Artificial intelligence (AI) and Machine Learning ( ML) are reshaping medical research and clinical practice, especially when it comes to Lung Cancer (Lei, 2024). AI/ML is increasingly integrated across various stages of lung cancer care, from detection to treatment. For example, deep learning models applied to low-dose computed tomography (CT) scans have demonstrated expert-level accuracy and reduced diagnostic errors compared to radiologists (Ardilla et. al, 2019). Among smokers, ML was more accurate in predicting early diagnosis than standard screening among eligible population (Gould et al, 2020).
This promising technology can potentially improve lung cancer patients' survival rates.
In the U.S, Lung cancer is the leading cause of mortality among all cancers, and the third most common type of cancer in the U.S (CDC, 2024). The US Preventive Services Task Force recommends yearly lung cancer screenings in high-risk individuals. This is defined as people who have a 20 pack year or more of smoking history, and smoke now or have quit within the past 15 years, and are between 50 and 80 years of age. The only recommended screening test for cancer is a low-dose CT scan. There are risks involved in screening-which include tests that indicate lung cancer is present when it is not ( false positive), overdiagnose (cases that never would of caused a problem but are present), effects of radiation causing cancer in otherwise healthy paitent-for these reasons screening is only recommended in adults who have a high risk of developing lung cancer (CDC, 2024).
Lung Cancer staging is based on three factors: tumor size, regional lymph node involvement, and metastasis- how much the cancer has spread( American Lung Association, 2025). Stages range from 0-5, with zero being the earliest stage, where the cancer is in the top lining of the lung or bronchus and not spread, to stage five, where it is most advanced and has spread to other body areas. Survival rates for lung cancer are low, with only 28.4 % surviving after five years (American Lung Association, 2025). However, the burden of late-stage detection can be significantly reduced with the help of AI, offering hope for improved outcomes.
In a Lung Cancer Screening Trial, AI/ML Models have been shown to outperform radiologists with a 94 % area under the curve, decreasing false positive rates by 11% compared to radiologists (Ardilla et. al, 2019). Deep learning models have also been studied and shown to hold promise in predicting responses in immunotherapy in patients with non-small cell lung cancer, working to improve clinical outcomes by refining patient selection and guiding treatment (Rakaee et al, 2024).