Data and AI Updates
Our Theme News
Our research
Our research is focused on using artificial intelligence (AI), which is a type of computer technology that can think and learn like humans. AI is really good at noticing patterns, especially in big amounts of data. We use AI to look at electronic health records, which are digital versions of a patient’s medical history.
Aims
The main goal of our research is to find patterns that can tell us when people might get sick or have health problems, even before these issues become serious. We look for these patterns in two ways:
This means we try to find health risks that affect a lot of people, like how often a certain disease happens in a specific area.
This means we look at each person’s records to predict their personal health risks, like if someone is more likely to get diabetes because of their health history.
Patterns
By finding these patterns, we can help doctors and nurses do a few important things:
Spot health problems early: This helps them treat patients before their conditions get worse.
Plan better care for patients: Especially for those with many long-term health issues, which helps save time and resources.
Meet the Data and AI theme memebers
Zainab Awan
Artificial intelligence (AI) and data sciences in multiple long-term conditions, Data Scientist
Shaurya Pal
Artificial intelligence (AI) and data sciences in multiple long-term conditions, Research Assistant
Secure Data Environment
Data and AI Updates
Our Theme News
PhD Student Liyuan Zhu describes her experience at the October, NIHR SafetyNet Symposium, Manchester 2025
Research Assistant, Shaurya Pal give a run down on the Psoriasis Association Annual Meeting, that took place in June 2025 hosted in London.
PhD Student Henry Song reveiws his experience of the 2nd Annual PSRC Pharmacy Conference 2025
Determining the course and severity of aggressive skin cancers enabling medics to personalise treatment.
Reynolds DJ, Mountain S, Bartle V, Remfry E, Barnes MR, Reynolds NJ, Thompson A
Patient and Public Involvement and Engagement (PPIE) is critical in the development and application of Artificial Intelligence (AI) in healthcare research to ensure that outcomes align with patients’ and the public’s needs. However, current PPIE practices often limit involvement to reactive tasks such as reviewing documents and providing plain English summaries. Whilst important, this approach can sideline PPIE from influencing key research decisions. Consequently, PPIE interactions often fail to adequately reach and influence everyday decision makers. On AI and big data research projects, these decisions are often made by Early Career Researchers (ECRs) who play a vital role in the day-to-day research process. After realising these limitations, and to address them, the NIHR-funded AI MULTIPLY consortium introduced twice-monthly “ECRs meet PPIE” sessions.
Alexander H, Malek R, Prieto-Merino D, Gribaleva E, Baden M, Beattie P, Brown S, Burton T, Cameron S, Coker B, Cork MJ, Hearn R, Ingram JR, Irvine AD, Johnston GA, Lambert A, Lunt M, Man I, Newell L, Ogg G, Patel P, Wan M, Warren RB, Woolf R, Yiu ZZN, Reynolds N, Ardern-Jones MR, Flohr C.
The main conventional systemic treatments for atopic dermatitis (AD) are methotrexate (MTX) and ciclosporin (CyA). Dupilumab was the first novel systemic agent to enter routine clinical practice. There are no head-to-head randomized controlled trials or real-world studies comparing these agents directly. Network meta-analyses provide indirect comparative efficacy and safety data and have shown strong evidence for dupilumab and CyA.
This research shows real-world comparison of CyA, dupilumab and MTX in AD suggests that dupilumab is consistently more effective than MTX and that CyA is most effective in very severe disease within 1 year of follow-up.
Al-Janabi A, Alabas OA, Yiu ZZ, Foulkes AC, Eyre S, Khan AH, Reynolds NJ, Smith CH, Griffiths CE, Warren RB, BADBIR Study Group.
Risk of Paradoxical Eczema in Patients Receiving Biologics for Psoriasis
Biologics used for plaque psoriasis have been reported to be associated with an atopic dermatitis (AD) phenotype, or paradoxical eczema, in some patients. The risk factors for this are unknown.
Incidence rates of paradoxical eczema, paradoxical eczema risk by biologic class, and the association of demographic and clinical variables with risk of paradoxical eczema were assessed using propensity score-weighted Cox proportional hazards regression models.
Hussain AB, Singleton G, Ball S, Weatherhead SC, Reynolds NJ, Hampton PJ.
With increasing evidence supporting earlier treatment intervention in patients with psoriasis and the growing number of available biosimilars it is likely that our prescribing of biologic therapies will continue to rise.1 Studies published from the British Association of Dermatologists Biologics and Immunomodulators Register group have demonstrated long-term safety of biologic therapies in psoriasis.2 Nevertheless, 6-monthly blood monitoring is performed for patients with psoriasis prescribed biologic therapies in most UK centres. This is largely guided by the British Association of Dermatologists 2020 guidelines for biologic therapy for psoriasis3 that recommends monitoring full blood count, creatinine and electrolytes and liver function tests at initially 3–4 months after starting therapy, then 6 monthly, or as clinically indicated. Six-monthly blood monitoring has significant healthcare cost implications, creates a burden on patient time and has a substantial environmental impact. However, patients with psoriasis requiring biologic therapies have a considerable burden of multiple long-term conditions that must be carefully considered when determining an individual’s blood monitoring frequency.
Motedayen Aval L, Yiu ZZN, Alabas OA, Griffiths CEM, Reynolds NJ, Hampton PJ, Smith CH, Warren RB; BADBIR Study Group.
Interleukin (IL)-23p19 and IL-17 inhibitors have demonstrated high efficacy for psoriasis in randomized controlled trials, though real-world data, particularly for risankizumab (IL-23p19 inhibitor) and brodalumab (IL-17 receptor (IL-17R) inhibitor), is limited.
Guselkumab and risankizumab have the most favourable drug survival for effectiveness, with comparable safety to ustekinumab, and more favourable than other BADBIR biologics. Longer drug survival may reduce treatment burden by minimizing treatment switches, clinic visits and disease flares, supporting IL-23p19 inhibitors as a practical long-term option for psoriasis.