Dataset Information

Evaluation of a prediction model for colorectal cancer: retrospective analysis of 2.5 million patient records.

ABSTRACT: Earlier detection of colorectal cancer greatly improves prognosis, largely through surgical excision of neoplastic polyps. These include benign adenomas which can transform over time to malignant adenocarcinomas. This progression may be associated with changes in full blood count indices. An existing risk algorithm derived in Israel stratifies individuals according to colorectal cancer risk using full blood count data, but has not been validated in the UK. We undertook a retrospective analysis using the Clinical Practice Research Datalink. Patients aged over 40 with full blood count data were risk-stratified and followed up for a diagnosis of colorectal cancer over a range of time intervals. The primary outcome was the area under the receiver operating characteristic curve for the 18-24-month interval. We also undertook a case-control analysis (matching for age, sex, and year of risk score), and a cohort study of patients undergoing full blood count testing during 2012, to estimate predictive values. We included 2,550,119 patients. The area under the curve for the 18-24-month interval was 0.776 [95% confidence interval (CI): 0.771, 0.781]. Performance improves as the time interval reduces. The area under the curve for the age-matched case-control analysis was 0.583 [0.574, 0.591]. For the population risk-scored in 2012, the positive predictive value at 99.5% specificity was 8.8% with negative predictive value 99.6%. The algorithm offers an additional means of identifying risk of colorectal cancer, and could support other approaches to early detection, including screening and active case finding.

SUBMITTER: Birks J

PROVIDER: S-EPMC5633543 | biostudies-literature | 2017 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Evaluation of a prediction model for colorectal cancer: retrospective analysis of 2.5 million patient records.

Birks Jacqueline J Bankhead Clare C Holt Tim A TA Fuller Alice A Patnick Julietta J

Cancer medicine 20170921 10

Earlier detection of colorectal cancer greatly improves prognosis, largely through surgical excision of neoplastic polyps. These include benign adenomas which can transform over time to malignant adenocarcinomas. This progression may be associated with changes in full blood count indices. An existing risk algorithm derived in Israel stratifies individuals according to colorectal cancer risk using full blood count data, but has not been validated in the UK. We undertook a retrospective analysis u ...[more]

PMID: 28941187

Similar Datasets

Project description:BackgroundAberrant DNA hypomethylation of the long interspersed nuclear elements (LINE-1 or L1) has been recognized as an early event of colorectal transformation. Simultaneous genetic and epigenetic analysis of colorectal adenomas may be an effective and rapid strategy to identify key biological features leading to accelerated colorectal tumorigenesis. In particular, global and/or intragenic LINE-1 hypomethylation of adenomas may represent a helpful tool for improving colorectal cancer (CRC) risk stratification of patients after surgical removal of polyps. To verify this hypothesis, we analyzed a cohort of 102 adenomas derived from 40 high-risk patients (who developed CRC in a post-polypectomy of at least one year) and 43 low-risk patients (who did not develop CRC in a post-polypectomy of at least 5 years) for their main pathological features, the presence of hotspot variants in driver oncogenes (KRAS, NRAS, BRAF and PIK3CA), global (LINE-1) and intragenic (L1-MET) methylation status.ResultsIn addition to a significantly higher adenoma size and an older patients' age, adenomas from high-risk patients were more hypomethylated than those from low-risk patients for both global and intragenic LINE-1 assays. DNA hypomethylation, measured by pyrosequencing, was independent from other parameters, including the presence of oncogenic hotspot variants detected by mass spectrometry. Combining LINE-1 and L1-MET analyses and profiling the samples according to the presence of at least one hypomethylated assay improved the discrimination between high and low risk lesions (p = 0.005). Remarkably, adenomas with at least one hypomethylated assay identified the patients with a significantly (p < 0.001) higher risk of developing CRC. Multivariable analysis and logistic regression evaluated by the ROC curves proved that methylation status was an independent variable improving cancer risk prediction (p = 0.02).ConclusionsLINE-1 and L1-MET hypomethylation in colorectal adenomas are associated with a higher risk of developing CRC. DNA global and intragenic hypomethylation are independent markers that could be used in combination to successfully improve the stratification of patients who enter a colonoscopy surveillance program.

Project description:BackgroundThe database used for the NHS Bowel Cancer Screening Programme (BCSP) derives participant information from primary care records. Combining predictors with FOBTs has shown to improve referral decisions and accuracy. The richer data available from GP databases could be used to complement screening referral decisions by identifying those at greatest risk of colorectal cancer. We determined the availability of data for key predictors and whether this information could be used to inform more accurate screening referral decisions.MethodsAn English BCSP cohort was derived using the electronic notifications received from the BCSP database to GP records. The cohort covered a period between 13th May 2009 to 17th January 2017. Completeness of variables and univariable associations were assessed. Risk prediction models were developed using Cox regression and multivariable fractional polynomials with backwards elimination. Optimism adjusted performance metrics were reported. The sensitivity and specificity of a combined approach using the negative FOBT model plus FOBT positive patients was determined using a probability equivalent to a 3% PPV NICE guidelines level.Results292,059 participants aged 60-74 were derived for the BCSP screening cohort. A model including the screening test result had a C-statistic of 0.860, c-slope of 0.997, and R2 of 0.597. A model developed for negative screening results only had a C-statistic of 0.597, c-slope of 0.940, and R2 of 0.062. Risk predictors included in the models included; age, sex, alcohol consumption, IBS diagnosis, family history of gastrointestinal cancer, smoking status, previous negatives and whether a GP had ordered a blood test. For the combined screening approach, sensitivity increased slightly from 53.90% (FOBT only) to 58.82% but at the expense of an increased referral rate.ConclusionsThis research has identified several potential predictors for CRC in a BCSP population. A risk prediction model developed for BCSP FOBT negative patients was not clinically useful due to a low sensitivity and increased referral rate. The predictors identified in this study should be investigated in a refined algorithm combining the quantitative FIT result. Combining data from multiple sources enables fuller patient profiles using the primary care and screening database interface.

Dataset Information

Evaluation of a prediction model for colorectal cancer: retrospective analysis of 2.5 million patient records.

Publications

Evaluation of a prediction model for colorectal cancer: retrospective analysis of 2.5 million patient records.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets