Democratising clinical trials among patient groups must become a pivotal target throughout the healthcare ecosystem
The success of multiple vaccines – with now over four billion administered around the world – has highlighted the power of emerging technologies as a catalyst for driving medical innovations in the development of effective healthcare treatments. Whether it’s quickly identifying the protein that affects an immune response, scaling up the manufacturing of vaccines to tens to millions of doses, or rapidly designing clinical trials and recruiting patients, patient data has played a critical role.
Having access to anonymised and de-identified patient data – such as artificial intelligence (AI) and machine learning that allow clinicians to analyse and act upon this data more quickly – has been key to shaping modern approaches.
There are many challenges associated with traditional clinical trial approaches that have stifled medical advances. Factors such as speed, accuracy, costs, failure rates and diverse patient population recruitment in combination with our lack of understanding the underlying biology of diseases, hinder the evolution of the process.
The use of data science and technology have been pivotal to drive positive change in how clinical trials are executed, and the way researchers use data to inform drug discovery and development, allowing for greater targeting amongst patient populations.
Conducting clinical trials through a multidisciplinary, collaborative and innovative approach will further speed up the development of vaccines, drugs and other treatments.
Synthetic control arms have the potential to reduce the amount of time it takes to develop medical treatments, fast-track participant enrolment and improve patient engagement by allying patient concerns around receiving a placebo.
Furthermore, it enables the management of large diverse trials while providing the opportunity to reduce both the time and costs associated with the clinical trial process. Importantly, this enables researchers to gain a better understanding around the efficacy of investigational treatments and also potentially improve the quality and ethics of clinical trials – particularly where use of a placebo may be deemed unethical.
Synthetic control arms use both real-world data that has previously been collected from sources such as electronic patient records, medical devices and historical clinical trial data to model patient control groups.
This ensures that all patients receive the active treatment, removing the need to administer placebo treatments to patients and reducing at least one ethical complication from the trial process. This approach can be particularly useful for rare diseases where patient populations are smaller or where lifespan is short due to the aggressive nature of the disease.
Deploying synthetic control arms throughout clinical trials in this way to bring trials closer to the patients can hugely reduce the inconvenience of travelling to research sites and the burden of undertaking consistent medical tests. Time spent on recruiting representative patients during the trial process can also be much more efficient.
Keeping it real
Real-world data analytics platforms for the life sciences and healthcare industries pioneer new models for democratising life sciences research, dramatically lowering barriers in accessing insights from global anonymised data.
The combination of AI and data analytics allows researchers to easily define patient cohorts using multiple criteria and build control arms in the platforms, helping them to conduct feasibility analysis for running synthetic control arms. This, in turn, improves understanding of inclusion and exclusion criteria and provides input into clinical design trial.
Using real-world data from a wide variety of resources also allows the creation of a comparator arm, as well as the analysis of outcomes by product or class across different health systems in order to understand real-world patient journeys.
Having access to an AI-driven data analytics platform also allows researchers and clinicians to communicate and collaborate with each other, creating virtual research networks that connect professionals across the healthcare ecosystem, while building communities with common interests in particular disease areas. It is with this model of working that we will begin to see the industry take strides in life sciences research innovation.
It’s critical that the industry, along with other key stakeholders, works with regulators to determine how patient data can be analysed to speed up the process of bringing medicines to more patients, while maintaining trust that the way that data is used meets the highest data security and governance standards.
Patients will always have ownership of their data. It is their right to know what it is used for and that they have a clear understanding of the positive impact this will have for the future of healthcare as a whole.
There is an ongoing mindset shift towards using AI in the pharma and healthcare sector, partially triggered by the pandemic and the rapid development of the COVID-19 vaccines.
Having access to real-world analytic tools provides clinicians, research academics and life sciences professionals with an instant AI research capability. Ultimately, these insights allow them to drive improved patient care, accelerate medical development and revolutionising life sciences research.