{"ok":true,"nota":{"id":"ed5aac31afbc69ab","slug":"un-sistema-de-inteligencia-artificial-ubica-el-foco-de-las-convulsione-ed5aac","titulo":"Un sistema de inteligencia artificial ubica el foco de las convulsiones usando electroencefalogramas comunes","resumen":"Desarrollaron un modelo de aprendizaje profundo que analiza electroencefalogramas de rutina para localizar la zona del cerebro donde se originan las crisis en epilepsia resistente. Hoy esa localización suele requerir estudios invasivos.","fuente":"biorxiv","fuenteNombre":"bioRxiv · preprints","color":"#be2628","autor":"Shi, S.","url":"https://www.biorxiv.org/content/10.64898/2026.10.16.759501v1?rss=1","imagen":"/hoy/portada/ed5aac31afbc69ab","tema":"salud","subtemas":["epilepsia","electroencefalograma","inteligencia artificial","cirugía cerebral","diagnóstico médico"],"entidades":["epilepsia focal farmacorresistente"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-22T00:00:00.000Z","indexTs":"2026-10-23T00:43:59.943Z","hash":"fac19b84b5e8c8f2a8c5343853f5b4b2dbac41b5962a30e6a37e27532a5e95ff","tsa":{"time":"Oct 23 00:44:44 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"Para muchas personas con epilepsia que no responde a los medicamentos, la cirugía es una opción, pero antes hay que ubicar exactamente el foco, y eso suele exigir estudios invasivos costosos y riesgosos. Si una herramienta puede hacerlo con un electroencefalograma convencional, el diagnóstico podría llegar a más pacientes y a más centros. Para alguien de acá, implica que la tecnología podría reducir esperas y procedimientos, aunque todavía no está validada clínicamente y el trabajo aún no pasó por revisión por pares.","quienFirma":"Autores no identificados en el texto proporcionado","confianza":"preprint","consulta":null},"sello":{"hash":"fac19b84b5e8c8f2a8c5343853f5b4b2dbac41b5962a30e6a37e27532a5e95ff","sello":"609a87c60967851a9be416e451fc09cb3f1dc676abbb6910a10518151692edd0","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6576175,"aleatorio":"daeeb50ec9f7bca881613780dde9f04ee72a757e827db72aa67649836704893c","tiempo":"2026-10-23T00:44:30.000Z"},"nist":{"cadena":2,"pulso":1995287,"salida":"785B78E3E11077EB44F5EAC072C9D26D0DE3089D9E6EED05010A6176EC3F0436B59E7FA4CE1BBF17EA14BD9B8FE300D2C49C4FE98128B2B1F342A830C3D7920D","tiempo":"2026-10-23T00:44:00.000Z"},"noAntes":"2026-10-23T00:44:30.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 23 00:44:44 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Localising the Seizure Onset Zone from Routine Interictal and Ictal Scalp EEG Via a Factorised Spatiotemporal Ensemble Deep Learning Framework","descripcion":"Background: Drug-resistant focal epilepsy requires precise localisation of the epileptogenic zone (EZ) for surgical resection. Current practice depends on invasive recordings or spontaneous seizure capture, a costly and risky bottleneck. Interictal scalp EEG can exhibit localising features like spikes, but scalp EEG suffers from volume conduction (the smearing of brain signals across multiple electrodes) and low signal-to-noise ratio (SNR), which obscure subtle spatial dynamics. Neurophysiologist review of long, often multi-day recordings is time-consuming and expertise-dependent, and while computational methods exist, they tend to rely heavily on human-designed features. Deep learning for E","pubDate":"2026-10-22","url":"https://www.biorxiv.org/content/10.64898/2026.10.16.759501v1?rss=1"},"indexado":"2026-10-23T00:43:59.943Z"}}