SamurAI: Privacy notice

Researchers are analysing de-identified routine patient records to develop algorithms alerting doctors when antibiotics may be changed.

Overview

The SamurAI project is a research project conducted at University College London Hospitals NHS Foundation Trust (ULCH) by researchers employed by University College London (UCL).

The SamurAI project re-uses data collected by UCLH about from patients as part of their care and support (‘patient data’).

This privacy notice outlines the purpose the SamurAI project, and how it collects and uses patient data.

You can find general information about how patient data are used in research at the links below:

Objectives of the SamurAI project

The Problem

Antibiotics save lives, but the more they are used, the less effective they become. Infections learn how to resist them. More than 50,000 people in the UK have infections that resist antibiotics, and this number will increase if we do nothing.

In a typical hospital, around 150 patients are taking antibiotics on any one day. Research suggests that 30-50% of individual prescriptions could be avoided if they were reviewed by a specialist in antibiotics looking at things with the danger of overuse in mind. However, there are currently not enough of these specialists - microbiologists and antibiotic pharmacists - to review every antibiotic prescription and provide feedback to every doctor. For last 2 years, researchers at University College London have been working with infection specialists, health psychologists and designers to solve this problem.

The Solution

We need to use fewer antibiotics. But antibiotics seem so helpful that this has not happened. The use of antibiotics in UK hospitals is still growing. Our plan is to develop and test an antibiotic surveillance system we call SamurAI. It involves computers working in a way that copies human thinking (‘artificial intelligence’) and it takes advantage of the introduction of electronic patient records into UK hospitals. The system will combine historical data for patients prescribed antibiotics with the findings of specialists in infection as they review prescriptions. Under specialist medical supervision, the computer system will ‘learn’ what works best and when to start, stop or change the use of antibiotics. Once up and running the system should be able to identify and flag patients who should be reviewed by specialists and guide antibiotic treatment for individual patients. The research will start at University College London Hospitals (UCLH), but our aim is to roll it out to 3 different hospitals within 4 years.

Research plan

First, we will ‘train’ SamurAI to recognise when antibiotics should be stopped or changed. SamurAI will learn using past patient data which record when infection specialists decide to stop or change antibiotics.

Then, we will evaluate whether SamurAI can accurately and safely identify patients who can stop, change or switch antibiotics. We will compare SamurAI’s predictions to what happens when experts review 720 patients taking antibiotics. If SamurAI’s predictions and the experts mainly agree, we will apply for funding to further develop and test SamurAI through carefully designed trials.

We expect SamurAI coud reduce antibiotic use by 10-20%, benefiting patients by reducing their time in hospital and the risk of side-effects from antibiotic treatment. Reduced use will also prolong the lifespan of our existing antibiotics. Once we have tested the system in our three hospitals, we aim to introduce it in new hospitals by 2027.

We will involve patients, the public and healthcare workers at all stages of the project, to understand their concerns about using patient data and agree how to protect it. We will hold a workshop to share research findings with patients.

Information collected for this research

University College London (UCL) has a data processing agreement with University College London Hospitals NHS Foundation Trust.

This agreement allows UCL researchers to access and analyse de-identified hospital data previously collected by UCLH from patients for individual care.

These data belong to:

  • adults aged 18 years or more on admission
  • who have not opted out from the use of their data for research or planning purposes through the National Data Opt-Out

These data contain information on:

  • patient sex, ethnic group and age
  • inpatient admissions, procedures, diagnoses, antibiotics prescribed and administered
  • clinical observations (vitals)
  • clinical investigations (microbiology sample testing, blood tests, renal function)
  • decisions made by infection specialists when reviewing antibiotics (for instance: stopping or changing antibiotic prescriptions).

These data are kept safe and secure, to protect your confidential information. There are four ways that privacy is protected:

  • removing details that identify a person, such as NHS numbers, Medical Record Numbers, dates of birth.
  • data are held in a secure computer network within University College London Hospitals NHS Foundation Trust (UCLH).
  • University College London researchers have signed an honorary contract with UCLH. This means are subject to the same obligations and training as UCLH health professionals.
  • the study was reviewed by an NHS research ethics committee and by UCLH’s Information Governance Panel, to make sure the reason for using patient data is appropriate.
  • data will be stored until 31 August 2022. All records will then be erased.

The legal basis for processing personal data for this purpose data at UCL falls under Article 6(1)(e) of the General Data Protection Regulations (GDPR), i.e. “a task carried out in the public interest”. It also falls under Article 9(2)(j), “processing is necessary for archiving purposes in the public interest, scientific or historical research purposes or statistical purposes”.

Ethical approval for this research was granted by the Health Research Authority West Midlands - Edgbaston Research Ethics Committee on 30 October 2020.

Your rights

Under data protection laws, you have rights including:

  • Your right of access - You have the right to ask us for copies of your personal information.
  • Your right to rectification - You have the right to ask us to rectify information you think is inaccurate. You also have the right to ask us to complete information you think is incomplete.
  • Your right to erasure - You have the right to ask us to erase your personal information in certain circumstances.
  • Your right to restriction of processing - You have the right to ask us to restrict the processing of your information in certain circumstances.
  • Your right to object to processing - You have the the right to object to the processing of your personal data in certain circumstances.
  • Your right to data portability - You have the right to ask that we transfer the information you gave us to another organisation, or to you, in certain circumstances.
  • You are not required to pay any charge for exercising your rights. If you make a request, we have one month to respond to you.

Please contact the UCLH Data Protection Officer below if you wish to make a request.

How can I complain?

University College London sponsors this study and is acting as Joint Data Controller together with University College London Hospitals NHS Foundation Trust.

If you wish to complain about our use of personal data, you can contact University College London Hospitals NHS Foundation Trust’s Data Protection Officer at the address below:

Data Protection Officer
2nd Floor
Maple House
Tottenham Court Road
London
W1T 7NF
Email: UCLH.IGQueries@nhs.net

You also have the right to lodge a complaint with the Information Commissioner’s Office (ICO) (the UK data protection regulator).  For further information on your rights and how to complain to the ICO, please refer to the ICO website.

How can I contact the researchers?

This research is led by Dr Laura Shallcross at University College London (UCL) and Dr Michael Brown at University College London Hospitals.

If you have questions or concerns about the study please contact:

Dr Laura Shallcross
UCL Institute of Health Informatics 222 Euston Road
London
NW1 2DA
Email: l.shallcross@ucl.ac.uk

Details about the project

Full title: Stewardship of Antimicrobials using Real-Time Artificial Intelligence - Phase 1: Pre-clinical device development or performance testing

IRAS project: 282591

UCLH R&D reference: 132886

HRA Research Ethics Committee reference: REC 20/WM/0269.

When was this privacy notice last updated?

This privacy notice was last updated in November 2020 and may be amended from time to time.



© 2020-2021 University College London. All rights reserved.

Powered by Hydejack v9.0.3