Interview with Philippe Pinton from Ferring Pharmaceuticals

So good afternoon and a very warm welcome to Philippe Pinton from Ferring Pharmaceuticals. Thank you, Philippe, for joining us for today's interview with Oxford Global. Today we'll be discussing precision medicine's role in modern healthcare, highlighting scientific and clinical innovations, the integration of AI and machine learning, and the challenges of translating precision strategies into practice. 

 
Fantastic. So, we'll get started with the first question. Could you please start by sharing the central focus of your work in precision medicine? 

 
Thanks for the question. I would say that my work centers on developing and implementing targeted therapies that address individual patient viability, aiming to improve clinical outcomes and reduce unnecessary treatment. For example, my team and I have led the studies on individual dosing of follitropin delta that is recombinant FSH in reproductive medicine, demonstrating how tailored approaches can optimise efficacy and safety. This approach, I would say exemplifies the shift from one-size-fits-all medicine to interventions informed by patient specific data, what we call omics genetics, for example, and biomarkers. 

 
Fantastic, thank you. How do you define the role of precision medicine within modern healthcare and what gaps are you most motivated to address? 

 
That's another very good question. And I'm not sure that there is an easy and simple answer to that question. Also, it's probably because the definition of precision medicine is quite wide and depends on who you're talking about at that moment. I would say that for me precision medicine personalises care by leveraging - as I previously mentioned - multiple mix including genetics, biomarkers or clinical data. And I'm particularly motivated to address some gaps in access to data integration, but also the translation of discoveries into routine practice. 
 

We have I think in the past, in the very recent past, we have developed a strong effort to bring AI driven models, whatever it's generative AI or computational model into inflammatory bowel disease management with completely new pathways in the domain with the integration of AI and real-world data or digital tools. We were, or we are moving closer to a new healthcare model that is not only more precise, but also more proactive and inclusive - this can be in oncology, gastroenterology and many other therapeutic areas. The goal, whatever is the therapeutic area, the goal remains the same. 
It's to better understand the individual behind the condition. 

 
Speaking about precision medicine, I think there is also a kind of shift in the pharma industry model. 
The blockbuster area that has been built on mass-market drugs and long development cycles is giving way to a new vision. 
Precision medicine, a future where treatments are tailored to the individuals, where AI oesn't just accelerate R&D but redefines it and where data becomes the most valuable molecule in the laboratory, I would say or the company. This is more than just a digital upgrade - it's more of a reinvention of how we understand health and how we manage patients in the future. 
It's about moving from treating diseases to predicting them and then to adjusting the treatment to one patient. 
It's from generalised care to a deeply personalised intervention - from isolated breakthroughs to connected ecosystems. 

 
Thank you very much. And what have been some of the most significant scientific or clinical innovations to emerge from your work? 

 
You know, it's, it's always difficult for someone that is quite humble and modest to highlight what we have done that is emerging from, more specifically emerging and impacting health from all work. I would say that key innovations include the development of biomarkers driven therapy and the integration of digital health tools to optimise the patient selection and monitoring which have led to improved efficacy and safety profiles. We, for more than a few years now, our work on digital twins and computational models in IBD, but also in reproductive medicine are exemplifying how advanced analytics can predict treatment response and personalised care. This innovation, I would say are not only improving outcomes, but also enabling us to be more adaptive and more efficient in designing clinical trials and analysing the data we are collecting. 

 
Fantastic, thank you. And that quite nicely leads on to my next question, which is if you can please describe how your significant contributions to precision medicine have influenced other areas of research development or clinical practice. 

 
I would say that my contribution, or the contribution of my teams have fostered cross disciplinary collaboration, accelerating drug discovery and clinical development and did enable more adaptive clinical trial designs which benefit both research and patient's care. For instance, we have recently set up randomised control trials in reproductive medicine that have influenced protocols for ovarian stimulation and embryo selection. Either from a clinical perspective, but also from an imaging perspective -these advances have encouraged a culture of innovation and continuous learning across the organisation and beyond. 

 
Thank you. And how are you integrating artificial intelligence and machine learning into the clinical research and practice? 

 
I think we, I'm having a big smile here, but I think it's on a daily basis for us. We use AI and machine learning to analyse complex data sets, predict patient's responses and streamline clinical trial recruitment, but also enhancing both discovery or research efficiency and clinical decision making. I would also say that just to come back to IBD, we have recently published the use of AI for prognosis, shared decision-making, and the creation of what we call digital twins to support precision dosing and to run in silico trials. These technologies are also helping us to identify new therapeutic targets and optimise resource allocation. 

 
 
Fantastic, thank you very much. And what are some of the key challenges you've encountered in translating precision strategies into everyday clinical practice and how have you addressed them? 

 
I think, you know, data is driving this question on this process. Challenges include data interoperability, regulatory orders and clinician adoption. To overcome this aspect, we invest in robust digital infrastructure, foster education and collaborate with many stakeholders to align standards and best practice. We have demonstrated this in a few multi centre trials and integrating AI into this project. I think building trust and demonstrating value to clinician and patient is also essential for full implementation. So it's very much about conversation, providing the right or the fair, but the trusted information to these people. I think the big issue is the fact that we are using AI. You know, one common thing that is frequently coming up- it's about black box. People are not always understanding what we are doing with the data, how we manage them, digest them. We use mathematical equation and suddenly there is a result, and we have to believe what is the results. I think it's all about conversation and then be frankly open to what we do. 

 
Fantastic, thank you. And I think that leads us quite nicely on to discussing the collaboration aspect further. So, your work often involves collaboration across industry, academia and healthcare providers. Can you talk us through what models of partnership you think work best to accelerate precision medicine research and its application? 

 
Unfortunately I mean there is not one model that is that is always working. I think you have to be quite flexible and adaptive with the people you are working with. But I would say that what I would call a multi-stakeholder consortia that unites pharma, industry or biotech companies, academia and also healthcare providers are the most effective. I would also say a word about considering patients, because the voice of patients is important. So we need to find a way to integrate them within the discussion and the setup of the project. Because all these people, I would say they, they pull resources, expertise and data to drive innovation and its implementation. 

 
Most of our partnerships, one we have recently set up with a group called Image Analysis Group for AI-driven research in pregnancy is a good illustration of this collaborative approach. We have this group helping us with everything that is related to digesting the data using AI, but they also include the clinical centres, but also patients to help us to bring the most efficient analysis. But how to transform this into a digital tool for the patients and the practitioners. So such a model of multi-stakeholder consortia, facilitates knowledge sharing, accelerates translation and also helps align goals across the different sectors. 

 
Fantastic, thank you very much. And then changing steer a little bit - given the rising costs of the advanced therapies, how can precision medicine be implemented in a way that remains sustainable and equitable across different healthcare systems? 

 
I think again, I think for me it's a shift of the pharma industry. So, and also the impact that we do have on the healthcare professionals and the health authorities. And then after that- the political bodies. I think precision medicine can be made sustainable by focusing on value-based care, leveraging real world data and evidence and advocating for policies that ensure a equitable access to advanced therapies. Our own individualised dosing strategy that we have implemented for several of our treatments in reproductive medicine are designed to be both clinically effective but also resource efficient. I think it's essential to design scalable solutions that can be adapted to diverse healthcare settings. I mean, you know, you have the French system, you have the US system, you have the Japanese system. So I think it's also a way for us when we think about one solution, one therapeutic solution that it should be applicable for many healthcare settings. 

 
Absolutely. And from your perspective, how is precision medicine changing the way we care for patients on an individual level - in terms of diagnosis, the treatment choices or just the overall patient experience? 

 
Well, I think I would eventually say that it can be the panacea. But I'm not sure about this based on my few years of experience into R&D and clinical developments. But I would say that precision medicine transforms care by enabling more accurate diagnosis, tailored treatment plans, and improved patient engagement, ultimately also by enhancing outcomes and patient satisfaction, which is I think a critical aspect in the way we care about patients. Patients in our studies have benefited from therapies that are more likely to be effective and have fewer side effects. As shown again, it's what we have done in IBD and reproductive medicine. I think we also care about this. I think oncology and rare disease are probably the perfect therapeutic area to emphasise and amplify the benefit of precision medicine. I think this kind of approach empowers patients but also clinicians to make more informed decision. 
I think this aspect, the shared decision making is a key aspect of a successful treatment, whatever the pathologies we are considering. 

 
Fantastic, thank you. And then I've just got two forward-looking questions for you to finish off the interview. So looking ahead, what do you see as the most promising emerging technology or methodology in precision medicine that could really reshape clinical care? 

 
Well, I think I mentioned several times artificial intelligence and we have made also strong progresses in discovering, you know, multi elements, we go deeper into the knowledge of the body. So all these multi data, but in multi omics, I think I see multi or mix integration, but also the AI powered clinical decision support that would be probably the most transformative and also enabling deeper insight into disease mechanism and more precise intervention. It's something that we are very much using or caring about at Ferring on, you know, the work we are doing on computational models for several years. And also the creation, the elaboration of digital twins in many pathologies is, I think it's paving the way for this innovation to become standard practice. I think the use of multiomics and also artificial intelligence. I think these technologies will likely redefine how we approach both prevention and treatment in the near future. I hope that in the future, I mean, all these aspects on precision medicine will apply to prevention. I think we are much more on the treatment side than on the prevention and I would hope that precision medicine will help us to emphasise the benefit of preventing disease. 

 
Fantastic, thank you very much. What are your priorities for the next phase of your work - scientifically, clinically or in terms of system level implementation? 

 
Yeah. So I think the I would say today and tomorrow my priorities are - you know, it's hard to include, I would say I, yeah, my priorities include expanding the use of real world data not only into modelling exercise, but to leverage their value when we go to the healthcare authorities for discussion, but also for looking after the approval of a treatment. 
I think, you know, there is a big difference between the real world and what we do observe in clinical trials. So I think that it’s important to expand the use of real-world data and at the same time advancing digital health integration and scaling precision approaches to broader population for greater impact. 
I think I'm also very much committed to fostering a culture of innovation and continuous improvement within my team. 
I think it's everything we are doing today on ongoing clinical and translational research programmes. 
I think we need to translate what we do observe in discovery to a solution for the patients. 
So I think this translational aspect is key for the future. 
And also, as I mentioned, it's to build robust partnerships and investing into education. 
I think that would be key to drive the system level, the, you know, the system-level change, I would say. 

 
That's brilliant. Thank you very much. And with that, we will close today's interview. 

 
A very big thank you again to Philippe for your time today and for sharing really interesting insights into your work at Ferring Pharmaceuticals and for giving us insights into your perspectives in terms of looking ahead in terms of what's next to come. So, thank you very much again for your time and take care. 
 

Thank you to you.