Key result
A 10-gene Naive Bayes classifier accurately distinguishes AF from SR with ~88% precision.
Why the study?
Atrial fibrillation is the most common arrhythmia with poorly understood biological mechanisms, motivating investigation using multi-omics and machine learning approaches.
Effect estimate: AUC 0.995
Integrative multi-omics and machine learning identified 10 feature genes that accurately distinguish atrial fibrillation from sinus rhythm, providing potential diagnostic and therapeutic targets.
No takes yet. Share an insight, caveat, or question.
These AF feature genes require prospective validation; leaves open their utility as biomarkers or targets pending functional studies.
Liu et al. (2020) studied Atrial fibrillation (n=148). Atrial fibrillation vs. Sinus rhythm was evaluated on Classification of atrial fibrillation from sinus rhythm samples in the independent validation test set using a Naive Bayes classifier (AUC 0.995). A Naive Bayes classifier based on 10 feature genes identified through multi-omics analysis accurately classified atrial fibrillation from sinus rhythm samples with a precision of 87.5% and an AUC of 0.995.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: