Structured product labeling improves detection of drug-intolerance issues

Area of Science:

• Health Informatics
• Clinical Decision Support
• Drug Safety

Background:

• Computerized provider order entry (CPOE) systems rely on accurate drug knowledge for decision support.
• Drug intolerance (allergy) detection is critical for patient safety but faces challenges with current data standards.
• The Health Level 7/U.S. Food and Drug Administration Structured Product Labeling (SPL) standard offers a framework for drug information.

Purpose of the Study:

• To evaluate the effectiveness of the SPL standard for drug-intolerance decision support within CPOE systems.
• To compare an SPL-based method with an existing CPOE drug-intolerance detection system.
• To identify areas for improvement in SPL content and terminology for allergy management.

Main Methods:

• A comparison was made between the Regenstrief Institute CPOE system and an SPL-based method utilizing NDF-RT/MeSH knowledge sources.
• Both methods were applied to a large dataset of drug intolerance records, orders, and dispensing data (>50,000 patients, 30 years).
• Quantitative analysis included the number of detected issues, patients, distinct drugs, and intolerances, with qualitative analysis of discrepancies.

Main Results:

• The SPL-based approach detected four times more drug-intolerance issues than the existing system.
• Twice as many patients with drug intolerances were identified using the SPL-based method.
• Despite less than 70% of terms mapping to SPL, the new approach demonstrated superior sensitivity.

Conclusions:

• The SPL-based approach is more sensitive for detecting drug intolerances in CPOE systems.
• Accelerating the mapping of local dictionaries to SPL and enhancing SPL content coverage is recommended.
• Addressing specificity issues in drug intolerance decision support requires improvements in terminology and recording methods.