Machine Learning Model Predicts Lung Cancer Risk

A machine learning model that includes data on a patient’s age and smoking history can predict lung cancer risk, as well as the need for lung cancer screening, according to a new study published in PLOS Medicine. 

Lung cancer kills more people worldwide than any other cancer, and patients have a poor prognosis if the disease is not detected early. Screening for lung cancer among people at high-risk could reduce lung cancer deaths by nearly a quarter, but the ideal way to identify the high-risk population remains unclear. The current standard-of-care model of lung cancer risk requires 17 variables, few of which are routinely available in electronic health records.

In this study, researchers analyzed data on 216,714 ever-smokers from the UK Biobank cohort and 26,616 ever-smokers participating in the US National Lung Screening trial to develop a risk model. The machine learning model they constructed used 3 predictors—age, smoking duration, and pack-years—to discern the odds of both developing lung cancer and dying of the disease over the next 5 years.

The analysis found that the machine learning model predicted lung cancer incidence with an 83.9% sensitivity and lung cancer deaths with an 85.5% sensitivity. The researchers noted that all versions of the new model had a higher sensitivity than the currently used risk prediction formulas and comparable specificity.

“We know that screening for those who have a high chance of developing lung cancer can save lives,” said Thomas Callender, PhD, of University College London and the study’s lead author. “With machine learning, we’ve been able to substantially simplify how we work out who is at high risk, presenting an approach that could be an exciting step in the direction of widespread implementation of personalized screening to detect many diseases early.”