Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 2 appraisals
Journal of robotic surgery
Short-term outcomes of robot-assisted versus conventional minimally invasive esophagectomy for resectable esophageal cancer: a systematic review and meta-analysis
Robot-assisted minimally invasive esophagectomy (RAMIE) has emerged as an alternative to conventional minimally invasive esophagectomy (MIE) for esophageal cancer, but its short-term perioperative advantages remain uncertain. To compare early postoperative outcomes of RAMIE and MIE in patients with resectable esophageal cancer, this systematic review and meta-analysis was conducted according to PRISMA 2020 guidelines. PubMed was searched for randomized controlled trials, propensity score-matched studies, and retrospective comparative studies published between January 2005 and December 2024. Adult patients undergoing RAMIE or conventional MIE for resectable esophageal cancer were included. Random-effects models were used to pool standardized mean differences and odds ratios with 95% confidence intervals. Study quality was assessed using the MINORS criteria and Cochrane RoB 2 tool. In addition, a post hoc GRADE assessment was carried out for key outcomes to evaluate the certainty of evidence. Forty-one studies involving 13,321 patients were included, of whom 4,327 underwent RAMIE and 8,994 underwent MIE. Compared with MIE, RAMIE was associated with lower blood loss, reduced conversion to open surgery, higher total lymph node yield, greater left recurrent laryngeal nerve lymph node harvest, fewer pulmonary complications, and lower overall postoperative morbidity. ICU stay and hospital stay were also e shorter after RAMIE, whereas operative time was longer. No significant differences were observed in R0 resection, anastomotic leak, recurrent laryngeal nerve palsy, cardiac complications, chyle leak, surgical site infection, or 30- and 90-day mortality. Post hoc GRADE assessment showed that the certainty of evidence was very low across key outcomes, mainly because of the predominance of non-randomized studies, substantial heterogeneity across several pooled analyses, and outcome-specific concerns regarding imprecision and publication bias. RAMIE is safe and may offer some short-term perioperative advantages over conventional MIE without clear evidence of increased major morbidity or short-term mortality. However, the certainty of evidence across key outcomes was very low, and the predominance of nonrandomized studies and substantial heterogeneity across several analyses warrant cautious interpretation. Further adequately powered randomized trials are required.
25 May 2026
Read appraisal →J Clin Oncol
Foundation Model for Predicting Prognosis and Adjuvant Therapy Benefit From Digital Pathology in GI Cancers
PURPOSE: Artificial intelligence (AI) holds significant promise for improving cancer diagnosis and treatment. Here, we present a foundation AI model for prognosis prediction on the basis of standard hematoxylin and eosin-stained histopathology slides. METHODS: In this multinational cohort study, we developed AI models to predict prognosis from histopathology images of patients with GI cancers. First, we trained a foundation model using over 130 million patches from 104,876 whole-slide images on the basis of self-supervised learning. Second, we fine-tuned deep learning models for predicting survival outcomes and validated them across seven cohorts, including 1,619 patients with gastric and esophageal cancers and 2,594 patients with colorectal cancer. We further assessed the model for predicting survival benefit from adjuvant chemotherapy. RESULTS: The AI models predicted disease-free survival and disease-specific survival with a concordance index of 0.726-0.797 for gastric cancer and 0.714-0.757 for colorectal cancer in the validation cohorts. The models stratified patients into high-risk and low-risk groups, with 5-year survival rates of 49%-52% versus 76%-92% in gastric cancer and 43%-72% versus 81%-98% in colorectal cancer. In multivariable analysis, the AI risk scores remained an independent prognostic factor after adjusting for clinicopathologic variables. Compared with stage alone, an integrated model consisting of stage and image information improved prognosis prediction across all validation cohorts. Finally, adjuvant chemotherapy was associated with improved survival in the high-risk group but not in the low-risk group (treatment-model interaction P = .01 and .006) for stage II/III gastric and colorectal cancer, respectively. CONCLUSION: The pathology foundation model can accurately predict survival outcomes and complement clinicopathologic factors in GI cancers. Pending prospective validation, it may be used to improve risk stratification and inform personalized adjuvant therapy.
1 Nov 2025
Read appraisal →