A new method that uses deep learning to analyze vast amounts of personal health record data could identify early signs of heart failure, researchers say.
A paper, which appears in the Journal of the American Medical Informatics Association (JAMIA), describes how the method addresses temporality in the data—something previously ignored by conventional machine learning models in health care applications.
The research uses a deep learning model to allow earlier detection of the incidents and stages that often lead to heart failure within 6-18 months. To achieve this, researchers use a recurrent neural network (RNN) to model temporal relations among events in electronic health records.
Temporal relationships communicate the ordering of events or states in time. This type of relation is traditionally used in natural language processing. However, researchers saw a new opportunity to leverage the power of RNNs.
“I studied deep learning and I was wondering if RNNs could be introduced into health care. It is a very popular model for processing sequences and is traditionally used for translation,” says Edward Choi, a PhD student at Georgia Tech, working with Jimeng Sun, an associate professor at the School of Computational Science and Engineering.
By utilizing RNN, the algorithm can anticipate early stages of heart failure, which will ultimately lead to better preventative care for patients at risk of heart disease.
“Machine learning is being used in every aspect of health care. From diagnosis and treatments to recommendations for patient care after surgeries. This particular model is focused on deep learning, which has had great success in many industries. However, in health care, we are on the front of pioneering deep learning and Edward is one of the first ones to apply it,” Sun says.
‘Deep learning’ goes faster with organized data
According to the Centers for Disease Control and Prevention, heart failure affects 5.7 million adults in the United States, and half of those who develop heart failure die within 5 years of diagnosis costing the nation an estimated $30.7 billion each year.
The new findings could provide relief to millions of Americans each year by allowing doctors to offer patients early intervention.
“This is a preliminary work, it showed potential that it can do better than classical models—it makes a good promise for how deep learning can make a positive impact in the health care industry,” says Choi.
The National Institutes of Health in collaboration with Sutter Health funded the work.
Source: Georgia Tech