I hope you enjoyed the first part of this “Demystifying AI in Drug Development” series. In this final part, I will explore 5 more use cases as well as discuss what we at IDEA Pharma do to create the most value for our clients. Without further ado, the first use case of this article is:
1. Resource Allocation
“Which development path options within liquid tumour oncology present the greatest amount of value with an acceptable amount of risk, in accordance with current and future competitor timelines in each therapeutic indication of interest?”
NLP can help major pharmaceutical developers allocate resources more efficiently by identifying the most promising areas of research, thereby reducing the risk of investing in dead-end projects. By analysing the literature on various diseases and treatments, NLP can identify areas of high potential for new drug development and help major pharmaceutical developers prioritize their research and development efforts in line with a developer’s strategic priorities and “North Star”. Again, I would caution against the idea of AI making these decisions as a standalone tool. AI can help structure the different variables surrounding a decision (such as current and future competitors, changes in standard of care or treatment workflows, etc), but at the end of the day, the stakes in healthcare are too high financially and sociologically. It seems highly unlikely an executive leadership team would leave a $200 million Phase 3 development decision solely with an AI algorithm, just as it seems unlikely the FDA would allow 1000 patients to be enrolled in a clinical trial (at the opportunity cost of receiving the best standard of care option). This brings us to our next use case:
2. Environmental Landscaping, Mergers, and Acquisitions
“Which external scientific breakthroughs can be brought in-house for clinical and commercial development in alignment with our portfolio strategy?”
NLP can also help major pharmaceutical developers keep up with the rapidly evolving landscape of the pharmaceutical industry by providing information about the latest advancements in medical and scientific research. This information can help major pharmaceutical developers identify merger and acquisition targets from smaller drug developers and biotech firms, thereby expanding their product portfolios and increasing their competitiveness in the market. However, much like the previous use case, it seems highly unlikely (and borderline illogical) that a multi-billion acquisition and development option would be left to a single algorithm to decide.
3. Clinical Trial Design
“What analogues exist for accelerated paths to approval across both therapeutic indications of focus and molecular class?”
NLP can also be used to analyse the literature on clinical trial design to identify best practices and to optimize the design of future trials. This can help to improve the chances of success of future trials, reduce the time and cost required to bring a new drug to market, and ensure that patients receive the best possible treatment. In the hands of a skilled cross-functional team, this information elucidates several “sub-value-adds” for further exploration: are we looking for “better” patient recruitment? Or are we looking for “optimal” data collection? What about ways to “improve” protocol adherence? Is the end goal “higher” chances of “success”, or “faster” time to market? If you’re a small Biotech, is it about “faster” time to “next clinical trial phase” to unlock the next round of funding? Again, many potential sub-use cases beneath the blanket of “clinical trial design”, of which it is up to human decision makers to decide the “best” course of action (with better data at hand, obviously). Related to this use case in particular is another potential rabbit hole of opportunity:
4. Safety Monitoring
“What real-world-monitoring advances can be applied to our development portfolio to increase the size and scale of our data advantage to optimise health outcomes?”
NLP can be used to monitor the safety of marketed drugs by analysing the literature on adverse events and side effects. This information can be used to identify emerging safety concerns and to support regulatory decisions related to the continued use of the drug. But, what exactly are we “monitoring”? Are we looking for possible biomarkers to track adverse events? Or are looking to scour databases to inform interventions to reduce the impact of adverse events (or, to improve “efficacy”)? What is the end goal? Better trial retention? Treatment adherence? AI can help accelerate the search for information, but, really, the true value is unlocked when insights are generated and wielded by the human experts that understand the corresponding situation and use case. Which brings us to our final use case:
5. Collaboration and Transparency
“What preclinical and clinical imperatives are most urgent and valuable to align on prior to initiating Phase 2 proof-of-concept trials?”
This is the ultimate end game, and where we at IDEA Pharma see huge leverage points for creating additional value using AI tools in concert with human expertise to drive better decisioning. NLP can increase collaboration and transparency between different departments within major pharmaceutical developers. By providing a centralized platform for accessing and analysing scientific literature, NLP can help facilitate communication and collaboration between departments such as research and development, clinical trials, regulatory affairs, and safety monitoring. However, it is up to the PEOPLE that make up organizations to decide what “value” really means.
As you can see, these are just a minute fraction of the use cases we at IDEA Pharma have identified (and explored in painstaking detail and granularity) where NLP and AI can help advance the study and development of medicine. In respect of this, incorporating advances in technological progress aligns with our mission at IDEA Pharma:
“To create path-to-market options that no-one else could, and inspire biopharma to develop and successfully launch more great medicines.”
Despite this clarity of mission, the complexity underlying our “North Star” as an organization is rife with the scientific, clinical, regulatory, and commercial complexity of today’s drug development landscape and environment. To help create the most value for our clients through our partnerships with the pharmaceutical industry and drug developers, we utilize a variety of machine learning and artificial intelligence tools in combination with our deep bench of industry, clinical, and commercial experts to help more great medicines reach more patients.
As we canvas the landscape of healthcare, life sciences, and technology, it’s amazing to see the amount of circular conversations dancing around specific use cases for AI as a tool for pharmaceutical firms, with many experts espousing the view of AI as a panacea to the challenges drug developer and patients face in tackling the growing complexity of disease.
At IDEA Pharma, we believe in the “art of innovation” – only through the combination of design thinking, industry expertise, collaboration, and clinical decision science can we help clients achieve their overarching mission and business imperatives. While there are complex scientific components to drug development (such as molecular biology, computational chemistry, and analytical econometrics), ultimately, healthcare is an art – the beautiful dance between healthcare practitioners and patients, leveraging the tools available to help each patient reach their goals.
In conclusion, NLP offers a wealth of opportunities for major pharmaceutical developers to enable their teams to improve the drug discovery process and bring new treatments to market faster and more efficiently. By synthesizing publicly available medical and scientific research, NLP can provide valuable insights to support their drug discovery efforts and help ensure the safety and efficacy of their products. At IDEA Pharma, we are constantly on the lookout for collaboration opportunities with the best and brightest across industries so we can learn from the best to deliver the most value to our clients, in alignment with our own “North Star”:
“To create path-to-market options that no-one else could, and inspire biopharma to develop and successfully launch more great medicines.”
At IDEA Pharma, we’d love to hear what you think to help us in our journey to bring more great medicines to more patients.
Jonathon Lee is a Consultant and Global Medical Strategist with IDEA Pharma, operating out of London, UK. He is a US-trained Doctor of Physical Therapy, Board-Certified Orthopedic Clinical Specialist, Fellow of the American Academy of Orthopedic Manual Physical Therapists, and an alumnus of the University of Oxford’s Saïd Business School. Connect with IDEA Pharma and Jonathon on LinkedIn to talk innovation in drug development, healthcare, and beyond.
