Expert Interviews
The Future of Clinical Research with Artificial Intelligence – An Interview with Sofía Ruiz
Today we are pleased to share an insightful conversation with Sofía Ruiz, a Clinical Research professional from Argentina, who brings valuable perspectives on the role of artificial intelligence in clinical trials. With her experience in research operations, Sofía highlights both the opportunities and the challenges of integrating AI into different phases of study management.
ABRS: What potential applications of artificial intelligence do you consider most relevant in the start-up phase of a clinical trial?
Sofia Ruiz: Artificial intelligence is a tool capable of analyzing large sets of historical data to optimize the design and planning of clinical trials, reducing both time and costs. Research indicates that AI algorithms can shorten planning timelines by as much as 20–30%.
This technology can be applied in several areas during the start-up stage. One example is protocol review, as well as the preparation of informed consents and contracts, where certain inconsistencies or ambiguities may be detected.
ABRS: How do you think AI can contribute to optimizing site or patient selection and recruitment?
Sofia Ruiz: Through the use of machine learning models, AI can identify patterns in health data to select the most suitable patients and predict those at higher risk of dropping out. Studies have reported significant increases in recruitment rates and up to a 15% reduction in dropout rates thanks to personalized, AI-supported interventions.
ABRS: In your experience, what ethical and regulatory challenges should be considered when implementing AI solutions in clinical research?
Sofia Ruiz: One of the main challenges is ensuring the protection of participants’ rights, safety, and dignity, as required by regulations such as Argentina’s Resolution 6677/10 or the Declaration of Helsinki. AI must not replace the responsibility of the principal investigator nor the human oversight in decisions that directly impact patients.
Another critical aspect is the protection of sensitive data. Confidentiality, integrity, and availability of information must be safeguarded under strong regulatory frameworks such as GDPR in Europe, HIPAA in the United States, or Law 25.326 in Argentina.
Currently, AI highlights the need for dynamic ethical and legal frameworks to keep pace with its development. Organizations like PAHO already recommend policies that balance innovation with human rights, while the European Union has advanced with the first comprehensive AI Act, classifying applications by risk levels.
Finally, the most complex issue is legal liability in cases of harm caused by AI. Due to its autonomy and unpredictability, AI does not always fit traditional frameworks of civil liability or defective product responsibility. This calls for an interdisciplinary approach and the development of a unified definition of AI that enables clear and consistent jurisprudence.
ABRS: What examples do you know of AI tools that are already making a positive impact in the management or monitoring of clinical trials?
Sofia Ruiz: Medidata, a leading clinical research platform, uses AI to predict recruitment rates. In addition, a clinic in Chile has developed AI-based software for stroke patients: it helps determine whether a special treatment is needed beforehand. Previously, the same decision was made as in most countries—based only on symptoms—whereas AI now supports faster, more tailored decisions.
ABRS: How would you integrate AI with current processes to improve efficiency without compromising data quality or safety?
Sofia Ruiz: AI should be conceived as a complementary tool, not a replacement for human oversight. It can provide speed, efficiency, and advanced analytical capacity for specific tasks, but validation and clinical decision-making must remain the responsibility of the principal investigator and medical staff. In this way, technology serves as support that enhances management without compromising quality or data safety.
Proper training is essential. Clinical research teams must have the knowledge needed to understand both the capabilities and limitations of AI algorithms, avoiding blind dependence on tools that, while powerful, require expert supervision.
For successful integration, continuous monitoring and auditing are required. Only through constant oversight can efficiency gains be achieved without sacrificing data quality or participant protection.
As Sofía Ruiz reminds us, artificial intelligence is not here to replace human judgment, but to enhance it. By combining technology with the expertise of clinical research professionals, the industry can achieve faster, more efficient, and ethically sound studies.
We sincerely thank Sofía Ruiz for sharing her valuable insights and experiences. At ABRS, we share this vision and remain committed to supporting innovation in clinical research while upholding the highest standards of quality, safety, and regulatory compliance.