Method for predicting effect of immunotherapy for lung cancer in advanced stage and related device

Abstract

This application discloses a method and related equipment for predicting the efficacy of immunotherapy in advanced lung cancer, belonging to the field of deep learning technology. The method includes: acquiring transcriptome sequencing data of the user to be predicted; inputting the transcriptome sequencing data into an immunotherapy efficacy prediction model to obtain an immunotherapy efficacy score output by the model; and determining the predicted immunotherapy efficacy result for the user based on the immunotherapy efficacy score output by the model. The immunotherapy efficacy prediction model is constructed based on the Cox proportional hazards model ridge regression algorithm, the random survival forest algorithm, and the extreme gradient boosting tree algorithm. This application improves the performance and stability of the prediction model by combining these algorithms, thereby enhancing the accuracy of predicting the efficacy of immunotherapy in advanced lung cancer.

Description

Technical Field

[0001] This application relates to the field of deep learning technology, and in particular to a method and related equipment for predicting the efficacy of immunotherapy for advanced lung cancer. Background Technology

[0002] Currently, for patients with inoperable advanced lung cancer, the treatment effects of traditional chemotherapy and radiotherapy are usually not ideal, while immunotherapy can significantly improve the prognosis.

[0003] In related technologies, PD-L1 expression and tumor mutational burden (TMB) are commonly used to predict advanced lung cancer patients who may benefit from immunotherapy. However, in practical applications, it has been found that traditional prediction methods suffer from low accuracy due to challenges posed by the spatiotemporal heterogeneity of tumors and different detection platforms.

[0004] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0005] This application provides a method and related equipment for predicting the efficacy of immunotherapy in advanced lung cancer, which can further improve the performance and stability of the prediction model, thereby improving the accuracy of predicting the efficacy of immunotherapy in advanced lung cancer.

[0006] On the one hand, embodiments of this application provide a method for predicting the efficacy of immunotherapy in advanced lung cancer, the method comprising the following steps: Obtain transcriptome sequencing data of the user to be predicted; The transcriptome sequencing data is input into the immunotherapy efficacy prediction model to obtain the immunotherapy efficacy score output by the immunotherapy efficacy prediction model. Based on the immunotherapy efficacy score output by the immunotherapy efficacy prediction model, the immunotherapy efficacy prediction result for the user to be predicted is determined. The immunotherapy efficacy prediction model is built on the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm.

[0007] Optionally, obtaining the transcriptome sequencing data of the user to be predicted includes: Obtain the raw transcriptome sequencing data of the user to be predicted; Based on the gene set of target lung cancer-mediated neural injury, feature extraction was performed on the original transcriptome sequencing data; Based on the feature extraction results, the transcriptome sequencing data of the user to be predicted is used. The target lung cancer-mediated nerve injury gene set was obtained by a combination of univariate linear regression analysis and univariate Cox regression analysis.

[0008] Optionally, inputting the transcriptome sequencing data into the immunotherapy efficacy prediction model to obtain the immunotherapy efficacy score output by the immunotherapy efficacy prediction model includes: The transcriptome sequencing data is input into the immunotherapy efficacy prediction model; The immune treatment efficacy score is calculated by each of the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm in the immunotherapy efficacy prediction model. The immunotherapy efficacy scores obtained by each algorithm are comprehensively calculated using a soft voting algorithm, and this comprehensive score is used as the output of the immunotherapy efficacy prediction model.

[0009] Optionally, determining the predicted immunotherapy effect for the user based on the immunotherapy effect score output by the immunotherapy effect prediction model includes: Obtain the threshold for predicting the efficacy of immunotherapy; If the immunotherapy efficacy score output by the immunotherapy efficacy prediction model is greater than or equal to the immunotherapy efficacy prediction threshold, the immunotherapy efficacy prediction result for the user to be predicted is determined to be high risk. If the immunotherapy efficacy score output by the immunotherapy efficacy prediction model is less than the immunotherapy efficacy prediction threshold, the immunotherapy efficacy prediction result for the user to be predicted is determined to be low risk.

[0010] Optionally, the immunotherapy efficacy prediction model is trained based on the following steps: Acquire multiple historical transcriptome sequencing data, and obtain the immunotherapy effects corresponding to the multiple historical transcriptome sequencing data; A training dataset is constructed by using each of the historical transcriptome sequencing data as a sample and the immunotherapy effect corresponding to each of the historical transcriptome sequencing data as the sample label. The immunotherapy efficacy prediction model is pre-trained using the training dataset.

[0011] Optionally, after pre-training the immunotherapy efficacy prediction model using the training dataset, the method further includes: Build a validation dataset; Based on the validation dataset, the immunotherapy efficacy prediction model was evaluated using receiver operating characteristic (ROC) curves. The predictive performance of the immunotherapy efficacy prediction model is determined based on the area under the receiver operating characteristic curve.

[0012] On the other hand, embodiments of this application provide a device for predicting the efficacy of immunotherapy in advanced lung cancer, the device comprising: The data acquisition module is used to acquire transcriptome sequencing data of the user to be predicted; The model evaluation module is used to input the transcriptome sequencing data into the immunotherapy efficacy prediction model to obtain the immunotherapy efficacy score output by the immunotherapy efficacy prediction model. The efficacy prediction module is used to determine the predicted efficacy of immunotherapy for the user to be predicted based on the immunotherapy efficacy score output by the immunotherapy efficacy prediction model. The immunotherapy efficacy prediction model is built on the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm.

[0013] On the other hand, embodiments of this application provide an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0014] On the other hand, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0015] On the other hand, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0016] This application's embodiments construct a prediction model by combining the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm, thereby further improving the performance and stability of the prediction model and thus enhancing the accuracy of predicting the efficacy of immunotherapy for advanced lung cancer. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the implementation environment for a method for predicting the efficacy of immunotherapy in advanced lung cancer, as provided in an embodiment of this application. Figure 2 This is a flowchart illustrating a method for predicting the efficacy of immunotherapy in advanced lung cancer, as provided in an embodiment of this application. Figure 3 This is a schematic diagram of a gene set for screening target lung cancer-mediated nerve damage provided in an embodiment of this application; Figure 4 This is a schematic diagram of the receiver operating characteristic curve of an immunotherapy efficacy prediction model provided in an embodiment of this application; Figure 5 This is a schematic diagram of a survival analysis curve for advanced lung cancer provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of a device for predicting the efficacy of immunotherapy for advanced lung cancer provided in an embodiment of this application; Figure 7 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0020] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0022] Currently, for patients with inoperable advanced lung cancer, the treatment effects of traditional chemotherapy and radiotherapy are usually not ideal, while immunotherapy can significantly improve the prognosis.

[0023] In related technologies, PD-L1 expression and tumor mutational burden (TMB) are commonly used to predict advanced lung cancer patients who may benefit from immunotherapy. However, in practical applications, it has been found that traditional prediction methods suffer from low accuracy due to challenges posed by the spatiotemporal heterogeneity of tumors and different detection platforms.

[0024] In view of this, this application provides a method and related equipment for predicting the efficacy of immunotherapy in advanced lung cancer. By combining the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm and extreme gradient boosting tree algorithm to construct a prediction model, the performance and stability of the prediction model are further improved, thereby improving the accuracy of predicting the efficacy of immunotherapy in advanced lung cancer.

[0025] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0026] The specific implementation methods of the embodiments of this application will be described in detail below with reference to the accompanying drawings. First, a method for predicting the efficacy of immunotherapy for advanced lung cancer provided in the embodiments of this application will be described with reference to the accompanying drawings.

[0027] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the implementation environment for a method for predicting the efficacy of immunotherapy in advanced lung cancer, as provided in this application embodiment. In this implementation environment, the main hardware and software components involved include a terminal processor 110 and a server 120.

[0028] Specifically, the terminal processor 110 may be equipped with a control program for predicting the efficacy of immunotherapy for advanced lung cancer, and the server 120 serves as the backend server for this control program. The terminal processor 110 and the backend server 120 are connected. The method for predicting the efficacy of immunotherapy for advanced lung cancer provided in this embodiment can be executed on the terminal processor 110 side.

[0029] Server 120 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0030] In addition, server 120 can also be a node server in a blockchain network.

[0031] The terminal processor 110 and the server 120 can establish a communication connection via a wireless network. This wireless network uses standard communication technologies and / or protocols. The network can be the Internet or any other network, including but not limited to a Local Area Network (LAN), Metropolitan Area Network (MAN), Wide Area Network (WAN), mobile, or any combination of wireless networks, private networks, or virtual private networks. Furthermore, these hardware and software components can use the same or different communication connection methods; this application does not impose specific limitations in this regard.

[0032] Of course, this is understandable. Figure 1 The implementation environment described in this application is only one of the optional application scenarios for the method of predicting the efficacy of immunotherapy for advanced lung cancer provided in this embodiment. The actual application is not fixed. Figure 1 The software and hardware environment shown is not specifically limited in this application.

[0033] like Figure 2 As shown, Figure 2 This is a flowchart illustrating a method for predicting the efficacy of immunotherapy in advanced lung cancer, as provided in an embodiment of this application, including but not limited to steps 100 to 300.

[0034] Step 100: Obtain transcriptome sequencing data of the user to be predicted.

[0035] In this embodiment of the application, the user to be predicted can be an advanced patient with non-small cell lung cancer (NSCLC). The transcriptome sequencing data of the user to be predicted is obtained and used as input data for the subsequent immunotherapy efficacy prediction model.

[0036] Transcriptome sequencing data is a collection of all transcripts in the cells of the user to be predicted, including messenger RNA, ribosomal RNA, transfer RNA and non-coding RNA, which can be used as a means to study gene expression.

[0037] Specifically, as an optional implementation, obtaining the transcriptome sequencing data of the user to be predicted includes: Obtain the raw transcriptome sequencing data of the user to be predicted; Based on the gene set of target lung cancer-mediated neural injury, feature extraction was performed on the original transcriptome sequencing data; Based on the feature extraction results, the transcriptome sequencing data of the user to be predicted is used. The target lung cancer-mediated nerve injury gene set was obtained by a combination of univariate linear regression analysis and univariate Cox regression analysis.

[0038] In practical applications, after obtaining the raw transcriptome sequencing data of the user to be predicted, features can be extracted from the raw transcriptome sequencing data based on the pre-screened modified target lung cancer-mediated neural injury gene set, and the feature extraction results can be used as the transcriptome sequencing data of the user to be predicted.

[0039] Specifically, the gene set for target lung cancer-mediated nerve injury can be obtained through a combination of univariate linear regression analysis and univariate Cox regression analysis.

[0040] In practical applications, please refer to Figure 3 , Figure 3 This is a schematic diagram of a screening gene set for target lung cancer-mediated nerve injury provided in an embodiment of this application. Treatment regimen data of historical advanced lung cancer patients are obtained and divided into a chemotherapy group and a combination therapy group (i.e., chemotherapy combined with immunotherapy). Univariate linear regression analysis (e.g., univariate logistic regression) is performed on both the chemotherapy and combination therapy groups to detect the association between gene expression and binary efficacy. Univariate Cox regression analysis is also performed to detect the association between gene expression and time events. This identifies gene set A that is significant only in the chemotherapy group, gene set B that is significant in both the chemotherapy and combination therapy groups, and gene set C that is significant only in the combination therapy group. For example, the significance threshold P-value can be set to 0.1. Gene set C, which is significant only in the combination therapy group, is selected as having a statistically significant correlation with efficacy / prognosis in patients receiving immunotherapy combination therapy, but not the same correlation in patients receiving chemotherapy alone. This set is considered the target lung cancer-mediated nerve injury gene set (L-CINI gene set).

[0041] For example, the traditional tumor-mediated neural injury gene set contains 46 genes. However, through the combined screening based on univariate linear regression analysis and univariate Cox regression analysis in this application, nine CINI genes closely related to the efficacy of lung cancer immunotherapy can be effectively extracted. These genes are COX18, JUN, KAT5, KCNMB4, PEAR1, RPL21P134, SLC25A25, SNORA11, and SNORD9. By accurately including these nine CINI genes closely related to the efficacy of lung cancer immunotherapy, more closely related feature data can be extracted from the original transcriptome sequencing data of the users to be predicted. This data can be used as input data for subsequent models, simplifying the evaluation process of biomarkers, reducing computational costs, and making it easier to promote and apply in clinical practice.

[0042] Step 200: Input the transcriptome sequencing data into the immunotherapy efficacy prediction model to obtain the immunotherapy efficacy score output by the immunotherapy efficacy prediction model; The immunotherapy efficacy prediction model is built on the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm.

[0043] In this embodiment of the application, the obtained transcriptome sequencing data is input into the immunotherapy efficacy prediction model, which then calculates the immunotherapy efficacy score based on the input data.

[0044] The immunotherapy efficacy prediction model is built upon the Cox proportional hazards model ridge regression algorithm, the random survival forest algorithm, and the extreme gradient boosting tree algorithm. Specifically, the Cox proportional hazards model ridge regression (RCOX) algorithm, by combining the Cox proportional hazards model with ridge regression (L2 regularization), has the advantage of strong clinical interpretability. It also solves the problems of coefficient instability and overfitting of the traditional Cox model under high-dimensional data by introducing L2 regularization. The random survival forest algorithm (RSF) is a non-parametric algorithm model based on Bagging, which has the advantages of no assumption constraints and adaptability to complex data. It can identify nonlinear key features that are difficult for the RCOX algorithm to capture. The extreme gradient boosting tree algorithm (XGBoost) is a gradient boosting algorithm model based on Boosting, which has powerful second-order optimization capabilities and can increase fitting and generalization capabilities through stepwise correction.

[0045] Therefore, by combining three complementary algorithms, this application can further improve the performance and stability of the prediction model, which helps to accurately identify whether patients with advanced lung cancer can benefit from immunotherapy, thereby improving the accuracy of treatment effect prediction.

[0046] Specifically, as an optional implementation, the step of inputting the transcriptome sequencing data into an immunotherapy efficacy prediction model to obtain an immunotherapy efficacy score output by the immunotherapy efficacy prediction model includes: The transcriptome sequencing data is input into the immunotherapy efficacy prediction model; The immune treatment efficacy score is calculated by each of the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm in the immunotherapy efficacy prediction model. The immunotherapy efficacy scores obtained by each algorithm are comprehensively calculated using a soft voting algorithm, and this comprehensive score is used as the output of the immunotherapy efficacy prediction model.

[0047] In this embodiment of the application, after the transcriptome sequencing data is input into the immunotherapy efficacy prediction model, the immunotherapy efficacy score of the user to be predicted is calculated by the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm and extreme gradient boosting tree algorithm in the immunotherapy efficacy prediction model. Then, the immunotherapy efficacy score output results of the three algorithms are averaged and combined by the soft voting algorithm to be used as the final immunotherapy efficacy score of the immunotherapy efficacy prediction model and output.

[0048] In practical applications, the immunotherapy efficacy prediction model is trained based on the following steps: Acquire multiple historical transcriptome sequencing data, and obtain the immunotherapy effects corresponding to the multiple historical transcriptome sequencing data; A training dataset is constructed by using each of the historical transcriptome sequencing data as a sample and the immunotherapy effect corresponding to each of the historical transcriptome sequencing data as the sample label. The immunotherapy efficacy prediction model is pre-trained using the training dataset.

[0049] In this embodiment, multiple historical transcriptome sequencing data and their corresponding immunotherapy effects from the treatment process of patients with advanced lung cancer can be obtained. Then, any historical transcriptome sequencing data is used as a sample, and the immunotherapy effect of that data is used as the sample label to form a training sample. Multiple training samples are acquired to construct a training dataset, which is then input into the immunotherapy effect prediction model for training, thus completing the pre-training process of the immunotherapy effect prediction model.

[0050] The pre-training process of the immunotherapy efficacy prediction model can be considered complete when a predetermined number of pre-training iterations are reached; or it can be considered complete when the training output of the immunotherapy efficacy prediction model converges.

[0051] In practical applications, after constructing the training dataset, it can be further divided into a training set and a validation dataset, with the training set accounting for 80% of the training dataset and the validation dataset accounting for 20%. The training set is used for model training, and the validation dataset is used for model validation.

[0052] Furthermore, after completing the pre-training process of the immunotherapy efficacy prediction model, the predictive performance of the model can be evaluated by plotting the receiver operating characteristic (ROC) curve and determining the area under the receiver operating characteristic (AUC). Specifically, after pre-training the immunotherapy efficacy prediction model using the training dataset, the method further includes: Build a validation dataset; Based on the validation dataset, the immunotherapy efficacy prediction model was evaluated using receiver operating characteristic (ROC) curves. The predictive performance of the immunotherapy efficacy prediction model is determined based on the area under the receiver operating characteristic curve.

[0053] In practical applications, please refer to Figure 4 , Figure 4 This is a schematic diagram of the receiver operating characteristic (ROC) curve of an immunotherapy efficacy prediction model provided in this application embodiment. The predictive performance of the immunotherapy efficacy prediction model can be determined by the area under the curve (AUC) of multiple receiver operating characteristic (ROC) curves.

[0054] For example, such as Figure 4 As shown, Figure 4The diagram shows the ROC curves of an immunotherapy efficacy prediction model with progression-free survival (PFS) as the endpoint. Specificity is plotted on the horizontal axis, sensitivity on the vertical axis, and AUCs at different time points are indicated. Specifically, the prediction performance can be divided into the prediction performance on the training dataset and the prediction performance on the validation dataset. On the training dataset, the black slant line in the ROC curve serves as the baseline. The blue ROC curve corresponds to a time point of 6 months with "enrollment / treatment start" as the zero point, and the red ROC curve corresponds to a time point of 12 months with "enrollment / treatment start" as the zero point. The AUCs under different ROC curves can be calculated separately; specifically, the AUC of the blue ROC curve is 0.868, and the AUC of the red ROC curve is 0.859.

[0055] Furthermore, on the validation dataset, the black slanted line in the ROC curve serves as the baseline, the blue ROC curve corresponds to a time point of 6 months with "enrollment / treatment start" as the zero point, and the red ROC curve corresponds to a time point of 12 months with "enrollment / treatment start" as the zero point. The AUC under different ROC curves can be calculated separately, specifically, the AUC of the blue ROC curve is 0.841, and the AUC of the red ROC curve is 0.745.

[0056] Therefore, compared with the publicly available data from current traditional prediction and evaluation methods, such as the AUC of 0.583 for PD-L1 expression and 0.595 for tumor mutation burden (TMB) expression, the immunotherapy efficacy prediction model provided in this application has better predictive performance on immunotherapy efficacy. By combining the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm to construct the prediction model, the performance and stability of the prediction model are further improved, thereby improving the accuracy of predicting the efficacy of immunotherapy in advanced lung cancer.

[0057] In practical applications, overall survival (OS) can also be selected as the endpoint to plot the ROC curve of the immunotherapy efficacy prediction model.

[0058] Further, please refer to Figure 5 , Figure 5 This is a schematic diagram of a survival analysis curve for advanced lung cancer provided in an embodiment of this application. This application can also, based on a validation dataset, plot the survival analysis curve results for an immunotherapy efficacy prediction model for advanced lung cancer, using progression-free survival (PFS) as the endpoint. Figure 5The text shows the progression-free survival (PFS) data. Survival analysis curves with progression-free survival (PFS) as the endpoint (Kaplan-Meier method) are plotted with patient follow-up time on the horizontal axis and survival probability on the vertical axis, highlighting different treatment regimens and predicted outcomes of different immunotherapies. Specifically, the red survival curve corresponds to patients with a high-risk predicted outcome of immunotherapy and receiving chemotherapy alone; the green curve corresponds to patients with a low-risk predicted outcome of immunotherapy and receiving chemotherapy alone; the cyan curve corresponds to patients with a high-risk predicted outcome of immunotherapy and receiving combination therapy (chemotherapy combined with immunotherapy); and the purple curve corresponds to patients with a low-risk predicted outcome of immunotherapy and receiving combination therapy (chemotherapy combined with immunotherapy). The survival probability is determined by the highest purple curve, indicating that patients with a low-risk predicted outcome of immunotherapy and receiving combination therapy (chemotherapy combined with immunotherapy) have a better chance of survival and can benefit from immunotherapy, thus providing data support for clinical decision-making. Patients with low clinical immunotherapy efficacy scores are more likely to benefit from first-line immunotherapy combined with chemotherapy.

[0059] In practical applications, overall survival (OS) can also be selected as the endpoint to plot the survival analysis curve of advanced lung cancer in the immunotherapy efficacy prediction model.

[0060] Step 300: Based on the immunotherapy efficacy score output by the immunotherapy efficacy prediction model, determine the immunotherapy efficacy prediction result for the user to be predicted.

[0061] In this embodiment of the application, the immunotherapy efficacy score output by the immunotherapy efficacy prediction model can be used as a basis for determining the immunotherapy efficacy prediction result for the user to be predicted.

[0062] Specifically, as an optional implementation, determining the predicted immunotherapy effect for the user based on the immunotherapy effect score output by the immunotherapy effect prediction model includes: Obtain the threshold for predicting the efficacy of immunotherapy; If the immunotherapy efficacy score output by the immunotherapy efficacy prediction model is greater than or equal to the immunotherapy efficacy prediction threshold, the immunotherapy efficacy prediction result for the user to be predicted is determined to be high risk. If the immunotherapy efficacy score output by the immunotherapy efficacy prediction model is less than the immunotherapy efficacy prediction threshold, the immunotherapy efficacy prediction result for the user to be predicted is determined to be low risk.

[0063] Specifically, the threshold for predicting the effect of immunotherapy can be obtained first. For example, it can be set according to the specific usage requirements of the scenario, or it can be obtained by obtaining the immunotherapy effect score corresponding to each sample in the training data and sorting it according to the numerical value, and selecting the median value as the threshold for predicting the effect of immunotherapy.

[0064] Furthermore, by comparing the numerical relationship between the immunotherapy efficacy prediction threshold and the immunotherapy efficacy score output by the immunotherapy efficacy prediction model, the predicted immunotherapy efficacy result for the user to be predicted is determined.

[0065] Specifically, if the immunotherapy efficacy prediction model outputs an immunotherapy efficacy score greater than or equal to the immunotherapy efficacy prediction threshold, the predicted immunotherapy efficacy for the user is determined to be high-risk, meaning that receiving immunotherapy may not achieve the expected survival benefit. Furthermore, if the immunotherapy efficacy prediction model outputs an immunotherapy efficacy score less than the immunotherapy efficacy prediction threshold, the predicted immunotherapy efficacy for the user is determined to be low-risk, meaning that receiving immunotherapy may result in a better survival benefit.

[0066] Therefore, compared to traditional prediction methods that rely on PD-L1 expression and tumor mutational burden (TMB) to predict advanced lung cancer patients who can benefit from immunotherapy but suffer from low accuracy due to the spatiotemporal heterogeneity of tumors and challenges from different detection platforms, this application constructs a prediction model by combining the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm. This further improves the performance and stability of the prediction model. By using the immunotherapy efficacy score output by the immunotherapy efficacy prediction model as a judgment criterion, combined with a pre-set immunotherapy efficacy prediction threshold, the prediction result of the immunotherapy efficacy of the user can be quickly determined, thus determining whether the user can benefit from immunotherapy. This helps clinicians to more easily develop personalized treatment plans for advanced lung cancer patients.

[0067] Please see Figure 6 , Figure 6 This is a schematic diagram of a device for predicting the efficacy of immunotherapy for advanced lung cancer according to an embodiment of this application. This application also provides a device for predicting the efficacy of immunotherapy for advanced lung cancer, which can implement the above-mentioned method for predicting the efficacy of immunotherapy for advanced lung cancer. The device includes: Data acquisition module 610 is used to acquire transcriptome sequencing data of the user to be predicted; The model evaluation module 620 is used to input the transcriptome sequencing data into the immunotherapy efficacy prediction model to obtain the immunotherapy efficacy score output by the immunotherapy efficacy prediction model. The effect prediction module 630 is used to determine the prediction result of the immunotherapy effect for the user to be predicted based on the immunotherapy effect score output by the immunotherapy effect prediction model. The immunotherapy efficacy prediction model is built upon the Cox proportional hazards model, ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm. It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0068] Please see Figure 7 , Figure 7 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. The electronic device includes: The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 702 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702 and is called and executed by the processor 701 using the methods described in the embodiments of this application. The input / output interface 703 is used to implement information input and output; The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704); The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0069] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0070] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0071] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0072] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0073] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0074] This application provides a method and related equipment for predicting the efficacy of immunotherapy for advanced lung cancer. It constructs a prediction model by combining the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm, thereby further improving the performance and stability of the prediction model and thus improving the accuracy of predicting the efficacy of immunotherapy for advanced lung cancer.

[0075] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0076] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0077] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0078] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0079] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0080] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0081] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0082] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0083] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0084] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0085] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for predicting the efficacy of immunotherapy in advanced lung cancer, characterized in that, The method includes the following steps: Obtain transcriptome sequencing data of the user to be predicted; The transcriptome sequencing data is input into the immunotherapy efficacy prediction model to obtain the immunotherapy efficacy score output by the immunotherapy efficacy prediction model. Based on the immunotherapy efficacy score output by the immunotherapy efficacy prediction model, the immunotherapy efficacy prediction result for the user to be predicted is determined. The immunotherapy efficacy prediction model is built on the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm.

2. The method according to claim 1, characterized in that, The acquisition of transcriptome sequencing data of the user to be predicted includes: Obtain the raw transcriptome sequencing data of the user to be predicted; Based on the gene set of target lung cancer-mediated neural injury, feature extraction was performed on the original transcriptome sequencing data; Based on the feature extraction results, the transcriptome sequencing data of the user to be predicted is used. The target lung cancer-mediated nerve injury gene set was obtained by a combination of univariate linear regression analysis and univariate Cox regression analysis.

3. The method according to claim 1, characterized in that, The step of inputting the transcriptome sequencing data into the immunotherapy efficacy prediction model to obtain the immunotherapy efficacy score output by the immunotherapy efficacy prediction model includes: The transcriptome sequencing data is input into the immunotherapy efficacy prediction model; The immune treatment efficacy score is calculated by each of the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm in the immunotherapy efficacy prediction model. The immunotherapy efficacy scores obtained by each algorithm are comprehensively calculated using a soft voting algorithm, and this comprehensive score is used as the output of the immunotherapy efficacy prediction model.

4. The method according to claim 1, characterized in that, The process of determining the predicted immunotherapy effect for the user based on the immunotherapy effect score output by the immunotherapy effect prediction model includes: Obtain the threshold for predicting the efficacy of immunotherapy; If the immunotherapy efficacy score output by the immunotherapy efficacy prediction model is greater than or equal to the immunotherapy efficacy prediction threshold, the immunotherapy efficacy prediction result for the user to be predicted is determined to be high risk. If the immunotherapy efficacy score output by the immunotherapy efficacy prediction model is less than the immunotherapy efficacy prediction threshold, the immunotherapy efficacy prediction result for the user to be predicted is determined to be low risk.

5. The method according to claim 1, characterized in that, The immunotherapy efficacy prediction model was trained based on the following steps: Acquire multiple historical transcriptome sequencing data, and obtain the immunotherapy effects corresponding to the multiple historical transcriptome sequencing data; A training dataset is constructed by using each of the historical transcriptome sequencing data as a sample and the immunotherapy effect corresponding to each of the historical transcriptome sequencing data as the sample label. The immunotherapy efficacy prediction model is pre-trained using the training dataset.

6. The method according to claim 5, characterized in that, After pre-training the immunotherapy efficacy prediction model using the training dataset, the method further includes: Build a validation dataset; Based on the validation dataset, the immunotherapy efficacy prediction model was evaluated using receiver operating characteristic (ROC) curves. The predictive performance of the immunotherapy efficacy prediction model is determined based on the area under the receiver operating characteristic curve.

7. A device for predicting the efficacy of immunotherapy in advanced lung cancer, characterized in that, The device includes: The data acquisition module is used to acquire transcriptome sequencing data of the user to be predicted; The model evaluation module is used to input the transcriptome sequencing data into the immunotherapy efficacy prediction model to obtain the immunotherapy efficacy score output by the immunotherapy efficacy prediction model. The efficacy prediction module is used to determine the predicted efficacy of immunotherapy for the user to be predicted based on the immunotherapy efficacy score output by the immunotherapy efficacy prediction model. The immunotherapy efficacy prediction model is built on the Cox proportional hazards model ridge regression algorithm, random survival forest algorithm, and extreme gradient boosting tree algorithm.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images