Surgeons need to know that proximal gastrectomy methods dtr and dft outperform tg and eg in key outcomes for early gastric cancer.

• Reflux esophagitis rates were higher in eg compared to dft and dtr.
• Anastomotic stenosis was less common with dtr than eg.
• Dft achieved the highest 12-month hemoglobin levels; hospital stay was shorter compared to other methods.

Consider dtr and dft for improved patient outcomes and easier recovery in proximal early gastric cancer surgeries.

Conditional relative survival after gastric cancer surgery shows promising results, suggesting better outcomes than previously thought.

• Five-year conditional relative survival (CRS) rose from 87.2% at one year to 95.4% at five years post-surgery.
• Stage III patients saw significant improvement, with CRS increasing from 53.2% at one year to 85.2% at five years.

Surgery remains a viable option for older patients, with those over 80 showing high survival rates similar to younger cohorts.

• Total gastrectomy patients may require additional nutritional support due to lower CRS compared to distal gastrectomy.

This study shows that deep learning can predict leakage during laparoscopic gastrectomy for gastric cancer, improving surgical outcomes.

• Leakage rates were 1.3% at the duodenal stump and 4.3% at the esophagojejunal anastomoses.
• The ResNet18 model achieved a recall of 84.7% for stump leakage and 80% for anastomosis leakage when trained on high-quality, single-image datasets with augmentation.

Using AI during surgery could facilitate timely interventions, enhancing patient safety and outcomes.

• Key image features, both local and surrounding tissues, were critical for accurate predictions.