Predictive and diagnosis models of stroke from hemodynamic signal monitoring

This work presents a novel and promising approach to the clinical management of acute stroke. Using machine learning techniques, our research has succeeded in developing accurate diagnosis prediction real-time models from hemodynamic data. These are able diagnose stroke subtype with 30 minutes monitoring, predict exitus during first 3 hours recurrence just 15 monitoring. Patients difficult access \acrshort{CT} scan, all patients that arrive at unit specialized hospital will benefit these positive results. The results obtained developed following: around $98\%$ precision ($97.8\%$ Sensitivity, $99.5\%$ Specificity), $99.8\%$ ($99.8\%$ Sens., $99.9\%$ Spec.) predicting ($98\%$ $99\%$ Spec.).