{"ok":true,"nota":{"id":"c7300574057d98aa","slug":"un-metodo-nuevo-mantiene-confiables-las-predicciones-de-riesgo-en-salu-c73005","titulo":"Un método nuevo mantiene confiables las predicciones de riesgo en salud mental cuando cambian los pacientes","resumen":"Investigadores desarrollaron ADAPT, un método para que los modelos que predicen riesgo en salud mental a partir de historias clínicas electrónicas sigan funcionando cuando cambian las poblaciones de pacientes y las prácticas de atención. Lo probaron frente a actualizaciones simples basadas solo en datos recientes.","fuente":"medrxiv","fuenteNombre":"medRxiv · preprints","color":"#1f7a4d","autor":"Xiong, X., Shi, E., Qian, Z., Zhu, H., Hong, C., Guo, Z., Smoller, J. W., Liu, M., Cai, T.","url":"https://www.medrxiv.org/content/10.64898/2026.10.28.26366683v1?rss=1","imagen":"/hoy/portada/c7300574057d98aa","tema":"salud","subtemas":["salud mental","historia clinica electronica","modelos predictivos","deriva temporal","prevencion"],"entidades":[],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-29T00:00:00.000Z","indexTs":"2026-10-30T00:18:54.680Z","hash":"8f17a6846ff06948059b3261168d07eaf972ea584c14ac90e0d2261d2420c14a","tsa":{"time":"Oct 30 00:19:40 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"Un sistema que alerta sobre riesgo de crisis en salud mental puede volverse menos preciso sin que nadie lo note, porque los pacientes y la forma de documentar cambian con los años. Este trabajo propone un ajuste que evita que la herramienta se desactive en silencio, y eso importa sobre todo en hospitales y centros que usan estas alertas para decidir a quién llamar primero. Es un preprint sin revisión externa todavía, así que hay que esperar validaciones en otros sistemas de salud.","quienFirma":"medRxiv · preprints","confianza":"preprint","consulta":null},"sello":{"hash":"8f17a6846ff06948059b3261168d07eaf972ea584c14ac90e0d2261d2420c14a","sello":"8ca274e929cba4ecbe7d6b8c4ca2cc9e6263b679fddd92dd1a62db8e34609234","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6596285,"aleatorio":"c081b28c47de1b3ebaff2ab6fadd94a4e1d5df8956cce1796159e8f3a3c84477","tiempo":"2026-10-30T00:19:30.000Z"},"nist":{"cadena":2,"pulso":2005076,"salida":"D1D471A81853AED712E452A7D73F82257D9E5310F62C5D5691DE99C64EC2110FF870FD06ACCC0EFE8D43CE6737ABC2C8D9860CE82BDD7542A5890EDDB8765434","tiempo":"2026-10-30T00:18:00.000Z"},"noAntes":"2026-10-30T00:19:30.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 30 00:19:40 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Maintaining EHR-based Predictive Clinical Decision Support in Mental Health against Temporal Shifts","descripcion":"Electronic health record (EHR)-based risk prediction offers opportunities for early intervention in mental health, but models may remain in use as patient populations, care practices, and documentation change. Such temporal shifts can reduce predictive performance, while updating models from recent data alone may be unstable when adverse outcomes are uncommon. We developed Adversarial Drift-Aware Predictive Transfer (ADAPT), a distributionally robust approach to improve the temporal durability of mental health risk prediction. ADAPT uses variation in models estimated from previous calendar periods to characterize plausible changes in predictor-outcome relationships. Data from the current per","pubDate":"2026-10-29","url":"https://www.medrxiv.org/content/10.64898/2026.10.28.26366683v1?rss=1"},"indexado":"2026-10-30T00:18:54.680Z"}}