How we read the signal

Analysis frame

Evidence level

Peer-reviewed research

Analytical lens

Distinguish lesion detection in a retrospective standalone test from clinical decision support and demonstrated patient benefit.

Affected groups
  • Patients whose MRI scans require careful interpretation
  • Clinical readers and hospitals considering diagnostic tools
What remains unknown
  • Independent multi-centre performance across scanners and populations
  • Effects on reader decisions, workload and patient outcomes
Second-order effects to watch
  • Reliable assistance could help focus expert attention on subtle findings.
  • False alarms could shift work rather than remove it, making workflow evaluation important.

What was and was not inspected

The accessible accepted-manuscript abstract and disclosures describe 457 test MRI examinations and an analysis of 456 participants with 515 lesions. We did not inspect the full methods or supplement, so details of reference-standard adjudication and the excluded examination remain evidence gaps. The authors themselves call for broader expert-reader validation.

Primary trail

Go to the source

Read the evidence behind this analysis. External links open in a new tab.

Scientific Reports — standalone cerebral microbleed detection study