Key result
A rule-based, semi-automatic annotation method combining alarm and patient data was developed to classify intensive care unit alarms as actionable or non-actionable for machine learning purposes.
Why the study?
False and non-actionable alarms contribute to alarm fatigue in ICUs, but annotating alarm and patient data for machine learning solutions is complex and resource intensive.
A rule-based annotation method combining alarm and patient data can facilitate the scalable classification of ICU alarms for machine learning, aiming to reduce alarm fatigue.
Answers are grounded in this paper and cite their sources.
May enable scalable ML annotation for ICU alarm reduction; leaves open clinical efficacy and requires prospective validation.
Alarm fatigue, a multi-factorial desensitization of personnel toward alarms, can harm both patients and healthcare staff in intensive care units (ICU). False and non-actionable alarms contribute to this condition. With an increasing number of alarms and more patient data being routinely collected and documented in ICUs, machine learning could help reduce alarm fatigue. As data annotation is complex and resource intensive, we propose a rule-based annotation method combining alarm and patient data to classify alarms as either actionable or non-actionable. This study presents the development of the annotation method and provides resources that were generated during the process, such as mappings.
No takes yet. Share an insight, caveat, or question.
Klopfenstein et al. (2023) studied Alarm fatigue in intensive care units. Rule-based semi-automatic annotation method was evaluated. A rule-based, semi-automatic annotation method combining alarm and patient data was developed to classify intensive care unit alarms as actionable or non-actionable for machine learning purposes.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: