Early detection and treatment through population-level screening have been proved to be an effective approach to decrease mortality risks of digestive cancers such as gastric and esophageal cancers. To date, most of the current population-level screening modalities for gastric and esophageal cancers adopt a universal screening strategy. However, there are concerns over the cost-effectiveness and feasibility of universal screening due to the lack of specialized screening technicians, and the potential harm to healthy individuals in the general population. Screening strategies based on prediction models that distinguish high-risk individuals from the general population would be a more cost-effective and feasible option to better identify target populations for cancer screening or surveillance. Unfortunately, although many prediction models for digestive cancers have been developed and published, few have been applied to screening programs. Therefore, evaluating the screening performance and cost-effectiveness of existing risk prediction models is a preferable approach. Meanwhile, due to the shared risk factors across cancer types and the rapid development of artificial intelligence (AI) assisted deep learning technology, it’s an urgent need to evaluate the performance and cost-effectiveness of a combined screening strategy using a pan-cancer risk prediction model, as compared to traditional screening strategies for individual cancer types in the digestive tract, especially in the gastric and esophageal cancers.
This Research Topic aims to collect a series of scientific contributions to the field of screening and risk prediction in gastric and esophageal cancers. To promote these prediction models into practice, we would encourage the authors to submit articles developing easy-to-use models. We would also welcome studies evaluating the performance and cost-effectiveness of existing models or clinically used biomarkers in different target populations. These may include, but are not limited to, the followings:
• Identification of risk factors or biomarkers for gastric and esophageal cancers with liquid biopsy, multi-omics data analysis, AI-assisted deep learning, or longitudinal analysis of serum markers used by clinicians.
• Real-world studies evaluating the cut-off values for risk stratification of existing prediction models.
• Development or validation of novel questionnaire-based risk stratification tools for gastric or esophageal cancer or pan-cancer screening.
• Development or validation of prediction models for the surveillance of gastric or esophageal cancer
• Evaluation or comparison of the performance of existing models in external populations
• Studies that add biomarkers to existing models and evaluate their performance
• Machine learning or AI-assisted model of early detection and surveillance for gastric or esophageal cancer
• Genetic susceptibility and its application in risk prediction of gastric or esophageal cancer
Please note: manuscripts consisting solely of bioinformatics or computational analysis of public genomic or transcriptomic databases which are not accompanied by validation (independent cohort or biological validation in vitro or in vivo) are out of scope for this section and will not be accepted as part of this Research Topic.
Early detection and treatment through population-level screening have been proved to be an effective approach to decrease mortality risks of digestive cancers such as gastric and esophageal cancers. To date, most of the current population-level screening modalities for gastric and esophageal cancers adopt a universal screening strategy. However, there are concerns over the cost-effectiveness and feasibility of universal screening due to the lack of specialized screening technicians, and the potential harm to healthy individuals in the general population. Screening strategies based on prediction models that distinguish high-risk individuals from the general population would be a more cost-effective and feasible option to better identify target populations for cancer screening or surveillance. Unfortunately, although many prediction models for digestive cancers have been developed and published, few have been applied to screening programs. Therefore, evaluating the screening performance and cost-effectiveness of existing risk prediction models is a preferable approach. Meanwhile, due to the shared risk factors across cancer types and the rapid development of artificial intelligence (AI) assisted deep learning technology, it’s an urgent need to evaluate the performance and cost-effectiveness of a combined screening strategy using a pan-cancer risk prediction model, as compared to traditional screening strategies for individual cancer types in the digestive tract, especially in the gastric and esophageal cancers.
This Research Topic aims to collect a series of scientific contributions to the field of screening and risk prediction in gastric and esophageal cancers. To promote these prediction models into practice, we would encourage the authors to submit articles developing easy-to-use models. We would also welcome studies evaluating the performance and cost-effectiveness of existing models or clinically used biomarkers in different target populations. These may include, but are not limited to, the followings:
• Identification of risk factors or biomarkers for gastric and esophageal cancers with liquid biopsy, multi-omics data analysis, AI-assisted deep learning, or longitudinal analysis of serum markers used by clinicians.
• Real-world studies evaluating the cut-off values for risk stratification of existing prediction models.
• Development or validation of novel questionnaire-based risk stratification tools for gastric or esophageal cancer or pan-cancer screening.
• Development or validation of prediction models for the surveillance of gastric or esophageal cancer
• Evaluation or comparison of the performance of existing models in external populations
• Studies that add biomarkers to existing models and evaluate their performance
• Machine learning or AI-assisted model of early detection and surveillance for gastric or esophageal cancer
• Genetic susceptibility and its application in risk prediction of gastric or esophageal cancer
Please note: manuscripts consisting solely of bioinformatics or computational analysis of public genomic or transcriptomic databases which are not accompanied by validation (independent cohort or biological validation in vitro or in vivo) are out of scope for this section and will not be accepted as part of this Research Topic.
