{"ok":true,"nota":{"id":"a2523e8935b900dc","slug":"un-modelo-de-inteligencia-artificial-anticipa-mejor-que-pacientes-pued-a2523e","titulo":"Un modelo de inteligencia artificial anticipa mejor qué pacientes pueden volver a terapia intensiva","resumen":"Los investigadores armaron un modelo que combina varias técnicas de aprendizaje profundo y lo entrenaron con historias clínicas electrónicas de pacientes de terapia intensiva. Buscaban predecir quiénes volverían a ser internados en ese sector después del alta.","fuente":"zenodo","fuenteNombre":"Zenodo · Investigación abierta","color":"#1682d4","autor":"KOUMANTAKIS, EMANUELE, Remoundou, Konstantina, Xynogalas, Stavros","url":"https://doi.org/10.54103/2282-0930/29400","imagen":"/hoy/portada/a2523e8935b900dc","tema":"ciencia","subtemas":["inteligencia artificial","terapia intensiva","alta hospitalaria","historias clínicas electrónicas","aprendizaje profundo"],"entidades":["Zenodo","terapia intensiva"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-20T07:17:22.000Z","indexTs":"2026-10-22T10:32:02.032Z","hash":"49d15bda16939b4892d9e300ea9b1d9dd63120a326f0ef0ae7e21ce70113b2ce","tsa":{"time":"Oct 22 10:32:41 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"motor","registro":"hallazgo","porQueImporta":"Cuando un paciente vuelve a terapia intensiva, aumentan el riesgo de muerte y los costos del sistema de salud. Acertar mejor con el momento del alta puede evitar que alguien vuelva a internarse. Para un hospital argentino con camas escasas, cada decisión de alta pesa doble. La pregunta de fondo es si una máquina puede ayudar a un médico a no equivocarse en el peor momento.","quienFirma":"Zenodo (repositorio abierto); autores no identificados en el registro","confianza":"preprint","consulta":{"pregunta":"¿Confiarías en una IA para decidir el alta de un familiar?"}},"sello":{"hash":"49d15bda16939b4892d9e300ea9b1d9dd63120a326f0ef0ae7e21ce70113b2ce","sello":"40db2798424291d3ea5f1a098f570cbb8f5943a36c36143d6bc473db052310aa","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6574471,"aleatorio":"8dc65bda024d9b15bc5015dca7a625bd58abcd79898d9e649dd88c7b09d4609e","tiempo":"2026-10-22T10:32:30.000Z"},"nist":{"cadena":2,"pulso":1994441,"salida":"917B00588BBAF41DD8C461E7D93EA47DC73C00983776285722380061C2505D68D1C49D178A1E9E1A422EEA35DB6367141AB79828DD0F9592CE1805F752B02469","tiempo":"2026-10-22T10:32:00.000Z"},"noAntes":"2026-10-22T10:32:30.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 22 10:32:41 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Read-ICU: An Ensemble Deep Learning Model for ICU Readmission Prediction","descripcion":"<p>Intensive Care Unit (ICU) readmissions are linked to increased morbidity, mortality, and healthcare costs. The correct timing of ICU discharge is critical to prevent these adverse outcomes. Traditional predictive models have limited accuracy, while deep learning (DL) models offer potential improvements by extracting richer information from multimodal electronic health record data.</p>","pubDate":"2026-10-20T07:17:22Z","url":"https://doi.org/10.54103/2282-0930/29400"},"indexado":"2026-10-22T10:32:02.032Z"}}