2018/04/25 by Mohammad Zaeri-Amirani, Zaeri-Amirani, Mohammad, Fatemeh Afghah +3 · 1 citation
Engineering · Medicine · #Computer Science and Game Theory (cs.GT) #FOS: Computer and information sciences #FOS: Electrical engineering #Fault Detection and Control Systems #Healthcare Technology and Patient Monitoring #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1804.11196
openalex publication_date 2018/04/25 · openalex created_date 2022/10/04 · openalex updated_date 2026/07/28
High false alarm rate in intensive care units (ICUs) has been identified as\none of the most critical medical challenges in recent years. This often results\nin overwhelming the clinical staff by numerous false or unurgent alarms and\ndecreasing the quality of care through enhancing the probability of missing\ntrue alarms as well as causing delirium, stress, sleep deprivation and\ndepressed immune systems for patients. One major cause of false alarms in\nclinical practice is that the collected signals from different devices are\nprocessed individually to trigger an alarm, while there exists a considerable\nchance that the signal collected from one device is corrupted by noise or\nmotion artifacts. In this paper, we propose a low-computational complexity yet\naccurate game-theoretic feature selection method which is based on a genetic\nalgorithm that identifies the most informative biomarkers across the signals\ncollected from various monitoring devices and can considerably reduce the rate\nof false alarms.\n