Impact of virtual triage and care referral on patient care seeking intent and clinical acuity alignment in an Australian health plan: A cross-sectional study

Abstract

Objective: To evaluate if artificial intelligence (AI)-based virtual triage and care referral (VTCR) improved care acuity alignment and has the potential to reduce unwarranted, avoidable care costs when integrated into the patient engagement capabilities of an Australian private health insurance company.
Methods: A cross-sectional study compared patient pre- and post-VTCR care intent across 4,471 encounters to evaluate the degree of clinical care acuity re-alignment (or divergence) which occurred and potential associated cost savings.
Results: Overall compliance or alignment with triage recommendations was high (74.0%), and VTCR was effective in educating patients about the most appropriate care to meet their actual clinical needs. One-half of patients (50.5%) changed their care intent. Following VTCR there was a 91.3% reduction of patients with uncertain care intent (39.8 percentage points [PP]); a 56.5% (6.2 PP) increase in intent to engage self-care, and a 35.7% (0.5 PP) decrease in emergency care intent (all p <.05). This yielded a potential $4.27 (8.6%) overall net savings per completed VTCR encounter, with potential savings of $284.55 (72.2%) per completed encounter among patients initially intending to seek emergency care, and 35 unnecessary outpatient visits potentially avoided per 1,000 encounters producing potential savings of $3.39 (6.5%) per completed encounter among patients initially intending to seek outpatient care. Almost 10% of patients intended to book a clinically appropriate telemedicine consultation following VTCR.
Conclusions: VTCR was found to be potentially clinically and cost-effective in re-directing patients who had an initial care intent not supported by their actual clinical acuity, reducing patient care uncertainty and potentially avoidable care utilization. Future research should include clinical validation of patient diagnosis and care services delivered as a primary outcome in order to confirm the potential savings identified in this study.

Keywords

Artificial intelligence / Care acuity alignment / Symptom checker / Telemedicine / Virtual triage and care referral

ACKNOWLEDGEMENTS

The authors are grateful to counterparts at NIB for their engagement and guidance in preparing this article, and to the patients who utilized VTCR and whose data made these analyses possible.

AUTHORS CONTRIBUTIONS

GAG, TP, and AKK designed the study methodology and interpreted the data; GAG wrote the first draft of the manuscript; GAG, TP, AKK and GLG edited all subsequent drafts of the manuscript; TP, AKK and GAG reviewed and organized the data, validated the data analyses, and co-authored the results interpretation and the discussion sections; GLG assisted with project management, literature search, reference integration, and completing journal submission.

FUNDING

No funding supported this work.

CONFLICTS OF INTEREST DISCLOSURE

All authors are either advisors to or employees of Infermedica.

INFORMED CONSENT

Patient-users provided their consent during the virtual triage encounter for their data to be used in a fully de-identified manner within aggregate analyses.

ETHICS APPROVAL

The Publication Ethics Committee of the Association for Health Sciences and Education. The journal’s policies adhere to the Core Practices established by the Committee on Publication Ethics (COPE).

PROVENANCE AND PEER REVIEW

Not commissioned; externally double-blind peer reviewed.

DATA AVAILABILITY STATEMENT

Study data may be made available upon reasonable request.

DATA SHARING STATEMENT

No additional data are available.

OPEN ACCESS

This is an open-access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/4.0/).

COPYRIGHTS

Copyright for this article is retained by the author(s), with first publication rights granted to the journal.

References

[1] Shaver J. The state of telehealth before and after the COVID-19 pandemic. Prim Care. 2022; 49(4): 517-530. PMid: 36357058. https://doi.org/10.1016/j.pop.2022.04.002

[2] Hutchings OR, Dearing C, Jagers D, et al. Virtual health care for community management of patients with COVID-19 in Australia: Observational cohort study. J Med Internet Res. 2021; 23(3): e21064. PMid: 33687341. https://doi.org/10.2196/21064

[3] Jonnagaddala J, Godinho MA, Liaw ST. From telehealth to virtual primary care in Australia? A rapid scoping review. Int J Med Inform. 2021; 151: 104470. PMid: 34000481. https://doi.org/10.1016/j.ijmedinf.2021.104470

[4] Needham C, Wheaton N, Wong Shee A, et al. Enhancing health-care at home for older people in rural and regional Australia: A protocol for co-creation to design and implement system change. PLoS One. 2023; 18(9): e0290386. PMid: 37682945. https://doi.org/10.1371/journal.pone.0290386

[5] Mahmoud MA, Daboos M, Gouda S, et al. Telemedicine (virtual clinic) effectively delivers the required healthcare service for pediatric ambulatory surgical patients during the current era of COVID-19 pandemic: A mixed descriptive study. J Pediatr Surg. 2022; 57(4): 630-636. PMid: 34953564. https://doi.org/10.1016/j.jpedsurg.2021.11.018

[6] Stewart J, Lu J, Gahungu N, et al. Western Australian medical students’ attitudes towards artificial intelligence in healthcare. PLoS One. 2023; 18(8): e0290642. PMid: 37651380. https://doi.org/10.1371/journal.pone.0290642

[7] Yang PF, Errington BR, Bartyn J, et al. Management of COVID-19 in the community using virtual care: An Australian perspective. J Telemed Telecare. October 01, 2024 [Ahead of print]. PMid: 39523603. https://doi.org/10.1177/1357633X241292236

[8] Gellert GA, Kabat-Karabon A, Gellert GL, et al. The potential of virtual triage AI to improve early detection, care acuity alignment, and emergent care referral of life-threatening conditions. Front Public Health. 2024; 12: 1362246. PMid: 38807993. https://doi.org/10.3389/fpubh.2024.1362246

[9] Cotte F, Mueller T, Gilbert S, et al. Safety of triage self-assessment using a symptom assessment app for walk-in patients in the emergency care setting: Observational prospective cross-sectional study. JMIR Mhealth Uhealth. 2022; 10(3): e32340. PMid: 35343909. https://doi.org/10.2196/32340

[10] Gellert GA, Garber L, Kabat-Karabon A, et al. Using AI-based virtual triage to improve acuity-level alignment of patient care seeking in an ambulatory care setting. Int J Hlthcare. 2024; 10(1): 41-50. https://doi.org/10.5430/ijh.v10n1p41

[11] Morse KE, Ostberg NP, Jones VG, et al. Use characteristics and triage acuity of a digital symptom checker in a large integrated health system: Population-based descriptive study. J Med Internet Res. 2020; 22(11): e20549. PMid: 33170799. https://doi.org/10.2196/20549

[12] Gellert GA, Galvão P, Gomes SM, et al. Impact of integrated virtual and live nurse triage on patient-member care seeking and health plan efficiency. Telemed Rep. 2024; 5(1): 330-338. https://doi.org/10.1089/tmr.2024.0054

[13] Miller S, Gilbert S, Virani V, et al. Patients’ utilization and perception of an artificial intelligence-based symptom assessment and advice technology in a British primary care waiting room: Exploratory pilot study. JMIR Hum Factors. 2020; 7(3): e19713. PMid: 32540836. https://doi.org/10.2196/19713

[14] Australian Prudential Regulation Authority. Quarterly private health insurance membership and benefits summary. December 2024. Avaialble from: https://www.apra.gov.au/quarterly-private-health-insurance-statistics

[15] Gellert GA, Kuszczy´nski K, Marcjasz N, et al. A comparative performance analysis of live clinical triage using rules-based protocols versus AI-based automated virtual triage. J Hospital Admin. 2023; 13(1): 8-15. https://doi.org/10.5430/jha.v13n1p8

[16] Berry AC, Cash BD, Wang B, et al. Online symptom checker diagnostic and triage accuracy for HIV and hepatitis C. Epidemiol Infect. 2019; 147: e104. PMid: 30869052. https://doi.org/10.1017/S0950268819000268

[17] Gilbert S, Mehl A, Baluch A, et al. How accurate are digital symptom assessment apps for suggesting conditions and urgency advice? A clinical vignettes comparison to GPs. BMJ Open. 2020; 10(12): e040269. https://doi.org/10.1136/bmjopen-2020-040269

[18] Hill MG, Sim M, Mills B. The quality of diagnosis and triage advice provided by free online symptom checkers and apps in Australia. Med J Aust. 2020; 212(11): 514-519. https://doi.org/10.5694/mja2.50600 PMid: 32391611.

[19] Fladt J, Meier N, Thilemann S, et al. Reasons for prehospital delay in acute ischemic stroke. J Am Heart Assoc. 2019; 8: e013101. https://doi.org/10.1161/JAHA.119.013101 PMid: 31576773.

[20] Taghaddosi M, Dianati M, Fath Gharib Bidgoli J, et al. Delay and its related factors in seeking treatment in patients with acute myocardial infarction. ARYA Atherosclerosis. 2010; 6(1): 35-41. PMid: 22577411.

[21] Mansella G, Keil C, Nickel CH, et al. Delayed diagnosis in pulmonary embolism: frequency, patient characteristics, and outcome. Respiration. 2020; 99(7): 589-597. PMid: 32694258. https://doi.org/10.1159/000508396

[22] Daniel P, Rodrigo C, McKeever TM, et al. Time to first antibiotic and mortality in adults hospitalised with community-acquired pneumonia: A matched-propensity analysis. Thorax. 2016; 71(6): 568-570. PMid: 26559161. https://doi.org/10.1136/thoraxjnl-2015-207513