Wearanize+ : a multimodal dataset for evaluating wearable technologies in sleep research

Abstract Sleep research heavily relies on polysomnography recordings to assess sleep architecture. While effective, this method is time-consuming and requires substantial resources and labor. Modern wearable devices provide a promising alternative for sleep monitoring as they are easy to wear and maintain. However, these devices are constrained by a limited number of channels and comparatively lower data quality, which often leads to unreliable outcomes derived from partial readings. To address this, we propose using multiple wearable devices and combining their outputs to acquire reliable sleep data. However, the feasibility of this approach must be rigorously tested before being relied upon to supplant polysomnography in scientific studies. To facilitate this, we have curated a dataset with concurrent full polysomnography and wearable device recordings of overnight sleep sessions. This dataset, named Wearanize+, comprises data from 130 healthy (mostly young adult) participants, one night each, collected at home using three wearable devices: Zmax headband, Empatica E4 wristband, and ActivPAL leg patch, alongside polysomnography. It also includes questionnaires providing information on participants’ sleep, dreams, and overall health. This paper documents the setup, data collection, and preprocessing steps of the Wearanize+ project, serving as a guide to using the resulting dataset. Our objectives with the dataset include developing machine learning models that can derive polysomnography-grade sleep stages from wearable devices’ data and exploring alternative data modalities for sleep-stage scoring, particularly when EEG signals are excessively noisy. The Wearanize+ dataset is available via the Radboud Data Repository. This paper is part of the Consumer Sleep Technology Collection. Statement of Significance The Wearanize+ dataset is a multimodal dataset containing overnight sleep recordings from 130 healthy adults, combining concurrent polysomnography with three wearables (Zmax headband, Empatica E4 wristband, and ActivPAL leg patch) and sleep and health questionnaires. The synchronized dataset is suitable for device-specific validation, development of machine learning models to infer polysomnography (PSG)-grade sleep stages from wearable data, and systematic evaluation of alternative modalities and multidevice fusion. By supporting rigorous validation and scalable model development, the dataset can help bridge the gap between wearable data and gold-standard PSG for large-scale, clinical sleep research.