Reliability of Instant Messaging-Based Evaluation of Brain Imaging in Acute Stroke.

ABSTRACT

BACKGROUND: The use of instant messenger applications among physicians has become common in acute stroke management, especially in developing countries. Photos or video sequences of brain computed tomography (CT) scans are being sent to receive real-time support in assessing radiological findings. We analyzed whether instant messaging-based evaluation is precise enough to extract relevant information from the images. METHODS: In this prospective study, anonymized videos and photos of CT and CT angiography scans of patients with symptoms of acute stroke were recorded from the diagnostic monitor using a smartphone. Two neurologists and 2 neuroradiologists performed evaluation of the images using WhatsApp. The gold standard was set by 2 experienced neuroradiologists who evaluated the CT images with their full radiological equipment. Statistical analysis included the calculation of Cohen kappa (κ). RESULTS: A total of 104 brain images (derived from 81 patients) were included. All 4 raters performed with a perfect (κ=1) interobserver reliability in diagnosing intracerebral hemorrhage. For subarachnoid hemorrhage, interobserver reliability was slightly lower (raters 1, 2, and 3, κ=1; rater 4, κ=0.88). For diagnosing stroke mimics, interobserver reliability showed considerable variations (κ between 0.32 and 1). Alberta Stroke Program Early CT Score differences overall were comparable between raters and did not exceed 3 to 4 points without noticeable outliers. All raters performed with a moderate-to-substantial interobserver reliability for detecting large vessel occlusions (κ=0.48 in rater 1, κ=0.62 in rater 2, and κ=0.63 in raters 3 and 4). CONCLUSIONS: Stroke neurologists can reliably extract information on intracerebral hemorrhage from CT images recorded via smartphone and sent through instant messaging tools. Remote diagnosis of early infarct signs and stroke mimics was less reliable. We developed a standard for the acquisition of images, taking data protection into account.