Designing a Visual Analytics Tool to Support Data Analysis Tasks of Digital Mental Health Interventions: Case Study
View abstract on PubMed
Summary
This summary is machine-generated.This study introduces a new model and visual analytics tool for analyzing digital health intervention data, improving insights into user engagement and intervention effectiveness for researchers.
Area Of Science
- Digital Health
- Health Informatics
- Human-Computer Interaction
Background
- Digital health interventions (DHIs) generate valuable user data for improving health management.
- Current DHI data analysis practices are fragmented, hindering comprehensive understanding.
- Data-driven insights are crucial for post-deployment intervention improvements.
Purpose Of The Study
- Propose an analysis task model for holistic DHI data analysis.
- Develop an interactive visual analytics tool based on the model.
- Evaluate the model's suitability and the tool's task support for DHI research.
Main Methods
- Constructed a DHI data analysis model with user characteristics, engagement, and effectiveness components.
- Designed Maum Health Analytics, a visual analytics tool prototype, mapping features to the model.
- Conducted a user study with 15 researchers using real-world DHI data and interviews.
Main Results
- Researchers found the analysis model and tool positively supported identifying users needing care and informing recommendations.
- The tool facilitated analysis of intervention effectiveness relative to user characteristics and engagement.
- Participants highlighted the tool's role in simplifying analytics and improving multidisciplinary communication.
Conclusions
- The proposed model and visual analytics tool offer a holistic approach to DHI data analysis.
- The tool simplifies complex analytic tasks and enhances collaboration among researchers.
- This integrated approach meets growing DHI data analysis needs and boosts efficiency.

