Dataset Information

Combining the Fecal Immunochemical Test with a Logistic Regression Model for Screening Colorectal Neoplasia.

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.

SUBMITTER: Liu F

PROVIDER: S-EPMC8058550 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundMany screening programs for colorectal cancer (CRC) use the fecal immunochemical test (FIT) to triage individuals for colonoscopy. Although these programs reduce CRC incidence and CRC-related mortality, the detection of advanced precursor lesions (advanced adenomas and advanced serrated polyps) by FIT could be improved. As an alternative for FIT, the antibody-based multitargetFIT (mtFIT) has been proposed. The mtFIT measures three protein markers: hemoglobin, calprotectin, and serpin family F member 2. In a retrospective diagnostic accuracy study in a large colonoscopy-controlled series (n = 1284), mtFIT showed increased sensitivity for advanced neoplasia (AN), at equal specificity, compared to FIT (42.9% versus 37.3%; p = 0.025). This increase was mainly due to a higher sensitivity of mtFIT for advanced adenomas (37.8% versus 28.1% for FIT; p = 0.006). The present mtFIT study aims to prospectively validate these findings in the context of the Dutch national CRC screening program.MethodThe mtFIT study is a cross-sectional intervention study with a paired design. Eligible subjects for the Dutch FIT-based national CRC screening program are invited to perform mtFIT in addition to FIT. Samples are collected at home, from the same bowel movement, and are shipped to a central laboratory by postal mail. If either one or both tests are positive, participants are referred for colonoscopy. Detailed colonoscopy and pathology data are centrally stored in a national screening database (ScreenIT; Topicus, Deventer, the Netherlands) that is managed by the screening organization, and will be retrieved for this study. We aim to determine the relative sensitivity for AN, comprising of CRC, advanced adenomas and advanced serrated polyps, of mtFIT compared to FIT at an equal positivity rate. Additionally, we will use the Adenoma and Serrated Pathway to Colorectal CAncer model to predict lifetime health effects and costs for programmatic mtFIT- versus FIT-based screening. The target sample size is 13,131 participants.DiscussionThe outcome of this study will inform on the comparative clinical utility of mtFIT versus FIT in the Dutch national CRC screening program and is an important step forward in the development of a new non-invasive stool test for CRC screening.Trial registrationClinicaltrials.gov ; NCT05314309, registered April 6th 2022, first inclusions March 25th 2022 https://clinicaltrials.gov/ct2/results?cond=&term=NCT05314309&cntry=&state=&city=&dist =.

Project description:To compare the performance of a new blood test for colorectal cancer (CRC) to an established fecal immunochemical test (FIT) in a study population with the full range of neoplastic and non-neoplastic pathologies encountered in the colon and rectum.Volunteers were asked to complete a FIT prior to colonoscopy. Blood was collected after bowel preparation but prior to colonoscopy, and plasma was assayed for the presence of methylated BCAT1 and IKZF1 DNA using a multiplex real-time PCR assay. Sensitivity and specificity estimates for the blood test were calculated from true- and false-positive rates for neoplasia and compared with FIT at a range of fecal hemoglobin (Hb) concentration positivity thresholds.In total, 1,381 volunteers (median age 64 years; 49% male) completed both tests prior to colonoscopy. Estimated sensitivity of the BCAT1/IKZF1 blood test for CRC was 62% (41/66; 95% confidence interval 49-74%) with a specificity of 92% (1207/1315; 90-93%). FIT returned the same specificity at a cutoff of 60??g Hb/g, at which its corresponding sensitivity for cancer was 64% (42/66; 51-75%). In the range of commonly used FIT cutoffs, respective cancer sensitivity and specificity estimates with FIT were: 59% (46-71%) and 93% (92-95%) at 80??g Hb/g, and 79% (67-88%) and 81% (78-83%) at 10??g Hb/g. Although estimated sensitivities were not significantly different between the two tests for any stage of cancer, FIT showed a significantly higher sensitivity for advanced adenoma at the lower cutoffs. Specificity of FIT, but not of the BCAT1/IKZF1 blood test, deteriorated substantially in people with overt blood in the feces. When combining FIT (cutoff 10??g Hb/g) with the BCAT1/IKZF1 blood test, sensitivity for cancer was 89% (79-96%) at 74% (72-77%) specificity.A test based on detection of methylated BCAT1/IKZF1 DNA in blood has comparable sensitivity but better specificity for CRC than FIT at the commonly used positivity threshold of 10??g Hb/g. Further evaluation of the new test relative to FIT in the population screening context is now required to fully understand the potential advantages and disadvantages of these biomarkers in screening.

Project description:IntroductionThe use of screening can prevent death from colorectal cancer, yet people without regular healthcare visits may not realize the benefits of this preventive intervention. The objective of this study was to determine the effectiveness of a mailed screening invitation or mailed fecal immunochemical test in increasing colorectal cancer screening uptake in veterans without recent primary care encounters.Study designThree-arm pragmatic randomized trial.Setting/participantsParticipants were screening-eligible veterans aged 50-75 years, without a recent primary care visit who accessed medical services at the Corporal Michael J. Crescenz Veteran Affairs Medical Center between January 1, 2017, and July 31, 2017. All data were analyzed from March 1, 2018, to July 31, 2018.InterventionParticipants were randomized to (1) usual opportunistic screening during a healthcare visit (n=260), (2) mailed invitation to screen and reminder phone calls (n=261), or (3) mailed fecal immunochemical test outreach plus reminder calls (n=61).Main outcome measuresThe main outcome under investigation was the completion of colorectal cancer screening within 6 months after randomization.ResultsOf 782 participants in the trial, 53.9% were aged 60-75 years and 59.7% were African American. The screening rate was higher in the mailed fecal immunochemical test group (26.1%) compared with usual care (5.8%) (rate difference=20.3%, 95% CI=14.3%, 26.3%; RR=4.52, 95% CI=2.7, 7.7) or screening invitation (7.7%) (rate difference=18.4%, 95% CI=12.2%, 24.6%; RR=3.4, 95% CI=2.1, 5.4). Screening completion rates were similar between invitation and usual care (rate difference=1.9%, 95% CI= -2.4%, 6.2%; RR=1.3, 95% CI=0.7, 2.5).ConclusionsMailed fecal immunochemical test screening promotes colorectal cancer screening participation among veterans without a recent primary care encounter. Despite the addition of reminder calls, an invitation letter was no more effective in screening participation than screening during outpatient appointments.Trial registrationThis study is registered at clinicaltrials.gov NCT02584998.

Dataset Information

Combining the Fecal Immunochemical Test with a Logistic Regression Model for Screening Colorectal Neoplasia.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets