BACKGROUND AND PURPOSE Organized systems of care have the potential to improve acute stroke care delivery. The current report describes the experience of implementing a countywide system of spoke-and-hub Stroke Neurology Receiving Centers (SNRC) that incorporated several comprehensive stroke center recommendations. METHODS Observational study of patients with suspected stroke <5 hours duration transported by Emergency Medical System personnel to an SNRC during the first year of this system. RESULTS A total of 1,360 patients with suspected stroke were evaluated at 9 hub SNRCs, of which 553 (40.7%) had a discharge diagnosis of ischemic stroke. Of these 553, intravenous (IV) tPA was given to 110 patients (19.9% of ischemic strokes). Care at the 6 neurointerventional-ready SNRC was a major focus, where 25.1% (99/395) of the patients with ischemic stroke received acute IV or intraarterial reperfusion therapy, and where provision of such therapies was less common with milder stroke, higher age, and Hispanic origin. The door-to-needle time for IV tPA met the <60 minute target in only 25% of patients and was 37% longer (p=0.0001) when SNRCs were neurointerventional-ready. CONCLUSIONS A stroke system that incorporates features of comprehensive stroke centers can be effectively implemented, and with substantial rates of acute reperfusion therapy administration. Experiences potentially useful to broader implementation of comprehensive stroke centers are considered.

Atrial fibrillation (AF) is the most common cardiac disease and is associated with other cardiac complications. Few attempts have been made for discriminating AF from other arrhythmias and noise. The aim of this study is to present a novel approach for such a classification in short ECG recordings acquired using a smartphone device. The implemented algorithm was tested on the Physionet Computing in Cardiology Challenge 2017 Database and, for the purpose of comparison, on the MIT-BH AF database. After feature extraction, the stepwise linear discriminant analysis for feature selection was used. The Least Square Support Vector Machine classifier was trained and cross-validated on the available dataset of the Challenge 2017. The best performance was obtained with a total of 30 features. The algorithm produced the following performance: F1 Normal rhythm = 0.92; F1 AF rhythm: 0.82; F1 Other rhythm = 0.75; Global F1 = 0.83, obtaining the third best result in the follow-up phase of the Physionet Challenge. On the MIT-BH ADF database the algorithm gave the following performance: F1 Normal rhythm = 0.98; F1 AF rhythm: 0.99; Global F1 = 0.98. Since the algorithm reliably detect AF and other rhythms in smartphone ECG recordings, it could be applied for personal health monitoring systems.

Aims: Atrial fibrillation (AF) is one of the principal cause of mortality in elderly, thus its detection is extremely clinically relevant. The aim of this study was to classify short, single lead, ECG recordings, as atrial fibrillation, normal sinus rhythm, other type of rhythms or noisy signal. Methods: First, we extracted, both from the ECG signals and from the RR interval series, about fifty features characterizing these four classes. Then, we applied the stepwise linear discriminant analysis for dimensionality reduction selecting a subset of thirty discriminating features. A Least Squares Support Vector Machine (LS-SVM) classifier using these features was tuned and trained on the dataset of the Physionet/Computing in Cardiology Challenge 2017. Results: The LS-SVM classifier provided, on the hidden test set of the Challenge, an official final score F1= 0.81, obtaining the twelfth place in the ranking of results with only 2 cents from the best (0.83). Conclusions: This approach seems promising in particular in detecting atrial fibrillation. Further work is needed to improve the discrimination of other rhythms and noisy signals.

Integration of a commercially available ECG management system with an existing clinical database can provide a rapid, practical solution that requires no major modifications to either software component. The success of this project makes us optimistic about extending CARDIS to support additional examination procedures such as digital coronary angiography and ultrasound examinations.

An integrated epidemiological surveillance and response system was set up for the 2006 Olympic Winter Games in Torino [1] between 1 February