Explainable artificial intelligence prediction-based model in laparoscopic liver surgery for segments 7 and 8: an international multicenter study.

BACKGROUND: Artificial intelligence (AI) is becoming more useful as a decision-making and outcomes predictor tool. We have developed AI models to predict surgical complexity and the postoperative course in laparoscopic liver surgery for segments 7 and 8. METHODS: We included patients with lesions located in segments 7 and 8 operated by minimally invasive liver surgery from an international multi-institutional database. We have employed AI models to predict surgical complexity and postoperative outcomes. Furthermore, we have applied SHapley Additive exPlanations (SHAP) to make the AI models interpretable. Finally, we analyzed the surgeries not converted to open versus those converted to open. RESULTS: Overall, 585 patients and 22 variables were included. Multi-layer Perceptron (MLP) showed the highest performance for predicting surgery complexity and Random Forest (RF) for predicting postoperative outcomes. SHAP detected that MLP and RF gave the highest relevance to the variables "resection type" and "largest tumor size" for predicting surgery complexity and postoperative outcomes. In addition, we explored between surgeries converted to open and non-converted, finding statistically significant differences in the variables "tumor location," "blood loss," "complications," and "operation time." CONCLUSION: We have observed how the application of SHAP allows us to understand the predictions of AI models in surgical complexity and the postoperative outcomes of laparoscopic liver surgery in segments 7 and 8.

Long-term oncological outcomes for HALS/Hybrid vs pure laparoscopic approach in colorectal liver metastases: a propensity score matched analysis.

BACKGROUND: Studies comparing hand-assisted laparoscopic (HALS)/Hybrid and pure laparoscopic (PLS) resection for colorectal cancer liver metastasis have focused on short-term results, while long-term oncological outcomes remain understudied. METHODS: We established a multi-institutional retrospective cohort study from four centers with experience in minimally invasive surgery between 2004 and 2020. Primary endpoints were overall survival (OS) and disease-free survival (DFS). Other endpoints analyzed were intraoperative and postoperative outcomes. Propensity score matching (PSM) was used to minimize baseline differences. RESULTS: A total of 219 HALS/Hybrid (57.8%) and 160 PLS (42.2%) patients were included. After PSM, 155 patients remained in each group. Operative time (182 vs. 248 min, p = 0.012), use of intraoperative ablation (12.3 vs. 4.5%, p = 0.024), positive resection margin (4.5 vs 13.2%, p = 0.012), and pringle time (21 vs. 37 min, p = 0.001) were higher in PLS group. DFS at 1, 3, 5, and 7 years in HALS/Hybrid and PLS groups were 65.4%, 39.3%, 37.5%, and 36.3% vs. 64.9%, 38.0%, 33.1%, and 33.1%, respectively (p = 0.84). OS at 1, 3, 5, and 7 years in HALS/Hybrid and PLS groups were 94.5%, 71.4%, 54.3%, and 46.0% vs. 96.0%, 68.5%, 51.2%, and 41.2%, respectively (p = 0.73). CONCLUSION: Our study suggests no differences in long-term oncologic outcomes between the two techniques. We discovered that longer total operative, pringle time, higher rates of intraoperative ablation, and positive resection margins were associated with PLS. These differences in favor of HALS/Hybrid could be due to a shorter learning curve and a greater ability to control hemorrhage.