Section
8 stories
Eleven hospitals trained without moving data. The performance is respectable, the coordination cost was enormous, and the paper is unusually honest about both.
Researchers propose scoring clinical models on appropriate abstention, arguing that confident answers on out-of-scope cases are the dominant real-world failure.
When variant interpretation drops from weeks to hours, the bottleneck moves to the conversation about what to do with the result.
A long-running mammography program reports its first durable change in recall rates — downward, after an initial rise that took eighteen months to reverse.
A methodological review finds that fewer than one in five published evaluations measured a patient outcome rather than a model metric.
Adenoma detection did not improve at high-performing sites. The subgroup where it did is the finding that matters.
Models that read eligibility criteria work well. Models that read the patient's chart to check them do not.
Deployment is accelerating, evidence is not, and the gap between them is the story of the spring.