Study Finds Artificial Intelligence Poised to Enhance Response to Future Viral Outbreaks
A groundbreaking patient triage system driven by artificial intelligence (AI) has been created by researchers. This pioneering platform has the capability to forecast the severity of a patient's illness and the duration of their hospitalization during a viral epidemic. Recently detailed in the journal Human Genomics, the system harnesses the potential of machine learning, a facet of AI, along with insights from metabolomics—exploring small molecules linked to cellular metabolism. The team behind this advancement employed COVID-19 as their disease model, crafting a solution that merges regular clinical data, patient comorbidity insights, and untargeted plasma metabolomics information to fuel its predictive prowess.
Triage is the prioritisation of patient care based on illness, severity, prognosis, and resource availability.
The platform, described recently in the journal Human Genomics, leverages machine learning, a form of AI, and data from metabolomics -- the study of small molecules related to cell metabolism.
The innovation 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, the researchers said.
"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 optimise patient health outcomes and use hospital resources most efficiently during an outbreak," said senior study author Vasilis Vasiliou, a professor at Yale University, US.
The researchers developed the platform using COVID-19 as a disease model. It integrates routine clinical data, patient comorbidity information, and untargeted plasma metabolomics data to drive its predictions.
"Our AI-powered patient triage platform is distinct from typical COVID-19 AI prediction models,” said Georgia Charkoftaki, a lead author of the study and an associate research scientist at Yale.
“It serves as the cornerstone for a proactive and methodical approach to addressing upcoming viral outbreaks," Charkoftaki said.
Using machine learning, the researchers built a model of COVID-19 severity and prediction of hospitalisation based on clinical data and metabolic profiles collected from patients hospitalized with the disease.
“The model led us to identify a panel of unique clinical and metabolic biomarkers that were highly indicative of disease progression and allows the prediction of patient management needs very soon after hospitalization,” the researchers wrote in the study.
