Comparative visual analytics for assessing medical records with sequence embedding

Abstract

Machine learning for data-driven diagnosis has been actively studied in medicine to provide better healthcare. Supporting analysis of a patient cohort similar to a patient under treatment is a key task for clinicians to make decisions with high confidence. However, such analysis is not straightforward due to the characteristics of medical records: high dimensionality, irregularity in time, and sparsity. To address this challenge, we introduce a method for similarity calculation of medical records. Our method employs event and sequence embeddings. While we use an autoencoder for the event embedding, we apply its variant with the self-attention mechanism for the sequence embedding. Moreover, in order to better handle the irregularity of data, we enhance the self-attention mechanism with consideration of different time intervals. We have developed a visual analytics system to support comparative studies of patient records. To make a comparison of sequences with different lengths easier, our system incorporates a sequence alignment method. Through its interactive interface, the user can quickly identify patients of interest and conveniently review both the temporal and multivariate aspects of the patient records. We demonstrate the effectiveness of our design and system with case studies using a real-world dataset from the neonatal intensive care unit of UC Davis.

Explaining artificial intelligence with visual analytics in healthcare

“…Results from k-means and k-nearest neighbors are usually visualized in scatter plots with dots colored according to their cluster (e.g., Klemm et al, 2014;X. Ji, Shen, et al, 2019, Figure 2a), or in projection plots after dimension reduction (e.g., R. Guo et al, 2020;S.-Y. Ji et al, 2017).…”

“…Select interactions mark data items, either manually through brushing (e.g., S. Guo et al, 2018), lasso selection (e.g., Kwon et al, 2019;Raidou, Kuijf, et al, 2016;Figure 3e), clicking on a legend (R. Guo et al, 2020), or pinning (Dingen et al, 2019;Kakar et al, 2019); or automatically based on a chosen metric (e.g., Stolper et al, 2014). Selected data are typically colored prominently to easily focus on them.…”

VERONICA: Visual Analytics for Identifying Feature Groups in Disease Classification

“…It allows the user to apply different clustering techniques and displays the result using a 3-dimensional radial coordinate visualization. Likewise, Guo et al [74] developed another EHR-based VA system to assist clinical researchers in clustering similar patients, comparing values of medical features of patients, and finding similar time tamps among similar patients. To support the user in performing these tasks, the system integrates a dimensionality reduction technique and a density-based clustering method with multiple interactive linked views.…”

Interactive Dimensionality Reduction for Comparative Analysis

“…Also, when analyzing the general public's political opinions, political scientists may want to find unique characteristics in some political party's supporters when comparing them with others [27,38]. This type of comparative analysis is universal and can be found in numerous domains, such as researches in healthcare [35,51], biomedicine [61,96], and sociology [41,71].…”