Development of a Validation and Inspection Tool for Armband-based Lifelog Data (VITAL) to Facilitate the Clinical Use of Wearable Data: A Prototype and Usability Evaluation

TL;DR

This paper presents VITAL, a prototype tool that integrates, visualizes, and manages wearable health data to support clinical decision-making, with positive usability feedback from clinicians.

Contribution

The study introduces VITAL, a novel pipeline for wearable data management that enhances clinical usability through integration, visualization, and quality control features.

Findings

VITAL successfully integrated data from multiple wearable devices.

Clinicians completed tasks with minimal errors using VITAL.

High user satisfaction and intent to adopt VITAL were reported.

Abstract

Background: The rise of mobile technology and health apps has increased the use of person-generated health data (PGHD). PGHD holds significant potential for clinical decision-making but remains challenging to manage. Objective: This study aimed to enhance the clinical utilization of wearable health data by developing the Validation and Inspection Tool for Armband-Based Lifelog Data (VITAL), a pipeline for data integration, visualization, and quality management, and evaluating its usability. Methods: The study followed a structured process of requirement gathering, tool implementation, and usability evaluation. Requirements were identified through input from four clinicians. Wearable health data from Samsung, Apple, Fitbit, and Xiaomi devices were integrated into a standardized dataframe at 10-minute intervals, focusing on biometrics, activity, and sleep. Features of VITAL support data integration, visualization, and quality management. Usability evaluation involved seven clinicians performing tasks, completing the Unified Theory of Acceptance and Use of Technology (UTAUT) survey, and participating in interviews to identify usability issues. Results: VITAL successfully integrated wearable data, thus enabling all participants to complete tasks with minimal errors without prior participant training. UTAUT survey results were positive, with average scores of 4.2 for performance expectancy, 3.96 for effort expectancy, and 4.14 for intention to use, indicating high user satisfaction and intent to adopt the tool. Conclusions: By enhancing wearable data integration, visualization, and quality management, the VITAL prototype shows significant potential for clinical application. Positive feedback highlights its promise, while emphasizing the need for further studies to confirm its real-world effectiveness.