ESCC Risk Assessment Tool

ESCC Risk Assessment Tool predicts individual risk of developing esophageal squamous cell carcinoma (ESCC) using a competing risk regression model to support early identification and risk stratification based on age, sex, tobacco smoking, alcohol consumption, and body mass index (BMI).

Key Features:

• Risk Prediction Model: Uses competing risk regression incorporating age, sex, tobacco smoking, alcohol consumption, and BMI with model derivation using data from the Nord-Trøndelag Health Study (HUNT).
• Validation: Externally validated in the UK Biobank cohort to assess generalizability across populations.
• Discrimination: Model discrimination measured by area under the receiver-operating characteristic curve (AUC) was 0.76 in the derivation cohort and 0.70 in the validation cohort.
• Calibration: Shows close agreement between predicted cumulative risk and observed probabilities of developing ESCC.
• Clinical Utility: Demonstrates a higher net benefit compared to treating all individuals as high-risk, supporting targeted preventive interventions.

Scientific Applications:

• Clinical risk stratification: Identifies high-risk individuals for consideration of early screening or preventive measures to improve outcomes.
• Research stratification and evaluation: Facilitates stratification of study participants and evaluation of ESCC risk factors and prevention strategies in epidemiological and clinical studies.

Methodology:

Competing risk regression modeling; variable selection and model derivation using HUNT data; external validation in UK Biobank; discrimination assessed by AUC; calibration assessed by comparing predicted cumulative risks to observed probabilities; net benefit compared to a treat-all approach.