How can AI improve patient outcomes in clinical trials?

Welcome back to our blog series where we share some of the highlights and key takeaways from our fireside chat with CEO of Simbec-Orion, Fabrice Chartier, and CEO of, Joern Klinger.

Our last blog post covered whether AI can help with achieving orphan drug status, recent trends in clinical trial design, how AI can integrate with existing processes, and what data’s platform utilises to predict clinical outcomes.

This post continues the discussion on how early utilisation of AI could help de-risk and accelerate clinical development, by discussing whether there is support for rare indications and how implementing AI in clinical trials can improve outcomes for patients.

Can support de-risking clinical trials for rare patient populations where the data is limited?

Joern Klinger, CEO,
Yes, we can. The causal modelling approach I described earlier is called Mendelian Randomization, because instead of assigning patients to treatment and placebo groups, you use the Mendelian rules, how they differ in the drug target gene to do that. It’s the standard technique, but can be data hungry. We’ve developed and successfully used our own techniques in a commercial and scientific setting and they work with very small data sets. This is of course key when you deal with rare diseases, where patients often feel left alone.

Could AI be utilised to support more equitable healthcare[1] and help eliminate bias[2] in clinical research, perhaps by identifying missed opportunities in specific patient groups?

Fabrice Chartier, CEO, Simbec-Orion
As a service provider, we can use our experience and expertise to provide recommendations on strategy, but in the end, the decision will always be made by the sponsor. With the additional insights available through’s technology, we now have a major ally to support our recommendations. As a CRO specialised in Oncology and Rare Disease for 30 years, we have seen many situations where certain patients’ groups were excluded from a clinical trial for the wrong reasons. The nature of AI-enabled causal modelling will support giving early direction for specific patient groups that can benefit from a certain drug. It will represent incredible new avenues for certain drugs that may have been abandoned. Certainly, I can see a lot of potential for AI to unlock access to better treatments for patient groups who may not have been considered previously.

What could ‘accelerated clinical development’ and the use of AI could mean for patients?

Fabrice Chartier, CEO, Simbec-Orion
Improving the patient experience in clinical trials is one of the most important benefits that AI can provide in clinical development. If we can target the right patient populations earlier, there is an obvious and immediate benefit for the patients.

If you look at “basket-type” protocols, you enrol a range of different patient populations to select one or two at the end of the project. For this type of trial, you need to enrol a lot of patients to participate, who may be suffering from a very severe condition, and after participating in the early phase study, the treatment may have no benefit at all.

With AI supporting clinical trials, we can enrol patients with a much higher expected clinical benefit. In addition to the ethical impact, patients may be more motivated to join a study which is predicted to be effective. Those patients that we know, upfront, are unlikely to benefit from the drug, will not be invited to take part. This will lead to smaller, more efficient, highly targeted early phase trials which can help to accelerate later phase development and bring marketed treatments to patients sooner. This means we can focus on the most effective medicines for patients, without patients missing out on alternative treatments.


About the Panel

Fabrice Chartier
Fabrice Chartier, CEO of Simbec-Orion, is a geneticist by background. After working in Academic Research at the CNRS in Paris for a couple of years, Fabrice joined the Pharmaceutical Industry in 1989, working for CROs and Pharma in France, the UK and the US. Fabrice co-founded Orion Clinical Services in 1997 to exclusively serve the Biotech sector working in oncology and rare disease. Orion Clinical Services and Simbec Research merged in 2014 to include clinical pharmacology services.

Joern Klinger
Joern Klinger, CEO of comes from a cognitive science background, after studying how children learn language and what happens in their brains when they do. After this, Joern completed a Masters in computational psychology at Oxford which focused on deep learning in the context of understanding the human brain. Joern acquired his PhD at the University of Texas at Austin where he combined working with children from Texas and an indigenous community in Mexico with computational modelling. Joern first got into drug development, when he met’s co-founder Marco, who had just completed his Post-Doc at the University of Cambridge with Chris Abell and Tom Blundell, the Astex founders. Marco had identified the inability to predict the efficacy of drugs in phase 2 trials as a major issue in drug development, which developed into thinking about how we could use machine learning/AI and biomedical data to overcome that.

About Simbec-Orion
Simbec-Orion is a responsive and agile full-service CRO with specialist expertise in clinical pharmacology, oncology, and rare diseases. Perfectly structured to support small to mid-size biotech companies, Simbec-Orion provides full-service clinical development services with a focus on tailormade and scalable solutions. Experts in early clinical development, Simbec-Orion utilises over 45 years of experience to develop bespoke strategies which support each client’s clinical and commercial objectives. Simbec-Orion is headquartered in the UK, with offices in Europe and the US.

About are the first to apply causal modelling in drug development at scale. At its core, causal modelling mimics prospective, randomized clinical trials in large retrospective data – the genomes and full phenotypes and medical histories of 3.3 million patients. This allows for fast predictions of clinical success with huge statistical power, and, at scale, enables the discovery and validation of every mechanism and disease affected by a given drug. In practice has enabled clients to secure funding, explain the biology of their drugs and improve the design of their clinical trials.

Back to Blog Archive