By Dr Francesca Properzi, PhD. Research Manager, and Maria João Cruz, Research Analyst, Centre for Health Solutions
This week we launched the third report in our series on the impact of artificial intelligence (AI) across the biopharma value chain. This latest report, Intelligent clinical trials: Transforming through AI-enabled engagement, explores how AI, in particular machine learning and natural language processing, can reduce clinical trial cycle times while reducing the costs and improving the productivity and outcomes of clinical development. In this blog, we highlight the main takeaways from our report.
Why clinical trials must transform
For many years, ‘linear and sequential’ clinical trials have remained the accepted way to ensure the efficacy and safety of new medicines. However, the lengthy tried and tested process of discrete and fixed phases of randomised controlled trials (RCTs) was designed principally for testing mass-market drugs and has changed little in recent decades. Consequently, as we demonstrate in our annual Measuring the Return from Pharmaceutical Innovation report, although biopharma companies have enjoyed numerous scientific breakthroughs, and experienced exceptional returns in some areas, over the past 10 years they have seen their rates of return steadily decline.
A critical reason for this decline is that the traditional clinical trial process lacks the analytical power, flexibility and speed required to develop complex new therapies that target smaller and often heterogeneous patient populations. Moreover, patient selection, recruitment and retention, together with difficulties managing and monitoring patients effectively, have become increasingly challenging, contributing to high trial failure rates and raising the costs of R&D. Currently, of the 10,000 candidate drugs originally screened, only ten make it to clinical trials and of those only one is approved for use with patients.
The impact of AI on the clinical trial process
Over the past few years, biopharma companies have been able to access increasing amounts of scientific and research data from a variety of sources, known collectively as real-world data (RWD). Unlocking RWD using predictive AI models and analytics tools can accelerate the understanding of diseases, identify suitable patients and key investigators to inform site selection, and support novel clinical study designs.
The adoption of AI technologies is therefore becoming a critical business imperative; specifically in the following six areas.
- Clinical trial design: Increasing amounts of scientific and research data, such as data from current and past clinical trials, patient support programmes and post-market surveillance, have energised trial design. AI-enabled technologies, having unparalleled potential to collect, organise and analyse the increasing body of data generated by clinical trials, including failed ones, and extract meaningful patterns of information to help with design.
- Patient enrichment, recruitment and enrolment: The FDA’s new guidance on clinical enrichment strategies is aimed at improving patient selection and optimising a drug’s effectiveness. We believe that AI technologies could enhance each of these strategies (see figure 1).
Figure 1. How AI technologies can help deliver clinical trial enrichment strategies highlighted in FDA guidance
- Investigator and site selection: A crucial aspect of a clinical trial is selecting high-functioning investigator sites with qualities such as effective administrative procedures, resource availability and clinicians with in-depth experience and understanding of the disease. AI-enabled technologies can help optimise the identification of target locations, investigators, and trial candidates, and the collection and collation of evidence to satisfy regulators that the trial process complies with Good Clinical Practice requirements.
- Patient monitoring, medication adherence and retention: AI algorithms can be used to help monitor and manage patients by automating data capture, digitalising standard clinical assessments and sharing data across systems. AI algorithms, in combination with wearable technology, can enable continuous patient monitoring and real-time insights into the safety and effectiveness of treatment while predicting the risk of dropouts, thereby enhancing engagement and retention.
- Using operational data to drive AI-enabled clinical trial analytics: Functional data silos and disparate systems can hinder biopharma companies from having a comprehensive view of their clinical trials portfolio. Consolidating all data, whatever the source, on a shared analytics platform, supported by open data standards, can foster collaboration and integration and provide insights across vital metrics. Incorporating a self-learning system, together with data visualisation tools can provide reliable insights.
- Outsourcing and strategic relationships to obtain necessary AI skills and talent: Many biopharma companies see Contract Research Organisations (CROs) as strategic partners, providing access not only to specialised expertise, but also to a wide range of potential trial participants. Biopharma companies have also attracted the attention of tech giants looking to expand into healthcare. For biopharma, tech giants can be potential partners and/or competitors; presenting both opportunities but also threats as they disrupt parts of the industry. At the same time, an increasing number of digital technology startups are working in the clinical trials space, partnering or contracting with biopharma. These partnerships marry tech giants and startups core expertise in digital science with biopharma’s knowledge and skills in medical science.
Clinical trials of the future
For the next few years, RCTs are likely to remain the gold standard for validating the efficacy and safety of new compounds in large populations. However, healthcare is on the brink of large-scale disruption driven by interoperable data, open and secure platforms, personalised care and a shift from healthcare to health. Biopharma companies are set to develop tailored therapies that cure diseases rather than treat symptoms. Consequently, clinical trials will need to accommodate more targeted approaches. Regulators around the globe have released guidance to encourage biopharma companies to use RWD strategies. Innovative trials using RWD are likely to play an increasing role in the regulatory process by defining new, patient-centred endpoints.
In the future, all stakeholders involved in the clinical trial process will align their decisions with patients’ needs and keep trial participants fully informed about the trial, the process and its progress. The use of AI-enabled digital health technologies and patient support platforms will revolutionise clinical trials with improved success in attracting, engaging and retaining patients before, during and after the research process after study termination (see figure 2).
Figure 2. Patient’s journey through an AI-enabled clinical trial
In the future, AI, together with enhanced computer simulations and advances in personalised medicine, will lead to in silico trials, using advanced computer modelling and simulations in the development and regulatory evaluation of a drug. The next decade will see an increase in the implementation of virtual trials that leverage the capabilities of innovative digital technologies to enable faster enrolment of more representative groups in real-time and in their normal environment, monitor patients remotely and lessen the financial and time commitments required. Indeed, half of all trials will be done virtually, with convenience improving patient retention and accelerating R&D cycle times.
Our second report of the series, Intelligent drug discovery: Powered by AI, explores how AI is helping to transform the drug discovery process, with seven case studies that illustrate dramatic reductions in discovery timelines and improved accuracy of predictions on the efficacy and safety of potential drug candidates. In this report on ‘Intelligent clinical trials’ we feature six case studies that illustrate how biopharma companies are already adopting AI technologies to improve their trial processes. While AI is yet to be widely adopted and applied to clinical trials, we show through our research the potential to transform clinical development.
Indeed, we expect the use of AI technologies to lead to faster, safer and significantly less expensive clinical trials. A crucial aspect is the potential to improve patient experience which will help biopharma companies embed patient-centricity more fully across the whole R&D process. Ultimately, transforming clinical trials will require companies to work entirely differently, drawing on change management skills, as well as partnerships and collaborations. If biopharma succeeds in capitalising on AI’s potential, the productivity challenges driving the decline in the rate of return on investment in innovation could be reversed, enabling the industry to thrive.