{"ok":true,"nota":{"id":"35793b981d14cc8a","slug":"un-modelo-de-pronostico-podria-hacer-los-ensayos-de-huntington-mas-efi-35793b","titulo":"Un modelo de pronóstico podría hacer los ensayos de Huntington más eficientes con menos pacientes","resumen":"Investigadores entrenaron nueve modelos de aprendizaje automático con datos de seguimiento de pacientes con la enfermedad de Huntington. Compararon cuánto mejora la precisión de un ensayo clínico al usar sus predicciones para ajustar los resultados.","fuente":"medrxiv","fuenteNombre":"medRxiv · preprints","color":"#1f7a4d","autor":"Noguerol Puente, C., Brizzi, F., Soubret, A., McColgan, P., Long, J., Boareto, M.","url":"https://www.medrxiv.org/content/10.64898/2026.10.19.26365884v1?rss=1","imagen":"/hoy/portada/35793b981d14cc8a","tema":"ciencia","subtemas":["enfermedad de huntington","ensayos clínicos","modelos predictivos","aprendizaje automático","enfermedades raras"],"entidades":["Enroll-HD"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-21T00:00:00.000Z","indexTs":"2026-10-21T22:39:37.287Z","hash":"28af66c686d87471add634ea80896c1ffefc488c9a0a178396baf420ab8126a1","tsa":{"time":"Oct 21 22:40:52 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"En una enfermedad rara como Huntington, reclutar pacientes para un ensayo es uno de los mayores obstáculos, y el trabajo estima cuánta eficiencia se gana al incorporar predicciones de progresión. Para una familia argentina con un caso en el entorno, esto puede significar que los tratamientos en desarrollo lleguen antes a probarse. Lo que todavía falta es que este método se valide en pacientes reales antes de cambiar la forma de diseñar los estudios.","quienFirma":"medRxiv (preprint; institución principal no identificada en el resumen)","confianza":"preprint","consulta":null},"sello":{"hash":"28af66c686d87471add634ea80896c1ffefc488c9a0a178396baf420ab8126a1","sello":"bd0c2f18c8ad968e7c430484673d5e519ac1931747dba8439c750fb459e68507","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6573047,"aleatorio":"2d5bf513cf7c1affa7426736d172d5981c9a94749f3f1efee998c0506487381c","tiempo":"2026-10-21T22:40:30.000Z"},"nist":{"cadena":2,"pulso":1993729,"salida":"2566CA36D87E2FBEC4D5E015FFCF0C1864DBD9B1365EDEAC0694FBFCE2C52475A35169CBCB950FAB325AC47DB3FC6E6C4F08665F398AD5CA0CA7EEC98EA260E3","tiempo":"2026-10-21T22:40:00.000Z"},"noAntes":"2026-10-21T22:40:30.000Z"},"verificacion":{"drand":true,"nist":"inaccesible"},"tsa":{"time":"Oct 21 22:40:52 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Quantifying statistical power gains from prognostic modeling in Huntington's Disease","descripcion":"Background and Objectives Huntington's disease is a rare neurodegenerative disease in which optimizing clinical trial design is essential. Although baseline characteristics are known to predict disease progression, the statistical efficiency gains achievable by formally integrating prognostic predictions into trial analyses have not been systematically quantified. We aimed to benchmark prognostic modeling approaches, quantify the trial efficiency gains from prognostic covariate adjustment, and deliver a ready-to-deploy framework for immediate implementation. Methods: We developed a two-step modeling pipeline using longitudinal Enroll-HD natural history data (NCT01574053) to train nine machin","pubDate":"2026-10-21","url":"https://www.medrxiv.org/content/10.64898/2026.10.19.26365884v1?rss=1"},"indexado":"2026-10-21T22:39:37.287Z"}}