English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In an emergency room (ER) setting, stroke triage or screening is a commonchallenge. A quick CT is usually done instead of MRI due to MRI's slowthroughput and high cost. Clinical tests are commonly referred to during theprocess, but the misdiagnosis rate remains high. We propose a novel multimodaldeep learning framework, DeepStroke, to achieve computer-aided stroke presenceassessment by recognizing patterns of minor facial muscles incoordination andspeech inability for patients with suspicion of stroke in an acute setting. Ourproposed DeepStroke takes one-minute facial video data and audio data readilyavailable during stroke triage for local facial paralysis detection and globalspeech disorder analysis. Transfer learning was adopted to reduceface-attribute biases and improve generalizability. We leverage a multi-modallateral fusion to combine the low- and high-level features and provide mutualregularization for joint training. Novel adversarial training is introduced toobtain identity-free and stroke-discriminative features. Experiments on ourvideo-audio dataset with actual ER patients show that DeepStroke outperformsstate-of-the-art models and achieves better performance than both a triage teamand ER doctors, attaining a 10.94% higher sensitivity and maintaining 7.37%higher accuracy than traditional stroke triage when specificity is aligned.Meanwhile, each assessment can be completed in less than six minutes,demonstrating the framework's great potential for clinical translation.

DeepStroke: An Efficient Stroke Screening Framework for Emergency Rooms with Multimodal Adversarial Deep Learning