Oxford researchers develop AI tool to map hidden effects of high blood pressure

Researchers identified six patterns of hypertension-related organ damage using AI.

AI could help uncover hidden organ damage caused by high blood pressure.

Researchers led by the University of Oxford have developed an AI tool called ‘HyperScore’ that could help doctors better understand how high blood pressure affects different organs and individuals in different ways. The approach could support more personalised treatment strategies in the future.

Using the AI tool, researchers identified six distinct patterns of hypertension-related disease by analysing hundreds of measurements, including cardiac imaging, brain MRI scans, blood tests and assessments of the kidneys, liver and vascular system.

The study found that individuals with higher HyperScores faced a greater risk of future cardiovascular events, even when conventional blood pressure measurements did not fully capture that risk. Changes detected through brain MRI imaging emerged as some of the strongest indicators of hypertension-related organ damage.

The researchers analysed data from more than 27,000 participants in the UK Biobank and validated their findings in an additional cohort of more than 5,500 individuals in the US. The researchers cautioned that the approach remains at an early stage and is not yet ready for routine clinical use in the UK.

Why does it matter?

High blood pressure is one of the world’s leading risk factors for heart disease, stroke and other chronic conditions, yet patients with similar blood pressure readings can experience very different health outcomes. The study suggests that AI may help identify hidden patterns of organ damage that are not captured by conventional measurements, potentially enabling more accurate risk assessment and personalised treatment strategies.

The research also highlights the growing role of AI in precision medicine. By combining imaging, laboratory data and clinical information, AI systems may help clinicians move beyond one-size-fits-all approaches to disease management. Although HyperScore remains at an early research stage, the findings demonstrate how AI could support earlier intervention and more targeted care for patients with complex cardiovascular risks.

Would you like to learn more about AI, tech and digital diplomacy? If so, ask our Diplo chatbot