AI models predicts mortality risk from CAD better than physicians

A model using artificial intelligence (AI) can better predict the risk of mortality in patients with coronary artery disease (CAD), compared to models designed by medical experts, according to a new study published in PLOS One.

A lot of AI-related research has been to diagnose and treat various diseases, but these findings may now help predict mortality risk in patients with CAD.

“Eventually, machine learning approaches combined with EHR may make it feasible to produce fine-tuned, individualized prognostic models, which will be particularly valuable in patients with conditions or combinations of conditions which would be very difficult for conventional modelling approaches to capture,” wrote lead author Andrew J. Steele, PhD, of the Francis Crick Institute in London.

Steele and colleagues, along with contributors from the Farr Institute of Health Informatics Research and University College London Hospitals NHS Foundation Trust, designed the AI model for CAD using the electronic health data of more than 82,000 patients.

The researchers trained their model to predict cardiac predictions based on 586 variables including age, gender and chest pains. Their model was compared to an “expert-constructed model,” with only 27 variables.

Steele and colleagues’ AI algorithm trained itself and was more accurate in predicting patient mortality risk while identifying new variables that were previously not included in physician predictions.

“Along with factors like age and whether or not a patient smoked, our models pulled out a home visit from their GP as a good predictor of patient mortality,” Steele said in a prepared statement issued by the Francis Crick Institute. “Home visits are not something a cardiologist might say is important in the biology of heart disease, but perhaps a good indication that the patient is too unwell to make it to the doctor themselves, and a useful variable to help the model make accurate predictions.”

The researchers noted similar models could potentially be implemented in clinics in the future and could revolutionize how providers deliver care to patients.

“Eventually, machine learning approaches combined with EHR may make it feasible to produce fine-tuned, individualized prognostic models, which will be particularly valuable in patients with conditions or combinations of conditions which would be very difficult for conventional modelling approaches to capture,” the authors concluded.

""

As a senior news writer for TriMed, Subrata covers cardiology, clinical innovation and healthcare business. She has a master’s degree in communication management and 12 years of experience in journalism and public relations.

Trimed Popup
Trimed Popup