A picture tells a thousand…exposures: Opportunities and challenges of deep learning image analyses in exposure science and environmental epidemiology. (January 2019)

• Record Type: Journal Article
• Authors: Weichenthal, Scott; Hatzopoulou, Marianne; Brauer, Michael
• Is Part Of: Environment international. Volume 122(2019)
• Page Start: 3
• Page End: 10
• Publication Date: 2019-01
• Subjects: Environmental protection -- Periodicals; Environmental health -- Periodicals; Environmental monitoring -- Periodicals; Environmental Monitoring -- Periodicals; Environnement -- Protection -- Périodiques; Hygiène du milieu -- Périodiques; Environnement -- Surveillance -- Périodiques; Environmental health; Environmental monitoring; Environmental protection; Periodicals; 333.705
• DOI: 10.1016/j.envint.2018.11.042
• Languages: English
• ISSNs: 0160-4120

Abstract

Abstract: Background: Artificial intelligence (AI) is revolutionizing our world, with applications ranging from medicine to engineering. Objectives: Here we discuss the promise, challenges, and probable data sources needed to apply AI in the fields of exposure science and environmental health. In particular, we focus on the use of deep convolutional neural networks to estimate environmental exposures using images and other complementary data sources such as cell phone mobility and social media information. Discussion: Characterizing the health impacts of multiple spatially-correlated exposures remains a challenge in environmental epidemiology. A shift toward integrated measures that simultaneously capture multiple aspects of the urban built environment could improve efficiency and provide important insights into how our collective environments influence population health. The widespread adoption of AI in exposure science is on the frontier. This will likely result in new ways of understanding environmental impacts on health and may allow for analyses to be efficiently scaled for broad coverage. Image-based convolutional neural networks may also offer a cost-effective means of estimating local environmental exposures in low and middle-income countries where monitoring and surveillance infrastructure is limited. However, suitable databases must first be assembled to train and evaluate these models and these novel approaches should be complemented with traditional exposure metrics. Conclusions: The promise of deep learning in environmental health is great and will complement existing measurements for data-rich settings and could enhance the resolution and accuracy of estimates in data poor scenarios. Interdisciplinary partnerships will be needed to fully realize this potential. Highlights: Characterizing the health impacts of multiple correlated exposures remains a challenge Deep learning image analysis may offer an alternative means of estimating multiple exposures Large databases of paired image-exposure data must be developed to support this initiative Methods are now available to integrate multiple data streams to support exposure science and environmental epidemiology High quality training data remains a priority