A retrospective study on machine learning-assisted stroke recognition for medical helpline calls

Jonathan Wenstrup, Jakob Drachmann Havtorn, Lasse Borgholt, Stig Nikolaj Blomberg, Lars Maaloe, Michael R Sayre, Hanne Christensen, Christina Kruuse, Helle Collatz Christensen*

*Corresponding author for this work

Abstract

Advanced stroke treatment is time-dependent and, therefore, relies on recognition by call-takers at prehospital telehealth services to ensure fast hospitalisation. This study aims to develop and assess the potential of machine learning in improving prehospital stroke recognition during medical helpline calls. We used calls from 1 January 2015 to 31 December 2020 in Copenhagen to develop a machine learning-based classification pipeline. Calls from 2021 are used for testing. Calls are first transcribed using an automatic speech recognition model and then categorised as stroke or non-stroke using a text classification model. Call-takers achieve a sensitivity of 52.7% (95% confidence interval 49.2-56.4%) with a positive predictive value (PPV) of 17.1% (15.5-18.6%). The machine learning framework performs significantly better (p < 0.0001) with a sensitivity of 63.0% (62.0-64.1%) and a PPV of 24.9% (24.3-25.5%). Thus, a machine learning framework for recognising stroke in prehospital medical helpline calls may become a supportive tool for call-takers, aiding in early and accurate stroke recognition.

Original languageEnglish
Article number235
JournalNPJ digital medicine
Volume6
Issue number1
Pages (from-to)235
ISSN2398-6352
DOIs
Publication statusPublished - 19 Dec 2023

Fingerprint

Dive into the research topics of 'A retrospective study on machine learning-assisted stroke recognition for medical helpline calls'. Together they form a unique fingerprint.

Cite this