London Secure Data Environment - Data Use Register

Each year, over 3 million people with cancer in England receive care through the NHS, generating millions of clinical documents, including things like letters between clinicians, multidisciplinary team meeting reports, and test results, written in medical language. This information is valuable for not only treatment, but also research because they contain rich detail about diagnoses, genetic biomarkers, treatments, and outcomes. However, computers can't read them in the way they're written. Instead, researchers rely on coded records that computers can process, but these codes only capture basic information and miss much of the detail. Going through millions of clinical notes by hand to extract the useful information would be an enormous task, and sharing sensitive patient documents directly with researchers raises serious privacy concerns.

The HEJMI builds on the Council's existing Environmental Justice Measure Index (EJMI) - a
weighted, small-area (LSOA) composite of environmental conditions spanning sustainable transport, green
space and tree canopy, air quality, flood risk, land-surface temperature, building energy efficiency and
deprivation (IMD). The purpose of this project is to link these environmental metrics to healthcare outcomes
so that the i

Support equitable healthcare planning by analysing service use, access and inequalities, providing evidence to improve service design, decision-making and patient outcomes across local communities

This project involves the analysis of OncoLlama curated data from 2 London-based sites, Guy’s and St. Thomas’ Hospital and University College London Hospital, to enable our examination of cancer inequalities across diverse populations. Further impactful outputs include comparison with national cancer records, whilst we will challenge how enriched data can potentially streamline clinical trial recruitment, particularly for underserved groups.

OncoLlama is an NHS-developed AI tool that aims to solve this by automatically converting clinical notes into structured, research-ready data inside NHS systems. This means all the useful detail is preserved and people’s medical records stay private. OncoLlama does this by analysing clinical documents and converts them into structured, research-ready records with over 98.5% accuracy across 20 cancer types.

Project led by Imperial College explores Lp(a) testing in ASCVD using NWL data to assess prevalence, patient profiles, care patterns, costs, and outcomes, aiming to improve testing uptake and inform future UK cardiovascular care guidance

Study assesses whether early Lp(a) testing in low‑risk patients reduces long‑term healthcare use, costs, and productivity loss versus late testing, analysing GP visits, prescriptions, hospitalisations, costs, and patient characteristics in NWL.

The project uses retrospective data, so it offers no immediate benefit to patients. Instead, it aims to improve understanding of chronic liver disease, support future research, and help NHS services plan and target care more effectively.

The project uses retrospective data, so it offers no immediate benefit to patients. Instead, it aims to improve understanding of chronic liver disease, support future research, and help NHS services plan and target care more effectively.

Supports neighbourhood health models in Westminster and Kensington & Chelsea by using WSIC data to develop population health insights, monitor inequalities, evaluate interventions, and enable proactive, integrated care and evidence-based decision-making.

Analyses linked WSIC and secondary care data on obesity services in NWL to assess referral gaps, treatment access, and resource use, aiming to improve care delivery, reduce inequalities, and support better health outcomes through evidence-based insights.

This project develops a data‑driven Probation Health Needs Assessment in H&F, RBKC and Westminster to understand health needs, access, and inequalities among adults on probation, using WSIC data to inform integrated service planning and commissioning

Assess ED attendances in infants (0–1) pre/post Sept 2024; measure RSV‑related cases; analyse trends and seasonality; identify demographic/geographic variation; inform local planning, commissioning, and prevention

The study assesses how digital NHS care (e.g. remote consultations) impacts access, continuity, quality, efficiency, and outcomes for children, analysing inequalities using WSIC data to inform equitable, evidence‑based service design.

Obesity affects 1 in 4 adults. While GLP‑1 drugs show promise, real‑world evidence is limited. This study uses WSIC data and target trial emulation to assess effectiveness, safety, and adherence in primary care, informing NHS policy and practice.

Evaluates the MSK Trailblazer programme supporting 1,200 adults across London, using WSIC data to assess impact on healthcare use and economic inactivity, informing cost-benefit models and future health and employment support decisions.

Uses LSOA-level WSIC data to predict how Westminster housing growth will affect demand for health, care, education and community services.

This data request seeks to understand unemployment among autistic people in Westminster, with breakdowns by age, gender and ethnicity, and to identify how many receive different types of Council‑provided support.

This retrospective project evaluates WSIC risk segmentation for Central London GP Federation to assess proactive care outcomes, identify predictors of unplanned admissions, and test a proof‑of‑concept ML risk model to improve care targeting.

This project analyses GNBSIs in NW London to identify infection sources, patient risk factors and pre‑infection care patterns, supporting ICB action to reduce disproportionately high rates.

The main purpose of this project is to identify where delays occur along elective surgical waiting-list
pathways in Northwest London (NWL) and understand how these delays affect patient outcomes. The
work initially focuses on adult elective surgical pathways and aims to produce practical evidence to
support service planning and investment decisions across NWL.

This project will benefit patients by providing population-level information on how mental health, autism and ADHD services function
in practice, including where delays, repeated assessments or discontinuities in care occur

Comorbidities and changes in the health and well-being of people who are at risk of developing dementia and exploring longitudinal electronic health care records at the level of the UK population can help us understand how these conditions relate to one another and interconnect, and what other lifestyle or historical factors might play a part.

Relevant healthcare data to attempt to detect/ evidence exacerbations of illnesses relating to changes to the air quality in Westminster and to monitor activity to see if local policy changes targeting air quality have an impact on exacerbations.

The new CRM clinic model targets adult patients (aged 20–80) identified as having high or intermediate risk for cardiovascular disease (CVD), chronic kidney disease (CKD), diabetes, or obesity, using a bespoke EMIS search logic.

We will look at which medicines are being prescribed, how they are used over time, and how well they work for different groups of patients. This includes treatments like budesonide and 5-ASAs, which are commonly used to help control inflammation and maintain remission.

If we are able to evidence a reduction in hospital admissions and LAS calls this will inform how we utilise our resources. In other words, this will help decide how and when to rollout the service to other neighbourhoods.
The outcome of the project will also enable us to make changes to how we deliver the ICAP service in order to have the most positive impact on patients. For example, we may need to increase the nursing input and reduce the social
work input or vice versa

This project aims to investigate the long-term risk of prediabetes among statin users, identify the proportion of this risk attributable to statin use, and examine how this component influences the overall long-term risk of prediabetes. We want to enhance the coherence of statin-associated lipid-lowering strategies, further improve the achievement rate of lipid-lowering goals, and reduce the burden on both individuals and society by developing a statin-induced prediabetes prediction model.