A Framework for Assurance of Medication Safety using Machine Learning

Abstract: Medication errors continue to be the leading cause of avoidable patient harm in hospitals. This paper sets out a framework to assure medication safety that combines machine learning and safety engineering methods. It uses safety analysis to proactively identify potential causes of medication error, based on expert opinion. As healthcare is now data rich, it is possible to augment safety analysis with machine learning to discover actual causes of medication error from the data, and to identify where they deviate from what was predicted in the safety analysis. Combining these two views has the potential to enable the risk of medication errors to be managed proactively and dynamically. We apply the framework to a case study involving thoracic surgery, e.g. oesophagectomy, where errors in giving beta-blockers can be critical to control atrial fibrillation. This case study combines a HAZOP-based safety analysis method known as SHARD with Bayesian network structure learning and process mining to produce the analysis results, showing the potential of the framework for ensuring patient safety, and for transforming the way that safety is managed in complex healthcare environments.

• The paper proposes a framework that integrates expert safety analysis with machine learning to accurately detect and mitigate medication errors.
• It employs a HAZOP-based SHARD method alongside Bayesian network learning and process mining to uncover hidden patterns in complex healthcare data.
• The case study on oesophagectomy highlights critical beta-blocker errors, demonstrating the framework’s potential to enhance patient safety in high-risk procedures.

The paper "A Framework for Assurance of Medication Safety using Machine Learning" addresses the critical issue of medication errors in hospitals, which are a leading source of avoidable patient harm. The authors propose a novel framework that integrates machine learning with safety engineering techniques to enhance medication safety.

At the core of the framework is the integration of safety analysis with machine learning methods. The safety analysis component utilizes expert opinion to proactively identify potential causes of medication errors. However, given the data-rich environment of modern healthcare, the paper emphasizes the importance of leveraging machine learning to analyze actual data and uncover real causes of these errors. This dual approach allows for identifying deviations between predicted and actual error causes, enabling a more dynamic and proactive risk management strategy.

The framework is applied to a case study focused on thoracic surgery, particularly oesophagectomy, highlighting critical errors in the administration of beta-blockers to control atrial fibrillation. This specific area is chosen due to the high stakes involved, where errors can lead to severe patient harm.

Key components of the framework include:

1. Safety Analysis Method: The paper utilizes a HAZOP-based method known as SHARD for systematic hazard analysis. SHARD helps identify potential risks and discrepancies in safety protocols through expert insights.
2. Machine Learning Techniques: The framework incorporates Bayesian network structure learning and process mining. These techniques are pivotal for analyzing complex healthcare data, identifying hidden patterns, and understanding the correlation between medical procedures and outcomes.

By combining these methods, the framework provides a comprehensive approach to enhancing medication safety. It demonstrates significant potential for transforming safety management in complex healthcare settings, moving from reactive responses to proactive risk management. This integration of human expertise with machine-driven insights marks a significant advancement in ensuring patient safety in hospitals.