Artificial intelligence (AI) software developer Lunit is touting the results of a recent PLOS One study showing that its Insight CXR algorithm successfully detected COVID-19 pneumonia on chest radiography.
The November 24 study compared the clinical effectiveness of the algorithm with formal radiology reports using COVID-19 cases from five medical institutions in South Korea. Researchers included chest x-rays from 279 patients in the analysis, Lunit noted.
Lunit reported that Insight CXR achieved a 95.6% sensitivity and 88.7% specificity for detecting COVID-19 from the radiographs. The algorithm also showed no significant difference in area under the curve values compared with radiology reports, according to the company.
The Lunit Insight CXR algorithm has analyzed more than 6.5 million images to aid with detecting 10 major chest diseases, including lung nodules and pneumothorax. The tool has received the CE mark and is available in Europe, the Middle East, Latin America, South East Asia, Australia, and New Zealand.