Potential to improve early detection of lung cancer through expansion of focused and opportunistic screening approaches: a scoping review focusing on potential expansion of screening risk factors and adoption of artificial intelligence models.
Authors
Affiliations (8)
Affiliations (8)
- Department of Clinical Oncology, The Chinese University of Hong Kong, Hong Kong, China.
- Department of Surgery (Division of Thoracic Surgery), McMaster University, Hamilton, Canada.
- Department of Chest Diseases, Faculty of Medicine, Hacettepe Universitesi, Ankara, Turkey.
- Department of Medicine, NYU Langone Health Perlmutter Cancer Center, New York City, NY, USA.
- Department of Surgery (Division of Thoracic Surgery), Kaiser Permanente Northern California, Oakland, CA, USA.
- Department of Surgery, University of California San Francisco Medical School of Medicine, San Francisco, USA.
- Department of Clinical Science, Kaiser Permanente Bernard J. Tyson School of Medicine, Pasadena, USA.
- Department of Internal Medicine, National Taiwan University, Taipei, Taiwan.
Abstract
Low-dose computerized tomography (LDCT) is the gold standard for lung cancer (LC) screening, but access is hindered by strict eligibility criteria and limited infrastructure in low/middle-income countries. A combination of approaches, including expanded screening eligibility criteria and artificial intelligence (AI), could improve detection of early LC in patients excluded by current screening criteria. A scoping review was conducted (PubMed, Cochrane library, congresses) to explore two potentially complementary approaches to enhance LC screening. The first identified LC risk factors and their potential inclusion in expanded screening criteria, allowing more people at risk to become eligible for screening; the second examined studies involving AI-augmented imaging (CXR or LDCT) to improve workflow, triage, and opportunistic nodule detection. Several robustly evidenced risk factors for LC were identified that are not included in current screening programs; widening of eligibility criteria could be considered based on local risk profile but requires further research to demonstrate benefit. Opportunistic use of AI-tools to assess incidental chest images may identify patients with pulmonary nodules requiring further investigation but their role in population-level LC screening requires prospective validation in diverse healthcare systems.