2. WHAT IS DATA ANALYSIS?
Data analysis is the process of
Inspecting, C
leansing, T
ransforming,
Modeling data with the goal of discovering useful
information, Informing conclusions,
Supporting decision-making.
Importance in Public Health:
Helps track disease trends and outbreaks (e.g., COVID-19,
Malaria). Supports resource allocation in hospitals and healthcare
centers.
Provides data-driven insights to improve public health policies.
3. Types of data analysis
a. Descriptive
b. Diagnostic
c. Predictive
d. Prescriptive
4. Descriptive analysis tells us what happened. This type of analysis
helps describe or summarize quantitative data by presenting
statistics.
Descriptive analysis answers the question: “what happened?”
Eg:
Tracking Dengue Cases: Health officials record monthly dengue cases
and find a peak in the rainy season.
Outcome: Helps prepare mosquito control programs and community
awareness.
DESCRIPTIVE ANALYSIS
Monthly dengue
cases over a
year.
5. If the descriptive analysis determines
analysis determines the “why”.
Helps identify the reasons behind observed trends and
patterns.
Eg:
Food Poisoning Outbreak: A hospital finds an increase in food
poisoning cases. Investigating patient records, they trace it to a
contaminated water source in a local restaurant.
Outcome: Authorities enforce sanitation measures to prevent
future outbreaks.
DIAGNOSTIC ANALYSIS
Different
causes of food
poisoning
cases.
Bacteria
Viral
the “what”, diagnostic
Toxins
Parasites
6. Predictive analysis answers the question: “what might happen in
the future?”
Uses statistical models and machine learning to forecast future
health trends.
Eg:
Flu Season Predictions: Data shows that flu cases spike every
winter. Hospitals analyze past trends to prepare vaccines and staff.
Outcome: Improves flu prevention and hospital readiness.
PREDICTIVE ANALYSIS
Flu cases over
multiple years,
with future
projections.
7. Uses insights from previous analyses to recommend
solutions.
Eg:
Reducing Maternal Mortality: Health agencies find high
maternal deaths in rural areas due to lack of prenatal
care. Action Taken: More prenatal clinics, mobile health
units, and emergency obstetric care are introduced.
Prescriptive analysis answers the
question:
“what should we do about it?”
PRESCRIPTIVE ANALYSIS
Maternal mortality rates
in different regions.
8. Data Collection:
Gathering relevant healthcare data from hospital records, surveys, and research
studies.
Data Cleaning:
Removing errors, duplicates, and missing values to ensure accurate analysis.
Data Exploration:
Visualizing trends using graphs, charts, and summary statistics.
Data Modeling:
and time-
series
Applying statistical techniques like regression, classification,
forecasting.
Interpretation & Conclusion:
Making data-driven decisions to improve public health policies.
STEPS IN THE DATA ANALYSIS PROCESS
9. Common Visualization Tools in Healthcare:
Bar Charts: Showing disease trends (e.g., malaria cases per month).
Pie Charts: Comparing disease causes (e.g., food poisoning sources).
Heatmaps: Identifying high-risk areas (e.g., maternal mortality
rates).
Line Graphs: Tracking long-term trends (e.g., flu cases over
years).
DATA VISUALIZATION TECHNIQUES
10. STATISTICAL TECHNIQUES FOR DATA
ANALYSIS
Basic Techniques:
Mean, Median, Mode (e.g., average hospital stay duration).
Standard Deviation (e.g., variation in patient recovery
times).
Advanced Techniques:
Regression Analysis: Predicting disease spread based on environmental
factors. Time Series Analysis: Forecasting seasonal disease patterns.
Hypothesis Testing: Evaluating treatment effectiveness.
11. Epidemiology: Tracking and predicting disease outbreaks (e.g.,
COVID-19 surveillance).
Public Health Planning: Allocating resources to high-risk regions.
Healthcare Policy Making: Using data to improve vaccination and
sanitation programs.
Hospital Management: Reducing patient readmission rates by
analyzing treatment outcomes.
APPLICATIONS OF DATA ANALYSIS IN
PMCH
12. Data Quality Issues: Incomplete, inaccurate, or biased data can
mislead analysis.
Privacy Concerns: Ensuring patient confidentiality while handling health
data.
Complexity of Models: Advanced AI and statistical models require
expertise.
Data Integration: Combining health data from multiple sources for
accurate insights.
CHALLENGES IN DATA ANALYSIS
13. Data Privacy: Compliance with GDPR and health data regulations.
Bias in Data: Avoiding discrimination in predictive healthcare models.
Transparency: Clearly communicating data insights and decision-making
processes.
Accountability: Ensuring that data-driven decisions are ethical and
beneficial.
ETHICAL CONSIDERATIONS IN DATA
ANALYSIS
14. Big Data Analytics: Using large-scale health data for better decision-
making.
AI & Machine Learning: Predicting disease outbreaks and optimizing
treatments.
Cloud Computing: Storing and analyzing vast amounts of patient data
securely.
Telemedicine & Remote Monitoring: Using real-time data for virtual
healthcare.
FUTURE TRENDS IN DATA ANALYSIS FOR
HEALTHCARE
15. CONCLUSION
Data analysis is crucial in modern public health decision-
making.
It helps predict disease trends, improve healthcare services,
and guide preventive measures.
Future advancements in AI, big data, and cloud computing
will revolutionize healthcare analytics.
