Enhancing Early Colon Cancer Detection: A Framework for Optimising Gastroenterology Units
Emmanuel Elorm Nortey-Adom
Bloomberg School of Public Health, Johns Hopkins University, Baltimore USA.
Sharon Aa-inir Karbo *
Bloomberg School of Public Health, Johns Hopkins University, Baltimore USA.
Emmanuel Animashaun
Bloomberg School of Public Health, Johns Hopkins University, Baltimore USA.
Isaac Kyeremateng
Institute of Informatics, Data Science and Biostatistics, Wash U Medicine, St. Louis, Missouri, USA.
Ellen Barnie Peprah
Bloomberg School of Public Health, Johns Hopkins University, Baltimore USA.
Esi Hagan
Bloomberg School of Public Health, Johns Hopkins University, Baltimore USA.
Godwin Awuni Anafo
London School of Hygiene and Tropical Medicine, London, UK.
*Author to whom correspondence should be addressed.
Abstract
Background: The rising incidence of colorectal cancer in younger populations, highlighted by revised screening guidelines, has placed gastroenterology units under unprecedented strain. This surge coincides with advancements in personalised therapies, whose efficacy is vastly superior for early-stage disease. A critical disconnect exists between the growing demand for high-quality colonoscopy and the operational capacity of existing services.
Objective: This paper proposes a newly developed comprehensive framework designed to optimise gastroenterology units. The primary aim is to enhance both the capacity for early cancer detection and the quality of the diagnostic procedure, thereby creating a more effective bridge to modern therapeutic modalities.
Methods: A narrative evidence synthesis was conducted to develop a multifaceted framework integrating four core strategies: artificial intelligence for workflow optimisation, lean management principles, computer-aided detection polyp recognition systems, and formal collaborative care models with primary care.
Results: Evidence synthesis indicates that this integrated model can significantly improve key performance indicators. AI-driven scheduling can drastically reduce patient wait times and improve resource utilisation. Lean methodologies standardise workflows and improve bowel preparation quality. Computer-aided detection systems demonstrably increase adenoma detection rates. Collaborative models enhance referral appropriateness and follow-up adherence, closing critical care gaps.
Conclusion: Optimising gastroenterology units requires a holistic strategy that synchronises operational efficiency with clinical excellence. The proposed framework provides a viable roadmap to increase screening accessibility, improve diagnostic quality, and ensure that more patients can benefit from the life-saving potential of early detection coupled with advanced, personalised treatments.
Keywords: Colorectal cancer screening, operational efficiency, artificial intelligence, colonoscopy, capacity optimisation, targeted therapy, collaborative care