Health, Public Health & Healthcare Management · Physical, Online
Public Health Data Analysis & Epidemiological Research Training Workshop
10 Days3 sessions available Certificate on completion
The Public Health Data Analytics, Epidemiology & AI Training Workshop equips public health professionals, researchers and healthcare programme managers with practical skills to analyse health data, interpret epidemiological trends and make evidence-based decisions. The training covers public health statistics, disease surveillance, outbreak analysis, health indicators, data cleaning, data visualisation and predictive analytics using tools such as Microsoft Excel, Python, SQL and Power BI. Participants also explore the application of artificial intelligence (AI) and machine learning in disease prediction, health trend forecasting and automated reporting. The course is designed to strengthen data-driven planning, monitoring, research and policy development across public health programmes, healthcare institutions, government agencies, NGOs and international health organisations.
The Public Health Data Analytics, Epidemiology & AI Training Workshop provides practical training in public health data analysis, epidemiological statistics, disease surveillance, health indicators and evidence-based decision-making. Participants learn to clean and analyse health datasets, interpret disease trends, build interactive dashboards using Excel and Power BI, perform statistical analysis with Python and SQL, and explore AI and machine learning applications in public health forecasting. Designed for public health professionals, researchers, healthcare programme managers and monitoring and evaluation specialists, this course develops the analytical skills required to improve health programme monitoring, research, planning and population health outcomes.
Course objectives
Collect, organise, clean and validate public health datasets while applying appropriate data quality, confidentiality and governance principles.
Develop analytical reports and evidence-based recommendations to support public health planning, programme evaluation and resource allocation.
Apply AI and machine learning techniques to public health forecasting, risk analysis and predictive modelling while recognising model limitations and ethical considerations.
Use Excel, SQL, Python and Power BI to conduct data analysis, develop dashboards and communicate public health findings effectively.
Analyse disease surveillance data, investigate outbreak trends and monitor key public health indicators.
Apply descriptive and inferential statistics, epidemiological measures and analytical methods to interpret population health patterns.
Who should attend
Public health officers, epidemiologists, health information management professionals, health informatics specialists, disease surveillance officers, outbreak response teams, biostatisticians, public health researchers, medical researchers, healthcare data analysts, health programme managers, monitoring and evaluation specialists, NGO and humanitarian health professionals, health policy analysts, government health officials, healthcare administrators, health systems planners, clinical research professionals, health statistics officers, health monitoring and evaluation officers, university graduates in public health and related disciplines, data analysts seeking to specialise in public health, professionals working in international health organisations.
Course content
Module 1: Introduction to Public Health Data Analytics Role of data analytics in public health, principles of population health analysis, types of public health data, routine health information systems, administrative and surveillance datasets, primary an
Module 2: Public Health Data Sources, Collection and Management Demographic and health surveys, census and vital registration data, electronic health records, facility-based health information systems, disease notification systems, immunisation and matern
Module 3: Data Cleaning, Preprocessing and Quality Assurance Importing datasets from Excel, CSV and database systems, identifying missing values, duplicate record detection, correcting inconsistent formats, standardising dates and categorical variables, d
Module 4: Public Health Statistics and Descriptive Analytics Types of variables and measurement scales, frequency distributions, proportions and percentages, mean median and mode, variance and standard deviation, quartiles and percentiles, cross-tabulatio
Module 5: Epidemiology and Applied Statistical Analysis Principles of descriptive and analytical epidemiology, person-place-time analysis, population at risk, exposure and outcome variables, cohort and case-control studies, cross-sectional studies, ecolog
Module 6: Disease Surveillance and Outbreak Analytics Principles of public health surveillance, indicator-based and event-based surveillance, case definitions, reporting completeness and timeliness, epidemic curves, baseline disease trends, outbreak detec
Module 7: Health Indicators, Monitoring and Programme Evaluation Development of measurable public health indicators, indicator definitions and metadata, numerator and denominator selection, baseline and target setting, maternal and child health indicators
Module 8: Microsoft Excel for Public Health Data Analysis Importing and organising health datasets, Excel tables and structured references, data validation, text and date functions, conditional formatting, sorting and filtering, removing duplicates, handl
Module 9: SQL and Database Analytics for Health Data Relational database concepts, tables and primary keys, database relationships, importing health data into databases, SELECT statements, filtering and sorting records, aggregate functions, GROUP BY and H
Module 10: Python for Public Health Data Science Python environment and notebook workflows, variables and data structures, importing CSV and Excel files, pandas DataFrames, NumPy for numerical analysis, data cleaning with pandas, missing value treatment,
Module 11: Data Visualisation and Power BI for Public Health Principles of effective health data visualisation, selecting appropriate charts, visualising disease trends and mortality patterns, comparing health outcomes across populations, geographic and f
Module 12: Geographic and Spatial Public Health Analytics Introduction to geographic information systems (GIS), geospatial public health data, coordinate systems and geographic boundaries, mapping disease cases and health facilities, choropleth maps, dise
Module 13: Time-Series Analysis and Public Health Forecasting Time-based health data structures, daily weekly monthly and annual trends, trend and seasonal components, moving averages, growth rates, baseline comparisons, epidemic curve interpretation, sea
Module 14: Artificial Intelligence and Machine Learning in Public Health Introduction to AI and machine learning, supervised and unsupervised learning, selecting features and target variables, preparing data for predictive modelling, training and testing
Module 15: Public Health Data Governance, Ethics and Responsible AI Confidentiality in health data, informed consent and lawful data use, de-identification and pseudonymisation, handling personally identifiable health information, data minimisation, role-
Module 16: Public Health Reporting, Research and Data Storytelling Structuring analytical reports, writing executive summaries, selecting appropriate indicators, presenting statistical findings, interpreting charts and tables, explaining trends to non-tec
Module 17: Integrated Public Health Analytics Capstone Project Selecting a public health problem, defining research questions and analytical objectives, identifying suitable data sources, developing a data dictionary, cleaning and validating a dataset, co
General notes
Public Health Data Analysis, Epidemiology Training Workshop, Public Health Statistics, Health Data Science, Disease Surveillance Analytics, Public Health Informatics, Python for Public Health, Power BI for Healthcare, AI in Public Health, Predictive Analytics in Epidemiology.
5. Practical Training Exercises and Expected Outputs Clean a sample disease surveillance dataset, validated dataset and data quality report, calculate incidence and prevalence rates from population health data, epidemiological indicator summary, analyse maternal and child health indicators, health programme performance report, identify missing values and duplicate records in facility data, data cleaning log and analysis-ready dataset, build an Excel dashboard for immunisation coverage, interactive immunisation monitoring dashboard, query health facility data using SQL, documented SQL queries and facility performance summaries, conduct descriptive analysis using Python, reproducible Python notebook and statistical summary, analyse weekly disease notifications, disease trend analysis and surveillance report, develop a Power BI dashboard for health indicators, interactive public health performance dashboard, map disease cases by geographic area, public health distribution map and geographic interpretation, forecast monthly outpatient attendance or disease notifications, forecast report with validation metrics and uncertainty limitations, build a basic machine learning model using synthetic or de-identified health data, model evaluation report with documented limitations, use AI to assist with drafting a public health report, human-verified analytical report with source checks, conduct a data privacy and governance assessment, public health data protection checklist, complete an integrated public health analytics project, final analytical report, dashboard and evidence-based recommendations.
The workshop uses a practical, hands-on learning approach combining instructor-led sessions, demonstrations, guided computer exercises, public health case studies, individual assignments and a final capstone project. Participants work with sample, synthetic or appropriately de-identified datasets covering disease surveillance, maternal and child health, immunisation, health service utilisation and programme performance. The training progresses from foundational statistical analysis to dashboards, predictive modelling and responsible AI applications.
Frequently asked questions
Public health data analytics is the process of collecting, processing, analysing and interpreting population health data to understand disease patterns, evaluate health programmes, identify risks and inform public health decisions.
The workshop is suitable for public health officers, epidemiologists, health information professionals, researchers, biostatisticians, healthcare programme managers, monitoring and evaluation specialists, NGO health staff and aspiring public health data analysts.
No. The course can begin with Excel and basic statistical concepts before introducing Python, SQL and machine learning. Participants with programming experience can progress more quickly to advanced analytical exercises.
The core tools include Excel, Python, pandas, Jupyter Notebook, SQL and Power BI. QGIS and R may be introduced depending on the training duration and learning objectives.
Yes. Topics include incidence, prevalence, mortality rates, case fatality rates, risk ratios, odds ratios, confidence intervals, hypothesis testing, regression fundamentals and interpretation of epidemiological results.
AI and machine learning can support disease trend forecasting, risk classification, service demand prediction, population grouping and report preparation. The course emphasises validation, transparency, privacy, bias assessment and human oversight.
Yes. Participants complete a capstone project involving a public health question, data preparation, statistical analysis, visualisation, interpretation and recommendations. Depending on their progress, they may also build a basic predictive model.
The skills are relevant to public health analytics, epidemiology support, health information management, disease surveillance, monitoring and evaluation, health research, programme performance analysis and health data science. The course provides practical skills but does not itself confer professional licensure or guarantee employment.
This course applies data analytics directly to public health problems. In addition to data cleaning, statistics, programming and dashboards, it covers epidemiology, disease surveillance, health indicators, population health research and responsible AI applications.