Arrow
use cases

AutoTriage: Optimizing Healthcare Triage with AI

Addressing challenges in triage services with AI by automating tasks and reducing waiting times in waiting lists and administrative burden.

Problem

Triage services are a critical juncture in healthcare delivery, where the prompt and accurate evaluation of patient needs is vital. Despite its importance, current triage practices are often marked by inefficiency, contributing to unnecessary emergency department visits that account for up to two-thirds of all cases. These misjudged triage situations can lead to inordinate delays and the use of medical resources on low-value care, substantially impacting healthcare expenditure with an excess of $32 billion spent nationally (1)(2). Complications in the triage process, highlighted by the extensive number of potential outcomes—over 120 permutations—exacerbate the difficulty of implementing effective and precise assessment systems in medical institutions (3). With emergency departments experiencing increased wait times, some patients endure over 12-hour delays from admission to a treatment decision (4), signaling a pressing need for improved triage protocols (5).

Why it matters

  • Triage services are crucial for evaluating patient needs, but current practices are inefficient, leading to unnecessary emergency department visits.
  • Ineffective triage contributes to delays, misuses medical resources, and costs over $32 billion nationally.
  • With over 120 potential outcomes and wait times exceeding 12 hours for some patients, there is a pressing need for improved triage protocols.

Solution

To streamline the triage process and help healthcare providers quickly assess patients' symptoms and urgency, a digital health assistant, "TriagePro AI", was developed for use in healthcare environments. high traffic.

Discover more and interact with our AI!

Datasources

The protocols and recommendations of the digital assistant are based on the "Manual for the implementation of a triage system in emergency rooms" of the Pan American Health Organization (6) and Moreno's comprehensive triage guidelines (7). By leveraging these established resources, the tool aligns with recognized classification procedures and assists healthcare providers in decision making.

Citations

  1. Delshad S, Dontaraju VS, Chengat V. Artificial Intelligence-Based Application Provides Accurate Medical Triage Advice When Compared to Consensus Decisions of Healthcare Providers. Cureus. 2021 Aug 6;13(8):e16956. doi: 10.7759/cureus.16956. PMID: 34405077; PMCID: PMC8352839.
  2. Dugas AF, Kirsch TD, Toerper M, Korley F, Yenokyan G, France D, Hager D, Levin S. An Electronic Emergency Triage System to Improve Patient Distribution by Critical Outcomes. J Emerg Med. 2016 Jun;50(6):910-8. doi: 10.1016/j.jemermed.2016.02.026. Epub 2016 Apr 25. Erratum in: J Emerg Med. 2016 Aug;51(2):224. PMID: 27133736.
  3. Raita Y, Goto T, Faridi MK, Brown DFM, Camargo CA Jr, Hasegawa K. Emergency department triage prediction of clinical outcomes using machine learning models. Crit Care. 2019 Feb 22;23(1):64. doi: 10.1186/s13054-019-2351-7. PMID: 30795786; PMCID: PMC6387562.
  4. Using intelligent automation to improve the triage and referral management pathway. (n.d.). NHS Transformation Directorate. https://transform.england.nhs.uk/key-tools-and-info/digital-playbooks/gastroenterology-digital-playbook/using-intelligent-automation-to-improve-the-triage-and-referral-management-pathway/
  5. Tool Developed to Assist with Triage in the Emergency Department. (2022, November 3). Johns Hopkins Medicine. https://www.hopkinsmedicine.org/news/articles/2022/11/tool-developed-to-assist-with-triage-in-the-emergency-department
  6. Pan American Health Organization. (2010). Manual for the Implementation of a Triage System in Emergency Rooms. Retrieved from https://iris.paho.org/handle/10665.2/3524
  7. Moreno, M. (n.d.). GUR-MN_01_Manual_Triage. Retrieved from https://es.scribd.com/document/518528563/GUR-MN-01-Manual-Triage

Problem

Triage services are a critical juncture in healthcare delivery, where the prompt and accurate evaluation of patient needs is vital. Despite its importance, current triage practices are often marked by inefficiency, contributing to unnecessary emergency department visits that account for up to two-thirds of all cases. These misjudged triage situations can lead to inordinate delays and the use of medical resources on low-value care, substantially impacting healthcare expenditure with an excess of $32 billion spent nationally (1)(2). Complications in the triage process, highlighted by the extensive number of potential outcomes—over 120 permutations—exacerbate the difficulty of implementing effective and precise assessment systems in medical institutions (3). With emergency departments experiencing increased wait times, some patients endure over 12-hour delays from admission to a treatment decision (4), signaling a pressing need for improved triage protocols (5).

Problem Size

  • Triage services are crucial for evaluating patient needs, but current practices are inefficient, leading to unnecessary emergency department visits.
  • Ineffective triage contributes to delays, misuses medical resources, and costs over $32 billion nationally.
  • With over 120 potential outcomes and wait times exceeding 12 hours for some patients, there is a pressing need for improved triage protocols.

Solution

To streamline the triage process and help healthcare providers quickly assess patients' symptoms and urgency, a digital health assistant, "TriagePro AI", was developed for use in healthcare environments. high traffic.

Opportunity Cost


Impact


Data Sources

The protocols and recommendations of the digital assistant are based on the "Manual for the implementation of a triage system in emergency rooms" of the Pan American Health Organization (6) and Moreno's comprehensive triage guidelines (7). By leveraging these established resources, the tool aligns with recognized classification procedures and assists healthcare providers in decision making.


References

  1. Delshad S, Dontaraju VS, Chengat V. Artificial Intelligence-Based Application Provides Accurate Medical Triage Advice When Compared to Consensus Decisions of Healthcare Providers. Cureus. 2021 Aug 6;13(8):e16956. doi: 10.7759/cureus.16956. PMID: 34405077; PMCID: PMC8352839.
  2. Dugas AF, Kirsch TD, Toerper M, Korley F, Yenokyan G, France D, Hager D, Levin S. An Electronic Emergency Triage System to Improve Patient Distribution by Critical Outcomes. J Emerg Med. 2016 Jun;50(6):910-8. doi: 10.1016/j.jemermed.2016.02.026. Epub 2016 Apr 25. Erratum in: J Emerg Med. 2016 Aug;51(2):224. PMID: 27133736.
  3. Raita Y, Goto T, Faridi MK, Brown DFM, Camargo CA Jr, Hasegawa K. Emergency department triage prediction of clinical outcomes using machine learning models. Crit Care. 2019 Feb 22;23(1):64. doi: 10.1186/s13054-019-2351-7. PMID: 30795786; PMCID: PMC6387562.
  4. Using intelligent automation to improve the triage and referral management pathway. (n.d.). NHS Transformation Directorate. https://transform.england.nhs.uk/key-tools-and-info/digital-playbooks/gastroenterology-digital-playbook/using-intelligent-automation-to-improve-the-triage-and-referral-management-pathway/
  5. Tool Developed to Assist with Triage in the Emergency Department. (2022, November 3). Johns Hopkins Medicine. https://www.hopkinsmedicine.org/news/articles/2022/11/tool-developed-to-assist-with-triage-in-the-emergency-department
  6. Pan American Health Organization. (2010). Manual for the Implementation of a Triage System in Emergency Rooms. Retrieved from https://iris.paho.org/handle/10665.2/3524
  7. Moreno, M. (n.d.). GUR-MN_01_Manual_Triage. Retrieved from https://es.scribd.com/document/518528563/GUR-MN-01-Manual-Triage

Book a Free Consultation

Trusted by the world's top healthcare institutions