A Visual Analytics Approach to Building Logistic Regression Models and its Application to Health Records
This work addresses the problem of enabling domain experts, such as in healthcare, to create interpretable machine learning models, though it appears incremental as it builds on existing visual analytics and regression techniques.
The paper tackles the challenge of building and evaluating logistic regression models in high-dimensional datasets by introducing UCReg, a user-centered visual analytics approach that allows users to select relevant attributes based on correlation panoramas, and demonstrates its effectiveness on Covid-19 and other health records data.
Multidimensional data analysis has become increasingly important in many fields, mainly due to current vast data availability and the increasing demand to extract knowledge from it. In most applications, the role of the final user is crucial to build proper machine learning models and to explain the patterns found in data. In this paper, we present an open unified approach for generating, evaluating, and applying regression models in high-dimensional data sets within a user-guided process. The approach is based on exposing a broad correlation panorama for attributes, by which the user can select relevant attributes to build and evaluate prediction models for one or more contexts. We name the approach UCReg (User-Centered Regression). We demonstrate effectiveness and efficiency of UCReg through the application of our framework to the analysis of Covid-19 and other synthetic and real health records data.