Key result
Probabilistic graphical models using social determinants and clinical variables improve personalized AF-related stroke risk prediction.
Why the study?
Stroke prevention treatments have outpaced means for stroke risk stratification in patients with AF, as current risk tools can limit optimal implementation of emerging therapies.
Can explainable artificial intelligence (probabilistic graphical models) improve stroke risk stratification in patients with atrial fibrillation?
Can explainable artificial intelligence (probabilistic graphical models) improve stroke risk stratification in patients with atrial fibrillation?
Explainable AI, specifically probabilistic graphical models, holds promise for improving personalized and equitable stroke risk assessment in patients with atrial fibrillation by incorporating non-traditional variables like social determinants of health.
Answers are grounded in this paper and cite their sources.
Does not yet warrant changes to AF stroke risk stratification; leaves open prospective validation of explainable AI incorporating social determinants.
Current risk stratification tools can limit the optimal implementation of new and emerging therapies for patients with heart rhythm disorders. For example, stroke prevention treatments have outpaced means for stroke risk stratification for patients with atrial fibrillation (AF). Artificial intelligence (AI) techniques have shown promise for improving various tasks in cardiovascular medicine. Here, we explain key concepts in AI that are central to using these technologies for better risk stratification, highlighting one approach particularly well suited to the task of portable, personalized risk stratification-probabilistic graphical models (PGMs). Probabilistic graphical models can empower physicians to ask and answer a variety of clinical questions, which we demonstrate using a preliminary model of AF-related stroke risk among 1.6 million patients within the University of Utah Health System. This example also highlights the ability of PGMs to combine social determinants of health and other non-traditional variables with standard clinical and demographic ones to improve personalized risk predictions and address risk factor interactions. When combined with electronic health data, these computational technologies hold great promise to empower personalized, explainable, and equitable risk assessment.
No takes yet. Share an insight, caveat, or question.
Reisinger et al. (2025) conducted a review in Atrial fibrillation (n=1,600,000). Probabilistic graphical models (PGMs) was evaluated on AF-related stroke risk. Probabilistic graphical models combined social determinants of health with standard clinical variables to improve personalized AF-related stroke risk predictions among 1.6 million patients.
Synapse has enriched 10 related papers. Consider them for comparative context: