@article{3030316,
    title = "Machine-Learning-Derived Model for the Stratification of Cardiovascular
risk in Patients with Ischemic Stroke",
    author = "Ntaios, George and Sagris, Dimitrios and Kallipolitis, Athanasios and and Karagkiozi, Efstathia and Korompoki, Eleni and Manios, Efstathios and and Plagianakos, Vasileios and Vemmos, Konstantinos and Maglogiannis, Ilias",
    journal = "Journal of Stroke and Cerebrovascular Diseases",
    year = "2021",
    volume = "30",
    number = "10",
    publisher = "Elsevier",
    issn = "1052-3057",
    doi = "10.1016/j.jstrokecerebrovasdis.2021.106018",
    keywords = "  Ischemic stroke; Cardiovascular risk; Risk stratification;
Machine learning",
    abstract = "Background Stratification of cardiovascular risk in patients with
ischemic stroke is impor-tant as it may inform management strategies. We
aimed to develop a machine-learning-derived prognostic model for the
prediction of cardiovascular risk in ischemic stroke patients. Materials
and Methods: Two prospective stroke registries with consecutive acute
ischemic stroke patients were used as training/validation and test
datasets. The outcome assessed was major adverse cardiovascular event,
defined as non-fatal stroke, non-fatal myocardial infarction, and
cardiovascular death during 2-year follow-up. The variables selection
was performed with the LASSO technique. The algorithms XGBoost (Extreme
Gradient Boosting), Random Forest and Support Vector Machines were
selected accord-ing to their performance. The evaluation of the
classifier was performed by bootstrap-ping the dataset 1000 times and
performing cross-validation by splitting in 60% for the training
samples and 40% for the validation samples. Results: The model included
age, gender, atrial fibrillation, heart failure, peripheral artery
disease, arterial hypertension, statin treatment before stroke onset,
prior anticoagulant treatment (in case of atrial fibril-lation),
creatinine, cervical artery stenosis, anticoagulant treatment at
discharge (in case of atrial fibrillation), and statin treatment at
discharge. The best accuracy was measured by the XGBoost classifier. In
the validation dataset, the area under the curve was 0.648
(95%CI:0.619-0.675) and the balanced accuracy was 0.58 </n> 0.14. In
the test dataset, the corresponding values were 0.59 and 0.576.
Conclusions: We propose an externally vali-dated
machine-learning-derived model which includes readily available
parameters and can be used for the estimation of cardiovascular risk in
ischemic stroke patients. (c) 2021 Elsevier Inc. All rights reserved."
}