Evaluation of a Machine Learning-Based Decision Support Intervention for Inpatient Falls

Area of Science:

• Healthcare Informatics
• Nursing Science
• Clinical Decision Support

Background:

• Inpatient falls are a significant cause of adverse events, with one-third of falls resulting in injuries.
• Current guidelines recommend multifaceted risk assessment and interventions, but traditional implementation yields mixed results.
• There is a need for improved strategies to effectively implement fall prevention measures in hospital settings.

Purpose of the Study:

• To propose and evaluate a novel systemic and clinical decision support approach for fall prevention.
• To leverage machine learning techniques to enhance the implementation of nursing preventive activities.
• To investigate the impact of this approach on patient outcomes related to falls.

Main Methods:

• Development of a machine learning-based clinical decision support system.
• Integration of the system into nursing workflows for fall risk assessment and intervention.
• Evaluation of the system's effectiveness in improving the implementation of preventive activities and patient outcomes.

Main Results:

• The machine learning approach demonstrated potential in optimizing the delivery of preventive nursing care.
• The study indicated a positive influence on outcome changes related to fall prevention strategies.
• The proposed system offers a promising alternative to traditional methods for managing inpatient falls.

Conclusions:

• A machine learning-driven clinical decision support system can enhance the effectiveness of inpatient fall prevention strategies.
• This approach offers a systematic way to improve nursing process implementation and achieve better patient outcomes.
• Further research and implementation are warranted to validate and scale this innovative fall prevention model.