JMIR Publications

ABSTRACT

Background:

It is believed that smoking is not the cause of approximately 53% of lung cancer instances diagnosed in females globally.

Objective:

The goal was to build and validate a straightforward model that excluded any invasive procedures and could evaluate and categorize the risk of lung cancer in Chinese non-smoking females.

Methods:

A population-based cancer monitoring initiative in urban China, a study was carried out with a vast population base and an immense numbers of people participating in it. The training set and the validation set were both constructed using a random distribution of the data. Following the identification of associated risk factors by multivariable Cox regression analysis, a predictive nomogram was developed. The standardization of the risk predicting nomogram was further evaluated by performing differentiation (area under the curve, or AUC), as well as standardization of the training set. This was followed by the standardization of the nomogram on the validation set.

Results:

In sum, there were 151,834 individuals who signed up to take part in the survey. Both the training set (consisting of 75,917) and the validation set (consisting of 75,917) were comprised of randomly selected participants. Potential predictors for lung cancer included age, history of chronic respiratory disease, first-degree family history of lung cancer, menopause, and history of benign breast disease. We displayed 1-year, 3-year, and 5-year lung cancer risk predicting nomograms employing these five factors. In the training set, the 1-, 3-, and 5-year lung cancer risk AUCs were 0.762, 0.718, and 0.703, respectively. In the validation set, the model showed a good predictive discrimination.

Conclusions:

We designed and validated a simple and noninvasive lung cancer risk model for nonsmoking females. This approach could be used to detect and classify female nonsmokers at high risk for getting lung cancer.