Discovering Public Health Nurse-Specific Family Home Visiting Intervention Patterns Using Visualization Techniques

Area of Science:

• Big Data analytics
• Public Health Nursing
• Health Informatics

Background:

• Large datasets in public health nursing (PHN) contain hidden patterns impacting client outcomes.
• Understanding the mechanisms of risk reduction in high-risk populations is crucial for effective interventions.

Purpose of the Study:

• To employ Big Data visualization techniques for discovering and validating novel patterns in public health nurse (PHN)-client-risk-intervention-outcome relationships.
• To investigate the underlying mechanisms of risk reduction among high-risk mothers through data visualization and statistical analysis.

Main Methods:

• Utilized a three-step visualization process to analyze complex social intervention data.
• Applied pattern detection techniques including streamgraphs, heat maps, and parallel coordinates.
• Integrated descriptive and inferential statistics to analyze contextual factors and validate discovered patterns.

Main Results:

• Client risk significantly decreased following the provision of personally tailored PHN services.
• Identified clinically significant and unique patterns in PHN-client-risk-intervention-outcome relationships.
• Statistical validation confirmed that tailored PHN interventions lead to improved client outcomes.

Conclusions:

• Data exploration and visualization are essential for uncovering methods to enhance care quality and client outcomes in public health.
• Tailoring of PHN interventions is a key factor in achieving positive client health outcomes.
• Further research is recommended to explore additional influencing factors and apply these visualization methods to diverse datasets.