British researchers are working to adapt technology from the aviation industry to help prevent complications among heart patients after surgery. Up to 1,000 sensors aboard aircraft help airlines determine when a plane requires maintenance, reports The Engineer, serving as a model for the British risk-prediction system.
The system analyzes information from hospital cardiovascular patients in real time and compares it with a database of thousands of previous cases to predict the most likely outcome.
"There are vast amounts of clinical data currently collected which is not analyzed in any meaningful way. This tool has the potential to identify subtle early signs of complications from real-time data," Stuart Grant, a research fellow in surgery at University Hospital of South Manchester, says in a hospital statement. Grant is part of the Academic Surgery Unit working with Lancaster University on the project, which is still its early stages.
The software predicts the patient's condition over a 24-hour period using four metrics: systolic blood pressure, heart rate, respiration rate and peripheral oxygen saturation, explains EE Times.
As a comparison tool, the researchers obtained a database of 30,000 patient records from the Massachusetts Institute of Technology and combined it with a smaller, more specialized database from Manchester.
In six months of testing, its accuracy is about 75 percent, The Engineer reports. More data and an improved algorithm could boost that rate to 85 percent, the researchers believe. Making the software web-based would allow physicians to access the data anywhere, even on tablets or phones, and could enable remote consultation with specialists.
In their next step, the researchers are applying for more funding and for ethical clearance for a large-scale trial.
U.S. researchers are working on a similar crystal ball, but one covering an array of conditions. Researchers from the University of Washington, MIT and Columbia University are using a statistical model that can predict future ailments based on a patient's history--and that of thousands of others.
And the U.S. Department of Health & Human Services is using mathematical modeling to analyze effects of specific healthcare interventions.
Predictive modeling also holds promise to make clinical research easier by using algorithms examine multiple scenarios based on different kinds of patient populations, specified health conditions and various treatment regimens