Mappings for "Developing a Scalable Annotation Method for Large Datasets That Enhances Alarms With Actionability Data to Increase Informativeness: Mixed Methods Approach"
View DatasetDescription
Studies identified false and non-actionnable alarms as a factor for alarm fatigue in intensive care units.To annotate patient alarms, and analyse the alarm situation in intensive care units, we conceptualized and performed data mappings related to airway management and medication interventions. The mappings were based on information retrieved from the patient data management system (PDMS) and clinical expertise. For the airway management mappings, we used additional resources such as ISO 19223:2019 or ventilator instruction manuals. The mappings do not include patient data.As the mappings are generic, they could be used in other contexts than alarm annotation and research.1. Respiratory Management Mappings:General tables summarizing the 1) categories based on ISO 19223:2019 to describe respiratory support therapies (RSTs), 2) defining the invasiveness level of a RST and 3) listing the abbreviations used in the mappingsTables including PDMS entries for airway devices (ADs), ventilation devices (VDs), and ventilation modes (VMs)Mapping of AD entries (from the PDMS) to defined categoriesMapping of VDs, VMs, and ADs to defined RSTs, including information on invasivenessTable specifying suitable ventilation parameters in the context of each RST2. Medication Mappings:General tables providing information on physiological alarm conditions (PACs), interventions, routes, and techniques of administration of interestMapping of routes of administration to techniques of administration including PDMS entriesMapping of active ingredients (including SNOMED CT Fully Specified Names and Identifiers), related PDMS information, and routes and techniques of administration to defined PAC and interventions
Citations (1)
- https://doi.org/10.2196/65961DataCite MDC
Cited on 14 October 2024
Weight: 1.00
Mentions (0)
No mentions found
Metrics Over Time
Publication Details
Subfield
Radiology, Nuclear Medicine and Imaging
Field
Medicine
Domain
Health Sciences
Confidence Score
44%
Source
Scholar Data Model