Found 18017 matches for
Due to a lack of integration between different sensors, false alarms (FA) in the intensive care unit (ICU) are frequent and can lead to reduced standard of care. We present a novel framework for FA reduction using a machine learning approach to combine up to 114 signal quality and physiological features extracted from the electrocardiogram, photoplethysmograph, and optionally the arterial blood pressure waveform. A machine learning algorithm was trained and evaluated on a database of 4107 expert-labeled life-threatening arrhythmias, from 182 separate ICU visits. On the independent test data, FA suppression results with no true alarm (TA) suppression were 86.4% for asystole, 100% for extreme bradycardia and 27.8% for extreme tachycardia. For the ventricular tachycardia alarms, the best FA suppression performance was 30.5% with a TA suppression rate below 1%. To reduce the TA suppression rate to zero, a reduction in FA suppression performance to 19.7% was required. © 2012 Elsevier Inc.
Healthcare information, and to some extent patient management, is progressing toward a wireless digital future. This change is driven partly by a desire to improve the current state of medicine using new technologies, partly by supply-and-demand economics, and partly by the utility of wireless devices. Wired technology can be cumbersome for patient monitoring and can restrict the behavior of the monitored patients, introducing bias or artifacts. However, wireless technologies, while mitigating some of these issues, have introduced new problems such as data dropout and “information overload” for the clinical team. This review provides an overview of current wireless technology used for patient monitoring and disease management. We identify some of the major related issues and describe some existing and possible solutions. In particular, we discuss the rapidly evolving fields of telemedicine and mHealth in the context of increasingly resource-constrained healthcare systems.