Diagnosing Cardiac Infections with Artificial Intelligence

By Craig Taylor

September 14, 2009

A new “teachable software” designed to mimic the brain’s cognitive function can help diagnose endocarditis (inflammation of the heart's inner lining)—eliminating the need for an invasive exam.

According to Mayo Clinic researchers, the software program “artificial neural network” (ANN) reacts differently to situations depending on its accumulated knowledge. That knowledge or training is provided by the researchers, similar to how a person would train a computer to play chess, by introducing it to as many situations as possible.

"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," said M. Rizwan Sohail, M.D., a Mayo Clinic infectious diseases specialist and leader of the study.

Sohail’s team studied 189 patients with device-related endocarditis diagnosed between 1991 and 2003. The ANN software program was tested retrospectively on the data from these cases. When tested on cases with a known diagnosis of endocarditis, the best-trained program was correct most of the time (72 of 73 implant-related infections and 12 of 13 endocarditis cases) with a confidence level greater than 99 percent.

Researchers say that, when used on an overall sample that included both known and unknown cases, the ANN accurately excluded endocarditis in at least half of the cases, thus eliminating half the cohort from a needless invasive procedure.