AUTHOR=Gellert George A. , Kabat-Karabon Aleksandra , Gellert Gabriel L. , Rasławska-Socha Joanna , Gorski Stanislaw , Price Tim , Kuszczyński Kacper , Marcjasz Natalia , Palczewski Mateusz , Jaszczak Jakub , Loh Irving K. , Orzechowski Piotr M. 

TITLE=The potential of virtual triage AI to improve early detection, care acuity alignment, and emergent care referral of life-threatening conditions

JOURNAL=Frontiers in Public Health

VOLUME=Volume 12 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2024.1362246

DOI=10.3389/fpubh.2024.1362246

ISSN=2296-2565

ABSTRACT=Objective: Evaluate the extent to which patient-users reporting symptoms of five severe/acute conditions classified by an AI-based virtual triage (VT) engine as warranting emergency care had no pre-VT intention to engage emergency department (ED) care, and whose care intention was misaligned or decoupled from actual risk of life-threatening symptoms.Methods: A dataset of 3,022,882 VT interviews over 16-months was evaluated to quantify and describe patient-users reporting symptoms of five potentially life-threatening conditions with pre-triage healthcare intention other than seeking urgent care, including myocardial infarction, stroke, asthma exacerbation, pneumonia and pulmonary embolism.Results: Data from 12,101 eligible VT patient-user episodes revealed a weighted mean of 38.5% of individuals VT referred to emergency care having a pre-triage healthcare intent excluding consulting a physician; a weighted mean of 61.5% would consult an outpatient physician but not seek emergency care.After adjustment for 13% VT safety over-triage/referral to ED, a weighted mean of 33.5% of patientusers had no intent to seek professional care, and 53.5% had no intent to seek emergent care.Conclusions: AI-based VT may offer a vehicle for earlier detection/care acuity alignment of severe evolving pathology by engaging patients who believe their symptoms are not serious, and for accelerating care referral/delivery for life-threatening pathologies where patient misunderstanding of risk, or indecision, cause care delay. A next step will be clinical confirmation that when decoupling of patient care intent from emergent care need occurs, VT can influence patient behavior to accelerate care referral and/or emergency care dispatch and treatment to improve clinical outcomes.