Scientists in the UK have developed an artificial intelligence system that can analyze the medical test results of patients with a heart disorder and accurately predict their lifespan over the following years.

Researchers at the London Institute of Medical Services focused their study on patients suffering from pulmonary hypertension, a disease that kills around one-third of patients within the first five years of being diagnosed.

The predictive software processed blood tests, MRI heart scans, and the general medical records from 256 patients with newly diagnosed pulmonary hypertension. 3D models of a patient's right ventricular structure were then constructed using approximately 30,000 datapoints, allowing the software to closely identify the presence of any abnormalities.

Using this 3D image of the patient's heart the system can replicate how the organ contracts during each individual beat as seen in the video below.

Based on the data the software could then predict patient mortality rates up to five years in the future. The system accurately predicted which patients would be alive in one year with about 80 percent accuracy. Previous human predictions using the same dataset had only achieved an accuracy rate of 60 percent.

Speaking to BBC News, Dr Declan O'Regan claimed the system is designed to help doctors target their treatment programs for specific patients, "So we can tailor getting absolutely the right intensive treatment to those who will benefit the most."

These types of computer-aided diagnostics are currently being developed by numerous medical researchers around the world to help doctors crunch large volumes of medical test data. One project from the Beth Israel Deaconess Medical Centre in Boston even developed a system that claimed a 96 percent accuracy rate in predicting a patient's probability of dying within the next 30 days.

While the ethical concerns surrounding how hospitals or insurance companies could use these types of diagnostic predictions are yet to faced, it is clear that computer-aided diagnostics will be vital in helping clinicians develop targeted treatments for patients with a new level of speed and accuracy.