Oral Presentation Asia Pacific Stroke Conference 2024

The feasibility of an automated artificial intelligence system in detecting signs of large vessel occlusion stroke (107372)

Helen M Badge 1 2 3 4 , Pui Lok Annette Fung 3 , Christopher Blair 2 3 5 , Dennis Cordato 2 3 5 , Megan Trebilcock 1 , Suraj Narayanan Sasikumar 2 4 , Rumbi Teramayi 2 3 5 , Lauren Christie 1 6 , Paul M Middleton 2 3 4 7 , Mark Parsons 2 3 5
  1. School of Allied Health, Australian Catholic University, North Sydney, NSW, Australia
  2. Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia
  3. University of New South Wales, Liverpool, NEW SOUTH WALES, Australia
  4. South West Emergency Research Institute, Liverpool, NSW, Australia
  5. Liverpool Hospital, Neurology & Neurophysiology Department, South Western Sydney Local Health District, Liverpool, NSW, Australia
  6. Allied Health, St Vincent's Health Network , Darlinghurst, NSW, Australia
  7. Emergency Department, South Western Sydney Local Health District, Liverpool, NSW, Australia

Background

Large vessel occlusion (LVO) stroke comprises 30-37% of all strokes and contributes disproportionately to stroke morbidity (61.6%) and mortality (95.6%). Aphasia is experienced in c.30% of LVO stroke and has a high sensitivity for LVO stroke prediction (91%). Emerging studies have applied artificial intelligence (AI) to predict LVO stroke and address challenges in accurate pre-hospital triage. Early detection of LVO stroke is critical to ensure access to time-critical interventions.

Aim: To evaluate the feasibility of using AI to differentiate people with and without stroke from speech.

Methods

This prospective observational study included consenting adults with a recent diagnosis of acute LVO stroke and controls without any neurological conditions. Ethics approval was obtained (South Western Sydney Local Health District Human Research Ethics Committee, 2022/ETH00483).

Data included demographic and clinical information and a short video taken on an iPhone while administering National Institutes of Health Stroke Scale (NIHSS) “Best Language” and “Dysarthria” questions. Supervised and unsupervised machine learning was used to detect whether audio (speech) data could differentiate stroke.

Results

Participants included 10 with LVO stroke (median age=71.6 (IQR=52-78)) and 10 controls. AI models could differentiate stroke from non-stroke: GPT-4 achieved a sensitivity and specificity of 0.6 and 1.0 (Task 1), and the wav2vec2 models achieved an AUC of 0.89 and 0.97 (Tasks 2-4). Several words and phrases demonstrated greater differentiation (“cactus,” “mama,” “huckleberry”, “near the table in the dining room”).

Conclusion 

Using multiple AI algorithms to predict LVO stroke based on language and acoustic features is feasible.

  1. Australian Institute of Health and Welfare. Heart, stroke and vascular disease: Australian facts. https://www.aihw.gov.au/reports/heart-stroke-vascular-diseases/hsvd-facts/contents/summary-of-coronary-heart-disease-and-stroke/stroke (2023).
  2. Malhotra, K., Gornbein, J. & Saver, J.L. Ischemic strokes due to large-vessel occlusions contribute disproportionately to stroke-related dependence and death: A review. Frontiers in Neurology 8, 651 (2017).
  3. Antipova, D., Eadie, L., Macaden, A. & Wilson, P. Diagnostic accuracy of clinical tools for assessment of acute stroke: A systematic review. BMC Emergency Medicine 19, 49 (2019).
  4. Kim, D., et al. A data-driven artificial intelligence model for remote triage in the prehospital environment. PLOS One 13, e0206006 (2018).
  5. Rodrigues, G., et al. Automated large artery occlusion detection in stroke: A single-center validation study of an artificial intelligence algorithm. Cerebrovascular Diseases 51, 259-264 (2022).
  6. Cimflova, P., et al. Validation of a machine learning software tool for automated large vessel occlusion detection in patients with suspected acute stroke. Neuroradiology 64, 2245-2255 (2022).
  7. Getman, Y., et al. Wav2vec2-based speech rating system for children with speech sound disorder. in Interspeech (2022).
  8. Lee, J.H., Lee, G.W., Bong, G., Yoo, H.J. & Kim, H.K. End-to-end model-based detection of infants with autism spectrum disorder using a pretrained model. Sensors (Basel) 23(2022).