Appropriate sedation and analgesia are crucial for successful endoscopic procedures, patient safety, and satisfaction. Endoscopic resection for upper gastrointestinal tumors requires a deep sedation level because the procedure is lengthy and induces moderate to severe pain. Continuous patient consciousness assessment and vigilant vital signs monitoring are required for deep sedation. General anesthesia may unintentionally occur even during deep sedation for endoscopic tumor resection, which may cause unexpected complications, especially in high-risk patients. Previous studies have revealed that general anesthesia increases the en bloc resection rate and decreases the procedure time. Complications, such as perforation, aspiration pneumonia, and cardiopulmonary instability, including hypoxemia, hypotension, and arrhythmia, occurred more frequently in patients with sedation compared to those with general anesthesia. Therefore, general anesthesia demonstrated potential benefits in endoscopic treatment results and patient safety. General anesthesia should be considered a useful alternative for sedation in patients undergoing endoscopic gastrointestinal tumor resection. However, more high-quality prospective studies are required to determine the safety and effectiveness of general anesthesia in endoscopic upper gastrointestinal tumor resection because most studies comparing general anesthesia and sedation in these procedures have been retrospectively conducted and the results were inconsistent.

Gastric cancer (GC) is one of the most common malignant tumors worldwide, with a 5-year survival rate of < 40%. The diagnosis and treatment decisions of GC rely on human experts' judgments on medical images; therefore, the accuracy can be hindered by image condition, objective criterion, limited experience, and interobserver discrepancy. In recent years, several applications of artificial intelligence (AI) have emerged in the GC field based on improvement of computational power and deep learning algorithms. AI can support various clinical practices in endoscopic examination, pathologic confirmation, radiologic staging, and prognosis prediction. This review has systematically summarized the current status of AI applications after a comprehensive literature search. Although the current approaches are challenged by data scarcity and poor interpretability, future directions of this field are likely to overcome the risk and enhance their accuracy and applicability in clinical practice.

Colorectal cancer is the third most common cancer worldwide. The occurrence of colon cancer can be prevented by removing precursor lesions. Several countries are making efforts to prevent the occurrence of colon cancer via screening programs. Korea is also following suite by screening individuals < 50 years of age. Currently, the incidence of colon cancer among the young is increasing globally, and Korea has a high colon cancer incidence rate among individuals in their 20s and 40s. Therefore, it may be necessary to start the screening individuals < 50 years of age to detect the cancer's manifestation early. Moreover, advanced adenomas associated with poor prognosis can be detected early, the overall screening rate can be increased, and death from colon cancer at a young age can be prevented. Although the period of colorectal cancer screening has been expanded, the overall colorectal cancer screening rate has not. Additionally, increasing the screening rate among individuals > 50 years could reduce the mortality rate at a lower cost. Although the incidence of colon cancer is increasing in younger individuals, the evidence to conclude that screening at the age of < 50 years has a meaningful impact on the incidence and survival rates of colon cancer remains insufficient. Therefore, rather than following the trend and performing screening early, an approach that actively selects cases where tests for colorectal cancer diagnosis are required is warranted.

Pancreatic cancer is one of the most aggressive cancers, and it is expected to become the second-leading cause of cancer-related death in the United States by 2030. Its 5-year survival rate is <10% and approximately 15% of cases are eligible for surgical treatment during diagnosis. Furthermore, the risk of recurrence within 1 year postoperative is as high as 50%. Therefore, chemotherapy plays a crucial role in pancreatic cancer treatment. Survival rates are speculated to have improved since the introduction of FOLFIRINOX and gemcitabine/nab-paclitaxel combination therapy for metastatic pancreatic cancer in the 2010s. Additionally, the implementation of both neoadjuvant and adjuvant treatments in resectable and borderline resectable pancreatic cancer caused better outcomes compared to upfront surgery. Recently, not only have these medications advanced in development, but so have PARP inhibitors and KRAS inhibitors, contributing to the treatment landscape. This study aimed to explore the latest insights into chemotherapy for pancreatic cancer.

Prediction is a significant topic in clinical research. The development and validation of a prediction model has been increasingly published in clinical research. In this review, we investigated analytical methods and validation schemes for a clinical prediction model used in digestive cancer research. Deep learning and logistic regression, with split-sample validation as an internal or external validation, were the most commonly used methods. Furthermore, we briefly introduced and summarized the advantages and disadvantages of each method. Finally, we discussed several points to consider when conducting prediction model studies.

Gastric cancer is histologically classified into two types. One is the intestinal and diffuse type according to Lauren's classification, and the other is the differentiated and undifferentiated type based on Nakamura's classification. In 2007, Japanese groups proposed a new type of well-differentiated gastric adenocarcinoma in the gastric fundic glands with distinct endoscopic and clinicopathologic features. This is gastric adenocarcinoma of the fundic-gland type (GA-FG), a rare variant of gastric cancer. In a 2012 Korean study, of 6,000 cases of gastric cancer tissues, only three cases of GA-FG were identified. GA-FG is usually located in the upper third of the stomach and not known to be associated with the Helicobacter pylori infection. We herein report a case of GA-FG diagnosed in a 63-year-old man. A gastric polyp was incidentally detected during an upper endoscopy screening while conducting a health check-up, and he was diagnosed with GA-FG after an endoscopic mucosal resection (EMR) was conducted for diagnostic and therapeutic purposes. Our case suggests that for both diagnostic and therapeutic purposes, EMR may be beneficial in case of gastric polyps with suspected GA-FG.