AI-Powered Gene Discovery Personalizes Psoriasis Treatment
Recent research from King’s College London has leveraged artificial intelligence to unlock novel insights into psoriasis, paving the way for personalized treatment strategies. By combining machine learning with genetic analysis, scientists have identified key biological pathways that could lead to more effective, targeted therapies for individuals living with this chronic skin condition.
Understanding Psoriasis
Psoriasis is a common inflammatory skin disease affecting approximately 1 in 50 people in the UK 1. Severe psoriasis significantly impacts quality of life and is often linked to long-term health conditions such as heart disease and Type 2 diabetes.
A significant challenge in treating psoriasis is that current, high-cost treatment options, like biologics, often fail without a clear reason, creating a burden on healthcare systems 1.
AI and Gene Discovery in Psoriasis
Researchers from King’s, Newcastle University, and Queen Mary University of London utilized advanced Machine Learning to identify several subtypes of psoriasis based on how an individual’s genes impact disease severity. This classification provides clinicians with a better understanding of why current treatments may fail, potentially leading to more personalized approaches 1, 3.
The team analyzed over 700 blood samples from more than 140 patients with moderate to severe psoriasis over an extended period. This analysis mapped how genes interact, both individually and within evolving networks, with other biological factors, such as Body Mass Index (BMI), to compare disease severity with common biological treatments 3.
Researchers identified a nine-gene biomarker linked to psoriasis severity and specific genetic variants associated with more severe baseline disease. They also discovered a 14-gene signature associated with BMI in unaffected skin and with disease severity in affected skin with lesions 3.
Dr. David Watson, Lecturer in Artificial Intelligence and joint first author of the study, explained, “Diseases that present the same are often completely different. Breast cancer, for example, is not one, but a thousand different diseases all under the same label. To be able to develop targeted treatments, you need to understand how all these different diseases work, or risk ‘fat-fingered’ interventions like chemotherapy, which can have large side effects 3.”
“Until now, we didn’t have that with psoriasis. But by using RNA sequencing and AI modelling, we can now 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,” Dr. Watson added 1.
Dr. Watson also noted the broader implications of this research, stating, “There are many immune-mediated inflammatory diseases, like rheumatoid arthritis and Crohn’s. And while they present differently, we know they are genetically linked – having one increases the risk of passing another to your kids 3.”
“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. If we can categorise the gene expression there too, we could potentially design personalised treatments for all these ailments which plague patients and cost our healthcare system millions,” Dr. Watson concluded 3.
The Role of AI in Dermatology
Machine learning (ML), a subset of artificial intelligence (AI), is increasingly vital in dermatology, offering significant advancements in healthcare delivery 2. AI is reshaping psoriasis care in several key areas, including diagnosis through image analysis, skin severity quantification, biomarker identification, and precision medicine enhancement 2.
The successful integration of AI in dermatology relies on dermatologists’ oversight to ensure its potential is fully realized in patient care, preserving the essential human element in medicine 2.
Worth a look