Early detection and diagnosis remains an effective yet challenging approach to improve the clinical outcome of patients with cancer. Low-dose computed tomography screening has been suggested to improve the diagnosis of lung cancer in high-risk individuals. To make screening more efficient, it is necessary to identify individuals who are at high risk.
We conducted a case-control study to develop a predictive model for identification of such high-risk individuals. Clinical data from 705 lung cancer patients and 988 population-based controls were used for the development and evaluation of the model. Associations between environmental variants and lung cancer risk were analyzed with a logistic regression model. The predictive accuracy of the model was determined by calculating the area under the receiver operating characteristic curve and the optimal operating point.
Our results indicate that lung cancer risk factors included older age, male gender, lower education level, family history of cancer, history of chronic obstructive pulmonary disease, lower body mass index, smoking cigarettes, a diet with less seafood, vegetables, fruits, dairy products, soybean products and nuts, a diet rich in meat, and exposure to pesticides and cooking emissions. The area under the curve was 0.8851 and the optimal operating point was obtained. With a cutoff of 0.35, the false positive rate, true positive rate, and Youden index were 0.21, 0.87, and 0.66, respectively.
The risk prediction model for lung cancer developed in this study could discriminate high-risk from low-risk individuals.
Tumori 2015; 101(1): 16 - 23
Article Type: ORIGINAL RESEARCH ARTICLE
AuthorsXu Wang, Kewei Ma, Jiuwei Cui, Xiao Chen, Lina Jin, Wei Li
- • Accepted on 09/09/2014
- • Available online on 14/02/2015
- • Published in print on 20/03/2015
This article is available as full text PDF.
- Wang, Xu [PubMed] [Google Scholar] 1
- Ma, Kewei [PubMed] [Google Scholar] 1
- Cui, Jiuwei [PubMed] [Google Scholar] 1
- Chen, Xiao [PubMed] [Google Scholar] 1
- Jin, Lina [PubMed] [Google Scholar] 2
- Li, Wei [PubMed] [Google Scholar] 1, * Corresponding Author (email@example.com)
Cancer Center, First Hospital of Jilin University, Changchun, Jilin Province - China
School of Public Health, Jilin University, Changchun, Jilin Province - China