AI-Driven Early Diagnosis and Risk Prediction in Early-Onset Colorectal Cancer

Early-onset colorectal cancer (EOCRC) is an area of rapidly intensifying research, as incidence rates among individuals under age 50 continue to rise globally. Unlike cases detected in older adults, EOCRC often presents with atypical symptoms, leading to significant delays in diagnosis and poorer outcomes. Traditionally, a lack of routine screening and limited clinical awareness have left many young adults undiagnosed until advanced disease stages. This growing health challenge has prompted increasing attention to the need for improved strategies that enable earlier identification and intervention tailored to the unique characteristics of EOCRC. Recent research indicates that advances in artificial intelligence (AI), machine learning, and digital health offer promising solutions for enhancing risk stratification, early symptom recognition, and interpretation of complex diagnostic data. These technologies not only facilitate the discovery of novel biomarkers by integrating multi-omics information but also improve the accuracy and timeliness of diagnosis through enhanced imaging and pathology analysis. Despite these advances, key gaps remain, including limited external validation of AI models, equitable implementation, and the integration of digital solutions into clinical and public health workflows.

This Research Topic aims to foster critical exploration of AI-driven tools and digital health platforms designed to accelerate the early detection of EOCRC in young populations. The main objectives are to deepen understanding of the factors contributing to the rising incidence and diagnostic delays, evaluate the effectiveness of computational tools in risk prediction and early diagnosis, and promote translational research that bridges epidemiology, computational science, molecular research, and clinical practice. The intention is to address questions regarding how AI and digital health technologies can transform EOCRC detection, improve treatment decision-making, and reduce disparities, ultimately improving prognosis for young adults.

The scope of this Research Topic encompasses the development, validation, and implementation of AI-driven approaches to EOCRC, while not extending into unrelated adult colorectal cancer or non-AI approaches. To gather further insights in the timely and effective detection of EOCRC among young adults, we welcome articles addressing, but not limited to, the following themes:

1. AI for symptom assessment and risk stratification, including machine learning models for early symptom identification and risk calculators integrating multifactorial data
2. Advances in AI-powered imaging, endoscopy, and digital pathology for detecting subtle features of EOCRC
3. Integration of multi-omics data using machine learning to discover novel biomarkers for early detection
4. Digital health and remote monitoring tools, including mHealth platforms, telehealth triage, and the use of digital biomarkers
5. Epidemiological and clinical studies elucidating reasons behind rising EOCRC rates and delayed diagnoses in young adults


Please note that manuscripts consisting solely of bioinformatics or computational analysis of public genomic or transcriptomic databases which are not accompanied by robust and relevant validation (clinical cohort or biological validation in vitro or in vivo) are out of scope for this Research Topic.

Keywords: colorectal cancer, young adults, outcomes, incidence, AI

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.