Applications are invited for a Statistician/Machine learning Engineer/Data Analyst to join the fast-growing Haematology Data Science Initiative (HDSCI), which comprises two major research projects Haem-Match (www.haemmatch.org) and BloodCounts! (www.bloodcounts.org).

Candidates should have a degree or equivalent experience or qualification in Informatics or Software Engineering, Mathematics, Computer Science or Systems Engineering at Bachelor level. They should also have experience of database and data warehouse design, experience of preparing detailed technical documentation, and knowledge of data modelling. Experience of managing large heterogenous datasets, experience with data analysis, hypothesis testing and algorithm evaluation essential.

The post holder will be working within the Clinical Research Informtics Unit (CRIU) which has also established collaborations with the Alan Turing Institute and Health Data Research UK, among others. This milieu will allow the post-holder to gain exposure to broad aspects of data science, both operational and research, including electronic health records, -omics, imaging, wearables, natural language processing, machine learning, artificial intelligence, and information governance.

Main duties of the job

The HDSCI project, coordinated through University of Cambridge, UCLH BRC, NHS Blood and Transplant and part of a larger international collaboration, is embedded in the CRIU and the postholder will be a member of the multidisciplinary HDSCI team, which includes clinical bioinformaticians, experts in statistical genomics, blood cell immunogenicity and randomised controlled trials, clinical haematologists caring for patients with inherited anaemias, and researchers in Artificial Intelligence & Machine Learning (AI& ML).

BloodCounts! brings together a network of experts across clinical, quantitative science and corporate enterprises to apply artificial intelligence to analyse routine clinical haematology data and turn them into a broad surveillance network to detect infectious disease outbreaks without the need for any new instruments or reagents. The post holder will:o Consolidate receive, decrypt and QC data necessary for the project.o Apply AI& ML to Full Blood Count (FBC) results with the aim of discovering signatures of important medical conditions (e.g., viral infection [incl. SARS- CoV- 2], iron-deficiency anaemia vs thalassaemia trait, thrombotic thrombocytopenic purpura and haemolytic uraemic syndrome, inherited haematological disorders),o Integrate polygenic scores for blood cell traits into FBC results reports with the aim of enhancing the diagnostic value of this test, which in the UK is applied to approximately 100 million samples per year.

About us

University College London Hospitals NHS Foundation Trust (UCLH) is one of the most complex NHS trusts in the UK, serving a large and diverse population. We provide academically led acute and specialist services, to people from the local area, from throughout the United Kingdom and overseas. Our vision is to deliver top-quality patient care, excellent education, and world-class research.

We provide first-class acute and specialist services across eight sites:

• University College Hospital (incorporating the Elizabeth Garrett Anderson Wing)

• National Hospital for Neurology and Neurosurgery

• Royal National ENT and Eastman Dental Hospitals

• University College Hospital Grafton Way Building

• Royal London Hospital for Integrated Medicine

• University College Hospital Macmillan Cancer Centre

• The Hospital for Tropical Diseases

• University College Hospital at Westmoreland Street

We are dedicated to the diagnosis and treatment of many complex illnesses. UCLH specialises in women's health and the treatment of cancer, infection, neurological, gastrointestinal and oral disease. It has world class support services including critical care, imaging, nuclear medicine and pathology.

We are committed to sustainability and have pledged to become a carbon net zero health service, embedding sustainable practice throughout UCLH. We have set an ambitious target of net zero for our direct emissions by 2031 and indirect emissions by 2040.

Job description

Job responsibilities

For the full Person Specification and more information regarding the main responsibilities of this role, please refer to the attached Job Description.

This vacancy has been advertised in accordance with the new NHS pay rate which will take effect from autumn 2024. Please note if your employment starts before the 24/25 pay scales are implemented you will be paid under the 23/24 pay scales and any backpay will be adjusted accordingly. Further information can be found at https://www.nhsemployers.org/articles/pay-scales-202425

Come and be a part of the best NHS trust in England to work for, according to our staff*

UCLH top trust to work at in England for the second year running! : University College London Hospitals NHS Foundation Trust

*In the most recent NHS staff survey UCLH had the highest percentage of staff who said they would recommend us as a place to work, out of all general acute or acute/community NHS trusts in England for the second year in a row.

UCLH top trust to work at in England for the second year running! University College London Hospitals NHS Foundation Trust.

Once again, UCLH has received the highest score of all general acute and acute/community NHS trusts in England for staff that would recommend us as a place to work.

Person Specification

Knowledge and Qualifications

Essential

• Degree or other qualification or evidence of relevant on-job qualification, e.g. Informatics, Mathematics, Software Engineering, Computer Science, or Systems Engineering at Bachelor level
• Data warehousing, BI or relevant Professional IT qualification to Masters level or equivalent experience

Desirable

• PhD in bioinformatics, computational biology or biology, physics and applied mathematics or related disciplines.

Experience

Essential

• Experience with data analysis - exploratory graphical and statistical analysis planning, hypothesis testing and algorithm evaluation

Desirable

• Experience of managing large heterogenous datasets.
• Experience with OMOP, FHIR and OpenEHR standards
• Experience in working in High Performance Compute cluster environments

Skills and Abilities

Essential

• Excellent data management skills, experience using programmatic tools - e.g., Python, R, MySql or PostgreSQL.
• Knowledge of bioinformatics software such as samtools, bcftools, and plink
• Experience using statistical methods to answer real world questions
• Using computer clusters and different database management systems (e.g. MySQL, mongodb)
• Ability to prepare and maintain complex documentation
• Broad range of IT technical skills and wider technical awareness

Desirable

• Experience with object oriented programming experience with interpreted programming languages - Working knowledge of one, capacity to read and understand others
• Demonstrated knowledge of working in a Unix based high-performance computing environment (including command line)
• Experience with software development good practices (version control, tests, code reviews)
• Experience in managing large (> 500M records) electronic healthcare record datasets - usually not uniform or standardized
• Knowledge of EHR specifications and standards, health information exchange standards and biomedical ontologies
• Understanding and/or experience of clinical systems interaction in a large complex healthcare environment

Communication

Essential

• Good communication skills including the ability to articulate technical content to non-technical colleagues and senior managers

Personal and People Development

Essential

• Experience in supervision and training of colleagues at all levels

Employer details

Employer name

University College London Hospitals NHS Foundation Trust

Address

UCL Institute for Health Informatics

222 Euston Road

London

NW1 2DA

Any attachments will be accessible after you click to apply.

309-UCLH-5032