Master of Science
Patterns of multimorbidity are complex and difficult to summarise using static visualization techniques like tables and charts. We present a visual analytics system with the goal of facilitating the process of making sense of data collected from patients with multimorbidity. The system reveals underlying patterns in the data visually and interactively, which enables users to easily assess both prevalence and correlation estimates of different chronic diseases among multimorbid patients with varying characteristics. To do so, the system uses count-based conditional probability, binary logistic regression, softmax regression and decision tree models to dynamically compute and visualize prevalence and correlation estimates for subsets of the data characterized by a user-selected set of pre-existing chronic conditions. The system also allows the user to examine the impact of adjusting for characteristics like age and gender on both the prevalence estimates and on correlations among diseases. By dynamically changing patient characteristics of interest and examining the resulting visualizations, the user can explore how prevalence and correlation estimates change with disease diagnosis and with other patient characteristics. This thesis is therefore a significant effort in understanding high-dimensional joint distributions of random variables and the created system can be used in any domain, such as economics, politics or social sciences, in which investigating the relationships between several random variables is vital to drawing the right conclusion.
Summary for Lay Audience
Multimorbidity, which is defined as the presence of multiple chronic diseases, is a growing health care problem especially for older adults. The traditional single-disease-centric approaches are no longer efficient to address the challenge of multimorbidity and a holistic framework is required to create effective prevention and treatment strategies. Therefore, we designed a visual analytics system for investigating multimorbidity patterns. Visual analytics is defined as the science of analytical reasoning facilitated by interactive visual interfaces. Unlike many studies in multimorbidity whose patterns are represented using simple tables and graphs, our system employs interactive visualizations. Through these visualizations, users can interact with different subsets of data and select a set of chronic diseases as well as several categories of age, gender and socioeconomic scores for investigation. To do so, the system uses statistical and machine learning algorithms including count-based conditional probability, binary logistic regression, softmax regression and decision tree to compute and visualize prevalence and correlation estimates of the diseases. Machine learning models are trained on the data to perform learning tasks by relying on patterns and inference created from the observations. Every time by every selection, the visualizations update the prevalence and correlation of diseases. The visual analytics system can be used in different areas of healthcare or other disciplines where investigating the associations between random variables with joint probability distributions is interesting.
Nouri, Maede Sadat, "A Visual Analytics System for Investigating Multimorbidity Using Supervised Machine Learning" (2020). Electronic Thesis and Dissertation Repository. 6964.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 4.0 License.