Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.
World J Gastroenterol. Aug 21, 2026; 32(31): 117409
Published online Aug 21, 2026. doi: 10.3748/wjg.117409
Published online Aug 21, 2026. doi: 10.3748/wjg.117409
Artificial intelligence morphology and host complexity for precision prediction of nodal metastasis in colorectal cancer
Gang Wang, Department of General Surgery, The First Affiliated Hospital of Soochow University, Suzhou 215006, Jiangsu Province, China
Sheng-Jie Pan, Department of Neurology, The First Affiliated Hospital of Soochow University, Suzhou 215006, Jiangsu Province, China
Co-corresponding authors: Gang Wang and Sheng-Jie Pan.
Author contributions: Pan SJ contributed to conceptualization, methodology, investigation, data curation, formal analysis, visualization, and drafting of the original manuscript, and provided overall scientific supervision; Wang G contributed to conceptualization, project administration, validation of the conceptual framework, provision of resources, and critical review and editing of the manuscript; Wang G and Pan SJ have played important and indispensable roles in the manuscript preparation as the co-corresponding authors.
AI contribution statement: AI-assisted tools, such as Grammarly and DeepL, were employed solely for language polishing, including improving grammar, clarity, and readability. These tools did not generate any scientific content. AI tools did not participate in study conceptualization, experimental design, data analysis, interpretation of results, or conclusions. All figures, tables, and graphical content were independently created by the authors without any AI assistance. In summary, AI tools were strictly used to refine language for clarity and readability. They did not influence the scientific content, analyses, or conclusions of the manuscript in any manner.
Conflict-of-interest statement: The authors declare no conflicts of interest related to the content of this editorial.
Corresponding author: Gang Wang, MD, PhD, Professor, Department of General Surgery, The First Affiliated Hospital of Soochow University, No. 899 Pinghai Road, Suzhou 215006, Jiangsu Province, China. 286651551@qq.com
Received: December 8, 2025
Revised: January 9, 2026
Accepted: January 21, 2026
Published online: August 21, 2026
Processing time: 238 Days and 3 Hours
Revised: January 9, 2026
Accepted: January 21, 2026
Published online: August 21, 2026
Processing time: 238 Days and 3 Hours
Core Tip
Core Tip: The case-level multiple instance learning framework proposed by Zou et al represents an important advance in extracting prognostic morphologic features for lymph node metastasis in colorectal cancer. However, morphology alone is insufficient to capture the full spectrum of metastatic biology. Integrating artificial intelligence-derived histopathologic features with host systemic signatures-including inflammation, immunometabolic reserve, autonomic regulation, and circadian organization-provides a more biologically grounded and clinically actionable framework for risk stratification and precision surgical decision-making.