ABSTRACT
Concentrations of ambient particulate matter (PM) depend on various factors including emissions of primary pollutants, meteorology and chemical transformations. New Delhi, India is the most polluted megacity in the world and routinely experiences extreme pollution episodes. As part of the Delhi Aerosol Supersite study, we measured online continuous PM1 (particulate matter of size less than 1µm) concentrations and composition for over five years starting January 2017, using an Aerosol Chemical Speciation Monitor (ACSM). Here, we describe the development and application of machine learning models using random forest regression to estimate the concentrations, composition, sources and dynamics of PM in Delhi. These models estimate PM1 species concentrations based on meteorological parameters including ambient temperature, relative humidity, planetary boundary layer height, wind speed, wind direction, precipitation, agricultural burning fire counts, solar radiation and cloud cover. We used hour of day, day of week and month of year as proxies for time-dependent emissions (e.g., emissions from traffic during rush hours). We demonstrate the applicability of these models to capture temporal variability of the PM1 species, to understand the influence of individual factors via sensitivity analyses, and to separate impacts of the COVID-19 lockdowns and associated activity restrictions from impacts of other factors. Our models provide new insights into the factors influencing ambient PM1 in New Delhi, India, demonstrating the power of machine learning models in atmospheric science applications. [ABSTRACT FROM AUTHOR] Copyright of Aerosol Science & Technology is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
ABSTRACT
BACKGROUND: Despite recognition of the neurologic and psychiatric complications associated with SARS-CoV-2 infection, the relationship between coronavirus disease 19 (COVID-19) severity on hospital admission and delirium in hospitalized patients is poorly understood. This study sought to measure the association between COVID-19 severity and presence of delirium in both intensive care unit (ICU) and acute care patients by leveraging an existing hospital-wide systematic delirium screening protocol. The secondary analyses included measuring the association between age and presence of delirium, as well as the association between delirium and safety attendant use, restraint use, discharge home, and length of stay. METHODS: In this single center retrospective cohort study, we obtained electronic medical record (EMR) data using the institutional Epic Clarity database to identify all adults diagnosed with COVID-19 and hospitalized for at least 48-h from February 1-July 15, 2020. COVID-19 severity was classified into four groups. These EMR data include twice-daily delirium screenings of all patients using the Nursing Delirium Screening Scale (non-ICU) or CAM-ICU (ICU) per existing hospital-wide protocols. RESULTS: A total of 99 patients were diagnosed with COVID-19, of whom 44 patients required ICU care and 17 met criteria for severe disease within 24-h of admission. Forty-three patients (43%) met criteria for delirium at any point in their hospitalization. Of patients with delirium, 24 (56%) were 65 years old or younger. After adjustment, patients meeting criteria for the two highest COVID-19 severity groups within 24-h of admission had 7.2 times the odds of having delirium compared to those in the lowest category [adjusted odds ratio (aOR) 7.2; 95% confidence interval (CI) 1.9, 27.4; P = 0.003]. Patients > 65 years old had increased odds of delirium compared to those < 45 years old (aOR 8.7; 95% CI 2.2, 33.5; P = 0.003). Delirium was associated with increased odds of safety attendant use (aOR 4.5; 95% CI 1.0, 20.7; P = 0.050), decreased odds of discharge home (aOR 0.2; 95% CI 0.06, 0.6; P = 0.005), and increased length of stay (aOR 7.5; 95% CI 2.0, 13; P = 0.008). CONCLUSIONS: While delirium is common in hospitalized patients of all ages with COVID-19, it is especially common in those with severe disease on hospital admission and those who are older. Patients with COVID-19 and delirium, compared to COVID-19 without delirium, are more likely to require safety attendants during hospitalization, less likely to be discharged home, and have a longer length of stay. Individuals with COVID-19, including younger patients, represent an important population to target for delirium screening and management as delirium is associated with important differences in both clinical care and disposition.