AI tool could help heart attack survivors receive tailored care, say experts
The health of heart attack survivors follows three distinct paths in the five years after their heart attack, say researchers from the University of Surrey. The research used an AI tool to find patterns that could not only help clinicians predict which path patients might follow but also allow them to tailor care sooner during recovery.
A new AI tool could help healthcare providers deliver personalized care to heart attack survivors, according to experts from the University of Surrey. The researchers used artificial intelligence to identify three distinct health trajectories that patients typically follow in the five years after a heart attack. The study, published in the Journal of the American Medical Informatics Association, analyzed health records of 12,701 UK Biobank participants who experienced a heart attack.
The AI tool found that 63% of patients developed cardiometabolic conditions, such as hypertension, type 2 diabetes, and dyslipidemia, along with episodic heart and respiratory complications. Meanwhile, 23% of patients suffered declines in the lungs, musculoskeletal system, and other organs, particularly among those who continued to smoke. Around 14% of patients developed structural heart diseases, arrhythmias, and kidney problems.
Dr. Anthony Onoja, lead author of the study and research fellow at the University of Surrey, stated that the AI tool could predict a patient's health trajectory immediately following a heart attack using their pre-existing diagnoses and demographic data. The team believes that this approach could enable hospitals to identify patients in the early stages of these trajectories and provide tailored care to prevent further complications.
The researchers also investigated the biological basis of these trajectories. Genetic analysis showed that each group mapped to distinct molecular pathways. For instance, the largest group (63%) exhibited immune activation and tissue remodeling, while the arrhythmia group was linked to insulin signaling and lipid transport. The smoking-related group showed chronic inflammation and degeneration.
Professor Nophar Geifman, senior author of the study, noted that while traditional risk assessments, such as the SMART score, are still the most effective predictors of mortality, the AI-generated trajectories provide additional insights into why and where interventions are needed. The study suggests that clinicians can now not only assess a patient's risk but also understand the underlying biological mechanisms for more targeted and effective care.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
