{"ok":true,"nota":{"id":"b76685906053717b","slug":"una-base-de-datos-reune-ejercicios-que-bajan-la-presion-y-busca-person-b76685","titulo":"Una base de datos reúne ejercicios que bajan la presión y busca personalizarlos","resumen":"Un equipo usó modelos de lenguaje para revisar miles de estudios y armar una base consultable con 255 trabajos sobre actividad física para la hipertensión. Cada dato extraído incluye la cita textual de la fuente original.","fuente":"medrxiv","fuenteNombre":"medRxiv · preprints","color":"#1f7a4d","autor":"Li, C., Obioha, C., Cui, X., Zhou, X., Wang, M.","url":"https://www.medrxiv.org/content/10.64898/2026.10.22.26366246v1?rss=1","imagen":"/hoy/portada/b76685906053717b","tema":"salud","subtemas":["hipertensión","actividad física","modelos de lenguaje","bases de datos médicas","ejercicio"],"entidades":["PubMed","PAHD"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-26T00:00:00.000Z","indexTs":"2026-10-26T21:44:45.754Z","hash":"8c1497b694cfec7301d8413e29ebdae63ed3cb14795ba2b7a751c9f82f95904c","tsa":{"time":"Oct 26 21:45:27 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"Se sabe que moverse ayuda a bajar la presión, pero las recomendaciones generales no tienen en cuenta la edad, otras enfermedades ni los medicamentos que toma cada persona. Una base organizada permite buscar qué tipo de ejercicio funcionó en casos parecidos al propio. Para alguien con presión alta que nunca supo por dónde empezar, esto abre la puerta a un plan más ajustado. Pero la herramienta sigue dependiendo de la supervisión médica, porque ningún cuadro sirve si no se adapta al cuerpo concreto.","quienFirma":"Equipo de investigación en salud digital (sin institución principal informada)","confianza":"preprint","consulta":null},"sello":{"hash":"8c1497b694cfec7301d8413e29ebdae63ed3cb14795ba2b7a751c9f82f95904c","sello":"3a7e9463aa5771fe1b9109cbf8fa9f297baa3143f2aa58809d5bb89eb618b937","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6587336,"aleatorio":"7f09892dc40bc182e2fd089c9cd7da6d4bf0ce04b004bf22db591df3c5e9aa66","tiempo":"2026-10-26T21:45:00.000Z"},"nist":{"cadena":2,"pulso":2000861,"salida":"7270D97C2D57F9CB7EB7B095A08C5FEB9B89AB79EC9A8CA95295DF433D69A435C33F40AA23444ADF25BC5940158B01E8B7275199BCC1D89A41E5D4F68D952C8B","tiempo":"2026-10-26T21:44:00.000Z"},"noAntes":"2026-10-26T21:45:00.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 26 21:45:27 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"A Knowledge Database of Physical Activity Interventions for Hypertension using Large Language Models","descripcion":"Physical exercise lowers blood pressure, but guidelines address broad populations and rarely consider age, comorbidities, medications or baseline severity. No structured, queryable database of exercise interventions for hypertension exists, and manual curation is not scalable. We present PAHD (Physical Activity for Hypertension Database), built with large language models (LLMs). An LLM screened 2,548 PubMed records by title and abstract, then full text, selecting 255 studies. LLMs extracted each study's groups, exercise protocols, patient characteristics and results; two LLMs cross-checked the study structure, and every value carries a verbatim quote. Code standardized and joined the extract","pubDate":"2026-10-26","url":"https://www.medrxiv.org/content/10.64898/2026.10.22.26366246v1?rss=1"},"indexado":"2026-10-26T21:44:45.754Z"}}