A Medical Device Daily
Are invasive exams a thing of the past when trying to diagnose for cardiac infections?
The tests could well be after Mayo Clinic (Rochester, Minnesota) researchers are touting that a teachable software, which was developed to mimic the human brain can diagnose cardiac infections such as Endocarditis with relative ease.
Endocarditis is an infection involving the valves and sometimes chambers of the heart and can easily be a problem in patients with implanted medical devices.
The mortality rate can be as high as one in five, even with aggressive treatment and removal of the device. With additional complications, the mortality could be over 60%. Diagnosis usually requires transesophageal echocardiography, an invasive procedure that also has risks. It involves use of an endoscope and insertion of a probe down the esophagus.
The artificial neural network, or ANN, as researchers are calling it, mimics the brain's cognitive function and reacts differently to situations depending on its accumulated knowledge.
The accumulated knowledge comes from ANN's exposure to a variety of different situations. In other words, researchers taught or trained the software to recognize the different scenarios of the onset of illness much like a person would train a computer to play chess. The program went through a total of three separate trainings to learn how to evaluate the symptoms it would be considering.
The team studied 189 Mayo patients with device-related endocarditis diagnosed between 1991 and 2003. The ANN was tested retrospectively on the data from these cases.
When tested on cases with known diagnosis of endocarditis, the best-trained ANN 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%.
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.
"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," M. Rizwan Sohail, MD, a Mayo Clinic infectious diseases specialist and leader of the study said in a statement.
The research team included Loai Saadah; Tawam-Johns; and Daniel Uslan, MD; Paul Friedman, MD; David Hayes, MD; Walter Wilson, MD; James Steckelberg, MD; and Larry Baddour, MD.
The findings were presented at the Interscience Conference on Antimicrobial Agents and Chemotherapy in San Francisco earlier this month.