No abstract

The virus SARS-CoV2, which causes coronavirus disease (COVID-19) has become a pandemic and has spread to every inhabited continent. Given the increasing caseload, there is an urgent need to augment clinical skills in order to identify from among the many mild cases the few that will progress to critical illness. We present a first step towards building an artificial intelligence (AI) framework, with predictive analytics (PA) capabilities applied to real patient data, to provide rapid clinical decision-making support. COVID-19 has presented a pressing need as a) clinicians are still developing clinical acumen to this novel disease and b) resource limitations in a surging pandemic require difficult resource allocation decisions. The objectives of this research are: (1) to algorithmically identify the combinations of clinical characteristics of COVID-19 that predict outcomes, and (2) to develop a tool with AI capabilities that will predict patients at risk for more severe illness on initial presentation. The predictive models learn from historical data to help predict who will develop acute respiratory distress syndrome (ARDS), a severe outcome in COVID-19. Our results, based on data from two hospitals in Wenzhou, Zhejiang, China, identified features on initial presentation with COVID-19 that were most predictive of later development of ARDS. A mildly elevated alanine aminotransferase (ALT) (a liver enzyme), the presence of myalgias (body aches), and an elevated hemoglobin (red blood cells), in this order, are the clinical features, on presentation, that are the most predictive. The predictive models that learned from historical data of patients from these two hospitals achieved 70% to 80% accuracy in predicting severe cases.

[1] Knowledge of long-range transport and vertical distribution of Asian dust aerosols in the free troposphere is important for estimating their impact on climate. Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO), surface micropulse lidar (MPL), and standard surface measurements are used to directly observe the long-range transport and vertical distribution of Asian dust aerosols in the free troposphere during the Pacific Dust Experiment (PACDEX). The MPL measurements were made at the Loess Plateau (35.95°N, 104.1°E) near the major dust source regions of the Taklamakan and Gobi deserts. Dust events are more frequent in the Taklamakan, where floating dust dominates, while more intensive, less frequent dust storms are more common in the Gobi region. The vertical distribution of the CALIPSO backscattering/depolarization ratios indicate that nonspherically shaped dust aerosols floated from near the ground to an altitude of approximately 9 km around the source regions. This suggests the possible long-range transport of entrained dust aerosols via upper tropospheric westerly jets. A very distinct large depolarization layer was also identified between 8 and 10 km over eastern China and the western Pacific Ocean corresponding to dust aerosols transported from the Taklamakan and Gobi areas, as confirmed by back trajectory analyses. The combination of these dust sources results in a two-layer or multilayered dust structure over eastern China and the western Pacific Ocean.

IMPORTANCE Severe acute respiratory syndrome coronavirus 2 has caused a global outbreak of coronavirus disease 2019 (COVID-19). Severe acute respiratory syndrome coronavirus 2 binds angiotensin-converting enzyme 2 of the rennin-angiotensin system, resulting in hypokalemia. OBJECTIVE To investigate the prevalence, causes, and clinical implications of hypokalemia, including its possible association with treatment outcomes, among patients with COVID-19.