Stroke diagnosis improved by AI support, multinational study finds
Dr. Chi Kyung (CK) Kim of the Department of Neurology at Korea University Guro Hospital and his research team successfully conducted a multinational validation of AI technology that precisely detects large vessel occlusion (LVO) in acute stroke patients using only standard brain CT (non-contrast CT) without contrast agents. The findings are published in the Journal of NeuroInterventional Surgery.…
A multinational study has found that AI can significantly improve the diagnosis of large vessel occlusion (LVO) in acute stroke patients using only non-contrast CT scans. Dr. Chi Kyung Kim and his team at Korea University Guro Hospital conducted the research, which was published in the Journal of NeuroInterventional Surgery. The AI algorithm analyzed data from 963 patients, including 723 from Korea and 240 from the United States.
The study demonstrated that the AI had an area under the curve (AUC) of 0.963 for the Korean patient group and 0.899 for the U.S. patient group, indicating high diagnostic performance. When medical professionals read non-contrast CT scans without AI, their diagnostic accuracy was 0.718. However, with AI assistance, this increased to 0.852, showing a substantial improvement.
Sensitivity and specificity of the AI also improved significantly, from 46.6% to 63.7% and 91.9% to 94.9%, respectively. The research confirmed that AI can serve as a valuable tool in emergency stroke care, helping to identify missed cases and maintain high diagnostic performance across different clinical settings and equipment.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
