面向患者分析与研究的可信AI/ML

Trustworthy AI/ML for PatientAnalytics and Research PM360 award-winning technology for AI-secure, privacy-firstmodeling with continuous monitoring and oversight Table of contents Responsible innovation in patient analytics and research2Heightened care in AI/ML2Adopting a principled, AI-secure approach to AI/ML2Shifting baseline for AI-Secure AI/ML3Bridging AI and data protection with federated modeling3Collection limitation and data minimization3Use limitation and purpose specification4Security safeguards4Accountability and oversight4Openness and transparency4Federated learning for AI/ML5Understanding the data journey for federated learning6Source ingestion: Pseudonymization andsegregation6Horizontal federated learning: Generating synthetic trends6Vertical federated learning: AI-secure AI/ML7Safe outputs7Beyond de-identification: Managing reconstruction risk8Leveraging synthetic trends for AI/ML8Managing reconstruction risk9AI governance and privacy operations (AI PrivOps): An integrated governance function10Continuous monitoring of AI PrivOPs metrics10Oversight without exposure11Human-in-the-loop for accountability11Ethics Board for patient analytics andresearch12Conclusion13Acknowledgment13 This paper outlines our approach to Artificial Intelligence (AI) and MachineLearning (ML) that withstands today’s threat landscape and serves as a blueprint Responsible innovation inpatient analytics and research Adopting a principled, AI-secure approach to AI/ML Envision a future where AI/ML models for health andwellness applications are proactively engineered withresilience and security at every layer. Sensitive dataremains protected, systemic vulnerabilities and risks are Life sciences are being transformed by ArtificialIntelligence (AI) and Machine Learning (ML). But withthat transformation comes a critical question: How dowe unlock value from sensitive health data without This white paper introduces a novel, principled approachthat puts AI security at the center of the systemarchitecture. Powered by the award-winning IQVIA Robust de-identification methods, which removeidentifying elements, can be used but the industry lackswidespread adoption of standardized practices. Thisabsence of fixed standards provides space to explore Synthetic data abstraction: Traditional modelsrely on raw data, increasing the surface areafor risk. Instead of relying on raw data, ourapproach transforms high-dimensional signals Heightened care in AI/ML This whitepaper introduces a novel privacy-first andAI-secure architecture for defensible AI developed byIQVIA. In response to AI and data protection concerns,the platform combines synthetic data abstractions, Federated learning architecture: Rather thanaggregating data into a central repository,our system employs a federated architecturein which source data are segregated within The solution enforces AI and data protection througharchitectural features such as input transformation, non-reversibility, and latent space modeling. Aligned withglobal standards such as ISO/IEC 42001 AI Management This regulatory evolution underscores the need forAI systems that are secure by design, aligned withorganizational objectives, and capable of adaptingto shifting oversight requirements. Patient analytics AI governance and privacy operations: Every step of the data flow is governed by strict policies and technically enforced oversight mechanismsthat are tracked and manage accordingly, includingcontinuous monitoring and auditable logs forend-to-end traceability. Segregated environments,role-based access controls, and robust audit trailsensure that data is used only for its intendedpurpose, in alignment with enterprise-levelgovernance and risk strategies. This approach is a response to today’s threat landscape— including risks such as AI model inversion, datareconstruction, linkage attacks, and the misuse of dataacross distributed systems — and serves as a blueprint IQVIA’s approach is designed to address those concernsdirectly. By using synthetic trends, federated modeling,and continuous monitoring, we minimize data exposurewhile enabling high-quality patient insights. An ethics Shifting baseline for AI-Secure AI/ML AI has transformed the landscape of health andwellness industries, enabling innovative solutionsthat enhance patient outcomes, streamline clinicalresearch, and improve patient engagement in health- Bridging AI and data protectionwith federated modeling IQVIA’s federated modeling approach translates abstractprinciples of AI-security and privacy protection intoconcrete system behaviors. The platform operationalizesthem through embedded architectural controls Across the globe, AI-driven applications are expectedto navigate an increasingly complex regulatoryenvironment. AI and data protection are convergingpriorities, with new and evolving laws, regulations, and Collection limitation and data minimization Through input transformation, IQVIA ensures that onlyessential att