Decentralized Trials That Scale Globally Without Compliance Risks - with Emma Vitalini of Amgen

2026-04-07 · Source: The AI in Business Podcast · Field: Health & Wellbeing — Pharmaceuticals & Biotechnology, Medical Devices & Health Technology, Healthcare Systems & Policy · Depth: Intermediate, extended

Summary

Emma Vitalini, Head of Global Digital Health Technology Innovation at Amgen, discusses how AI and decentralized trial technologies are transforming patient recruitment, screening, and compliance in highly regulated healthcare environments. AI improves patient identification by analyzing unstructured genomic and clinical data, accelerating enrollment, and boosting diversity. Decentralized trials, supported by wearables and home assistants, enhance global accessibility, though challenges remain in linking patients to sites for sample collection. The discussion also covers how modular consent and API-based data querying enable hypothesis testing without extensive data movement, helping sponsors scale trials while maintaining regulatory trust and patient transparency. Vitalini emphasizes the need for flexibility, explainable AI, and a human-in-the-loop approach to manage risks and build trust in AI solutions.

Key takeaway

For Directors of AI/ML and Research Scientists in biotech, understanding how AI and decentralized trials can accelerate patient recruitment and ensure compliance is critical. You should prioritize starting with low-risk, high-value internal AI use cases to build organizational confidence and always partner with compliance, legal, and regulatory teams from the outset. Focus on solutions offering flexibility, explainability, and a "human in the loop" to mitigate risks and ensure patient trust, especially when considering vendor partnerships.

Key insights

AI and decentralized trials accelerate patient recruitment and enhance compliance in regulated healthcare.

Principles

• Prioritize patient empowerment and informed consent.
• Maintain human oversight in AI-driven health processes.
• Ensure flexibility and explainability in AI solutions.

Method

AI surfaces unstructured genomic/clinical data for patient identification. API-based querying enables hypothesis testing without large data transfers. Modular consent platforms manage compliance in global decentralized trials.

In practice

• Use AI to analyze genomic data for patient identification.
• Implement API-based data querying for hypothesis testing.
• Adopt modular consent platforms for global compliance.

Topics

• Decentralized Clinical Trials
• AI in Patient Recruitment
• Genomic Data Analysis
• Regulatory Compliance
• Explainable AI

Best for: Director of AI/ML, Research Scientist, AI Ethicist

Related on AIssential

• 🔬 Training Transformers to solve 95% failure rate of Cancer Trials — Ron Alfa & Daniel Bear, Noetik — Improving cancer drug success requires advanced AI models for precise patient selection based on multimodal biological data.
• Expanding our AI and Healthcare Portfolio — AI deployment in healthcare, driven by profit, poses significant risks to patient safety, worker dignity, and democratic oversight.
• Collaborating on a nationwide randomized study of AI in real-world virtual care — A nationwide randomized study will rigorously evaluate conversational AI in real-world virtual healthcare settings.
• Doctolib, AP-HP, and Roche launch startup programme to bridge healthtech–clinical gap — The Care Forward program accelerates healthtech deployment by integrating startups directly into clinical and regulatory ecosystems.
• FDA approval, fundraising, and the reality of building in healthcare according to BioticsAI founder — Navigating highly regulated sectors like healthcare demands rigor, early regulatory engagement, and a resilient company culture.
• TrialMatchAI: an end-to-end AI-powered clinical trial recommendation system to streamline patient-to-trial matching — TrialMatchAI automates clinical trial matching using LLMs and RAG for explainable, accurate patient eligibility.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The AI in Business Podcast.