Baishideng Publishing Group Inc, 7041 Koll Center Parkway, Suite 160, Pleasanton, CA 94566, USA
Share the Article
Negoi I. Personalized surveillance in colorectal cancer: Integrating circulating tumor DNA and artificial intelligence into post-treatment follow-up. World J Gastroenterol 2025; 31(18): 106670 [PMID: 40496357 DOI: 10.3748/wjg.v31.i18.106670]
World J Gastroenterol. May 14, 2025; 31(18): 106670 Published online May 14, 2025. doi: 10.3748/wjg.v31.i18.106670
Personalized surveillance in colorectal cancer: Integrating circulating tumor DNA and artificial intelligence into post-treatment follow-up
Ionut Negoi
Ionut Negoi, Department of General Surgery, Carol Davila University of Medicine and Pharmacy Bucharest, Clinical Emergency Hospital of Bucharest, Bucharest 014461, Romania
Author contributions: Negoi I contributed to this study, designed the overall concept and outline of the manuscript, contributed to the discussion and design of the manuscript, contributed to the writing and editing of the manuscript, and reviewed the literature.
Conflict-of-interest statement: The author has no conflicts of interest to disclose.
Corresponding author: Ionut Negoi, MD, PhD, Associate Professor, Department of General Surgery, Carol Davila University of Medicine and Pharmacy Bucharest, Clinical Emergency Hospital of Bucharest, No. 8 Floreasca Street, Sector 1, Bucharest 014461, Romania. negoiionut@gmail.com
Received: March 4, 2025 Revised: April 7, 2025 Accepted: April 18, 2025 Published online: May 14, 2025 Processing time: 70 Days and 13.3 Hours
Core Tip
Core Tip: Given the increasing incidence of colorectal cancer, especially among younger populations, effective post-treatment surveillance is essential for early detection of recurrence and improved outcomes. Intensive surveillance has variable efficacy, underscoring the need for personalized, risk-based protocols. Suboptimal adherence to guidelines further highlights the need for efficient, individualized approaches. Circulating tumor DNA shows promise as a biomarker, offering high specificity and diagnostic accuracy. Additionally, artificial intelligence models utilizing patient and tumor data have the potential to refine surveillance, with predictive accuracy ranging from 0.581 to 0.979. Nonetheless, cost, accessibility, and validation remain significant barriers to widespread clinical implementation.
