Automated ASPECTS Tool Raises Clinician Sensitivity by 9.7 Percentage Points in MRMC Reader Study

StrokeSENS ASPECTS, an AI tool, improved sensitivity for early ischemic changes on NCCT by 9.7 pp (p<0.001) and inter-reader agreement (κ 0.32→0.61) in an 8-reader, 100-case retrospective MRMC study of MCA/ICA occlusion patients.

• Multi-reader, multi-case study with 8 clinicians interpreting 100 NCCT scans; reference standard was consensus of three expert neuroradiologists.
• Overall accuracy improved by 2.6 pp, balanced accuracy by 5.7 pp, specificity by 1.6 pp (all p<0.001). Inter-reader agreement rose from Fleiss’ κ=0.32 to 0.61.
• Retrospective case sample; no external or multicenter validation reported.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.