Lunit, AI Solution in Emergency Room Reduces Emergency Patient Triage Time by 77%

Medical AI company Lunit announced on the 26th that a recent study published in the European Journal of Radiology revealed that using 'Lunit Insight CXR' in actual emergency settings at medical institutions reduced the time required for emergency patient triage by 77%.

Dr. Srinath Sridhar's research team at Changi General Hospital in Singapore classified a total of 20,944 chest X-ray images taken in the hospital emergency room from August to December 2023 into three categories: normal, non-emergency, and emergency, using Lunit's AI solution. Subsequently, 43 radiology specialists were involved to evaluate the results. The AI showed a sensitivity of 89% and specificity of 93% for normal cases, demonstrating reliable performance.

For non-emergency cases, the AI recorded a sensitivity of 93% and specificity of 91%, showing strong capability in identifying cases that did not require urgent care. Additionally, in emergency cases, the AI demonstrated a sensitivity of 82% and specificity of 99%, proving the necessity of AI solutions in emergency situations. It was confirmed that AI use in emergency settings can significantly reduce the workload of medical staff.

The average processing time for AI to classify emergency patients was reduced by 77% compared to physicians, and even in the minimum processing time, AI was faster than specialists, taking 0.2 seconds compared to 1.7 seconds for doctors.

The research team stated, "This study, designed primarily for emergency room environments, verified the effectiveness of AI in quickly and accurately classifying chest X-ray results across diverse patient groups," adding, "The results demonstrated by AI will assist physicians in making immediate decisions about patients."

Seobum Seok, CEO of Lunit, explained, "This study proved the clinical utility of AI in real medical environments," and added, "The 99% specificity shown by Lunit's AI solution in classifying patients requiring emergency care will contribute to improving the efficiency of medical staff in the future."