AI-enhanced health information exchange systems: a systematic review of implementation challenges and opportunities
Abstract
This systematic review evaluates the integration of Artificial Intelligence (AI) into Health Information Exchange (HIE) systems to improve data utilisation, patient outcomes, and healthcare delivery efficiency. Through a comprehensive analysis of major academic databases from 2015 to 2024, 72 peer-reviewed papers were selected following rigorous screening processes, including duplicate removal, title/abstract screening, and full-text evaluation against predefined criteria. The analysis examined AI implementation across directed exchange, query-based exchange, and consumer-mediated exchange systems. Results demonstrate AI significantly enhances HIE functionality through improved data standardisation, error detection, and system integration. Key benefits include enhanced predictive capabilities for patient outcomes, optimised resource utilisation, and effective automated processing of unstructured clinical data. Critical solutions identified include federated learning techniques to preserve privacy, explainable AI models to support clinical adoption, and robust bias-detection frameworks to ensure equitable outcomes. Future opportunities encompass integrating diverse data sources, exploring federated learning approaches, balancing data utility with privacy concerns, and developing transparent AI models to increase clinical acceptance. The study emphasises ongoing data standardisation efforts and ethical considerations in AI deployment, particularly for real-time, context-aware…
How strong is the evidence?
Evidence Hub reads this as a systematic review. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.