Publication Type

Conference Paper

Version

acceptedVersion

Publication Date

5-2023

Abstract

Explainable artificial intelligence (AI) techniques are increasingly being explored to provide insights into why AI and machine learning (ML) models provide a certain outcome in various applications. However, there has been limited exploration of explainable AI techniques on time-series data, especially in the healthcare context. In this paper, we describe a threshold-based method that utilizes a weakly supervised model and a gradient-based explainable AI technique (i.e. saliency map) and explore its feasibility to identify salient frames of time-series data. Using the dataset from 15 post-stroke survivors performing three upper-limb exercises and labels on whether a compensatory motion is observed or not, we implemented a feed-forward neural network model and utilized gradients of each input on model outcomes to identify salient frames that involve compensatory motions. According to the evaluation using frame-level annotations, our approach achieved a recall of 0.96 and an F2-score of 0.91. Our results demonstrated the potential of a gradient-based explainable AI technique (e.g. saliency map) for time-series data, such as highlighting the frames of a video that therapists should focus on reviewing and reducing the efforts on frame-level labeling for model training.

Keywords

Time-Series Data, Explainable AI, Stroke Rehabilitation Exercises

Discipline

Artificial Intelligence and Robotics | Health Information Technology | Numerical Analysis and Scientific Computing

Publication

ICLR 2023 Workshop on Time Series Representation Learning for Health

Publisher

Taylor & Francis (Routledge): SSH Titles

City or Country

Virtual

Copyright Owner and License

Authors

Download

Share

COinS