Important: Disclaimer
This site is no longer active
Since August 2023 we have moved our content to a central Signpost Site
This is not the official site but a store of technical documents and ongoing work. Opinions expressed in posts are not representative of the views of NHS England and any content here should not be regarded as official output in any form. For more information about NHS England please visit our official website
Projects
Separated into different stages - complete, dissemination, delivery, and discovery
Complete
-
ESNEFT Analysis - Diabetes Inequalities
Stephen Richer
One component of our Data Science Internship project on Inequalities in Population Health Data
PHM Data Data manipulation OSNnx -
DNAttend - ML framework for predicting patient non-attendance
Stephen Richer
One component of our Data Science Internship project on Inequalities in Population Health Data
DNA Prediciton CatBoost PHM Data -
Discrete Event Simulation - Ambulances
Martina Fonseca
Proof of concept simmer discrete event simulation for the ambulance setting - used at NHS-R 2022 Conference
Ambulance Discrete event simuation RSimmer -
H4_12 - The role of Patient Initiated Follow-Up and Digital Outpatients in supporting the elctive recovery
Martina Fonseca
Simulation of the role that PIFU and other interventions can play in addressing the elective backlog
HSMA4 Project discrete event simuation simPy -
Using LIME to explain facial disease classification
Anwesha Mohanty
Application of Local Interoperable Model-agnostic Explanations to an InceptionV3 Classifyier looking at a Rosacea
LIME XAI Python -
STM for survey data
Anna Linton & Paul Carroll
Application of Structural Topic Modelling and visualisation of insights. Currently private repo but being made public soon
Free Text Analysis STM R -
Txt-Ray Align
Dekai Zhang & Dan Schofield
Code to contrastively train and align text and image encoders and evaluate them on an image-to-text retrieval task using MIMIC-CXR. Currently private repo but being made public soon
Image Encoder Text Encoder Python -
Model Class Reliance
Elizabeth Dolan
Internship project investigating the use of MCR to identify the value of including commerical sales data in respiratory predictions
Model Explainability Commercial Data Python -
AIF ALlocation Streamlit Tool
Craig Shenton & Christopher Todd
Tool built to support need based allocations
Collaborative Analytics Streamlit Python -
Open Cyber
Martina Fonseca
Summary statistics from the DSPT 2020/21 toolkit
Cyber Security Compliance Open Analytics -
GP Mapping
Mattia Ficarelli
This page tracks the number of patients registered at individual GP Practices
Primary Care Mapping Open Analytics -
The Prescribing Cost of Antibiotics
Mattia Ficarelli
Plotly chart and folium map visualizing the prescribing cost of the antibiotics Amoxicillin, Doxycycline Hyclate and Caefalexin for Clinical Commissioning Groups (CCGs)
Open Analytics Open Prescribing Python -
Open Healthcare Statistics
Craig Shenton, Adam Ivison (NHS BSA), Arouba Zubair, Mary Amanuel
Collecting statistics on open-source NHS and healthcare related code repositories
Open Analytics GitHub Python -
Digital Health Insights
Mary Amanuel, Craig Shenton
What can the 2021 GP Patient Survey tell us about access to online general practice services?
GP Patient Survey Digital Health Open Analytics -
Open Analytics Template
Craig Shenton
NHS.UK themed template for open analytics projects. Build your own open source end-to-end analytical tool using python, plotly, github.io, and github actions.
Open Analytics GitHub Python -
eLfH-PHM-RiskStrat
Matthew Francis (PHE) and Martina Fonseca
Risk Stratification - A practical example in R to accompany the HEE e-LfH module.
R Prediction Analytics -
NHS App Analytics Dashboard
Arouba Zubair, Mary Amanuel
The NHS App dashboard enables you to see how many patients are using the NHS App across England, and which features they are using. It can be accessed by anyone with an NHS email address.
Dashboard NHS App Analytics -
Social Care Connectivity Devices
Craig Shenton
NHSX led programme to procure and gift 11,000 (data-enabled) iPads to care homes in response to COVID-19.
Care Homes IPads Analytics -
Transform
Jonny Pearson
Methodology to calculate impact of aging population on activity forecasts.
Forecasts b-spline linear -
NHSX Academic publications
Martina Fonseca
Displaying statistics on NHS and NHSX-affiliated publications on Pubmed.
Open Analytics Publications Python -
SynPath - Diabetes
Jonny Pearson (on behalf of Tiyi Morris)
SynPath module for generating type 2 diabetes pathway
PhD Data Science Intern Scheme Simulation Synthetic
Delivery
-
Time Series Forecasting
Milan Storey & Paul Carroll
Base starting code for comparative forecasting developed as part of a DDaT placement
Forecasting Prophet SARIMA -
Privacy Fingerprint
Dan Schofield & Jonny Pearson
Public facing materials for our commission on creating a tool to identify sensitive elements beyond PII in text
Text Data Privacy NLP -
System Hierarchies
Faaiz Shanawas
Aiming to visualise and represent the structure and mapping of different NHS organisations
Structure Mapping Python NHS -
Travel Times
Mattia Ficarelli & Paul Carroll
PoC for an interactive mapping tool to support decision-making.
Mapping OSMnx Python -
SynPath
Jonny Pearson
A library for generating synthetic electronic health records in FHIR v4 format using agent-based modeling to simulate patient pathways.
Simulation Synthetic FHIR -
AU Data Engineering - Azure Databricks
Craig Shenton & Mattia Ficarelli
Our public facing store of code used to transform our data flows using databricks compute
Data Engineering Azure ETL Pipelines -
AU Azure Databricks CICD
Mattia Ficarelli & Abdu Nuhu
CICD implementation of our engineering pipelines
Data Engineering Azure ETL Pipelines -
AU Data Engineering
Craig Shenton & Mattia Ficarelli
Our public facing store of code used to orchestrate our data flows
Data Engineering Azure ETL Pipelines -
Tableau Analytics
Ollie Jones & Mattia Ficarelli
Contains Tableau workbooks for NHSX analytics projects.
Data Engineering Tableau Business Intelligence -
SynthVAE
Jonny Pearson (on behalf of Dom Danks)
Synthetic data generation by a Variational AutoEncoder with Differential Privacy assessed using Synthetic Data Vault metrics
PhD Data Science Intern Scheme Variational AutoEnconder Synthetic
Discovery
-
NHS Language Corpus Discovery Tools
Dan Schofield
Tools used as part of the NHS Language Corpus Discovery
Natural Language Processing Dataset Building Open