Alessandra Oortwijn
Global Head Evidence Generation Alfasigma Spa
Dr. Alessandra Nunes Faria Oortwijn is a seasoned medical affairs leader and the current Global Head of Evidence Generation at Alfasigma S.p.a. With over a decade of clinical and academic experience and more than 20 years in the pharmaceutical industry, she brings a wealth of expertise across clinical development, scientific communication, medical education, launch excellence, KOL engagement and real-world evidence (RWE) research. Her work spans multiple therapeutic areas, with a strong focus on internal medicine, particularly endocrinology and immunology. Dr. Oortwijn is recognized for her strategic vision and commitment to advancing evidence-based healthcare on a global scale.
Seminars
- Benchmark how pharma are validating AI algorithms for structuring unstructured data (clinician notes, oncology staging, biomarkers) while ensuring reproducibility and regulatory alignment
- Learn practical strategies for human-in-the-loop review to balance automation with trust, avoiding “hallucinations” and privacy breaches in sensitive patient datasets
- See early examples of AI use cases accepted by regulators or HTA bodies and what lessons they hold for wider adoption
As AI models rapidly advance, their real-world applicability remains limited by fragmented data, regulatory uncertainty, and lack of clinical alignment. This roundtable will bring together clinicians, RWE experts, and data scientists to debate how AI can meaningfully support research questions today, including regulatory-relevant analyses, patient-centric endpoints, and expanded access data generation, while overcoming the challenges of standardisation, accuracy, and trust.
Join this roundtable to discuss:
- Fit-for-Purpose AI Models in RWE: When does AI truly add value, and how can clinicians and data scientists co-define research questions that models can reliably address?
- Regulatory Readiness & Trustworthiness: How should AI algorithms be validated for decision-making, given regulatory bodies’ limited comfort with model-based inferences?
- Data Fragmentation, Bias & Standardisation Gaps: How do we improve data quality and consistency, across wearables, biometrics, unstructured records, to ensure AIdriven insights are reproducible?
- Patient-Centric Evidence Generation with Advocacy Partners: What role can patient groups play in defining outcomes and providing meaningful data for AIenabled research, such as treatment satisfaction or preference studies?
