Blogs & more

The use of Artificial Intelligence in the clinical trial setting

Written by Andrew Mills Business Development Director, CHASE clinical
The use of Artificial Intelligence in the clinical trial setting

Artificial intelligence (AI) is often defined as technology that enables a computer to think or act in a more 'human' like manner.  This is achieved by taking in various information from its surroundings.  The subsequent response is based on what the computer learns or senses.  This blog discusses briefly AI in the UK healthcare system and its applications in the clinical trial setting.

The technology behind AI is becoming more and more advanced. Machines are improving their ability to 'learn' from mistakes and change how they approach a task the next time.  This can be applied to healthcare settings in a variety of ways, and NHS England is setting up a special laboratory to boost the role of AI within the health service.

Health Secretary, Matt Hancock, recently announced that AI technology has enormous power to improve care, save lives and ensure doctors have more time to spend with patients in an ever-demanding environment, and consequently the UK government is investing £250 million in AI health technology.

AI can be used in healthcare for research purposes in clinical trials or real world data situations and, additionally, to improve patient care through improved diagnosis and monitoring in everyday clinical practice.

The era of blockbusters is coming to an end which means large pharma and other drug developers have significant challenges. R & D costs have continued to accelerate and it takes on average 10-15 years & $2 billion to get a new drug to market.  About half of this investment is devoted purely to clinical trials so can AI help to reduce costs or improve productivity?

This technology has not yet had a significant impact on clinical trials.  However AI-based models are supporting clinical trial design, for example in the critical area of patient recruitment.  AI-based monitoring systems are used to improve study adherence and decrease patient dropout rates.

Harrer and colleagues1 reported that AI can potentially improve the success rate of clinical trials by:

  • Identifying and characterising patient subpopulations best suited for specific drugs.
  • Regulatory bodies, governments, large Pharma and start-ups are exploring and implementing AI for improving clinical trial design.
  • Efficiently measuring biomarkers that reflect the effectiveness of the drug being tested.

The authors also discuss the direction of travel for patients. For example:

  • AI-enabled systems potentially allow patients more access to their personal data & more control over personal data.
  • AI could monitor individual patients' adherence to protocols continuously in real time to support required changes.
  • These techniques could help guide patients to trials.
  • AI can have impact on improving patient monitoring before and during trials, for example neurological studies.

The review also evaluated the potential implications for pharma, which included:

  • Computer vision algorithms that could potentially pinpoint relevant patient populations through a range of inputs from handwritten forms to digital medical imagery.
  • Applications of AI analysis to failed clinical trial data to uncover insights for future trial design and learn from potential trial failures.
  • The use of AI capabilities such as Machine Learning (ML), Deep Learning (DL), and Natural Language Processing (NLP) for correlating large and diverse data sets such as electronic health records, medical literature and trial databases. This learning should improve trial design, patient-trial matching and patient recruitment.

"Health AI" is a growing field connecting medicine, pharma, data science and engineering.  This means the next generation of health-related AI experts will need a broad array of knowledge in analytics, coding and technology integration.  Data privacy, security and accessibility, are critical elements and with current GDPR, the ethics of applying AI techniques to sensitive medical information.

Further research is necessary before the AI demonstrated in pilot studies can be integrated in clinical trial designs.  However one thing is certain, the use of AI will continue to increase as its utility and value is further validated. Which organisations are likely to adopt this technology first and what learnings will early adopters of this technology be willing to share?  Exciting times ahead in the field of Health AI for sure.


  1. Trends in Pharmacological Sciences, August 2019, Vol. 40, No. 8 5