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

Non-invasive early detection on esophageal squamous cell carcinoma and precancerous lesions by microbial biomarkers combining epidemiological factors in China

BACKGROUND

Microbiota may be associated with esophageal squamous cell carcinoma (ESCC) development. However, it is not known the predictive value of microbial biomarkers combining epidemiological factors for the early detection of ESCC and precancerous lesions.

METHODS

A total of 449 specimens (esophageal swabs and saliva) were collected from 349 participants with different esophageal statuses in China to explore and validate ESCC-associated microbial biomarkers from genes level to species level by 16S rRNA sequencing, metagenomic sequencing and real-time quantitative polymerase chain reaction.

RESULTS

A bacterial biomarker panel including Actinomyces graevenitzii (A.g_1, A.g_2, A.g_3, A.g_4), Fusobacteria nucleatum (F.n_1, F.n_2, F.n_3), Haemophilus haemolyticus (H.h_1), Porphyromonas gingivalis (P.g_1, P.g_2, P.g_3) and Streptococcus australis (S.a_1) was explored by metagenomic sequencing to early detect the participants in Need group (low-grade intraepithelial neoplasia, high-grade intraepithelial neoplasia and ESCC) vs participants without these lesions as the Noneed group. Significant quantitative differences existed for each microbial target in which the detection efficiency rate was higher in saliva than esophageal swab. In saliva, the area under the curve (AUC) based on the microbial biomarkers (A.g_4 ∩ P.g_3 ∩ H.h_1 ∩ S.a_1 ∩ F.n_2) was 0.722 (95% CI 0.621-0.823) in the exploration cohort. Combining epidemiological factors (age, smoking, drinking, intake of high-temperature food and toothache), the AUC improved to 0.869 (95% CI 0.802-0.937) in the exploration cohort, which was validated with AUC of 0.757 (95% CI 0.663-0.852) in the validation cohort.

CONCLUSIONS

It is feasible to combine microbial biomarkers in saliva and epidemiological factors to early detect ESCC and precancerous lesions in China.

Performance of Prediction Models for Esophageal Squamous Cell Carcinoma in General Population: A Systematic Review and External Validation Study

INTRODUCTION

Prediction models for esophageal squamous cell carcinoma (ESCC) need to be proven effective in the target population before they can be applied to population-based endoscopic screening to improve cost-effectiveness. We have systematically reviewed ESCC prediction models applicable to the general population and performed external validation and head-to-head comparisons in a large multicenter prospective cohort including 5 high-risk areas of China (Fei Cheng, Lin Zhou, Ci Xian, Yang Zhong, and Yan Ting).

METHODS

Models were identified through a systematic review and validated in a large population-based multicenter prospective cohort that included 89,753 participants aged 40-69 years who underwent their first endoscopic examination between April 2017 and March 2021 and were followed up until December 31, 2022. Model performance in external validation was estimated based on discrimination and calibration. Discrimination was assessed by C-statistic (concordance statistic), and calibration was assessed by calibration plot and Hosmer-Lemeshow test.

RESULTS

The systematic review identified 15 prediction models that predicted severe dysplasia and above lesion (SDA) or ESCC in the general population, of which 11 models (4 SDA and 7 ESCC) were externally validated. The C-statistics ranged from 0.67 (95% confidence interval 0.66-0.69) to 0.70 (0.68-0.71) of the SDA models, and the highest was achieved by Liu et al (2020) and Liu et al (2022). The C-statistics ranged from 0.51 (0.48-0.54) to 0.74 (0.71-0.77), and Han et al (2023) had the best discrimination of the ESCC models. Most models were well calibrated after recalibration because the calibration plots coincided with the x = y line.

DISCUSSION

Several prediction models showed moderate performance in external validation, and the prediction models may be useful in screening for ESCC. Further research is needed on model optimization, generalization, implementation, and health economic evaluation.

Design of risk prediction model for esophageal cancer based on machine learning approach

Background and aim

Esophageal cancer (EC) is a highly prevalent and progressive disease. Early prediction of EC risk in the population is crucial in preventing this disease and enhancing the overall health of individuals. So far, few studies have been conducted on predicting the EC risk based on the prediction models, and most of them focused on statistical methods. The ML approach obtained efficient predictive insights into the clinical domain. Therefore, this study aims to develop a risk prediction model for EC based on risk factors and by leveraging the ML approach to stratify the high-risk EC people and obtain efficient preventive purposes at the community level.

Material and methods

The current retrospective study was performed from 2018 to 2022 in Sari City based on 3256 EC and non-EC cases. The six selected algorithms, including Random Forest (RF), eXtreme Gradient Boosting (XG-Boost), Bagging, K-Nearest Neighbor (K-NN), Support Vector Machine (SVM), and Artificial Neural Networks (ANNs), were used to develop the risk prediction model for EC and achieve the preventive purposes.

Results

Comparing the performance efficiency of algorithms revealed that the XG-Boost model gained the best predictability for EC risk with AU-ROC = 0.92 and AU-ROC-test = 0.889 for internal and validation states, respectively. Based on the XG-Boost, the factors, including sex, drinking hot liquids, fruit consumption, achalasia, and vegetable consumption, were considered the five top predictors of EC risk.

Conclusion

This study showed that the XG-Boost could provide insight into the early prediction of the EC risk for people and clinical providers to stratify the high-risk group of EC and achieve preventive measures based on modifying the risk factors associated with EC and other clinical solutions.

Development and validation of a novel risk prediction algorithm to estimate 10-year risk of oesophageal cancer in primary care: prospective cohort study and evaluation of performance against two other risk prediction models

Background

Methods to identify patients at increased risk of oesophageal cancer are needed to better identify those for targeted screening. We aimed to derive and validate novel risk prediction algorithms (CanPredict) to estimate the 10-year risk of oesophageal cancer and evaluate performance against two other risk prediction models.

Methods

Prospective open cohort study using routinely collected data from 1804 QResearch® general practices. We used 1354 practices (12.9 M patients) to develop the algorithm. We validated the algorithm in 450 separate practices from QResearch (4.12 M patients) and 355 Clinical Practice Research Datalink (CPRD) practices (2.53 M patients). The primary outcome was an incident diagnosis of oesophageal cancer found in GP, mortality, hospital, or cancer registry data. Patients were aged 25-84 years and free of oesophageal cancer at baseline. Cox proportional hazards models were used with prediction selection to derive risk equations. Risk factors included age, ethnicity, Townsend deprivation score, body mass index (BMI), smoking, alcohol, family history, relevant co-morbidities and medications. Measures of calibration, discrimination, sensitivity, and specificity were calculated in the validation cohorts.

Finding

There were 16,384 incident cases of oesophageal cancer in the derivation cohort (0.13% of 12.9 M). The predictors in the final algorithms were: age, BMI, Townsend deprivation score, smoking, alcohol, ethnicity, Barrett's oesophagus, hiatus hernia, H. pylori infection, use of proton pump inhibitors, anaemia, lung and blood cancer (with breast cancer in women). In the QResearch validation cohort in women the explained variation (R2) was 57.1%; Royston's D statistic 2.36 (95% CI 2.26-2.46); C statistic 0.859 (95% CI 0.849-0.868) and calibration was good. Results were similar in men. For the 20% at highest predicted risk, the sensitivity was 76%, specificity was 80.1% and the observed risk at 10 years was 0.76%. The results from the CPRD validation were similar.

Interpretation

We have developed and validated a novel prediction algorithm to quantify the absolute risk of oesophageal cancer. The CanPredict algorithms could be used to identify high risk patients for targeted screening.

Funding

Innovate UK and CRUK (grant 105857).

Current Status and Future Prospects for Esophageal Cancer

Esophageal cancer (EC) is the ninth most common cancer and the sixth leading cause of cancer deaths worldwide. Esophageal squamous cell carcinoma (ESCC) and esophageal adenocarcinoma (EAC) are the two main histological subtypes with distinct epidemiological and clinical features. While the global incidence of ESCC is declining, the incidence of EAC is increasing in many countries. Decades of epidemiologic research have identified distinct environmental exposures for ESCC and EAC subtypes. Recent advances in understanding the genomic aspects of EC have advanced our understanding of EC causes and led to using specific genomic alterations in EC tumors as biomarkers for early diagnosis, treatment, and prognosis of this cancer. Nevertheless, the prognosis of EC is still poor, with a five-year survival rate of less than 20%. Currently, there are significant challenges for early detection and secondary prevention for both ESCC and EAC subtypes, but Cytosponge™ is shifting this position for EAC. Primary prevention remains the preferred strategy for reducing the global burden of EC. In this review, we will summarize recent advances, current status, and future prospects of the studies related to epidemiology, time trends, environmental risk factors, prevention, early diagnosis, and treatment for both EC subtypes.

lncRNA SSTR5-AS1 Predicts Poor Prognosis and Contributes to the Progression of Esophageal Cancer

Esophageal cancer (ESCA), as a common cancer worldwide, is a main cause of cancer-related mortality. Long noncoding RNAs (lncRNAs) have been shown in an increasing number of studies to be capable of playing an important regulatory function in human malignancies. Our study is aimed at delving into the prognostic value and potential function of lncRNA SSTR5-AS1 (SSTR5-AS1) in ESCA. The gene expression data of 182 ESCA samples from TCGA and 653 nontumor specimens from GTEx. The expressions of SSTR5-AS1 were analyzed. We investigated whether there was a correlation between the expression of SSTR5-AS1 and the clinical aspects of ESCA. In order to compare survival curves, the Kaplan-Meier method together with the log-rank test was utilized. The univariate and multivariate Cox regression models were used to analyze the data in order to determine the SSTR5-AS1 expression's significance as a prognostic factor in ESCA patients. In order to investigate the level of SSTR5-AS1 expression in ESCA cells, RT-PCR was utilized. CCK-8 trials served as a model for the loss-of-function tests. In this study, we found that the expressions of SSTR5-AS1 were increased in ESCA specimens compared with nontumor specimens. According to the ROC assays, high SSTR5-AS1 expression had an AUC value of 0.7812 (95% CI: 0.7406 to 0.8217) for ESCA. Patients who had a high level of SSTR5-AS1 expression had a lower overall survival rate than those who had a low level of SSTR5-AS1 expression. In addition, multivariate analysis suggested that SSTR5-AS1 was an independent predictor of overall survival for ESCA patients. Moreover, RT-PCR experiments indicated that SSTR5-AS1 expression was distinctly increased in three ESCA cells compared with HET1A cells. CCK-8 experiments indicated that silence of SSTR5-AS1 distinctly inhibited the proliferation of ESCA cells. Overall, ESCA patients with elevated SSTR5-AS1 had a worse chance of survival, suggesting it could be used as a prognostic and diagnostic biomarker for ESCA.

Development and Validation of Esophageal Squamous Cell Carcinoma Risk Prediction Models Based on an Endoscopic Screening Program

IMPORTANCE

Assessment tools are lacking for screening of esophageal squamous cell cancer (ESCC) in China, especially for the follow-up stage. Risk prediction to optimize the screening procedure is urgently needed.

OBJECTIVE

To develop and validate ESCC prediction models for identifying people at high risk for follow-up decision-making.

DESIGN, SETTING, AND PARTICIPANTS

This open, prospective multicenter diagnostic study has been performed since September 1, 2006, in Shandong Province, China. This study used baseline and follow-up data until December 31, 2021. The data were analyzed between April 6 and May 31, 2022. Eligibility criteria consisted of rural residents aged 40 to 69 years who had no contraindications for endoscopy. Among 161 212 eligible participants, those diagnosed with cancer or who had cancer at baseline, did not complete the questionnaire, were younger than 40 years or older than 69 years, or were detected with severe dysplasia or worse lesions were eliminated from the analysis.

EXPOSURES

Risk factors obtained by questionnaire and endoscopy.

MAIN OUTCOMES AND MEASURES

Pathological diagnosis of ESCC and confirmation by cancer registry data.

RESULTS

In this diagnostic study of 104 129 participants (56.39% women; mean [SD] age, 54.31 [7.64] years), 59 481 (mean [SD] age, 53.83 [7.64] years; 58.55% women) formed the derivation set while 44 648 (mean [SD] age, 54.95 [7.60] years; 53.51% women) formed the validation set. A total of 252 new cases of ESCC were diagnosed during 424 903.50 person-years of follow-up in the derivation cohort and 61 new cases from 177 094.10 person-years follow-up in the validation cohort. Model A included the covariates age, sex, and number of lesions; model B included age, sex, smoking status, alcohol use status, body mass index, annual household income, history of gastrointestinal tract diseases, consumption of pickled food, number of lesions, distinct lesions, and mild or moderate dysplasia. The Harrell C statistic of model A was 0.80 (95% CI, 0.77-0.83) in the derivation set and 0.90 (95% CI, 0.87-0.93) in the validation set; the Harrell C statistic of model B was 0.83 (95% CI, 0.81-0.86) and 0.91 (95% CI, 0.88-0.95), respectively. The models also had good calibration performance and clinical usefulness.

CONCLUSIONS AND RELEVANCE

The findings of this diagnostic study suggest that the models developed are suitable for selecting high-risk populations for follow-up decision-making and optimizing the cancer screening process.

Tobacco Smoking and Gastrointestinal Cancer Risk

Background

Smoking tobacco is the most preventable cause of gastrointestinal (GI) cancer disease in Germany. The more and the longer you smoke, the higher your risk of GI cancer. About 28% of 18-64 year-old Germans are current smokers; in addition, 11% of the population is regularly exposed to secondhand tobacco smoke.

Summary

Tobacco use is causally associated with esophageal, gastric, pancreatic, biliary, hepatocellular, colorectal, and anal cancers. Combining smoking with alcohol use, excess body weight, diabetes, or chronic infections synergistically enhances GI cancer risk. Smoking cessation effectively reduces tobacco-associated GI cancer risk.

Key Messages

Smokers should be encouraged to stop smoking tobacco and join programs of risk-adaptive cancer screening.