ESOC 2023 | Limitations of AI in identifying stroke in an emergency telephone setting

Jonathan Wenstrup, MD PhD Candidate, Herlev Hospital, Herlev, Denmark, discusses the current limitations of deep learning and artificial intelligence (AI) technology in the identification of stroke via emergency telephone calls. In his recent study assessing the value of a machine learning framework for stroke recognition during medical emergency calls, Dr Wenstrup and his team found that the AI tool was better at recognising stroke than the healthcare telecommunicators, with a higher positive predictive value and a higher sensitivity. In this video, he comments on the limitations of the tool, elaborating on the lack of live data this technology has been exposed to, the lack of knowledge in how useful a triage telephone operator may find this, and fact that the AI is only as good as the data it is trained on. Regardless of this, Dr Wenstrup believes this is a useful tool in a clinical setting and hopes for its future implementation in aiding triage telephone operators. This interview took place during the European Stroke Organisation Conference (ESOC) in Munich, Germany.

These works are owned by Magdalen Medical Publishing (MMP) and are protected by copyright laws and treaties around the world. All rights are reserved.