Guidelines for integrating large language models in radiology emphasize regulatory oversight, data privacy protection, and bias reduction to support safe use in clinical practice.
“These findings indicate that standardized efficacy, safety, and risk assessment reporting remains inadequate for FDA-cleared AI/ML devices, underscoring the need for dedicated regulatory pathways and robust postmarket surveillance to ensure patient safety."
In a long-term cohort study, researchers found that specific retinal changes—thinner photoreceptor layers and thicker retinal pigment epithelium—were linked to a higher risk of developing amyotrophic lateral sclerosis, suggesting potential noninvasive biomarkers for early detection.