PhenoFlow: A Human-LLM Driven Visual Analytics System for Exploring Large and Complex Stroke Datasets

Acute stroke demands prompt diagnosis and treatment to achieve optimal patient outcomes. However, the intricate and irregular nature of clinical data associated with acute stroke, particularly blood pressure (BP) measurements, presents substantial obstacles to effective visual analytics and decision-making. Through a year-long collaboration with experienced neurologists, we developed PhenoFlow, a visual analytics system that leverages the collaboration between human and Large Language Models (LLMs) to analyze the extensive and complex data of acute ischemic stroke patients. PhenoFlow pioneers an innovative workflow, where the LLM serves as a data wrangler while neurologists explore and supervise the output using visualizations and natural language interactions. This approach enables neurologists to focus more on decision-making with reduced cognitive load. To protect sensitive patient information, PhenoFlow only utilizes metadata to make inferences and synthesize executable codes, without accessing raw patient data. This ensures that the results are both reproducible and interpretable while maintaining patient privacy. The system incorporates a slice-and-wrap design that employs temporal folding to create an overlaid circular visualization. Combined with a linear bar graph, this design aids in exploring meaningful patterns within irregularly measured BP data. Through case studies, PhenoFlow has demonstrated its capability to support iterative analysis of extensive clinical datasets, reducing cognitive load and enabling neurologists to make well-informed decisions. Grounded in long-term collaboration with domain experts, our research demonstrates the potential of utilizing LLMs to tackle current challenges in data-driven clinical decision-making for acute ischemic stroke patients.

Extracting Human Attention through Crowdsourced Patch Labeling

In image classification, a significant problem arises from bias in the datasets. When it contains only specific types of images, the classifier begins to rely on shortcuts - simplistic and erroneous rules for decision-making. This leads to high performance on the training dataset but inferior results on new, varied images, as the classifier's generalization capability is reduced. For example, if the images labeled as mustache consist solely of male figures, the model may inadvertently learn to classify images by gender rather than the presence of a mustache. One approach to mitigate such biases is to direct the model's attention toward the target object's location, usually marked using bounding boxes or polygons for annotation. However, collecting such annotations requires substantial time and human effort. Therefore, we propose a novel patch-labeling method that integrates AI assistance with crowdsourcing to capture human attention from images, which can be a viable solution for mitigating bias. Our method consists of two steps. First, we extract the approximate location of a target using a pre-trained saliency detection model supplemented by human verification for accuracy. Then, we determine the human-attentive area in the image by iteratively dividing the image into smaller patches and employing crowdsourcing to ascertain whether each patch can be classified as the target object. We demonstrated the effectiveness of our method in mitigating bias through improved classification accuracy and the refined focus of the model. Also, crowdsourced experiments validate that our method collects human annotation up to 3.4 times faster than annotating object locations with polygons, significantly reducing the need for human resources. We conclude the paper by discussing the advantages of our method in a crowdsourcing context, mainly focusing on aspects of human errors and accessibility.

CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models

Large language models (LLMs) have facilitated significant strides in generating conversational agents, enabling seamless, contextually relevant dialogues across diverse topics. However, the existing LLM-driven conversational agents have fixed personalities and functionalities, limiting their adaptability to individual user needs. Creating personalized agent personas with distinct expertise or traits can address this issue. Nonetheless, we lack knowledge of how people customize and interact with agent personas. In this research, we investigated how users customize agent personas and their impact on interaction quality, diversity, and dynamics. To this end, we developed CloChat, an interface supporting easy and accurate customization of agent personas in LLMs. We conducted a study comparing how participants interact with CloChat and ChatGPT. The results indicate that participants formed emotional bonds with the customized agents, engaged in more dynamic dialogues, and showed interest in sustaining interactions. These findings contribute to design implications for future systems with conversational agents using LLMs.

CLAMS: A Cluster Ambiguity Measure for Estimating Perceptual Variability in Visual Clustering

Visual clustering is a common perceptual task in scatterplots that supports diverse analytics tasks (e.g., cluster identification). However, even with the same scatterplot, the ways of perceiving clusters (i.e., conducting visual clustering) can differ due to the differences among individuals and ambiguous cluster boundaries. Although such perceptual variability casts doubt on the reliability of data analysis based on visual clustering, we lack a systematic way to efficiently assess this variability. In this research, we study perceptual variability in conducting visual clustering, which we call Cluster Ambiguity. To this end, we introduce CLAMS, a data-driven visual quality measure for automatically predicting cluster ambiguity in monochrome scatterplots. We first conduct a qualitative study to identify key factors that affect the visual separation of clusters (e.g., proximity or size difference between clusters). Based on study findings, we deploy a regression module that estimates the human-judged separability of two clusters. Then, CLAMS predicts cluster ambiguity by analyzing the aggregated results of all pairwise separability between clusters that are generated by the module. CLAMS outperforms widely-used clustering techniques in predicting ground truth cluster ambiguity. Meanwhile, CLAMS exhibits performance on par with human annotators. We conclude our work by presenting two applications for optimizing and benchmarking data mining techniques using CLAMS. The interactive demo of CLAMS is available at clusterambiguity.dev.

ZADU: A Python Library for Evaluating the Reliability of Dimensionality Reduction Embeddings

Dimensionality reduction (DR) techniques inherently distort the original structure of input high-dimensional data, producing imperfect low-dimensional embeddings. Diverse distortion measures have thus been proposed to evaluate the reliability of DR embeddings. However, implementing and executing distortion measures in practice has so far been time-consuming and tedious. To address this issue, we present ZADU, a Python library that provides distortion measures. ZADU is not only easy to install and execute but also enables comprehensive evaluation of DR embeddings through three key features. First, the library covers a wide range of distortion measures. Second, it automatically optimizes the execution of distortion measures, substantially reducing the running time required to execute multiple measures. Last, the library informs how individual points contribute to the overall distortions, facilitating the detailed analysis of DR embeddings. By simulating a real-world scenario of optimizing DR embeddings, we verify that our optimization scheme substantially reduces the time required to execute distortion measures. Finally, as an application of ZADU, we present another library called ZADUVis that allows users to easily create distortion visualizations that depict the extent to which each region of an embedding suffers from distortions.

Classes are not Clusters: Improving Label-based Evaluation of Dimensionality Reduction

A common way to evaluate the reliability of dimensionality reduction (DR) embeddings is to quantify how well labeled classes form compact, mutually separated clusters in the embeddings. This approach is based on the assumption that the classes stay as clear clusters in the original high-dimensional space. However, in reality, this assumption can be violated; a single class can be fragmented into multiple separated clusters, and multiple classes can be merged into a single cluster. We thus cannot always assure the credibility of the evaluation using class labels. In this paper, we introduce two novel quality measures -- Label-Trustworthiness and Label-Continuity (Label-T&C) -- advancing the process of DR evaluation based on class labels. Instead of assuming that classes are well-clustered in the original space, Label-T&C work by (1) estimating the extent to which classes form clusters in the original and embedded spaces and (2) evaluating the difference between the two. A quantitative evaluation showed that Label-T&C outperform widely used DR evaluation measures (e.g., Trustworthiness and Continuity, Kullback-Leibler divergence) in terms of the accuracy in assessing how well DR embeddings preserve the cluster structure, and are also scalable. Moreover, we present case studies demonstrating that Label-T&C can be successfully used for revealing the intrinsic characteristics of DR techniques and their hyperparameters.

Sanity Check for External Clustering Validation Benchmarks using Internal Validation Measures

We address the lack of reliability in benchmarking clustering techniques based on labeled datasets. A standard scheme in external clustering validation is to use class labels as ground truth clusters, based on the assumption that each class forms a single, clearly separated cluster. However, as such cluster-label matching (CLM) assumption often breaks, the lack of conducting a sanity check for the CLM of benchmark datasets casts doubt on the validity of external validations. Still, evaluating the degree of CLM is challenging. For example, internal clustering validation measures can be used to quantify CLM within the same dataset to evaluate its different clusterings but are not designed to compare clusterings of different datasets. In this work, we propose a principled way to generate between-dataset internal measures that enable the comparison of CLM across datasets. We first determine four axioms for between-dataset internal measures, complementing Ackerman and Ben-David's within-dataset axioms. We then propose processes to generalize internal measures to fulfill these new axioms, and use them to extend the widely used Calinski-Harabasz index for between-dataset CLM evaluation. Through quantitative experiments, we (1) verify the validity and necessity of the generalization processes and (2) show that the proposed between-dataset Calinski-Harabasz index accurately evaluates CLM across datasets. Finally, we demonstrate the importance of evaluating CLM of benchmark datasets before conducting external validation.

Uniform Manifold Approximation with Two-phase Optimization

We introduce Uniform Manifold Approximation with Two-phase Optimization (UMATO), a dimensionality reduction (DR) technique that improves UMAP to capture the global structure of high-dimensional data more accurately. In UMATO, optimization is divided into two phases so that the resulting embeddings can depict the global structure reliably while preserving the local structure with sufficient accuracy. As the first phase, hub points are identified and projected to construct a skeletal layout for the global structure. In the second phase, the remaining points are added to the embedding preserving the regional characteristics of local areas. Through quantitative experiments, we found that UMATO (1) outperformed widely used DR techniques in preserving the global structure while (2) producing competitive accuracy in representing the local structure. We also verified that UMATO is preferable in terms of robustness over diverse initialization methods, number of epochs, and subsampling techniques.

Distortion-Aware Brushing for Interactive Cluster Analysis in Multidimensional Projections

Brushing is an everyday interaction in 2D scatterplots, which allows users to select and filter data points within a continuous, enclosed region and conduct further analysis on the points. However, such conventional brushing cannot be directly applied to Multidimensional Projections (MDP), as they hardly escape from False and Missing Neighbors distortions that make the relative positions of the points unreliable. To alleviate this problem, we introduce Distortion-aware brushing, a novel brushing technique for MDP. While users perform brushing, Distortion-aware brushing resolves distortions around currently brushed points by dynamically relocating points in the projection; the points whose data are close to the brushed data in the multidimensional (MD) space go near the corresponding brushed points in the projection, and the opposites move away. Hence, users can overcome distortions and readily extract out clustered data in the MD space using the technique. We demonstrate the effectiveness and applicability of Distortion-aware brushing through usage scenarios with two datasets. Finally, by conducting user studies with 30 participants, we verified that Distortion-aware brushing significantly outperforms previous brushing techniques in precisely separating clusters in the MD space, and works robustly regardless of the types or the amount of distortions in MDP.

Measuring and Explaining the Inter-Cluster Reliability of Multidimensional Projections

We propose Steadiness and Cohesiveness, two novel metrics to measure the inter-cluster reliability of multidimensional projection (MDP), specifically how well the inter-cluster structures are preserved between the original high-dimensional space and the low-dimensional projection space. Measuring inter-cluster reliability is crucial as it directly affects how well inter-cluster tasks (e.g., identifying cluster relationships in the original space from a projected view) can be conducted; however, despite the importance of inter-cluster tasks, we found that previous metrics, such as Trustworthiness and Continuity, fail to measure inter-cluster reliability. Our metrics consider two aspects of the inter-cluster reliability: Steadiness measures the extent to which clusters in the projected space form clusters in the original space, and Cohesiveness measures the opposite. They extract random clusters with arbitrary shapes and positions in one space and evaluate how much the clusters are stretched or dispersed in the other space. Furthermore, our metrics can quantify pointwise distortions, allowing for the visualization of inter-cluster reliability in a projection, which we call a reliability map. Through quantitative experiments, we verify that our metrics precisely capture the distortions that harm inter-cluster reliability while previous metrics have difficulty capturing the distortions. A case study also demonstrates that our metrics and the reliability map 1) support users in selecting the proper projection techniques or hyperparameters and 2) prevent misinterpretation while performing inter-cluster tasks, thus allow an adequate identification of inter-cluster structure.