Researchers from the Universities of Cambridge, Bristol and Edinburgh have suggested that COVID-19 vaccinations could lower the incidence of arterial thromboses.

The study was supported by the British Heart Foundation (BHF) Data Science Centre at Health Data Research UK.

Researchers analysed the de-identified health records of 46 million adults from GP practices, hospital admissions and death records in England between December 2020 and January 2022, provided by NHS England.

The team compared the incidence of cardiovascular diseases (CVDs) following COVID-19 vaccination with the incidence before or without vaccination during the first two years of the vaccination programme.

CVD affects around seven million people in the UK and is a significant cause of disability and death.

Overall, the study revealed that the incidence of arterial thromboses, such as heart attacks and strokes, which affect 200,000 people in the UK every year combined, was up to 10% lower in the 13 to 24 weeks after the first dose of COVID-19 vaccine.

Following a second dose, the incidence increased to a 27% lower incidence after receiving the AstraZeneca vaccine and up to 20% lower following the Pfizer/BioNtech vaccine.

Additionally, the incidence of venous thrombotic events, such as pulmonary embolism and lower limb deep venous thrombosis, demonstrated a similar pattern.

Researchers from King’s College London have developed a new artificial intelligence (AI) brain imaging model in collaboration with University College London (UCL) that is realistic and accurate enough to use in medical research.

The three-dimensional, synthetic images of the human brain could help support research to predict, diagnose and treat brain diseases including dementia, stroke and multiple sclerosis.

According to Brain Research UK, there are an estimated 11 million people in the UK who are living with a neurological condition. Among the most common are Alzheimer’s disease, epilepsy and stroke.

In collaboration with the London Medical Imaging and AI Centre for Value-Based Healthcare and NVIDIA data scientists and engineers, researchers trained the AI model in weeks as opposed to months using the NVIDIA Cambridge-1 supercomputer.

The model is able to produce 3D, high-resolution images that have all the characteristics of real human brains, including correct folding patterns and regions of the risk size, while also accurately producing images that reflect clinical factors such as age, sex or disease status.

After looking at large volumes of data, the AI model learned how age and sex affect the brain, as well as how pathologies impact anatomy. When tested, the data produced by the model was realistic enough to replicate human anatomy.

Researchers believe this tool could help to make AI diagnosis more accurate and equitable and help neuroscientists better understand how brains change with age and with disease, which could lead to treatments for critical conditions.