Non-endoscopic Applications of Machine Learning in Gastric Cancer: A Systematic Review.

PURPOSE: Gastric cancer is an important health burden characterized by high prevalence and mortality rate. Upper gastrointestinal endoscopy coupled with biopsy is the primary means in which gastric cancer is diagnosed, and most of machine learning (ML) tools are developed in this area. This systematic review focuses on the applications of ML in gastric cancer that do not involve endoscopic image recognition. METHODS: A systematic review of ML applications that do not involve endoscopy and are relevant to gastric cancer was performed in two databases and independently evaluated by the two authors. Information collected from the included studies are year of publication, ML algorithm, ML performance, specimen used to create the ML model, and clinical application of the model. RESULTS: From 791 screened studies, 63 studies were included in the systematic review. The included studies demonstrate that the non-endoscopic applications of ML can be divided into three main categories, which are diagnostics, predicting response to therapy, and prognosis prediction. Various specimen and algorithms were found to be used for these applications. Most of its clinical use includes histopathologic slide reading in the diagnosis of gastric cancer and a risk scoring system to determine the survival of patients or to determine the important variables that may affect the patient's prognosis. CONCLUSION: The systematic review suggests that there are numerous examples of non-endoscopic applications of ML that are relevant to gastric cancer. These studies have utilized various specimens, even non-conventional ones, thus showing great promise for the development of more non-invasive techniques. However, most of these studies are still in the early stages and will take more time before they can be clinically deployed. Moving forward, researchers in this field of study are encouraged to improve data curation and annotation, improve model interpretability, and compare model performance with the currently accepted standard in the clinical practice.

COVID-19 and its effects on the digestive system and endoscopy practice.

The Coronavirus Disease 2019 (COVID-19) is a respiratory illness caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and has been classified as a pandemic by the World Health Organization in March 2020. Several studies have demonstrated that the gastrointestinal (GI) tract is also a potential route. As the pandemic is continuously evolving, and more data are made available, this article highlights the best evidence and practices regarding the effects of the SARS-CoV-2 virus relevant to GI practice. Published clinical studies have supported that SARS-CoV-2 affects the GI tract and the liver. The largest published dataset comprised of 4243 patients and showed a pooled prevalence of GI symptoms at 17.6%. GI symptoms varied and usually preceded pulmonary symptoms by 1-2 days. These include anorexia (26.8%), nausea and vomiting (10.2%), diarrhea (12.5%), and abdominal pain (9.2%). Incidence of liver injury ranges from 15 to 53%. Evidence shows that the severity of COVID-19 infection is compounded by its effects on nutrition, most especially for the critically ill. As such, nutrition societies have recommended optimization of oral diets and oral nutritional supplements followed by early enteral nutrition if nutritional targets are not met, and parenteral nutrition in the distal end of the spectrum. In addition to possible fecal-oral transmission, GI endoscopy procedures, which are considered to be aerosol-generating procedures, contribute to increased risk to GI health-care professionals. Infection prevention measures and guidelines are essential in protecting both patients and personnel.

Data on the sequence-derived properties of gastric cancer - binding peptides.

The article presents a dataset containing nine classes of calculated sequence-derived descriptors for 78 peptide sequences, 21 of which demonstrate the ability to bind with gastric cancer cells. The datasaet was used in the paper "A screening algorithm for gastric cancer binding peptides" [1] for the creation of a classification model that can predict the ability of a given peptide sequence to bind with gastric cancer cells. The 78 peptide sequences were extracted from a systematic literature search, and the various peptide descriptors were calculated using the R package "Peptides". The nine calculated sequence-derived descriptor classes are the Blosum indices, Cruciani properties, FASGAI vectors, Kidera factors, ProtFP, ST-scales, T-scales, VHSE scales, and Z-scales. The resulting dataset, which is composed of over 4000 data points, offers a rich resource for further protochemometric analyses of the curated peptide sequences relevant to cancer diagnostics and therapeutics.