JMIR Publications

ABSTRACT

Background:

Wearable technologies have become increasingly prominent in the field of healthcare. However, the utilization of intricate machine learning and deep learning algorithms often leads to the development of "black box" models, which lack transparency and comprehensibility for both medical professionals and end-users. In this context, the integration of explainable artificial intelligence (XAI) has emerged as a crucial solution. By providing insight into the inner workings of complex algorithms, XAI aims to foster trust and empower stakeholders to use wearable technologies responsibly.

Objective:

This paper aims to review the recent literature, exploring the application of explainability in wearables. By examining how XAI can enhance the interpretability of generated data and models, this review seeks to shed light on the possibilities that arise at the intersection of wearable technologies and XAI.

Methods:

For this review, we examined recent literature published between 2018 and 2022, focusing on the role of explainability in wearable technologies. We analyzed 25 research papers to gain insights into the current state of explainability in wearables.

Results:

Our findings reveal that wrist-worn wearables, such as Fitbit and Empatica e4, are prevalent in healthcare applications. However, there is a limited emphasis on making the data generated by these devices explainable. Among various explainability methods, post-hoc approaches, with SHapley Additive exPlanation (SHAP) as a prominent choice due to its adaptability, stand out. The outputs of explainability methods are commonly presented visually, often in the form of graphs or user-friendly reports. Nevertheless, our review highlights a limitation in user evaluation and underscores the importance of involving users in the development process.

Conclusions:

The integration of XAI in wearable healthcare technologies is crucial to address the issue of "black box" models. While wrist-worn wearables are widespread, there is a notable gap in making the data they generate explainable. Post-hoc methods like SHAP have gained traction for their adaptability in explaining complex algorithms visually. However, user evaluation remains an area where improvement is needed, and involving users in the development process can contribute to more transparent and reliable AI models in healthcare applications. Further research in this area is essential to enhance the transparency and trustworthiness of AI models used in wearable healthcare technology.