Validation of a pan-ELastography Machine-learning (ELM) score to predict clinically significant portal hypertension in compensated advanced chronic liver disease.
Publisher DOI
PubMed ID
42419604
Abstract
Background
Clinically significant portal hypertension (CSPH) drives decompensation and mortality in advanced chronic liver disease (ACLD). Although non-selective β-blockers (NSBB) reduce risk, accurate identification of patients with CSPH requires invasive hepatic venous pressure gradient (HVPG) measurement. The non-invasive Baveno-VII CSPH criteria based on liver stiffness measurement (LSM) and platelet count (PLT)-yield 40-50% indeterminate ("gray-zone") results and vary across etiologies and elastography techniques. Spleen stiffness measurement (SSM) has been proposed to improve the accuracy of the Baveno-VII CSPH criteria. We developed and validated a machine-learning (ML) model integrating pan-elastographic LSM and SSM results with clinical variables to improve CSPH rule-out and rule-in accuracy while minimizing indeterminate cases.Methods
We analyzed 1,435 compensated ACLD patients with paired HVPG, LSM, SSM, and clinical parameters. LSM and SSM were obtained by vibration-controlled transient elastography (VCTE), two-dimensional shear-wave elastography (2D-SWE), or point-SWE (p-SWE). Models were trained (n=943) and internally validated (n=150) using harmonized LSM/SSM from different technologies and clinical variables (PLT, Child-Pugh, age, gender, etiology). Cut-offs were selected for 100% negative predictive value (NPV) to rule-out and 100% positive predictive value (PPV) to rule-in CSPH. External validation was conducted in 342 patients across seven centers, comparing ML performance against Baveno VII, Baveno-SSM single- and dual-cut-off criteria, and, in the VCTE subgroup, ANTICIPATE and NICER scores.Results
A Random Forest-based model based achieved the highest performance (external validation: AUC=0.91, Brier Score=0.13), with cut-offs≤0.45 (rule-out) and ≥0.60 (rule-in) yielding NPV=0.90 (95%C.I.0.84-0.94) and PPV=0.96 (95%C.I.0.92-0.98). The ML gray-zone was 12.3%, versus 47.9% (Baveno VII;p<0.001), 38.6% (Baveno-SSM-dual;p<0.001), and 19.6% (Baveno-SSM-single;p<0.05). In the VCTE external-validation subgroup (n=275), ELM achieved comparable rule-in performance to ANTICIPATE and NICER, while reducing the gray zone to 12.0% versus 41.1% and 41.8%, respectively.Conclusions
The ELM Score outperformed current Baveno criteria and markedly reduced gray zones across elastography modalities, supporting broader, safer, and non-invasive identification of ACLD patients with HVPG-defined CSPH who may be candidates for NSBB therapy.
Clinically significant portal hypertension (CSPH) drives decompensation and mortality in advanced chronic liver disease (ACLD). Although non-selective β-blockers (NSBB) reduce risk, accurate identification of patients with CSPH requires invasive hepatic venous pressure gradient (HVPG) measurement. The non-invasive Baveno-VII CSPH criteria based on liver stiffness measurement (LSM) and platelet count (PLT)-yield 40-50% indeterminate ("gray-zone") results and vary across etiologies and elastography techniques. Spleen stiffness measurement (SSM) has been proposed to improve the accuracy of the Baveno-VII CSPH criteria. We developed and validated a machine-learning (ML) model integrating pan-elastographic LSM and SSM results with clinical variables to improve CSPH rule-out and rule-in accuracy while minimizing indeterminate cases.Methods
We analyzed 1,435 compensated ACLD patients with paired HVPG, LSM, SSM, and clinical parameters. LSM and SSM were obtained by vibration-controlled transient elastography (VCTE), two-dimensional shear-wave elastography (2D-SWE), or point-SWE (p-SWE). Models were trained (n=943) and internally validated (n=150) using harmonized LSM/SSM from different technologies and clinical variables (PLT, Child-Pugh, age, gender, etiology). Cut-offs were selected for 100% negative predictive value (NPV) to rule-out and 100% positive predictive value (PPV) to rule-in CSPH. External validation was conducted in 342 patients across seven centers, comparing ML performance against Baveno VII, Baveno-SSM single- and dual-cut-off criteria, and, in the VCTE subgroup, ANTICIPATE and NICER scores.Results
A Random Forest-based model based achieved the highest performance (external validation: AUC=0.91, Brier Score=0.13), with cut-offs≤0.45 (rule-out) and ≥0.60 (rule-in) yielding NPV=0.90 (95%C.I.0.84-0.94) and PPV=0.96 (95%C.I.0.92-0.98). The ML gray-zone was 12.3%, versus 47.9% (Baveno VII;p<0.001), 38.6% (Baveno-SSM-dual;p<0.001), and 19.6% (Baveno-SSM-single;p<0.05). In the VCTE external-validation subgroup (n=275), ELM achieved comparable rule-in performance to ANTICIPATE and NICER, while reducing the gray zone to 12.0% versus 41.1% and 41.8%, respectively.Conclusions
The ELM Score outperformed current Baveno criteria and markedly reduced gray zones across elastography modalities, supporting broader, safer, and non-invasive identification of ACLD patients with HVPG-defined CSPH who may be candidates for NSBB therapy.
Date Issued
2026-07-08
Publication Type
Article
Language(s)
en
Author(s)
Giuffrè, Mauro | |
Kresevic, Simone | |
Ravaioli, Federico | |
Zykus, Romanas | |
Rautou, Pierre-Emmanuel | |
Elkrief, Laure | |
Colecchia, Luigi | |
Kukic, Sandro | |
Barisic-Jaman, Mislav | |
Grgurevic, Ivica | |
Stefanescu, Horia | |
Hirooka, Masashi | |
Fraquelli, Mirella | |
Rosselli, Matteo | |
Chang, Pik Eu Jason | |
Crocè, Lory | |
Ajcevic, Milos | |
Piscaglia, Fabio | |
Reiberger, Thomas | |
Llop, Elba | |
Mueller, Sebastian | |
Puente, Ángela | |
Fortea, José Ignacio | |
Kim, Sang Gyun | |
You, Kisung | |
Marasco, Giovanni | |
Azzaroli, Francesco | |
Shung, Dennis L | |
Colecchia, Antonio | |
Dajti, Elton |
Journal
Journal of Hepatology
Publisher
Elsevier
ISSN
1600-0641
0168-8278
Access(Rights)
embargo