The Defense Innovation Unit, an agency within the DOD, announced on Oct. 22 findings from an 18-month predictive health monitoring research project, which aimed to create an early warning algorithm to identify infection before an individual show signs or symptoms, according to a news release emailed to Becker’s Hospital Review.
The project, called Rapid Analysis of Threat Exposure, uses large-scale data machine learning and additional analyses across 165 different biomarkers stored in a Philips dataset of more than 41,000 cases of hospital-acquired infection. The dataset was taken from a data repository of more than 7 million hospital patient encounters.
RATE revealed that using AI to examine certain combinations of vital signs and other biomarkers could help predict the likelihood of infection up to 48 hours in advance of clinical suspicion, which includes observable symptoms.
DOD and Philips plan to complete further research on the project to determine whether the results can be applied as an algorithm integrated into a wearable device to non-invasively monitor a soldier’s health. The research may also be applied to help monitor hospital patients for infection prior to presenting clinical symptoms.
More articles on artificial intelligence:
4 obstacles to widespread adoption of AI in healthcare
Indiana U receives $60M to establish AI initiative for digital health
Microsoft, Nuance partner to develop ‘exam room of the future’ with the help of AI
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.