Key result
AI models detect AF from baseline sinus rhythm ECGs with ~0.74 AUC, with deep learning superior.
Why the study?
Prompt detection of paroxysmal AF is hindered by the lack of an efficient detection method and a unified screening approach.
Do artificial intelligence models accurately detect atrial fibrillation using baseline sinus rhythm ECGs in patients without prior AF confirmation?
Systematic Review (n=1,459,653)
Do artificial intelligence models accurately detect atrial fibrillation using baseline sinus rhythm ECGs in patients without prior AF confirmation?
Effect estimate: Median AUC 0.740 (95% CI 0.630 to 0.830)
Artificial intelligence, particularly deep learning models, demonstrates promising diagnostic capability in detecting atrial fibrillation from baseline sinus rhythm ECGs.
Performance too modest for clinical screening; leaves open optimization and prospective validation of deep learning models.
BACKGROUND: Atrial fibrillation (AF) is a prevalent arrhythmia associated with adverse outcomes, often presenting paroxysmally. The lack of an efficient method to promptly detect paroxysmal AF and the absence of a unified screening approach necessitate exploring novel solutions. Artificial intelligence (AI) models show promise in addressing this gap, enabling early intervention. This study assessed the effectiveness of AI in detecting AF using baseline sinus rhythm-ECG (SR-ECG) and factors influencing their performance. METHODS: A systematic review was conducted across eight databases and registries (International Platform of Registered Systematic Review and Meta-analysis Protocols (INPLASY) registration: INPLASY202530059). References up to May 2024 were double-screened for eligibility. Included studies used AI to detect AF from baseline SR-ECGs in patients without prior AF confirmation. Quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. Performance metrics were summarised using medians with subgroup analyses by AI type and AF confirmation timeframe. RESULTS: 14 studies and 33 AI models were analysed. Participant data were available for 13 studies, totalling 1459653 patients, with one study providing only testing dataset data. Median (95% CI) performance metrics were: accuracy 58.0% (55.0 to 62.0), sensitivity 62.0% (57.0 to 70.2), specificity 57.8% (51.0 to 61.1), precision 52.0% (47.0 to 56.0) and area under the receiver operating characteristic curve (AUC) 0.740 (0.630 to 0.830). Deep learning (DL) models outperformed traditional machine learning in sensitivity (72.6% vs 54.5%; q=0.027) and AUC (0.830 vs 0.610; q<0.001). Models using a 31-day confirmation window showed higher accuracy (83.2% vs 56.0%; q=0.010) and AUC (0.851 vs 0.630; q<0.001) than those using a 1-year timeframe. 11 studies (78.6%) cited possible negative cases misclassification as a limitation, and nine (64.3%) were deemed 'high risk of bias' in at least one domain. CONCLUSIONS: AI-enhanced SR-ECG for identifying AF patients holds growing potential. Our findings show that DL and models incorporating a 31-day confirmation window are more effective in this context. Further research is needed to explore clinical benefits and cost-effectiveness.
No takes yet. Share an insight, caveat, or question.
Tsiartas et al. (2025) conducted a systematic review in Atrial fibrillation (n=1,459,653). Artificial intelligence (AI) models vs. Traditional machine learning (in subgroup analysis) was evaluated on Detection of AF using baseline SR-ECG (AUC) (Median AUC 0.740, 95% CI 0.630 to 0.830). Artificial intelligence models detecting atrial fibrillation from baseline sinus rhythm ECGs achieved a median AUC of 0.740 (95% CI 0.630-0.830), with deep learning outperforming traditional methods.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: