Door to Puncture in Large Vessel Occlusions Pre‐ and Postimplementation of an Automated Image Interpretation and Communication Platform: A Single Center Study

 No clue.

Door to Puncture in Large Vessel Occlusions Pre‐ and Postimplementation of an Automated Image Interpretation and Communication Platform: A Single Center Study

Emma Frost,

Mary Penckofer,

Linda Zhang,

Kenyon Sprankle,

Nicholas Vigilante,

Omnea Elgendy,

Jiyoun Ackerman,

Abyson Kalladanthyil,

Manisha Koneru,

Zixin Yi,

Jane Khalife,

Taryn Hester,

… See all authors

Originally published9 Mar 2024https://doi.org/10.1161/SVIN.123.001306Stroke: Vascular and Interventional Neurology. 2024;0:e001306

Abstract

BACKGROUND

Artificial intelligence platforms, like Viz.ai with large vessel occlusion detection, have been used for disease detection and interprovider communication. Whether this software expedites patient transfer and evaluation for treatment needs further exploration.

METHODS

A single‐center retrospective registry was queried for patients with acute large vessel occlusion of the intracranial internal carotid, middle cerebral M1 or M2 segments, or basilar artery treated in a comprehensive stroke network (8 spokes, 1 hub) for 6 months pre‐ and post‐implementation of the Viz large vessel occlusion platform (excluding a 1‐month “washout” period). Robust regression was used to summarize time from initial hospital contact to arterial puncture (primary outcome) between periods, with prespecified subgroup analyses, which were assessed using interaction terms.

RESULTS

Of the 132 patients (n = 58 preintervention), there were nonsignificantly fewer patients undergoing endovascular therapy in the postintervention period (86.2% preintervention versus 73.0% postintervention; P = 0.07). Among patients who underwent endovascular therapy (n = 50 preintervention, n = 54 postintervention), there was a nonsignificant reduction in time from first contact to arterial puncture (median 155 minute preintervention versus 116 minute postintervention; P = 0.10); however, this became significant in adjusted robust regression accounting for stroke severity, age, Alberta Stroke Program Early Computed Tomography Scale score, daytime versus nighttime and weekend versus weekday arrival, and use of perfusion imaging (β −20.9 [95% CI, −40.5 to −1.4)]. There was also a significant interaction observed for the association between spoke versus hub arrival and the Viz large vessel occlusion period, with shorter intervals observed for transferred patients (n = 32 preintervention with a median of 169 versus 142 minutes for n = 33 postintervention; P_interaction<0.01).

CONCLUSION

Implementation of the artificial intelligence platform was not associated with shorter intervals between initial hospital contact and neurointervention among all‐comers. A meaningful difference in time to treatment was observed among transferred patients. Larger data sets are needed to validate these observations.

• Download figure

Delays in arterial puncture and recanalization success of proximal large vessel occlusion (LVO) stroke are associated with significant functional disability.¹ Earlier provider awareness of an acute LVO on imaging, activation of the neurointerventional team, and sooner transfer initiation are key to reducing disability in patients with LVO planned for endovascular therapy (EVT). Viz.ai is a multimodality software platform permitting image sharing and storage, clinical information capture, and provider communication regarding acute medical management. A pivotal moment for the use of artificial intelligence (AI) in neurology was the Food and Drug Administration approval in February 2018 of the Viz.ai Contact application, an AI care coordination platform that analyzes computed tomography (CT) images for indicators associated with a stroke and then notifies medical providers of potential strokes.² Viz.ai created Viz LVO, an algorithm of the initial platform that is used to identify LVOs on CT angiography and facilitate secure messaging between health care providers.³ This platform can be particularly useful in hub‐and‐spoke models in health care, where the hub is resource rich, usually a tertiary care institution with large amounts of supplies and services, where the spokes are other campuses or locations with more limited services available.⁴ One recent stepped‐wedge cluster randomized clinical trial of 243 patients reported faster time from hospital arrival to arterial puncture following implementation of Viz LVO.⁵ However, this trial excluded patients transferred from external institutions. In this study we sought to validate the findings from Martinez‐Gutierrez et al in a single‐center, pre‐/postintervention assessment of platform implementation with further exploration of this technology across a hub‐and‐spoke network.

More at link.