Absolute risk prediction for esophageal squamous cell carcinoma adaptable to regional disease burden across diverse regions

Abstract Background:Esophageal squamous cell carcinoma (ESCC) exhibits a long latency period and has a significant geographical disparity in incidence, which underscores the need for models predicting the long-term absolute risk adaptable to regional disease burden. Methods:31,883 participants in a large-scale population-based screening trial (Hua County, China) were enrolled to develop the model. Severe dysplasia and above (SDA) identified at screening or follow-up were defined as the outcome. We calculated the absolute risk in three steps: 1) constructing a relative risk model using logistic regression, 2) calculating the age-specific baseline hazard, and 3) adjusting for the competing risk of all-cause death excluding ESCC. Flexible incidence rate parameters were integrated into the model to ensure its relevance across diverse regions worldwide. Results:A total of 295 SDAs were detected. The relative risk model consisted of old age, male gender, irregular meal pattern, preference for hot or hard food, BMI of less than 22 kg/m2, and ESCC family history. The area under the receiver operating characteristic curve was 0.753 (95% CI: 0.749-0.757). The averaged 5-year and 10-year absolute risk were 0.53% and 1.30% among participants. Based on our model, we developed an online calculator incorporated flexible incidence rate parameters, demonstrating ideal risk stratification tailored to regions with varying disease burdens (https://pkugenetics.shinyapps.io/escc_risk_prediction/). Conclusions:We developed an absolute risk model to predict individualized long-term risk of ESCC, accounting for local disease burden. Impact:This model has the potential to mitigate the global burden of ESCC by enabling targeted screening and personalized prevention strategies.