Abstract
Bedside patient monitors are ubiquitous tools in modern critical care units to provide timely patient status. However, current systems suffer from high volume of false alarms leading to alarm fatigue, one of top technical hazards in clinical settings. Many studies are racing to develop improved algorithms towards precision patient monitoring, while little has been done to investigate the aspect of algorithm generalizability across different health institutions. Our group has been developing an evolving framework termed SuperAlarm that extracts multivariate patterns in data streams (monitor alarms, electronic health records and physiologic waveforms) of modern health enterprise to predict patient deterioration and has demonstrated great potential in mitigating alarm fatigue. In this study, we further investigate the generalizability of SuperAlarm by designing a comprehensive approach to achieve performance comparison in predicting in-hospital code blue (CB) events across two health institutions. SuperAlarm model trained with alarm data in one institution is tested on both internal and external test sets. Results show comparable performance with sensitivity up to 80% within one-hour window of events and over 90% in reduction of false alarms in both institutions. Cross-institutional performance agreement can be further improved by predicting a more stringent CB subtype (cardiopulmonary arrest), with internal sensitivity lying within 95% confident interval of external one up to 8-hour before event onset. The cross-institutional performance comparison offers first-hand knowledge on both advantages and challenges in generalizing a prediction algorithm across different institutions, which hold key information to guide the design of model training and deployment strategy.
Highlights
Bedside patient monitors are essential clinical devices in acute care settings that provide timely information about patients’ physiologic condition
When comparing other two metrics, external performance achieves higher Alarm frequency reduction rate (AFRR) at 94.9% than internal AFRR at 93.1% (p
The present study follows the consistent SuperAlarm framework as our previous studies [27], [28] but with much larger cross-institutional datasets and selection of model parameters, while focuses on developing a comprehensive scheme to test the generalizability of SuperAlarm across different institutions
Summary
Bedside patient monitors are essential clinical devices in acute care settings that provide timely information about patients’ physiologic condition. A variety of factors individually or collectively contribute to the excessive false alarms including inappropriate system settings, suboptimal signal quality and deficiencies in proprietary algorithms [7]. Another significant contributor to the excessive alarms is nuisance alarms. Bedside caregivers can develop alarm fatigue as they are constantly exposed to visual and auditory sensory overload from excessive alarms in a typical 8-12 hour shift [11]–[14] This creates an unsafe clinical environment as alarms of impending adverse events might be overlooked among false or nuisance ones, resulting in delayed or even missed opportunity for timely intervention [15]–[18]. This may inflate the stress level of patients as these alarms direct act at the bedside leading to a decline in the quality of patient care
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE access : practical innovations, open solutions
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
