New Software Creates Virtual 3-D Hearts to Help Better Guide Treatment

Scientists at Imperial College London have designed software that creates virtual 3-D versions of patients’ heart motion, helping doctors to determine likely outcomes in patients with pulmonary hypertension (PH) with greater accuracy, and possibly improve their treatment.

The technology uses cardiac magnetic resonance imaging (MRI), blood tests, and other clinical observations, according to the study, “Machine Learning of Threedimensional Right Ventricular Motion Enables Outcome Prediction in Pulmonary Hypertension: A Cardiac MR Imaging Study.” It was published in the journal Radiology.

“This is the first time computers have interpreted heart scans to accurately predict how long patients will live. It could transform the way doctors treat heart patients,” lead author Declan O’Regan, PhD, of the MRC London Institute of Medical Sciences (LMS) at Imperial College London, said in a news release.

Researchers used data from 256 recently diagnosed PH patients to test the software. The patients underwent cardiac MRI, right-sided heart catheterization, and 6-minute walk testing (a test of exercise ability), with a median follow-up of four years.

The software analyzed the MRI images, and it copied the way more than 30,000 points in the patients’ hearts contracted with each beat. It then created a virtual 3-D heart for each patient and learned which features were indications of heart failure.

When used in conjunction with conventional imaging and hemodynamic, functional, and clinical markers, the virtual 3-D heart led to better survival predictions, and it improved differentiation in median survival time between patients in high- and low-risk groups.

“The computer performs the analysis in seconds and simultaneously interprets data from imaging, blood tests and other investigations without any human intervention. It could help doctors to give the right treatments to the right patients, at the right time,” said Tim Dawes of the LMS, who developed the software algorithms.

The technology could eventually be used to predict the outcomes of patients with other heart conditions.

“We would like to develop the technology so it can be used in many heart conditions to complement how doctors interpret the results of medical tests. The goal is to see if better predictions can guide treatment to help people to live longer,” Dawes said.

The researchers plan to test the software using data from a different hospital. The goal isto not only predict survival, but also predict which treatment would best benefit each patient.