Explainable Machine Learning Model to Prediction EGFR Mutation in Lung Cancer
ObjectivesThe aim of this study is to determine whether the clinical features including blood markers can establish an explainable machine learning model to predict epidermal growth factor receptor (EGFR) mutation in lung cancer.MethodsWe retrospectively analyzed 7,413 patients with lung adenocarcin...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-06-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.924144/full |
| _version_ | 1811241438938136576 |
|---|---|
| author | Ruiyuan Yang Xingyu Xiong Haoyu Wang Weimin Li Weimin Li Weimin Li Weimin Li |
| author_facet | Ruiyuan Yang Xingyu Xiong Haoyu Wang Weimin Li Weimin Li Weimin Li Weimin Li |
| author_sort | Ruiyuan Yang |
| collection | DOAJ |
| description | ObjectivesThe aim of this study is to determine whether the clinical features including blood markers can establish an explainable machine learning model to predict epidermal growth factor receptor (EGFR) mutation in lung cancer.MethodsWe retrospectively analyzed 7,413 patients with lung adenocarcinoma (LA) diagnosed by gene sequencing in West China Hospital of the Sichuan University from April 2015 to June 2019. The machine learning algorithms (MLAs) included logistic regression (LR), random forest (RF), LightGBM, support vector machine (SVM), multi-layer perceptron (MLP), extreme gradient boosting (XGBoost), and decision tree (DT). Demographic characteristics, personal history, and blood markers were taken into. The area under the receiver operating characteristic curve (AUC) and SHapley Additive exPlanation (SHAP) value were used to explain the prediction models.ResultsOf the 7,413 patients with LA (47.6%), 3,527 were identified with EGFR mutation; RF achieved greatest performance in predicting EGFR mutation AUC [0.771, 95% confidence interval (CI): 0.770, 0.772], which was like XGBoost with AUC (0.740, 95% CI: 0.739, 0.741). The five most influential features were smoking consumption, sex, cholesterol, age, and albumin globulin ratio. The SHAP summary and dependence plot have been used to explain the affection of the 12 features to this model and how a single feature influences the output, respectively.ConclusionWe established EGFR mutation prediction models by MLAs and revealed that the RF was preferred, AUC (0.771, 95% CI: 0.770, 0.772), which was better than the traditional models. Therefore, the artificial intelligence–based MLA predicting model may become a practical tool to guide in diagnosis and therapy of LA. |
| first_indexed | 2024-04-12T13:36:11Z |
| format | Article |
| id | doaj.art-15a66990b2b345f4b1d41ae45a73ea4c |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-12T13:36:11Z |
| publishDate | 2022-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-15a66990b2b345f4b1d41ae45a73ea4c2022-12-22T03:30:59ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-06-011210.3389/fonc.2022.924144924144Explainable Machine Learning Model to Prediction EGFR Mutation in Lung CancerRuiyuan Yang0Xingyu Xiong1Haoyu Wang2Weimin Li3Weimin Li4Weimin Li5Weimin Li6Department of Respiratory and Critical Care Medicine, West China Hospital, Sichuan University, Chengdu, ChinaDepartment of Respiratory and Critical Care Medicine, West China Hospital, Sichuan University, Chengdu, ChinaDepartment of Respiratory and Critical Care Medicine, West China Hospital, Sichuan University, Chengdu, ChinaDepartment of Respiratory and Critical Care Medicine, West China Hospital, Sichuan University, Chengdu, ChinaInstitute of Respiratory Health Frontiers Science Center for Disease-related Molecular Network, West China Hospital, Sichuan University, Chengdu, ChinaPrecision Medicine Center, Precision Medicine Key Laboratory of Sichuan Province, West China Hospital, Sichuan University, Chengdu, ChinaThe Research Units of West China, Chinses Academy of Medical Sciences, West China Hospital, Chengdu, ChinaObjectivesThe aim of this study is to determine whether the clinical features including blood markers can establish an explainable machine learning model to predict epidermal growth factor receptor (EGFR) mutation in lung cancer.MethodsWe retrospectively analyzed 7,413 patients with lung adenocarcinoma (LA) diagnosed by gene sequencing in West China Hospital of the Sichuan University from April 2015 to June 2019. The machine learning algorithms (MLAs) included logistic regression (LR), random forest (RF), LightGBM, support vector machine (SVM), multi-layer perceptron (MLP), extreme gradient boosting (XGBoost), and decision tree (DT). Demographic characteristics, personal history, and blood markers were taken into. The area under the receiver operating characteristic curve (AUC) and SHapley Additive exPlanation (SHAP) value were used to explain the prediction models.ResultsOf the 7,413 patients with LA (47.6%), 3,527 were identified with EGFR mutation; RF achieved greatest performance in predicting EGFR mutation AUC [0.771, 95% confidence interval (CI): 0.770, 0.772], which was like XGBoost with AUC (0.740, 95% CI: 0.739, 0.741). The five most influential features were smoking consumption, sex, cholesterol, age, and albumin globulin ratio. The SHAP summary and dependence plot have been used to explain the affection of the 12 features to this model and how a single feature influences the output, respectively.ConclusionWe established EGFR mutation prediction models by MLAs and revealed that the RF was preferred, AUC (0.771, 95% CI: 0.770, 0.772), which was better than the traditional models. Therefore, the artificial intelligence–based MLA predicting model may become a practical tool to guide in diagnosis and therapy of LA.https://www.frontiersin.org/articles/10.3389/fonc.2022.924144/fullEGFR mutationlung cancerpredictionmachine learningSHAP value |
| spellingShingle | Ruiyuan Yang Xingyu Xiong Haoyu Wang Weimin Li Weimin Li Weimin Li Weimin Li Explainable Machine Learning Model to Prediction EGFR Mutation in Lung Cancer Frontiers in Oncology EGFR mutation lung cancer prediction machine learning SHAP value |
| title | Explainable Machine Learning Model to Prediction EGFR Mutation in Lung Cancer |
| title_full | Explainable Machine Learning Model to Prediction EGFR Mutation in Lung Cancer |
| title_fullStr | Explainable Machine Learning Model to Prediction EGFR Mutation in Lung Cancer |
| title_full_unstemmed | Explainable Machine Learning Model to Prediction EGFR Mutation in Lung Cancer |
| title_short | Explainable Machine Learning Model to Prediction EGFR Mutation in Lung Cancer |
| title_sort | explainable machine learning model to prediction egfr mutation in lung cancer |
| topic | EGFR mutation lung cancer prediction machine learning SHAP value |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.924144/full |
| work_keys_str_mv | AT ruiyuanyang explainablemachinelearningmodeltopredictionegfrmutationinlungcancer AT xingyuxiong explainablemachinelearningmodeltopredictionegfrmutationinlungcancer AT haoyuwang explainablemachinelearningmodeltopredictionegfrmutationinlungcancer AT weiminli explainablemachinelearningmodeltopredictionegfrmutationinlungcancer AT weiminli explainablemachinelearningmodeltopredictionegfrmutationinlungcancer AT weiminli explainablemachinelearningmodeltopredictionegfrmutationinlungcancer AT weiminli explainablemachinelearningmodeltopredictionegfrmutationinlungcancer |