Deep learning predicts prevalent and incident Parkinson's disease from UK Biobank fundus imaging.

Parkinson's disease is the world's fastest-growing neurological disorder. Research to elucidate the mechanisms of Parkinson's disease and automate diagnostics would greatly improve the treatment of patients with Parkinson's disease. Current diagnostic methods are expensive and have limited availability. Considering the insidious and preclinical onset and progression of the disease, a desirable screening should be diagnostically accurate even before the onset of symptoms to allow medical interventions. We highlight retinal fundus imaging, often termed a window to the brain, as a diagnostic screening modality for Parkinson's disease. We conducted a systematic evaluation of conventional machine learning and deep learning techniques to classify Parkinson's disease from UK Biobank fundus imaging. Our results suggest Parkinson's disease individuals can be differentiated from age and gender-matched healthy subjects with 68% accuracy. This accuracy is maintained when predicting either prevalent or incident Parkinson's disease. Explainability and trustworthiness are enhanced by visual attribution maps of localized biomarkers and quantified metrics of model robustness to data perturbations.

Costs of IQ Loss from Leaded Aviation Gasoline Emissions.

In the United States, general aviation piston-driven aircraft are now the largest source of lead emitted to the atmosphere. Elevated lead concentrations impair children's IQ and can lead to lower earnings potentials. This study is the first assessment of the nationwide annual costs of IQ losses from aircraft lead emissions. We develop a general aviation emissions inventory for the continental United States and model its impact on atmospheric concentrations using the community multi-scale air quality model (CMAQ). We use these concentrations to quantify the impacts of annual aviation lead emissions on the U.S. population using two methods: through static estimates of cohort-wide IQ deficits and through dynamic economy-wide effects using a computational general equilibrium model. We also examine the sensitivity of these damage estimates to different background lead concentrations, showing the impact of lead controls and regulations on marginal costs. We find that aircraft-attributable lead contributes to $1.06 billion 2006 USD ($0.01-$11.6) in annual damages from lifetime earnings reductions, and that dynamic economy-wide methods result in damage estimates that are 54% larger. Because the marginal costs of lead are dependent on background concentration, the costs of piston-driven aircraft lead emissions are expected to increase over time as regulations on other emissions sources are tightened.

Public health, climate, and economic impacts of desulfurizing jet fuel.

In jurisdictions including the US and the EU ground transportation and marine fuels have recently been required to contain lower concentrations of sulfur, which has resulted in reduced atmospheric SO(x) emissions. In contrast, the maximum sulfur content of aviation fuel has remained unchanged at 3000 ppm (although sulfur levels average 600 ppm in practice). We assess the costs and benefits of a potential ultra-low sulfur (15 ppm) jet fuel standard ("ULSJ"). We estimate that global implementation of ULSJ will cost US$1-4bn per year and prevent 900-4000 air quality-related premature mortalities per year. Radiative forcing associated with reduction in atmospheric sulfate, nitrate, and ammonium loading is estimated at +3.4 mW/m(2) (equivalent to about 1/10th of the warming due to CO(2) emissions from aviation) and ULSJ increases life cycle CO(2) emissions by approximately 2%. The public health benefits are dominated by the reduction in cruise SO(x) emissions, so a key uncertainty is the atmospheric modeling of vertical transport of pollution from cruise altitudes to the ground. Comparisons of modeled and measured vertical profiles of CO, PAN, O(3), and (7)Be indicate that this uncertainty is low relative to uncertainties regarding the value of statistical life and the toxicity of fine particulate matter.