Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-2048
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-20T22:03:31.080439Z
status: published
lens: g_space
sector: health
headline: Teleassistance and Artificial Intelligence to Support Prehospital Triage by Emergency Nurses: A Scoping Review
dek: Introduction To map and critically synthesize international evidence on the use of teleassistance and artificial intelligence to support emergency nurses in prehospital triage. Background Digital transformation and artificial intelligence are reshaping emergency care systems. In Europe, emergency nurses working within dispatch and telecommunication centers (112/118; 112 being the pan-European emergency number and 118 being the Italian national emergency medical service number) increasingly manage remote assessme…
gain_title: Across five included studies, AI and digital triage systems were associated with improved triage consistency and timeliness, and video teleassistance with fewer inappropriate ED transfers and greater nurse confidence.
problem_title: (none)
trace_subject: (none)
gain_reading: Across five included studies, AI and digital triage systems were associated with improved triage consistency and timeliness, and video teleassistance with fewer inappropriate ED transfers and greater nurse confidence.
gain_evidence: Digital and artificial intelligence systems were associated with improved triage consistency and timeliness. | Video teleassistance was associated with fewer inappropriate ED transfers and increased professional confidence.
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers searched four databases covering 2005 to 2024 for studies of nurses using teleassistance or artificial intelligence in prehospital triage. Of 1214 records identified, only five studies met the inclusion criteria, and these covered video calls, digital and AI triage systems, and the cognitive demands of telephone triage.

The findings suggest these tools may help emergency nurses assess patients remotely more accurately, quickly and confidently. The evidence base is very small, and many full-text reports could not be retrieved, so the strength and generalizability of the conclusions remain uncertain and call for further nurse-led research.
limitation: Only five studies were included, and 72 of 165 reports sought (43.6%) could not be retrieved, mainly because of restricted full-text access, which limits how far the findings can be generalized.
tag: Evidence-backed gain
key_points: Only 5 of 93 reports assessed for eligibility met the inclusion criteria: 2 experimental video-call studies, 2 observational digital or AI triage studies, and 1 qualitative study. | Video teleassistance was associated with fewer inappropriate emergency department transfers and increased professional confidence. | Digital and AI systems were associated with improved triage consistency and timeliness. | The mean quality score was 83% on Joanna Briggs Institute tools, with no high-risk studies.
rundown: The review followed Joanna Briggs Institute methodology and PRISMA extension guidelines for scoping reviews, with a protocol registered on the Open Science Framework. Searches ran in PubMed, Scopus, CINAHL and Embase, and two reviewers independently screened 910 titles and abstracts after 304 duplicates were removed.

The setting is emergency nurses in dispatch and telecommunication centers, such as the 112 and 118 numbers, who increasingly manage remote assessments using video and algorithmic tools. The authors note that evidence on impact, safety and integration into clinical practice remains limited.

A qualitative study included in the review illustrated the high cognitive complexity of remote assessment. The authors conclude that structured governance, training and human oversight remain essential alongside these technologies.
sources:
- peer_reviewed | Journal of Emergency Nursing | https://doi.org/10.1016/j.jen.2026.08.008 | 2026-10-13
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

168de00264b712665b4d81c536dad495d3ea02c0e1b92376503c442dc11a589c

previous

0000000000000000000000000000000000000000000000000000000000000000