Risk Prediction Models for Colorectal Cancer: A Systematic Review

A novel model based on protein post-translational modifications comprising the immune landscape and prediction of colorectal cancer prognosis

Background

Phosphorylation is a critical post-translational modification (PTM) type contributing to colorectal cancer (CRC). The study aimed to construct a nomogram model to predict colon adenocarcinoma (COAD) prognosis based on PTM signatures.

Methods

The Cancer Genome Atlas (TCGA) database has been indexed for COAD patients' RNA sequencing, proteomic data, and clinical details. To find potential PTM prognostic signatures, the least absolute shrinkage and selection operator (LASSO) was deployed. Model validation procedures included the use of the Kaplan-Meier (K-M) method, the receiver operating characteristic (ROC) curve, the area under the curve (AUC), and the decision curve analysis (DCA). Additionally, biological enrichment, tumor immune microenvironment, and chemotherapy were also assessed. To validate the model, CRC cells were used in in vitro experiments using western blotting, proliferation assay, colony formation assay, and flow cytometry.

Results

The LASSO regression analysis identified 8 PTM sites. Based on the median PTM score, patients were classified into low- and high-risk groups. K-M results showed that high-risk patients had worse prognoses (P<0.001). Our model demonstrated powerful effectiveness and predictive value (TCGA whole group: 1-year AUC =0.611, 2-year AUC =0.574, 3-year AUC =0.627). Additionally, high-risk CRC patients were enriched in KRAS signaling pathways (P=0.01), possessed more robust immune escape capacity (P=0.001, and induced cell-cycle arrest of CRC cells (P<0.01).

Conclusions

We established and validated a novel nomogram model related to PTM that can predict prognosis and guide the treatment of COAD.

Development and evaluation of a risk prediction tool for risk-adapted screening of colorectal cancer in China

Risk prediction tools for colorectal cancer (CRC) have potential to improve the efficiency of population-based screening by facilitating risk-adapted strategies. However, such an applicable tool has yet to be established in the Chinese population. In this study, a risk score was created using data from the China Kadoorie Biobank (CKB), a nationwide cohort study of 409,854 eligible participants. Diagnostic performance of the risk score was evaluated in an independent CRC screening programme, which included 91,575 participants who accepted colonoscopy at designed hospitals in Zhejiang Province, China. Over a median follow-up of 11.1 years, 3136 CRC cases were documented in the CKB. A risk score was created based on nine questionnaire-derived variables, showing moderate discrimination for 10-year CRC risk (C-statistic = 0.68, 95 % CI: 0.67-0.69). In the CRC screening programme, the detection rates of CRC were 0.25 %, 0.82 %, and 1.93 % in low-risk (score <6), intermediate-risk (score: 6-19), and high-risk (score >19) groups, respectively. The newly developed score exhibited a C-statistic of 0.65 (95 % CI: 0.63-0.66), surpassing the widely adopted tools such as the Asia-Pacific Colorectal Screening (APCS), modified APCS, and Korean Colorectal Screening scores (all C-statistics = 0.60). In conclusion, we developed a novel risk prediction tool that is useful to identify individuals at high risk of CRC. A user-friendly online calculator was also constructed to encourage broader adoption of the tool.

Understanding the Preferences and Considerations of the Public Towards Risk-Stratified Screening for Colorectal Cancer: Insights From Think-Aloud Interviews Based on a Discrete Choice Experiment

CONTEXT

Risk stratification has been suggested as a strategy for improving cancer screening. Any changes to existing programmes must be acceptable to the public.

OBJECTIVE

This study aimed to explore the preferences and considerations of individuals relating to the introduction of different risk-based strategies to determine eligibility for colorectal cancer (CRC) screening.

STUDY DESIGN

Participants completed a discrete choice experiment (DCE) within online interviews. Nine conjoint-analysis tasks were created, each with two potential CRC screening programmes. The attributes included personal risk of CRC, screening invitation strategy and impact. Participants chose between programmes while thinking aloud and sharing their thoughts. Transcripts were analysed using codebook thematic analysis.

PARTICIPANTS

Twenty participants based in England aged 40-79 years without previous cancer history or medical expertise.

RESULTS

When choosing between programmes, participants first and primarily looked to prioritise saving lives. The harms associated with screening were viewed as a surprise but also felt by most to be inevitable; the benefits frequently outweighed, therefore, harms were considered less important. Risk stratification using individual characteristics was considered a nuanced approach to healthcare, which tended to be preferred over the age-alone model. Detailed personal risk information could be taken more seriously than non-personalised information to motivate behaviour change. Although it had minimal impact on decision-making, not diverting resources for screening from elsewhere was valued. Individuals who chose not to provide health information were considered irresponsible, while it was important that those with no information to provide should not lose out.

CONCLUSION

Risk-stratified CRC screening is generally aligned with public preferences, with decisions between possible stratification strategies dominated by saving lives. Even if attributes including risk factors, risk stratification strategy and risk communication contributed less to the overall decision to select certain programmes, some levels more clearly fulfilled public values; therefore, all these factors should be taken into consideration when redesigning and communicating CRC screening programmes.

PATIENT OR PUBLIC CONTRIBUTION

The primary data source for this study is interviews with 20 members of the public (current, past or future CRC screening invitees). Two public representatives contributed to planning this study, particularly the DCE.

Colorectal cancer risk stratification using a polygenic risk score in symptomatic primary care patients-a UK Biobank retrospective cohort study

Colorectal cancer (CRC) is a leading cause of cancer mortality worldwide. Accurate cancer risk assessment approaches could increase rates of early CRC diagnosis, improve health outcomes for patients and reduce pressure on diagnostic services. The faecal immunochemical test (FIT) for blood in stool is widely used in primary care to identify symptomatic patients with likely CRC. However, there is a 6-16% noncompliance rate with FIT in clinic and ~90% of patients over the symptomatic 10 µg/g test threshold do not have CRC. A polygenic risk score (PRS) quantifies an individual's genetic risk of a condition based on many common variants. Existing PRS for CRC have so far been used to stratify asymptomatic populations. We conducted a retrospective cohort study of 50,387 UK Biobank participants with a CRC symptom in their primary care record at age 40+. A PRS based on 201 variants, 5 genetic principal components and 22 other risk factors and markers for CRC were assessed for association with CRC diagnosis within 2 years of first symptom presentation using logistic regression. Associated variables were included in an integrated risk model and trained in 80% of the cohort to predict CRC diagnosis within 2 years. An integrated risk model combining PRS, age, sex, and patient-reported symptoms was predictive of CRC development in a testing cohort (receiver operating characteristic area under the curve, ROCAUC: 0.76, 95% confidence interval: 0.71-0.81). This model has the potential to improve early diagnosis of CRC, particularly in cases of patient noncompliance with FIT.

External validation of the colorectal cancer risk score LiFeCRC using food frequency questions in the HUNT study

PURPOSE

To mitigate the increasing colorectal cancer (CRC) incidence globally and prevent CRC at the individual level, individual lifestyle information needs to be easily translated into CRC risk assessment. Several CRC risk prediction models exist and their clinical usefulness depends on their ease of use. Our objectives were to assess and externally validate the LiFeCRC score in our independent, unselected population and to investigate the use of simpler food frequency measurements in the score.

METHODS

Incidental colon and rectal cancer cases were compared to the general population among 78,580 individuals participating in a longitudinal health study in Norway (HUNT). Vegetable, dairy product, processed meat and sugar/confectionary consumption was scored based on food frequency. The LiFeCRC risk score was calculated for each individual.

RESULTS

Over a median of 10 years following participation in HUNT, colon cancer was diagnosed in 1355 patients and rectal cancer was diagnosed in 473 patients. The LiFeCRC score using food frequencies demonstrated good discrimination in CRC overall (AUC 0.77) and in sex-specific models (AUC men 0.76 and women 0.77) in this population also including individuals ≥ 70 years and patients with diabetes. It performed somewhat better in colon (AUC 0.80) than in rectal cancer (AUC 0.72) and worked best for female colon cancer (AUC 0.81).

CONCLUSION

Readily available clinical variables and food frequency questions in a modified LiFeCRC score can identify patients at risk of CRC and may improve primary prevention by motivating to lifestyle change or participation in the CRC screening programme.

Risk Prediction Models for Oral Cancer: A Systematic Review

In the last 30 years, there has been an increasing incidence of oral cancer worldwide. Earlier detection of oral cancer has been shown to improve survival rates. However, given the relatively low prevalence of this disease, population-wide screening is likely to be inefficient. Risk prediction models could be used to target screening to those at highest risk or to select individuals for preventative interventions. This review (a) systematically identified published models that predict the development of oral cancer and are suitable for use in the general population and (b) described and compared the identified models, focusing on their development, including risk factors, performance and applicability to risk-stratified screening. A search was carried out in November 2022 in the Medline, Embase and Cochrane Library databases to identify primary research papers that report the development or validation of models predicting the risk of developing oral cancer (cancers of the oral cavity or oropharynx). The PROBAST tool was used to evaluate the risk of bias in the identified studies and the applicability of the models they describe. The search identified 11,222 articles, of which 14 studies (describing 23 models), satisfied the eligibility criteria of this review. The most commonly included risk factors were age (n = 20), alcohol consumption (n = 18) and smoking (n = 17). Six of the included models incorporated genetic information and three used biomarkers as predictors. Including information on human papillomavirus status was shown to improve model performance; however, this was only included in a small number of models. Most of the identified models (n = 13) showed good or excellent discrimination (AUROC > 0.7). Only fourteen models had been validated and only two of these validations were carried out in populations distinct from the model development population (external validation). Conclusions: Several risk prediction models have been identified that could be used to identify individuals at the highest risk of oral cancer within the context of screening programmes. However, external validation of these models in the target population is required, and, subsequently, an assessment of the feasibility of implementation with a risk-stratified screening programme for oral cancer.

Lifestyle predictors of colorectal cancer in European populations: a systematic review

Background

Colorectal cancer (CRC) is the second most prevalent cancer in Europe, with one-fifth of cases attributable to unhealthy lifestyles. Risk prediction models for quantifying CRC risk and identifying high-risk groups have been developed or validated across European populations, some considering lifestyle as a predictor.

Purpose

To identify lifestyle predictors considered in existing risk prediction models applicable for European populations and characterise their corresponding parameter values for an improved understanding of their relative contribution to prediction across different models.

Methods

A systematic review was conducted in PubMed and Web of Science from January 2000 to August 2021. Risk prediction models were included if (1) developed and/or validated in an adult asymptomatic European population, (2) based on non-invasively measured predictors and (3) reported mean estimates and uncertainty for predictors included. To facilitate comparison, model-specific lifestyle predictors were visualised using forest plots.

Results

A total of 21 risk prediction models for CRC (reported in 16 studies) were eligible, of which 11 were validated in a European adult population but developed elsewhere, mostly USA. All models but two reported at least one lifestyle factor as predictor. Of the lifestyle factors, the most common predictors were body mass index (BMI) and smoking (each present in 13 models), followed by alcohol (11), and physical activity (7), while diet-related factors were less considered with the most commonly present meat (9), vegetables (5) or dairy (2). The independent predictive contribution was generally greater when they were collected with greater detail, although a noticeable variation in effect size estimates for BMI, smoking and alcohol.

Conclusions

Early identification of high-risk groups based on lifestyle data offers the potential to encourage participation in lifestyle change and screening programmes, hence reduce CRC burden. We propose the commonly shared lifestyle predictors to be further used in public health prediction modelling for improved uptake of the model.

AGA Clinical Practice Update on Risk Stratification for Colorectal Cancer Screening and Post-Polypectomy Surveillance: Expert Review

DESCRIPTION

Since the early 2000s, there has been a rapid decline in colorectal cancer (CRC) mortality, due in large part to screening and removal of precancerous polyps. Despite these improvements, CRC remains the second leading cause of cancer deaths in the United States, with approximately 53,000 deaths projected in 2023. The aim of this American Gastroenterological Association (AGA) Clinical Practice Update Expert Review was to describe how individuals should be risk-stratified for CRC screening and post-polypectomy surveillance and to highlight opportunities for future research to fill gaps in the existing literature.

METHODS

This Expert Review was commissioned and approved by the American Gastroenterological Association (AGA) Institute Clinical Practice Updates Committee (CPUC) and the AGA Governing Board to provide timely guidance on a topic of high clinical importance to the AGA membership, and underwent internal peer review by the CPUC and external peer review through standard procedures of Gastroenterology. These Best Practice Advice statements were drawn from a review of the published literature and from expert opinion. Because systematic reviews were not performed, these Best Practice Advice statements do not carry formal ratings regarding the quality of evidence or strength of the presented considerations. Best Practice Advice Statements BEST PRACTICE ADVICE 1: All individuals with a first-degree relative (defined as a parent, sibling, or child) who was diagnosed with CRC, particularly before the age of 50 years, should be considered at increased risk for CRC. BEST PRACTICE ADVICE 2: All individuals without a personal history of CRC, inflammatory bowel disease, hereditary CRC syndromes, other CRC predisposing conditions, or a family history of CRC should be considered at average risk for CRC. BEST PRACTICE ADVICE 3: Individuals at average risk for CRC should initiate screening at age 45 years and individuals at increased risk for CRC due to having a first-degree relative with CRC should initiate screening 10 years before the age at diagnosis of the youngest affected relative or age 40 years, whichever is earlier. BEST PRACTICE ADVICE 4: Risk stratification for initiation of CRC screening should be based on an individual's age, a known or suspected predisposing hereditary CRC syndrome, and/or a family history of CRC. BEST PRACTICE ADVICE 5: The decision to continue CRC screening in individuals older than 75 years should be individualized, based on an assessment of risks, benefits, screening history, and comorbidities. BEST PRACTICE ADVICE 6: Screening options for individuals at average risk for CRC should include colonoscopy, fecal immunochemical test, flexible sigmoidoscopy plus fecal immunochemical test, multitarget stool DNA fecal immunochemical test, and computed tomography colonography, based on availability and individual preference. BEST PRACTICE ADVICE 7: Colonoscopy should be the screening strategy used for individuals at increased CRC risk. BEST PRACTICE ADVICE 8: The decision to continue post-polypectomy surveillance for individuals older than 75 years should be individualized, based on an assessment of risks, benefits, and comorbidities. BEST PRACTICE ADVICE 9: Risk-stratification tools for CRC screening and post-polypectomy surveillance that emerge from research should be examined for real-world effectiveness and cost-effectiveness in diverse populations (eg, by race, ethnicity, sex, and other sociodemographic factors associated with disparities in CRC outcomes) before widespread implementation.

Colorectal Cancer Screening Decision Based on Predicted Risk: Protocol for a Pilot Randomized Controlled Trial

BACKGROUND

Incidence of and mortality from colorectal cancer (CRC) can be effectively reduced by screening with the fecal immunochemical test (FIT) or colonoscopy. Individual risk to develop CRC within 15 years varies from <1% to >15% among people aged 50 to 75 years. Communicating personalized CRC risk and appropriate screening recommendations could improve the risk-benefit balance of screening test allocations and optimize the use of limited colonoscopy resources. However, significant uncertainty exists regarding the feasibility and efficacy of risk-based screening.

OBJECTIVE

We aim to study the effect of communicating individual CRC risk and a risk-based recommendation of the FIT or colonoscopy on participants' choice of screening test. We will also assess the feasibility of a larger clinical trial designed to evaluate the impact of personalized screening on clinical outcomes.

METHODS

We will perform a pilot randomized controlled trial among 880 residents aged 50 to 69 years eligible to participate in the organized screening program of the Vaud canton, Switzerland. Participants will be recruited by mail by the Vaud CRC screening program. Primary and secondary outcomes will be self-assessed through questionnaires. The risk score will be calculated using the open-source QCancer calculator that was validated in the United Kingdom. Participants will be stratified into 3 groups-low (<3%), moderate (3% to <6%), and high (≥6%) risk-according to their 15-year CRC risk and randomized within each risk stratum. The intervention group participants will receive a newly designed brochure with their personalized risk and screening recommendations. The control group will receive the usual brochure of the Vaud CRC screening program. Our primary outcome, measured using a self-administered questionnaire, is appropriate screening uptake 6 months after the intervention. Screening will be defined as appropriate if participants at high risk undertake colonoscopy and participants at low risk undertake the FIT. We will also measure the acceptability of the risk score and screening recommendations and the psychological factors influencing screening behavior. We will also assess the feasibility of a full-scale randomized controlled trial.

RESULTS

We expect that a total sample of 880 individuals will allow us to detect a difference of 10% (α=5%) between groups. The main outcome will be analyzed using a 2-tailed chi-squared test. We expect that appropriate screening uptake will be higher in the intervention group. No difference in overall screening uptake is expected.

CONCLUSIONS

We will test the impact of personalized risk information and screening recommendations on participants' choice of screening test in an organized screening program. This study should advance our understanding of the feasibility of large-scale risk-based CRC screening. Our results may provide insights into the optimization of CRC screening by offering screening options with a better risk-benefit balance and optimizing the use of resources.

TRIAL REGISTRATION

ClinicalTrials.gov NCT05357508; https://www.clinicaltrials.gov/study/NCT05357508.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/46865.

Polygenic scores in cancer

Since the publication of the first genome-wide association study for cancer in 2007, thousands of common alleles that are associated with the risk of cancer have been identified. The relative risk associated with individual variants is small and of limited clinical significance. However, the combined effect of multiple risk variants as captured by polygenic scores (PGSs) may be much greater and therefore provide risk discrimination that is clinically useful. We review the considerable research efforts over the past 15 years for developing statistical methods for PGSs and their application in large-scale genome-wide association studies to develop PGSs for various cancers. We review the predictive performance of these PGSs and the multiple challenges currently limiting the clinical application of PGSs. Despite this, PGSs are beginning to be incorporated into clinical multifactorial risk prediction models to stratify risk in both clinical trials and clinical implementation studies.

Prediction of advanced colorectal neoplasia based on metabolic parameters among symptomatic patients

BACKGROUND AND AIM

Worldwide, colorectal cancer (CRC) is the third most common cancer and ranks second among the leading causes of cancer death. This study aims to devise and validate a scoring system based on metabolic parameters to predict the risk of advanced colorectal neoplasia (ACN) in a large Chinese population.

METHODS

This was a cohort study of 495 584 symptomatic subjects aged 40 years or older who have received colonoscopy in Hong Kong from 1997 to 2017. The algorithm's discriminatory ability was evaluated as the area under the curve (AUC) of the mathematically constructed receiver operating characteristic curve.

RESULTS

Age, male gender, inpatient setting, abnormal aspartate transaminase/alanine transaminase, white blood cell, plasma gamma-glutamyl transferase, high-density lipoprotein cholesterol, triglycerides, and hemoglobin A1c were significantly associated with ACN. A scoring of < 2.65 was designated as "low risk (LR)." Scores at 2.65 or above had prevalence higher than the overall prevalence and hence were assigned as "high risk (HR)." The prevalence of ACN was 32% and 11%, respectively, for HR and LR groups. The AUC for the risk score in the derivation and validation cohort was 70.12%.

CONCLUSIONS

This study has validated a simple, accurate, and easy-to-use scoring algorithm, which has a high discriminatory capability to predict ACN in symptomatic patients. Future studies should examine its predictive performance in other population groups.

Development and External Validation of Partial Proportional Odds Risk Prediction Models for Cancer Stage at Diagnosis among Males and Females in Canada

Risk prediction models for cancer stage at diagnosis may identify individuals at higher risk of late-stage cancer diagnoses. Partial proportional odds risk prediction models for cancer stage at diagnosis for males and females were developed using data from Alberta's Tomorrow Project (ATP). Prediction models were validated on the British Columbia Generations Project (BCGP) cohort using discrimination and calibration measures. Among ATP males, older age at diagnosis was associated with an earlier stage at diagnosis, while full- or part-time employment, prostate-specific antigen testing, and former/current smoking were associated with a later stage at diagnosis. Among ATP females, mammogram and sigmoidoscopy or colonoscopy were associated with an earlier stage at diagnosis, while older age at diagnosis, number of pregnancies, and hysterectomy were associated with a later stage at diagnosis. On external validation, discrimination results were poor for both males and females while calibration results indicated that the models did not over- or under-fit to derivation data or over- or under-predict risk. Multiple factors associated with cancer stage at diagnosis were identified among ATP participants. While the prediction model calibration was acceptable, discrimination was poor when applied to BCGP data. Updating our models with additional predictors may help improve predictive performance.

Predicting suicide risk in 137,112 people with severe mental illness in Finland: external validation of the Oxford Mental Illness and Suicide tool (OxMIS)

Oxford Mental Illness and Suicide tool (OxMIS) is a standardised, scalable, and transparent instrument for suicide risk assessment in people with severe mental illness (SMI) based on 17 sociodemographic, criminal history, familial, and clinical risk factors. However, alongside most prediction models in psychiatry, external validations are currently lacking. We utilised a Finnish population sample of all persons diagnosed by mental health services with SMI (schizophrenia-spectrum and bipolar disorders) between 1996 and 2017 (n = 137,112). To evaluate the performance of OxMIS, we initially calculated the predicted 12-month suicide risk for each individual by weighting risk factors by effect sizes reported in the original OxMIS prediction model and converted to a probability. This probability was then used to assess the discrimination and calibration of the OxMIS model in this external sample. Within a year of assessment, 1.1% of people with SMI (n = 1475) had died by suicide. The overall discrimination of the tool was good, with an area under the curve of 0.70 (95% confidence interval: 0.69-0.71). The model initially overestimated suicide risks in those with elevated predicted risks of >5% over 12 months (Harrell's E_max = 0.114), which applied to 1.3% (n = 1780) of the cohort. However, when we used a 5% maximum predicted suicide risk threshold as is recommended clinically, the calibration was excellent (ICI = 0.002; E_max = 0.005). Validating clinical prediction tools using routinely collected data can address research gaps in prediction psychiatry and is a necessary step to translating such models into clinical practice.

Validation of a breast cancer risk prediction model based on the key risk factors: family history, mammographic density and polygenic risk

PURPOSE

We compared a simple breast cancer risk prediction model, BRISK (which includes mammographic density, polygenic risk and clinical factors), against a similar model with more risk factors (simplified Rosner) and against two commonly used clinical models (Gail and IBIS).

METHODS

Using nested case-control data from the Nurses' Health Study, we compared the models' association, discrimination and calibration. Classification performance was compared between Gail and BRISK for 5-year risks and between IBIS and BRISK for remaining lifetime risk.

RESULTS

The odds ratio per standard deviation was 1.43 (95% CI 1.32, 1.55) for BRISK 5-year risk, 1.07 (95% CI 0.99, 1.14) for Gail 5-year risk, 1.72 (95% CI 1.59, 1.87) for simplified Rosner 10-year risk, 1.51 (95% CI 1.41, 1.62) for BRISK remaining lifetime risk and 1.26 (95% CI 1.16, 1.36) for IBIS remaining lifetime risk. The area under the receiver operating characteristic curve (AUC) was improved for BRISK over Gail for 5-year risk (AUC = 0.636 versus 0.511, P < 0.0001) and for BRISK over IBIS for remaining lifetime risk (AUC = 0.647 versus 0.571, P < 0.0001). BRISK was well calibrated for the estimation of both 5-year risk (expected/observed [E/O] = 1.03; 95% CI 0.73, 1.46) and remaining lifetime risk (E/O = 1.01; 95% CI 0.86, 1.17). The Gail 5-year risk (E/O = 0.85; 95% CI 0.58, 1.24) and IBIS remaining lifetime risk (E/O = 0.73; 95% CI 0.60, 0.87) were not well calibrated, with both under-estimating risk. BRISK improves classification of risk compared to Gail 5-year risk (NRI = 0.31; standard error [SE] = 0.031) and IBIS remaining lifetime risk (NRI = 0.287; SE = 0.035).

CONCLUSION

BRISK performs better than two commonly used clinical risk models and no worse compared to a similar model with more risk factors.

Colorectal Cancer Risk Assessment and Precision Approaches to Screening: Brave New World or Worlds Apart?

Current colorectal cancer (CRC) screening recommendations take a "one-size-fits-all" approach using age as the major criterion to initiate screening. Precision screening that incorporates factors beyond age to risk stratify individuals could improve on current approaches and optimally use available resources with benefits for patients, providers, and health care systems. Prediction models could identify high-risk groups who would benefit from more intensive screening, while low-risk groups could be recommended less intensive screening incorporating noninvasive screening modalities. In addition to age, prediction models incorporate well-established risk factors such as genetics (eg, family CRC history, germline, and polygenic risk scores), lifestyle (eg, smoking, alcohol, diet, and physical inactivity), sex, and race and ethnicity among others. Although several risk prediction models have been validated, few have been systematically studied for risk-adapted population CRC screening. In order to envisage clinical implementation of precision screening in the future, it will be critical to develop reliable and accurate prediction models that apply to all individuals in a population; prospectively study risk-adapted CRC screening on the population level; garner acceptance from patients and providers; and assess feasibility, resources, cost, and cost-effectiveness of these new paradigms. This review evaluates the current state of risk prediction modeling and provides a roadmap for future implementation of precision CRC screening.

Using Online Colorectal Cancer Risk Calculators to Guide Screening Decision-Making

BACKGROUND

Several online calculators estimate colorectal cancer risk, but their consistency is unknown. Our objectives were to quantify the variation in predicted risk and to determine which calculators are best used in the clinical setting.

METHODS

We used the Google search engine to identify online colorectal cancer risk calculators and assessed the output of each for 3 hypothetical screening scenarios (low-, average-, and high-risk), varied by age (50, 62, 75 years), sex, and race (Black, White), with risk levels based on risk-appropriate values for variables in each model. Estimated risks for models within a given scenario were rated as consistent or inconsistent based on comparison with either the absolute magnitude of difference or average lifetime risk of colorectal cancer. Summary statistics for consistent and inconsistent estimates were compared using chi-square and Fisher's exact tests.

RESULTS

We identified 5 online colorectal cancer risk calculators. Inconsistencies were found in none of 5-year, 19% of 10-year, and 81% of lifetime colorectal cancer risk estimate comparisons (P < .001). For a 50-year-old, 22% of risk estimate comparisons were inconsistent, vs 33% for a 62-year-old, and 36% for a 75-year-old (P = 0.14).

CONCLUSIONS

Online colorectal cancer risk models are more consistent in predicting colorectal cancer risk for 5- and 10-year time frames compared with lifetime. For a US population, the National Cancer Institute's Colorectal Cancer Risk Assessment Tool is a rigorously developed calculator that can be used in the clinical setting to provide 5-year and lifetime risk estimates.

Prediction of Gastrointestinal Tract Cancers Using Longitudinal Electronic Health Record Data

BACKGROUND

Luminal gastrointestinal (GI) tract cancers, including esophageal, gastric, small bowel, colorectal, and anal cancers, are often diagnosed at late stages. These tumors can cause gradual GI bleeding, which may be unrecognized but detectable by subtle laboratory changes. Our aim was to develop models to predict luminal GI tract cancers using laboratory studies and patient characteristics using logistic regression and random forest machine learning methods.

METHODS

The study was a single-center, retrospective cohort at an academic medical center, with enrollment between 2004-2013 and with follow-up until 2018, who had at least two complete blood counts (CBCs). The primary outcome was the diagnosis of GI tract cancer. Prediction models were developed using multivariable single timepoint logistic regression, longitudinal logistic regression, and random forest machine learning.

RESULTS

The cohort included 148,158 individuals, with 1025 GI tract cancers. For 3-year prediction of GI tract cancers, the longitudinal random forest model performed the best, with an area under the receiver operator curve (AuROC) of 0.750 (95% CI 0.729-0.771) and Brier score of 0.116, compared to the longitudinal logistic regression model, with an AuROC of 0.735 (95% CI 0.713-0.757) and Brier score of 0.205.

CONCLUSIONS

Prediction models incorporating longitudinal features of the CBC outperformed the single timepoint logistic regression models at 3-years, with a trend toward improved accuracy of prediction using a random forest machine learning model compared to a longitudinal logistic regression model.

Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review

The inclusion of machine-learning-derived models in systematic reviews of risk prediction models for colorectal cancer is rare. Whilst such reviews have highlighted methodological issues and limited performance of the models included, it is unclear why machine-learning-derived models are absent and whether such models suffer similar methodological problems. This scoping review aims to identify machine-learning models, assess their methodology, and compare their performance with that found in previous reviews. A literature search of four databases was performed for colorectal cancer prediction and prognosis model publications that included at least one machine-learning model. A total of 14 publications were identified for inclusion in the scoping review. Data was extracted using an adapted CHARM checklist against which the models were benchmarked. The review found similar methodological problems with machine-learning models to that observed in systematic reviews for non-machine-learning models, although model performance was better. The inclusion of machine-learning models in systematic reviews is required, as they offer improved performance despite similar methodological omissions; however, to achieve this the methodological issues that affect many prediction models need to be addressed.

Opportunistic colonoscopy in healthy individuals: A non-trivial risk of adenoma

BACKGROUND

Colorectal cancer (CRC) is the second leading cause of cancer death worldwide. Opportunistic colonoscopy may be beneficial in reducing the incidence of CRC by detecting its precursors.

AIM

To determine the risk of colorectal adenomas in a population who underwent opportunistic colonoscopy, and demonstrate the need for opportunistic colonoscopy.

METHODS

A questionnaire was distributed to patients who underwent colonoscopy in the First Affiliated Hospital of Zhejiang Chinese Medical University from December 2021 to January 2022. The patients were divided into two groups, the opportunistic colonoscopy group who underwent a health examination including colonoscopy without intestinal symptoms due to other diseases, and the non-opportunistic group. The risk of adenomas and influence factors were analyzed.

RESULTS

Patients who underwent opportunistic colonoscopy had a similar risk to the non-opportunistic group, in terms of overall polyps (40.8% vs. 40.5%, P = 0.919), adenomas (25.8% vs. 27.6%, P = 0.581), advanced adenomas (8.7% vs. 8.6%, P = 0.902) and CRC (0.6% vs. 1.2%, P = 0.473). Patients with colorectal polyps and adenomas in the opportunistic colonoscopy group were younger (P = 0.004). There was no difference in the detection rate of polyps between patients who underwent colonoscopy as part of a health examination and those who underwent colonoscopy for other reasons. In patients with intestinal symptoms, abnormal intestinal motility and changes in stool characteristics were frequent (P = 0.014).

CONCLUSION

The risk of overall colonic polyps, advanced adenomas in healthy people undergoing opportunistic colonoscopy no less than that in the patients with intestinal symptoms, positive FOBT, abnormal tumor markers, and who accepted re-colonoscopy after polypectomy. Our study indicates that more attention should be paid to the population without intestinal symptoms, especially smokers and those older than 40 years.

Predictors of treatment refusal in patients with colorectal cancer: A systematic review

This systematic review was conducted to investigate predictors of treatment refusal in colorectal cancer (CRC) patients. An understanding of these predictors would inform statistical models for the identification of high-risk patients who might benefit from interventions that seek to improve treatment compliance. We performed a search of PubMed and Scopus to identify potentially relevant studies on predictors of treatment refusal in CRC patients that were published between January 1, 2000 and December 31, 2021. We screened manuscripts using predefined eligibility criteria. Information on study design, study location, patient characteristics, treatments, rates and predictors of treatment refusal, and the impact of treatment refusal on mortality or survival were collected from eligible studies. Study quality was assessed using the Newcastle-Ottawa score. The overall findings of the review process were summarized using descriptive statistics and a narrative synthesis. A total of 13 studies were included in this review. Ten studies reported on refusal of CRC surgery, refusal rate: 0.25%-3.26%; three studies reported on chemotherapy refusal (one of which reported on both surgery and chemotherapy refusal), refusal rate: 7.8%-41.5%; and one study reported on refusal of any cancer treatment, refusal rate: 8.7%. The bulk of the published literature confirmed the harmful association between treatment refusal and poor survival outcomes in CRC patients. Frequently cited predictors of treatment refusal included patient demographic characteristics (age, race, gender), clinical characteristics (disease stage, comorbidity), and factors that impact access to cancer care services (healthcare insurance, facility level). Potentially high rates of treatment refusal pose a challenge to CRC control. This review has identified several factors which must be considered when attempting to reduce treatment refusal in CRC patients. Furthermore, these factors should be tested as components of predictive risk models for this important outcome.

Risk prediction models for head and neck cancer: A rapid review

Background

Cancer risk assessment models are used to support prevention and early detection. However, few models have been developed for head and neck cancer (HNC).

Methods

A rapid review of Embase and MEDLINE identified n = 3045 articles. Following dual screening, n = 14 studies were included. Quality appraisal using the PROBAST (risk of bias) instrument was conducted, and a narrative synthesis was performed to identify the best performing models in terms of risk factors and designs.

Results

Six of the 14 models were assessed as "high" quality. Of these, three had high predictive performance achieving area under curve values over 0.8 (0.87-0.89). The common features of these models were their inclusion of predictors carefully tailored to the target population/anatomical subsite and development with external validation.

Conclusions

Some existing models do possess the potential to identify and stratify those at risk of HNC but there is scope for improvement.

[PAPPS Expert Groups. Cancer prevention recommendations: Update 2022]

Cancer is a major cause of morbidity and mortality. Tobacco use, unhealthy diet, and physical inactivity are some of the lifestyle risk factors that have led to an increase in cancer. This article updates the evidence and includes recommendations for prevention strategies for each of the cancers with the highest incidence. These are based on the reduction of risk factors (primary prevention) and early diagnosis of cancer through screening and early detection of signs and symptoms, in medium-risk and high-risk populations. This update of the 2022 PAPPS has taken into account the vision of the National Health System Cancer Strategy, an update approved by the Interterritorial Council of the National Health System on January 2021 and the European Strategy (Europe's Beating Cancer Plan) presented on 4 February 2021.

Full Blood Count Trends for Colorectal Cancer Detection in Primary Care: Development and Validation of a Dynamic Prediction Model

Colorectal cancer has low survival rates when late-stage, so earlier detection is important. The full blood count (FBC) is a common blood test performed in primary care. Relevant trends in repeated FBCs are related to colorectal cancer presence. We developed and internally validated dynamic prediction models utilising trends for early detection. We performed a cohort study. Sex-stratified multivariate joint models included age at baseline (most recent FBC) and simultaneous trends over historical haemoglobin, mean corpuscular volume (MCV), and platelet measurements up to baseline FBC for two-year risk of diagnosis. Performance measures included the c-statistic and calibration slope. We analysed 250,716 males and 246,695 females in the development cohort and 312,444 males and 462,900 females in the validation cohort, with 0.4% of males and 0.3% of females diagnosed two years after baseline FBC. Compared to average population trends, patient-level declines in haemoglobin and MCV and rise in platelets up to baseline FBC increased risk of diagnosis in two years. C-statistic: 0.751 (males) and 0.763 (females). Calibration slope: 1.06 (males) and 1.05 (females). Our models perform well, with low miscalibration. Utilising trends could bring forward diagnoses to earlier stages and improve survival rates. External validation is now required.

External validation of models for predicting risk of colorectal cancer using the China Kadoorie Biobank

BACKGROUND

In China, colorectal cancer (CRC) incidence and mortality have been steadily increasing over the last decades. Risk models to predict incident CRC have been developed in various populations, but they have not been systematically externally validated in a Chinese population.  This study aimed to assess the performance of risk scores in predicting CRC using the China Kadoorie Biobank (CKB), one of the largest and geographically diverse prospective cohort studies in China.

METHODS

Nine models were externally validated in 512,415 participants in CKB and included 2976 cases of CRC. Model discrimination was assessed, overall and by sex, age, site, and geographic location, using the area under the receiver operating characteristic curve (AUC). Model discrimination of these nine models was compared to a model using age alone. Calibration was assessed for five models, and they were re-calibrated in CKB.

RESULTS

The three models with the highest discrimination (Ma (Cox model) AUC 0.70 [95% CI 0.69-0.71]; Aleksandrova 0.70 [0.69-0.71]; Hong 0.69 [0.67-0.71]) included the variables age, smoking, and alcohol. These models performed significantly better than using a model based on age alone (AUC of 0.65 [95% CI 0.64-0.66]). Model discrimination was generally higher in younger participants, males, urban environments, and for colon cancer. The two models (Guo and Chen) developed in Chinese populations did not perform better than the others. Among the 10% of participants with the highest risk, the three best performing models identified 24-26% of participants that went on to develop CRC.

CONCLUSIONS

Several risk models based on easily obtainable demographic and modifiable lifestyle factor have good discrimination in a Chinese population. The three best performing models have a higher discrimination than using a model based on age alone.

Metformin use is not associated with colorectal cancer incidence in type-2 diabetes patients: evidence from methods that avoid immortal time bias

PURPOSE

Immortal time bias (ITB) continues to distort many observational studies on metformin use and cancer risk. Our objective was to employ three statistical methods proven to avoid ITB and compare their results to that of a naïve time-fixed analysis in order to provide further evidence of metformin's association, or none thereof, with colorectal cancer (CRC) incidence.

METHODS

A total of 41,533 Korean subjects with newly diagnosed type-2 diabetes in 2005-2015 were selected from a prospectively maintained cohort (median follow-up of 6.3 years). Time-to-CRC incidence was regressed upon metformin use (yes/no, average prescription days/year) using time-dependent Cox, landmark, nested case-control, and time-fixed Cox analyses. Other CRC risk factors were included to adjust for possible confounding.

RESULTS

Neither metformin ever-use nor average metformin prescription days/year was associated with incident CRC hazard in time-dependent Cox, landmark, and nested case-control analyses with HR (95% CI) of 0.88 (0.68-1.13), 0.86 (0.65-1.12), and 1.10 (0.86-1.40) for metformin ever-use, and 0.97 (0.90-1.04), 0.95 (0.88-1.04), and 1.02 (0.95-1.10) for average metformin prescription days/year, respectively. In contrast, time-fixed Cox regression showed a falsely exaggerated protective effect of metformin on CRC incidence.

CONCLUSION

The association between metformin use and subsequent CRC incidence was statistically nonsignificant after accounting for time-related biases such as ITB. Previous studies that avoided these biases and meta-analyses of RCTs on metformin and cancer incidence were in agreement with our results. A definitive, large-scale RCT is needed to clarify this topic, and future observational studies should be explicit in avoiding ITB and other time-related biases.

Cost-effectiveness of risk-tailored screening strategy for colorectal cancer: A systematic review

BACKGROUND AND AIM

Though one-size-fits-all age-based screening for colorectal cancer (CRC) is effective in reducing the incidence and mortality, the evidence regarding on personized screening based on individual risk factors has been growing. The study aimed to perform a systematic review to synthesize economic evidence of risk-tailored CRC screening strategies.

METHODS

This systematic review was conducted in EMBASE, Web of Science, PubMed, Cochrane Library, Econlit, and National Institute for Health Research Economic Evaluation Database from inception to June 30, 2021. We calculated the incremental cost-effectiveness ratio (ICER) of cost per life year or quality-adjusted life year gained for the risk-tailored screening compared with no screening or uniform screening. A strategy was cost-effective with less cost and equal or more effectiveness than the comparator along with lower ICER than the willingness-to-pay threshold.

RESULTS

Our review finally comprised seven studies. Five studies reported the results of comparisons of risk-tailored CRC screening with no screening, and supported that risk-tailored screening was cost-effective. All of seven studies reported the ICERs of risk-tailored screening and age-based screening. Disparities in the discrimination of risk-prediction tool, accuracy of adopted techniques, uptake rate of screening and cost estimation impacted the cost-effectiveness.

CONCLUSIONS

Studies on the economic evaluation of risk-tailored CRC screening are limited, and current evidence is not sufficient to support the replacement of risk-tailored screening for traditional age-based screening.

Expression of Autophagic and Inflammatory Markers in Normal Mucosa of Individuals with Colorectal Adenomas: A Cross Sectional Study among Italian Outpatients Undergoing Colonoscopy

Colorectal cancer (CRC) ranks among the three most common cancers in terms of both cancer incidence and cancer-related deaths in Western industrialized countries. Lifetime risk of colorectal cancer may reach 6% of the population living in developed countries. In the current era of personalized medicine, CRC is no longer considered as a single entity. In more recent years many studies have described the distinct differences in epidemiology, pathogenesis, genetic and epigenetic alterations, molecular pathways and outcome depending on the anatomical site. The aim of our study is to assess in a multidimensional model the association between metabolic status and inflammatory and autophagic changes in the normal colorectal mucosa classified as right-sided, left-sided and rectum, and the presence of adenomas. One hundred and sixteen patients undergoing colonoscopy were recruited and underwent a complete serum lipid profile, immunofluorescence analysis of colonic biopsies for MAPLC3 and myeloperoxidase expression, matched with clinical and anthropometric characteristics. Presence of adenomas correlated with cholesterol (total and LDL) levels, IL-6 levels, and MAPLC3 tissue expression, especially in the right colon. In conclusion, serum IL-6 amount and autophagic markers could be good predictors of the presence of colorectal adenomas.

Risk-stratified selection to colonoscopy in FIT colorectal cancer screening: development and temporal validation of a prediction model

BACKGROUND

Faecal immunochemical tests (FITs) yield many false positives and challenge colonoscopy capacity in colorectal cancer (CRC) screening programmes. We aimed to develop a risk-based selection of participants to undergo diagnostic colonoscopy.

METHODS

The study was observational and used registry data from the Danish CRC screening programme. We included all participants invited 2014-2016 with a positive FIT (≥ 20 μg fHb/g) who underwent colonoscopy (n = 56,459). We predicted the risk of CRC or advanced neoplasia (AN) from age, gender and FIT value using logistic regression. We evaluated calibration and discrimination and conducted temporal validation. We compared the number of CRCs and adenomas identified by risk cut-offs and by a corresponding FIT cut-off.

RESULTS

AUCs were 74.9% (95% CI: 73.6; 76.3) and 67.4% (95% CI: 66.8%; 68.0%) for the models predicting CRC and AN in the validation dataset. The cut-off of CRC risk calculated from age, gender and FIT value identified 1.03 times (95% CI: 1.02; 1.05) more CRCs and 1.01 times (95% CI: 1.01; 1.01) more medium/high-risk adenomas compared with the corresponding FIT cut-off.

CONCLUSIONS

With existing data, risk-stratified FIT screening using a risk cut-off instead of a FIT cut-off can slightly improve the selection to colonoscopy of those at highest risk of cancer and adenomas.

Methodological conduct of prognostic prediction models developed using machine learning in oncology: a systematic review

BACKGROUND

Describe and evaluate the methodological conduct of prognostic prediction models developed using machine learning methods in oncology.

METHODS

We conducted a systematic review in MEDLINE and Embase between 01/01/2019 and 05/09/2019, for studies developing a prognostic prediction model using machine learning methods in oncology. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement, Prediction model Risk Of Bias ASsessment Tool (PROBAST) and CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS) to assess the methodological conduct of included publications. Results were summarised by modelling type: regression-, non-regression-based and ensemble machine learning models.

RESULTS

Sixty-two publications met inclusion criteria developing 152 models across all publications. Forty-two models were regression-based, 71 were non-regression-based and 39 were ensemble models. A median of 647 individuals (IQR: 203 to 4059) and 195 events (IQR: 38 to 1269) were used for model development, and 553 individuals (IQR: 69 to 3069) and 50 events (IQR: 17.5 to 326.5) for model validation. A higher number of events per predictor was used for developing regression-based models (median: 8, IQR: 7.1 to 23.5), compared to alternative machine learning (median: 3.4, IQR: 1.1 to 19.1) and ensemble models (median: 1.7, IQR: 1.1 to 6). Sample size was rarely justified (n = 5/62; 8%). Some or all continuous predictors were categorised before modelling in 24 studies (39%). 46% (n = 24/62) of models reporting predictor selection before modelling used univariable analyses, and common method across all modelling types. Ten out of 24 models for time-to-event outcomes accounted for censoring (42%). A split sample approach was the most popular method for internal validation (n = 25/62, 40%). Calibration was reported in 11 studies. Less than half of models were reported or made available.

CONCLUSIONS

The methodological conduct of machine learning based clinical prediction models is poor. Guidance is urgently needed, with increased awareness and education of minimum prediction modelling standards. Particular focus is needed on sample size estimation, development and validation analysis methods, and ensuring the model is available for independent validation, to improve quality of machine learning based clinical prediction models.

Risk of Colorectal Cancer in Patients With Irritable Bowel Syndrome: A Meta-Analysis of Population-Based Observational Studies

Background and Aims

Evidence on the association between irritable bowel syndrome (IBS) and colorectal cancer (CRC) risk is inconsistent. Therefore, we aimed to examine whether IBS leads to an increased risk for CRC using a systematic review and meta-analysis approach.

Methods

PubMed, Embase, and Web of Science were systematically searched to identify all relevant literature published through July 30, 2021. The pooled risk ratios (RRs) and corresponding 95% confidence intervals (CIs) for CRC after diagnosis of IBS were computed using random-and fixed-effects models and stratified by age, follow-up time, gender, and study design. The quality of included studies was assessed by the Newcastle-Ottawa scale.

Results

We included six studies consisting of 1,085,024 participants. Overall, the risk of detecting CRC after the initial IBS diagnosis was significantly higher than non-IBS controls (RR = 1.52, 95% CI: 1.04-2.22, P = 0.032). The peak of elevated risk occurred within the first year of IBS diagnosis (RR = 6.84, 95% CI: 3.70-12.65, P < 0.001), and after 1 year, the risk of CRC was similar to that of the general population (RR = 1.02, 95% CI: 0.88-1.18, P = 0.813). Notably, we found that the RR of CRC was more significant in IBS patients younger than 50 years compared to those older than 50 years (RR = 2.03, 95% CI: 1.17-3.53, P = 0.012 vs. 1.28, 95%CI: 0.94-1.75, P = 0.118, respectively). Gender and study design did not affect the results.

Conclusion

The risk of CRC within one year of the initial IBS diagnosis was increased approximately six-fold, whereas the long-term risk was not increased. However, current evidence does not support that IBS leads to an increased incidence of CRC, and the early excess risk is more likely attributable to misclassification resulting from overlapping symptoms rather than causation. Clinicians must remain vigilant for the CRC risk in patients younger than 50 years with IBS-like symptoms to avoid delaying necessary screening.

Five-year absolute risk estimates of colorectal cancer based on CCRAT model and polygenic risk scores: A validation study using the Quebec population-based cohort CARTaGENE

The objective was to evaluate the predictive performance of the Colorectal Cancer Risk Assessment Tool (CCRAT) and three polygenic risk scores (Hsu et al., 2015; Law et al., 2019, Archambault et al., 2020) to predict the occurrence of colorectal cancer at five years in a Quebec population-based cohort. By using the CARTaGENE cohort, we computed the absolute risk of colorectal cancer with the CCRAT model, the polygenic risk scores (PRS) and combined clinico-genetic models (CCRAT + PRS). We also tailored the CCRAT model by using the marginal age-specific colorectal incidence rates in Canada and the risk score distribution. We reported the calibration and the discrimination. Performances of the PRSs, combined and tailored CCRAT models were compared to the original CCRAT model. The expected-to-observed ratio of the original CCRAT model was 0.54 [0.43-0.68]. The c-index was 74.79 [68.3-80.5]. The tailored CCRAT model improved the expected-to-observed ratio (0.74 [0.59-0.94]) and c-index (76.39 [69.7-82.1]). All PRS improved the expected-to-observed ratios (around 0.83, confidence intervals including one). PRSs' c-indexes were not significantly different from CCRAT models. Results from the combined models were close to those from the PRS models, Archambault combined model's c-index being significantly higher than the original and tailored CCRAT models (78.67 [70.8-86.5]; p < 0.001 and p = 0.028, respectively). In this Quebec cohort, CCRAT model has a good discrimination with a poor calibration. While the tailored CCRAT provides some gain in calibration, clinico-genetic models improved both calibration and discrimination. However, better calibrations must be obtained before a practical use among the inhabitants of Quebec province.

Polygenic risk prediction models for colorectal cancer: a systematic review

BACKGROUND

Risk prediction models incorporating single nucleotide polymorphisms (SNPs) could lead to individualized prevention of colorectal cancer (CRC). However, the added value of incorporating SNPs into models with only traditional risk factors is still not clear. Hence, our primary aim was to summarize literature on risk prediction models including genetic variants for CRC, while our secondary aim was to evaluate the improvement of discriminatory accuracy when adding SNPs to a prediction model with only traditional risk factors.

METHODS

We conducted a systematic review on prediction models incorporating multiple SNPs for CRC risk prediction. We tested whether a significant trend in the increase of Area Under Curve (AUC) according to the number of SNPs could be observed, and estimated the correlation between AUC improvement and number of SNPs. We estimated pooled AUC improvement for SNP-enhanced models compared with non-SNP-enhanced models using random effects meta-analysis, and conducted meta-regression to investigate the association of specific factors with AUC improvement.

RESULTS

We included 33 studies, 78.79% using genetic risk scores to combine genetic data. We found no significant trend in AUC improvement according to the number of SNPs (p for trend = 0.774), and no correlation between the number of SNPs and AUC improvement (p = 0.695). Pooled AUC improvement was 0.040 (95% CI: 0.035, 0.045), and the number of cases in the study and the AUC of the starting model were inversely associated with AUC improvement obtained when adding SNPs to a prediction model. In addition, models constructed in Asian individuals achieved better AUC improvement with the incorporation of SNPs compared with those developed among individuals of European ancestry.

CONCLUSIONS

Though not conclusive, our results provide insights on factors influencing discriminatory accuracy of SNP-enhanced models. Genetic variants might be useful to inform stratified CRC screening in the future, but further research is needed.

Designing a Predictive Model for Colorectal Neoplasia Diagnosis Based on Clinical and Laboratory Findings in Colonoscopy Candidate Patients

BACKGROUND

Health authorities have expanded two strategies to diminish CRC-related influence: CR screening and improve diagnostic process in symptomatic patients. The aim of the current study is to design a predictive model to identify the most important risk factors that can efficiently predict patients who have high risk of colorectal neoplasia.

METHOD

A cross-sectional study was constructed to include all patients who had positive test for FIT or had one or more risk factors for colorectal cancer based on the guidelines of detecting high-risk groups for colorectal cancer in Iran. Multivariable binary logistic regression model was constructed for prediction of colorectal neoplasia. We used sensitivity, specificity, positive and negative predictive value, and positive and negative likelihood ratio to check the accuracy. The Hosmer-Lemeshow test, chi-square test, and p value were used to determine the precision of model.

RESULT

Following an AIC stepwise selection model, only nine potential variables, namely gender, watery diarrhea, IBD, abdominal pain, melena, body mass index, depression drug, anti-inflammatory drug, and age, were found to be a predictor of colorectal neoplasia. The best cut-point probability in the final model was 0.27 and results of sensitivity and specificity, based on maximizing these two criteria, were 66% and 62%, respectively.

CONCLUSION

Overall, our model prediction was comparable with other risk prediction models for colorectal cancer. It had a modest discriminatory power to distinguish an individual's neoplasia colorectal risk.

Risk Prediction Model for Esophageal Cancer Among General Population: A Systematic Review

Objective: The risk prediction model is an effective tool for risk stratification and is expected to play an important role in the early detection and prevention of esophageal cancer. This study sought to summarize the available evidence of esophageal cancer risk predictions models and provide references for their development, validation, and application. Methods: We searched PubMed, EMBASE, and Cochrane Library databases for original articles published in English up to October 22, 2021. Studies that developed or validated a risk prediction model of esophageal cancer and its precancerous lesions were included. Two reviewers independently extracted study characteristics including predictors, model performance and methodology, and assessed risk of bias and applicability with PROBAST (Prediction model Risk Of Bias Assessment Tool). Results: A total of 20 studies including 30 original models were identified. The median area under the receiver operating characteristic curve of risk prediction models was 0.78, ranging from 0.68 to 0.94. Age, smoking, body mass index, sex, upper gastrointestinal symptoms, and family history were the most commonly included predictors. None of the models were assessed as low risk of bias based on PROBST. The major methodological deficiencies were inappropriate date sources, inconsistent definition of predictors and outcomes, and the insufficient number of participants with the outcome. Conclusions: This study systematically reviewed available evidence on risk prediction models for esophageal cancer in general populations. The findings indicate a high risk of bias due to several methodological pitfalls in model development and validation, which limit their application in practice.

A user-friendly objective prediction model in predicting colorectal cancer based on 234 044 Asian adults in a prospective cohort

BACKGROUND

Prediction models of colorectal cancer (CRC) had limited application for not being user-friendly. Whether fecal immunochemical tests (FITs) can help predict CRC has been overlooked.

PATIENTS AND METHODS

With 1972 CRCs identified, 234 044 adults aged ≥40 years were successively enrolled between 1994 and 2008. Prediction models were developed by questionnaire/medical screening and quantitative FIT. NNS (number needed to scope to find one cancer) is time dependent, spanning entire study period. Significant 'risk factors' were family history, body mass index, smoking, drinking, inactivity, hypertension, diabetes, carcinoembryonic antigen, and C-reactive protein.

RESULTS

Positive FIT (≥20 μg/g hemoglobin/feces) had cancer risk 10-fold larger than negative FIT, and within each age group, another 10-fold difference. The C statistic of FIT (0.81) with age and sex alone was superior to the 'common risk-factors' model (0.73). NNS, stratified by age and by FIT values, demonstrated a scorecard of cancer risks, like 1/15 or 1/25, in 5 years. When FIT was negative, cancer risk was small (1/750-1/3000 annually). The larger the FIT, the sooner the appearance of CRC. For every 80-μg/g increase of FIT, there were 1.5-year earlier development of CRC incidence and 1-year earlier development of CRC mortality, respectively. Given the same FIT value, CRC events appeared in the proximal colon sooner than the distal colon.

CONCLUSIONS

A simple user-friendly model based on a single FIT value to predict CRC risk was developed. When positive, NNS offered a simple quantitative value, with a better precision than most risk factors, even combined. When FIT is negative, risk is very small, but requiring a repeat every other year to rule out false negative. FIT values correlated well with CRC prognosis, with worst for proximal CRC.

The classification capability of the Asia Pacific Colorectal Screening score in Korea: an analysis of the Cancer Screenee Cohort

OBJECTIVES

This study aimed to validate a simple risk assessment tool for estimating the advanced colorectal neoplasia (ACN) risk at colonoscopy screenings and potential factors relevant for implementing this tool in the Korean population.

METHODS

Our study analyzed data from the Cancer Screenee Cohort Study conducted by the National Cancer Center in Korea. The risk level was assessed using the Asia Pacific Colorectal Screening (APCS) score developed by the Asia-Pacific Working Group on Colorectal Cancer. Logistic regression models were used to examine the associations between colorectal-related outcomes and the risk level by APCS score. The discriminatory performance of the APCS score for various colorectal-related outcomes was assessed using C-statistics.

RESULTS

In 12,520 individuals, 317 ACN cases and 4,528 adenoma cases were found. The APCS tool successfully classified the study population into different risk groups, and significant differences in the ACN rate and other outcomes were observed. The APCS score demonstrated acceptable discrimination capability with area under the curve values ranging from 0.62 to 0.65 for various outcomes. The results of the multivariate logistic regression model revealed that the high-risk group had a 3.1-fold higher risk of ACN (95% confidence interval, 2.08 to 4.67) than the average-risk group. Body mass index (BMI) was identified as a significant predictor of ACN in both multivariate and subgroup analyses.

CONCLUSIONS

Our study highlighted significant differences in colorectal-related screening outcomes by colorectal risk level measured using the APCS score, and BMI could be used to improve the discriminatory capability of the APCS score.

Reporting of prognostic clinical prediction models based on machine learning methods in oncology needs to be improved

OBJECTIVE

Evaluate the completeness of reporting of prognostic prediction models developed using machine learning methods in the field of oncology.

STUDY DESIGN AND SETTING

We conducted a systematic review, searching the MEDLINE and Embase databases between 01/01/2019 and 05/09/2019, for non-imaging studies developing a prognostic clinical prediction model using machine learning methods (as defined by primary study authors) in oncology. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement to assess the reporting quality of included publications. We described overall reporting adherence of included publications and by each section of TRIPOD.

RESULTS

Sixty-two publications met the inclusion criteria. 48 were development studies and 14 were development with validation studies. 152 models were developed across all publications. Median adherence to TRIPOD reporting items was 41% [range: 10%-67%] and at least 50% adherence was found in 19% (n=12/62) of publications. Adherence was lower in development only studies (median: 38% [range: 10%-67%]); and higher in development with validation studies (median: 49% [range: 33%-59%]).

CONCLUSION

Reporting of clinical prediction models using machine learning in oncology is poor and needs urgent improvement, so readers and stakeholders can appraise the study methods, understand study findings, and reduce research waste.

Predicting the risk of cancer in adults using supervised machine learning: a scoping review

OBJECTIVES

The purpose of this scoping review is to: (1) identify existing supervised machine learning (ML) approaches on the prediction of cancer in asymptomatic adults; (2) to compare the performance of ML models with each other and (3) to identify potential gaps in research.

DESIGN

Scoping review using the population, concept and context approach.

SEARCH STRATEGY

PubMed search engine was used from inception to 10 November 2020 to identify literature meeting following inclusion criteria: (1) a general adult (≥18 years) population, either sex, asymptomatic (population); (2) any study using ML techniques to derive predictive models for future cancer risk using clinical and/or demographic and/or basic laboratory data (concept) and (3) original research articles conducted in all settings in any region of the world (context).

RESULTS

The search returned 627 unique articles, of which 580 articles were excluded because they did not meet the inclusion criteria, were duplicates or were related to benign neoplasm. Full-text reviews were conducted for 47 articles and a final set of 10 articles were included in this scoping review. These 10 very heterogeneous studies used ML to predict future cancer risk in asymptomatic individuals. All studies reported area under the receiver operating characteristics curve (AUC) values as metrics of model performance, but no study reported measures of model calibration.

CONCLUSIONS

Research gaps that must be addressed in order to deliver validated ML-based models to assist clinical decision-making include: (1) establishing model generalisability through validation in independent cohorts, including those from low-income and middle-income countries; (2) establishing models for all cancer types; (3) thorough comparisons of ML models with best available clinical tools to ensure transparency of their potential clinical utility; (4) reporting of model calibration performance and (5) comparisons of different methods on the same cohort to reveal important information about model generalisability and performance.

Optimizing Positivity Thresholds for a Risk-Adapted Screening Strategy in Colorectal Cancer Screening

INTRODUCTION

Risk-adapted screening combining the Asia-Pacific Colorectal Screening score, fecal immunochemical test (FIT), and colonoscopy improved the yield of colorectal cancer screening than FIT. However, the optimal positivity thresholds of risk scoring and FIT of such a strategy warrant further investigation.

METHODS

We included 3,407 participants aged 50-74 years undergoing colonoscopy from a colorectal cancer screening trial. For the risk-adapted screening strategy, subjects were referred for subsequent colonoscopy or FIT according to their risk scores. Diagnostic performance was evaluated for FIT and the risk-adapted screening method with various positivity thresholds. Furthermore, a modeled screening cohort was established to compare the yield and cost using colonoscopy, FIT, and the risk-adapted screening method in a single round of screening.

RESULTS

Risk-adapted screening method had higher sensitivity for advanced neoplasm (AN) (27.6%-76.3% vs 13.8%-17.3%) but lower specificity (46.6%-90.8% vs 97.4%-98.8%) than FIT did. In a modeled screening cohort, FIT-based screening would be slightly affected because the threshold varied with a reduction of 76.0%-80.9% in AN detection and 82.0%-84.4% in cost when compared with colonoscopy. By contrast, adjusting the threshold of Asia-Pacific Colorectal Screening score from 3 to 5 points for risk-adapted screening varied from an increase of 12.6%-14.1% to a decrease of 55.6%-60.1% in AN detection, with the reduction of cost from 4.2%-5.3% rising to 66.4%-68.5%.

DISCUSSION

With an appropriate positivity threshold tailored to clinical practice, the risk-adapted screening could save colonoscopy resources and cost compared with the colonoscopy-only and FIT-only strategies.

The Costs and Benefits of Risk Stratification for Colorectal Cancer Screening Based On Phenotypic and Genetic Risk: A Health Economic Analysis

Population-based screening for colorectal cancer is an effective and cost-effective way of reducing colorectal cancer incidence and mortality. Many genetic and phenotypic risk factors for colorectal cancer have been identified, leading to development of colorectal cancer risk scores with varying discrimination. However, these are not currently used by population screening programs. We performed an economic analysis to assess the cost-effectiveness, clinical outcomes, and resource impact of using risk-stratification based on phenotypic and genetic risk, taking a UK National Health Service perspective. Biennial fecal immunochemical test (FIT), starting at an age determined through risk-assessment at age 40, was compared with FIT screening starting at a fixed age for all individuals. Compared with inviting everyone from age 60, using a risk score with area under the receiver operating characteristic curve of 0.721 to determine FIT screening start age, produces 418 QALYs, costs £247,000, and results in 218 fewer colorectal cancer cases and 156 fewer colorectal cancer deaths per 100,000 people, with similar FIT screening invites. There is 96% probability that risk-stratification is cost-effective, with net monetary benefit (based on £20,000 per QALY threshold) estimated at £8.1 million per 100,000 people. The maximum that could be spent on risk-assessment and still be cost-effective is £114 per person. Lower benefits are produced with lower discrimination risk scores, lower mean screening start age, or higher FIT thresholds. Risk-stratified screening benefits men more than women. Using risk to determine FIT screening start age could improve the clinical outcomes and cost effectiveness of colorectal cancer screening without using significant additional screening resources. PREVENTION RELEVANCE: Colorectal cancer screening is essential for early detection and prevention of colorectal cancer, but implementation is often limited by resource constraints. This work shows that risk-stratification using genetic and phenotypic risk could improve the effectiveness and cost-effectiveness of screening programs, without using substantially more screening resources than are currently available.

Regulation of KRAS protein expression by miR-544a and KRAS-LCS6 polymorphism in wild-type KRAS sporadic colon adenocarcinoma

Colorectal carcinoma (CRC) results from the accumulation of genetic mutations and alterations in signaling pathways. KRAS is mutated in 40% of CRC cases and is involved in increased tumor cells proliferation and survival. Although KRAS mutations are a dominant event in CRC tumorigenesis, increased wild-type KRAS expression has a similar effect on accelerated tumor growth. In this study, we investigated the KRAS status in correlation with clinicopathological features in sporadic CRC and more importantly the role of let-7a-5p and miR-544a-3p in the regulation of wild-type KRAS protein expression in the tumor center (T1) and invasive tumor front (T2). Analysis showed that 39.1% of tumor samples had KRAS mutations. In wild-type KRAS tumors, 62.0% were positive for KRAS protein expression and there was a higher percentage of KRAS-positive tumor cells and a higher intensity of immunohistochemical reaction in T2 than in T1 samples. This could not be attributed to differences in KRAS mRNA levels, suggesting regulation via miR-544a-3p expression which was significantly decreased in T2 samples. Furthermore, we demonstrated that tumor samples carrying the KRAS-LCS6 variant allele had significantly higher protein expression of the wild-type KRAS. Our results suggest the role of the KRAS-LCS6 polymorphism and miR-544a-3p expression in the regulation of wild-type KRAS protein expression in sporadic CRC.

Alterations, Interactions, and Diagnostic Potential of Gut Bacteria and Viruses in Colorectal Cancer

Gut microbiome alteration was closely associated with colorectal cancer (CRC). Previous studies had demonstrated the bacteria composition changes but lacked virome profiles, trans-kindom interactions, and reliable diagnostic model explorations in CRC. Hence, we performed metagenomic sequencing to investigate the gut microbiome and microbial interactions in adenoma and CRC patients. We found the decreased microbial diversity in CRC and revealed the taxonomic alterations of bacteria and viruses were highly associated with CRC at the species level. The relative abundance of oral-derived species, such as Fusobacterium nucleatum, Fusobacterium hwasookii, Porphyromonas gingivalis, and Bacteroides fragilis, increased. At the same time, butyrate-producing and anti-inflammatory microbes decreased in adenoma and CRC by non-parametric Kruskal-Wallis test. Despite that, the relative abundance of Escherichia viruses and Salmonella viruses increased, whereas some phages, including Enterobacteria phages and Uncultured crAssphage, decreased along with CRC development. Gut bacteria was negatively associated with viruses in CRC and healthy control by correlation analysis (P=0.017 and 0.002, respectively). Viruses were much more dynamic than the bacteria as the disease progressed, and the altered microbial interactions were distinctively stage-dependent. The degree centrality of microbial interactions decreased while closeness centrality increased along with the adenoma to cancer development. Uncultured crAssphage was the key bacteriophage that enriched in healthy controls and positively associated with butyrate-producing bacteria. Diagnostic tests based on bacteria by random forest confirmed in independent cohorts showed better performance than viruses for CRC. In conclusion, our study revealed the novel CRC-associated bacteria and viruses that exhibited specific differences and intensive microbial correlations, which provided a reliable diagnostic panel for CRC.

Evaluation of a risk score based on dietary and lifestyle factors to target a population at risk in colorectal cancer screening

BACKGROUND

The aim of our study was to assess three risk scores to predict lesions, advanced neoplasia (high-risk adenomas and colorectal cancer (CRC)) and CRC in individuals who participate to colorectal cancer screening.

METHODS

The data of dietary and lifestyle risk factors were carried out during 2 mass screening campaigns in France (2013-2016) and the FOBT result was collected until December 2018. The colonoscopy result in positive FOBT was recovered. Three risk scores (Betés score, Kaminski score and adapted-HLI) were calculated to detect individuals at risk of lesions.

RESULTS

The Betés score had an AUROC of 0.63 (95% CI, [0.61-0.66]) for lesions, 0.65 (95% CI, [0.61-0.68]) for advanced neoplasia and 0.65 (95% CI, [0.58-0.72]) for predicting screen-detected CRC. The adapted HLI score had an AUROC of 0.61 (95% CI, [0.58-0.65]) for lesions, 0.61 (95% CI, [0.56-0.65]) for advanced neoplasia and 0.55 (95% CI, [0.45-0.65]) for predicting screen-detected CRC. The Kaminski score had an AUROC of 0.65 (95% CI, [0.63-0.68]) for lesions, 0.65 (95% CI, [0.61-0.68]) for advanced neoplasia and 0.69 (95% CI, [0.62-0.76]) for predicting screen-detected CRC.

CONCLUSION

A simple questionnaire based on CRC risk factors could help general practitioners to identify participants with higher risk of significant colorectal lesions and incite them to perform the fecal occult blood test.