Improving the quality of ECGs collected using mobile phones: The PhysioNet/Computing in Cardiology Challenge 2011

摘要: The aim of the PhysioNet/Computing in Cardiology Challenge 2011 was to develop an efficient algorithm able run within a mobile phone, that can provide useful feedback process acquiring diagnostically 12-lead ECG recordings. PhysioNet provided large set records for use Challenge, together with open-source sample application on Android and classify ECGs as acceptable or unacceptable. A total 49 teams individuals participated challenge, which entailed three events. In event 1, participants developed algorithms classifying respect quality, submitted their algorithms' classifications 500 ECGs, obtaining 89–93% accuracy using variety methods. 2, Java implementations be used application; we tested these two reference phones same data scoring method 80–91% accuracy. Event 3 similar but conducted not available study by participants, function both phone processing speed; this event, levels were achieved average execution times less than 2 seconds phones.