Why the study?
Postthrombotic syndrome is a chronic condition developing after DVT diagnosed using the Villalta scale, but heterogeneity among patients and within the Villalta scale remains to be investigated.
Does unsupervised machine learning identify distinct clinical profiles of postthrombotic syndrome in patients with deep vein thrombosis?
Population
818 patients from the IDEAL DVT study
Comparison
Unsupervised machine learning-identified clinical profiles and Villalta item clusters
Design
Unsupervised machine learning analysis
Follow-up
2 years
Authors
Loading...
May guide individualized PTS assessment by profile; leaves open whether Villalta scoring requires reappraisal in prospective studies.
Does unsupervised machine learning identify distinct clinical profiles of postthrombotic syndrome in patients with deep vein thrombosis?
Unsupervised machine learning reveals distinct clinical profiles and separates signs from symptoms in postthrombotic syndrome, suggesting a need to reappraise the Villalta scoring system for personalized risk prediction.
Iding et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: