Clinical trials – when digital becomes critical

What is the status of clinical studies today?
What would be the future of it? 

— Clinical trials are research studies designed to assess the safety and efficacy of medical interventions on human health outcomes. Trials’ design can vary based on what researchers are trying to find out. For example, treatment studies are designed to understand the effects of new medicines or devices, while observational trials are intended to understand patients living with a particular health condition. 

Studies are also categorised by phase. Phase I trials represent the first step of research that includes human participants and focuses on safety assessment, Phases II and III evaluate treatment efficacy, while Phase IV entails long-term safety monitoring post-approval. 

Until recently, all clinical trials were conducted in person. Volunteers who wished to participate had to travel to a research site, whether it was their local doctor’s office or a distant location across the country. These traditional clinical trials posed several challenges related to patient recruitment, resource limitations, intricate protocols, protracted timelines, accurate adverse events reporting, regulatory compliance, geographical diversity, patient inclusivity, and strong data management. Innovations, such as decentralised trials and digital technologies, strive to address these challenges. 

The future of clinical trials holds exciting advancements driven by technology and scientific innovation. The most impactful trends include digital transformation (digital endpoints, Patient-Reported Outcome Measures (PROMS), Patient-Reported Experience Measures (PREMS), Artificial Intelligence (AI), and real-world data), precision medicine, decentralisation (remote trials), predictive models, and a focus on ethics and transparency. These advancements aim to make trials faster, more efficient, and better aligned with patient needs. 

How can the life sciences industry adopt more patient-centric approaches in clinical studies, and what benefits do they offer in terms of engagement and outcomes? 

— Patient-centricity is a key driver of change in the healthcare sector. It means putting patients at the centre of the entire research and development process. The life sciences industry, which used to focus mainly on business-to-business relationships with healthcare providers, buyers, and regulators, is now shifting to direct-to-patient (DTP) models that allow more personalised solutions. This reflects the growing demand of patients, who are no longer passive recipients of medical interventions, but informed consumers who want to be involved in their own care. 

Clinical trials that adopt a patient-centric approach aim to align the research and development process with the needs, preferences, and values of patients. By engaging patients as partners in the design, operations and dissemination of clinical trials, those approaches can reduce the burden on patients and/or their relatives, improving the participation and retention of volunteers, as well as the relevance and generalisability of the results. They can also enhance the quality and efficiency of clinical trials by improving adherence and facilitating recruitment. Moreover, patient-centric approaches can build trust and transparency between researchers and patients, which can lead to better communication and collaboration. 

How do you foresee emerging technologies, such as artificial intelligence, impacting the design and execution of clinical studies in the life sciences industry? 

— AI has emerged as a transformative technology with tremendous potential in the field of clinical studies, particularly in patient identification and recruitment. Thus, solutions such as Natural Language Processing (NLP) can be leveraged to analyse electronic health records data, streamlining the identification of potential trial participants. This not only accelerates recruitment but also lightens the workload for trial teams. Additionally, machine learning has proven useful in detecting unusual patterns within health datasets, genomic, imaging data, and more. Thus, AI is likely to contribute to earlier diagnosis, particularly in the context of rare diseases which can potentially lead to improved patient outcomes and prognosis. Its applications in healthcare are endless, including the automation of several tasks, from administrative workflow to clinical documentation and patient monitoring. Recently, in silico trials have emerged and gained momentum. By leveraging computer simulations and modelling, virtual participant groups can be created to mirror real-world cohorts and predict outcomes. In silico trials can also help optimise trial design, by identifying optimal doses, duration, and targeted population for new interventions while assessing their potential adverse events or interactions. Despite several AI deployment challenges in the health sector (such as ethical concerns, data privacy, data security, possible biases, etc.), advances in computational techniques, like explainable AI (xAI) or attention models, have the potential to transform many aspects of healthcare, enabling a future that is more personalised, precise, and predictive. 

How could we effectively leverage the growing volume of patient-generated data and Real-Word Data (RWD) through digital tools to generate Real-World Evidence (RWE)? 

— Real-World Data is collected from sources outside of randomised controlled trials, such as electronic health records, claims databases, registries, and mobile/connected devices. RWE is the clinical evidence derived from the analysis and interpretation of RWD. RWE can provide valuable information about the effectiveness, safety, and value of medical interventions in real-world settings and populations, with a growing importance amongst stakeholders. 

Despite the expectations, RWD poses significant challenges and limitations, such as data quality, validity, reliability, representativeness, interoperability, privacy, and security. Several national and regional initiatives are working to create a common framework for RWD collection, management, and use. For example, the Food and Drug Administration (FDA) in the US supports using RWD for regulatory purposes. The European Medicines Agency (EMA) in Europe advocates for RWD in drug evaluation, and the European Health Data Space (EHDS) initiative aims to unify health data across EU member states. At a global level, organisations like the International Society for Pharmaceutical Engineering (ISPE) and the Observational Health Data Sciences and Informatics (OHDSI) promote RWD harmonisation worldwide. By establishing common standards, ensuring data quality, and fostering international collaboration, we can maximise the impact of RWD and AI in improving patient care, advancing medical research, and enabling informed decision-making. Moreover, the volume and complexity of such data pose additional challenges for their analysis and interpretation. AI-based solutions and blockchain could help overcome some of these hurdles and enable the generation of high-quality evidence to support regulatory and reimbursement decisions. 

What role do you see technology playing in optimising data ingestion throughout the entire patient healthcare professional journey? 

— As previously said, RWD, which is generated by various sources such as sensors, electronic health records, medical claims, registries, wearables and social media, has attracted a lot of attention and raised high expectations for modern decision-making. However, there is a gap between the hype and the reality of RWD, particularly related to the large volume and the heterogeneity of data, the lack of structure and standardisation, and the difficulty of interpretation which limits the usability. AI-based solutions can help overcoming some of these obsatcles. We also need to continue data standardisation and harmonisation efforts at every layer to ensure interoperability and comparability across different data sources and formats. Indeed, one of the key factors for improving the quality and impact of RWD is fostering interdisciplinary collaboration among all the relevant stakeholders, researchers, clinicians, regulators, payers, and patients — Real-World Data is collected from sources outside of randomised controlled trials, such as electronic health records, claims databases, registries, and mobile/connected devices. RWE is the clinical evidence derived from the analysis and interpretation of RWD. RWE can provide valuable information about the effectiveness, safety, and value of medical interventions in real-world settings and populations, with a growing importance amongst stakeholders.