The deep learning system, trained in disease detection, scanned 165,174 chest radiographs from 22,284 patients in four countries. In detecting active tuberculosis, its sensitivity was higher (88 percent versus 75 percent) and its specificity was “noninferior” (79 percent versus 84 percent) compared to nine India-based radiologists, the Google-funded study found. It also reduced costs by 40 percent to 80 percent per tuberculosis-positive patient.
“To achieve the long-term public health vision of eliminating tuberculosis globally, there is a pressing need to scale up identification and treatment in resource-constrained settings,” the study’s authors wrote. “The [deep learning system] may be able to facilitate tuberculosis screening in areas with limited radiologist resources and merits further prospective clinical validation.”
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.