AI can prevent hours of unnecessary testing for stable chest pain

A machine learning system can determine with near-perfect accuracy when further cardiac imaging tests are not necessary, saving patients and physicians time and money, according to research presented May 12 at the International Conference on Nuclear Cardiology and Cardiac CT.

In a study, cardiologists and the decision support system, called ARTificial Intelligence for clinical Cardiac nAvigation, or ARTICA, both examined 982 patients with stable chest pain. While the physicians determined that less than 5 percent of the patients could refrain from further testing, ARTICA advised no further testing for 67 percent.

After CT angiography scans were conducted on all the patients, 97 percent of those ARTICA said required no further testing were found to have no significant coronary artery disease, thus proving the AI correct. On average, ARTICA's recommendations could save healthcare providers one hour and patients two hours, plus the costs of pricey CTA scans.

However, ARTICA is less accurate when determining which patients do require further testing. "We know that when ARTICA says don't do a test it is almost 100 percent right," Marco Mazzanti, MD, study author and cardiologist at London's Royal Brompton Hospital, said in a statement. "When ARTICA decides a test is needed, we are less certain that this is correct. By adding more data to the 'super brain' these decisions will become more accurate and enable us to deliver more personalized care."

More articles about AI:
AI retinal scanner that can detect Alzheimer's given FDA 'Breakthrough Device' status
Harvard Business Review: Look at AI as a system-wide update, not a point solution
Catasys will use AI, human interaction to address loneliness epidemic

© Copyright ASC COMMUNICATIONS 2019. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Top 40 Articles from the Past 6 Months