Healthcare & Medical Analytics (online & on campus)

This module, which I have created and continuously develop in response to rapid innovation in the field, explores how data analytics is used to identify, understand, and address critical challenges in both private and public healthcare systems. It focuses on how data can be leveraged to inform strategic and operational decisions in an increasingly complex and data-rich environment.

​

Students will develop a strong understanding of the specific challenges and dynamics of the healthcare sector, and how data, when thoughtfully applied, can support more effective, equitable, and efficient healthcare delivery. We will practice this using a range of descriptive analysis methods, econometrics, syntheic data creation, data scrapting and machine learning methods. 

​

To achieve this, we examine the structure and incentives of healthcare markets, the business models that underpin successful health ecosystems, and the analytical tools required to navigate them. The module combines theoretical foundations with hands-on experience, using real-world medical and healthcare datasets and applying techniques introduced earlier in the programme.

We will work with a range of data sources, including:

• Self-reported individual-level data from the UK and the US

• Patient-level data

• Healthcare provider data (including GP-level and synthetic datasets)

• Pharmaceutical industry data at the market level

 

In addition, the module addresses key issues such as health policy, data privacy, security, and information governance.

​

Examples of topics we cover in this module: 

• What makes healthcare markets unique? Needs, incentives, and the challenge of setting priorities.

• Measuring health: From patient outcomes to population-level indicators - strengths and limitations.

• Environmental health and spatial analysis: Using geographic data to support public health insights.

• Understanding self-reported data: Biases, causal inference, and interpretive caution.

• Predictive analytics in healthcare: Applications such as forecasting missed appointments and resource use.

• Text and sentiment analysis: Insights from qualitative data in patient feedback and beyond.

• Machine learning applications: For example, using classifiers to predict obesity or identify at-risk populations.

 

Learning Outcomes

​

By the end of the module, students will be able to:

• Formulate key analytical questions relevant to healthcare providers, pharmaceutical firms, and public health agencies.

• Identify and interpret core metrics used in healthcare analytics, while recognising their limitations.

• Understand the unique features of health-related data and the privacy and ethical concerns that come with it.

• Apply statistical, econometric, and machine learning methods to real-world healthcare data.

• Evaluate the appropriateness and implications of different analytical approaches and metrics in healthcare settings.

• Develop evidence-based recommendations and identify areas for improvement in healthcare delivery and outcomes.