News | September 14, 2009

Mayo Clinic Uses Artificial Intelligence to Help Diagnose Cardiac Infections

September 13, 2009 – Mayo Clinic researchers say that "teachable software" designed to mimic the human brain may help them diagnose cardiac infections without an invasive exam, according to findings being presented today at the Interscience Conference on Antimicrobial Agents and Chemotherapy (ICAAC) in San Francisco.

Endocarditis, an infection involving the valves and sometimes chambers of the heart, can be a problem in patients with implanted medical devices. It is serious and can be deadly. 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 percent. 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 software program is called an "artificial neural network" (ANN) because it mimics the brain's cognitive function and reacts differently to situations depending on its accumulated knowledge. That knowledge or training is provided by researchers, similar to how a person would "train" a computer to play chess, by introducing it to as many situations as possible. In this case, the ANN underwent three separate "trainings" to learn how to evaluate the symptoms it would be considering.

"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.

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 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.

For more information: www.mayo.edu

Related Content

Male Triathletes May Be Putting Their Heart Health at Risk
News | Cardiac Diagnostics| January 09, 2018
Competitive male triathletes face a higher risk of a potentially harmful heart condition called myocardial fibrosis,...
ERT Acquires iCardiac Technologies
News | Cardiac Diagnostics| December 19, 2017
ERT recently announced it has acquired iCardiac Technologies, a provider of centralized cardiac safety and respiratory...
New Study Suggests Protein Could Protect Against Coronary Artery Disease

Patients with no obstructed blood flow in the coronary arteries had higher levels of CXCL5 (blue) compared to patients with moderate levels (green) or lower levels (yellow) of CXCL5, who had increased severity of coronary obstructions (indicated by the arrows). Credit: Schisler lab

News | Cardiac Diagnostics| December 07, 2017
December 7, 2017 — The buildup of plaque in the heart’s arteries is an unfortunate part of aging.
E-cigarettes Most Likely to be Used by Alcohol Drinkers and Former Cigarette Smokers, at American Heart Association (AHA), #AHA2017.
News | Cardiac Diagnostics| December 06, 2017
December 6, 2017 — Electronic cigarettes are more frequently used by people who recently quit smoking and alcohol dri
Lack of sleep may cause heart disease in older women. American heart Association, #AHA2017
News | Cardiac Diagnostics| December 06, 2017
December 6, 2017 — Older women who do not get enough sleep were more likely to have poor cardiovascular health, accor
New Tool Predicts Risk of Heart Attack in Older Surgery Patients
News | Cardiac Diagnostics| December 05, 2017
A tool designed to more accurately predict the risk of heart attack in older patients undergoing non-cardiac surgery...
EPIC Norfolk prospective population study showed any physical activity is better than none in older adults in preventing cardiovascular disease.

The EPIC Norfolk prospective population study showed any physical activity is better than none in older adults in preventing cardiovascular disease.

News | Cardiac Diagnostics| November 24, 2017
November 24, 2017 — Any physical activity in the elderly is better than none at all for reducing cardiovascular risk,
Analytics 4 Life Presents Clinical Data on Machine-Learned Cardiac Imaging Technology at TCT 2017
News | Cardiac Diagnostics| November 01, 2017
Analytics 4 Life announced it will be presenting new clinical data on the company's ongoing Coronary Artery Disease...
American Heart Association, Verily and AstraZeneca Launch One Brave Idea Science Innovation Center
News | Cardiac Diagnostics| October 20, 2017
The American Heart Association, Verily and AstraZeneca announced the opening of the One Brave Idea Science Innovation...
The Role of Telomere Length in Cardiovascular Risk Assessment
Feature | Cardiac Diagnostics| October 19, 2017 | Nanette H. Bishopric, M.D., FACC, FAHA
A new area of DNA testing involving telomere length may enhance a patient’s cardiovascular disease risk stratificatio
Overlay Init