Improving Adherence to Clinical Pathways Through Natural Language Processing on Electronic Medical Records

Area of Science:

• Health Informatics
• Artificial Intelligence in Medicine
• Clinical Decision Support Systems

Background:

• Clinical decision support systems (CDSS) can enhance healthcare delivery.
• Implementing real-time AI-driven recommendations is crucial for improving clinical practices.
• The Spanish National Health System sought innovative solutions to reduce clinical variability.

Purpose of the Study:

• To develop and implement a pioneering real-time clinical decision support system (CDSS).
• To leverage natural language processing (NLP) and artificial intelligence (AI) for healthcare recommendations.
• To evaluate the impact of the CDSS on adherence rates and clinical variability within the Spanish National Health System.

Main Methods:

• Development of a CDSS integrating NLP and AI techniques.
• Real-time notification system for primary care physicians.
• Implementation within the Spanish National Health System.

Main Results:

• Achieved improvements in adherence rates in 8 out of 18 practices.
• Received highly positive feedback from healthcare providers, noting the system's speed, utility, and non-intrusive nature.
• Demonstrated a reduction in clinical variability.

Conclusions:

• The developed CDSS is a practical and effective tool for enhancing healthcare processes.
• NLP and AI techniques are valuable for evaluating and improving healthcare.
• This represents the first real-time CDSS implementation in the Spanish National Health System.