Development and validation of a prediction model for colorectal cancer prognosis
Principal Investigator
Name
Ching Wai Krista Chung
Institution
The University of Hong Kong
Position Title
PhD Student
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-1741
Initial CDAS Request Approval
Nov 12, 2024
Title
Development and validation of a prediction model for colorectal cancer prognosis
Summary
Colorectal cancer (CRC) is the second leading cause of cancer deaths worldwide, emphasizing the critical need for early detection and personalized preventive strategies to enhance survival rates and alleviate this disease burden. While existing CRC prognostic models have primarily focused on personal and clinicopathological factors, the integration of lifestyle factors with clinicopathological factors has shown promise in improving model predictive performance among 1,024 stage III CRC patients.1 There is potential to further enhance these models by incorporating a wider array of predictive variables. Our project aims to leverage the comprehensive data from the PLCO cohort to develop a precise CRC predictive model. We also aim to explore whether a predictive model that encompasses variables such as sociodemographics, medical history, dietary consumption, smoking, and physical activity, in addition to clinicopathological variables, provides accurate CRC risk stratification.
Reference:
1. Cheng E, Ou FS, Ma C, et al. Diet- and Lifestyle-Based Prediction Models to Estimate Cancer Recurrence and Death in Patients With Stage III Colon Cancer (CALGB 89803/Alliance). J Clin Oncol. 2022;40(7):740-751. doi:10.1200/JCO.21.01784
Reference:
1. Cheng E, Ou FS, Ma C, et al. Diet- and Lifestyle-Based Prediction Models to Estimate Cancer Recurrence and Death in Patients With Stage III Colon Cancer (CALGB 89803/Alliance). J Clin Oncol. 2022;40(7):740-751. doi:10.1200/JCO.21.01784
Aims
1. To develop a CRC prognostic model that integrates sociodemographic, medical history, dietary consumption, smoking, and physical activity, in addition to clinicopathological variables.
2. To evaluate the model’s prediction performance.
3. To identify the essential predictors.
Collaborators
Daniel Yee Tak Fong, School of Nursing, The University of Hong Kong
Naomi Takemura, School of Nursing, The Hong Kong Polytechnic University