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.

Multimodal prehabilitation program in patients with resectable perihilar cholangiocarcinoma: keypoints for an implementation protocol and literature review.

BACKGROUND: Postoperative complications after perihilar cholangiocarcinoma surgical procedure are still very high. The implementation of a multimodal prehabilitation program could improve these outcomes. Based on our experience and that of the literature in hepatobiliary and pancreatic surgery, we propose a protocol to promote its implementation. METHODS: First, we performed a retrospective analysis of the implementation feasibility of a multimodal prehabilitation program in patients' candidates for elective perihilar cholangiocarcinoma surgery in our center. Second, we conducted a literature search of publications in PubMed until December 2022. Relevant data about hepato-pancreato-biliary surgery and prehabilitation programs in features and postoperative outcomes was analyzed. RESULTS: Since October 2020, 11 patients were evaluated for prehabilitation in our hospital. Two of them could not be resected intraoperatively due to disease extension. The median hospital stay was 10 days (iqr, 7-11). There were no major complications and 1 patient died. Of a total of 17 articles related to prehabilitation in hepato-biliary-pancreatic surgery, no reports focusing exclusively on perihilar cholangiocarcinoma were found. Six of the studies had nutritional therapies in addition to physical interventions, and 12 studies used home-based exercise therapy. CONCLUSIONS: Based on our experience and the data obtained from other studies, a prehabilitation program could be useful to improve perioperative physical and mental fitness in patients' candidates for elective perihilar cholangiocarcinoma surgery. However, more well-designed studies are needed to allow us to obtain more evidence.

Textbook outcome in patients with biliary duct injury during cholecystectomy.

BACKGROUND: Iatrogenic bile duct injury (BDI) during cholecystectomy is associated with a complex and heterogeneous management owing to the burden of morbidity until their definitive treatment. This study aimed to define the textbook outcomes (TOs) after BDI with the purpose to indicate the ideal treatment and to improve it management. METHODS: We collected data from patients with an BDI between 1990 and 2022 from 27 hospitals. TO was defined as a successful conservative treatment of the iatrogenic BDI or only minor complications after BDI or patients in whom the first repair resolves the iatrogenic BDI without complications or with minor complications. RESULTS: We included 808 patients and a total of 394 patients (46.9%) achieved TO. Overall complications in TO and non-TO groups were 11.9% and 86%, respectively (P < .001). Major complications and mortality in the non-TO group were 57.4% and 9.2%, respectively. The use of end-to-end bile duct anastomosis repair was higher in the non-TO group (23.1 vs 7.8, P < .001). Factors associated with achieving a TO were injury in a specialized center (adjusted odds ratio [aOR], 4.01; 95% CI, 2.68-5.99; P < .001), transfer for a first repair (aOR, 5.72; 95% CI, 3.51-9.34; P < .001), conservative management (aOR, 5.00; 95% CI, 1.63-15.36; P = .005), or surgical management (aOR, 2.45; 95% CI, 1.50-4.00; P < .001). CONCLUSION: TO largely depends on where the BDI is managed and the type of injury. It allows hepatobiliary centers to identify domains of improvement of perioperative management of patients with BDI.