DigitalExposome: A dataset for wellbeing classification using environmental air quality and human physiological data

Area of Science:

• Environmental Health
• Urban Planning
• Digital Epidemiology

Background:

• Urban environments critically influence mental wellbeing, but research linking air quality, physiology, and mental health is limited.
• Integrating diverse environmental, physiological, and self-reported mental wellbeing data presents significant research challenges.
• The DigitalExposome dataset aims to bridge this gap by offering a comprehensive resource.

Purpose of the Study:

• To establish a novel dataset linking urban environmental exposures with physiological responses and self-reported mental wellbeing.
• To facilitate research into the complex interplay between air quality, human physiology, and mental health in urban settings.
• To provide insights for evidence-based urban planning and public health strategies.

Main Methods:

• Collected data from 40 participants (aged 18-50) in Nottingham, UK (Oct 2021-Sep 2022).
• Utilized a custom environmental monitoring system (Enviro-IoT), Empatica E4 wearable, and a smartphone app for data collection during urban walks.
• Recorded environmental variables (particulates, gases), physiological metrics (HR, HRV, EDA), and mental wellbeing labels.

Main Results:

• The DigitalExposome dataset comprises over 42,437 samples, integrating environmental, physiological, and mental wellbeing data.
• Processed data through resampling, interpolation, and normalization for robust analysis.
• The dataset enables exploration of relationships between air quality, physiological changes, and mental wellbeing.

Conclusions:

• This novel dataset provides a foundation for understanding the impact of urban environments on mental health.
• Offers valuable insights for developing healthier urban spaces and targeted public health interventions.
• Highlights the potential of digital tools and integrated data for advancing environmental health research.