This is the authors' abstract. We don't add key points for this paper.
Artificial intelligence (AI), Internet of Things (IoT), and wearable technologies are transforming healthcare by enabling continuous collection and analysis of physiological information outside clinical environments. Multimodal wearable sensing can provide information for intelligent monitoring and remote healthcare applications. This study aimed to characterize the distribution and variability of physiological measurements from wearable sensor recordings and examine their potential integration within an AI- and IoT-enabled framework for remote physiological monitoring. A secondary analysis was conducted using the Wearable Exam Stress Dataset. Recordings obtained through an Empatica E4 wearable device were examined, including blood volume pulse, electrodermal activity, heart rate, inter-beat interval, skin temperature, and acceleration. Descriptive statistics and quartile-based measures were used to characterize the recorded signals. The sensor streams demonstrated distinct observation structures and distributional characteristics. Blood volume pulse generated the largest observation stream, whereas inter-beat interval contained event-based measurements. The physiological variables showed different levels of variability and distribution, demonstrating the heterogeneous nature of wearable measurements and the importance of considering signal characteristics during computational analysis. The findings provide an empirical foundation for the proposed incorporation of multimodal wearable physiological signals into AI- and IoT-enabled smart healthcare architectures. Further studies should evaluate these approaches using larger, representative populations and validated predictive models before clinical implementation.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Pradhan et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: