Lead Health Data Scientist
- Alan Turing Fellow 2021-2022
- CPRD fob holder for NDORMS
- Big Health Data group co-chair
- EHDEN UK data science technical lead
- EHDEN OMOP common data model specialist
I am a computer scientist and software engineer at the Centre for Statistics in Medicine at NDORMS. I am responsible for the automation of data engineering, data mining and advanced curation of real-world health data routinely collected by GPs (e.g. Clinical Practice Research Datalink - CPRD - GOLD and Aurum), hospitals (e.g. Hospital Episode Statistics - HES) and registries (e.g. Office for National Statistics - ONS - Mortality, etc.)
I am passionate about the impact of algorithmic automation on real-world data management, its role in the statistical process and its impact on medical research. My main interests are:
- performance and competitiveness
- assessment, measurement and enhancement of real-world clinical data quality
- research quality, consistency, reproducibility and transparency
My aim is to make best use of clinical real-world data by developing robust, transparent and automated processes regulated and documented by standard operating procedures.
I graduated in Computer Science at Udine University and completed my PhD in Information and Communication Technologies at Trento University, Italy. I have worked for several years in companies developing firmware and software for electronic devices.
In 2006 I moved to the U.K. to join the Clinical Trial Service Unit (CTSU) at Oxford University. My biggest achievement in this role was the whole IT management of ATLAS (Adjuvant Tamoxifen Longer Against Shorter), a long-term early breast cancer randomised controlled clinical trial. ATLAS involved more than 15,000 women recruited from over 600 sites in more than 20 countries worldwide, and its findings on patients' survival and recurrence using 5 versus 10 years of Tamoxifen changed clinical practice in the UK and worldwide.
In 2013 I joined NDORMS to lead the big data management of the Epidemiology Unit, and I started developing Curator, a data science tool for clinical real-world data, which has allowed for the delivery of more than twenty observational studies so far. In 2017 I was given solo responsibility for the NDORMS CPRD fob. In 2018 I became co-char of the Big Health Data Group and I joined the European Health Data and Evidence Network (EHDEN) collaboration. In 2019 I became responsible for OHDSI UK Data Science activities.