Abstract
Background: The fecal immunochemical test (FIT) is a widely used strategy for colorectal cancer (CRC) screening with moderate sensitivity. To further increase the sensitivity of FIT in identifying colorectal neoplasia, in this study, we established a classifier model by combining FIT result and other demographic and clinical features. Methods: A total of 4,477 participants were examined with FIT and those who tested positive (over 100 ng/ml) were followed up by a colonoscopy examination. Demographic and clinical information of participants including four domains (basic information, clinical history, diet habits and life styles) that consist of 15 features were retrieved from questionnaire surveys. A mean decrease accuracy (MDA) score was used to select features that are mostly related to CRC. Five different algorithms including logistic regression (LR), classification and regression tree (CART), support vector machine (SVM), artificial neural network (ANN) and random forest (RF) were used to generate a classifier model, through a 10X cross validation process. Area under curve (AUC) and normalized mean squared error (NMSE) were used in the evaluation of the performance of the model. Results: The top six features that are mostly related to CRC include age, gender, history of intestinal adenoma or polyposis, smoking history, gastrointestinal discomfort symptom and fruit eating habit were selected. LR algorithm was used in the generation of the model. An AUC score of 0.92 and an NMSE score of 0.076 were obtained by the final classifier model in separating normal individuals from participants with colorectal neoplasia. Conclusion: Our results provide a new “Funnel” strategy in colorectal neoplasia screening via adding a classifier model filtering step between FIT and colonoscopy examination. This strategy minimizes the need of colonoscopy examination while increases the sensitivity of FIT-based CRC screening.
Highlights
Colorectal cancer (CRC) is the fourth most common cancer, and accounts for around 10% of the newly diagnosed cases of cancers (Siegel et al, 2020)
The aim of this study is to generate a classifier model to evaluate the likelihood of colorectal neoplasia based on fecal immunochemical test (FIT) results and a cohort of other features
Five analytical methods including logistic regression (LR), supportvector machine (SVM), classification and regression tree (CART), artificial neural network (ANN) and random forest (RF) were used in the data analysis step, and the AUC and NMSE scores were used in judging the performance of the classifier model
Summary
Colorectal cancer (CRC) is the fourth most common cancer, and accounts for around 10% of the newly diagnosed cases of cancers (Siegel et al, 2020). Three main types of CRC screening strategies have been suggested by various international guidelines, which are physical-based, blood-based and faecal-based methods. Physical-based methods such as colonoscopy are currently the most sensitive tests in CRC screening. Feacal-based methods detect biomarkers in patients’ stool samples including guaiac-based faecal occult blood test (gFOBT), fecal immunochemical test (FIT) and multitargeted stool DNA test (FIT-DNA). In comparison with physical-based screening methods, FIT is a non-invasive test and can be done without dietary or medication restrictions; in comparison with bloodbased screening methods, FIT is cheaper and faster in the report generation process while yielding fairly reliable results. The fecal immunochemical test (FIT) is a widely used strategy for colorectal cancer (CRC) screening with moderate sensitivity. To further increase the sensitivity of FIT in identifying colorectal neoplasia, in this study, we established a classifier model by combining FIT result and other demographic and clinical features
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have