The artificial intelligence and machine learning in lung cancer immunotherapy

Area of Science:

• Oncology
• Medical Informatics
• Artificial Intelligence

Background:

• Immunotherapy has shown significant benefits for lung cancer patients.
• Accurate patient selection and efficacy prediction are crucial for successful immunotherapy.
• Machine learning (ML)-based artificial intelligence (AI) is emerging in medical applications.

Purpose of the Study:

• To review the applications of AI in predicting immunotherapy efficacy for lung cancer.
• To discuss AI's role in predicting programmed death-ligand 1 (PD-L1) and tumor mutation burden (TMB).
• To explore AI's utility in assessing the tumor microenvironment (TME) and guiding clinical decisions.

Main Methods:

• Review of recent studies combining diverse data types (radiology, pathology, genomics, proteomics).
• Analysis of AI and ML algorithms for predictive modeling in cancer.
• Focus on AI applications for PD-L1/TMB and TME prediction.

Main Results:

• AI models can predict PD-L1 expression, TMB, and TME characteristics.
• AI aids in predicting immunotherapy benefits and potential side effects.
• Integration of multi-modal data with AI shows promise for personalized medicine.

Conclusions:

• AI and ML are transforming lung cancer immunotherapy by enabling precise patient stratification.
• "Digital biopsy" using AI may offer a superior alternative to traditional assessment methods.
• AI advancements are expected to improve clinical decision-making and patient outcomes in lung cancer treatment.