Tell us about your data science career so far?
I started my data science career at Blackpool CCG before moving on to Leeds CCG as a Senior Data Scientist, a role which later transitioned into West Yorkshire ICB. My most recent role was with Arden and GEM CSU as a Principal Data Scientist. Earlier in my career, I also worked as a Data Scientist at the Driver and Vehicle Standards Agency.
Tell us about a recent project you worked on where data analytics played a key role?
At an ICB I worked on several projects focused on children and young people’s mental health services, particularly exploring the reasons why many disengage from support when they turn 18.
By analysing data from an 800,000-strong population, we traced patient histories from primary to secondary care and uncovered key insights about the challenges young people face in accessing services as they transition to adulthood. This included understanding sociodemographic factors and identifying vulnerable groups who are more likely to disengage.
I also worked on projects related to IAPT (Improving Access to Psychological Therapies), looking at groups who weren’t accessing primary care but instead resorted to self-harm, leading to secondary care admissions. Data insights helped inform targeted interventions and improve support for these individuals.
Tell us one thing we might not know about Project Athena
While many see our advanced analytics model for fraud detection as innovative, similar techniques have been used by banks for years to detect fraud. The difference is that we’re adapting this proven approach for the healthcare sector, ensuring that resources are protected and directed to where they’re needed most.
How important are patients in the work that you do?
Although my work often involves technical tasks such as setting up servers or analysing large data sets, it’s always with the patient in mind. Every insight we generate helps protect NHS resources and ensures that funds are spent where they will make the most impact—on patient care.
Project Athena uses machine learning to help detect large scale NHS fraud. How is machine learning having an impact across the NHS?
Machine learning is already having a significant impact across the NHS, particularly in cancer detection. By analysing medical images, machine learning systems can identify patterns that may indicate the presence of cancer. These systems are trained on thousands of scans, learning to recognise features like unusual shapes or tissue densities. When new images are analysed, the algorithm compares them, flagging areas of concern for a radiologist to review. This approach increases the accuracy of diagnoses by detecting subtle changes that might be missed by the human eye, ultimately supporting earlier detection, and reducing error rates.
Can machine learning work in isolation?
No, machine learning cannot work in isolation. It relies on the expertise of subject matter experts to interpret findings and apply the correct approach. In Project Athena, our systems will use machine learning to detect fraud by analysing patterns in data. Just as machine learning identifies unusual shapes in medical scans, our system will flag suspicious activities based on known fraud patterns. While this improves detection accuracy and reduces error rates, it still requires someone like a member of our Project Athena response team to apply their expertise. What may seem like an anomaly to the system could be explained by a subject matter expert with deeper knowledge.
Tell us something we wouldn’t know about you?
Since a young age, I've been fascinated by the universe, which led me to pursue a master's degree in physics with astronomy and cosmology, followed by a PhD in solar physics. These academic experiences have shaped my approach to problem-solving and data analysis, skills that I continue to apply in my career today.