Advancing Colorectal Cancer Diagnosis with AI-Powered Breathomics: Navigating Challenges and Future Directions.

Area of Science:

• Oncology
• Analytical Chemistry
• Bioinformatics

Background:

• Early colorectal cancer detection is vital for improving patient outcomes and reducing mortality.
• Current screening methods have limitations, including low patient uptake due to discomfort, hindering early-stage diagnosis.
• Novel, non-invasive screening alternatives are a significant research priority.

Purpose of the Study:

• To review research on breathomics for non-invasive colorectal cancer detection.
• To focus on machine learning applications for analyzing breathomics data in cancer screening.
• To identify challenges and future directions for artificial intelligence in breathomics for colorectal cancer.

Main Methods:

• Utilizing Volatile Organic Compounds (VOCs) present in exhaled breath.
• Applying machine learning algorithms for the analysis of complex breathomics data.
• Exploring the potential of breath analysis within the European ONCOSCREEN project framework.

Main Results:

• Breathomics presents a promising avenue for non-invasive cancer detection and monitoring.
• Machine learning is crucial for interpreting the intricate patterns of VOCs in breath.
• Advancements in breath analysis could significantly disrupt current colorectal cancer screening practices.

Conclusions:

• Breathomics, coupled with machine learning, offers a viable non-invasive strategy for early colorectal cancer detection.
• Addressing challenges in artificial intelligence application is key to realizing the full potential of breathomics.
• Future research directions, including the ONCOSCREEN project, aim to refine these methods for clinical application.