Summary – English

Challenges

Medical telephone triage is a demanding task for telephone operators today.

Telephone triage at emergency medical communication centres are increasingly relying on assessments to direct patients to the appropriate level of care. The telephone operators who perform these assessments carry a great responsibility, as the accuracy of their responses can have a significant impact on patients’ health outcomes. To make informed assessments, telephone operators must gather correct and relevant information from callers, which requires effective communication skills.

Unfortunately, operators today are often burdened by multiple tools that distract them from their conversations with callers, leading to poor workflow and reduced call quality. While decision-support tools were intended to enhance the quality of assessments, they often steer conversations into predefined tracks and negatively affect the flow of communication.

Our Solution

Telephone operators and artificial intelligence are collaborating to assist callers.

In RE-AIMED, we will explore how the use of artificial intelligence can improve the operator’s workflow and communication between the caller and the operator. Artificial intelligence can use information about and from the conversation to provide the operator with tailored questions, allowing the conversation to develop naturally. By selecting questions and answers, the operator can document the conversation while also receiving assistance in recognizing medical patterns. Most assessments do not concern serious illness, but rare and serious cases must be detected. Therefore, key challenges in the project are how to prevent the artificial intelligence from misinterpreting or overlooking rare cases, and how to ensure a user design that provides sufficient information and guidance without disturbing the operator’s concentration and conversation with the caller.

The Future Service

RE-AIMED opens doors for the future of medical telephone assessments.

The project will create large, standardized, and detail-coded datasets that describe medical assessment conversations. This provides an opportunity for further research on telephone assessments, medical decision-making, communication, and reduction of misinterpretations in machine learning.