Stroke is a leading cause of death worldwide. With escalating healthcare costs, early non-invasive stroke risk stratification is vital. The current paradigm of stroke risk assessment and mitigation is focused on clinical risk factors and comorbidities. Standard algorithms predict risk using regression-based statistical associations, which, while useful and easy to use, have moderate predictive accuracy. This review summarises recent efforts to deploy machine learning (ML) to predict stroke risk and enrich the understanding of the mechanisms underlying stroke. The surveyed body of literature includes studies comparing ML algorithms with conventional statistical models for predicting cardiovascular disease and, in particular, different stroke subtypes. Another avenue of research explored is ML as a means of enriching multiscale computational modelling, which holds great promise for revealing thrombogenesis mechanisms. Overall, ML offers a new approach to stroke risk stratification that accounts for subtle physiologic variants between patients, potentially leading to more reliable and personalised predictions than standard regression-based statistical associations.
Background Following atrial fibrillation ablation, it is challenging to distinguish patients who will remain arrhythmia-free from those at risk for recurrence. New explainable machine learning (xML) techniques allow for systematic assessment of arrhythmia recurrence risk following catheter ablation. We aim to develop an xML algorithm that predicts recurrence and reveals key risk factors to facilitate better follow-up strategy after an ablation procedure. Methods We reconstructed pre-and post-ablation models of the left atrium (LA) from late gadolinium enhanced magnetic resonance (LGE-MRI) for 67 patients. Patient-specific features (LGE-based measurements of pre/post-ablation arrhythmogenic substrate, LA geometry metrics, computational simulation results, and clinical risk factors) trained a random forest classifier to predict recurrent arrhythmia. We calculated each risk factor’s marginal contribution to model decision making via SHapley Additive exPlanations (SHAP). Results The classifier accurately predicts post-ablation arrhythmia recurrence (mean receiver operating characteristic [ROC] area under the curve [AUC]: 0.80 ± 0.04; mean precision-recall [PR] AUC: 0.82 ± 0.08). SHAP analysis reveals that of 89 features tested, the key population risk factors for recurrence are: large left atrium, low LGE-quantified post-ablation scar in the atrial floor region, and previous attempts at direct current cardioversion. We also examine patient-specific recurrence predictions, since xML allows us to understand why a particular individual can have large prediction weights for some categories without tipping the balance towards an incorrect prediction. Finally, we validate our model in a completely new, 15-patient retrospective holdout cohort (80% correct). Conclusion Our SHAP-based explainable machine learning approach is a proof-of-concept clinical tool to explain arrhythmia recurrence risk in patients who underwent ablation by combining patient-specific clinical profiles and LGE-derived data.
Brain injury after hypoxia–ischemia (HI) is the leading cause of morbidity and mortality in term and near-term neonates worldwide. The ferret is a promising translational model to study HI due to its gyrified brain and white-to-gray matter ratio that more closely resembles humans compared to rodents. Caffeine, an adenosine A2A receptor (A2AR) antagonist, shows neuroprotective potential after HI, but its effects have not been fully characterized. We sought to evaluate caffeine’s effect on neuronal cell death, cytotoxicity, and inflammatory and oxidative stress markers in a term-equivalent ferret organotypic brain slice model of HI. Slices were cultured for 72 h, exposed to two hours of oxygen–glucose deprivation (OGD), and randomized to OGD alone, OGD with caffeine (20 or 50 mg/L), or OGD with caffeine and an A2AR agonist. Healthy slices served as controls. Outcomes included global cell death, regional cell death, microglial morphology, and expression of inflammatory and oxidative stress genes (46–48 slices/group for cell death assays and 18 slices/group for imaging, balanced by sex). Caffeine 50 mg/L significantly reduced global cell death compared to OGD (p = 0.02), and this effect persisted despite co-administration of an A2AR agonist (p = 0.01), suggesting that protection was not primarily mediated through A2AR signaling. Caffeine also did not change regional pyknotic nuclei counts (p > 0.05). Caffeine altered microglial morphology, increasing the proportion of microglia with features characteristic of control conditions. OGD significantly increased expression of inflammatory and oxidative stress-related genes (p < 0.05) compared with control slices, whereas caffeine did not significantly alter gene expression. In summary, caffeine partially reversed global cell death after OGD and altered microglial morphology. Larger, higher-powered studies are needed to further investigate caffeine’s effects on neonatal HI.
7 July 2026 in Catheterization and Cardiovascular Interventions