Data Scientist

Job overview

Neuropsychology services generate a wealth of psychometric assessment data, which is critical for understanding patient profiles, informing clinical decisions, and supporting service development. However, much of this data remains siloed in local records, limiting its potential for broader analysis and quality improvement.

The proposal is to digitise local neuropsychology assessment data for use in downstream analysis. This will involve engaging with the internal data science team and developing tools to interrogate both locally and cloud-stored information. The resulting infrastructure will support internal audits, facilitate service performance reviews, and empower locally inspired research projects.

A key component of this initiative is the creation of a registry designed specifically for neuropsychology assessment data; to enable systematic evaluation of patient outcomes and service delivery, providing a valuable resource for audit, service evaluation, and research. It will also help identify trends and inform future clinical practice.

The post-holder will play a central role in this work, collaborating with the data science team to develop and maintain the necessary analytics platforms and data infrastructure. Responsibilities will include contributing to quality management, ensuring compliance with national standards and regulations, and helping to shape data governance processes for the use of digitised assessment data in both clinical and research contexts.

Main duties of the job

• Developing machine learning models to enhance efficiency in the neuropsychology department by optimizing diagnositic patient assessment
• Develop code to streamline data collation, identify the most specific and sensitive diagnostic tests, and eliminate redundancy.
• Benchmarking and fine-tuning machine learning algorithms tools for quality control, and validating new features in collaboration with internal and external stakeholders
• Configure and maintain database servers and processes, including monitoring of system health and performance, to ensure high levels of performance, availability, and security.
• Develop pipelines / solutions to interact with third party software to ensure patient neuropsychometry data is available and suitable for downstream analysis.
• Apply data modelling techniques to ensure development and implementation support efforts meet integration and performance expectations
• Build appropriate and useful reporting deliverables
• Continuously scanning the scientific literature to identify new approaches tomachine learning applicationsthat can be implemented to improve our capabilities

Working for our organisation

King’s College Hospital NHS Foundation Trust is one of the UK’s largest and busiest teaching Trusts with a turnover of £1 billion, million patient contacts a year and around 15,000 staff based across 5 main sites in South East London. The Trust provides a full range of local hospital services across its different sites, and specialist services from King’s College Hospital (KCH) sites at Denmark Hill in Camberwell and at the Princess Royal University Hospital (PRUH) site in Bromley.

The trust-wide strategy Strong Roots, Global Reachis our Vision to be BOLD, Brilliant people, Outstanding care, Leaders in Research, Innovation and Education, Diversity, Equality and Inclusion (EDI) at the heart of everything we do. By being person-centred, digitally-enabled, and focused on sustainability, we can take Team King’s to another level

King’s is dedicated to embracing the broad diversity of our staff, patients and communities and stand firmly against all forms of prejudice and discrimination. This includes, but is not limited to, racism, ableism, homophobia, biphobia, transphobia, sexism, ageism, religious discrimination, and any other prejudiced behaviour that undermines the rights, wellbeing and identity of our staff, and patients.