Practical Challenges of Progressive Data Science in Healthcare

TL;DR

This paper discusses the practical challenges and insights gained from applying progressive data science to healthcare data visualization projects, highlighting issues like data inconsistency and deployment complexities.

Contribution

It provides a reflective analysis of three healthcare visualization projects using progressive data science, identifying key challenges and practical considerations.

Findings

Inconsistent data collection practices pose significant challenges.

Adapting visualizations to varying data completeness is complex.

Design modifications are necessary for real-world deployment.

Abstract

The healthcare system collects extensive data, encompassing patient administrative information, clinical measurements, and home-monitored health metrics. To support informed decision-making in patient care and treatment management, it is essential to review and analyze these diverse data sources. Data visualization is a promising solution to navigate healthcare datasets, uncover hidden patterns, and derive actionable insights. However, the process of creating interactive data visualization can be rather challenging due to the size and complexity of these datasets. Progressive data science offers a potential solution, enabling interaction with intermediate results during data exploration. In this paper, we reflect on our experiences with three health data visualization projects employing a progressive data science approach. We explore the practical implications and challenges faced at various stages, including data selection, pre-processing, data mining, transformation, and interpretation and evaluation. We highlighted unique challenges and opportunities for three projects, including visualizing surgical outcomes, tracking patient bed transfers, and integrating patient-generated data visualizations into the healthcare setting. We identified the following challenges: inconsistent data collection practices, the complexity of adapting to varying data completeness levels, and the need to modify designs for real-world deployment. Our findings underscore the need for careful consideration of using a progressive data science approach when designing visualizations for healthcare settings.