1. Temporal stratification of amyotrophic lateral sclerosis patients using disease progression patterns.
- Author
-
M. Amaral, Daniela, Soares, Diogo F., Gromicho, Marta, de Carvalho, Mamede, Madeira, Sara C., Tomás, Pedro, and Aidos, Helena
- Subjects
AMYOTROPHIC lateral sclerosis ,DISEASE progression ,MOTOR neuron diseases ,NEURODEGENERATION ,HIERARCHICAL clustering (Cluster analysis) - Abstract
Identifying groups of patients with similar disease progression patterns is key to understand disease heterogeneity, guide clinical decisions and improve patient care. In this paper, we propose a data-driven temporal stratification approach, ClusTric, combining triclustering and hierarchical clustering. The proposed approach enables the discovery of complex disease progression patterns not found by univariate temporal analyses. As a case study, we use Amyotrophic Lateral Sclerosis (ALS), a neurodegenerative disease with a non-linear and heterogeneous disease progression. In this context, we applied ClusTric to stratify a hospital-based population (Lisbon ALS Clinic dataset) and validate it in a clinical trial population. The results unravelled four clinically relevant disease progression groups: slow progressors, moderate bulbar and spinal progressors, and fast progressors. We compared ClusTric with a state-of-the-art method, showing its effectiveness in capturing the heterogeneity of ALS disease progression in a lower number of clinically relevant progression groups. The authors proposed ClusTric, a temporal stratification approach to find disease progression groups. Applied to Amyotrophic Lateral Sclerosis, the method identifies four progression groups with distinguished characteristics. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF