• Politics
  • Diversity, equity and inclusion
  • Financial Decision Making
  • Telehealth
  • Patient Experience
  • Leadership
  • Point of Care Tools
  • Product Solutions
  • Management
  • Technology
  • Healthcare Transformation
  • Data + Technology
  • Safer Hospitals
  • Business
  • Providers in Practice
  • Mergers and Acquisitions
  • AI & Data Analytics
  • Cybersecurity
  • Interoperability & EHRs
  • Medical Devices
  • Pop Health Tech
  • Precision Medicine
  • Virtual Care
  • Health equity

Risk Prediction Model Helps Identify Risk of Developing Lung Cancer


Catching lung cancer early could lead to better treatment and management of care.

human anatomy

A risk prediction model could help researchers determine if patients with a lung nodule have a high or low risk of developing lung cancer, according to a study published in the journal Cancer Prevention Research.

The model performed with a 73% sensitivity and 81% specificity, according to the researchers.

Patients classified as high-risk had more than 14 times the risk of developing lung cancer.

“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,” said Barbara Nemesure, Ph.D., director of the Cancer Prevention and Control Program and the Lung Cancer Program at Stony Brook Cancer Center in New York.

The researchers analyzed data from 2,924 patients with a lung nodule assessed at the Stony Brook Cancer Center’s Lung Cancer Evaluation Center between Jan. 2002 and Dec. 2015. If patients had a history of lung cancer or received a diagnosis within six months of the initial consultation, they were excluded. Only 171 patients developed lung cancer during this period.

The research team randomly divided the patients into two groups: discovery (1,469) and replication (1,455).

In the replication group, the researchers computed concordance to indicate predictive accuracy. Researchers calculated risk scores using linear predictions and the Youden index helped identify high- versus low-risk patients. Cumulative lung cancer incidence was examined for both risk groups.

Researchers collected clinical and radiological data to develop a risk prediction model. Through multivariable analyses, the research team identified that age, smoking pack-years, history of cancer, the presence of chronic obstructive pulmonary disease and nodule characteristics like size and the presence of speculation, could best predict who in the discovery group would develop lung cancer.

Researchers found that when they applied the risk score to the replication group, the model discriminated cancer risk with a sensitivity of 73% and specificity of 81%.

“Lung cancer is often asymptomatic in early stages, and the identification of high-risk individuals is a major priority,” Nemesure said.

The study authors wrote that the model could help assist physicians in managing the care and treating patients who are at increased risk of developing lung cancer.

Get the best insights in digital health directly to your inbox.


New Tool Identifies High-Risk Patients with COPD

FDA Clears COPD Wearable Aimed at Reducing Hospital Admissions

Telehealth Rehab Program for Patients with COPD Reduces 30-day Readmissions

Related Videos
Image: Ron Southwick, Chief Healthcare Executive
George Van Antwerp, MBA
Edmondo Robinson, MD
Craig Newman
© 2024 MJH Life Sciences

All rights reserved.