Exploring an Intermediate Colorectal Cancer Screening Test Based on Stool Proteomics and Machine Learning for...

Area of Science:

• Biomarker discovery
• Proteomics
• Colorectal cancer screening

Background:

• Fecal immunochemical test (FIT) is effective for colorectal cancer (CRC) screening.
• FIT produces false positives, leading to unnecessary colonoscopies.
• A need exists for improved triage strategies in CRC screening.

Purpose of the Study:

• To investigate repurposing leftover FIT stool samples for proteomics analysis.
• To develop a triage step for patients before colonoscopy.
• To reduce unnecessary colonoscopies and prioritize CRC detection.

Main Methods:

• High-throughput mass spectrometry on 141 FIT-positive stool samples.
• Analysis included controls, advanced adenomas (AA), and CRC cases.
• Machine learning tools were employed for data analysis.

Main Results:

• Proteomics analysis achieved ≥90% specificity in identifying false FIT positives.
• This strategy effectively reduces unnecessary colonoscopies.
• CRC cases were accurately predicted as true positives, aiding prioritization.

Conclusions:

• Proteomics analysis of leftover FIT samples is feasible.
• This method serves as an intermediate triage step in CRC screening.
• The approach enhances the efficiency of colonoscopy recommendations.