High detection rate of adenomas in familial colorectal cancer

Model with the GBDT for Colorectal Adenoma Risk Diagnosis

Background and Objective:

Colorectal cancer (CRC) is a common malignant tumor of the digestive system; it is associated with high morbidity and mortality. However, an early prediction of colorectal adenoma (CRA) that is a precancerous disease of most CRC patients provides an opportunity to make an appropriate strategy for prevention, early diagnosis and treatment. It has been aimed to develop a machine learning model to predict CRA that could assist physicians in classifying high-risk patients, make informed choices and prevent CRC.

Methods:

Patients who had undergone a colonoscopy to fill out a questionnaire at the Sixth People Hospital of Shanghai in China from July 2018 to November 2018 were instructed. A classification model with the gradient boosting decision tree (GBDT) was developed to predict CRA. This model was compared with three other models, namely, random forest (RF), support vector machine (SVM), and logistic regression (LR). The area under the receiver operating characteristic curve (AUC) was used to evaluate performance of the models.

Results:

Among the 245 included patients, 65 patients had CRA. The area under the receiver operating characteristic (AUCs) of GBDT, RF, SVM ,and LR with 10 fold-cross validation was 0.8131, 0.74, 0.769 and 0.763. An online prediction service, CRA Inference System, to substantialize the proposed solution for patients with CRA was also built.

Conclusion:

Four classification models for CRA prediction were developed and compared, and the GBDT model showed the highest performance. Implementing a GBDT model for screening can reduce the cost of time and money and help physicians identify high-risk groups for primary prevention.

Guidelines for the management of hereditary colorectal cancer from the British Society of Gastroenterology (BSG)/Association of Coloproctology of Great Britain and Ireland (ACPGBI)/United Kingdom Cancer Genetics Group (UKCGG)

Heritable factors account for approximately 35% of colorectal cancer (CRC) risk, and almost 30% of the population in the UK have a family history of CRC. The quantification of an individual's lifetime risk of gastrointestinal cancer may incorporate clinical and molecular data, and depends on accurate phenotypic assessment and genetic diagnosis. In turn this may facilitate targeted risk-reducing interventions, including endoscopic surveillance, preventative surgery and chemoprophylaxis, which provide opportunities for cancer prevention. This guideline is an update from the 2010 British Society of Gastroenterology/Association of Coloproctology of Great Britain and Ireland (BSG/ACPGBI) guidelines for colorectal screening and surveillance in moderate and high-risk groups; however, this guideline is concerned specifically with people who have increased lifetime risk of CRC due to hereditary factors, including those with Lynch syndrome, polyposis or a family history of CRC. On this occasion we invited the UK Cancer Genetics Group (UKCGG), a subgroup within the British Society of Genetic Medicine (BSGM), as a partner to BSG and ACPGBI in the multidisciplinary guideline development process. We also invited external review through the Delphi process by members of the public as well as the steering committees of the European Hereditary Tumour Group (EHTG) and the European Society of Gastrointestinal Endoscopy (ESGE). A systematic review of 10 189 publications was undertaken to develop 67 evidence and expert opinion-based recommendations for the management of hereditary CRC risk. Ten research recommendations are also prioritised to inform clinical management of people at hereditary CRC risk.

High-risk family colorectal cancer screening service in Ireland: Critical review of clinical outcomes

BACKGROUND

We present the 15-year experience of a family colorectal cancer screening service in Ireland with emphasis on real life experience and outcomes.

METHODS

Questionnaires were used to assess family cancer history and assign patients to risk categories; 'Moderate Risk', HNPCC, (suspected) genetic syndrome (non-HNPCC), 'Low Risk'. Screening was by full colonoscopy. We report neoplastic yield, examining effect of risk category, age, gender, and index colonoscopy findings.

RESULTS

Between 1998 and 2013, 2242 individuals were referred; 57.3% female, 42.7% male, median age 46 years (range9-85yrs). Median follow up time was 7.9yrs (range 0.5-15.3yrs). Follow up data after exclusion (non-compliance, known CRC) was available in 1496 (66.7%): 'Moderate risk' 785 (52.5%), HNPCC 256 (17.1%), (suspected) genetic syndrome (non-HNPCC) 85 (5.7%), 'Low Risk' 370 (24.7%). Screening was performed in 1025(68.5%) patients; colonoscopy data available for 993 (96.9%); total 1914 colonoscopies. At index colonoscopy, 178 (18.0%) patients had adenomas; 56 (5.5%) advanced adenoma. During the entire study period, 240 (24.2%) had an adenoma; 69 (7.0%) advanced adenoma. Cancers were diagnosed on screening in 2 patients. Older age and male gender were associated with higher adenoma detection rate; p<0.001, p=0.01, respectively. Risk category did not affect adenoma yield. Adenoma and advanced adenoma detection at index colonoscopy were associated with detection of same at follow up screening; p<0.001.

CONCLUSION

Male gender and age (>50) were the core identifiable risk factors for neoplasia at screening colonoscopy in this family screening setting. Our results would support less intensive surveillance in younger patients (<50), particularly where index colonoscopy is normal.

Evaluation of a population-based approach to familial colorectal cancer

As Newfoundland has the highest rate of familial colorectal cancer (CRC) in the world, we started a population‐based clinic to provide colonoscopic and Lynch syndrome (LS) screening recommendations to families of CRC patients based on family risk. Of 1091 incident patients 51% provided a family history. Seventy‐two percent of families were at low or intermediate–low risk of CRC and colonoscopic screening recommendations were provided by letter. Twenty‐eight percent were at high and intermediate–high risk and were referred to the genetic counsellor, but only 30% (N = 48) were interviewed by study end. Colonoscopy was recommended more frequently than every 5 years in 35% of families. Lower family risk was associated with older age of proband but the frequency of screening colonoscopy recommendations varied across all age groups, driven by variability in family history. Twenty‐four percent had a high MMR predict score for a Lynch syndrome mutation, and 23% fulfilled the Provincial Program criteria for LS screening. A population‐based approach in the provision of colonoscopic screening recommendations to families at risk of CRC was limited by the relatively low response rate. A family history first approach to the identification of LS families was inefficient.

Identification of familial colorectal cancer and hereditary colorectal cancer syndromes through the Dutch population-screening program: results ofa pilot study

OBJECTIVES

In 2014, a population-screening program using immuno-faecal occult blood testing (I-FOBT) has started in the Netherlands. The aims of this study were to evaluate the proportion of individuals in the Dutch screening program with a positive I-FOBT that fulfill the criteria for familial colorectal cancer (FCC) and to evaluate the proportion of participants that needs genetic counseling or colonoscopic surveillance.

MATERIAL AND METHODS

This retrospective observational study was performed in two large hospitals. Individuals aged between 55 and 75 years with a positive I-FOBT that underwent colonoscopy were included. A detailed family history was obtained in all individuals.

RESULTS

A total of 657 individuals with a positive I-FOBT test underwent colonoscopy. A total of 120 (18.3%) participants were found to have a positive family history for CRC, 20 (3.0%) fulfilled the FCC criteria, 4 (0.6%) the Bethesda guidelines and 1 (0.2%) participant the Amsterdam criteria. Multiple adenomas (>10) were found in 21 (3.2%) participants. No cases of serrated polyposis were identified. Based on these criteria and guidelines, a total of 35 (5.3%) required referral to the clinical geneticist and the relatives of 20 (3.0%) participants should be referred for surveillance colonoscopy.

CONCLUSION

Obtaining a detailed family history at the time of intake of participants with a positive I-FOBT in the Dutch surveillance program increased the identification of participants with familial CRC.

Risk of Advanced Neoplasia in First-Degree Relatives with Colorectal Cancer: A Large Multicenter Cross-Sectional Study

BACKGROUND

First-degree relatives (FDR) of patients with colorectal cancer have a higher risk of developing colorectal cancer than the general population. For this reason, screening guidelines recommend colonoscopy every 5 or 10 y, starting at the age of 40, depending on whether colorectal cancer in the index-case is diagnosed at <60 or ≥60 y, respectively. However, studies on the risk of neoplastic lesions are inconclusive. The aim of this study was to determine the risk of advanced neoplasia (three or more non-advanced adenomas, advanced adenoma, or invasive cancer) in FDR of patients with colorectal cancer compared to average-risk individuals (i.e., asymptomatic adults 50 to 69 y of age with no family history of colorectal cancer).

METHODS AND FINDINGS

This cross-sectional analysis includes data from 8,498 individuals undergoing their first lifetime screening colonoscopy between 2006 and 2012 at six Spanish tertiary hospitals. Of these individuals, 3,015 were defined as asymptomatic FDR of patients with colorectal cancer ("familial-risk group") and 3,038 as asymptomatic with average-risk for colorectal cancer ("average-risk group"). The familial-risk group was stratified as one FDR, with one family member diagnosed with colorectal cancer at ≥60 y (n = 1,884) or at <60 y (n = 831), and as two FDR, with two family members diagnosed with colorectal cancer at any age (n = 300). Multiple logistic regression analysis was used for between-group comparisons after adjusting for potential confounders (age, gender, and center). Compared with the average-risk group, advanced neoplasia was significantly more prevalent in individuals having two FDR with colorectal cancer (odds ratio [OR] 1.90; 95% confidence interval [CI] 1.36-2.66, p < 0.001), but not in those having one FDR with colorectal cancer diagnosed at ≥60 y (OR 1.03; 95% CI 0.83-1.27, p = 0.77) and <60 y (OR 1.19; 95% CI 0.90-1.58, p = 0.20). After the age of 50 y, men developed advanced neoplasia over two times more frequently than women and advanced neoplasia appeared at least ten y earlier. Fewer colonoscopies by 2-fold were required to detect one advanced neoplasia in men than in women. Major limitations of this study were first that although average-risk individuals were consecutively included in a randomized control trial, this was not the case for all individuals in the familial-risk cohort; and second, the difference in age between the average-risk and familial-risk cohorts.

CONCLUSIONS

Individuals having two FDR with colorectal cancer showed an increased risk of advanced neoplasia compared to those with average-risk for colorectal cancer. Men had over 2-fold higher risk of advanced neoplasia than women, independent of family history. These data suggest that screening colonoscopy guidelines should be revised in the familial-risk population.

Colorectal cancer screening in the familial risk population: Is colonoscopy still the strategy of choice?

First-degree relatives of patients with colorectal cancer (CRC) are at high risk of this disease. For this reason, medical organizations and clinical guidelines recommend more intensive screening and surveillance for such first-degree relatives than for the average-risk population. Colonoscopy has been the cornerstone of CRC screening in this setting. Although colonoscopy is the most sensitive technique for the detection of neoplastic lesions (especially non-advanced adenomas), its role is less clear for CRC. In addition, screening colonoscopy has several limitations that may affect the success of a screening campaign, such as poor participant acceptance, the need for skilled endoscopists, participant access to screening colonoscopy, overburdened endoscopy units, potential complications, and procedure-related costs. In addition, recent evidence has cast doubt on the advantage of colonoscopy over other strategies for the detection of advanced neoplastic lesions. Despite being less sensitive in general, other screening methods frequently recommended in the average-risk population may be more acceptable and thus help increase CRC screening uptake. This review discusses recent evidence on the risk of CRC in first-degree relatives, the advantages and disadvantages of each screening technique, participation rates depending on the technique, patient preferences, and barriers to screening.

Randomized Comparison of Surveillance Intervals in Familial Colorectal Cancer

PURPOSE

Colonoscopic surveillance is recommended for individuals with familial colorectal cancer (CRC). However, the appropriate screening interval has not yet been determined. The aim of this randomized trial was to compare a 3-year with a 6-year screening interval.

PATIENTS AND METHODS

Individuals between ages 45 and 65 years with one first-degree relative with CRC age < 50 years or two first-degree relatives with CRC were selected. Patients with zero to two adenomas at baseline were randomly assigned to one of two groups: group A (colonoscopy at 6 years) or group B (colonoscopy at 3 and 6 years). The primary outcome measure was advanced adenomatous polyps (AAPs). Risk factors studied included sex, age, type of family history, and baseline endoscopic findings.

RESULTS

A total of 528 patients were randomly assigned (group A, n = 262; group B, n = 266). Intention-to-treat analysis showed no significant difference in the proportion of patients with AAPs at the first follow-up examination at 6 years in group A (6.9%) versus 3 years in group B (3.5%). Also, the proportion of patients with AAPs at the final follow-up examination at 6 years in group A (6.9%) versus 6 years in group B (3.4%) was not significantly different. Only AAPs at baseline was a significant predictor for the presence of AAPs at first follow-up. After correction for the difference in AAPs at baseline, differences between the groups in the rate of AAPs at first follow-up and at the final examination were statistically significant.

CONCLUSION

In view of the relatively low rate of AAPs at 6 years and the absence of CRC in group A, we consider a 6-year surveillance interval appropriate. A surveillance interval of 3 years might be considered in patients with AAPs and patients with ≥ three adenomas.

Familial colorectal cancer screening: When and what to do?

Colorectal cancer (CRC) is the third leading cause of death worldwide and represents a clinical challenge. Family members of patients affected by CRC have an increased risk of CRC development. In these individuals, screening is strongly recommended and should be started earlier than in the population with average risk, in order to detect neoplastic precursors, such as adenoma, advanced adenoma, and nonpolypoid adenomatous lesions of the colon. Fecal occult blood test (FOBT) is a non invasive, widespread screening method that can reduce CRC-related mortality. Sigmoidoscopy, alone or in addition to FOBT, represents another screening strategy that reduces CRC mortality. Colonoscopy is the best choice for screening high-risk populations, as it allows simultaneous detection and removal of preneoplastic lesions. The choice of test depends on local health policy and varies among countries.

Colonoscopy findings in high-risk individuals compared to an average-risk control population

BACKGROUND AND AIMS

There is clear evidence of reduced morbidity and mortality from regular colonoscopy programs in patients with Lynch syndrome (LS). Today, also individuals with empirically increased risks of colorectal cancer (CRC) are offered colonoscopic surveillance. The aim was to compare the findings at the first screening colonoscopy in LS carriers, and individuals with an increased risk of bowel cancer due to family history of CRC with a control population.

METHODS

Altogether 1397 individuals with an increased risk for CRC were divided in four risk groups: one with LS carriers and three groups with individuals with different family history of CRC. The findings were compared between the different risk groups and a control group consisting of 745 individuals from a control population who took part in a population-based colonoscopy study.

RESULTS

In LS, 30% of the individuals had adenomas and 10% advanced adenomas. The corresponding figures in the other risk groups were 14-24% and 4-7%, compared with 10% and 3% in the control group. The relative risk of having adenomas and advanced adenomas was, compared to controls, significantly higher for all risk groups except the group with the lowest risk. Age was a strong predictor for adenomas and advanced adenomas in both risk individuals and controls.

CONCLUSIONS

Individuals with a family history of CRC have a high prevalence and cumulative risk of adenomas and advanced adenomas, and screening is motivated also in this risk group.

Familial colorectal cancer: a review

Familial colorectal cancer constitutes a heterogeneous group of patients in whom the underlying molecular mechanism is still unknown. Predisposition to a such neoplasms in this setting seems to be due to common low-penetrance genetic components, but the role of genetic testing in clinical practice has to be determined. Although screening guidelines in this moderate-risk population are empiric, data obtained in epidemiologic, meta-analyses and cohort studies and, more recently, the increased risk of advanced adenomas in first degree relatives who underwent screening colonoscopy support the need to include these individuals in specific screening programs. However, data to determine what test to use, how often to use and which organizational strategy to implement are needed. At present, screening uptake in this population is less than optimal; offering the opportunity to access to screening and improving screening uptake is a first significant step.

Colonoscopic surveillance of first-degree relatives of colorectal cancer patients in a faecal occult blood screening programme

BACKGROUND

In some Italian areas, colonoscopic surveillance of first-degree relatives (FDRs) of colorectal cancer (CRC) patients is provided as a part of local population-based faecal occult blood test (FOBT) screening programmes. The objective of the present study was to assess the feasibility and early results of this surveillance model.

METHODS

Data from district screening centres were used to evaluate the process of identification and selection of eligible FDRs (residence in the Emilia-Romagna Region, age 40-75 years, no recent colonoscopy) of screen-detected CRC patients and the detected prevalence of disease. The probability for an FDR to undergo colonoscopy and to be diagnosed with CRC and advanced adenoma was estimated using the Kaplan-Meier method. The sex- and age-standardised ratio of detected prevalence to that expected based on results from a colonoscopy screening study of the Italian general population was estimated.

RESULTS

Between 2005 and 2011, 9319 FDRs of 2437 screen-detected CRC patients (3.8 per patient) were identified and contacted. Their likelihood of being eligible for, and accepting, colonoscopy was 0.11 (95% confidence interval: 0.11-0.12). Among the 926 subjects undergoing colonoscopy, the prevalence of previous negative screening FOBT was 63%. Eleven CRCs (1.2%) and 100 advanced adenomas (10.8%) were detected. The standardised ratio of detected prevalence to that expected was 0.91 (95% confidence interval: 0.19-2.66) for CRC and 1.48 (1.04-2.05) for advanced adenoma.

CONCLUSIONS

The procedure of selection of FDRs was extremely ineffective. Due to previous negative screening tests, the prevalence of disease was less than expected. A population-based FOBT screening programme is a highly unsuitable setting for the provision of surveillance to FDRs of CRC patients.

[Genetics of colorectal cancer]

Colorectal cancer (CRC) is one of the most frequent neoplasms in developed countries and up to 5% of all cases occur in the context of a hereditary syndrome. These hereditary forms often require a high index of suspicion for their diagnosis and specific and specialized management. Moreover, a diagnosis of hereditary CRC has major consequences not only for the patient--for whom there are highly effective preventive measures--but also for the patient's relatives, who may carry the same condition. The most significant advances in the field of hereditary CRC have been produced in the diagnosis and characterization of Lynch's syndrome and serrated polyposis syndrome.

Colonoscopic findings in first-degree relatives of patients with colorectal cancer: a population-based screening program

BACKGROUND

A screening colonoscopy is recommended in first-degree relatives (FDRs) of colorectal cancer patients; few prospective, controlled studies have evaluated colorectal findings in a population-based screening program.

OBJECTIVE

To evaluate the prevalence of colorectal neoplasia (adenomas and adenocarcinomas) in this increased-risk population, to compare it with that of average-risk individuals, and to identify features that might allow risk stratification for neoplasia among FDRs.

DESIGN

Cross-sectional study.

SETTING

Population-based screening program in Trentino, Italy.

PATIENTS

FDRs of colorectal cancer patients between 45 and 75 years of age with no history of hereditary colorectal cancer syndromes or inflammatory bowel disease.

CONTROLS

Average-risk individuals undergoing screening colonoscopy.

INTERVENTION

Screening colonoscopy.

RESULTS

Neoplasia was found in 33.4% of 1252 FDRs and in 30.3% of 765 controls; advanced neoplasia was found in 11.3% of FDRs and in 6.3% of controls. Odds ratios (ORs) from the multivariate logistic regression analysis adjusted for age, sex, cecal intubation rates, and colon cleansing showed an increased risk of advanced neoplasia (OR 2.41; 95% CI, 1.69-3.43; P < .0001) in FDRs. Age older than 56 years (OR 1.83; 95% CI, 1.15-2.99; P = .013) and male sex (OR 2.17; 95% CI, 1.39-3.10; P < .001) are independent predictors of advanced neoplasia.

LIMITATIONS

Italian subjects living in the same geographic area; of 4301 FDRs, 2521 were excluded.

CONCLUSIONS

The increased risk of advanced neoplasia supports the current recommendation for colonoscopic screening in this group; age and sex may assist in risk stratification of these individuals.