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

Abstract

ObjectiveTo evaluate the extent to which patient-users reporting symptoms of five severe/acute conditions requiring emergency care to an AI-based virtual triage (VT) engine had no intention to get such care, and whose acuity perception was misaligned or decoupled from actual risk of life-threatening symptoms.MethodsA dataset of 3,022,882 VT interviews conducted over 16 months was evaluated to quantify and describe patient-users reporting symptoms of five potentially life-threatening conditions whose pre-triage healthcare intention was other than seeking urgent care, including myocardial infarction, stroke, asthma exacerbation, pneumonia, and pulmonary embolism.ResultsHealthcare intent data was obtained for 12,101 VT patient-user interviews. Across all five conditions a weighted mean of 38.5% of individuals whose VT indicated a condition requiring emergency care had no pre-triage intent to consult a physician. Furthermore, 61.5% intending to possibly consult a physician had no intent to seek emergency medical care. After adjustment for 13% VT safety over-triage/referral to ED, a weighted mean of 33.5% of patient-users had no intent to seek professional care, and 53.5% had no intent to seek emergency care.ConclusionAI-based VT may offer a vehicle for early detection and care acuity alignment of severe evolving pathology by engaging patients who believe their symptoms are not serious, and for accelerating care referral and delivery for life-threatening conditions where patient misunderstanding of risk, or indecision, causes 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 engagement and/or emergency care dispatch and treatment to improve clinical outcomes.

Using AI-based virtual triage to improve acuity-level alignment of patient care seeking in an ambulatory care setting

“…Improved care acuity alignment through automated triage and accelerated care referral can reduce care delays, a contributor to preventable morbidity/mortality and unnecessary care utilization. [12][13][14][15][16][17][18][19][20][21][22][23] It could also potentially enable a reduction of avoidable care utilization at higher than necessary levels of care acuity, which can help reduce avoidable healthcare over-utilization, and associated avoidable care expenditure or costs. However, an almost equal percentage of patients did not change their care seeking when pre-VT intent was not aligned with the care recommendation generated by VT AI, indicating that AI-based VT must continue its evolution and continuous improvement in how it influences patient-user perception, and how effectively it compels changes in patient care seeking behavior.…”

“…The fact that roughly two-thirds of patients who changed their healthcare seeking behavior did so to escalate the acuity of care sought suggests that VT may also have value in earlier detecting and referring conditions which can reduce care delays, and favorably impact patient outcomes and system financial performance. [12][13][14][15][16][17][18][19][20][21][22][23] While it is clinically intuitive that only a handful of patients using VT with a pre-VT intent to visit an ED changed their care seeking to lower acuity care, it is noteworthy that 1.3% of all patients using VT with a non-ED pre-VT intent followed the advice of VT to seek ED care. It appears from this data that few patients with emergency conditions use VT in an ambulatory care setting.…”

“…Nonetheless, evidence suggests that VT can detect early prodromal symptoms of common, life-threatening conditions among those accessing the Symptomate functionality available on the internet from home or work. [23] Thus, VT may have a role in early detection/referral of life-threatening symptoms.…”

“…Research on such synergistic integration of other virtual and digital diagnostic technologies could revolutionize the accuracy and power of AI-based VT to earlier identify patients at elevated risk of severe illness, and accelerate healthcare delivery for conditions where care delays can mean the difference between life and death. [23] It will also enable far greater accuracy in acuity assessment and appropriate care acuity patient guidance, reducing avoidable higher than necessary acuity care seeking and utilization, and expanding telemedical care opportunities. This will allow over-utilized EDs to function as EDs rather than as primary care clinics, reduce overall care system and out-of-pocket expenses for patients, and help health systems and payers achieve far greater efficiencies in managing all outpatient care delivery.…”