Distinct time trends in colorectal cancer incidence in countries with SDI levels from 1990 to 2019: an age-period-cohort analysis for the Global Burden of Disease 2019 study.

Introduction: The burden of colorectal cancer (CRC) plays a pivotal role in the global cancer epidemic. Our study reported the incidence trends in CRC and the associated effects of age, period, and birth cohort in 204 countries and territories over the past 30 years. Methods: The incidence data of CRC were extracted from the Global Burden of Disease Study (GBD) 2019. We performed the age-period-cohort (APC) model to estimate the overall annual percentage change (net drift) in the incidence rate, the annual percentage change by age group (local drift), and the relative risk (period and cohort effects) of the period and cohort in CRC during 1990-2019. This approach allows examining and distinguishing age, period, and cohort effects in incidence and potentially distinguishing colorectal cancer gaps in prevention and screening. Results: In 2019, the incidence of CRC was 2.17 (95% UI 2.00-2.34) million, of which China, the United States of America, and Japan had the highest incidence population, accounting for 45.9% of the global population. The age-standardized incidence rate (ASIR) was 26.7 (95% UI 28.9-24.6) per 100,000 people, of which 30 countries had an incidence rate greater than 40.0 per 100,000 people. From 1990 to 2019, the middle SDI region had the largest increase in incidence rate, with a net drift of 2.33% (95% CI 2.2-2.46%, p < 0.001). Globally, the incidence population was concentrated in the age group of 50-69 years, and the age group of 30-34 years had the largest increase in incidence rate (local drift 1.19% (95% CI 1.01-1.37%)). At the same time, the sex and age distributions of CRC incidence had significant heterogeneity across regions and countries. In the past 30 years, the incidence rate in 31 countries has been well controlled (net drift <0), and most of them were concentrated in high-and high-middle-SDI regions, such as Australia, Czechia, and Belgium, and the relative risk of incidence generally improved over time and consecutive young birth cohorts. CRC incidence showed an unfavorable trend (net drift ≥1%) in 89 countries, of which 27 countries were more significant (net drift >2%), mostly concentrated in the middle SDI region, such as China, Mexico, and Brazil, and the risk of period and birth cohort was unfavorable. Conclusion: Globally, the incidence of CRC has shown an overall upward trend over the past 30 years, with the exception of some countries with higher SDI values. Significant age-period-cohort differences were observed in the risk of incidence in CRC worldwide. Effective prevention and control policies need to take into account the age-period-cohort effect characteristics of different regions.

Multi-step validation of a deep learning-based system with visual explanations for optical diagnosis of polyps with advanced features.

Artificial intelligence (AI) has been found to assist in optical differentiation of hyperplastic and adenomatous colorectal polyps. We investigated whether AI can improve the accuracy of endoscopists' optical diagnosis of polyps with advanced features. We introduced our AI system distinguishing polyps with advanced features with more than 0.870 of accuracy in the internal and external validation datasets. All 19 endoscopists with different levels showed significantly lower diagnostic accuracy (0.410-0.580) than the AI. Prospective randomized controlled study involving 120 endoscopists into optical diagnosis of polyps with advanced features with or without AI demonstration identified that AI improved endoscopists' proportion of polyps with advanced features correctly sent for histological examination (0.960 versus 0.840, p < 0.001), and the proportion of polyps without advanced features resected and discarded (0.490 versus 0.380, p = 0.007). We thus developed an AI technique that significantly increases the accuracy of colorectal polyps with advanced features.