Patients set to benefit from new guidelines on Artificial Intelligence health solutions
29 September 2020
Patients could benefit from faster and more effective introduction of artificial intelligence (AI) techniques to diagnose and treat disease – thanks to a new regulatory framework aiming to improve the quality and transparency of studies in AI.
As evaluation of health interventions involving machine learning or other AI components moves towards clinical trials, an international group of scientists has developed guidelines aiming to reduce ‘wasted effort’ around the cutting-edge technology.
Future clinical trials evaluating an AI intervention will be expected – and often required – to report their publications to the new standards and will reference this work. The extra guidelines will also help medical professionals, regulators and funders assess the quality of planned clinical trials.
Researchers from the University of Birmingham and University Hospitals Birmingham NHS Foundation Trust (UHB) worked with leading institutions from across the world and have published their findings and the new guidelines today in Nature Medicine, British Medical Journal and Lancet Digital Health.
Researchers developed the additional guidance to tackle international concerns that many studies of AI are of poor quality and are not transparent. This was highlighted in research published last September, led by many of the same researchers which highlighted that less than one per cent of 20,500 analysed studies relating to health AI were of sufficient quality that independent viewers could have confidence in their results.
Professor Alastair Denniston, Lead for AI at Birmingham Health Partners Centre for Regulatory Science and Innovation, and Consultant Ophthalmologist at UHB, commented: “Patients could benefit hugely from the use of AI in medical settings, but before we introduce these technologies into everyday practice we need to know that they have been robustly evaluated and proven to be effective and safe. Our previous work showed just how big a problem this can be and that we needed a way to cut through the hype surrounding AI in healthcare.
“These new reporting guidelines – SPIRIT-AI and CONSORT-AI – provide a solution to the ‘hype’ problem. They provide a clear, transparent framework to support the design and reporting of AI trials that will help to improve quality and transparency. These extended guidelines will help to reduce wasted effort and deliver effective AI-led medical interventions to patients quicker.”
SPIRIT-AI extension is a new guideline for clinical trials protocols and CONSORT-AI extension is a new reporting guideline for clinical trial reports, for evaluating interventions with AI component.
Professor Melanie Calvert, NIHR Senior Investigator and Director of Birmingham Health Partners Centre for Regulatory Science and Innovation commented: “There is growing recognition that interventions involving AI need rigorous evaluation to demonstrate their impact on health outcomes. Without this, we risk not generating sufficiently robust evidence to decide whether AI interventions should be commissioned in the real world.
“These new guidelines will help to identify and overcome research challenges associated with AI-led health innovation, but we could not have got to this exciting point without the help of patients involved in research.”
Elaine Manna, from London, has been living with age-related macular degeneration for 20 years and was one of a number of patient partners who helped to develop the new guidelines. She was asked to provide a patient perspective on developing the guidelines after taking part in an AI research study involving Moorfields Eye Hospital NHS Foundation Trust, in London, and British technology company DeepMind Health.
Elaine commented: “A super-fast algorithm was tested on my eye – diagnosing my condition as well as an expert ophthalmologist or optometrist. This was a development with significant implications for saving sight and reducing waiting times for appointments.
“It’s vital for patients to be equally involved in their healthcare – understanding how decisions are made, being informed and involved in decision making. Helping to develop the SPIRIT-AI and CONSORT-AI guidelines, I went from thinking of myself as someone with a degenerative eye disease to someone who felt empowered.”
The SPIRIT-AI extension includes 15 new items and the CONSORT-AI extension includes 14 new items – all considered sufficiently important for clinical trial protocols of AI interventions to be routinely reported in addition to core items.
Partner institutions and organisations involved in developing the new guidelines include:
- University Hospitals Birmingham NHS Foundation Trust, UK
- Moorfields Eye Hospital, London, UK
- UCL, London, UK
- University of Manchester, UK
- The Alan Turing Institute, London, UK
- The Hospital for Sick Children, Toronto, Canada
- Ottawa Hospital Research Institute, Canada;
- University of Washington, USA
- Google Health, USA
- Salesforce, San Francisco, USA
The work was funded by a Wellcome Trust Institutional Strategic Support Fund: Digital Health Pilot Grant, Research England (part of UKRI), Health Data Research UK and the Alan Turing Institute. Calvert is an NIHR Senior Investigator. The views expressed in this article are those of the author(s) and not necessarily those of the NIHR, or the Department of Health and Social Care.