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.

Global Outcomes Benchmarks in Laparoscopic Liver Surgery for Segments 7 and 8: International Multicenter Analysis

BACKGROUND

In recent years, there has been growing interest in laparoscopic liver resection (LLR) and the audit of the results of surgical procedures. The aim of this study was to define reference values for LLR in segments 7 and 8.

METHODS

Data on LLR in segments 7 and 8 between January 2000 and December 2020 were collected from 19 expert centers. Reference cases were defined as no prior hepatectomy, ASA <3, body mass index <35 kg/m2, no chronic kidney disease, no cirrhosis and portal hypertension, no chronic obstructive pulmonary disease (FEV1<80%), and no cardiac disease. Reference values were obtained from the 75th percentile of the medians of all reference centers.

RESULTS

Of 585 patients, 461 (78.8%) met the reference criteria. The overall complication rate was 27.5% (6% were Clavien-Dindo≥3a) with a mean CCI of 7.5 ± 16.5. At 90-day follow-up, the references values for overall complications were 31%, Clavien≥3a 7.4%, conversion 4.4%, hospital stay < 6 days, and readmission rate < 8.33%, respectively. Eastern centers patients categorized as low risk had a lower rate of overall complications (20.9% vs 31.2%, p=0.01) with similar Clavien-Dindo≥3a (5.5% and 4.8%, p=0.83) compared to Western centers, respectively.

CONCLUSION

This study shows the need to establish standards for the postoperative outcomes in LLR based on the complexity of the resection and the location of the lesions.