Skip to content

This repo collects the open-source work of the Analytics Service within NHS Digital Data Services

License

Notifications You must be signed in to change notification settings

NHSDigital/data-analytics-services

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

55 Commits
 
 
 
 
 
 
 
 

Repository files navigation

We'd like to share our work with you

This page showcases some of the work done by teams within NHS England.

We aim to deliver world-class data and services to improve the health and wellbeing of people in England by using data, curation and advanced analytics in innovative ways.

We have created this site with this mission in mind, to share and discuss open-source technology work. We will also distribute our code, publications and internal tools for feedback, with the hope this can help us improve our production processes.

Note The repo is curated by the Data Science team: to contact us raise an issue on GitHub or via email (england.RAPchampions@nhs.net) and we will respond promptly.

Our repositories

Repo name Description Languages Published Report
Open data standards Draft of open data CSV standards for comment Markdown No
Data Visualisation for Health and Care Community of Practice Committe of folk working in data visualisation across CSUs, Trusts, NHS Digital, NHS England and others. Various No
Medicines text mining tool Medicines text mining application. Python, PySpark No
MPS Diagnostics Interpretable metadata for MPS record linkage and Person ID Python, PySpark User Guide
NHSD analytics services blog Repo for blog webpage HTML, CSS No
codonPython Aim to reduce the DAE barrier for new analysts at NHSD. Python No
Artificial Data Generator Pipelines and reusable code for generating anonymous artificial versions of NHS Digital assets in Databricks. Python, PySpark No
DNAttend ML framework for predicting patient non-attendance Python Documentation
nhs_time_of_travel This GitHub repository and accompanying webpage contain the initial proof of concept and exploratory analysis for the design of a holistic and interactive mapping tool to support decision-making in health and social care. Python Yes
MedicalMap A collaborative open source project between NHS Python Community and Google Health, building on nhs_time_of_travel to create various mapping functionality in a streamlit app Python No
open-cyber A webpage giving select headline stats on cybersecurity in healthcare organisations Python Site
antibiotic_cost Plotly chart and folium map visualizing the prescribing cost of the antibiotics Amoxicillin, Doxycycline Hyclate and Caefalexin for Clinical Commissioning Groups (CCGs) Python Site
open-health-statistcs Statistics on open source healthcare repositories Python Site
Forecasting A repo of different forecasting methods for different situations Python No
SynPath Proof Of Concept - Open Patient Pathway Generator using and an agent based approach Python Report
MultiNet This command line tool provides user-friendly and automated multi-morbidity network analysis. Detect significant associations are correcting for confounding factors such as Age and Sex. Includes community detection for un-directed networks. Option to build directed networks when diagnosis times are available. Python No
ambulance-DES Proof of concept simmer discrete event simulation for the ambulance setting R Conference Slides
HSMA4-12-DES-rheum Discrete Event Simulation - The role of Patient Initiated Follow-up in supporting the elective recovery in rheumatology R No
eLfH-PHM-RiskStrat A worked example to support the e-Learning for Health (e-LfH) PHM Risk Stratification Module. R No
ai-dictionary Prototype AI Dictionary from the NHS AI Lab JavaScript Site
SystemHierarchies Aiming to visualise and represent the structure and mapping of different NHS organisations Python No
nhse-io-jekyll-template Template for io pages using Jekyll incorporating the NHS service manual html, Ruby Site

Open Code from Internship Programme

see Internship Site for more details

Repo Name Description Languages Published Report
SynthVAE NHSE DS Internship developing a Synthetic data generation by a Variational AutoEncoder with Differential Privacy assessed using Synthetic Data Vault metrics Python Reports
SynPath_Diabetes NHSE DS Internship developing a SynPath module for generating type 2 diabetes pathway Python Report
Diabetes Prevalence Management and Health Inequalities NHSE DS Internship looking at how to identify inequalities in population health data Python Report
stm-survey-text NHSE DS Internship developing a Structural Topic Modelling code to gain insights from free text responses to NHS surveys and their associated metadata Python Report
LIME-XAI-Facial-Disease-Classification NHSE DS Internship Scheme project investigating if a LIME application using superpixels is appropriate for facial healthcare image classification Python Report
TxtRayAlign NHSE DS Internship exploring contrastive alignment of image and text encoders for image-based radiology report retrieval and generation, and identification of possible evaluation metrics Python Reports
commercial-data-healthcare-predictions NHSE DS Internship investigating of the value of commercial sales data on respiratory death predictions using Model Class Reliance Python Report
NHSSynth NHSE DS Internship developing a Python package alongside research and investigative materials covering the effectiveness of the package and synthetic data more generally when applied to NHS use cases. Python No
ELM4PSIR NHSE DS Internship exploring Language Modelling for (NHS) Patient Safety Incident Reports - DART PhD Internship Project Python Report

RAP Guidance Repositories

Repo name Description Languages Published Report
RAP Community of Practice Collection of NHSD RAP resources to help analysts adopt and apply RAP practices. The github pages website of this repo is here: RAP Community of Practice Website Python, PySpark, Markdown No
RAP package template RAP package template Python No
RAP Example Pipeline - PySpark Example of good practices in a simple pipeline using artificial HES data Python No

RAP Publication Repositories

An easy way to find all fo the NHS Digital publication repos, is to look at the #nhs-digital-publication topic

Repo name Description Languages Published Report First Published
ASC-Outcomes-Framework This is the code repository for Adult Social Care Outcomes Framework Python ✔️ 2023-04-17
ASC-Overview Code repository for Adult Social Care Overview Python ✔️ 2023-06-13
ASC-Safeguarding-Adults Safeguarding Adults is a legal obligation for English Councils responsible for Adult Social Services. It aims to protect vulnerable adults from abuse or neglect. The Safeguarding Adults Collection (SAC) gathers data from these councils, generating insights on national, regional, and local safeguarding efforts. Python ✔️ 2023-06-13
ASC-User-Survey Code repository for the Personal Social Services Adult Social Care Survey publication R, Python, Markdown ✔️ 2022-09-20
ASC_LA_Peer_Groups Calculates statistical neighbours (aka peers) for Local Authorities in England, for use in Adult Social Care statistics. Python, Markdown ✔️ 2024-01-16
GDPPR_Analytical_Code To share analysis code using the GDPPR dataset. SQL, Python, Markdown ✔️ 2021-03-08
IAPT Patient Outcomes Data Science Accelerator Project Code used to produce the Data Science Accelerator on IAPT patient outcomes Python, Markdown 2022-11-03
idhc_publication Code used to produce the Learning Disability Health Check Scheme publication Python ✔️ 2023-04-17
iif_indicators Code for the following IIF indicators: AC-02: Emergency admissions for specified Ambulatory Care Sensitive Conditions per registered patient. ACC-08: Number of general practice appointments for which the time from booking to appointment was two weeks or less. EHCH-04: Number of general practice appointments categorised as 'patient contact as part of weekly care home round'. Python, PySpark 2023-01-10
mental-health-act-annual-statistics This repository contains all of code used to create the Annual Uses of The Mental Health Act publication. Python, PySpark ✔️ 2023-06-29
mental-health-bulletin This repository contains all of code used to create the Mental Health Bulletin publication. Python, PySpark ✔️ 2023-06-29
mental-health-monthly-statistics This repository contains all of code used to create the Mental Health Monthly Statistics publication. Python, PySpark ✔️ 2023-06-29
National Child Measurement Programme Provisional Report Code Codebase for NCMP Report publication SQL, Python ✔️ 2022-08-11
National Child Measurement Programme Report Code Codebase for NCMP Report publication SQL, Python ✔️ 2022-12-12
National Diabetes Audit A sample repo for working with Reproducible Analytical Pipelines (RAP). Python, PySpark 2021-10-14
NCDes package Code used to produce the Network Contract Directed Enhanced Service publication Python, Markdown ✔️ 2022-10-07
NHS-Breast-Screening-Programme-Report-Code Code repository for the NHS Breast Screening Programme report Python ✔️ 2023-03-15
Sexual-Reproductive-Health-Services-Report-Code This project produces the required publication outputs for the Sexual and Reproductive Health Services (Contraception) publication: Data tables, charts, and map data. Python ✔️ 2023-06-19
Smoking-Drinking-and-Drug-Use-Report-Code Code repository for the Smoking Drinking and Drug Use Report R, Python, Markdown ✔️ 2022-08-26
Workforce: Absence Rates Codebase for Absence Rates publication SQL, Python ✔️ 2022-07-21

We blog!

Please visit our NHS Digital Blog to discover the latest developments and updates from our analytics teams.

Work with us

Our teams design, develop and operate the national IT and data services that support clinicians at work, help patients get the best care, and use data to improve health and care. Our mission demands smart, usable, and reliable technology. Come serve the people by helping us design and build better products.

Learn more about the work we do in Data, Insights and Statistics group of the Data services - NHS Digital.

Licence

Data Analytics Services codebase is released under the MIT License.

The documentation is © Crown copyright and available under the terms of the Open Government 3.0 licence.