Utility of the Iwate difficulty scoring system for laparoscopic right posterior sectionectomy: do surgical outcomes differ for tumors in segments VI and VII?

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.

Propensity Score-Matching Analysis Comparing Robotic Versus Laparoscopic Limited Liver Resections of the Posterosuperior Segments: An International Multicenter Study

OBJECTIVE

The purpose of this study was to compare the outcomes of robotic limited liver resections (RLLR) versus laparoscopic limited liver resections (LLLR) of the posterosuperior segments.

BACKGROUND

Both laparoscopic and robotic liver resections have been used for tumors in the posterosuperior liver segments. However, the comparative performance and safety of both approaches have not been well examined in the existing literature.

METHODS

This is a post hoc analysis of a multicenter database of 5446 patients who underwent RLLR or LLLR of the posterosuperior segments (I, IVa, VII, and VIII) at 60 international centers between 2008 and 2021. Data on baseline demographics, center experience and volume, tumor features, and perioperative characteristics were collected and analyzed. Propensity score-matching (PSM) analysis (in both 1:1 and 1:2 ratios) was performed to minimize selection bias.

RESULTS

A total of 3510 cases met the study criteria, of whom 3049 underwent LLLR (87%), and 461 underwent RLLR (13%). After PSM (1:1: and 1:2), RLLR was associated with a lower open conversion rate [10 of 449 (2.2%) vs 54 of 898 (6.0%); P =0.002], less blood loss [100 mL [IQR: 50-200) days vs 150 mL (IQR: 50-350); P <0.001] and a shorter operative time (188 min (IQR: 140-270) vs 222 min (IQR: 158-300); P <0.001]. These improved perioperative outcomes associated with RLLR were similarly seen in a subset analysis of patients with cirrhosis-lower open conversion rate [1 of 136 (0.7%) vs 17 of 272 (6.2%); P =0.009], less blood loss [100 mL (IQR: 48-200) vs 160 mL (IQR: 50-400); P <0.001], and shorter operative time [190 min (IQR: 141-258) vs 230 min (IQR: 160-312); P =0.003]. Postoperative outcomes in terms of readmission, morbidity and mortality were similar between RLLR and LLLR in both the overall PSM cohort and cirrhosis patient subset.

CONCLUSIONS

RLLR for the posterosuperior segments was associated with superior perioperative outcomes in terms of decreased operative time, blood loss, and open conversion rate when compared with LLLR.

Comparison of clinical outcome between laparoscopic and open hepatectomy of high difficulty score for hepatocellular carcinoma: a propensity score analysis

BACKGROUND

Laparoscopic liver resection (LLR) of high difficulty score is technically challenging. There is a lack of clinical evidence to support its applicability in terms of the long-term survival benefits. This study aims to compare clinical outcomes between LLR and the open liver resection of high difficulty score for hepatocellular carcinoma (HCC).

MATERIALS AND METHODS

From 2010 to 2020, using Iwate criteria, 424 patients underwent liver resection of high difficulty score by the laparoscopic (n = 65) or open (n = 359) approach. Propensity score (PS) matching was performed between the two groups. Short-term and long-term outcomes were compared between PS-matched groups. Univariate and multivariate analyses were performed to identify prognostic factors affecting survival.

RESULTS

The laparoscopic group had significantly fewer severe complications (3% vs. 10.8%), and shorter median hospital stays (6 days vs. 8 days) than the open group. Meanwhile, the long-term oncological outcomes were comparable between the two groups, in terms of the tumor recurrence rate (40% vs. 46.1%), the 5-year overall survival rate (75.4% vs. 76.2%), and the 5-year recurrence-free survival rate (50.3% vs. 53.5%). The high preoperative serum alpha-fetoprotein level, multiple tumors, and severe postoperative complications were the independent poor prognostic factors associated with worse overall survival. The surgical approach (Laparoscopic vs. Open) did not influence the survival.

CONCLUSION

LLR of high difficulty score for selected patients with HCC has better short-term outcomes than the open approach. More importantly, it can achieve similar long-term survival outcomes as the open approach.