{"ok":true,"nota":{"id":"528ba55147b25020","slug":"una-ia-que-analiza-video-y-audio-detecto-signos-de-acv-tan-bien-como-l-528ba5","titulo":"Una IA que analiza video y audio detectó signos de ACV tan bien como los equipos de emergencia","resumen":"Se comparó un sistema de inteligencia artificial que analiza grabaciones de pacientes con sospecha de ACV contra el criterio de paramédicos. Los resultados se evaluaron frente a un consenso de expertos en neurología.","fuente":"medrxiv","fuenteNombre":"medRxiv · preprints","color":"#1f7a4d","autor":"Javault, C., Vargas Gonzalez, E., Pibre, L., Yriarte, F., Thouvenot, E.","url":"https://www.medrxiv.org/content/10.64898/2026.10.16.26365784v1?rss=1","imagen":"/hoy/portada/528ba55147b25020","tema":"salud","subtemas":["acv","inteligencia artificial","emergencias","paramédicos","diagnóstico"],"entidades":["APOLLAI","medRxiv"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-22T00:00:00.000Z","indexTs":"2026-10-22T16:38:44.280Z","hash":"8ea215e334fd9bdf3b90362d3ce66cf7ed709c4099b71ae9f2a419329712155b","tsa":{"time":"Oct 22 16:39:43 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"motor","registro":"hallazgo","porQueImporta":"Muchos ACV no se reconocen antes de llegar al hospital, y cada minuto cuenta para evitar secuelas. Si una herramienta así ayuda a detectar a tiempo, una ambulancia podría llegar con el diagnóstico más cerca de la realidad. Para cualquier familia, eso puede significar la diferencia entre una recuperación parcial y un daño permanente. Todavía falta ver cómo funciona en el día a día de la atención real.","quienFirma":"medRxiv (preprint de investigación médica)","confianza":"preprint","consulta":{"pregunta":"¿Confiarías en una IA para que evalúe a un familiar con síntomas de ACV?"}},"sello":{"hash":"8ea215e334fd9bdf3b90362d3ce66cf7ed709c4099b71ae9f2a419329712155b","sello":"e040e654a2747dd15a664e0790e3e073773385468fdb04dc43ada6b94b6b6557","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6575204,"aleatorio":"ac0f4a6ce509202540c9641abb3a70f7f06eeb36f68a34e1bc3e430369a775da","tiempo":"2026-10-22T16:39:00.000Z"},"nist":{"cadena":2,"pulso":1994801,"salida":"123765DCC46130497358D1E6393BF76FC82D205E2F260DEF171C4887B733C1209F31A193DDD877AB50C2E9F79D0A125A26712AD900F817275AC0E40E5C1C39BC","tiempo":"2026-10-22T16:38:00.000Z"},"noAntes":"2026-10-22T16:39:00.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 22 16:39:43 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"APOLLAI, a multimodal AI system, versus EMS personnel for prehospital detection of stroke-related deficits","descripcion":"Background and Purpose: Prehospital 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. Methods: In this prospective study, video recordings of 295 patients with suspected stroke (mean age, 70.3 {+/-}13.3 years) were","pubDate":"2026-10-22","url":"https://www.medrxiv.org/content/10.64898/2026.10.16.26365784v1?rss=1"},"indexado":"2026-10-22T16:38:44.280Z"}}