Large language models and multimodal foundation models for precision oncology.

Area of Science:

• Oncology
• Artificial Intelligence
• Bioinformatics

Background:

• Rapid advancements in artificial intelligence (AI) since 2022.
• Large language models (LLMs) achieve human-level text processing capabilities.
• Increasing use of transformer neural networks for both text and image processing.

Purpose of the Study:

• Summarize recent AI developments relevant to oncology.
• Highlight the shift towards multimodal AI models.
• Discuss the expected impact of these advancements on precision oncology.

Main Methods:

• Review of technological progress in AI, particularly LLMs and transformer networks.
• Analysis of the convergence of text and image processing in AI.
• Editorial summary of emerging AI trends and their implications.

Main Results:

• AI, especially LLMs, now matches human performance in text processing.
• Transformer neural networks are a common basis for AI models.
• Development of multimodal AI capable of processing diverse data inputs simultaneously.

Conclusions:

• The convergence of AI technologies marks a significant shift from specialized models.
• Multimodal AI is poised to revolutionize cancer research and precision oncology.
• These AI advancements are expected to have a substantial impact in the coming years.