Data Analytics in Healthcare Course Syllabus



The Data Analytics in Healthcare course will be conducted over 3 consecutive days, covering 7 lectures on data analytics principles and techniques, 5 lab sessions in which participants get to acquire basic data analytics skills and training on the use of the R-Commander statistical package, plenary session for course participants to present and discuss their lab work and a MCQ-based assessment of training outcomes.

Participants are required to bring their own notebook/laptop computer for the lab sessions using R-Commander

(no coding is needed).


Unit 1.      Strategic Importance of fostering a data-driven culture in an organization


1.1    Business value of data to an organization eg healthcare institution

1.2    Types of data analytics techniques and their strengths and weaknesses

1.3    Data governance and what it means to the organization

1.4    Importance of fostering a data-driven culture in an organization

1.5    The data scientist – what it takes to have the “sexiest job of this century”

1.6    What skill sets should a data analytics team have?


Unit 2.      Data processing and reporting techniques


2.1    The Data Life Cycle

2.2    Data sources and data structures – examples from healthcare

2.3    Measuring quality and safety of care

2.4    Defining and Developing Key Performance Indicators

2.5    Dashboards – uses and design pitfalls


Unit 3.      Study designs & sampling techniques (including sample size estimations)


3.1    Common study designs for data generation and collection

3.2    Types of Probability and Non-Probability Sampling Techniques

3.3.   Statistical issues involving the use of sampling

3.4    Principles of sample size estimation & power calculations for basic statistical tests

3.5    Use of WinSSize for sample size and power calculations

(all course participations will get a FREE copy of WinSSize developed by Prof KC Lun for World Health Organization)


Unit 4.      Data summary and visualization techniques


4.1    Statistics – the basics all data scientists should know

4.2    Data summary techniques (for measurement and categorical data)

4.3    Visualization techniques (for measurement and categorical data)

4.4    Interactive visualization techniques

4.5    Common misuses of data visualization


Unit 5.      Basic Statistical Techniques for Analysis of Measurement and Non-Measurement Data


5.1    Techniques for Statistical Inference – the 95% Confidence Interval

5.2    General principles involving test of statistical significance – Null Hypothesis, p-value and interpreting test outcomes

5.3    Basic statistical tests involving measurement outcome variables

5.4    Basic statistical tests involving non-measurement outcome variables

5.5    Misuses of statistical tests of significance


Unit 6.     Predictive Analytics involving Regression Techniques


6.1    Principles of predictive analytics

6.2    Predicting one outcome variable from a predictor variable – simple linear regression

6.3    Predicting one measurement outcome variable from several predictor variables – multiple linear regression

6.4    Predicting one binary outcome variable from several predictor variables – multiple logistic regression

6.5    Misuses of regression techniques in predictive analytics


Unit 7.      Predictive Analytics involving Non-Regression Techniques


7.1    Introduction to Bayesian techniques in predictive analytics

7.2   Application of Bayesian techniques in predicting health screening outcomes

7.3   Principles of Survival Analysis (techniques for analyzing time-related events) including use of Cox’s Proportional Hazards Regression

7.3   Use of Support Vector Machines for cluster analysis

7.4   Strategic applications of Sentiment Analysis in Healthcare

7.5 (in connection with 7.4) Text mining using R (with examples from Twitter)

Home | Syllabus | Timetable | Labs | Tutor Registration Venue | Course Brochure | Course Feedback