Artificial Intelligence in Colorectal Cancer Supportive Care: A Scoping Review
Year: 2025
Type: article
Study design: Systematic Review
Abstract: PURPOSE: Artificial Intelligence (AI) has the potential to enhance supportive care for cancer survivors from diagnosis through treatment and into survivorship. This study aimed to provide an overview of available evidence on AI applications in supportive care for individuals with colorectal cancer (CRC). METHODS: This scoping review was conducted following the Joanna Briggs Institute guidelines. Studies published between 2014 and 2025 were retrieved from six databases: PubMed, Embase, CINAHL, Scopus, Web of Science, and PsycINFO, using a combination of search terms relevant to "colorectal cancer," "artificial intelligence," and "supportive care." Data on study characteristics, participants, settings, types of AI technologies, and supportive care dimensions were extracted for analysis. RESULTS: Out of 1,792 articles, 40 were identified as eligible for inclusion in this scoping review. AI applications for CRC supportive care are primarily in early development, focusing on machine learning-based prediction models that provide informational support for post-surgical side effects. The use of AI for physical support in symptom management and emotional support during cancer treatment and beyond was limited. CONCLUSION: Implementing AI technology offers an opportunity to enhance supportive care for patients with CRC. This study suggests that current AI applications for CRC supportive care primarily focus on informational support, underscoring the need for further development of AI to provide comprehensive support, including psychological, social, spiritual, and practical aspects. IMPLICATIONS FOR NURSING PRACTICE: Further research is needed to develop AI-driven tools that comprehensively address the supportive care needs of cancer patients and enhance their outcomes.
Source: Seminars in Oncology Nursing
Institutions: University of Michigan, U-M Rogel Cancer Center
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
Estimated APC paid: $3,590
Funder: University of Michigan
OpenAlex ID: W4417518345
