Research on lung cancer treatment often relies on administrative claims data, which can lack the detailed clinical information necessary for accurate analysis.

Shane Neibart, MD, MS

This limitation poses significant challenges, as improper classification can lead to misguided treatment decisions, skewed outcomes, and potential disparities. A recent study, led by Shane Neibart, MD, MS, and Miranda Lam, MD, MBA, addresses the challenge of classifying radiation therapy (RT). Specifically, it focuses on identifying treatment sites and intentions (curative vs palliative) for lung cancer patients using claims databases. 

The study analyzed 3,846 RT episodes among 3,491 lung cancer patients, finding that algorithms based on claims data worked well in identifying treatments when using intensity modulated radiation therapy (IMRT) and stereotactic body radiation therapy (SBRT).

Miranda Lam, MD, MBA

However, these methods were less effective in classifying 3D conformal radiation therapy (3DCRT). This difference highlights the need for more precise ways of understanding and analyzing different radiation treatments. 

The authors emphasize that accurate classification through these validated algorithms can mitigate misclassification bias, strengthening the validity of health services and comparative effectiveness research.

This advancement will enable more precise evaluations of healthcare disparities and treatment outcomes in lung cancer patients, ultimately improving patient care.

Published in JCO Clinical Cancer Informatics on January 16, 2026| Read the paper: “Validation of Claims-Based Algorithms to Classify Thoracic Radiation Therapy Claims” 

Summary reviewed by: Shane Neibart, MD, MS, lead author