer screening model includes: a sample acquisition and data acquisition module, which is used to obtain samples of patients with lung nodules without lung cancer and collect baseline parameters of the samples of patients with lung nodules; the baseline parameters include radial lung nodules and serum thymidine kinase 1; a model training module, which is used to train the model with the baseline parameters as independent variables and the risk of new lung cancer within 3 years after the baseline visit as the dependent variable; a model evaluation and verification module, which is used to evaluate the predictive performance and internally verify the trained model, and then obtain a risk prediction model for new lung cancer in patients with lung nodules without cancer within 3 years. The present application can be used to predict the risk of lung nodules without lung cancer developing into lung cancer in a large sample of Chinese population.

Description

Technical Field

[0001] The present application relates to the field of intelligent medical detection technology, and in particular to a device for constructing a lung cancer screening model, a lung cancer screening device, equipment and medium. Background Art

[0002] Lung cancer is a leading cause of global health burden, therefore early detection and treatment are crucial to reduce lung cancer mortality.

[0003] Low-dose computed tomography (LDCT) is a commonly used method for detecting pulmonary nodules. However, there are still challenges in using LDCT to assess the risk of canceration of pulmonary nodules. The false-positive rate in the two-year follow-up is as high as 23.3%, which may lead to unnecessary radiation exposure, invasive biopsy, economic costs and patient anxiety. The risk assessment method of pulmonary nodules after LDCT examination needs to be improved to optimize the follow-up strategy.

[0004] At present, the lung cancer screening guidelines in my country recommend that further examinations be decided based solely on the radial and density of lung nodules measured by LDCT. The guidelines in Europe and the United Kingdom recommend the use of prediction models, which can significantly reduce the false positive rate. However, due to differences in the distribution of predictive factors, these foreign models are not applicable to Chinese people. In addition, the published Chinese population models are limited in applicability due to the small sample size (<1000). Therefore, there is an urgent need for a prediction model construction technology based on a large sample of the Chinese population to predict the risk of lung cancer in patients with lung nodules without lung cancer. Summary of the invention

[0005] In order to predict the risk of lung nodule patients without lung cancer developing lung cancer, the present application provides a device for constructing a lung cancer screening model, a lung cancer screening device, equipment and medium.

[0006] In the first aspect, the present application provides a device for constructing a lung cancer screening model using the following technical solution:

[0007] A device for constructing a lung cancer screening model, comprising:

[0008] A sample acquisition and data collection module is used to obtain samples from patients with lung nodules who do not have lung cancer, and to collect baseline parameters of the samples from patients with lung nodules; the baseline parameters include radial lung nodules and serum thymidine kinase 1;

[0009] A model training module, for performing model training using the baseline parameters as independent variables and the risk of new lung cancer within 3 years after the baseline visit as a dependent variable;

[0010] The model evaluation and verification module is used to evaluate the predictive effectiveness and internally verify the trained model, thereby obtaining a risk prediction model for new lung cancer within 3 years in patients without cancerous lung nodules.

[0011] By adopting the above-mentioned technical means, especially using the baseline parameters (including lung nodule radial and serum thymidine kinase 1) as independent variables, the risk of new lung cancer within 3 years after the baseline visit is used as the dependent variable for model training, so that it can be used for a large sample of Chinese people to achieve the risk prediction of lung cancer in patients with lung nodules without lung cancer. In other words, this application can be used to predict the probability of new lung cancer in the next 3 years instead of diagnosing existing lung cancer, because patients with lung nodules who are currently free of lung cancer also have the risk of developing lung cancer in the future as the disease progresses, and there is currently no technology that can predict this. This application is the first practical tool that can predict the risk of lung cancer in the medium and short term. In addition, in this application, the model constructed using lung nodule radial and serum thymidine kinase 1 can further improve the sensitivity and specificity of lung cancer risk prediction; in addition, the short-term lung cancer risk prediction model in this application can detect high-risk factors for patients at an early stage and provide relevant intervention measures, thereby promoting early diagnosis and treatment, and will also bring the following benefits: Early detection and diagnosis: By using the short-term lung cancer risk prediction model, doctors can detect patients who may be at high risk earlier and conduct relevant examinations and diagnoses in a timely manner. This will help detect lung cancer early, provide earlier treatment opportunities, and improve patient survival rates; Personalized treatment plans: The prediction model can provide personalized treatment recommendations and plans for each patient based on the patient's individual characteristics and risk factors. This can not only improve the treatment effect, but also reduce unnecessary treatment processes or drug side effects; Efficient resource utilization: By using the risk prediction model of this application, medical resources can be more targeted and allocated to those patient groups, reducing the waste of resources, including beds, manpower, equipment, etc., and improving the efficiency of medical services in the face of a large number of patients; Cost reduction: Early diagnosis and treatment are usually more effective than late treatment, and can reduce the cost of subsequent treatment. In addition, through the use of risk prediction models, the health risks of lung cancer patients can be better managed and the economic burden on the medical system can be reduced.

[0012] Preferably, in the model training module, model training specifically includes: fitting a logistic regression model, and using LASSO regularization to constrain the parameters of the model.

[0013] More preferably, the use of LASSO regularization to constrain model parameters includes: controlling the sparsity of the model by adjusting the regularization parameters, thereby screening out the independent variable features that have the strongest impact on the dependent variable.

[0014] In this application, LASSO can automatically shrink the coefficients of some unimportant features to zero by adding an L1 regularization term, thereby achieving automatic variable selection. In contrast, the stepwise regression method requires manual setting of the thresholds for entering and exiting the model, which requires multiple iterations, while LASSO can screen out features that have a significant impact on the target variable at one time, which is simpler and more efficient.

[0015] Preferably, the risk prediction model for new lung cancer in patients without cancerous lung nodules within 3 years is:

[0016]

[0017] Wherein, the lp=-7.066+lp(serum thymidine kinase 1)+lp(pulmonary nodule radial)

[0018] (Linear prediction value) lp(pulmonary nodule radial direction) = 0.3392*pulmonary nodule radial direction;

[0019] (Linear prediction value) lp(serum thymidine kinase 1) = 0.3355*serum thymidine kinase 1.

[0020] By adopting the above technical solution and using the risk prediction model for new-onset lung cancer within 3 years in patients with cancer-free lung nodules obtained in this application, the risk probability of new-onset lung cancer within 3 years in patients with cancer-free lung nodules can be accurately calculated.

[0021] Preferably, in the sample acquisition and data collection module, the sample excludes individuals with cancer at baseline, individuals with a history of tumors, and individuals with a history of thoracic surgery at baseline;

[0022] and / or

[0023] In the sample acquisition and data collection module, the samples are selected from individuals who are 30 years old or above and have lung nodules detected for the first time, have received at least one follow-up, have no lung cancer or history of lung cancer, and have no history of thoracic surgery at baseline.

[0024] By adopting the above-mentioned technical means, the samples selected for modeling in this application exclude individuals with cancer at baseline, individuals with a history of tumors, and individuals with a history of thoracic surgery at baseline, so that this application can be applied to patients with lung nodules without a history of tumors rather than patients with existing tumors. The group of patients with lung nodules is large, with an incidence rate of 35.5%, and a certain risk of lung cancer (0.54%). Therefore, this application can help prevent a large number of new cases of lung cancer. In this application, selecting samples in which lung nodules are detected for the first time can avoid interference with lung cancer risk prediction due to interventions that may be received after the detection of nodules, such as anti-inflammatory treatment; in addition, selecting samples aged 30 years or above and selecting samples that have received at least one follow-up can ensure that the samples have follow-up information and can confirm whether there is a new diagnosis of lung cancer during the follow-up to avoid misclassification, thereby improving the accuracy of the model constructed by the construction device.

[0025] Preferably, in the model evaluation and verification module, when evaluating the predictive effectiveness of the trained model, the predictive effectiveness of the model is evaluated by evaluating the discrimination and calibration of the model;

[0026] Specifically, the discrimination is evaluated by the area under the receiver operating characteristic (ROC) curve (AUC) and its 95% CI; thereby making it more robust to class-imbalanced data sets, so that the results are not affected by class imbalance, and can better reflect the performance of the model (whereas usually in the case of class imbalance, indicators such as accuracy may be misleading); in addition, the results are not affected by threshold selection, and a more comprehensive model evaluation can be provided for different application scenarios and needs; finally, the discrimination is evaluated by the area under the receiver operating characteristic (ROC) curve (AUC) and its 95% CI, so that it can be directly applied to multi-category classification problems without the need for additional modification or conversion.

[0027] and / or

[0028] The calibration degree is evaluated by the ratio of the model predicted probability to the actual probability (E:O), the optimal calibration intercept (CITL) and the calibration slope, so as to provide multiple dimensions of evaluation, and thus a more comprehensive understanding of the calibration performance of the model; specifically, the ratio index can intuitively represent the degree of calibration of the model, the calibration slope can measure the change of the calibration performance of the model with the confidence level, and CITL can evaluate the calibration performance of the model on a large-scale data set; in addition, the calibration degree is evaluated by the ratio of the model predicted probability to the actual probability (E:O), the optimal calibration intercept (CITL) and the calibration slope, which can more accurately evaluate the calibration performance of the model, because each indicator has its unique advantages and limitations, and the comprehensive use of these indicators can make up for the shortcomings of each indicator and provide a more comprehensive and accurate evaluation result. In addition, these indicators are interpretable and can intuitively show the calibration performance of the model. For example, the ratio index can indicate the degree of consistency between the model's prediction and the actual probability, the calibration slope can show the change of the calibration performance of the model with the confidence level, and the reliability curve and reliability histogram provided by CITL can intuitively show the calibration performance of the model. Finally, using these metrics together can help detect potential problems in the model, such as overconfidence or over-caution. By comparing the ratio of predicted probability to actual probability, analyzing changes in the calibration slope, and evaluating the calibration performance of the model on large-scale datasets, model deficiencies can be discovered.

[0029] Preferably, in the model evaluation and verification module, a ten-fold cross validation is used to perform internal verification on the model; specifically, the following steps are performed:

[0030] Divide the data set consisting of sample data into ten subsets of equal size;

[0031] For each subset, take it as the test set in turn, and combine the remaining nine subsets as the training set;

[0032] Fit a logistic regression model on the training set;

[0033] The fitted model was used to predict the test set, and the performance indicators of the model on the test set were calculated, including the area under the receiver operating characteristic curve, the ratio of the model predicted probability to the actual probability, the optimal calibration intercept, and the calibration slope.

[0034] Repeat steps 1 to 3 for each subset, using it as a test set in turn. Use the fitted model to predict the test set until each subset is used as a test set, and record the performance indicators each time.

[0035] For each performance index, the mean and standard deviation of ten tests were calculated to evaluate the average performance and stability of the model.

[0036] By using the above technical means to verify the model, each subset is verified once, so as to make full use of the entire data set and reduce the bias introduced by improper data division. In addition, since each sample is used as part of the final evaluation result, the performance indicators of the model are more stable and reliable, which can better reflect the generalization ability of the model. In addition, by using the above method to continuously train and verify on different training sets and validation sets, it is possible to timely find that the model performs well on the training set but performs poorly on the validation set, so as to avoid overfitting the model to the data; finally, by using the above method to internally verify the model, the best parameter configuration can be found from 11 variables (i.e., the baseline parameters select the radial direction of lung nodules and serum thymidine kinase 1) to improve the model performance.

[0037] In the second aspect, the present application provides a lung cancer screening device that adopts the following technical solution:

[0038] A lung cancer screening device comprises a lung cancer screening model constructed by the lung cancer screening model construction device described in any of the above items.

[0039] In a third aspect, the present application provides an electronic device that adopts the following technical solution:

[0040] An electronic device comprises a memory and a processor, wherein the memory stores a lung cancer screening model constructed by a construction device for implementing a lung cancer screening model as described in any of the above items and can be loaded and executed by the processor.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium that adopts the following technical solution:

[0042] A computer-readable storage medium stores a lung cancer screening model constructed by a construction device for implementing a lung cancer screening model as described in any of the above items and capable of being loaded and executed by a processor.

[0043] In summary, the present application includes at least one of the following beneficial technical effects:

[0044] In this application, in particular, the baseline parameters (including lung nodule radial and serum thymidine kinase 1) are used as independent variables, and the risk of new lung cancer within 3 years after the baseline visit is used as the dependent variable for model training, so that it can be used for a large sample of Chinese people to predict the risk of lung cancer in patients with lung nodules without lung cancer. In other words, this application can be used to predict the probability of new lung cancer in the next 3 years instead of diagnosing existing lung cancer, because patients with lung nodules who currently do not have lung cancer also have the risk of developing lung cancer in the future as the disease progresses, and there is currently no technology to predict this. This application is the first practical tool that can predict short- and medium-term lung cancer risks. In addition, in this application, the model constructed using lung nodule radial and serum thymidine kinase 1 can further improve the sensitivity and specificity of lung cancer risk prediction;

[0045] The samples selected for modeling in this application exclude individuals with baseline cancer, individuals with a history of tumors, and individuals with a history of thoracic surgery at baseline, so that this application can be applied to patients with lung nodules without a history of tumors rather than patients with existing tumors. The group of patients with lung nodules is large, with an incidence rate of 35.5%, and a certain risk of lung cancer (0.54%). Therefore, this application can help prevent a large number of new lung cancer cases. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a block diagram of a device for constructing a lung cancer screening model according to an embodiment of the present application.

[0047] Figure 2 This is a flow chart for screening research samples in the experimental example.

[0048] Figure 3 Figure 1 is a schematic diagram of model construction and verification in the experimental example, where (a) is the LASSO result; (b) is the 3-year risk prediction model and the receiver operating characteristic (ROC) curve of each predictive factor; (c) is the calibration curve of the model in internal validation; and (d) is the ROC curve of the model in internal validation.

[0049] Figure 4 Threshold and decision curve diagram; where ac is the Youden index corresponding to the 3-year lung cancer risk prediction model, lung nodule radial and serum thymidine kinase 1 threshold, respectively; (d) is the model decision curve. DETAILED DESCRIPTION

[0050] The following is combined with Figure 1-Figure 4 This application is described in further detail.

[0051] The present application embodiment discloses a device for constructing a lung cancer screening model. Figure 1 , a device for constructing a lung cancer screening model, comprising:

[0052] A sample acquisition and data collection module, used to obtain samples from patients with lung nodules who do not have lung cancer, and to collect baseline parameters of the samples from patients with lung nodules;

[0053] The sample excluded individuals with cancer at baseline, individuals with a history of tumors, and individuals with a history of thoracic surgery at baseline;

[0054] and / or

[0055] In the sample acquisition and data collection module, the sample is selected from individuals who are 30 years old or older and have lung nodules detected for the first time, have received at least one follow-up, have no lung cancer or history of lung cancer (if there is no record of lung cancer during the follow-up period, the follow-up period is at least 3 years), and have no history of thoracic surgery at baseline;

[0056] The baseline parameters include lung nodule radial and serum thymidine kinase 1. Specifically, when training the model, the baseline parameters include: age, gender, smoking status, three serum biomarkers - serum thymidine kinase 1 (STK1p), carcinoembryonic antigen (CEA) and alpha-fetoprotein (AFP), four clinical characteristics - body mass index (BMI), hypertension, hyperglycemia and dyslipidemia and lung nodule radial;

[0057] The baseline parameters can be obtained by:

[0058] Age, sex, and smoking status were self-reported by patients and recorded by physicians. For patients without smoking status records, physicians' written notes were further reviewed. Patients whose smoking status could not be confirmed were not included in the study.

[0059] The three serum biomarkers extracted, including STK1p, CEA and AFP, are data at the baseline visit. STK1p can be detected by enhanced chemiluminescence (CIS-2) based on TK1-IgY polyclonal antibody. Serum CEA and AFP can be measured by chemiluminescence (ALINITY ci-series).

[0060] Four clinical characteristics, including BMI, hypertension, hyperglycemia, and dyslipidemia, where BMI (kg / m2) was calculated based on self-reported height and weight. Hypertension was defined according to the diagnosis record, high systolic blood pressure (≥130 mmHg), or high diastolic blood pressure (≥80 mmHg). Hyperglycemia was defined according to the diagnosis record, high fasting blood glucose (≥6.1 mmol / L), or high 2-hour postprandial blood glucose (≥7.8 mmol / L). Dyslipidemia was defined according to the diagnosis record or abnormal levels of total cholesterol (≥6.2 mmol / L), triglycerides (≥11.3 mmol / L), low-density lipoprotein cholesterol (≥4.14 mmol / L), or high-density lipoprotein cholesterol (<1.04 mmol / L).

[0061] LDCT scans were routinely performed and analyzed by hospital radiologists according to existing guidelines. The radial direction of pulmonary nodules could be obtained based on the LDCT report. The radial direction (mm) of the nodule was defined as the maximum diameter of the solid area for part-solid and solid nodules, or the maximum diameter for ground-glass nodules. When patients had multiple nodules, the maximum diameter of the largest nodule was used.

[0062] A model training module, for performing model training using the baseline parameters as independent variables and the risk of new lung cancer within 3 years after the baseline visit as a dependent variable;

[0063] Lung cancer was defined based on ICD-9 and ICD-10 codes recorded in the hospital information system. Individuals without codes were considered to have no lung cancer. For patients with new-onset lung cancer, the study endpoint was the date of lung cancer diagnosis. For patients without new-onset lung cancer, the study endpoint was the date of the last visit after the baseline visit.

[0064] Specifically, the model training includes: fitting a logistic regression model and using LASSO regularization to constrain the parameters of the model;

[0065] The fitting logistic regression model comprises: establishing a logistic regression model using a LASSO regression algorithm, wherein the goal of LASSO is to minimize the following loss function: L(β)=-loglikelihood(y,Xβ)+α*∑|β|; wherein loglikelihood(y,Xβ) represents the log-likelihood loss of logistic regression; α is a hyperparameter for controlling the regularization strength, and the optimal α value can be selected by cross-validation and other methods; ∑|β| represents the L1 regularization term of the parameter, and the model parameter β can be obtained by fitting the model using the selected optimal hyperparameter α value.

[0066] In this application, the LASSO regression algorithm is used to establish a logistic regression model, which has the following advantages:

[0067] 1. Feature selection: LASSO can realize automatic selection of feature variables by performing L1 regularization on the parameters so that the coefficients of some features tend to zero; this can reduce unimportant features in the model and improve the interpretability and generalization ability of the model; compared with existing methods such as stepwise regression, which requires manual setting of thresholds for entering and exiting the model and requires multiple iterations, LASSO in this application can screen out features that have a significant impact on the target variable at one time, which is simpler and more efficient.

[0068] 2. Model regularization: LASSO can control the complexity of the model by adjusting the regularization parameters to prevent overfitting; in addition, L1 regularization can make the model more sparse, reduce unnecessary features, and thus improve the generalization ability of the model. However, the existing stepwise regression rule does not have a clear sparsity feature.

[0069] 3. Dealing with collinearity: LASSO can effectively deal with the collinearity problem between features, that is, when there is a high correlation between the input features, LASSO can select one of the features as a representative and reduce the coefficients of other related features to zero, thereby reducing the impact of multicollinearity on the model and improving modeling efficiency. However, the stepwise regression rule cannot directly deal with multicollinearity and may select one of the related features and ignore other related features.

[0070] 4. Interpretability: LASSO's constraints on model parameters can make the model more interpretable. Since L1 regularization reduces the coefficients of some features to zero, it is clear which features have a greater or lesser impact on the target variable.

[0071] 5. Stability: LASSO can still fit the model stably with fewer samples and a large number of features, and has better performance.

[0072] 6. LASSO is very flexible and can be adjusted according to the characteristics of the specific problem and data set to obtain the best model performance and sparsity. However, the stepwise regression rule has no clear parameters to adjust.

[0073] In summary, compared with the stepwise regression method, the use of the LASSO regression algorithm to establish a logistic regression model in this application has the advantages of automatic selection of feature variables, model regularization, sparsity, handling of collinearity, interpretability and stability, which can help improve the performance and explanatory power of the logistic regression model.

[0074] The method of using LASSO regularization to constrain the parameters of the model includes: controlling the sparsity of the model by adjusting the regularization parameters, thereby screening out the independent variable features that have the strongest impact on the dependent variable. In the present application, the independent variable features that have the strongest impact on the dependent variable are pulmonary nodule radial and serum thymidine kinase 1;

[0075] Specifically, by using cross-validation and other techniques to select the best regularization parameter, and then by increasing the regularization parameter, the sparsity of the model can be increased, that is, the number of non-zero coefficients in the model can be reduced; conversely, reducing the regularization parameter can reduce the sparsity of the model, that is, increase the number of non-zero coefficients in the model, thereby screening out the independent variable characteristics that have the strongest impact on the dependent variable.

[0076] By adopting the above method, the coefficients of some unimportant features can be shrunk to zero, thus achieving variable selection. That is, LASSO can automatically screen out features that have a significant impact on the target variable, reduce redundant features in the model, and improve the interpretability of the model.

[0077] The model evaluation and verification module is used to evaluate the predictive performance and internally verify the trained model, thereby obtaining a risk prediction model for new lung cancer within 3 years in patients without cancerous lung nodules;

[0078] In this embodiment, the risk prediction model for new lung cancer in patients with no cancerous lung nodules within 3 years is obtained as follows:

[0079]

[0080] Wherein, the lp=-7.066+lp(serum thymidine kinase 1)+lp(pulmonary nodule radial)

[0081] (Linear prediction value) lp(pulmonary nodule radial direction) = 0.3392*pulmonary nodule radial direction;

[0082] (Linear prediction value) lp(serum thymidine kinase 1) = 0.3355*serum thymidine kinase 1.

[0083] In this embodiment, when evaluating the prediction performance of the trained model, the prediction performance is evaluated by evaluating the discrimination and calibration of the model;

[0084] Specifically, the discrimination is evaluated by the area under the receiver operating characteristic (ROC) curve (AUC) and its 95% CI; and / or the calibration is evaluated by the ratio of the model predicted probability to the actual probability (E:O), the optimal calibration intercept (CITL) and the calibration slope.

[0085] Calibration plots can be used to visually compare model-predicted probabilities to actual probabilities.

[0086] In this embodiment, a ten-fold cross validation is used to perform internal validation on the model; specifically, the following steps are performed:

[0087] S1, divide the data set consisting of sample data into ten subsets of equal size;

[0088] S2, for each subset, take it as the test set in turn, and combine the remaining nine subsets as the training set;

[0089] S3, fit the logistic regression model on the training set;

[0090] S4, use the fitted model to predict the test set and calculate the performance indicators of the model on the test set, including the area under the receiver operating characteristic curve, the ratio of the model predicted probability to the actual probability, the optimal calibration intercept and the calibration slope.

[0091] S5 repeats steps S2-S4 until each subset is used as a test set, and records the performance indicators each time;

[0092] S6, for each performance index, the mean and standard deviation of ten tests are calculated to evaluate the average performance and stability of the model.

[0093] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0094] This embodiment also discloses a lung cancer screening device. A lung cancer screening device includes a lung cancer screening model constructed by the lung cancer screening model construction device described in any one of the above items.

[0095] This embodiment also discloses an electronic device, comprising a memory and a processor, wherein the memory stores a lung cancer screening model constructed by the lung cancer screening model construction device as described in any one of the above items and can be loaded and executed by the processor.

[0096] The electronic device may be a desktop computer, a laptop computer, a cloud server or other electronic device, and the electronic device includes but is not limited to a processor and a memory. For example, the electronic device may also include input and output devices, a network access device, and a bus.

[0097] The processor in the present application may include one or more processing cores. The processor calls the data stored in the memory by running or executing the instructions, programs, code sets or instruction sets stored in the memory, and executes the various functions and processing data of the present application. The processor can be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller and a microprocessor. It is understandable that for different devices, the electronic device used to realize the above-mentioned processor function can also be other, and the embodiments of the present application are not specifically limited.

[0098] Among them, the memory can be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device, or it can be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital card (SD) or a flash memory card (FC) equipped on the electronic device, and the memory can also be a combination of an internal storage unit and an external storage device of the electronic device. The memory is used to store computer programs and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or is to be output, and this application does not impose any restrictions on this.

[0099] This embodiment also discloses a computer-readable storage medium. A computer-readable storage medium stores a lung cancer screening model constructed by the lung cancer screening model construction device as described in any one of the above items and capable of being loaded and executed by a processor.

[0100] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0101] Experimental example:

[0102] 1. Sample acquisition and data collection

[0103] The health management center provides routine health examinations, including chest LDCT scans and serological tests. In this experiment, 13,609 patients with pulmonary nodules from January 1, 2018 to December 31, 2021 were obtained from the hospital's electronic medical records (EMR) for retrospective screening; 6,841 (50.27%) of them met the inclusion criteria (such as Figure 2 =As shown) - Patients aged 30 years or older with first detection of pulmonary nodules, the baseline visit was defined as the visit at which the pulmonary nodules were first detected, the baseline visit had complete candidate predictive factor information, and the patient had received at least 1 follow-up; if the patient had no record of lung cancer during follow-up, the follow-up should be at least 3 years. The number of excluded people was 6768 (49.73%): 93 (0.68%) had a history of baseline tumor (cancer International Classification of Diseases (ICD)-9 or ICD-10 code) or thoracic surgery, 1,117 (8.21%) had incomplete baseline information, and 5,558 (40.84%) had no follow-up record. The median age of the 6841 study subjects (51 years (IQR = 45-59) vs. 53 years (45-61)) and the proportion of women (40.32% vs. 39.74%) were similar to those of the 13,609 patients before screening. The median follow-up time of the subjects was 3.00 years (IQR: 3.00-3.40). The age of the subjects was 31-91 years. During the follow-up period, 52 patients (0.76%) had new lung cancer. The age, gender, smoking and clinical characteristics of patients with and without new lung cancer were similar at baseline (as shown in Table 1). Patients with new lung cancer had higher nodule radial (p<0.001) and STK1p (p<0.001) at baseline than those without new lung cancer (as shown in Table 1), indicating that the selection of lung nodule radial and serum thymidine kinase 1 are effective factors for predicting lung cancer.

[0104] Table 1 Baseline characteristics of the subjects

[0105]

[0106]

[0107] Note: Data are medians (interquartile ranges) or n (%). For smoking indicators, data outside brackets are sample sizes, and data inside brackets are percentages. For radial nodules, data outside brackets are medians, and data inside brackets are quarterback ranges.

[0108] The P value represents the significance of the difference between the groups with and without new lung cancer, and p<0.05 represents a significant difference. For continuous variables such as age, the p value is obtained by the Wilcoxon rank sum test; for categorical variables such as gender, the p value is obtained by the chi-square test.

[0109] 1. Prediction model construction

[0110] The LASSO algorithm selected nodule radial direction and STK1p from 11 candidate indicators as predictors of the logistic model (e.g. Figure 3 a, as shown in Table 2).

[0111] Table 2

[0112]

[0113] Univariate and multivariate logistic regression analysis showed (Table 3) that both predictors were associated with the 3-year risk of lung cancer. The AUC of the model was 0.92 (95% CI: 0.87, 0.97), which was higher than 0.89 (0.84, 0.95) of the nodule radial and 0.74 (0.68, 0.80) of STK1p (P < 0.001) ( Figure 3 b). E:O (0.998), CITL (0.002) and calibration slope (0.95) of the model in internal validation ( Figure 3 c) and AUC (0.92) ( Figure 3 d) shows its excellent performance.

[0114] Table 3 Predictive factors screened by LASSO procedure to construct logistic regression model

[0115]

[0116]

[0117] Table 3 shows that the odds ratio of radial lung nodules and serum thymidine kinase 1 is greater than 1 and the p value is <0.05, indicating that these two factors are significantly positively correlated with lung cancer.

[0118] In logistic regression, a constant is a variable with a coefficient of 0. It is an independent variable with no dependent variable, and its coefficient is set to 0 in the model. Constants are often used in linear regression models to control the effects of other independent variables on the dependent variable.

[0119] The coefficient in logistic regression refers to the parameter used in the model to measure the degree of influence of the independent variable on the dependent variable. For binary logistic regression, the coefficient represents the influence of the independent variable on the log odds ratio of the dependent variable. Specifically, when the value of the independent variable increases by one unit, the log odds ratio will increase or decrease accordingly, depending on whether the coefficient is positive or negative.

[0120] Specifically, in logistic regression, the coefficients are obtained by maximum likelihood estimation. The specific steps are as follows: Assume there is a binary classification problem, where the target variable takes two values, usually represented as 0 and 1;

[0121] The linear combination is converted into a probability value using the logistic function (also called the sigmoid function). The formula of the logistic function is as follows: P(Y=1)=1 / (1+exp(-z));

[0122] Where P(Y=1) represents the probability that the target variable is equal to 1, exp represents the natural exponential function, and z represents the linear combination;

[0123] According to the principle of maximum likelihood estimation, select the coefficient that makes the observed data have the highest probability of occurrence. Among them, the goal of maximum likelihood estimation is to maximize the likelihood function of all samples, that is, to maximize the product of likelihood functions:

[0124] L(β)=P(y=1|x)^y*P(y=0|x)^(1-y),

[0125] Where β represents the coefficient of the model, x represents the feature vector, and y represents the actually observed target variable.

[0126] Take the logarithm of the likelihood function to facilitate calculation and optimization:

[0127] log(L(β))=Σ(y*log(P(y=1|x))+(1-y)*log(P(y=0|x))).

[0128] Using an optimization algorithm (e.g., gradient descent, Newton-Raphson, etc.), find the coefficients that maximize the log-likelihood function.

[0129] Based on Youden index (such as Figure 4 The optimal threshold of the model prediction probability is 0.06%. The sensitivity and specificity at this threshold are 88.5% (false negative rate is 11.5%) and 89.0% (false positive rate is 11.0%), respectively, which are higher than the optimal thresholds of using nodule radial or STK1p alone (as shown in Table 4). The decision curve of the model is shown in Figure 4 d. Within the threshold range of 0%-50%, the net benefit of model-based intervention is always higher than no intervention or intervention of all samples (i.e., the effect of intervention on the two factors selected in this application - "radial lung nodules and serum thymidine kinase 1" is higher than no intervention, or intervention of all factors; where intervention of all samples means that follow-up diagnosis and treatment, such as PET-CT, is provided for all samples). The 3-year probability of new lung cancer in the high-risk group with a predicted probability higher than 0.06% is higher than that in the low-risk group (OR = 44.75 [95% CI: 19.06, 105.05]; P < 0.001), indicating that the probability of high risk predicted by the corresponding model for people with new lung cancer is 44.75 times higher than that of low risk.

[0130] Table 4 Optimal thresholds

[0131]

[0132] Note: AUC = area under the receiver operating characteristic (ROC) curve; 95% CI = 95% confidence interval.

[0133] In specific implementation, a web application can be developed on the terminal based on the model, and then a probability assessment of new lung cancer within 3 years can be provided for individual patients with lung nodules based on the input predictive factors.

[0134] The technology of this application can be applied to scenarios such as primary medical institutions, physical examination centers, health management centers, and public health institutions for early screening of lung cancer.

[0135] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, all equivalent changes made according to the devices and principles of the present application should be included in the protection scope of the present application.

Claims

1. A device for constructing a lung cancer screening model, characterized in that: include: A sample acquisition and data collection module is used to obtain samples from patients with lung nodules who do not have lung cancer, and to collect baseline parameters of the samples from patients with lung nodules; the baseline parameters include radial lung nodules and serum thymidine kinase 1; A model training module, for performing model training using the baseline parameters as independent variables and the risk of new lung cancer within 3 years after the baseline visit as a dependent variable; The model evaluation and verification module is used to evaluate the predictive performance and internally verify the trained model, thereby obtaining a risk prediction model for new lung cancer within 3 years in patients without cancerous lung nodules; Among them, the risk prediction model for new lung cancer in patients with no cancerous lung nodules within 3 years is: Wherein, the lp=-7.066+lp(serum thymidine kinase 1)+lp(pulmonary nodule radial) lp(pulmonary nodule radial direction)=0.3392*pulmonary nodule radial direction; lp(serum thymidine kinase 1)=0.3355*serum thymidine kinase 1.

2. The device for constructing a lung cancer screening model according to claim 1, characterized in that: In the model training module, model training specifically includes: fitting a logistic regression model, and using LASSO regularization to constrain the parameters of the model.

3. The device for constructing a lung cancer screening model according to claim 2, characterized in that: The method of using LASSO regularization to constrain model parameters includes: controlling the sparsity of the model by adjusting the regularization parameters, thereby screening out the independent variable features that have the strongest impact on the dependent variable.

4. The device for constructing a lung cancer screening model according to claim 1, characterized in that: In the sample acquisition and data collection module, the sample excludes individuals with cancer at baseline, individuals with a history of tumors, and individuals with a history of thoracic surgery at baseline; and / or In the sample acquisition and data collection module, the samples are selected from individuals who are 30 years old or above and have lung nodules detected for the first time, have received at least one follow-up, have no lung cancer or history of lung cancer, and have no history of thoracic surgery at baseline.

5. The device for constructing a lung cancer screening model according to claim 1, characterized in that: In the model evaluation and verification module, when evaluating the predictive performance of the trained model, the predictive performance of the model is evaluated by evaluating the discrimination and calibration of the model; Specifically, the discrimination was evaluated by the area under the receiver operating characteristic curve and its 95% CI; and / or The calibration was assessed by the ratio of the model predicted probability to the actual probability, the optimal calibration intercept and the calibration slope.

6. The device for constructing a lung cancer screening model according to claim 1, characterized in that: In the model evaluation and verification module, a ten-fold cross validation is used to perform internal verification of the model; specifically, the following steps are performed: Divide the data set consisting of sample data into ten subsets of equal size; For each subset, take it as the test set in turn, and combine the remaining nine subsets as the training set; Fit a logistic regression model on the training set; Use the fitted model to predict the test set and calculate the performance indicators of the model on the test set, including the area under the receiver operating characteristic curve, the ratio of the model predicted probability to the actual probability, the optimal calibration intercept and the calibration slope; Repeat steps 1 to 3 for each subset, using it as a test set in turn. Use the fitted model to predict the test set until each subset is used as a test set, and record the performance indicators each time. For each performance index, the mean and standard deviation of ten tests were calculated to evaluate the average performance and stability of the model.

7. A lung cancer screening device, characterized in that: A lung cancer screening model constructed by the device for constructing a lung cancer screening model as described in any one of claims 1-6.

8. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a lung cancer screening model that can be loaded and executed by the processor to implement the lung cancer screening model constructed by the construction device as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The device stores a lung cancer screening model that can be loaded and executed by a processor and is constructed by a construction device for implementing a lung cancer screening model as described in any one of claims 1 to 6.

Images