Evolving Dynamics of Colorectal Cancer in High Socio-Demographic Regions

BACKGROUND: Colorectal cancer (CRC) poses a significant global health challenge, with evolving demographic trends emphasizing the need for accurate forecasting models. Existing forecasting models lack comprehensive coverage. By integrating machine learning algorithms, this study aims to provide more accurate and precise predictions, filling critical gaps in understanding CRC incidence, death, and disability-adjusted life year (DALY) rate trends, especially in high socio-demographic index (SDI) regions. Specific emphasis is placed on exploring age-, sex-, and country-specific variations in CRC trends. 

MATERIALS AND METHODS: An ensemble forecasting algorithm integrating Simple Linear Regression, Exponential Smoothing, and Autoregressive Integrated Moving Average, capable of handling a short time series was developed and validated, utilizing a dataset encompassing age-, sex-, and country-specific CRC incidence, mortality, and DALY rates. 

RESULTS: Our forecasting models reveal rising trends in CRC burden in the 15-49 years age group (young-onset) and decreasing trends in CRC burden in the 50-74 years age group (late-onset) in high SDI regions with sex-specific variations in incidence, mortality, and DALY rates. Some inflection points for demographic shifts in CRC disease burden, particularly death rates, were identified as early as within the next 5 years. We predict a shift in CRC burden towards females, particularly in older adults. 

CONCLUSION: A novel multifactor model was developed for comparing the incidence, mortality, and DALY rates of young- and late-onset CRC in high SDI regions. The rising incidence of young-onset CRC in high SDI regions underscores the need for proactive health strategies. By refining predictive models, adjusting screening guidelines to target younger, high-risk populations, and investing in public awareness and research, we can facilitate early detection and improve outcomes. This study addresses a significant gap in CRC forecasting and provides a robust framework for anticipating demographic shifts in CRC burden, making it an indispensable tool for healthcare planning.