Scientists at the Imperial College London have developed a software which creates virtual 3D hearts by replicating the real organ and predicts the time of heart failure.
The artificial intelligence heart, which is created after analyzing MRI images of a patient's heart and his/her blood tests, automatically learns the features and predicts the time of the organ's failure. The software has been demonstrated to have an accuracy of about eighty percent.
The technology has been tested on patients with pulmonary hypertension, a condition which leads to heart failure if not treated appropriately and in time. However, the type of required treatment depends on predicting which risk group (high or low) patients fall into. The results of the new study show that this machine learning technique is faster and more accurate at making predictions than current methods.
Dr. Declan O'Regan, the lead author of the study from the MRC London Institute of Medical Sciences (LMS) at the Imperial College London, said that this is the first time computers have interpreted heart scans to accurately predict the life of patients. The scientists say this technology could transform the way doctors treat patients and can also be used on patients with other types of heart diseases.
Pulmonary Hypertension
There are around 7000 victims of pulmonary hypertension in the UK. The condition is characterized by high pressure in vessels that supply blood to the lungs. The disease puts strain on the right side of the heart causing progressive damage over time, and ultimately leading to heart failure if not treated. A maximum of one-third of patients die within five years of diagnosis.
Treatment for pulmonary hypertension, which includes medication to allow a more easy blood flow through the lungs, helps patients to live longer. The present treatment methods, in contrast with the new method, include time-consuming measurements of heart function by hand to identify patients at greatest risk of deteriorating.
The team of researchers plan to test the software on patients from different hospitals to verify the findings.