BACKGROUND
Machine Learning-Enabled Clinical Information Systems (ML-CIS) have the potential to drive healthcare delivery and research. The Fast Healthcare Interoperability Resources (FHIR) data standard is increasingly applied in developing these systems. However, methods for applying FHIR to ML-CIS are variable.
OBJECTIVE
This study evaluates and compares the functionalities, strengths, and weaknesses of existing systems and proposes guidelines for optimizing future work with ML-CIS.
METHODS
Embase, PubMed, and Web of Science were searched for articles describing machine-learning systems used for clinical data analytics or decision support in compliance with FHIR standards. Information regarding each system’s functionality, data sources, formats, security, performance, resource requirements, scalability, strengths, and limitations were compared across systems.
RESULTS
39 articles describing FHIR-based ML-CIS were divided into three categories according to their primary focus: Clinical Decision Support Systems (CDSSs) (n=18), data management and analytic platforms (n=10), or auxiliary modules and application programming interfaces (n=11). Model strengths included novel use of cloud systems, Bayesian networks, visualization strategies, and techniques for translating unstructured or free text data to FHIR frameworks. Most intelligent systems lacked electronic health record interoperability and externally validated evidence of clinical efficacy.
CONCLUSIONS
Shortcomings in current ML-CIS can be addressed by incorporating modular and interoperable data management, analytic platforms, secure inter-institutional data exchange, and application programming interfaces with adequate scalability to support both real-time and prospective clinical applications using electronic health record platforms with diverse implementations.
CLINICALTRIAL