Artificial Neural Networks aid in diagnosis of heart infection

Artificial neural networks (ANNs) are, as their name suggests, computer-implemented analogues of the brain's neural network, though not nearly so sphisticated. One of a number of approaches to "artificial intelligence", this particular one can be either hardware- or software-based and is well-suited to approaches such as pattern recognition and classification, tasks that our ouwn brains excel at, since artificial neural networks are capable of learning.

Researchers at the Mayo Clinic employed this technique to assist in the diagnosis of a heart infection, endocarditis, related to implanted devices such as pacemakers. If left unchecked, such an infection can be fatal, and treatment is no certain cure. Under normal conditions, this disease has to be confirmed via an invasive surgical procedure, but the ANN allowed them to rule out endocarditis in cases of unknown diagnosis.  

During this process, they trained the neural network using known cases with both positive and negative diagnoses, then presented it with a mixed bag of both known and unknown cases. The ANN was able to correctly rule out endocarditis in half of the cases. In the long run, such an accomplishment could help to avoid unnecessary and expensive surgical procedures.

Given the current discussions surrounding health care costs and the search for ways to reduce them, use of artificial intelligence techniques such as neural networks and their expert system cousins could very possibly serve as potential allies in that battle.