Data, dialogue, and design: patient and public involvement and engagement for natural language processing with real-world cancer data.

Abstract

Introduction: This study describes the process and outcomes of a Patient and Public Involvement and Engagement (PPIE) event designed to incorporate patient perspectives into the application of Natural Language Processing (NLP) for analyzing unstructured free-text cancer medical notes. The analysis of routinely collected data aims to provide evidence to support clinical decision making in patient groups that are often under-represented in conventional clinical trials, highlighting the critical role of PPIE in responsibly implementing AI within healthcare. The study focuses on ensuring that NLP research reflects patient-centered and clinically relevant considerations.

Methods: The event involved 13 participants: nine cancer survivors and caregivers, acting as contributors, and four researchers. These participants engaged in focus group discussions on three key topics: data use, consent preferences, and communication strategies for this type of research.

Results: Some key findings included that two-thirds (6/9) of contributors preferred a national opt-out consent model for data use, while one-third (3/9) favored project-specific consent. They offered perspectives on data use, including how it is processed and stored. They also highlighted the importance of clear, accessible information about the research process to build trust and facilitate informed decision-making.