An innovative patient triage platform powered by artificial intelligence is capable of predicting patient disease severity and length of hospitalization during a viral outbreak, researchers say.

The platform, which leverages machine learning and metabolomics data, is intended to improve patient management and help health care providers allocate resources more efficiently during severe viral outbreaks that can quickly overwhelm local health care systems. Metabolomics is the study of small molecules related to cell metabolism.

“Being able to predict which patients can be sent home and those possibly needing intensive care unit admission is critical for health officials seeking to optimize patient health outcomes and use hospital resources most efficiently during an outbreak,” says Vasilis Vasiliou, a professor of epidemiology at Yale University School of Public Health and senior author of the study published in the journal Human Genomics.

The researchers developed the platform, which integrates routine clinical data, patient comorbidity information, and untargeted plasma metabolomics data to drive its predictions, using COVID-19 as a disease model.

“Our AI-powered patient triage platform is distinct from typical COVID-19 AI prediction models,” says lead author Georgia Charkoftaki, an associate research scientist in the environmental health sciences department. “It serves as the cornerstone for a proactive and methodical approach to addressing upcoming viral outbreaks.”

Read the full article about improving patient triage with AI at Futurity.