Automated Medication Error Risk Assessment System (Auto-MERAS).

Area of Science:

• Health Informatics
• Patient Safety
• Clinical Decision Support

Background:

• Medication errors pose a significant threat to patient safety.
• Existing systems often require manual data entry, increasing nurse workload.
• Predictive models for medication errors are crucial for proactive intervention.

Purpose of the Study:

• To develop and validate the Automated Medical Error Risk Assessment System (Auto-MERAS).
• To integrate Auto-MERAS into electronic health record (EHR) systems.
• To assess the system's ability to predict medication errors, considering situational and environmental factors.

Main Methods:

• Development of the Auto-MERAS algorithm.
• Integration of Auto-MERAS within an existing EHR system.
• Validation of predictive accuracy using area under the receiver operating characteristic curves (AUC).

Main Results:

• Auto-MERAS demonstrated high predictive validity for medication errors (AUC > 0.80).
• The system successfully predicted risks sensitive to situational and environmental factors.
• No additional data entry was required from nurses for risk prediction.

Conclusions:

• Auto-MERAS is a validated tool for predicting medication errors within EHR systems.
• The system enhances patient safety by identifying at-risk situations proactively.
• Integration of such systems can improve clinical decision-making without increasing healthcare professional workload.