Data enabled trials at UCLH

AI tech applied to improve care and research at UCLH

28 September 2022

Technology that can interpret ‘unstructured’ text in patient records is being tested across UCLH to improve care and research.

The software called CogStack – developed by a team from the UCLH Biomedical Research Centre, the UCL Institute of Health Informatics, NIHR Maudsley BRC and King’s College London/Hospital (KCL/H) – uses a type of AI called natural language processing (NLP) to interpret this information which would otherwise need to be interpreted manually by NHS staff.

Read more.

AI tool predicts number of A&E patients admitted into hospital

8 September 2022

An artificial intelligence tool developed by UCL researchers alongside UCLH staff is being used to predict how many patients coming through the emergency department will need to be admitted into the hospital, helping planners manage demand on beds.

Read more.

Framework to enhance research using real-world data

1 September 2022

An international team including UCL and UCLH researchers have set out a framework to improve the integrity and quality of research using healthcare data.

A key aim of the CODE-EHR framework is to boost confidence in using the results of studies using data in clinical decision making.

The framework covers data quality, data privacy, transparency of processes and comparability of data. It outlines minimum standards around:

  • Datasets construction and linkage
  • How to ensure data is of high quality and fit for purpose
  • Transparency around disease outcomes and definitions, and codes and algorithms used
  • How data are analysed
  • Ethics and governance, communicating processes for consent, data privacy and patient and public involvement.

Read more.

App detecting neonatal jaundice from the eye successful in first major clinical trial

9 June 2022

A smartphone app that identifies severe neonatal jaundice could provide a cheaper alternative to expensive screening procedures, according to a study by UCLH, UCL and the University of Ghana.

Read more.

UCLH to be part of vital health data partnership

1 April 2022

UCLH is working in partnership with University Hospitals Birmingham NHS Foundation Trust in a major digital health initiative in which researchers use data collected in acute care settings to improve patient care.

Acute care is the provision of unplanned medical care, from out-of-hours primary care, ambulance assessment, emergency medicine, to surgery and intensive care. It is traditionally a difficult area to research at scale but also a national priority area for patient care.

The work means UCLH becomes a key partner in a Health Data Research UK (HDR UK) programme called PIONEER, the Health Data Research Hub for Acute Care, led by UHB.

Read more.

20 second AI heart tool begins NHS roll-out

14 March 2022

A new artificial intelligence (AI) tool that can detect heart disease in record speed, helping to improve care for heart patients, is being rolled out at UCLH.

The first-of-its-kind AI tool, developed by UCL researchers, analyses heart MRI scans in just 20 seconds whilst the patient is in the scanner.

This compares to the 13 minutes or more it would take for a doctor to manually analyse the images after the scan has been performed. It also detects changes to the heart structure and function with 40 per cent greater precision and extracts more information than a human can.

Read more.

Can MRI scans predict MS progression?

7 March 2022

Two UCL and UCLH studies will look at whether analysis of advanced ​MRI scans can predict onset of multiple sclerosis (MS) and indicate which MS patients are at risk of developing irreversible disability.

Knowing who may develop progressive MS and whose disease is likely to lead to disability – and the reasons for onset and disease progression – may enable beneficial treatments to be given at an early stage.

Read more.

New approach to make research a part of everyday clinical care

7 January 2022

UCLH clinicians and researchers are to test a novel way of running clinical trials using the hospital’s electronic health records system.

The new approach is designed to reduce research costs, answer clinical questions difficult to answer through traditional trials and enable many more studies to take place. The approach uses a computer prompt to ask a clinician making an everyday care decision, especially where there is no clear cut wrong or right answer, whether the patient should be randomised into a study or not.

Read more.

UCLH and UCL set out vision for AI to transform hearing care

21 October 2021

UCLH and UCL researchers have set out how artificial intelligence (AI) can and should be harnessed to transform hearing healthcare and research.

In a paper published in Nature Machine Intelligence, they highlight the potential of AI to significantly improve screening, diagnosis and management of hearing and ear conditions, and how ‘telemedicine’ can improve access to hearing care and enable care during a pandemic.

Read more.

UCLH testing digital programme to make research faster

22 October 2021

UCLH is testing a programme that semi-automates the transfer of patient data from electronic health records to research-specific software.

The movement of information from electronic health records to research applications for clinical research studies is currently done manually. Semi-automation could make research cheaper and faster, and bring the benefits of research to patients more quickly.

The data transfer platform programme being tested is called Archer and was developed by the company IgniteData.

Read more.

Use of innovative technology to 'unlock' health records and transform patient care

19 August 2021

Researchers at UCLH and UCL are applying AI technology to 'unlock’ data held in patients’ health records so that it can be used to improve care, planning and research.

The team from the UCLH BRC, NIHR Maudsley BRC and King’s College Hospital have developed an innovative platform called CogStack, which uses a type of AI called natural language processing which is able to interpret information in records that is held in an ‘unstructured’ way.

With government funding received from an AI Award, this CogStack project will apply natural language processing to read clinical language in the NHS and assess the magnitude of efficiency savings and improved performance if the process of clinical coding is augmented by this technology.

Read more.

Enabling multicentre clinical trials at UCLH through data harmonisation

UCLH is the first English-speaking Epic site in the world to implement SNOMED-CT, a structured clinical vocabulary designed for use in electronic health records.

With SNOMED-CT set to be more commonly used across the NHS, use of the structured language will mean data-enabled trials at UCLH will be easy to scale to other UK sites and international partners. It means data collected across all sites will be harmonised.

Use of SNOMED-CT has also enabled UCLH to develop a clinical trials database that presents UCLH clinicians and patients with a searchable list of trials that may be suitable for a patient.

Read more about use of SNOMED-CT at UCLH.

Remote monitoring of research at UCLH

UCLH has been able to keep key research studies open during the pandemic thanks to a rapid switch from ‘on-site’ to ‘remote’ trial monitoring, enabled by UCLH’s electronic health record system called Epic.

Industry sponsors of clinical trials carry out ‘monitoring’ activities to oversee their trials. This monitoring is usually done in person at trial sites.

At the start of the pandemic, UCLH rapidly implemented a secure system of ‘remote monitoring’ – allowing sponsors continued and timely oversight via digital means and without the need to be on-site during the pandemic.

Read more about the switch to remote monitoring at UCLH enabled by Epic.

Increasing study recruitment, awareness, and transparency through a digital trials database

UCLH clinicians have developed a digital database of research studies called Find a Study.

Clinicians – at UCLH and elsewhere – can use the database to suggest suitable research studies happening at UCLH to their patients, and patients and members of the public can search the database for trials they may wish to take part in.

The database has been built with clinical IT design principles in mind, meaning it can be integrated with other clinical systems such as Epic, the electronic health record system at UCLH.

Find a Study is based on a platform called Keytrials, also developed at UCLH. It is designed to be used by other NHS Trusts who can build their own versions of Find a Study, making it easier to embed research within NHS Trusts. Use of Keytrials could ultimately be scaled across the whole of the NHS.

Read more.