Artificial intelligence (AI) is shaking up the healthcare industry. With applications in drug discovery, medical imaging, disease modeling and conducting clinical trials, it promises to revolutionize the way we conduct research, treat disease and work with patients.
In drug discovery, we have seen some of the awareness behind the hype and early demonstrations of AI enabling target identification and pipeline development. AI can also support diagnostic decision-making in medical imaging, reading scans with exceptional speed and accuracy and detecting abnormalities invisible to the human eye.
AI disease modeling, on the other hand, provides a deeper understanding of the etiology, transmission and progression of diseases such as motor neuron disease, cancer and HIV. One of the most promising frontiers in this space, however, is conducting clinical trials and improving the likelihood of regulatory or technical success.
Increasing a clinical trial’s chances of success requires the careful alignment of several different factors, with clinical trial sponsors looking for solutions that minimize delays while maximizing results. Various operational and scientific decisions must be made in the clinical trial process – from site selection to parameter selection – that can help reduce trial risks and lead to better outcomes. Increasingly, AI is being used to help study teams solve some of the challenges they face, whether operational, scientific or ethical.
AI produces actionable operational insights
From an operational perspective, trial sites may vary in performance, particularly in terms of the speed and diversity of patient recruitment. Using AI analytics, sponsors and Contract Research Organizations (CROs) can leverage historical trial data or real-world data to better understand site performance and thus make more informed decisions. regarding time and resource allocation.
This knowledge and oversight can result in shortened development times, which ultimately benefits patients. This use of AI has been particularly important in the face of Covid-19, where AI has proven invaluable in rare disease trials and in oncology by helping sponsors make rapid pivots based on time predictions. real and information based on backlogs at trial sites due to an influx of Covid patients. Although still in its infancy, AI is being used to assess patient availability and diversity data, allowing sponsors and CROs to de-risk their decisions in a competitive landscape.
Scientific hypotheses can be pressure tested by AI
The recipe for trial success requires a thorough understanding of the disease in question, the patient population it affects, and potential treatments. Historically, this has been achieved through review of scientific literature and previous clinical research.
AI is now being used to augment the intelligence behind a trial. By analyzing multiple sets of inputs, including historical trial designs, drug biology, sponsor characteristics, and clinical trial results across development programs, it allows us to refine protocols and predict accurately test success.
In particular, integrating real-world data with clinical trial data can provide deeper clinical insights into patient outcomes and improve risk monitoring. It can also support decisions around endpoint selection, better equipping sponsors and CROs to target the best and most clinically relevant endpoints. AI is also used to flag real-time trends emerging in trials that otherwise would not have been evident until the end of a study when all the data is analyzed.
AI supports more diverse trials
Another challenge that has long plagued clinical trials is the lack of diversity in trial participants. From a scientific and ethical point of view, it is essential to remedy the under-representation of certain populations in trials. Research that ignores different ethnicities, ages, genders and lifestyles will not result in effective treatments that are representative of patient populations.
AI can play a role in bridging this gap, identifying trial sites best placed to serve underrepresented communities. By simulating patient models, certain conclusions and assumptions can be made about the proportion of patients in a subgroup who will respond to a particular treatment. This can inform how clinical trial teams think about recruitment and recruitment diversity. However, those involved in the development and use of AI systems need to pay close attention to dismantling rather than reproducing biases in their data collection and use. This includes the construction of models transposable to a large epidemiologically representative population. As always, regulation has a role to play in shaping approaches to risk management, data provenance and mandatory transparency.
Synthetic control arms as a powerful data-driven tool
Synthetic Control Arms (SCA), also known as External Control Arms, are another innovative tool enabled by big data, powerful computing, and advanced analytics. While AI serves to mimic real life, SCAs use real patient-level data and biostatistical methods to replicate a control arm, eliminating the need for a placebo group.
Like AI, these advanced statistical methods and analyzes require huge amounts of data to accurately mimic real life. Although well-established biostatistical approaches may not be covered by the definition of “AI”, it is important to note that traditional methods coupled with high-quality data have shown great promise and success in the contexts regulations.
Beyond diversity, patient recruitment comes with other challenges, particularly the time pressure to recruit as quickly as possible, as well as the ethical implications of recruiting for a control group of a trial for conditions where there may not be effective treatments available, such as many rare diseases. Synthetic control arms create a proxy for actual patient-level clinical trial data and can offer representative datasets that provide valuable insight into a disease, indication, or treatment.
Additionally, models can be run iteratively, which means dynamic datasets can be run through a variety of analyzes to model several different outcomes. A small number of synthetic control arm submissions have been FDA approved, including one for a hybrid design in a phase III trial in recurrent glioblastoma, a disease with few treatment options and high unmet need. SCAs are just one of many advanced analytical tools and statistical methods with great potential in the clinical stages of drug development.
The untapped potential of AI in clinical research
By harnessing the power of AI, we have gained a better understanding of disease, patient populations and potential treatments. Technology is transforming the way we conduct clinical trials: it is improving elements of trial design, including target population selection, comparison groups and clinical endpoints. It also improves patient safety and patient recruitment and gives pharmaceutical companies crucial information and analysis on how their drugs work. But we’ve only scratched the surface of what we can really achieve. The potential is enormous, and AI will certainly become an essential part of clinical research and drug development in the future.
Photo: Blue Planet Studio, Getty Images