Sensor data-driven analysis for identification of causal relationships between exposure to air pollution and respiratory rate in asthmatics

TL;DR

This study employs a data-driven causal analysis method on wearable sensor data to establish short-term exposure-response relationships between air pollution and respiratory rate in asthmatic adolescents, revealing personalized effects.

Contribution

It introduces a novel application of the PCMCI+ algorithm to identify causal links between PM2.5 exposure and respiratory rate using high-resolution wearable sensor data in a real-world setting.

Findings

Personalized short-term causal relationships identified

Causal effects observed up to 8 hours delay

Demonstrated feasibility of causal discovery in epidemiology

Abstract

According to the Lancet report on the global burden of disease published in October 2020, air pollution is among the five highest risk factors for global health, reducing life expectancy on average by 20 months. This paper describes a data-driven method for establishing causal relationships within and between two multivariate time series data streams derived from wearable sensors: personal exposure to airborne particulate matter of aerodynamic sizes less than 2.5um (PM2.5) gathered from the Airspeck monitor worn on the person and continuous respiratory rate (breaths per minute) measured by the Respeck monitor worn as a plaster on the chest. Results are presented for a cohort of 113 asthmatic adolescents using the PCMCI+ algorithm to learn the short-term causal relationships between lags of \pm exposure and respiratory rate. We consider causal effects up to a maximum delay of 8 hours, using data at both a 1 minute and 15 minute resolution in different experiments. For the first time a personalised exposure-response relationship between PM2.5 exposure and respiratory rate has been demonstrated to exist for short-term effects in asthmatic adolescents during their everyday lives. Our results lead to recommendations for work on specific open problems in causal discovery, to increase the feasibility of this approach for similar epidemiology studies in the future.