AI technology analyses chest X-rays for long-term mortality

22 July 2019 (Last Updated December 23rd, 2019 10:22)

Massachusetts General Hospital (MGH) scientists have developed new artificial intelligence (AI) technology that analyses chest X-rays for prognostic information on long-term health and mortality.

AI technology analyses chest X-rays for long-term mortality
Previously, AI was leveraged for automated diagnosis of pneumonia and tuberculosis using chest X-rays. Credit: Stillwaterising.

Massachusetts General Hospital (MGH) scientists have developed new artificial intelligence (AI) technology that analyses chest X-rays for prognostic information on long-term health and mortality.

The team believes that the technology could help in predicting which individuals would benefit from screening and preventive treatment for a variety of conditions, including heart disease and lung cancer.

Previously, AI was leveraged for automated diagnosis of pneumonia and tuberculosis using chest X-rays.

In the latest research, scientists designed a convolutional neural network called CXR-risk to examine visual information. It was trained using more than 85,000 chest X-rays from 42,000 clinical trial subjects.

The team paired each image with data about the person’s survival over a 12-year period. This was intended to enable the AI technology to identify chest X-ray features that best predict health and mortality.

A study involving chest X-rays of 16,000 participants from two prior trials showed that 53% of the people identified as ‘very high risk’ by CXR-risk died over 12 years.

In cases of individuals identified as ‘very low risk’, less than 4% went on to die, said the team.

According to the study findings, the neural network provided information predicting long-term mortality, independent of radiologists’ readings and other factors such as age and smoking status.

A combination of the new technology with other risk factors, including genetics and smoking status, is expected to offer more accurate predictions, allowing earlier diagnosis, prevention and treatments.

MGH Division of Cardiovascular Imaging research director Michael Lu said: “This is a new way to extract prognostic information from everyday diagnostic tests. It’s information that’s already there that we’re not using, that could improve people’s health.”

Findings from the study are set to be published in the JAMA Network Open journal.