AI and Lung Cancer: Progress, Challenges, and a Patient’s Perspective

Artificial intelligence (AI) is rapidly transforming cancer care, and lung cancer is at the forefront of this revolution. From early detection and personalized screening to treatment optimization and imaging genomics, AI offers unprecedented opportunities to improve outcomes for patients. However, significant hurdles remain, including concerns about model bias and fairness. Alongside these advancements, the patient experience highlights the critical importance of self-advocacy and trusting one’s instincts when facing a challenging diagnosis.

The Rise of AI in Lung Cancer Management

AI algorithms, particularly deep learning methods like convolutional neural networks (CNNs) and transformers, excel at discerning intricate patterns in large datasets. This capability is proving invaluable in various aspects of lung cancer management. Supervised learning methods are widely applied in image analysis, requiring extensive annotations, even as weakly supervised methods, such as multiple-instance learning and vision transformers (ViTs), address annotation limitations and enable large-scale data analysis. Unsupervised methods, like self-supervised learning, further uncover hidden patterns in unlabeled data [1].

Specific applications of AI in lung cancer include:

• Smoking Cessation: AI-powered tools can help individuals quit smoking by providing personalized support and interventions.
• Personalized Screening: AI can analyze patient data to identify those at high risk of developing lung cancer, enabling targeted screening programs.
• Imaging Genomics: AI can integrate imaging data with genomic information to predict treatment response and prognosis.
• Treatment Selection: AI algorithms can analyze patient characteristics and tumor profiles to recommend the most effective treatment options.

Addressing the Challenges: Bias and Fairness

Despite its potential, the implementation of AI in lung cancer care is not without challenges. A critical concern is the potential for model bias and fairness. AI algorithms are trained on data, and if that data reflects existing biases in healthcare, the algorithms may perpetuate or even amplify those biases. Ensuring that AI models are trained on diverse and representative datasets is crucial to avoid disparities in care.

A Patient’s Journey: The Importance of Self-Advocacy

The story of Janis Chen powerfully illustrates the importance of patient self-advocacy. After experiencing chest pain and having a family history of lung cancer, Janis repeatedly sought medical attention, only to be initially dismissed as experiencing anxiety [1], [3]. She had to persistently request a chest x-ray, which ultimately revealed tumors in both lungs. Her experience underscores the need for patients to trust their instincts and advocate for their health, even when faced with skepticism from healthcare professionals.

Janis was diagnosed with stage 4 EGFR+ lung cancer with metastasis. Initially, her medical team believed the cancer was curable, but complications during a biopsy delayed a definitive diagnosis. She underwent surgery in October 2022 and again in November, before receiving the final diagnosis. Despite the challenging prognosis – initially estimated at 11 months – Janis continues to live, navigating the complexities of a “chronically terminal” state, a reality increasingly common due to advancements in treatment [1].

Janis’s story also highlights the emotional and existential challenges faced by patients with advanced cancer. She emphasizes the importance of finding support and meaning in the face of uncertainty, and the need to redefine strength not as “fighting” the disease, but as living fully in the present moment.

The Future of AI in Lung Cancer

The future of AI in lung cancer is promising. Ongoing research is focused on developing more sophisticated AI algorithms, improving data quality, and addressing ethical concerns. [4] Explainable AI (XAI) is also gaining traction, aiming to produce AI decision-making processes more transparent and understandable to clinicians and patients. As AI continues to evolve, it has the potential to significantly improve the lives of individuals affected by lung cancer, offering hope for earlier detection, more effective treatments, and a better quality of life.