{"ok":true,"nota":{"id":"58285287dc66fa3a","slug":"un-nuevo-metodo-con-eeg-distingue-mejor-a-personas-con-parkinson-de-sa-582852","titulo":"Un nuevo método con EEG distingue mejor a personas con Parkinson de sanas","resumen":"Investigadores propusieron cambiar la forma de combinar predicciones de un electroencefalograma para decidir si una persona tiene Parkinson. En lugar de promediar, usan catorce medidas de la distribución de esas predicciones. Lo evaluaron con datos de EEG.","fuente":"biorxiv","fuenteNombre":"bioRxiv · preprints","color":"#be2628","autor":"Taghipour Langrodi, P., Khodadadi, A., Rezaei, F., Anvarian, Z., Sotero, R. C., Madadi, S.","url":"https://www.biorxiv.org/content/10.64898/2026.10.13.759017v1?rss=1","imagen":"/hoy/portada/58285287dc66fa3a","tema":"salud","subtemas":["parkinson","electroencefalograma","inteligencia artificial","diagnóstico","neurología"],"entidades":[],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-20T00:00:00.000Z","indexTs":"2026-10-20T14:25:26.749Z","hash":"e81ffb4f28724d674272d33ad4c8a754d292a4c22bae8954946af52ab387686e","tsa":{"time":"Oct 20 14:27:21 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"El electroencefalograma es un estudio no invasivo y relativamente accesible, y mejorar cómo se interpreta podría ayudar a detectar el Parkinson con más precisión en el futuro. Hoy sigue siendo una investigación con datos limitados y que todavía no se usa para diagnosticar a nadie. Para un paciente o su familia en Argentina, el avance es una herramienta en desarrollo, no un diagnóstico disponible.","quienFirma":"Preprint en bioRxiv (institución no indicada en la fuente)","confianza":"preprint","consulta":null},"sello":{"hash":"e81ffb4f28724d674272d33ad4c8a754d292a4c22bae8954946af52ab387686e","sello":"c81a697e0eee59cb3702c5e840f7321c4f9d907a9ba89df964abc5a8a2536f64","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6569180,"aleatorio":"0c3adb1760f2c85b375daddd44899109817540f5d27c13ddee553bae30c5427a","tiempo":"2026-10-20T14:27:00.000Z"},"nist":{"cadena":2,"pulso":1991795,"salida":"D4D2B04303A5B41F484C86DB438B8E0C95FCC89E084BE5BBBB2E330616597BBCB3A1560995DA52DFF63FF8DDDCA72180409DCFF4097FD9B157B5F2A5FC57D2A5","tiempo":"2026-10-20T14:26:00.000Z"},"noAntes":"2026-10-20T14:27:00.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 20 14:27:21 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Beyond Mean Pooling: Statistical Meta-Aggregation for Subject-Level EEG Classification in Parkinson's Disease","descripcion":"Electroencephalography (EEG) provides a non-invasive, temporally precise tool for studying neural alterations associated with Parkinson's disease (PD). When labels are defined at the subject level but inputs are epoch level, a key design choice is how epoch-wise predictions are aggregated to a single subject-level decision. Most prior work uses mean pooling, which assumes all epochs contribute equally and independently. This study proposes a statistical meta-aggregation strategy that represents each subject by 14 descriptors of the epoch-wise prediction distribution, including measures of central tendency, dispersion, shape, and high-confidence concentration. Using a self-supervised contrast","pubDate":"2026-10-20","url":"https://www.biorxiv.org/content/10.64898/2026.10.13.759017v1?rss=1"},"indexado":"2026-10-20T14:25:26.749Z"}}