{"ok":true,"nota":{"id":"3910e97b01ac909f","slug":"con-inteligencia-artificial-separaron-el-autismo-en-grupos-y-encontrar-3910e9","titulo":"Con inteligencia artificial, separaron el autismo en grupos y encontraron genes distintos para cada uno","resumen":"Usaron machine learning sobre catorce síntomas clínicos de más de seis mil niños autistas de una base grande de Estados Unidos. Con eso armaron subtipos y compararon qué variantes genéticas, comunes y raras, aparecían en cada grupo.","fuente":"medrxiv","fuenteNombre":"medRxiv · preprints","color":"#1f7a4d","autor":"Tan, Q., Xie, J., Snyder, L. G., Chen, R., Yang, L., Chen, F., Trost, B., Fernandez, B., Chiang, C. W.-K., Mancuso, N., ","url":"https://www.medrxiv.org/content/10.64898/2026.10.19.26365670v1?rss=1","imagen":"/hoy/portada/3910e97b01ac909f","tema":"ciencia","subtemas":["autismo","genetica","machine learning","neurodesarrollo","diagnostico"],"entidades":["SPARK","Simons Foundation"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-24T00:00:00.000Z","indexTs":"2026-10-24T16:59:18.926Z","hash":"64f369fa86483ebd5c6f9879a7ebd771a2d80060a2a56d0103aa0a4eedea7848","tsa":{"time":"Oct 24 16:59:40 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"Hasta ahora el autismo se estudiaba como si fuera una sola cosa, y eso puede ocultar diferencias reales entre chicos con síntomas muy distintos. Si los subtipos se confirman, las familias de acá podrían recibir diagnósticos y apoyos más ajustados a cada caso. Todavía falta que otros equipos repliquen el hallazgo, y la clasificación se hizo con datos de un solo país. Eso no alcanza para cambiar la atención hoy, pero sí para cambiar cómo se piensa el problema.","quienFirma":"Simons Foundation Powering Autism Research for Knowledge (SPARK)","confianza":"preprint","consulta":null},"sello":{"hash":"64f369fa86483ebd5c6f9879a7ebd771a2d80060a2a56d0103aa0a4eedea7848","sello":"6bd5b76cf69995cecc325cf54e1fa98ab2c3c58e13758e69e2f4945972b1b34d","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6581004,"aleatorio":"18fa3ebd0d23e51eddcfd942bf92bbc809cc6eeb0ce5c2a97021a740f6fe817b","tiempo":"2026-10-24T16:59:00.000Z"},"nist":{"cadena":2,"pulso":1997695,"salida":"2AC2AD0FD15EA4B557A3E6116D19A7A248B9BE4CD68ECAF85135A44A079725445FC9BE22BDB61B93C43C9F1673D19E58C8A772BD4555DCB4851540739CADD210","tiempo":"2026-10-24T16:58:00.000Z"},"noAntes":"2026-10-24T16:59:00.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 24 16:59:40 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Machine Learning-Derived Subtypes of Autism Reveal Distinct Genetic Contributions from Common and Rare Variants","descripcion":"Background: Autism spectrum disorder (ASD) is characterized by substantial heterogeneity in core symptom severity and co-occurring conditions, complicating efforts to understand its genetic basis. Most genetic studies rely on binary case-control ASD definitions, which may obscure clinically meaningful variation and distinct genetic contributions across the autism spectrum. Methods: We constructed machine learning (ML)-based categorical ASD subtypes and corresponding continuous ASD subtype scores using 14 key clinical symptom measures with adjustment of sex and age among 6,355 autistic children in the Simons Foundation Powering Autism Research for Knowledge (SPARK) cohort by Discriminative Di","pubDate":"2026-10-24","url":"https://www.medrxiv.org/content/10.64898/2026.10.19.26365670v1?rss=1"},"indexado":"2026-10-24T16:59:18.926Z"}}