Advertisement

Risk-Prediction Model Aims to Predict Incident Lung Cancer in Patients With a Pulmonary Nodule

Advertisement

Key Points

  • When the risk score was applied to the replication cohort, the researchers found that the model could discriminate cancer risk with a sensitivity and specificity of 73% and 81%, respectively.
  • Compared with individuals in the low-risk category, those in the high-risk category had more than 14 times the risk of developing lung cancer.

A risk-prediction model developed using clinical and radiologic features could stratify individuals presenting with a lung nodule as having a high or low risk for lung cancer, according to a study published by Nemesure et al in Cancer Prevention Research.

“While lung nodules are not uncommon, a major challenge in the field is determining which nodules will progress to cancer,” said first author Barbara Nemesure, PhD, Director of the Cancer Prevention and Control Program and the Lung Cancer Program at Stony Brook Cancer Center. “Through our model, we can identify which individuals with lung nodules should be closely monitored, so that we can catch the disease at an early stage and ultimately reduce the burden of lung cancer deaths,” she added.

Prior studies in this area include a retrospective analysis of patients with lung cancer and an analysis of high-risk individuals undergoing screening for the disease, noted Dr. Nemesure. The current study aimed to prospectively predict lung cancer incidence among the general population presenting with a lung nodule.

Methods

Researchers analyzed data from 2,924 patients presenting with a lung nodule assessed at the Stony Brook Cancer Center’s Lung Cancer Evaluation Center between January 2002 and December 2015. Patients were excluded if they had a history of lung cancer or if they were diagnosed with lung cancer within 6 months of the initial consultation.

Participants were randomly assigned to discovery (1,469 patients) and replication (1,455 patients) cohorts. Among them, 171 developed lung cancer over the 13-year period.

Clinical and radiologic data were collected to develop a risk-prediction model. Using multivariable analyses, the researchers found that the combined variables of age, smoking pack-years, personal history of cancer, the presence of chronic obstructive pulmonary disease, as well as nodule characteristics such as size, the presence of spiculation, and the presence of a ground-glass opacity could best predict who would develop lung cancer among the discovery cohort. These factors were combined to develop an overall risk score to stratify patients into high- and low-risk categories.

Risk Score Performance

When the risk score was applied to the replication cohort, the researchers found that the model could discriminate cancer risk with a sensitivity and specificity of 73% and 81%, respectively. Compared with individuals in the low-risk category, those in the high-risk category had more than 14 times the risk of developing lung cancer.

“Even though the majority of lung nodules do not progress to cancer, it is still vitally important that patients seek follow-up care,” noted Dr. Nemesure. This was a single-center study that may not be generalizable to the public at large, she concluded.

Disclosure: This study was supported by the Stony Brook Cancer Center. For full disclosures of the study authors, visit cancerpreventionresearch.aacrjournals.org.

The content in this post has not been reviewed by the American Society of Clinical Oncology, Inc. (ASCO®) and does not necessarily reflect the ideas and opinions of ASCO®.


Advertisement

Advertisement



Advertisement