May 13 2019
Based on a study presented at International Conference on Nuclear Cardiology and Cardiac CT (ICNC) on May 12th, 2019, artificial intelligence (AI) can avoid unnecessary diagnostic tests in patients with stable chest pain. A decision support system can save 1 hour of testing for each patient.
The American Society of Nuclear Cardiology (ASNC), the European Association of Cardiovascular Imaging (EACVI) of the European Society of Cardiology (ESC), and the European Association of Nuclear Medicine (EANM) cocreated the ICNC.
We know that doctors overtest patients and ignore recommendations about when a test justified about two-thirds of the time. Our ‘super brain’ decision support system, called ARTICA, strictly follows ESC guidelines and does not advise unnecessary examinations.
Dr Marco Mazzanti, Study Author, Royal Brompton Hospital, London, UK
A total of 982 patients with stable chest pain, a common cause of visits to emergency departments and general practitioners, were enrolled in the study. A comparison was made by the scientists on the same day regarding the decisions on which tests to carry out, taken by a cardiologist and by ARTICA. ARTICA suggested no more testing in 658 (67%) patients, whereas a cardiologist took a decision that only 45 (4.6%) patients did not require further tests.
A computed tomography angiography (CTA) scan revealed that 639 (97%) of the patients whom ARTICA suggested did not need tests had no significant coronary artery disease, that is, the decision was correct. By avoiding these tests, staff saved 1 hour and patients 2 hours on average.
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.
Dr Marco Mazzanti, Study Author, Royal Brompton Hospital, London, UK
For example, a CTA scan, used to search blocked blood vessels, costs €200–400. It was recommended by cardiologists for 816 (83%) patients and by ARTICA for just 95 patients (10%).
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.
Dr Marco Mazzanti, Study Author, Royal Brompton Hospital, London, UK
He found that exercise testing or functional imaging was suggested by ARTICA for 224 (23%) patients and by cardiologists 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. 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.
Dr Marco Mazzanti, Study Author, Royal Brompton Hospital, London, UK
ARTICA (ARTificial Intelligence for clinical Cardiac nAvigation) is a decision support system developed by the scientists, which uses machine learning, a kind of AI, for decision making according to the recommended practice. The scientists stored guidelines for patients with stable chest pain and frequently gathered medical data. The details were analyzed constantly using a machine-learning algorithm until it determined whether or not a patient required a test (and which test).