Machine learning is overtaking humans in predicting death and heart attack, suggesting a continued maturation of the technology and a potential for increased efficiency among caregivers in the healthcare system, finds a study presented at the International Conference on Nuclear Cardiology and Cardiac.
By repeatedly analysing 85 variables in 950 patients with known six-year outcomes, an algorithm "learned" how imaging data interacts. It then identified patterns correlating the variables to death and heart attack with more than 90 percent accuracy.
Machine learning, the modern bedrock of artificial intelligence, is used every day. Google's search engine, face recognition on smartphones, self-driving cars, Netflix and Spotify recommendation systems all use machine learning algorithms to adapt to the individual user.
Study author Dr. Luis Eduardo Juarez-Orozco said these advances go above and beyond what has presently been achieved in medicine, where providers need to be cautious when weighing risks and outcomes. The data, she said, is not yet being used to its full potential.
Doctors use risk scores to make treatment decisions. But these scores are based on just a handful of variables and often have modest accuracy in individual patients. Through repetition and adjustment, machine learning can exploit large amounts of data and identify complex patterns that may not be evident to humans.
The study enrolled 950 patients with chest pain who underwent the center's usual protocol to look for coronary artery disease. A coronary computed tomography angiography (CCTA) scan yielded 58 pieces of data on presence of coronary plaque, vessel narrowing, and calcification. Those with scans suggestive of disease underwent a positron emission tomography (PET) scan which produced 17 variables on blood flow. Ten clinical variables were obtained from medical records including sex, age, smoking and diabetes.
During an average six-year follow-up there were 24 heart attacks and 49 deaths from any cause. The 85 variables were entered into a machine learning algorithm called LogitBoost, which analysed them over and over again until it found the best structure to predict who had a heart attack or died.
The predictive performance using the 10 clinical variables alone -- similar to current clinical practice -- was modest, with an area under the curve (AUC) of 0.65 (where 1.0 is a perfect test and 0.5 is a random result). When PET data were added, AUC increased to 0.69. The predictive performance increased significantly when CCTA data were added to clinical and PET data, giving an AUC 0.82 and more than 90 percent accuracy.
AI and machine learning have a number of potential applications in healthcare, including even the revenue cycle. AI could be transformational in predicting denials, for example, by getting down to the reasons and then preventing the problem before it happens.
ON THE RECORD
"Doctors already collect a lot of information about patients -- for example, those with chest pain," said Juarez-Orozco. "We found that machine learning can integrate these data and accurately predict individual risk. This should allow us to personalise treatment and ultimately lead to better outcomes for patients."