V‐Awake: A Visual Analytics Approach for Correcting Sleep Predictions from Deep Learning Models

Abstract

The usage of deep learning models for tagging input data has increased over the past years because of their accuracy and high‐performance. A successful application is to score sleep stages. In this scenario, models are trained to predict the sleep stages of individuals. Although their predictive accuracy is high, there are still mis classifications that prevent doctors from properly diagnosing sleep‐related disorders. This paper presents a system that allows users to explore the output of deep learning models in a real‐life scenario to spot and analyze faulty predictions. These can be corrected by users to generate a sequence of sleep stages to be examined by doctors. Our approach addresses a real‐life scenario with absence of ground truth. It differs from others in that our goal is not to improve the model itself, but to correct the predictions it provides. We demonstrate that our approach is effective in identifying faulty predictions and helping users to fix them in the proposed use case.

A Survey of Human‐Centered Evaluations in Human‐Centered Machine Learning

“… Papers that provide use cases or usage scenarios developed by the authors without the inclusion of expert feedback, or case studies that do not consider human factors pertaining to the expert (e.g., [GWGvW19; KTC∗19; LJLH19; PLM∗17; SJS∗18; WPB∗20]). This was the most frequent reason for exclusion. Papers that describe applications that do not allow user interaction with the model beyond filtering of data points (i.e., purely exploratory systems in which the user can neither influence the model behavior during the analysis session nor optimize towards a specific model output) (e.g., [JVW20; LLT∗20; XXL∗20]). Papers not describing system evaluations but research agendas (e.g., [AVW∗18]), or workshops (e.g., [AW18; BCP∗19]). Papers that provide quantitative evaluations of results not generated by participants in a study setting (e.g., [BZL∗18; YDP19]). …”

The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations

“…The goal of model‐specific techniques is to explain the inner workings of a particular ML model. However, some tools combine both specific models and model‐agnostic algorithms, such as Chae et al [CGR*17], Roesch and Günther [RG19], Pezzotti et al [PHV*18], and others [CWGW19, KKB19, MCMT14].…”

ExplainExplore: Visual Exploration of Machine Learning Explanations

“…However, most approaches only use data analysis and only use machine learning for recommendations [11,22,25]. Decision support using machine learning techniques to provide explanations is a recent development, and as such, the amount of work is scarce [9,12,50].…”

“…These visual analytics systems often tailor for specific algorithms. Neural networks have received the most attention with systems visualizing or projecting neuron weights [27,35,38,45,60] or highlighting important regions contributing to a prediction [9,24,40]. A few model-agnostic such as Prospector [29] and What-if tool [59] exist, and mainly focus on hypothesis testing.…”

“…Many systems focus only on global [1,2,11,25,34,35,38,39,41,45,46] or local [9,12,29] explanation, but few combine the two [23,27,30]. These perspectives are complementary [23] and hence are both supported in our system.…”