Medical practitioner perspectives on AI in emergency triage

Introduction

A proposed Diagnostic AI System for Robot-Assisted Triage ("DAISY") is under development to support Emergency Department ("ED") triage following increasing reports of overcrowding and shortage of staff in ED care experienced within National Health Service, England ("NHS") but also globally. DAISY aims to reduce ED patient wait times and medical practitioner overload. The objective of this study was to explore NHS health practitioners' perspectives and attitudes towards the future use of AI-supported technologies in ED triage.

Methods

Between July and August 2022 a qualitative-exploratory research study was conducted to collect and capture the perceptions and attitudes of nine NHS healthcare practitioners to better understand the challenges and benefits of a DAISY deployment. The study was based on a thematic analysis of semi-structured interviews. The study involved qualitative data analysis of the interviewees' responses. Audio-recordings were transcribed verbatim, and notes included into data documents. The transcripts were coded line-by-line, and data were organised into themes and sub-themes. Both inductive and deductive approaches to thematic analysis were used to analyse such data.

Results

Based on a qualitative analysis of coded interviews with the practitioners, responses were categorised into broad main thematic-types, namely: trust; current practice; social, legal, ethical, and cultural concerns; and empathetic practice. Sub-themes were identified for each main theme. Further quantitative analyses explored the vocabulary and sentiments of the participants when talking generally about NHS ED practices compared to discussing DAISY. Limitations include a small sample size and the requirement that research participants imagine a prototype AI-supported system still under development. The expectation is that such a system would work alongside the practitioner. Findings can be generalisable to other healthcare AI-supported systems and to other domains.

Discussion

This study highlights the benefits and challenges for an AI-supported triage healthcare solution. The study shows that most NHS ED practitioners interviewed were positive about such adoption. Benefits cited were a reduction in patient wait times in the ED, assistance in the streamlining of the triage process, support in calling for appropriate diagnostics and for further patient examination, and identification of those very unwell and requiring more immediate and urgent attention. Words used to describe the system were that DAISY is a "good idea", "help", helpful, "easier", "value", and "accurate". Our study demonstrates that trust in the system is a significant driver of use and a potential barrier to adoption. Participants emphasised social, legal, ethical, and cultural considerations and barriers to DAISY adoption and the importance of empathy and non-verbal cues in patient interactions. Findings demonstrate how DAISY might support and augment human medical performance in ED care, and provide an understanding of attitudinal barriers and considerations for the development and implementation of future triage AI-supported systems.

The Effect of Human Supervision on an Electronic Implementation of the Canadian Triage Acuity Scale (CTAS)

BACKGROUND

Most electronic emergency department (ED) triage systems allow nurses to modify computer-generated triage scores. It is currently unclear how this affects triage validity.

OBJECTIVE

Are nurse-generated triage scores more strongly associated with rates of admission, intensive care unit (ICU) consultation, and mortality than computer-generated scores?

METHODS

Retrospective observational cohort study of all adult visits to a tertiary ED. An electronic implementation of the Canadian Triage Acuity Scale (CTAS) generated a CTAS score for each visit. In some cases, the triage nurse overwrote the computer-generated CTAS score with a score they felt was more appropriate. Among visits with nurse-modified triage scores, we compared the rate of acuity-related outcomes (mortality, ICU consultation, hospital admission) in each CTAS level as categorized by nurse-generated vs. computer-generated scores.

RESULTS

In a cohort of 229,744 patients, 19,566 (8.51%) had nurse-modified triage scores. Most modifications consisted of assigning a higher acuity triage score than recommended by the computer. Visits with triage scores 1-2 according to the nurse-generated scores had the same or higher rates of the acuity outcomes than visits that were CTAS 1-2 according to the computer-generated CTAS scores. Conversely, visits with triage scores 4-5 according to the nurse-generated scores had lower rates of the outcomes than visits that were CTAS 4-5 according to the computer-generated CTAS scores.

CONCLUSIONS

Nursing supervision of the computer-automated CTAS triage system was associated with fewer hospital admissions, ICU consultations, and deaths in the triage score 4-5 categories, suggesting a safer triage process than the automated CTAS algorithm alone.

Transition in Care from EMS Providers to Emergency Department Nurses: A Systematic Review

Background: Transitions in care between emergency medical services (EMS) providers and emergency department (ED) nurses are critical to patient care and safety. However, interactions between EMS providers and ED nurses can be problematic with communication gaps and have not been extensively studied. The aim of this review was to examine (1) factors that influence transitions in care from EMS providers to ED nurses and (2) the effectiveness of interventional strategies to improve these transitions. Methods: We conducted a mixed-methods systematic review that included searches of electronic databases (DARE, MEDLINE, EMBASE, Cochrane Central Register of Controlled Trials, CINAHL, Joanna Briggs Institute EBP), gray literature databases, organization websites, querying experts in emergency medicine, and the reference lists cited in included studies. All English-language studies of any design were eligible for inclusion. Two reviewers independently screened titles/abstracts and full-texts for inclusion and methodological quality, as well as extracted data from included studies. We used narrative and thematic synthesis to integrate and explore relationships within the data. Results: In total, 8,348 studies were screened and 130 selected for full text review. The final synthesis included 20 studies. Across 15 studies of moderate-to-high methodological quality, 6 factors influenced transitions: different professional lenses, operational constraints, professional relationships, information shared between the professions, components of the transition process, and patient presentation and involvement. Three interventions were identified in 6 methodologically weak studies: (1) transition guideline (DeMIST, Identification, Mechanism/Medical complaint, Injuries/Information related to the complaint, Signs, Treatment and Trends - Allergies, Medication, Background history, Other information [IMIST-AMBO]) with training, (2) mobile web-based technology (EMS smartphone and geographic information system location data), and (3) a new clinical role (ED ambulance off-load nurse dedicated to triaging and assessing EMS patients). There were mixed findings for the effectiveness of transition guidelines and the new clinical role. Mobile technology was seen positively by both EMS providers and ED nurses as helpful for better describing the pre-hospital context and for planning flow in the ED. Conclusion: While multimedia applications may potentially improve the handoff process, future intervention studies need to be rigorously designed. We recommend interdisciplinary training of EMS and ED staff in the use of flexible structured protocols, especially given review findings that interdisciplinary communication and relationships can be challenging.