[China guideline for the screening, early detection and early treatment of esophageal cancer (2022, Beijing)]

Development of an artificial intelligent model for pre-endoscopic screening of precancerous lesions in gastric cancer

BACKGROUND

Given the high cost of endoscopy in gastric cancer (GC) screening, there is an urgent need to explore cost-effective methods for the large-scale prediction of precancerous lesions of gastric cancer (PLGC). We aim to construct a hierarchical artificial intelligence-based multimodal non-invasive method for pre-endoscopic risk screening, to provide tailored recommendations for endoscopy.

METHODS

From December 2022 to December 2023, a large-scale screening study was conducted in Fujian, China. Based on traditional Chinese medicine theory, we simultaneously collected tongue images and inquiry information from 1034 participants, considering the potential of these data for PLGC screening. Then, we introduced inquiry information for the first time, forming a multimodality artificial intelligence model to integrate tongue images and inquiry information for pre-endoscopic screening. Moreover, we validated this approach in another independent external validation cohort, comprising 143 participants from the China-Japan Friendship Hospital.

RESULTS

A multimodality artificial intelligence-assisted pre-endoscopic screening model based on tongue images and inquiry information (AITonguequiry) was constructed, adopting a hierarchical prediction strategy, achieving tailored endoscopic recommendations. Validation analysis revealed that the area under the curve (AUC) values of AITonguequiry were 0.74 for overall PLGC (95% confidence interval (CI) 0.71-0.76, p < 0.05) and 0.82 for high-risk PLGC (95% CI 0.82-0.83, p < 0.05), which were significantly and robustly better than those of the independent use of either tongue images or inquiry information alone. In addition, AITonguequiry has superior performance compared to existing PLGC screening methodologies, with the AUC value enhancing 45% in terms of PLGC screening (0.74 vs. 0.51, p < 0.05) and 52% in terms of high-risk PLGC screening (0.82 vs. 0.54, p < 0.05). In the independent external verification, the AUC values were 0.69 for PLGC and 0.76 for high-risk PLGC.

CONCLUSION

Our AITonguequiry artificial intelligence model, for the first time, incorporates inquiry information and tongue images, leading to a higher precision and finer-grained pre-endoscopic screening of PLGC. This enhances patient screening efficiency and alleviates patient burden.

Latest insights into the global epidemiological features, screening, early diagnosis and prognosis prediction of esophageal squamous cell carcinoma

As a highly invasive carcinoma, esophageal cancer (EC) was the eighth most prevalent malignancy and the sixth leading cause of cancer-related death worldwide in 2020. Esophageal squamous cell carcinoma (ESCC) is the major histological subtype of EC, and its incidence and mortality rates are decreasing globally. Due to the lack of specific early symptoms, ESCC patients are usually diagnosed with advanced-stage disease with a poor prognosis, and the incidence and mortality rates are still high in many countries, especially in China. Therefore, enormous challenges still exist in the management of ESCC, and novel strategies are urgently needed to further decrease the incidence and mortality rates of ESCC. Although the key molecular mechanisms underlying ESCC pathogenesis have not been fully elucidated, certain promising biomarkers are being investigated to facilitate clinical decision-making. With the advent and advancement of high-throughput technologies, such as genomics, proteomics and metabolomics, valuable biomarkers with high sensitivity, specificity and stability could be identified for ESCC. Herein, we aimed to determine the epidemiological features of ESCC in different regions of the world, especially in China, and focused on novel molecular biomarkers associated with ESCC screening, early diagnosis and prognosis prediction.

Esophageal cancer screening, early detection and treatment: Current insights and future directions

Esophageal cancer ranks among the most prevalent malignant tumors globally, primarily due to its highly aggressive nature and poor survival rates. According to the 2020 global cancer statistics, there were approximately 604000 new cases of esophageal cancer, resulting in 544000 deaths. The 5-year survival rate hovers around a mere 15%-25%. Notably, distinct variations exist in the risk factors associated with the two primary histological types, influencing their worldwide incidence and distribution. Squamous cell carcinoma displays a high incidence in specific regions, such as certain areas in China, where it meets the cost-effectiveness criteria for widespread endoscopy-based early diagnosis within the local population. Conversely, adenocarcinoma (EAC) represents the most common histological subtype of esophageal cancer in Europe and the United States. The role of early diagnosis in cases of EAC originating from Barrett's esophagus (BE) remains a subject of controversy. The effectiveness of early detection for EAC, particularly those arising from BE, continues to be a debated topic. The variations in how early-stage esophageal carcinoma is treated in different regions are largely due to the differing rates of early-stage cancer diagnoses. In areas with higher incidences, such as China and Japan, early diagnosis is more common, which has led to the advancement of endoscopic methods as definitive treatments. These techniques have demonstrated remarkable efficacy with minimal complications while preserving esophageal functionality. Early screening, prompt diagnosis, and timely treatment are key strategies that can significantly lower both the occurrence and death rates associated with esophageal cancer.

Secular trends and attributable risk factors of esophageal cancer deaths among non-elderly adults based on Global Burden of Disease Study

OBJECTIVE

Esophageal cancer (EC) poses a persistent threat to the health of non-elderly adults. This study aims to elucidate the temporal trends of EC-related mortality and investigate the impact of various risk factors on such deaths in the age group of 20-59 years, spanning 3 decades.

METHODS

Data on EC deaths were acquired from the Global Burden of Disease, Injuries, and Risk Factors (GBD) study. We employed estimated average percentage change (EAPC) and linear mixed-effects (LME) models to analyze mortality trends and pertinent risk factors for EC.

RESULTS

Between 1990 and 2019, EC mortality showed a downward trend, and the global number of deaths from EC among non-elderly adults surged by 24.37%. During this period, mortality rates saw an increase in only two regions-the Caribbean and Western Sub-Saharan Africa (EAPCs > 0). For male deaths, smoking and alcohol use emerged as the primary risk factors, while high body mass index (BMI) stood out as the main risk factor for female deaths. Furthermore, the LME model identified male sex, advancing age, alcohol use, smoking, and chewing tobacco as factors associated with an additional rise in EC deaths.

CONCLUSION

EC continues to exert a substantial toll on mortality among young and middle-aged adults globally. Implementing targeted interventions are significant in alleviating the burden of this disease within this population.

Identifying potential DNA methylation markers for the detection of esophageal cancer in plasma

Background: Esophageal cancer (EC) is a leading cause of cancer-related deaths in China, with the 5-year survival rate reaching less than 30%, because most cases were diagnosed and treated at the advanced stage. However, there is still a lack of low-cost, efficient, and accurate non-invasive methods for the early detection of EC at present. Methods: A total of 48 EC plasma and 101 control plasma samples were collected in a training cohort from 1 January 2021 to 31 December 2021, and seven cancer-related DNA methylation markers (ELMO1, ZNF582, FAM19A4, PAX1, C13orf18, JAM3 and TERT) were tested in these samples to select potential markers. In total, 20 EC, 10 gastric cancer (GC), 10 colorectal cancer (CRC), and 20 control plasma samples were collected in a validation cohort to evaluate the two-gene panel. Results: ZNF582, FAM19A4, JAM3, or TERT methylation in plasma was shown to significantly distinguish EC and control subjects (p < 0.05), and the combination of ZNF582 and FAM19A4 methylation was the two-gene panel that exhibited the best performance for the detection of EC with 60.4% sensitivity (95% CI: 45.3%-73.9%) and 83.2% specificity (95% CI: 74.1%-89.6%) in the training cohort. The performance of this two-gene panel showed no significant difference between different age and gender groups. When the two-gene panel was combined with CEA, the sensitivity for EC detection was further improved to 71.1%. In the validation cohort, the sensitivity of the two-gene panel for detecting EC, GC, and CRC was 60.0%, 30.0%, and 30.0%, respectively, with a specificity of 90.0%. Conclusion: The identified methylation marker panel provided a potential non-invasive strategy for EC detection, but further validation should be performed in more clinical centers.

A protocol of Chinese expert consensuses for the management of health risk in the general public

Introduction

Non-communicable diseases (NCDs) represent the leading cause of mortality and disability worldwide. Robust evidence has demonstrated that modifiable lifestyle factors such as unhealthy diet, smoking, alcohol consumption and physical inactivity are the primary causes of NCDs. Although a series of guidelines for the management of NCDs have been published in China, these guidelines mainly focus on clinical practice targeting clinicians rather than the general population, and the evidence for NCD prevention based on modifiable lifestyle factors has been disorganized. Therefore, comprehensive and evidence-based guidance for the risk management of major NCDs for the general Chinese population is urgently needed. To achieve this overarching aim, we plan to develop a series of expert consensuses covering 15 major NCDs on health risk management for the general Chinese population. The objectives of these consensuses are (1) to identify and recommend suitable risk assessment methods for the Chinese population; and (2) to make recommendations for the prevention of major NCDs by integrating the current best evidence and experts' opinions.

Methods and analysis

For each expert consensus, we will establish a consensus working group comprising 40-50 members. Consensus questions will be formulated by integrating literature reviews, expert opinions, and an online survey. Systematic reviews will be considered as the primary evidence sources. We will conduct new systematic reviews if there are no eligible systematic reviews, the methodological quality is low, or the existing systematic reviews have been published for more than 3 years. We will evaluate the quality of evidence and make recommendations according to the GRADE approach. The consensuses will be reported according to the Reporting Items for Practice Guidelines in Healthcare (RIGHT).

The current state of artificial intelligence in endoscopic diagnosis of early esophageal squamous cell carcinoma

Esophageal squamous cell carcinoma (ESCC) is a common malignant tumor of the digestive tract. The most effective method of reducing the disease burden in areas with a high incidence of esophageal cancer is to prevent the disease from developing into invasive cancer through screening. Endoscopic screening is key for the early diagnosis and treatment of ESCC. However, due to the uneven professional level of endoscopists, there are still many missed cases because of failure to recognize lesions. In recent years, along with remarkable progress in medical imaging and video evaluation technology based on deep machine learning, the development of artificial intelligence (AI) is expected to provide new auxiliary methods of endoscopic diagnosis and the treatment of early ESCC. The convolution neural network (CNN) in the deep learning model extracts the key features of the input image data using continuous convolution layers and then classifies images through full-layer connections. The CNN is widely used in medical image classification, and greatly improves the accuracy of endoscopic image classification. This review focuses on the AI-assisted diagnosis of early ESCC and prediction of early ESCC invasion depth under multiple imaging modalities. The excellent image recognition ability of AI is suitable for the detection and diagnosis of ESCC and can reduce missed diagnoses and help endoscopists better complete endoscopic examinations. However, the selective bias used in the training dataset of the AI system affects its general utility.