XClose

Short courses

Home
Menu

Harnessing Electronic Health Records (EHR) for Research: a Series of Short Courses

  • 7 hours per day
  • 1 or 2 days per course

Overview

Harnessing Electronic Health Records (EHR) for Research is an intensive programme of inter-related short courses.

It covers a wide range of basic and applied health research applications in this rapidly developing field.

These courses address the 'why', 'what' and 'how' of EHR research and critically evaluate scientific opportunities and challenges in what's being proposed as a new paradigm in medical research.

The courses are taught by internationally recognised faculty and span:

  • tools and techniques for assembling and interrogating large linked EHR datasets
  • formulating and answering clinically meaningful research questions
  • sharing insights across services and beyond, including with practitioners, patients and the public

This programme is run by UCL's Institute of Health Informatics. 

Programme structure

There are 12 one and two-day courses, held over three weeks.

The courses are grouped into themes:

  • Using patient data in research (week 1)
  • Practical skills for records research (week 2)
  • New approaches for records research (week 3)

You can book any number of courses (from one to all 12), based on what's relevant to your research and learning needs.

Who these courses are for

These courses are intended for people with a wide range of backgrounds, including those working in:

  • healthcare
  • epidemiology
  • biostatistics
  • health informatics
  • NHS IT
  • bioinformatics
  • genomics
  • computer science

They're suitable for people at different career stages - from those thinking of doing an MSc or PhD, to established researchers.

Cost and concessions

The standard fees are:

  • £350 - one-day course
  • £500 - two-day course

A £50 discount is available for bookings made at least 30 days before the start date of the course. 

Courses available

12 courses are available - further information on each can be found below.

Using patient data in research - week 1

Learning Health Systems

Overview

Learning Health Systems (LHS) coordinate, integrate and feedback between research, teaching and healthcare delivery.

Electronic health records and improvements in data science offer new opportunities to implement LHS at scale.

This one-day course will focus on the meaning and advantages of LHS with real examples from the UK and internationally.

You'll work through the challenges of putting this model of healthcare into practice in the real world.

In particular, you'll explore the ways in which electronic health records are already being used and could be used as an integral part of LHS.

Course team

  • Dr Amitava Banerjee (lead tutor) - Senior Lecturer in Clinical Data Science and Honorary Consultant in Cardiology at UCL and the Farr Institute of Health Informatics Research, London
  • Dr Tom Foley - Senior Clinical Lead for Data, NHS Digital, and Principal Investigator at The Learning Healthcare Project
  • Dr Charles Gutteridge - Chief Clinical Informatics Officer and Consultant Haematologist, Barts Health NHS Trust
  • Gary Leeming - Director for Informatics at the Greater Manchester Academic Health Science Network, and Chief Technology Officer at Connected Health Cities
  • Professor Daniel Ray - Director of Data Science at NHS Digital, and Honorary Professor of Health Informatics at UCL and the Farr Institute London
  • Dr Alistair Storey - Founder and Clinical Lead of the pan-London Find&Treat Service based out of University College London Hospitals
  • Dr Harpreet Sood - Associate Chief Clinical Information Officer, NHS England
  • Dr Wai Keong Wong - Consultant Haematologist and Clinical Research Informatics Officer at University College London Hospitals
SQL for Biomedical Researchers

Overview

Databases are increasingly being used for the rapid querying and construction of complex datasets in health and social care.

On this two-day course you'll learn about:

  • the theory behind the relational data model
  • how data can be modelled and stored in a relational database 
  • the different data types that are used

In practical sessions, you'll learn how to model biomedical data in a contemporary relational database management system and how to craft simple and complex queries for analysing and transforming the data.

Learning outcomes

By the end of the course, you'll:

  • understand the relational data model, data types and basic data modelling techniques
  • know how to pre-format and load data in a database system
  • know how to create simple and complex queries using SQL

Course team

  • Dr Arturo Gonzalez-Izquierdo (lead tutor) - Data Scientist at the UCL Institute of Health Informatics
  • Dr Spiros Denaxas - Senior Lecturer in Biomedical Informatics based at the Farr Institute London
  • Dr Václav Papez - Research Associate at the UCL Institute of Health Informatics
Answering Clinical Research Questions with Health Records

Overview

Harnessing the scale and depth of linked electronic health records for research has the potential to fundamentally change how healthcare is delivered, bringing enormous benefits for patients.

This one-day course introduces the breadth of health informatics research, focusing on the use of nationally available datasets for clinical research.

You'll learn about the practicalities of health informatics research - from developing the research question through to methodology and obtaining research funding.

This course is ideal for individuals with a primary degree in healthcare who are interested in health informatics research but have little or no experience in this area.

Learning outcomes

By the end of this course, you'll: 

  • have gained an overview of how health informatics can be used in clinical or population health research
  • be aware of the main sources of data for research using health informatics
  • understand the main methodological approaches required to analyse health records
  • have an awareness of the main research and information governance issues relating to health informatics research
  • understand the role of patient and public involvement in the health informatics research agenda
  • be able to identify funding streams relevant to research in this area

Course team

  • Dr Laura Shallcross (lead tutor) - National Institute for Health Research Clinical Lecturer in Public Health at UCL Institute of Health Informatics, and the Department of Health
  • Dr Ruth Blackburn - UKRI Innovation Fellow, UCL Institute of Health Informatics
  • Natalie Fitzpatrick - Data Science Facilitator, UCL Institute of Health Informatics
  • Dr Nathan Lea - Senior Research Associate, UCL Institute of Health Informatics
  • Professor Daniel Ray - Director of Data Science at NHS Digital, and Honorary Professor of Health Informatics at UCL
  • Dr Julie George - Public Health Consultant and Honorary Senior Clinical Lecturer, UCL
  • Dr Catherine Smith -  Research Associate at the UCL Institute of Health Informatics
Innovation in Care with Health Data - a one day hackathon

Overview

At this one-day hackathon you'll explore the practical challenges of handling health information to improve care.

You'll choose form a list of key data driven challenges for care, or propose your own, and work with fabricated health data to meet your chosen challenge.

Throughout the day, you'll learn about the key areas that need to be addressed to produce results for advancing care.

You'll start by exploring your proposals in terms of:

  • ethical needs
  • information governance
  • security concerns 

You'll use the data protection by design and default approach, and a data protection impact assessment as used by University College London Hospitals (UCLH). This will guide the application for accessing the data in the first place.

This course is being run by the BRC Clinical Research Informatics Unit at UCL/UCLH.

Learning outcomes

By the end of this course, you'll have gained knowledge in: 

  • basic fundamentals around technical infrastructure, processes and mechanisms of reusing routinely clinical data for healthcare research 
  • principles and Information Governance framework (including General Data Protection Regulation principles)
  • multiple innovative tools linked to Electronic Health Record (EHR) data (such as Natural Language Processing)
  • various initiatives using routinely clinical data for research and operations (such as the NIHR Healthcare Informatics Collaborative)

Course team

  • Luis Romao (lead tutor) - Honorary Research Associate at the UCL Institute of Health Informatics
  • Folkert Asselbergs - Professor of Precision Medicine in Cardiovascular Disease at Institute of Cardiovascular Science, UCL, Director NIHR BRC Clinical Research Informatics Unit at UCLH, Professor of Cardiovascular Genetics and Consultant Cardiologist at the Department of Cardiology, University Medical Center Utrecht, and Chief Scientific Officer of the Durrer Center for Cardiovascular Research, Netherlands Heart Institute

Practical skills for records research - week 2

Genetic Association Studies and Mendelian Randomisation

Overview

Mendelian randomisation studies have become increasingly popular in the past decade following the growth in availability of genome-wide data.

This two-day course will cover basic concepts behind genetic association studies with focus on genome-wide association studies (GWAS).

You'll learn about Mendelian randomisation (MR) and using genetic variants identified through GWAS to estimate the causal relationship of a non-genetic risk factor on an outcome of interest.

In the practical part of the course, you'll be taken through quality controlling genetic datasets and the use of statistical methods and software to analyse and visualise results for genome-wide data, using PLINK, HAPLOVIEW, R and Stata.

Course team

  • Dr Tom Palmer (lead tutor) - Lecturer in Medical Statistics in the Department of Mathematics and Statistics, Lancaster University
  • Dr Harpreet Sood - NHS England's Associate Chief Clinical Information Officer and a practicing NHS doctor
  • Dr Charles Gutteridge - Chief Clinical Informatics Officer and Consultant Haematologist at Barts Health NHS Trust
  • Dr Tom Foley - Senior Clinical Lead for Data, NHS Digital, and Principal Investigator at The Learning Healthcare Project
  • Dr Wai Keong Wong - Consultant Haematologist specialising in Bone Marrow Diagnostics and clinical IT and informatics
  • Dr Alistair Storey - Founder and Clinical Lead of the pan-London Find&Treat Service based out of University College London Hospitals
  • Gary Leeming - Greater Manchester Academic Health Science Network Director for Informatics and the Connected Health Cities CTO
  • Prof Daniel Ray - Director of Data Science at NHS Digital 
Introduction to R for Healthcare Researchers

Overview

The programming language R is becoming increasing popular for managing and analysing all forms and sizes of data.

This one-day course will take you from basic concepts to some of the most powerful and diverse applications of R.

You'll learn how to manage data in a variety of formats and use both inbuilt and user-defined tools to perform tasks that are routinely encountered with real data.

By the end of the course you should be confident to use R for your own research projects.

Course team

  • Dr Kenan Direk (lead tutor) - Research Associate at UCL and the Farr Institute of Health Informatics Research, London
  • Dr Ghazaleh Fatemifar (lead tutor) - Research Associate at UCL and the Farr Institute London 
Introduction to Python for Health Data Science 

Overview

The Python programming language is increasingly being used for data science in biomedicine.

This one-day introductory course will cover the basic aspects of programming in Python, using examples from biomedicine.

The interactive lecture sessions will allow you to explore concepts in-depth and raise questions, helping you to develop greater understanding of Python.

Learning outcomes

By the end of this course, you'll be able to:

  • explain the principles of Python as a programming language
  • outline and apply the interaction with Python
  • define and use basic elements of Python such as variables and expressions/operators
  • explain and apply data types such as numbers, strings, lists, sets, dictionaries, namespaces, and tuples
  • outline and use if-statements (flow controls)
  • present and practice loop-constructs in Python
  • describe the syntax of a function and demonstrate the use of functions
  • demonstrate error handling in Python
  • present the essentials of modules, libraries, file input and output, and best practices
  • apply Python in data science problems in healthcare

Course team

  • Dr Spiros Denaxas (lead tutor) - Senior Lecturer in Biomedical Informatics based at the Farr Institute of Health Informatics Research, London
  • Dr Holger Kunz (lead tutor) - Teaching Fellow at the UCL Institute of Health Informatics
  • Dr Maria Pikoula (lead tutor) - Research Fellow at the UCL Institute of Health Informatics
Visualising Health Informatics Research

Overview

This one-day course will cover the fundamental aspects of visualising health informatics research, comparing current applications and practices.

Healthcare research relies increasingly on strong relationships with information technologies, not just to expand the collectively acquired knowledge but also to translate advances into visually arresting representations.

The successful visualisation of health informatics research carries the potential to revolutionise the scientific dialogue, the public understanding and participation in medical research. Processing and translating healthcare research can relate with the public on multiple levels, with an individual researcher, patient or population group.

Learning outcomes

By the end of this course, you should: 

  • have gained an overview of how health informatics research output can be visualised
  • be aware of the main guidelines and pitfalls for the visualisation of medical research
  • understand the main methods/applications used for the visualisation of health informatics research
  • understand the role of patient and public involvement in the health informatics research agenda

Course team

  • Dr Julie George (lead tutor) - Public Health Consultant & Honorary Senior Clinical Lecturer, UCL
  • Dr Cristina Renzi - Principal Clinical Research Associate, UCL Institute of Epidemiology and Health Care
  • Dr Catherine Smith - Research Associate, UCL Institute of Health Informatics
  • Professor Paul Taylor - Professor of Health Informatics at UCL Institute of Health Informatics.
  • Jessica May - Project and Engagement Manager for the UKCRC Tissue Directory and Coordination Centre 

New approaches for records research - week 3

Phenotyping Methods for Linked Electronic Health Records (EHRs) - CALIBER

Overview

Primary and secondary care records are increasingly being linked for use in research.

These data, however, are collected as part of routine care or for administrative purposes and a significant amount of work is required to build robust and accurate definitions of clinical concepts that can be used to identify cases for further study.

On this one-day course you'll learn about the basic theory behind the extraction of phenotype data from combined data resources such as CALIBER.

CALIBER (Clinical research using linked bespoke studies and electronic health records) is a research platform consisting of 'research ready' variables extracted from linked EHRs from primary care, coded hospital records, social deprivation information and cause-specific mortality data.

Learning outcomes

By the end of this course, you'll:

  • be familiar with two contemporary primary and secondary data sources - Clinical Practice Research Datalink (CPRD) and Hospital Episode Statistics (HES)
  • understand what types of EHR data are collected and the different ways in which data are recorded
  • understand how to combine linked EHR data sources to define disease cases

Course team

  • Dr Arturo Gonzalez-Izquierdo (lead tutor) - Data Scientist at the Farr Institute of Health Informatics Research, London
  • Dr Jennifer Quint (lead tutor) - Senior Lecturer in Epidemiology at the London School of Hygiene & Tropical Medicine, and Honorary Consultant in Thoracic Medicine at University College London Hospitals NHS Trust
  • Dr Spiros Denaxas - Senior Lecturer in Biomedical Informatics at the Farr Institute London
  • Dr Ghazaleh Fatemifar - Research Associate, UCL and the Farr Institute London
  • Dr Constantinos Parisinos - Wellcome Trust Clinical Research Training Fellow at UCL, and Specialist Registrar in Gastroenterology and Hepatology at Barts Health NHS Trust
Machine Learning: Supervised Learning

Overview

In an era of modern healthcare, it's essential that all stakeholders are aware of the foundations of machine learning and the latest trends in this field.

On this one-day introductory course you'll learn about the basic aspects of machine learning in healthcare, and the associated challenges and opportunities.

Through interactive lectures and practical and group discussions, you'll explore concepts in-depth and raise questions.

You'll develop greater understanding of the role of machine learning in healthcare to automatically discover new associations and the construction of clinical rules and predictive models.

Learning outcomes

By the end of this course, you should be able to:

  • outline the requirements for applying machine learning to healthcare data and assess when their application is warranted
  • describe methods for the selection and extraction of relevant features
  • investigate and define suitable machine learning methods for problems in prevention, diagnosis, prognosis, phenotyping and therapy
  • design effective evaluation frameworks
  • contrast the strengths and weaknesses of various machine learning methods

Course team

  • Dr Holger Kunz (lead tutor) - Teaching Fellow at the UCL Institute of Health Informatics
  • Dr Dinisio Acosta - Senior Research Associate and Director of the Graduate Programme in Health Informatics at UCL 
Machine Learning: Unsupervised Learning

Overview

Unsupervised learning methods are essential tools for data scientists and statisticians. They're often applied as a pre-processing step for feature selection and dimensionality reduction in statistical learning tasks.

Cluster analysis is the most popular example of stand-alone unsupervised learning methods, often seen as an exploratory and hypothesis-generating approach.

Despite its wide use in many fields, cluster analysis is challenging to design, implement and evaluate. The challenge stems from the exploratory nature of the clustering process, and the multiple ways the analysis outputs can be interpreted.

On this one-day course you'll learn about the fundamentals of cluster analysis and dimensionality reduction. This will help you confidently design and implement such methods independently on a variety of datasets.

Course team

  • Dr Maria Pikoula (lead tutor) - Research Fellow at the UCL Institute of Health Informatics
Analysing Free Text in Medical Records

Overview

The secondary use of Electronic Health Records (EHRs) has transformative potential for how healthcare research is conducted, providing new possibilities in areas of business intelligence, observational research, clinical trial recruitment and decision support.

However, as much as 80% of the data in EHRs are in the form of unstructured text, making this information 'invisible' for standard analysis techniques.

This two-day course will provide an introduction to the field of clinical natural language processing (NLP) and the complexity that different NLP problems pose.

The course involves a series of talks and practical sessions. If you want to take part in the practical sessions you should have some basic programming experience.

Course team

  • Dr Angus Roberts (lead tutor) - Senior Research Fellow in The University of Sheffield's Natural Language Processing group in the Department of Computer Science
  • Dr Sumithra Velupillai (lead tutor) - visiting researcher at the IoPPN/BRC Nucleus, King's College for a three-year Marie Sklodowska Curie Actions/Swedish Research Council fellowship

Course information last modified: 7 Aug 2019, 14:52