An enrichment model using regular health examination data for early detection of colorectal cancer

Abstract

ObjectiveChallenges remain in current practices of colorectal cancer (CRC) screening, such as low compliance, low specificities and expensive cost. This study aimed to identify high-risk groups for CRC from the general population using regular health examination data.MethodsThe study population consist of more than 7,000 CRC cases and more than 140,000 controls. Using regular health examination data, a model detecting CRC cases was derived by the classification and regression trees (CART) algorithm. Receiver operating characteristic (ROC) curve was applied to evaluate the performance of models. The robustness and generalization of the CART model were validated by independent datasets. In addition, the effectiveness of CART-based screening was compared with stool-based screening.ResultsAfter data quality control, 4,647 CRC cases and 133,898 controls free of colorectal neoplasms were used for downstream analysis. The final CART model based on four biomarkers (age, albumin, hematocrit and percent lymphocytes) was constructed. In the test set, the area under ROC curve (AUC) of the CART model was 0.88 [95% confidence interval (95% CI), 0.87−0.90] for detecting CRC. At the cutoff yielding 99.0% specificity, this model’s sensitivity was 62.2% (95% CI, 58.1%−66.2%), thereby achieving a 63-fold enrichment of CRC cases. We validated the robustness of the method across subsets of test set with diverse CRC incidences, aging rates, genders ratio, distributions of tumor stages and locations, and data sources. Importantly, CART-based screening had the higher positive predictive value (1.6%) than fecal immunochemical test (0.3%).ConclusionsAs an alternative approach for the early detection of CRC, this study provides a low-cost method using regular health examination data to identify high-risk individuals for CRC for further examinations. The approach can promote early detection of CRC especially in developing countries such as China, where annual health examination is popular but regular CRC-specific screening is rare.

Predictive model using hemoglobin, albumin, fibrinogen, and neutrophil-to-lymphocyte ratio to distinguish patients with colorectal cancer from those with benign adenoma

“…The final, best CART model consisted also of only four biomarkers: age, ALB, hematocrit/HGB and relative lymphocyte count (%). The CART model showed high AUC (0.88), sensitivity 62.2% at the high 99% specificity, in a multivariate CRC enrichment model [19]. It is in agreement with the results of our study and the idea that routinely used complete blood count may provide valuable information and an early warning for detection of cancer (CRC).…”

“…al. [19] designed a trial to identify the high-risk groups for CRC from a general population by their routine laboratory test biomarkers based on the regression trees (CART) model. The final, best CART model consisted also of only four biomarkers: age, ALB, hematocrit/HGB and relative lymphocyte count (%).…”

“…Many challenges remain in current practices of CRC screening and stratification, such as expensive cost, difficult logistic, low compliance and specificity. There were epidemiological studies using regular health examination data for valid screening for CRC using complete blood count [19]. Blood has a specific properties and functions in the human body [20].…”

Development and validation of two aspiration prediction models in patients receiving nasogastric feeding

“…Patients taking sedative-hypnotics were assigned 26 points. The risk of aspiration signified the aspiration probability ranging from 0.001 to 0.99. bottom shows the proportion of patients in the box to the total patients receiving nasogastric feeding (Shi et al, 2019). The optimal splitting points of the intubation depth and indwelling days were 48 cm and 24 days, respectively.…”

Real‐world application of a fast stool DNA test for colorectal cancer screening in primary screening positive population

“…Early screening has been demonstrated to be an effective strategy to reduce the incidence and mortality of CRC 3 . However, there are several challenges remaining in current practice of CRC screening in China, such as low compliance of colonoscopy, insufficient medical resources, low sensitivities of serum tumor markers, and financial burden of the government 4,5 . Therefore, a cost‐effective, accurate and noninvasive method is urgently needed to promote early CRC screening in China.…”