Diagnosis to dissection: AI's role in early detection and surgical intervention for gastric cancer.

Gastric cancer remains a formidable health challenge worldwide; early detection and effective surgical intervention are critical for improving patient outcomes. This comprehensive review explores the evolving landscape of gastric cancer management, emphasizing the significant contributions of artificial intelligence (AI) in revolutionizing both diagnostic and therapeutic approaches. Despite advancements in the medical field, the subtle nature of early gastric cancer symptoms often leads to late-stage diagnoses, where survival rates are notably decreased. Historically, the treatment of gastric cancer has transitioned from palliative care to surgical resection, evolving further with the introduction of minimally invasive surgical (MIS) techniques. In the current era, AI has emerged as a transformative force, enhancing the precision of early gastric cancer detection through sophisticated image analysis, and supporting surgical decision-making with predictive modeling and real-time preop-, intraop-, and postoperative guidance. However, the deployment of AI in healthcare raises significant ethical, legal, and practical challenges, including the necessity for ongoing professional education and the development of standardized protocols to ensure patient safety and the effective use of AI technologies. Future directions point toward a synergistic integration of AI with clinical best practices, promising a new era of personalized, efficient, and safer gastric cancer management.

A decade of experience with 530 minimally invasive robotic hepatectomies from a single tertiary hepatobiliary center: analysis of short-term outcomes and oncologic survival.

BACKGROUND: This research is the first study in the United States to document more than a decade of experience with 530 patients who underwent robotic hepatectomy at a single high-volume institution. METHODS: With institutional review board approval, a prospectively collected database of consecutive patients who underwent robotic hepatectomy from 2012 to January 2024 was reviewed. Data are presented as median (mean ± SD). RESULTS: Of the 530 robotic hepatectomies, 231 (44.0%) were minor resections, 133 (25.0%) were technically major resections, and 166 (31.0%) were major resections. The patients were aged 63.0 (61.0 ± 14.7) years with a body mass index of 28.0 (29.0 ± 7.9) kg/m2. Cirrhosis was present in 80 patients (19.0%), with an American Society of Anesthesiologists score of 3.0 (3.0 ± 0.5) and a Model for End-Stage Liver Disease score of 7.0 (8.0 ± 3.0). Of note, 280 patients (53.0%) had previous abdominal operations, and 44 patients (8%) had previous liver resections. The operative time was 233.0 (260.0 ± 130.7) minutes, and the estimated blood loss was 100.0 (165.0 ± 205.0) mL. Moreover, 353 patients (66%) had hepatectomies for neoplastic disease, and 500 patients (95%) had an R0 resection margin. The tumor size was 4.0 (5.0 ± 3.6) cm. The total 90-day postoperative complications were 45 (8%), of which 21 (4%) were classified as major complications (Clavien-Dindo score of >III). The length of stay was 3.0 (4.0 ± 3.7) days, and the 30-day readmission rate was 86 (16%). The overall survival rates at 1, 3, and 5 years were 82%, 65%, and 59% for colorectal liver metastases, 84%, 68%, and 60% for hepatocellular carcinoma, and 79%, 61%, and 50% for intrahepatic cholangiocarcinoma, respectively. CONCLUSION: After a decade of application and optimization at a high-volume institution, the robotic approach has been demonstrated to be a safe and effective approach to liver resection.

Comparison of IWATE, Institut Mutualiste Montsouris, and Southampton Laparoscopic Liver Resection Difficulty Scoring Systems for Predicting Intra and Postoperative Outcomes in Robotic Hepatectomy.

BACKGROUND: IWATE, Institut Mutualiste Montsouris (IMM), and Southampton are established difficulty scoring systems (DSS) for laparoscopic hepatectomy, yet none specifically address robotic hepatectomy. Our study evaluates these 3 DSS for predicting perioperative outcomes in robotic hepatectomy. METHODS: With IRB approval, we prospectively followed 359 consecutive patients undergoing robotic hepatectomies, assessing categorical metrics like conversions to open, intra/postoperative issues, Clavien-Dindo Score (≥III), 30 and 90-day mortality, and 30-day readmissions using Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) to determine efficacy in predicting their occurrence for each DSS. Continuous metrics such as operative duration, estimated blood loss (EBL), length of stay, and total cost were analyzed using Spearman's correlation and regression. Predictive strength was significant with an AUC or correlation ≥.700 and P-value ≤.05. RESULTS: IMM had highest predictive accuracy for conversions to open (AUC = .705) and postoperative complications (AUC = .481). Southampton was most accurate in predicting Clavien Dindo ≥ III complications (AUC = .506). IWATE excelled in predicting 30-day mortality (AUC = .552), intraoperative issues (AUC = .798), In-hospital mortality (AUC = .450), 90-day mortality (AUC = .596), and readmissions (AUC = .572). Regression showed significant relationships between operative duration, EBL, and hospital cost with increasing scores for all DSS (P ≤ .05). DISCUSSION: Statistical analysis of the 3 DSS indicates that each has specific strengths that can best predict intra- and/or postoperative outcomes. However, all showed inaccuracies and conflicting relationships with the variables, indicating lack of substantial hierarchy between DSS. Given these inconsistencies, a dedicated comprehensive DSS should be created for robotic hepatectomy.