Mayo Clinic (09/12/09) Nellis, Robert
Researchers at the Mayo Clinic have trained an artificial neural network (ANN) to evaluate the symptoms for infections involving the valves and chambers of the heart, and they believe the software has the potential to replace diagnosis with more invasive exams. The team trained the ANN on three separate occasions by introducing as many situations related to endocarditis infections as possible. Then the researchers tested the software on 189 cases involving device-related endocarditis between 1991 and 2003. On cases with known diagnosis of endocarditis, the best-trained ANN was correct in 72 of 73 implant-related infections and 12 of 13 endocarditis cases, with a confidence level greater than 99 percent. And for an overall sample of both known and unknown cases, the software accurately excluded endocarditis in at least half of the cases, eliminating such patients from an unnecessary endoscope and insertion of a probe down the esophagus. “If, through this novel method, we can help determine a percentage of endocarditis diagnoses with a high rate of accuracy, we hope to save a significant number of patients from the discomfort, risk, and expense of the standard diagnostic procedure,” says study leader M. Rizwan Sohail.
Filed under: ICT