APOLLAI, a multimodal AI system, versus EMS personnel for prehospital detection of stroke-related deficits
- 1AI-Stroke
Abstract
Background and PurposePrehospital stroke recognition remains suboptimal, with nearly one-third of strokes unidentified before hospital arrival, and neurological assessment being inherently subjective, with substantial interobserver variability even among certified clinicians. APOLLAI, a multimodal artificial intelligence system, was developed to detect stroke-related neurological deficits from video and audio recordings. We compared the diagnostic performance of APOLLAI and emergency medical services (EMS) personnel against an expert consensus reference standard.
MethodsIn this prospective study, video recordings of 295 patients with suspected stroke (mean age, 70.3{+/-}13.3 years) were obtained at Nimes University Hospital (August 2023-July 2025). Five National Institutes of Health Stroke Scale items (best gaze, facial palsy, motor arm, aphasia, dysarthria) were independently annotated by seven certified stroke neurologists, combined into consensus labels using the Dawid-Skene algorithm, and separately assessed by EMS personnel (mean of 15 raters per patient). APOLLAI, a multimodal machine-learning framework that combines computer vision, audio-based deep learning, and a final support vector machine (SVM) fusion classifier, was evaluated against EMS using sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC).
ResultsInterrater agreement among the seven neurologists was moderate overall (mean {kappa}=0.541; range, 0.367-0.732), indicating an intrinsic difficulty of neurological assessment. APOLLAI showed higher sensitivity than EMS for all five neurological tasks and for the global assessment (78.5% versus 59.4%), with broadly comparable specificity (87.0% versus 85.9% for the global assessment). AUC values ranged from 0.839 (facial palsy) to 0.966 (best gaze), with a global AUC of 0.882.
ConclusionsAPOLLAI demonstrated higher sensitivity than EMS personnel for detecting stroke-related neurological deficits, with preserved specificity. These findings support its potential as a standardized, scalable adjunct to prehospital stroke recognition, warranting prospective validation under real-world EMS conditions.
Related
- Choriocapillaris Flow Deficits and Outer Retinal Biomarkers in Early Macular Telangiectasia Type 2: A Multimodal Imaging Study
- Potential Locations for Noninvasive Brain Stimulation in Treating Poststroke Deficits: Exploration From Multimodal Neuroimaging
- Prehospital Detection of Acute Pulmonary Embolism and Its Association with Clinical Outcomes: A Retrospective Cohort Study
- Prehospital Point-of-Care GFAP for Detection of Intracranial Hemorrhage in Acute Nontraumatic Coma
- Multimodal Detection of a Minute Uterine Cornual Lesion in Cervical Clear Cell Carcinoma
BibTeX
@misc{javault2026apollai,
title = {{APOLLAI, a multimodal AI system, versus EMS personnel for prehospital detection of stroke-related deficits}},
author = {C. Javault and E. Vargas Gonzalez and L. Pibre and F. Yriarte and E. Thouvenot},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.16.26365784},
url = {https://www.medrxiv.org/content/10.64898/2026.10.16.26365784v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - APOLLAI, a multimodal AI system, versus EMS personnel for prehospital detection of stroke-related deficits
AU - C. Javault
AU - E. Vargas Gonzalez
AU - L. Pibre
AU - F. Yriarte
AU - E. Thouvenot
PY - 2026
DA - 2026/10/16
PB - medRxiv
DO - 10.64898/2026.10.16.26365784
UR - https://www.medrxiv.org/content/10.64898/2026.10.16.26365784v1
AB - Background and PurposePrehospital stroke recognition remains suboptimal, with nearly one-third of strokes unidentified before hospital arrival, and neurological assessment being inherently subjective, with substantial interobserver variability even among certified clinicians. APOLLAI, a multimodal artificial intelligence system, was developed to detect stroke-related neurological deficits from video and audio recordings. We compared the diagnostic performance of APOLLAI and emergency medical services (EMS) personnel against an expert consensus reference standard. MethodsIn this prospective study, video recordings of 295 patients with suspected stroke (mean age, 70.3{+/-}13.3 years) were obtained at Nimes University Hospital (August 2023-July 2025). Five National Institutes of Health Stroke Scale items (best gaze, facial palsy, motor arm, aphasia, dysarthria) were independently annotated by seven certified stroke neurologists, combined into consensus labels using the Dawid-Skene algorithm, and separately assessed by EMS personnel (mean of 15 raters per patient). APOLLAI, a multimodal machine-learning framework that combines computer vision, audio-based deep learning, and a final support vector machine (SVM) fusion classifier, was evaluated against EMS using sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). ResultsInterrater agreement among the seven neurologists was moderate overall (mean {kappa}=0.541; range, 0.367-0.732), indicating an intrinsic difficulty of neurological assessment. APOLLAI showed higher sensitivity than EMS for all five neurological tasks and for the global assessment (78.5% versus 59.4%), with broadly comparable specificity (87.0% versus 85.9% for the global assessment). AUC values ranged from 0.839 (facial palsy) to 0.966 (best gaze), with a global AUC of 0.882. ConclusionsAPOLLAI demonstrated higher sensitivity than EMS personnel for detecting stroke-related neurological deficits, with preserved specificity. These findings support its potential as a standardized, scalable adjunct to prehospital stroke recognition, warranting prospective validation under real-world EMS conditions.
ER -