Prediction of lung cancer risk in Chinese population with genetic‐environment factor using extreme gradient boosting
Abstract Background Detecting early‐stage lung cancer is critical to reduce the lung cancer mortality rate; however, existing models based on germline variants perform poorly, and new models are needed. This study aimed to use extreme gradient boosting to develop a predictive model for the early dia...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-12-01
|
| Series: | Cancer Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/cam4.4800 |
| _version_ | 1827198031476293632 |
|---|---|
| author | Yutao Li Zixiu Zou Zhunyi Gao Yi Wang Man Xiao Chang Xu Gengxi Jiang Haijian Wang Li Jin Jiucun Wang Huai Zhou Wang Shicheng Guo Junjie Wu |
| author_facet | Yutao Li Zixiu Zou Zhunyi Gao Yi Wang Man Xiao Chang Xu Gengxi Jiang Haijian Wang Li Jin Jiucun Wang Huai Zhou Wang Shicheng Guo Junjie Wu |
| author_sort | Yutao Li |
| collection | DOAJ |
| description | Abstract Background Detecting early‐stage lung cancer is critical to reduce the lung cancer mortality rate; however, existing models based on germline variants perform poorly, and new models are needed. This study aimed to use extreme gradient boosting to develop a predictive model for the early diagnosis of lung cancer in a multicenter case–control study. Materials and Methods A total of 974 cases and 1005 controls in Shanghai and Taizhou were recruited, and 61 single nucleotide polymorphisms (SNPs) were genotyped. Multivariate logistic regression was used to calculate the association between signal SNPs and lung cancer risk. Logistic regression (LR) and extreme gradient boosting (XGBoost) algorithms, a large‐scale machine learning algorithm, were adopted to build the lung cancer risk model. In both models, 10‐fold cross‐validation was performed, and model predictive performance was evaluated by the area under the curve (AUC). Results After FDR adjustment, TYMS rs3819102 and BAG6 rs1077393 were significantly associated with lung cancer risk (p < 0.05). For lung cancer risk prediction, the model predicted only with epidemiology attained an AUC of 0.703 for LR and 0.744 for XGBoost. Compared with the LR model predicted only with epidemiology, further adding SNPs and applying XGBoost increased the AUC to 0.759 (p < 0.001) in the XGBoost model. BAG6 rs1077393 was the most important predictor among all SNPs in the lung cancer prediction XGBoost model, followed by TERT rs2735845 and CAMKK1 rs7214723. Further stratification in lung adenocarcinoma (ADC) showed a significantly elevated performance from 0.639 to 0.699 (p = 0.009) when applying XGBoost and adding SNPs to the model, while the best model for lung squamous cell carcinoma (SCC) prediction was the LR model predicted with epidemiology and SNPs (AUC = 0.833), compared with the XGBoost model (AUC = 0.816). Conclusion Our lung cancer risk prediction models in the Chinese population have a strong predictive ability, especially for SCC. Adding SNPs and applying the XGBoost algorithm to the epidemiologic‐based logistic regression risk prediction model significantly improves model performance. |
| first_indexed | 2024-04-11T06:08:33Z |
| format | Article |
| id | doaj.art-5345a1dea55f48e280c4b3c5e39f5ef9 |
| institution | Directory Open Access Journal |
| issn | 2045-7634 |
| language | English |
| last_indexed | 2025-03-21T10:10:33Z |
| publishDate | 2022-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Cancer Medicine |
| spelling | doaj.art-5345a1dea55f48e280c4b3c5e39f5ef92024-07-04T06:51:08ZengWileyCancer Medicine2045-76342022-12-0111234469447810.1002/cam4.4800Prediction of lung cancer risk in Chinese population with genetic‐environment factor using extreme gradient boostingYutao Li0Zixiu Zou1Zhunyi Gao2Yi Wang3Man Xiao4Chang Xu5Gengxi Jiang6Haijian Wang7Li Jin8Jiucun Wang9Huai Zhou Wang10Shicheng Guo11Junjie Wu12School of Life Sciences Fudan University Shanghai ChinaSchool of Life Sciences Fudan University Shanghai ChinaCompany 6 of Basic Medical School Navy Military Medical University Shanghai ChinaSchool of Life Sciences Fudan University Shanghai ChinaDepartment of Biochemistry and Molecular Biology Hainan Medical University Haikou ChinaClinical College of Xiangnan University Chenzhou ChinaDepartment of Thoracic Surgery the First Affiliated Hospital of Naval Medical University (Second Military Medical University) Shanghai ChinaSchool of Life Sciences Fudan University Shanghai ChinaSchool of Life Sciences Fudan University Shanghai ChinaSchool of Life Sciences Fudan University Shanghai ChinaDepartment of Laboratory Diagnosis the First Affiliated Hospital of Naval Medical University (Second Military Medical University) Shanghai ChinaSchool of Life Sciences Fudan University Shanghai ChinaSchool of Life Sciences Fudan University Shanghai ChinaAbstract Background Detecting early‐stage lung cancer is critical to reduce the lung cancer mortality rate; however, existing models based on germline variants perform poorly, and new models are needed. This study aimed to use extreme gradient boosting to develop a predictive model for the early diagnosis of lung cancer in a multicenter case–control study. Materials and Methods A total of 974 cases and 1005 controls in Shanghai and Taizhou were recruited, and 61 single nucleotide polymorphisms (SNPs) were genotyped. Multivariate logistic regression was used to calculate the association between signal SNPs and lung cancer risk. Logistic regression (LR) and extreme gradient boosting (XGBoost) algorithms, a large‐scale machine learning algorithm, were adopted to build the lung cancer risk model. In both models, 10‐fold cross‐validation was performed, and model predictive performance was evaluated by the area under the curve (AUC). Results After FDR adjustment, TYMS rs3819102 and BAG6 rs1077393 were significantly associated with lung cancer risk (p < 0.05). For lung cancer risk prediction, the model predicted only with epidemiology attained an AUC of 0.703 for LR and 0.744 for XGBoost. Compared with the LR model predicted only with epidemiology, further adding SNPs and applying XGBoost increased the AUC to 0.759 (p < 0.001) in the XGBoost model. BAG6 rs1077393 was the most important predictor among all SNPs in the lung cancer prediction XGBoost model, followed by TERT rs2735845 and CAMKK1 rs7214723. Further stratification in lung adenocarcinoma (ADC) showed a significantly elevated performance from 0.639 to 0.699 (p = 0.009) when applying XGBoost and adding SNPs to the model, while the best model for lung squamous cell carcinoma (SCC) prediction was the LR model predicted with epidemiology and SNPs (AUC = 0.833), compared with the XGBoost model (AUC = 0.816). Conclusion Our lung cancer risk prediction models in the Chinese population have a strong predictive ability, especially for SCC. Adding SNPs and applying the XGBoost algorithm to the epidemiologic‐based logistic regression risk prediction model significantly improves model performance.https://doi.org/10.1002/cam4.4800Chinese populationextreme gradient boostinglung cancerrisk modelsingle nucleotide polymorphisms |
| spellingShingle | Yutao Li Zixiu Zou Zhunyi Gao Yi Wang Man Xiao Chang Xu Gengxi Jiang Haijian Wang Li Jin Jiucun Wang Huai Zhou Wang Shicheng Guo Junjie Wu Prediction of lung cancer risk in Chinese population with genetic‐environment factor using extreme gradient boosting Cancer Medicine Chinese population extreme gradient boosting lung cancer risk model single nucleotide polymorphisms |
| title | Prediction of lung cancer risk in Chinese population with genetic‐environment factor using extreme gradient boosting |
| title_full | Prediction of lung cancer risk in Chinese population with genetic‐environment factor using extreme gradient boosting |
| title_fullStr | Prediction of lung cancer risk in Chinese population with genetic‐environment factor using extreme gradient boosting |
| title_full_unstemmed | Prediction of lung cancer risk in Chinese population with genetic‐environment factor using extreme gradient boosting |
| title_short | Prediction of lung cancer risk in Chinese population with genetic‐environment factor using extreme gradient boosting |
| title_sort | prediction of lung cancer risk in chinese population with genetic environment factor using extreme gradient boosting |
| topic | Chinese population extreme gradient boosting lung cancer risk model single nucleotide polymorphisms |
| url | https://doi.org/10.1002/cam4.4800 |
| work_keys_str_mv | AT yutaoli predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT zixiuzou predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT zhunyigao predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT yiwang predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT manxiao predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT changxu predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT gengxijiang predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT haijianwang predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT lijin predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT jiucunwang predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT huaizhouwang predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT shichengguo predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting AT junjiewu predictionoflungcancerriskinchinesepopulationwithgeneticenvironmentfactorusingextremegradientboosting |