AI Boosts Patient Risk Prediction Accuracy

Researchers use machine learning to improve cardiovascular disease risk assessment

Jan. 28, 2026 at 10:55pm

Got story updates? Submit your updates here. ›

Researchers at the University of Missouri School of Medicine have developed a machine learning model that can more accurately predict a patient's risk of major adverse cardiac events (MACE) compared to traditional statistical models. The model was trained on data from positron emission tomography (PET) scans of patients with coronary artery disease, allowing it to handle complex relationships between variables that traditional models struggle with.

Why it matters

Accurately identifying high-risk patients is crucial for providing personalized care and maintaining quality of life. Cardiovascular disease remains the leading cause of death worldwide, so improving risk assessment tools can help save lives.

The details

The researchers' machine learning model used data from advanced nuclear scans to determine a patient's risk of MACE, which includes events like heart attacks and strokes. This allowed the model to leverage more data and better understand the complex relationships between variables compared to traditional statistical models. The researchers say this approach can be applied to other diseases as well to improve prognostic risk assessment.

  • The study was recently published ahead of print in the Journal of Nuclear Cardiology.

The players

Fares Alahdab

An associate professor of Biomedical Informatics, Biostatistics, and Epidemiology and of Cardiology at the Mizzou School of Medicine, as well as the Director of Graduate Programs in Health Informatics.

Ahmed Ibrahim Ahmed

A study co-author from Houston Methodist DeBakey Heart & Vascular Center.

Mahmoud Al Rifai

A study co-author from Houston Methodist DeBakey Heart & Vascular Center.

Mouaz Al-Mallah

A study co-author from Houston Methodist DeBakey Heart & Vascular Center.

Radwa El Shawi

A study co-author from the University of Tartu in Estonia.

Got photos? Submit your photos here. ›

What they’re saying

“Our model assigned patient risk of MACE more accurately than other predictive models that interpret data. This can help optimize individual care for the patient.”

— Fares Alahdab, Associate Professor (Mirage News)

“We trained our model on information from advanced nuclear scans of patients with coronary artery disease, and some of these methods can be applicable to other diseases as well.”

— Fares Alahdab, Associate Professor (Mirage News)

“Identifying patients most at-risk for adverse health events is crucial for personalizing their care plan and maintaining their quality of life.”

— Fares Alahdab, Associate Professor (Mirage News)

The takeaway

This study demonstrates how machine learning can be leveraged to improve risk prediction models in healthcare, leading to more personalized and effective care for patients with cardiovascular disease. The approach used here could potentially be applied to other medical conditions as well.