LATIDIA · Investigación

Los beneficios de la asistencia médica de IA varían según la experiencia del usuario

El estudio encuentra que los no expertos difirieron a la asistencia de diagnóstico basada en LLM, incluso cuando estaba mal, mientras que los médicos detectaron errores de IA.

La noticia

A one-size-fits-all approach likely isn’t the best strategy when designing artificial intelligence systems that assist users in disease diagnosis. A new study by researchers at MIT and elsewhere found that, while AI assistance generally improved the accuracy of non-experts and clinicians in diagnosing skin diseases, AI explainability methods had different impacts depending on the users’ knowledge level. Explainable AI methods help users know when to trust a model’s predictions by describing or validating the model’s decision-making. For instance, a model might use a heat map to highlight image regions that were most important in its diagnosis or a large language model (LLM) to explain the prediction in plain language. In