Predictive power of ALBI score-based nomogram for 30-day mortality following transcatheter aortic valve implantation

This retrospective, multi-center study evaluates the relationships between novel liver function scoring systems - Albumin-Bilirubin (ALBI) score, EZ-ALBI, PALBI, and MELD-XI - and outcomes in patients undergoing transcatheter aortic valve implantation (TAVI). Feature importance was assessed with SHAP-values via the XGBoost-algorithm.

The ALBI score exhibited the strongest association with 30-day mortality after TAVI (AUC = 0.723, p < 0.001), outperforming other scores in this regard and consistently demonstrating predictive power across various subgroup populations. Higher 30-day mortality rates were observed in the higher tertiles of the ALBI score compared to the lower tertiles (log-rank p-value = 0.004). The ALBI-based nomogram (C-index = 0.81, 95% CI:0.73-0.86, p = 0 < 001) demonstrated superior predictive power for 30-day mortality post-TAVI compared to the STS (C-index = 0.71, 95% CI :0.64-0.77, p = 0 < 001). In addition, the nomogram showed a significant improvement in reclassification (69.3%, p < 0.001) and a stronger discrimination 15.2%, p < 0.001) compared to the STS. It integrates nine variables, first ALBI score (SHAP:1.165), including NYHA class (0.594), body mass index (0.510), glomerular filtration rate, creatinine, hemoglobin, gender, predilatation requirement, presence of chronic kidney disease, and providing a comprehensive risk assessment tool.

This study exhibits the significance of liver dysfunction with AS patients and suggests incorporating liver function parameters in pre-operative risk assessments for better clinical outcomes in TAVI procedures.