Clinical Development of a Tool for Optimized Self- and Hetero-diagnosis of Stroke Using Artificial Intelligence: Stage1- Collection of Video-clinical Data in a Pragmatic Situation.
The study authors aim to form a collection of video-clinical data in a pragmatic situation to enable the development of relevant AI algorithms (for both hetero- and self-diagnosis modes). The aim is to optimize management through early diagnosis (self- and hetero-diagnosis) and thus to reduce sequelae disability. The study authors hypothesize that some stroke patients will be able to successfully perform a self-test consisting of a few exercises dictated by an application on a smartphone or tablet and recorded on video.
• Patients treated in the emergency department or hospitalized in the NICU at the CHU de Nîmes for suspected stroke or transient ischemic attack in the acute phase (\<72h), with or without motor deficit
• Patient to be seen again in consultation within 4 months
• Patient has given free and informed consent and signed the consent form. If the patient is not in a position to give consent, it must be obtained, prior to filming the first video, from the designated trusted support person or relatives present. In this case, data will not be used until the patient is able to sign the consent (CNIL).
• Patient affiliated or beneficiary of a health insurance scheme