{"id":26157031,"url":"https://github.com/birmingham-and-solihull-ics/unsupervised-clustering-practices","last_synced_at":"2025-07-20T09:06:44.725Z","repository":{"id":278549118,"uuid":"935989033","full_name":"Birmingham-and-Solihull-ICS/Unsupervised-Clustering-Practices","owner":"Birmingham-and-Solihull-ICS","description":"K-means and hierarchical clustering of GP practices based on QOF performance measures","archived":false,"fork":false,"pushed_at":"2025-02-20T10:57:43.000Z","size":25,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-11T09:44:32.898Z","etag":null,"topics":["hierachical-clustering","k-means-clustering","python","qof","unsupervised-machine-learning"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Birmingham-and-Solihull-ICS.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-20T10:54:09.000Z","updated_at":"2025-02-20T10:59:01.000Z","dependencies_parsed_at":"2025-02-20T11:52:47.409Z","dependency_job_id":null,"html_url":"https://github.com/Birmingham-and-Solihull-ICS/Unsupervised-Clustering-Practices","commit_stats":null,"previous_names":["birmingham-and-solihull-ics/unsupervised-clustering-practices"],"tags_count":0,"template":false,"template_full_name":"Birmingham-and-Solihull-ICS/BSOLproject","purl":"pkg:github/Birmingham-and-Solihull-ICS/Unsupervised-Clustering-Practices","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Birmingham-and-Solihull-ICS%2FUnsupervised-Clustering-Practices","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Birmingham-and-Solihull-ICS%2FUnsupervised-Clustering-Practices/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Birmingham-and-Solihull-ICS%2FUnsupervised-Clustering-Practices/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Birmingham-and-Solihull-ICS%2FUnsupervised-Clustering-Practices/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Birmingham-and-Solihull-ICS","download_url":"https://codeload.github.com/Birmingham-and-Solihull-ICS/Unsupervised-Clustering-Practices/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Birmingham-and-Solihull-ICS%2FUnsupervised-Clustering-Practices/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260097485,"owners_count":22958210,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["hierachical-clustering","k-means-clustering","python","qof","unsupervised-machine-learning"],"created_at":"2025-03-11T09:38:30.070Z","updated_at":"2025-06-16T04:40:56.400Z","avatar_url":"https://github.com/Birmingham-and-Solihull-ICS.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# **GP Practice Segmentation Using Unsupervised Machine Learning**\n\n## **Project Overview**\nThis project aims to apply **unsupervised machine learning** techniques, specifically **K-Means clustering** and **Hierarchical clustering**, to segment **General Practitioner (GP) practices** based on **Quality and Outcomes Framework (QOF) performance measures** and other **demographic markers**. By identifying meaningful clusters, this analysis will help uncover patterns in healthcare performance and inform targeted interventions.\n\n## **Objectives**\n- Explore and preprocess **QOF performance data** and **demographic indicators**.\n- Apply **K-Means** and **Hierarchical clustering** to group GP practices into meaningful segments.\n- Evaluate the clustering results to identify patterns and insights.\n- Visualize and interpret the clusters for actionable recommendations.\n\n## **Project Status**\n🟢 **Ongoing** (Early Stages)  \n- **Data collection**: In progress  \n- **Data cleaning and preprocessing**: Not started  \n- **Feature selection**: Not started  \n- **Clustering implementation**: Not started  \n- **Evaluation and visualization**: Not started  \n\n## **Data Sources**\nThe analysis will utilize publicly available data, including but not limited to:\n- **Quality and Outcomes Framework (QOF)** – Performance measures of GP practices.\n- **Demographic Data** – Population characteristics, socioeconomic factors, and regional variations.\n- **Additional Datasets** – Any relevant healthcare indicators.\n\n## **Methodology**\n1. **Data Preparation**\n   - Collect and preprocess **QOF and demographic data**.\n   - Handle missing values, outliers, and standardize features.\n   \n2. **Feature Engineering**\n   - Select relevant performance and demographic metrics.\n   - Apply **dimensionality reduction (if needed)** to improve clustering performance.\n\n3. **Clustering Techniques**\n   - Implement **K-Means clustering** to segment GP practices.\n   - Use **Hierarchical clustering** for alternative segmentation and comparison.\n\n4. **Model Evaluation**\n   - Use **Elbow Method** and **Silhouette Score** to determine the optimal number of clusters.\n   - Compare clustering results and interpret key patterns.\n\n5. **Visualization \u0026 Insights**\n   - Generate **heatmaps**, **scatter plots**, and **geospatial maps** to illustrate cluster characteristics.\n   - Summarize findings to inform policy recommendations.\n\n\nThis repository is dual licensed under the [Open Government v3]([https://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/) \u0026 MIT. All code can outputs are subject to Crown Copyright.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbirmingham-and-solihull-ics%2Funsupervised-clustering-practices","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbirmingham-and-solihull-ics%2Funsupervised-clustering-practices","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbirmingham-and-solihull-ics%2Funsupervised-clustering-practices/lists"}