ReviewCureus2026
N-terminal Pro-B-Type Natriuretic Peptide (NT-proBNP) Versus Artificial Intelligence-Enabled Electrocardiography for the Diagnosis of Acute Heart Failure in Emergency Departments: A Systematic Review.
Review in Cureus, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
9 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
N-terminal pro-B-type natriuretic peptide (NT-proBNP) is the guideline-endorsed biomarker for diagnosing acute heart failure (AHF) in the emergency department (ED), while artificial intelligence-enabled electrocardiography (AI-ECG) has emerged as a rapid, phlebotomy-free alternative. AI-ECG models are trained end-to-end on raw waveform or ECG image data and learn subtle depolarisation, repolarisation and conduction features that are not recognisable by conventional criteria; most were trained to detect left ventricular systolic dysfunction (LVSD) rather than the AHF syndrome itself. Their relative performance has not been systematically appraised. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020, four databases were searched from January 2020 to August 2026 for original primary studies reporting the diagnostic accuracy of NT-proBNP and/or AI-ECG for AHF, or its structural correlate LVSD, in adult ED patients. Full database-specific search strategies are reported. Risk of bias was assessed with Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) and reporting completeness of the artificial intelligence studies with the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) 2024. Heterogeneity in target conditions, thresholds and reference standards precluded meta-analysis, and comparisons were classified a priori as direct (within-cohort) or indirect (between-study). Eleven studies comprising more than 40,000 ED encounters were included. NT-proBNP discriminated adjudicated AHF consistently across large prospective cohorts (area under the curve (AUC) 0.87-0.92), with excellent rule-out performance at 300 pg/mL (sensitivity 96%-99%, negative predictive value 95%-98%) but modest specificity (54%-56%). AI-ECG achieved AUCs of 0.88-0.94, highest for LVSD rather than adjudicated AHF, and exceeded NT-proBNP in all four direct within-cohort comparisons (0.89 vs 0.80; 0.91-0.92 vs 0.75). In contrast to the standardised NT-proBNP decision limits, only three of seven AI-ECG studies reported an explicit operating threshold, and the models were trained on four different target labels. Eight studies were at low and three at high risk of bias. CLAIM appraisal showed complete reporting of study design and evaluation but incomplete reporting of model specification, data partitioning and data availability. NT-proBNP remains the better-validated test for adjudicated AHF and retains unmatched rule-out value, whereas AI-ECG offers faster and cheaper detection of structural substrate. Because no study compared the two tests against an adjudicated AHF reference standard, they appear complementary rather than interchangeable, and prospective head-to-head and outcome-based studies are required.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.