Improving information retrieval from electronic health records using dynamic and multi-collaborative filtering.

Area of Science:

• Health Informatics
• Information Retrieval
• Artificial Intelligence

Background:

• Physicians experience significant information overload due to the vast amount of data in electronic health records (EHRs).
• Inefficiencies in accessing relevant patient information within health information technology systems hinder clinical decision-making.
• Current systems often struggle to prioritize critical information during patient encounters.

Purpose of the Study:

• To introduce a novel hybrid dynamic and multi-collaborative filtering method for enhanced information retrieval from EHRs.
• To improve the efficiency and accuracy of recommending relevant patient information to physicians during clinical visits.
• To address the challenge of information overload in healthcare settings.

Main Methods:

• Developed a hybrid dynamic and multi-collaborative filtering approach.
• Modeled information search dynamics using a Markov model.
• Incorporated collaborative filtering principles to prioritize information based on physician, patient, and item similarities.

Main Results:

• The proposed method achieved 46.7% accuracy in top-5 recommendations and 24.7% in top-1 recommendations.
• Demonstrated a 22.3% improvement over the conventional Markov model for top-1 recommendations.
• Validated using EHR data from the Indiana Network for Patient Care.

Conclusions:

• The hybrid dynamic and multi-collaborative filtering method effectively improves information retrieval from EHRs.
• This approach offers a promising solution to mitigate physician information overload and enhance clinical workflow.
• The findings suggest potential for significant improvements in clinical decision support systems.