Simple Risk Model Could Help Predict Lung Cancer Risk in Female Non-Smokers

By Leah Lawrence - Last Updated: August 29, 2022

Researchers from China have developed a lung cancer risk prediction nomogram for female non-smokers, according to data presented at the IASLC World Conference on Lung Cancer.

Lanwei Guo, Henan Cancer Hospital, China, and colleagues looked at data from 151,834 patients in Henan province, China, from October 2013 to October 2019 from the Cancer Screening Program in Urban China (CanSPUC). They were attempting to develop and validate a simple and non-invasive model that could assess and stratify lung cancer risk in female non-smokers in China.

Included patients were randomly divided into the training (n=75,917) and validation n=(75,917) sets. Related risk factors were identified through multivariable Cox regression analysis, followed by establishment of risk prediction nomogram. Discrimination [area under the curve (AUC)] and calibration were further performed to assess the validation of risk prediction nomogram in the training set, and then validated by the validation set.

Elder age, history of chronic respiratory disease (P=.004), first-degree family history of lung cancer, menopause, and history of benign breast disease (P=.026) were the independent risk factors for lung cancer.

Using these five variables, Dr. Guo and colleagues created one-year, three-year, and five-year lung cancer risk prediction nomograms. The area under the curve was 0.762, 0.718, and 0.703 for the one-, three-, and five-year lung cancer risk in the training set, respectively.

In the validation set, the model showed a good predictive discrimination, and the area under the curve was 0.646, 0.658, and 0.650 for the one-, three-, and five-year lung cancer risk.

“We developed and validated a simple and non-invasive lung cancer risk model in female non-smokers that can be applied to identify and triage patients at high risk for developing lung cancer in female non-smokers,” Dr. Guo reported.

Further prospective studies are required to validate the model in external populations, they noted.