DOI 10.1007/s10620-026-10223-1
Validation of a Digital Platform for Colorectal Cancer Risk Stratification and Personalized Screening Recommendations.
Аннотация
BACKGROUND
Colorectal cancer (CRC) is largely preventable through risk-adapted screening, yet participation remains below recommended targets. Digital platforms may help bridge this gap by identifying at-risk individuals and facilitating timely preventive evaluation. We aimed to validate the accuracy of ChequeáTuColon (CTC), a digital tool designed to stratify CRC risk, detect alarm symptoms, and provide personalized guideline-based screening recommendations.
METHODS
We conducted a validation study using data from individuals who completed the CTC digital assessment during a CRC awareness campaign at a tertiary care center in March 2026. A random sample was selected for validation. Three expert gastroenterologists, blinded to CTC outputs, independently reviewed participant data and assigned risk categories and screening recommendations. We evaluated concordance across four domains: alarm symptom detection, risk stratification, indication for genetic evaluation, and recommended screening initiation age.
RESULTS
Of 35758 individuals who completed the assessment, 395 were randomly selected for validation (median age 59 years; range 23-83). Overall, 50.4% were classified as average risk, 19.5% as increased risk, and 4.8% as high risk; 20.3% reported alarm symptoms. Among asymptomatic average-risk individuals, 20% were overdue for screening (mean delay 9.5 years), compared to 45% among increased- and high-risk individuals (mean delay 22 years). CTC demonstrated complete agreement with expert adjudication across all domains (100%; κ=1.000).
CONCLUSIONS
CTC achieved perfect concordance with expert guideline-based recommendations. The platform also identified substantial screening delays, particularly among higher-risk individuals, which highlights a potential role for digital tools in supporting guideline-based screening implementation. Further evaluation of patients' experience and downstream screening completion are still needed to evaluate its impact in clinical practice.
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.