AUTHOR=Ramos Lucas A. , Kappelhof Manon , van Os Hendrikus J. A. , Chalos Vicky , Van Kranendonk Katinka , Kruyt Nyika D. , Roos Yvo B. W. E. M. , van der Lugt Aad , van Zwam Wim H. , van der Schaaf Irene C. , Zwinderman Aeilko H. , Strijkers Gustav J. , van Walderveen Marianne A. A. , Wermer Mariekke J. H. , Olabarriaga Silvia D. , Majoie Charles B. L. M. , Marquering Henk A.
TITLE=Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke
JOURNAL=Frontiers in Neurology
VOLUME=11
YEAR=2020
URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2020.580957
DOI=10.3389/fneur.2020.580957
ISSN=1664-2295
ABSTRACT=Background: Although endovascular treatment (EVT) has greatly improved outcomes in acute ischemic stroke, still one third of patients die or remain severely disabled after stroke. If we could select patients with poor clinical outcome despite EVT, we could prevent futile treatment, avoid treatment complications, and further improve stroke care. We aimed to determine the accuracy of poor functional outcome prediction, defined as 90-day modified Rankin Scale (mRS) score ≥5, despite EVT treatment.
Methods: We included 1,526 patients from the MR CLEAN Registry, a prospective, observational, multicenter registry of ischemic stroke patients treated with EVT. We developed machine learning prediction models using all variables available at baseline before treatment. We optimized the models for both maximizing the area under the curve (AUC), reducing the number of false positives.
Results: From 1,526 patients included, 480 (31%) of patients showed poor outcome. The highest AUC was 0.81 for random forest. The highest area under the precision recall curve was 0.69 for the support vector machine. The highest achieved specificity was 95% with a sensitivity of 34% for neural networks, indicating that all models contained false positives in their predictions. From 921 mRS 0–4 patients, 27–61 (3–6%) were incorrectly classified as poor outcome. From 480 poor outcome patients in the registry, 99–163 (21–34%) were correctly identified by the models.
Conclusions: All prediction models showed a high AUC. The best-performing models correctly identified 34% of the poor outcome patients at a cost of misclassifying 4% of non-poor outcome patients. Further studies are necessary to determine whether these accuracies are reproducible before implementation in clinical practice.