Clinical Data Science / Course details

We offer our PgCert Clinical Data Science units as individual continuing professional development (CPD) courses.

These units aim to empower healthcare professionals from across the health and social care workforce, from knowledge and library specialists to nurses, AHPs, healthcare scientists, doctors and beyond, to apply data science in practice and translate data into patient benefit.

Our CPD units will give professionals across the board the opportunity to develop their data science skills and drive digital transformation in their practice. Participants will bring with them their clinical, health and social care knowledge and experience, and the programme will provide the computer science methods and maths, stats and machine learning skills to allow practitioners to make use of their data, adding value to their clinical work to benefit patients.

We offer the following units:

Clinical Data Engineering introduces learners to data wrangling, data quality and data governance providing them with an understanding of structured and unstructured data formats, how data is modelled in various commonly used database systems, as well as an awareness of the role of the data engineer/data engineering in healthcare.

Maths, Stats and Machine Learning covers data analysis methods, including statistical learning (statistics and machine learning methods) supported by knowledge and understanding of the mathematical principles underpinning these methods.

Data Visualisation and Communication focuses on the theories of visualisation and how to explore and communicate data through visualisations that can be tailored for different audiences without unintentionally misleading or confusing the intended recipient.

Human Factors and Digital Transformation provides students with an overview of the process of capturing and presenting user requirements and implementing and evaluating systems in the clinical, health and social care environment.

Clinical Data Engineering

• Gain hands on experience accessing and transforming data into suitable data analysis formats (e.g. application of statistical methods/machine learning algorithms) by creating data processing pipelines.
• Build familiarity with using, accessing and querying data in different database storage systems (e.g. relational and NoSQL database systems).
• Develop awareness of the importance of data security issues from a technical and legislative perspective.
• Explore the benefits and challenges with accessing health/clinical data.
• Understand and practice data cleaning.
• Gain awareness of all the typical stages of the data processing pipeline.

Maths, stats and Machine Learning

• Apply mathematical concepts to common data science and machine learning methods.
• Practice with writing analysis scripts (using R and Python) to analyse datasets using statistical and machine learning methods.
• Understand the effect and importance of the data and modelling choices on algorithm output.
• Explore of ethical and legal issues around the use of machine learning in health and clinical care

Data Visualisation and Communication

• Equip students with the knowledge and tools to use data visualisation for exploration and explanation of data.
• Create data visualisations, including interactive data visualisations and digital dashboards.
• Communicate a narrative about data to clinical and patient stakeholders adjusting the approach depending on the audiences needs.
• Understand the theories of designing good visualisations that communicate the intended message clearly without misleading or confusing the target audience.

Human Factors and Digital Transformation

• Learn methods needed to capture and represent user requirements.
• Map and understand existing work flows and digital/data/AI driven implementation challenges.
• Explore tools and techniques for the evaluation of data products and services.
• Develop and design systems using user-centred and co-design principles.
• Understand and raise awareness of the challenges and opportunities for digital transformation in health and social care.

As busy professionals it can be hard to fit academic study around work and home life. We have designed the course to be as flexible as possible with online self-directed material, optional online synchronous sessions that are recorded so participants don't miss out if can't make all the sessions.

Course content is delivered online, enabling you to study around other commitments. We also have mandatory networking and team working events (one day for each unit, with the exception of the human factors unit that has two) and activities to help maintain motivation and build communities of practice.

Co-creation

The course has been co-designed with end users and other stakeholders (including patients) to ensure that it is of real value to working professionals in health and social care. We have partnered with leading organisations in health education and care, including the National School of Healthcare Science in the National Health Service and The Christie NHS Foundation Trust.

Professional diversity

We aim to enable as widespread a representation of healthcare professional groups and roles (such as knowledge and library specialists, nurses, AHPs, healthcare scientists, doctors and beyond) as possible across the course to ensure professionals feel empowered to apply data science in practice and translate data for organisational and patient benefit.

Expert teaching

You will learn with experts that have clinical as well as industry experience working in healthcare, data science and data engineering. There will also be a variety of guest speakers from industry, academia, and healthcare.

The course is mainly delivered online, with self-directed learning materials that can be accessed at any time.

This is also supported by synchronous webinars, forums and digital communication platforms that help you to build an active learning community and benefit from networking.

There is also a face-to-face day allowing you to visit Manchester, make use of the university campus and equipment, and connect with educators and fellow students in person. The Human Factors unit has two face-to-face days.

Sessions are recorded so that students who cannot make synchronous or face-to-face sessions are still able to view any sessions they miss.

Your assessment will vary depending on units chosen:

Clinical Data Engineering

• Learners create an authentic data management plan for a fictional scenario or real-world project that they would like to implement in their organisation.

Maths, Stats and Machine Learning

• Learners create a short report about how a form of either statistical or machine learning modelling could be used to drive improvements in a healthcare setting.

Data Visualisation and Communication

• Learners record a 10 minute presentation describing a set of data visualisations they have created for a technical and lay audience.

Human Factors and Digital Transformation

• Recorded PowerPoint (or equivalent) presentation detailing a proposal for a digital transformation project detailing problem, method of stakeholder engagement and elicitation of requirements, technology proposed, method of evaluation, challenges/barriers to implementation and how these may be overcome