Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Nonjabulo-M15/Health-and-Demographic-Patterns-in-South-Africa-HDPSA-Data-Mining

Domaine:

healthcare

Type de record:

project
Créateur:
Non
Hôte:
Applied CRISP-DM to 12 national health datasets using R & Power BI. Performed EDA, clustering, classification, and association rule mining. Built predictive models for child mortality and interactive dashboards highlighting regional health risk patterns. # Health-and-Demographic-Patterns-in-South-Africa-HDPSA-Data-Mining ## Overview Collaborated in applying the CRISP-DM (Cross Industry Standard Process for Data Mining) methodology to analyze public health and demographic datasets in South Africa. The goal was to identify patterns between healthcare access, sanitation, literacy, nutrition, and mortality rates using data mining and business intelligence techniques. ## Objectives - Identify high-risk health regions - Determine predictors of child and maternal mortality - Analyze relationships between sanitation and disease - Evaluate impact of immunization and COVID-19 prevention behaviors - Develop interactive dashboards for decision support ## Datasets Used - Access to Health Care - Child Mortality - HIV Behavior - Immunization - Toilet Facilities - Water - COVID-19 Prevention - Maternal Mortality - Literacy - ARI Symptoms - Anthropometry - IYCF (Infant & Young Child Feeding) ## Methodology – CRISP-DM ### 1. Business Understanding Defined key health indicators and stakeholder objectives. ### 2. Data Understanding - Exploratory Data Analysis (EDA) - Missing value detection - Outlier analysis - Correlation analysis - Initial visualizations in R ### 3. Data Preparation - Data cleaning - Feature engineering - Categorical encoding - Data merging - Scaling and normalization ### 4. Modelling **Clustering** - K-Means - Hierarchical Clustering - Elbow Method **Classification** - Logistic Regression - Decision Trees - Random Forest **Association Rules** - Apriori Algorithm - Support, Confidence, Lift evaluation ## Model Evaluation - Accuracy - Precision - Recall - F1-Score - Confusion Matrix - Silhouette Score ## Dashboard Developed interactive dashboards using: - Power BI - Region-level filters - Mortality risk segmentation - Sanitation coverage visuals ## Tools & Technologies - R - R Markdown - Power BI - Excel ## Key Insights - Strong relationship between sanitation access and reduced ARI cases - Liter …

Visit

github.com

Similaires

Omnilux24/South-Africa---Subnational-Demographic-and-Health-DataProgress of organisational data mining in South AfricaHousehold cooking fuel use patterns and determinants across southern Africa: Evidence from the demographic and health survey dataData mining to analyse recurrent crime in South AfricaRaksRaks/HDPSA-BIN381Spatial patterns of childhood diarrhea in Ethiopia: data from Ethiopian demographic and health surveys (2000, 2005, and 2011)

Omnilux24/South-Africa---Subnational-Demographic-and-Health-Data

# South Africa Subnational Demographic and Health Data Analysis ## Overview This repository cont

Progress of organisational data mining in South Africa

International audience This paper describes three largely qualitative studies, spread

Household cooking fuel use patterns and determinants across southern Africa: Evidence from the demographic and health survey data

Improving access to modern energy sources is critical to enhancing the quality of life of many peopl

Data mining to analyse recurrent crime in South Africa

When South Africa is compared to other countries, it has a notably high rate of crime. The country h

RaksRaks/HDPSA-BIN381

This project for Business Intelligence 381 (BIN381) investigates Health and Demographic Patterns in

Spatial patterns of childhood diarrhea in Ethiopia: data from Ethiopian demographic and health surveys (2000, 2005, and 2011)