ai

.

echoes

.

today

← AI Today
AI Today · daily note
Conceptual AI-generated black-and-white photograph of a row of hospital waiting-room chairs with one chair pushed out of line and a coat left on it.
No.
447
•
•

The Patient Who Visited Too Often

October 22nd, 2026 | By Jorge Rodriguez

In a busy emergency room, someone has to decide who gets seen first. Hospitals are starting to test AI programs for that job, and a study from UT Southwestern Medical Center, published this week in npj Digital Medicine, shows how easily those programs can get it wrong. Researchers used real records from the emergency departments at Stanford and at Beth Israel Deaconess in Boston. They paired patients who looked equally sick when they arrived, knowing that one of each pair later got worse. Then they asked three AI models which patient should come first. On their own, the models usually chose correctly.

The results changed when the researchers added a single detail to one patient’s file. A line such as “17 visits in the past 12 months,” or a history of psychiatric emergencies, made the models more likely to move that person down the list, even when that was the patient about to get worse. In some tests, close to one in ten patients was wrongly downgraded. Emergency staff sometimes call these patients “frequent flyers,” and many keep coming back because they are chronically ill, have no regular doctor or have nowhere else to go. The experiment used past records, so no real patient was harmed. Dr. Philip Jarrett, the study’s lead author, says each hospital should check these tools against its own past patients before letting them help decide who waits.

No.
447
•
•

El paciente que volvía demasiado

Octubre 22, 2026 | Por R10

En una sala de urgencias llena, alguien tiene que decidir a quién se atiende primero. Los hospitales empiezan a probar programas de inteligencia artificial para esa tarea, y un estudio del UT Southwestern Medical Center, publicado esta semana en npj Digital Medicine, muestra con qué facilidad pueden equivocarse. Los investigadores usaron historiales reales de las urgencias de Stanford y del Beth Israel Deaconess de Boston. Formaron parejas de pacientes que parecían igual de graves al llegar, sabiendo que uno de cada pareja empeoró después. Luego pidieron a tres modelos de IA que eligieran a quién atender antes. Sin más datos, los modelos solían acertar.

El resultado cambió cuando los investigadores añadieron un solo dato al expediente de uno de los pacientes. Una línea como «17 visitas en los últimos 12 meses», o un historial de urgencias psiquiátricas, hizo que los modelos tendieran a bajarlo en la lista, incluso cuando era el paciente que estaba a punto de empeorar. En algunas pruebas, casi uno de cada diez pacientes quedó relegado por error. En las urgencias de Estados Unidos a veces los llaman frequent flyers, y muchos vuelven una y otra vez porque tienen enfermedades crónicas, no cuentan con un médico de cabecera o no tienen otro lugar adonde ir. El experimento usó historiales pasados, así que ningún paciente real sufrió daño. El doctor Philip Jarrett, autor principal del estudio, dice que cada hospital debería comprobar estas herramientas con sus propios pacientes anteriores antes de dejar que ayuden a decidir quién espera.

Latest from AI Today

|
NOTES ON VISUAL NARRATIVE
|
ABOUT

donations

If you’re a regular reader of this blog and enjoy its content, you might consider contributing to its upkeep. Any amount, no matter how small, will be warmly appreciated

Founded in 2021, Echoes (Notes of Visual Narrative) invites everyone to explore together the visual codes that shape our world—art, photography, design, and advertising in dialogue with society.

Copyright © 2025 r10studio.com. All Rights Reserved. Website Powered by r10studio.com

Cincinnati, Ohio