Ummi Suhaimei

B.Sc, M.Res, M.P.H

Universiti Brunei Darussalam

student

PLCO (Learn more about this study)

PLCO-1317

Sep 5, 2023

Colorectal Cancer Risk Reduction and Early Detection using Epidemiological and Digital Technology

Colorectal cancer (CRC) is a pressing global health issue, ranking as the second leading cause of cancer-related deaths worldwide, with approximately 1.8 million new cases and 881,000 deaths reported in 2018. To combat this disease effectively, it is imperative to focus on early detection and risk reduction strategies. In Brunei, despite the availability of screening programs, CRC incidence rates are steadily increasing. Leveraging digital technology, including mobile health apps, offers a promising avenue to enhance existing screening initiatives and bolster early detection and risk reduction efforts for CRC.

The primary aim of this proposed research project is to develop a machine learning/deep learning (ML/DL) based model tailored specifically for risk reduction and early detection of CRC in Brunei. This endeavor is underpinned by a set of clear objectives:

1. Reviewing and assessing the landscape of currently available CRC risk calculators, both at the local and global levels.
2. Evaluating the existing CRC screening procedures, considering both local and global perspectives.
3. Developing and comparing a theory-based model with an ML/DL-based model for CRC risk prediction, utilizing open-source global data as a foundation.
4. Integrating the ML/DL-based CRC risk prediction algorithm into a digital platform, either web-based or mobile-based, such as the BruHealth app.
5. Conducting rigorous internal and external validation procedures for the ML/DL-based CRC risk calculator, using data specific to Brunei.

The proposed research holds substantial significance for multiple reasons. First, the potential to detect and prevent CRC at an early stage can lead to considerable cost savings within the healthcare system by reducing the necessity for expensive treatments and procedures associated with advanced-stage cancer. Moreover, identifying individuals at high risk for CRC through machine learning techniques has the potential to improve health outcomes and ultimately save lives. Overall, this study is poised to make a substantial impact on the field of CRC research, offering new and more effective methodologies for predicting and preventing this prevalent and debilitating disease.

In conclusion, this research project seeks to address the alarming rise in CRC incidence in Brunei by leveraging the capabilities of machine learning and deep learning technologies. By systematically reviewing existing CRC risk calculators and screening procedures, developing and validating an advanced ML/DL-based risk prediction model, and integrating it into a user-friendly digital platform, the study aims to significantly enhance early detection and risk reduction efforts. Ultimately, the project has the potential to revolutionize CRC research and contribute to the development of more precise and accessible tools for tackling this formidable health challenge.

Aim:
The main aim of the proposed project is to develop a machine learning/deep learning (ML/DL) based model for risk reduction and early detection of CRC in Brunei.

Objectives:
1. To review current and available CRC risk calculators locally and globally.
2. To review current and available CRC screening procedures locally and globally.
3. To develop and compare theory- based model and ML/DL-based model for CRC risk
prediction using open-source global data.
4. To integrate the ML/DL-based CRC risk prediction algorithm in a calculator of web- or
mobile- digital platform.
5. To conduct internal and external validation procedures of the ML/DL-based CRC risk
calculator using Brunei data.