Deep Learning Detection of Active Pulmonary Tuberculosis at Chest Radiography Matched the Clinical Performance of Radiologists

Good news! Machine learning keeps on giving! 

Unfortunately, the group of selected human doctors is very small and and all were based in India.

"A new artificial intelligence tool by Google detected tuberculosis in chest X-rays, matching the skills of radiologists, according to a new Radiology study published yesterday; the AI system met or exceeded WHO performance standards for detecting the disease, which kills 1.4 million people annually."

From the abstract:

"... A total of 165 754 images in 22 284 subjects (mean age, 45 years; 21% female) were used for model development and testing. In the four-country test set (1236 subjects, 17% with active TB), the receiver operating characteristic (ROC) curve of the DLS was higher than those for all nine India-based radiologists, with an area under the ROC curve of 0.89 (95% CI: 0.87, 0.91). Compared with these radiologists, at the prespecified operating point, the DLS sensitivity was higher (88% vs 75%, P < .001) and specificity was noninferior (79% vs 84%, P = .004). Trends were similar within other patient subgroups, in the South Africa data set, and across various TB-specific chest radiograph findings. In simulations, the use of the DLS to identify likely TB-positive chest radiographs for NAAT confirmation reduced the cost by 40%–80% per TB-positive patient detected. ..."

Deep Learning Detection of Active Pulmonary Tuberculosis at Chest Radiography Matched the Clinical Performance of Radiologists | Radiology (open access)

Credits: Johns Hopkins Bloomberg School of Public Health: Global Health NOW