Participatory-informed preference optimization (PiPrO): A reinforcement learning simulation study
Open Access
- 19 March 2026
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS Digital Health
- Vol. 5 (3) , e0001294
Abstract
Artificial intelligence (AI) has transformative potential in public health, but its impact is limited by models that implicitly prioritize a single stakeholder perspective and do not make explicit and tunable trade-offs between community and clinician endorsement. To address this gap, we introduce Participatory-informed Preference Optimization (PiPrO), a large language model embedding-based calibration framework that generates a single clinical outcome prediction while explicitly accounting for differences between community and physician interpretations of the same scenario. PiPrO takes as input two embeddings derived from a large language model representing a community-facing context and a physician-facing context. It then applies a shared lightweight feedforward predictor to produce per-stakeholder scores which are then mixed using a single global mixing weight (alpha). Alpha controls how strongly the final prediction reflects the community versus physician responses and is learned using a policy-gradient update driven by an abundant but noisy community text and a sparse and biased physician text. PiPrO reliably learned stable alpha values and a consistent reward signal. Alpha shifts systematically toward physician weighting as community feedback becomes noisier and shifts toward community weighting as physician feedback becomes more biased. Our results suggest PiPrO’s potential to produce more transparent, and context-sensitive AI-driven healthcare recommendations. Future research should validate this approach using real-world community inputs to ensure generalizability and practical impact.Keywords
Funding Information
- National Human Genome Research Institute (5RM1HG010461)
This publication has 43 references indexed in Scilit:
- An intuitionistic fuzzy automated negotiation model for personalized and efficient shared decision-makingScientific Reports, 2025
- Deep deterministic policy gradient-based automatic negotiation framework for shared decision-makingScientific Reports, 2025
- A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisationnpj Digital Medicine, 2025
- A review of Explainable Artificial Intelligence in healthcareComputers and Electrical Engineering, 2024
- Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for MedicineNew England Journal of Medicine, 2023
- Community-based participatory research application of an artificial intelligence-enhanced electrocardiogram for cardiovascular disease screening: A FAITH! Trial ancillary studyAmerican Journal of Preventive Cardiology, 2022
- Empowering local communities using artificial intelligencePatterns, 2022
- External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized PatientsJAMA Internal Medicine, 2021
- Community Health Workers Improve Linkage to Hypertension Care in Western KenyaJACC, 2019
- Tackling health inequalities and social exclusion through partnership and community engagement? A reality check for policy and practice aspirations from a Social Inclusion Partnership in ScotlandCritical Public Health, 2010