A Quantum Leap into the Future of Clinical Trials
A few weeks ago, we shared some perspectives on applying quantum computing to the future of healthcare. But what if we took things one step further and asked, how can quantum computing be applied specifically to clinical trial design and optimization? Thankfully, experts at Deloitte, IBM, Cleveland Clinic and others answered that question for us.
Give Me the TL;DR
Clinical trials are essential to drug discovery and development, but most trials are severely delayed, have minimal success, and cost a ton of money—think billions, not millions.
Quantum computing has the potential to revolutionize clinical trials by addressing key issues such as site selection, patient identification, and drug efficacy, thereby reducing economic burdens and improving trial efficiency.
Break it Down for Me
Machine Learning and Artificial Intelligence Can Only Go So Far
Clinical trials typically utilize machine learning (ML) and artificial intelligence (AI) in trial simulations, and while these methods are beneficial, they are limited to the accuracy and reliability of input data. Why is this an issue? Because these mathematical models do not adequately consider biophysical and physiological characteristics of molecules. So what is the problem with that? This leads to discrepancies between in vitro and in vivo studies, resulting in poor efficacy and toxicity predictions when transferring results from animal models to humans.
Here’s where quantum machine learning, aka QML, comes into play. QML algorithms represent a promising advancement for overcoming limitations of traditional ML/AI methods by efficiently processing complex biological and medical data. Beyond QML, quantum computers are also very good at solving differential equations that describe our biological processes. These two ingredients make quantum computers an ideal candidate to simulate drugs interaction within the human body before conducting the trial.
Tackling the Tedious Task of Site Selection
Believe it or not, one of the most critical steps in a successful clinical trial is not the science behind the drug discovery, but rather, the location of the trial itself. A trial site needs to have the necessary infrastructure and resources (think staff, access to public transportation, etc.), but also, access to an area where enough participants can be recruited (especially if things like incidence of disease, exposure to environmental factures, regulatory requirements, etc., are needed). Quantum optimization algorithms can be applied to clinical trial site selection, enhancing the process by considering multiple factors and constraints.
I want You: Cohort Identification Optimization
Another key component of clinical trials? Patient cohorts, which are identified based on inclusion and exclusion criteria. Traditional methods like rule-based systems are time intensive, and data-driven techniques like ML/AI require multiple datasets that need to be optimized and don’t consider more personalized experiences.
Enter quantum computing. Quantum algorithms can greatly improve how we handle complex health data. Quantum feature maps can organize diverse data types in innovative ways beyond traditional computers' capabilities. Quantum neural networks leverage natural patterns in medical data to improve performance and avoid issues like vanishing gradients. Quantum GANs (Quantum Generative Adversarial Networks used for unsupervised learning) generate high-quality synthetic data with less training, which helps to create control groups for clinical trials. That said, it’s worth noting the effectiveness of these methods depends on the specific type of trial data.
In short? QML can improve cohort identification in clinical trials by processing complex, highly dimensional datasets, offering new ways to represent correlations and generate synthetic data for control arms.
Now What?
As with most emerging technologies, one question leads to another, which leads to an infinite number of additional questions. In this case, what other challenges can we solve with quantum computing as it relates to clinical trials? What are the barriers to overcome to increase the adoption of quantum computing by clinical trials experts in their established workflows? With today’s utility-scale quantum computers, what is the largest trial that can be analyzed and optimized?
We might not have all the answers now, but here’s what we do know: Quantum computing has the potential to revolutionize clinical trials by improving simulation accuracy, site selection, and cohort identification, ultimately making trials more inclusive, effective, and successful. No wonder 2025 has been deemed the international year of quantum science and technology.
-Anh Dung Pham, Quantum Computing Research Lead, Deloitte Consulting LLP