New AI Tool Maps Heart Attack Recovery Paths to Personalise Care

The team compared the AI-generated trajectories with established clinical risk tools, including the SMART score.

A new AI tool has identified three distinct health trajectories among people recovering from a heart attack, using patterns in medical records to predict how their health may evolve over the following five years.

Researchers at the University of Surrey, England, have used temporal machine learning to identify different patterns of illness that can emerge after a heart attack.

The study analysed health records from 12,701 UK Biobank participants who had experienced an acute myocardial infarction and tracked the sequence and timing of diagnoses following the event.

The largest group, representing 63 per cent of participants, developed cardiometabolic conditions including hypertension, type 2 diabetes and dyslipidemia, alongside episodic heart and respiratory complications.

Another 23 per cent, associated with smoking-related risk, experienced deterioration involving the lungs, musculoskeletal system, and other organs. The remaining 14 per cent developed structural heart disease, arrhythmias, and kidney problems.

The differences between these groups were also reflected in mortality. The smoking-related trajectory had a mortality rate of 44 per cent, more than three times that of the largest cardiometabolic group.

Respiratory conditions, older age, and higher deprivation scores were among the key factors associated with the highest-risk trajectory.

Dr Anthony Onoja, lead author of the study and Research Fellow from the University of Surrey, said, "We found that we could predict the health trajectory a patient would follow after a heart attack, at the point of the event itself, using their pre-existing diagnoses and demographic data. Our AI tool was incredibly effective at finding and predicting the highest-risk group, where respiratory conditions, older age, and higher deprivation scores were key predictors.”

"Our approach is exciting, but we are still early in this journey, and we believe that in the future this could help hospitals identify people who follow these trajectories early and develop tailored care for them," he added.

The team compared the AI-generated trajectories with established clinical risk tools, including the SMART score.

Professor Nophar Geifman, senior author of the study from the University of Surrey, said, "Clinicians typically use risk assessments, such as the SMART score, to help them understand how likely a patient is to have another heart event. We found that these tools are still the strongest single predictor of mortality in our study, but the trajectories added detail that a stand-alone score cannot provide. The patterns we have identified show that we can capture more than just a patient's risk but, crucially, why and where intervention could be needed."

The approach remains at an early research stage and would require validation across other populations and healthcare settings before routine clinical use.

Stay tuned for more such updates on Digital Health News