Related Experiment Video
Updated: Jul 9, 2026
A Three-Dimensional Spheroid Model to Investigate the Tumor-Stromal Interaction in Hepatocellular Carcinoma
Published on: September 30, 2021
A robust clustering strategy for stratification unveils unique patient subgroups in acutely decompensated cirrhosis
Sara Palomino-Echeverria1, Estefania Huergo1, Asier Ortega-Legarreta1
1Unit of Translational Bioinformatics, Navarrabiomed - Fundación Miguel Servet, Pamplona, Spain.
Insights
This study introduces ClustALL, a computational tool for identifying patient subgroups in complex diseases. ClustALL successfully stratified patients with decompensated cirrhosis, offering insights for clinical trial design and disease management.
Area of Science:
- Computational biology
- Clinical data science
- Biostatistics
Background:
- Patient heterogeneity complicates disease management and clinical trial design.
- Current classifications may miss key heterogeneity factors not directly linked to prognosis.
- Addressing complex data challenges is crucial for accurate patient stratification.
Purpose of the Study:
- To develop a robust computational pipeline (ClustALL) for unsupervised patient stratification.
- To identify patient subgroups that are stable across populations and algorithmic parameters.
- To apply ClustALL to acutely decompensated cirrhosis and assess its clinical utility.
Main Methods:
- Developed ClustALL, a pipeline handling mixed-type, missing, and collinear clinical data.
- Employed unsupervised learning for patient stratification.
- Filtered stratifications for population-based and parameter-based robustness.
- Validated findings in independent European and Latin American cohorts.
Main Results:
- ClustALL identified five robust stratifications in acutely decompensated cirrhosis using admission data.
- Stratifications incorporated liver function markers, organ dysfunction, and precipitating events.
- A three-cluster stratification demonstrated prognostic value, improved by follow-up reassessment.
- Findings were validated in a separate prospective cohort.
Conclusions:
- ClustALL identified three distinct patient clusters in acutely decompensated cirrhosis.
- Tracking these clusters over time can inform future clinical trial strategies.
- ClustALL is a novel, robust method for patient stratification in complex diseases.
Background:
Patient heterogeneity poses significant challenges for managing individuals and designing clinical trials, especially in complex diseases. Existing classifications rely on outcome-predicting scores, potentially overlooking crucial elements contributing to heterogeneity without necessarily impacting prognosis.
Methods:
To address patient heterogeneity, we developed ClustALL, a computational pipeline that simultaneously faces diverse clinical data challenges like mixed types, missing values, and collinearity. ClustALL enables the unsupervised identification of patient stratifications while filtering for stratifications that are robust against minor variations in the population (population-based) and against limited adjustments in the algorithm's parameters (parameter-based).
Results:
Applied to a European cohort of patients with acutely decompensated cirrhosis (n = 766), ClustALL identified five robust stratifications, using only data at hospital admission. All stratifications included markers of impaired liver function and number of organ dysfunction or failure, and most included precipitating events. When focusing on one of these stratifications, patients were categorized into three clusters characterized by typical clinical features; notably, the 3-cluster stratification showed a prognostic value. Re-assessment of patient stratification during follow-up delineated patients' outcomes, with further improvement of the prognostic value of the stratification. We validated these findings in an independent prospective multicentre cohort of patients from Latin America (n = 580).
Conclusions:
By applying ClustALL to patients with acutely decompensated cirrhosis, we identified three patient clusters. Following these clusters over time offers insights that could guide future clinical trial design. ClustALL is a novel and robust stratification method capable of addressing the multiple challenges of patient stratification in most complex diseases.
Related Concept Videos
01:23Cirrhosis I: Introduction
01:24Cirrhosis II: Pathophysiology