Article by Natalia de la Figuera – Co-founder and COO of GENESIS Biomed

• Digital transformation and artificial intelligence are redefining the traditional model of clinical trials..

• Today’s clinical trials enable more effective recruitment.

• The incorporation of omics and epigenetic data in clinical trials allows progress towards more personalised medicine.

• The main challenges are interoperability and data governance.

Clinical trials are an essential element for biomedical innovation, but their execution continues to face significant structural challenges: long development times, difficulties in patient recruitment, high operational costs and increasing complexity in multicentre and international studies. In this context, digitalisation and artificial intelligence (AI) have become strategic levers to transform clinical research and adapt it to an increasingly personalised medicine-oriented environment.

The adoption of digital technologies is enabling progress towards more flexible and efficient clinical trial models. The use of electronic medical records, remote monitoring and the support of digital devices has reduced the administrative burden and improved data quality and traceability. Hybrid trials (combining traditional face-to-face and remote elements) have therefore gained prominence by facilitating patient participation and reducing reliance on face-to-face visits.

Today, artificial intelligence has demonstrated a tangible impact, especially in one of the most critical phases of clinical trials: patient recruitment. Studies and pilots have shown that the use of AI algorithms applied to real clinical data can reduce recruitment times by 30-50%. For example, automated identification of eligible patients from electronic medical records has enabled a shift from manual screening processes, which could take months, to systems that generate potential cohorts in a matter of weeks or even days. This approach is particularly relevant for rare diseases or studies with complex inclusion criteria, where recruitment is often the main limiting factor. Beyond volume, AI also helps to improve the quality of recruitment, identifying patients who more precisely fit the study profile and reducing drop-out rates. This translates into more efficient trials, with less need for over-recruitment and a higher probability of success.

Another key element in the evolution of clinical trials is the incorporation of omics and epigenetic data. The integration of genomic, transcriptomic, proteomic or metabolomic information allows for more precise stratification of patients and the design of studies aligned with the principles of personalised medicine. In this context, omics data are not only used for patient selection, but also for the definition of more sensitive endpoints, the identification of predictive biomarkers and the monitoring of treatment response. This approach is particularly relevant in oncology, rare diseases and advanced therapies, where biological heterogeneity critically conditions therapeutic efficacy. In addition, the availability of epigenetic data opens new opportunities to understand the interplay between genetics, environment and clinical response, allowing for more adaptive and dynamic trial designs. Combining these layers of information with AI accelerates analysis and facilitates the generation of more robust and actionable clinical evidence.

Alongside these developments, other relevant trends are emerging in clinical trials. These include the use of synthetic control arms based on real-world data, adaptive trials, which allow the study design to be modified based on intermediate outcomes, as well as trials with greater patient engagement through digital tools that facilitate the collection of quality of life data and patient-reported outcomes (PROs).

However, despite these advances, significant barriers remain. One of the main ones is interoperability between healthcare systems, especially in multi-centre trials involving hospitals in different countries. The heterogeneity of data formats, clinical terminologies and levels of digitisation hinders the integration and joint analysis of information. In addition, regulatory and organisational differences between health systems slow down the implementation of international studies and limit the use of existing clinical data. Overcoming these barriers requires common standards and clear governance to enable secure and compliant data sharing.

In short, digital transformation and artificial intelligence are redefining the traditional clinical trial model, accelerating recruitment and enabling more personalised medicine. The future of clinical trials will be marked by the convergence of digitalisation, artificial intelligence and advanced data, including omics and epigenetic information. This new paradigm will make it possible to accelerate the development of therapies, improve the efficiency of clinical research and move towards increasingly personalised medicine, provided that the challenges of interoperability, governance and equity in access to innovation are decisively addressed.