The silent killer: lung cancer and the emerging role of AI in early detection

Lung cancer remains one of the deadliest forms of cancer globally, claiming millions of lives each year. 

According to the World Health Organisation (WHO), the global cancer burden is expected to soar to over 35 million new cases annually by 2050—a shocking 77% increase from 2022, when 20 million cases were reported. Of these, lung cancer alone is projected to account for 2.5 million cases, or 12.4% of the total cancer burden worldwide. 

Tobacco use continues to be the primary cause, responsible for nearly two-thirds of all lung cancer deaths. 

Despite widespread awareness of the dangers of smoking, many remain unaware of other deadly risk factors, particularly air pollution, which is emerging as a major contributor to lung cancer. 

WHO estimates that approximately 29% of lung cancer deaths globally are linked to air pollution, and for non-smokers, this risk is particularly alarming. Nearly half of all non-smokers diagnosed with lung cancer are thought to have developed the disease due to exposure to polluted air.

The situation is especially critical in regions like South Asia, where air quality has reached dangerous levels. In 2023, Bangladesh ranked the most air-polluted country in the world, with pollution levels exceeding WHO's safety guidelines by 16 times. Pakistan and India followed closely behind. In urban centers such as Dhaka, pollutants like fine particulate matter (PM2.5) are prevalent, due to unregulated emissions from vehicles and industries, as well as poor urban planning and construction practices. These pollutants pose a serious threat to public health, making city dwellers particularly vulnerable to lung cancer.

While early detection can significantly reduce the high mortality rate associated with lung cancer, the costs of diagnosis remain prohibitive, particularly in low-income countries like Bangladesh. 

Access to advanced medical care is limited, and many individuals are diagnosed too late. However, recent advances in Artificial Intelligence (AI) offer a glimmer of hope in the fight against lung cancer. AI-driven technologies are revolutionising medical diagnostics, especially in the early detection of lung cancer. Using algorithms powered by machine learning (ML) and deep learning (DL), AI can analyse lung scans such as chest X-rays and CT scans with remarkable accuracy. These systems have the potential to detect cancerous tissues early when treatment is most effective. What is particularly promising is that AI-based diagnostic tools do not rely on expensive equipment, making them a viable solution for underdeveloped and remote areas with limited healthcare resources.

By democratising access to early detection, AI holds the potential to save countless lives in places where traditional healthcare infrastructure is lacking. Ongoing research is focused on improving the accuracy and efficiency of AI tools, with particular emphasis on lung cancer prognosis, the identification of malignant lung lesions, and the classification of cancer subtypes. Innovative techniques such as 3D Convolutional Neural Networks (3D CNNs), Class Activation Maps (CAMs), and Recurrent Neural Networks (RNNs) are all part of the effort to enhance AI's capabilities in detecting and analysing lung cancer. 

As air pollution continues to rise, the need for innovative and accessible solutions to cancer detection becomes more urgent. AI presents a promising frontier, offering hope for early diagnosis and improved survival rates. However, realising the full potential of this technology will require sustained research and investment, as well as greater public awareness and commitment to environmental reforms.

In countries like Bangladesh, where the impacts of air pollution are most severe, a combination of stricter environmental regulations and the adoption of AI-driven diagnostic tools could significantly reduce the lung cancer burden. The future is not without hope. With advancements in AI, a collective focus on public health, and environmental re- forms, we can envision a world where lung cancer no longer claims so many lives. The path forward is clear: we must continue to invest in both technology and the environment to combat this silent killer.

Prof Dr Kamruddin Nur is currently serving as a full Professor in the Department of Computer Science, American International University-Bangladesh (AIUB). His research interests include pervasive computing, computer vision, machine learning, and robotic automation.

Contact: kamruddin@aiub.edu 

Disclaimer: The views and opinions expressed in this article are those of the author and do not necessarily reflect the opinions and views of The Business Standard