Using artificial intelligence on patients with stable chest pain could save hospitals time and money because it can prevent unnecessary diagnostic tests, a UK study has found.
Delegates at the International Conference on Nuclear Cardiology and Cardiac CT in Lisbon, Portugal, yesterday (12 May 2019) heard that using ARTICA, a decision support system that follows ESC guidelines, drastically reduced the need for additional tests.
A study, led by Dr Marco Mazzanti, of the Royal Brompton Hospital, London, enrolled 982 patients with stable chest pain and the researchers compared decisions made on a single day by cardiologists and ARTICA on which tests should be carried out on patients.
ARTICA, which stands for ARTificial Intelligence for clinical Cardiac nAvigation, advised that 67% of patients (658) required no further tests, while cardiologists ruled out more testing in 4.6% (45) patients.
ARTICA said that 639 (97%) of the patients did not need tests and CT tests showed they had no significant coronary artery disease, the conference heard. Cardiologists recommended it for 816 (83%) patients while ARTICA recommended it for just 95 patients (10%). Avoiding those further tests would save, on average, staff one hour and patients two hours.
Dr Mazzanti said: “We know that doctors over-test patients and ignore recommendations about when a test justified about two-thirds of the time.
“AI has the potential to save costs and staff time by identifying patients with chest pain who do not have significant coronary artery disease and therefore do not need expensive cardiac imaging.
“As doctors we order a lot of tests which cost a lot of money and waste time. ARTICA is like a second set of eyes to make sure we follow recommendations.”
He added that ARTICA recommended exercise testing or functional imaging for 224 (23%) patients while cardiologists recommended it for just 100 (10%) patients.
“We know that when ARTICA says don’t do a test it is almost 100% right because the CTA scan confirmed no blocked arteries,” he said.
“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 personalised care.”
ARTICA uses machine learning to make decisions based on recommended practice. The researchers inputted guidelines for patients with stable chest pain and routinely collected medical data. A machine learning algorithm analysed the information repeatedly until it learned to identify who needed a test, and which test, and who did not.
Abstract: Cost analysis of cardiac imaging using artificial intelligence in subjects with stable chest pain. Results from the ARTICA database
Leave a Reply