Key result
CBC inflammatory indices link to post-AMI AF but provide uncertain incremental predictive value.
Why the study?
New-onset AF after AMI is associated with adverse outcomes and inflammation contributes to AF onset and progression, motivating an interpretable ML framework integrating CBC-derived inflammatory indices with routine clinical parameters for risk assessment.
Does integrating complete blood count-derived inflammatory indices with routine clinical parameters in a machine learning framework improve the prediction of new-onset atrial fibrillation in patients with acute myocardial infarction?
Cohort (n=3,077)
No
Does integrating complete blood count-derived inflammatory indices with routine clinical parameters in a machine learning framework improve the prediction of new-onset atrial fibrillation in patients with acute myocardial infarction?
Although CBC-derived systemic inflammatory indices are independently associated with new-onset atrial fibrillation after acute myocardial infarction, integrating them into machine learning models provides uncertain incremental predictive value over routine clinical parameters like left atrial diameter, age, and BNP.
Answers are grounded in this paper and cite their sources.
Does not support routine use of inflammatory indices for post-MI AF prediction; leaves open incremental utility beyond standard metrics.
New-onset atrial fibrillation (NOAF) after acute myocardial infarction (AMI) is associated with adverse outcomes. Inflammation contributes to atrial fibrillation (AF) onset and progression. We developed an interpretable machine learning (ML) framework integrating complete blood count (CBC)-derived inflammatory indices with routine clinical parameters for NOAF risk assessment. We retrospectively analyzed 3,077 AMI patients without prior AF (2018–2023). Multivariable logistic regression, restricted cubic splines (RCS), and threshold analyses evaluated six inflammatory indices: neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), systemic immune-inflammation index (SII), monocyte-to-lymphocyte ratio (MLR), systemic inflammation response index (SIRI), and aggregate index of systemic inflammation (AISI). Boruta and LASSO selections were intersected. Eight ML models were evaluated, with Shapley Additive Explanations (SHAP) for interpretation. NOAF incidence was 7.73%. Six indices were associated with NOAF in separate adjusted models (all p < 0.05). Estimated change points were approximately 5.5 (NLR), 1217 (SII), 2.9 (SIRI), and 430 (AISI). The support vector machine (SVM) achieved the highest mean training out-of-fold (OOF) area under the precision–recall curve (PR-AUC; 0.357) and a held-out test PR-AUC of 0.407. Mean absolute SHAP values were highest for left atrial diameter (LAD), age, and B-type natriuretic peptide (BNP); SIRI ranked first among inflammatory features. Fixed-feature ablation showed modest PR-AUC and Brier-score improvements, uncertain ROC-AUC gains, and no consistent net benefit on decision-curve analysis. CBC-derived inflammatory indices were associated with NOAF, but their incremental predictive value beyond routine clinical variables remains uncertain. Given moderate predictive performance and no external validation, multicenter validation is needed before clinical implementation.
No takes yet. Share an insight, caveat, or question.
Meng et al. (2026) conducted a cohort in Acute myocardial infarction (AMI) (n=3,077). CBC-derived systemic inflammatory indices (NLR, PLR, SII, MLR, SIRI, AISI) integrated into machine learning models vs. Routine clinical parameters without inflammatory features was evaluated on New-onset atrial fibrillation (NOAF) (p=< 0.05). CBC-derived inflammatory indices were associated with new-onset AF post-AMI, but offered uncertain incremental value over routine variables.
Synapse has enriched 10 related papers. Consider them for comparative context: