Personalised psoriasis treatments – insights from AI

The severity of psoriasis can be linked to genes, new research using machine learning suggests, supporting the possibility of more tailored treatments.

Psoriasis is a chronic inflammatory skin condition triggered by the body's immune response, causing skin cells to replace themselves more rapidly than normal and resulting in scaly, itchy patches. While psoriasis affects one in 50 people in the UK, it remains difficult to determine which factors contribute to differences in disease severity or whether individuals will develop related diseases. UK researchers combined machine learning and genetic analysis to categorise psoriasis into several subtypes, linking specific genes to the disease's severity.

'Diseases that present the same are often completely different,' explained Dr David Watson, from the Department of Informatics at King's College London and joint first author of the study published in Nature Communications Medicine. 'To be able to develop targeted treatments, you need to understand how all these different diseases work.'

In collaboration with colleagues at Newcastle University and Queen Mary University of London, the researchers analysed skin and blood samples from 146 patients with moderate to severe psoriasis. They looked at how different genes interacted with other factors, such as body mass index (BMI), to influence how severe the disease was.

They discovered a set of nine genes that can act as a marker of how severe someone's psoriasis is, and a set of 14 genes connected to BMI in healthy skin and to disease severity in affected skin.

The results mean it is now possible to 'categorise how genes affect the trajectory of psoriasis and group the disease into several sub-types as a prerequisite for better treatment – helping better deal with the most severe cases,' said Dr Watson. He and his co-authors hope their research may help explain why certain treatments – which are costly for the NHS – sometimes do not work.

Severe psoriasis can have a serious impact on quality of life, and can sometimes lead to the development of other health problems, such as psoriatic arthritis, cardiovascular disease, and metabolic syndrome, which in turn may reduce life expectancy.

Other inflammatory conditions, including Crohn's disease, are similarly influenced by genetics and can run in families. In the future, Dr Watson and his colleagues hope their findings will extend beyond psoriasis to these other conditions.

'This is a complex world, and by figuring out how genes influence the path of one inflammatory disease, we hope to take this learning and apply it to a host of different diseases and see how they materialise in patients,' he said.